2565 files changed, 76029 insertions, 54100 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index b8a4ff365582..a3308a220f86 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1518,6 +1518,14 @@ config STRICT_MODULE_RWX
 config ARCH_HAS_PHYS_TO_DMA
 	bool
 
+config ARCH_HAS_CPU_RESCTRL
+	bool
+	help
+	  An architecture selects this option to indicate that the necessary
+	  hooks are provided to support the common memory system usage
+	  monitoring and control interfaces provided by the 'resctrl'
+	  filesystem (see RESCTRL_FS).
+
 config HAVE_ARCH_COMPILER_H
 	bool
 	help
@@ -1584,6 +1592,10 @@ config HAVE_SPARSE_SYSCALL_NR
 	  entries at 4000, 5000 and 6000 locations. This option turns on syscall
 	  related optimizations for a given architecture.
 
+config ARCH_HAS_VDSO_ARCH_DATA
+	depends on GENERIC_VDSO_DATA_STORE
+	bool
+
 config ARCH_HAS_VDSO_TIME_DATA
 	bool
 
@@ -1695,6 +1707,13 @@ config ARCH_HAS_KERNEL_FPU_SUPPORT
 	  Architectures that select this option can run floating-point code in
 	  the kernel, as described in Documentation/core-api/floating-point.rst.
 
+config ARCH_VMLINUX_NEEDS_RELOCS
+	bool
+	help
+	  Whether the architecture needs vmlinux to be built with static
+	  relocations preserved. This is used by some architectures to
+	  construct bespoke relocation tables for KASLR.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 65fe1e54c6da..fa3e4c246cda 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -10,10 +10,6 @@
 #include <asm/machvec.h>
 #include <asm/hwrpb.h>
 
-/* The generic header contains only prototypes.  Including it ensures that
-   the implementation we have here matches that interface.  */
-#include <asm-generic/iomap.h>
-
 /*
  * Virtual -> physical identity mapping starts at this offset
  */
@@ -276,13 +272,24 @@ extern void		__raw_writeq(u64 b, volatile void __iomem *addr);
 #define __raw_writel __raw_writel
 #define __raw_writeq __raw_writeq
 
-/*
- * Mapping from port numbers to __iomem space is pretty easy.
- */
+extern unsigned int ioread8(const void __iomem *);
+extern unsigned int ioread16(const void __iomem *);
+extern unsigned int ioread32(const void __iomem *);
+extern u64 ioread64(const void __iomem *);
+
+extern void iowrite8(u8, void __iomem *);
+extern void iowrite16(u16, void __iomem *);
+extern void iowrite32(u32, void __iomem *);
+extern void iowrite64(u64, void __iomem *);
+
+extern void ioread8_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread16_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread32_rep(const void __iomem *port, void *buf, unsigned long count);
+
+extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count);
 
-/* These two have to be extern inline because of the extern prototype from
-   <asm-generic/iomap.h>.  It is not legal to mix "extern" and "static" for
-   the same declaration.  */
 extern inline void __iomem *ioport_map(unsigned long port, unsigned int size)
 {
 	return IO_CONCAT(__IO_PREFIX,ioportmap) (port);
@@ -629,10 +636,6 @@ extern void outsl (unsigned long port, const void *src, unsigned long count);
 #define RTC_PORT(x)	(0x70 + (x))
 #define RTC_ALWAYS_BCD	0
 
-/*
- * These get provided from <asm-generic/iomap.h> since alpha does not
- * select GENERIC_IOMAP.
- */
 #define ioread64 ioread64
 #define iowrite64 iowrite64
 #define ioread8_rep ioread8_rep
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 1f0eb4f25c0f..a3eaab094ece 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -852,14 +852,9 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1);
 	perf_sample_data_init(&data, 0, hwc->last_period);
 
-	if (alpha_perf_event_set_period(event, hwc, idx)) {
-		if (perf_event_overflow(event, &data, regs)) {
-			/* Interrupts coming too quickly; "throttle" the
-			 * counter, i.e., disable it for a little while.
-			 */
-			alpha_pmu_stop(event, 0);
-		}
-	}
+	if (alpha_perf_event_set_period(event, hwc, idx))
+		perf_event_overflow(event, &data, regs);
+
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
 
 	return;
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 3e61073f4b30..a89ce84371f9 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -177,7 +177,7 @@ srmcons_close(struct tty_struct *tty, struct file *filp)
 
 	if (tty->count == 1) {
 		port->tty = NULL;
-		del_timer(&srmconsp->timer);
+		timer_delete(&srmconsp->timer);
 	}
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -196,40 +196,44 @@ static const struct tty_operations srmcons_ops = {
 static int __init
 srmcons_init(void)
 {
+	struct tty_driver *driver;
+	int err;
+
 	timer_setup(&srmcons_singleton.timer, srmcons_receive_chars, 0);
-	if (srm_is_registered_console) {
-		struct tty_driver *driver;
-		int err;
-
-		driver = tty_alloc_driver(MAX_SRM_CONSOLE_DEVICES, 0);
-		if (IS_ERR(driver))
-			return PTR_ERR(driver);
-
-		tty_port_init(&srmcons_singleton.port);
-
-		driver->driver_name = "srm";
-		driver->name = "srm";
-		driver->major = 0; 	/* dynamic */
-		driver->minor_start = 0;
-		driver->type = TTY_DRIVER_TYPE_SYSTEM;
-		driver->subtype = SYSTEM_TYPE_SYSCONS;
-		driver->init_termios = tty_std_termios;
-		tty_set_operations(driver, &srmcons_ops);
-		tty_port_link_device(&srmcons_singleton.port, driver, 0);
-		err = tty_register_driver(driver);
-		if (err) {
-			tty_driver_kref_put(driver);
-			tty_port_destroy(&srmcons_singleton.port);
-			return err;
-		}
-		srmcons_driver = driver;
-	}
 
-	return -ENODEV;
+	if (!srm_is_registered_console)
+		return -ENODEV;
+
+	driver = tty_alloc_driver(MAX_SRM_CONSOLE_DEVICES, 0);
+	if (IS_ERR(driver))
+		return PTR_ERR(driver);
+
+	tty_port_init(&srmcons_singleton.port);
+
+	driver->driver_name = "srm";
+	driver->name = "srm";
+	driver->major = 0;	/* dynamic */
+	driver->minor_start = 0;
+	driver->type = TTY_DRIVER_TYPE_SYSTEM;
+	driver->subtype = SYSTEM_TYPE_SYSCONS;
+	driver->init_termios = tty_std_termios;
+	tty_set_operations(driver, &srmcons_ops);
+	tty_port_link_device(&srmcons_singleton.port, driver, 0);
+	err = tty_register_driver(driver);
+	if (err)
+		goto err_free_drv;
+
+	srmcons_driver = driver;
+
+	return 0;
+err_free_drv:
+	tty_driver_kref_put(driver);
+	tty_port_destroy(&srmcons_singleton.port);
+
+	return err;
 }
 device_initcall(srmcons_init);
 
-
 /*
  * The console driver
  */
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index c59d53d6d3f3..2dd6340de6b4 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -506,3 +506,4 @@
 574	common	getxattrat			sys_getxattrat
 575	common	listxattrat			sys_listxattrat
 576	common	removexattrat			sys_removexattrat
+577	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 61c2198b1359..2d491b8cdab9 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -273,14 +273,6 @@ srm_paging_stop (void)
 }
 #endif
 
-void __init
-mem_init(void)
-{
-	set_max_mapnr(max_low_pfn);
-	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-	memblock_free_all();
-}
-
 static const pgprot_t protection_map[16] = {
 	[VM_NONE]					= _PAGE_P(_PAGE_FOE | _PAGE_FOW |
 								  _PAGE_FOR),
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index f324f0e3341a..809edc59af25 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -170,7 +170,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
 	if (parent)
 		panic("DeviceTree incore intc not a root irq controller\n");
 
-	root_domain = irq_domain_add_linear(intc, nr_cpu_irqs, &arcv2_irq_ops, NULL);
+	root_domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_cpu_irqs, &arcv2_irq_ops, NULL);
 	if (!root_domain)
 		panic("root irq domain not avail\n");
 
@@ -178,7 +178,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
 	 * Needed for primary domain lookup to succeed
 	 * This is a primary irqchip, and can never have a parent
 	 */
-	irq_set_default_host(root_domain);
+	irq_set_default_domain(root_domain);
 
 #ifdef CONFIG_SMP
 	irq_create_mapping(root_domain, IPI_IRQ);
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index 6885e422870e..1b159e9e0234 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -112,8 +112,9 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
 	if (parent)
 		panic("DeviceTree incore intc not a root irq controller\n");
 
-	root_domain = irq_domain_add_linear(intc, NR_CPU_IRQS,
-					    &arc_intc_domain_ops, NULL);
+	root_domain = irq_domain_create_linear(of_fwnode_handle(intc),
+					       NR_CPU_IRQS,
+					       &arc_intc_domain_ops, NULL);
 	if (!root_domain)
 		panic("root irq domain not avail\n");
 
@@ -121,7 +122,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent)
 	 * Needed for primary domain lookup to succeed
 	 * This is a primary irqchip, and can never have a parent
 	 */
-	irq_set_default_host(root_domain);
+	irq_set_default_domain(root_domain);
 
 	return 0;
 }
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index cdd370ec9280..02b28a9324f4 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -391,7 +391,8 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 
 	pr_info("MCIP: IDU supports %u common irqs\n", nr_irqs);
 
-	domain = irq_domain_add_linear(intc, nr_irqs, &idu_irq_ops, NULL);
+	domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_irqs,
+					  &idu_irq_ops, NULL);
 
 	/* Parent interrupts (core-intc) are already mapped */
 
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 6e5a651cd75c..ed6d4f0cd621 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -599,10 +599,8 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 
 		arc_perf_event_update(event, &event->hw, event->hw.idx);
 		perf_sample_data_init(&data, 0, hwc->last_period);
-		if (arc_pmu_event_set_period(event)) {
-			if (perf_event_overflow(event, &data, regs))
-				arc_pmu_stop(event, 0);
-		}
+		if (arc_pmu_event_set_period(event))
+			perf_event_overflow(event, &data, regs);
 
 		active_ints &= ~BIT(idx);
 	} while (active_ints);
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 6a71b23f1383..a73cc94f806e 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -150,41 +150,18 @@ void __init setup_arch_memory(void)
 	 */
 	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
 
-	high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
-
 	arch_pfn_offset = min(min_low_pfn, min_high_pfn);
 	kmap_init();
-
-#else /* CONFIG_HIGHMEM */
-	/* pfn_valid() uses this when FLATMEM=y and HIGHMEM=n */
-	max_mapnr = max_low_pfn - min_low_pfn;
-
 #endif /* CONFIG_HIGHMEM */
 
 	free_area_init(max_zone_pfn);
 }
 
-static void __init highmem_init(void)
+void __init arch_mm_preinit(void)
 {
 #ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
 	memblock_phys_free(high_mem_start, high_mem_sz);
-	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
 #endif
-}
-
-/*
- * mem_init - initializes memory
- *
- * Frees up bootmem
- * Calculates and displays memory available/used
- */
-void __init mem_init(void)
-{
-	memblock_free_all();
-	highmem_init();
 
 	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
 	BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE);
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index b07004d53267..fd8897a0e52c 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -32,7 +32,7 @@ void __iomem *ioremap(phys_addr_t paddr, unsigned long size)
 		return (void __iomem *)(u32)paddr;
 
 	return ioremap_prot(paddr, size,
-			    pgprot_val(pgprot_noncached(PAGE_KERNEL)));
+			    pgprot_noncached(PAGE_KERNEL));
 }
 EXPORT_SYMBOL(ioremap);
 
@@ -44,10 +44,8 @@ EXPORT_SYMBOL(ioremap);
  * might need finer access control (R/W/X)
  */
 void __iomem *ioremap_prot(phys_addr_t paddr, size_t size,
-			   unsigned long flags)
+			   pgprot_t prot)
 {
-	pgprot_t prot = __pgprot(flags);
-
 	/* force uncached */
 	return generic_ioremap_prot(paddr, size, pgprot_noncached(prot));
 }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 835b5f100e92..25ed6f1a7c7a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -121,7 +121,7 @@ config ARM
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M
 	select HAVE_KRETPROBES if HAVE_KPROBES
-	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_IS_LLD)
+	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_CAN_USE_KEEP_IN_OVERLAY)
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_OPTPROBES if !THUMB2_KERNEL
@@ -133,6 +133,7 @@ config ARM
 	select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
+	select HAVE_RUST if CPU_LITTLE_ENDIAN && CPU_32v7
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 00ca7886b18e..4808d3ed98e4 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -150,6 +150,7 @@ endif
 KBUILD_CPPFLAGS	+=$(cpp-y)
 KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
 KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float
+KBUILD_RUSTFLAGS += --target=arm-unknown-linux-gnueabi
 
 CHECKFLAGS	+= -D__arm__
 
diff --git a/arch/arm/boot/dts/allwinner/Makefile b/arch/arm/boot/dts/allwinner/Makefile
index 48666f73e638..d799ad153b37 100644
--- a/arch/arm/boot/dts/allwinner/Makefile
+++ b/arch/arm/boot/dts/allwinner/Makefile
@@ -199,6 +199,7 @@ DTC_FLAGS_sun8i-h3-nanopi-r1 := -@
 DTC_FLAGS_sun8i-h3-orangepi-pc := -@
 DTC_FLAGS_sun8i-h3-bananapi-m2-plus-v1.2 := -@
 DTC_FLAGS_sun8i-h3-orangepi-pc-plus := -@
+DTC_FLAGS_sun8i-v3s-netcube-kumquat := -@
 dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-a23-evb.dtb \
 	sun8i-a23-gt90h-v4.dtb \
@@ -261,6 +262,7 @@ dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-v3s-anbernic-rg-nano.dtb \
 	sun8i-v3s-licheepi-zero.dtb \
 	sun8i-v3s-licheepi-zero-dock.dtb \
+	sun8i-v3s-netcube-kumquat.dtb \
 	sun8i-v40-bananapi-m2-berry.dtb
 dtb-$(CONFIG_MACH_SUN9I) += \
 	sun9i-a80-optimus.dtb \
diff --git a/arch/arm/boot/dts/allwinner/sun8i-v3s-netcube-kumquat.dts b/arch/arm/boot/dts/allwinner/sun8i-v3s-netcube-kumquat.dts
new file mode 100644
index 000000000000..5143cb4e7b78
--- /dev/null
+++ b/arch/arm/boot/dts/allwinner/sun8i-v3s-netcube-kumquat.dts
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2025 Lukas Schmid <lukas.schmid@netcube.li>
+ */
+
+/dts-v1/;
+#include "sun8i-v3s.dtsi"
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/{
+	model = "NetCube Systems Kumquat";
+	compatible = "netcube,kumquat", "allwinner,sun8i-v3s";
+
+	aliases {
+		serial0 = &uart0;
+		ethernet0 = &emac;
+		rtc0 = &ds3232;
+		rtc1 = &rtc; /* not battery backed */
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	/* 40 MHz Crystal Oscillator on PCB */
+	clk_can0: clock-can0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency  = <40000000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		autorepeat;
+
+		key-user {
+			label = "GPIO Key User";
+			linux,code = <KEY_PROG1>;
+			gpios = <&pio 1 2 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; /* PB2 */
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-heartbeat {
+			gpios = <&pio 4 4 GPIO_ACTIVE_HIGH>; /* PE4 */
+			linux,default-trigger = "heartbeat";
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+		};
+
+		led-mmc0-act {
+			gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 */
+			linux,default-trigger = "mmc0";
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_DISK;
+		};
+	};
+
+	/* EA3036C Switching 3 Channel Regulator - Channel 2 */
+	reg_vcc3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&reg_vcc5v0>;
+	};
+
+	/* K7805-1000R3 Switching Regulator supplied from main 12/24V terminal block */
+	reg_vcc5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+};
+
+&codec {
+	allwinner,audio-routing =
+		"Headphone", "HP",
+		"Headphone", "HPCOM",
+		"MIC1", "Mic",
+		"Mic", "HBIAS";
+	status = "okay";
+};
+
+&ehci {
+	status = "okay";
+};
+
+&emac {
+	allwinner,leds-active-low;
+	nvmem-cells = <&eth0_macaddress>;
+	nvmem-cell-names = "mac-address";
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	eeprom0: eeprom@50 {
+		compatible = "atmel,24c02";		/* actually it's a 24AA02E48 */
+		reg = <0x50>;
+		pagesize = <16>;
+		read-only;
+		vcc-supply = <&reg_vcc3v3>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		eth0_macaddress: macaddress@fa {
+			reg = <0xfa 0x06>;
+		};
+	};
+
+	tusb320: typec@60 {
+		compatible = "ti,tusb320";
+		reg = <0x60>;
+		interrupts-extended = <&pio 1 5 IRQ_TYPE_LEVEL_LOW>;  /* PB5 */
+	};
+
+	ds3232: rtc@68 {
+		compatible = "dallas,ds3232";
+		reg = <0x68>;
+	};
+};
+
+/* Exposed as the Flash/SD Header on the board */
+&mmc0 {
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	broken-cd;
+	status = "okay";
+};
+
+/* Connected to the on-board ESP32 */
+&mmc1 {
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	broken-cd;
+	status = "okay";
+};
+
+&ohci {
+	status = "okay";
+};
+
+/* Disable external 32k osc as it is broken on current revision */
+&osc32k {
+	status = "disabled";
+};
+
+&pio {
+	vcc-pb-supply = <&reg_vcc3v3>;
+	vcc-pc-supply = <&reg_vcc3v3>;
+	vcc-pe-supply = <&reg_vcc3v3>;
+	vcc-pf-supply = <&reg_vcc3v3>;
+	vcc-pg-supply = <&reg_vcc3v3>;
+
+	gpio-line-names = "", "", "", "", // PA
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "CAN_nCS", "CAN_nINT", "USER_SW", "PB3", // PB
+			  "USB_ID", "USBC_nINT", "I2C0_SCL", "I2C0_SDA",
+			  "UART0_TX", "UART0_RX", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "SPI_MISO", "SPI_SCK", "FLASH_nCS", "SPI_MOSI", // PC
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "", // PD
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "Q12", "Q11", "Q10", "Q9", // PE
+			  "LED_SYS0", "I1", "Q1", "Q2",
+			  "I2", "I3", "Q3", "Q4",
+			  "I4", "I5", "Q5", "Q6",
+			  "I6", "I7", "Q7", "Q8",
+			  "I8", "UART1_TXD", "UART1_RXD", "ESP_nRST",
+			  "ESP_nBOOT", "", "", "",
+			  "", "", "", "",
+			  "SD_D1", "SD_D0", "SD_CLK", "SD_CMD", // PF
+			  "SD_D3", "SD_D2", "LED_SYS1", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "ESP_CLK", "ESP_CMD", "ESP_D0", "ESP_D1", // PG
+			  "ESP_D2", "ESP_D3", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "";
+};
+
+/* Disable external 32k osc as it is broken on current revision */
+&rtc {
+	/delete-property/ clocks;
+};
+
+/* Exposed as a USB-C connector with USB-Serial converter */
+&uart0 {
+	pinctrl-0 = <&uart0_pb_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+/* Connected to the Bootloader/Console of the ESP32 */
+&uart1 {
+	pinctrl-0 = <&uart1_pe_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&usb_otg {
+	extcon = <&tusb320 0>;
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usbphy {
+	usb0_id_det-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
+	status = "okay";
+};
+
+&spi0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	cs-gpios = <0>, <&pio 1 0 GPIO_ACTIVE_LOW>; /* PB0 */
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		label = "firmware";
+		spi-max-frequency = <40000000>;
+	};
+
+	can@1 {
+		compatible = "microchip,mcp2518fd";
+		reg = <1>;
+		clocks = <&clk_can0>;
+		interrupts-extended = <&pio 1 1 IRQ_TYPE_LEVEL_LOW>;  /* PB1 */
+		spi-max-frequency = <20000000>;
+		vdd-supply = <&reg_vcc3v3>;
+		xceiver-supply = <&reg_vcc3v3>;
+	};
+};
diff --git a/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi b/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi
index 9e13c2aa8911..f909b1d4dbca 100644
--- a/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi
+++ b/arch/arm/boot/dts/allwinner/sun8i-v3s.dtsi
@@ -416,6 +416,12 @@
 				function = "uart0";
 			};
 
+			/omit-if-no-ref/
+			uart1_pe_pins: uart1-pe-pins {
+				pins = "PE21", "PE22";
+				function = "uart1";
+			};
+
 			uart2_pins: uart2-pins {
 				pins = "PB0", "PB1";
 				function = "uart2";
diff --git a/arch/arm/boot/dts/amlogic/meson8.dtsi b/arch/arm/boot/dts/amlogic/meson8.dtsi
index 9ff142d9fe3f..f785e0de0847 100644
--- a/arch/arm/boot/dts/amlogic/meson8.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8.dtsi
@@ -449,7 +449,11 @@
 	};
 
 	pwm_ef: pwm@86c0 {
-		compatible = "amlogic,meson8-pwm", "amlogic,meson8b-pwm";
+		compatible = "amlogic,meson8-pwm-v2";
+		clocks = <&xtal>,
+			 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+			 <&clkc CLKID_FCLK_DIV4>,
+			 <&clkc CLKID_FCLK_DIV3>;
 		reg = <0x86c0 0x10>;
 		#pwm-cells = <3>;
 		status = "disabled";
@@ -699,11 +703,19 @@
 };
 
 &pwm_ab {
-	compatible = "amlogic,meson8-pwm", "amlogic,meson8b-pwm";
+	compatible = "amlogic,meson8-pwm-v2";
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &pwm_cd {
-	compatible = "amlogic,meson8-pwm", "amlogic,meson8b-pwm";
+	compatible = "amlogic,meson8-pwm-v2";
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/amlogic/meson8b-ec100.dts b/arch/arm/boot/dts/amlogic/meson8b-ec100.dts
index 18ea6592b7d7..236999548094 100644
--- a/arch/arm/boot/dts/amlogic/meson8b-ec100.dts
+++ b/arch/arm/boot/dts/amlogic/meson8b-ec100.dts
@@ -443,8 +443,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_c1_pins>, <&pwm_d_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>, <&xtal>;
-	clock-names = "clkin0", "clkin1";
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/amlogic/meson8b-mxq.dts b/arch/arm/boot/dts/amlogic/meson8b-mxq.dts
index fb28cb330f17..0bca0b33eea2 100644
--- a/arch/arm/boot/dts/amlogic/meson8b-mxq.dts
+++ b/arch/arm/boot/dts/amlogic/meson8b-mxq.dts
@@ -162,8 +162,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_c1_pins>, <&pwm_d_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>, <&xtal>;
-	clock-names = "clkin0", "clkin1";
 };
 
 &uart_AO {
diff --git a/arch/arm/boot/dts/amlogic/meson8b-odroidc1.dts b/arch/arm/boot/dts/amlogic/meson8b-odroidc1.dts
index 2aa012f38a3b..1cd2093202ca 100644
--- a/arch/arm/boot/dts/amlogic/meson8b-odroidc1.dts
+++ b/arch/arm/boot/dts/amlogic/meson8b-odroidc1.dts
@@ -347,8 +347,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_c1_pins>, <&pwm_d_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>, <&xtal>;
-	clock-names = "clkin0", "clkin1";
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/amlogic/meson8b.dtsi b/arch/arm/boot/dts/amlogic/meson8b.dtsi
index 9e02a97f86a0..fdb0abe23a0c 100644
--- a/arch/arm/boot/dts/amlogic/meson8b.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8b.dtsi
@@ -403,8 +403,12 @@
 	};
 
 	pwm_ef: pwm@86c0 {
-		compatible = "amlogic,meson8b-pwm";
+		compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
 		reg = <0x86c0 0x10>;
+		clocks = <&xtal>,
+			 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+			 <&clkc CLKID_FCLK_DIV4>,
+			 <&clkc CLKID_FCLK_DIV3>;
 		#pwm-cells = <3>;
 		status = "disabled";
 	};
@@ -674,11 +678,19 @@
 };
 
 &pwm_ab {
-	compatible = "amlogic,meson8b-pwm";
+	compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &pwm_cd {
-	compatible = "amlogic,meson8b-pwm";
+	compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2";
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "Video PLL" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
index 6bf4241fe3b7..c78ed064d166 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcm2835-rpi.dtsi"
 
-#include <dt-bindings/power/raspberrypi-power.h>
 #include <dt-bindings/reset/raspberrypi,firmware-reset.h>
 
 / {
@@ -101,7 +100,3 @@
 &vchiq {
 	interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 };
-
-&xhci {
-	power-domains = <&power RPI_POWER_DOMAIN_USB>;
-};
diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index e4e42af21ef3..c06d9f5e53c8 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -134,7 +134,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -145,7 +145,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -156,7 +156,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -167,7 +167,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -451,8 +451,6 @@
 					  IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) |
 					  IRQ_TYPE_LEVEL_LOW)>;
-		/* This only applies to the ARMv7 stub */
-		arm,cpu-registers-not-fw-configured;
 	};
 
 	cpus: cpus {
@@ -610,6 +608,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&pm BCM2835_POWER_DOMAIN_USB>;
 			/* DWC2 and this IP block share the same USB PHY,
 			 * enabling both at the same time results in lockups.
 			 * So keep this node disabled and let the bootloader
@@ -1177,6 +1176,7 @@
 };
 
 &uart0 {
+	arm,primecell-periphid = <0x00341011>;
 	interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 };
 
diff --git a/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts b/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
index 53cb0c58f6d0..3da2daee0c84 100644
--- a/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
+++ b/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
@@ -124,19 +124,19 @@
 		};
 
 		port@1 {
-			label = "lan1";
+			label = "lan4";
 		};
 
 		port@2 {
-			label = "lan2";
+			label = "lan3";
 		};
 
 		port@3 {
-			label = "lan3";
+			label = "lan2";
 		};
 
 		port@4 {
-			label = "lan4";
+			label = "lan1";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts b/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
index 6c666dc7ad23..01ec8c03686a 100644
--- a/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
+++ b/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
@@ -126,11 +126,11 @@
 
 	ports {
 		port@0 {
-			label = "lan4";
+			label = "wan";
 		};
 
 		port@1 {
-			label = "lan3";
+			label = "lan1";
 		};
 
 		port@2 {
@@ -138,11 +138,11 @@
 		};
 
 		port@3 {
-			label = "lan1";
+			label = "lan3";
 		};
 
 		port@4 {
-			label = "wan";
+			label = "lan4";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/cirrus/ep7211-edb7211.dts b/arch/arm/boot/dts/cirrus/ep7211-edb7211.dts
index 808cd5778e27..adc74243ed19 100644
--- a/arch/arm/boot/dts/cirrus/ep7211-edb7211.dts
+++ b/arch/arm/boot/dts/cirrus/ep7211-edb7211.dts
@@ -88,7 +88,7 @@
 };
 
 &portd {
-	lcden {
+	lcden-hog {
 		gpio-hog;
 		gpios = <2 GPIO_ACTIVE_HIGH>;
 		output-high;
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-netgear-wg302v1.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-netgear-wg302v1.dts
index 19d56e9aec9d..a351a97d257e 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-netgear-wg302v1.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-netgear-wg302v1.dts
@@ -8,6 +8,7 @@
 
 #include "intel-ixp42x.dtsi"
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
 
 / {
 	model = "Netgear WG302 v1";
@@ -32,6 +33,35 @@
 		serial0 = &uart1;
 	};
 
+	leds {
+		compatible = "gpio-leds";
+		test_led: led-test {
+			color = <LED_COLOR_ID_AMBER>;
+			function = "test";
+			gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+		wlan_led: led-wlan {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_WLAN;
+			gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+			linux,default-trigger = "phy0tx";
+		};
+	};
+
+	gpio_keys {
+		/* RESET is on GPIO13 which can't fire interrupts */
+		compatible = "gpio-keys-polled";
+		poll-interval = <100>;
+
+		button-reset {
+			linux,code = <KEY_RESTART>;
+			label = "reset";
+			gpios = <&gpio0 13 GPIO_ACTIVE_LOW>;
+		};
+	};
+
 	soc {
 		bus@c4000000 {
 			flash@0,0 {
@@ -57,7 +87,7 @@
 			status = "okay";
 
 			/*
-			 * Taken from WG302 v2 PCI boardfile (wg302v2-pci.c)
+			 * Taken from WG302 v1 PCI boardfile (wg302v1-pci.c)
 			 * We have slots (IDSEL) 1 and 2 with one assigned IRQ
 			 * each handling all IRQs.
 			 */
@@ -70,10 +100,10 @@
 			<0x0800 0 0 3 &gpio0 8 IRQ_TYPE_LEVEL_LOW>, /* INT C on slot 1 is irq 8 */
 			<0x0800 0 0 4 &gpio0 8 IRQ_TYPE_LEVEL_LOW>, /* INT D on slot 1 is irq 8 */
 			/* IDSEL 2 */
-			<0x1000 0 0 1 &gpio0 9 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 2 is irq 9 */
-			<0x1000 0 0 2 &gpio0 9 IRQ_TYPE_LEVEL_LOW>, /* INT B on slot 2 is irq 9 */
-			<0x1000 0 0 3 &gpio0 9 IRQ_TYPE_LEVEL_LOW>, /* INT C on slot 2 is irq 9 */
-			<0x1000 0 0 4 &gpio0 9 IRQ_TYPE_LEVEL_LOW>; /* INT D on slot 2 is irq 9 */
+			<0x1000 0 0 1 &gpio0 10 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 2 is irq 10 */
+			<0x1000 0 0 2 &gpio0 10 IRQ_TYPE_LEVEL_LOW>, /* INT B on slot 2 is irq 10 */
+			<0x1000 0 0 3 &gpio0 10 IRQ_TYPE_LEVEL_LOW>, /* INT C on slot 2 is irq 10 */
+			<0x1000 0 0 4 &gpio0 10 IRQ_TYPE_LEVEL_LOW>; /* INT D on slot 2 is irq 10 */
 		};
 
 		ethernet@c8009000 {
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
index 51a716c59669..0adeccabd4fe 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp4xx.dtsi
@@ -193,10 +193,10 @@
 			compatible = "intel,ixp4xx-ethernet";
 			reg = <0xc800c000 0x1000>;
 			status = "disabled";
-			intel,npe = <0>;
 			/* Dummy values that depend on firmware */
 			queue-rx = <&qmgr 0>;
 			queue-txready = <&qmgr 0>;
+			intel,npe-handle = <&npe 0>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
index 8208c6a9627a..7aa71a9aa1bb 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
@@ -453,7 +453,7 @@
 	pinctrl-0 = <&cf_gtr_fan_pwm &cf_gtr_wifi_disable_pins>;
 	pinctrl-names = "default";
 
-	wifi-disable {
+	wifi-disable-hog {
 		gpio-hog;
 		gpios = <30 GPIO_ACTIVE_LOW>, <31 GPIO_ACTIVE_LOW>;
 		output-low;
@@ -465,7 +465,7 @@
 	pinctrl-0 = <&cf_gtr_isolation_pins &cf_gtr_poe_reset_pins &cf_gtr_lte_disable_pins>;
 	pinctrl-names = "default";
 
-	lte-disable {
+	lte-disable-hog {
 		gpio-hog;
 		gpios = <2 GPIO_ACTIVE_LOW>;
 		output-low;
@@ -476,14 +476,14 @@
 	 * This signal, when asserted, isolates Armada 38x sample at reset pins
 	 * from control of external devices. Should be de-asserted after reset.
 	 */
-	sar-isolation {
+	sar-isolation-hog {
 		gpio-hog;
 		gpios = <15 GPIO_ACTIVE_LOW>;
 		output-low;
 		line-name = "sar-isolation";
 	};
 
-	poe-reset {
+	poe-reset-hog {
 		gpio-hog;
 		gpios = <16 GPIO_ACTIVE_LOW>;
 		output-low;
diff --git a/arch/arm/boot/dts/marvell/armada-388-clearfog-base.dts b/arch/arm/boot/dts/marvell/armada-388-clearfog-base.dts
index f7daa3bc707e..cf32ba9b4e8e 100644
--- a/arch/arm/boot/dts/marvell/armada-388-clearfog-base.dts
+++ b/arch/arm/boot/dts/marvell/armada-388-clearfog-base.dts
@@ -34,7 +34,7 @@
 };
 
 &gpio0 {
-	phy1_reset {
+	phy1-reset-hog {
 		gpio-hog;
 		gpios = <19 GPIO_ACTIVE_LOW>;
 		output-low;
diff --git a/arch/arm/boot/dts/marvell/kirkwood-openrd.dtsi b/arch/arm/boot/dts/marvell/kirkwood-openrd.dtsi
index 47f03c69c55a..9d7cff4feada 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-openrd.dtsi
+++ b/arch/arm/boot/dts/marvell/kirkwood-openrd.dtsi
@@ -53,7 +53,7 @@
 			cd-gpios = <&gpio0 29 9>;
 		};
 		gpio@10100 {
-			p28 {
+			p28-hog {
 				gpio-hog;
 				gpios = <28 GPIO_ACTIVE_HIGH>;
 				/*
@@ -71,7 +71,7 @@
 			};
 		};
 		gpio@10140 {
-			p2 {
+			p2-hog {
 				gpio-hog;
 				gpios = <2 GPIO_ACTIVE_HIGH>;
 				/*
diff --git a/arch/arm/boot/dts/microchip/aks-cdu.dts b/arch/arm/boot/dts/microchip/aks-cdu.dts
index b65f80e1ef05..302cb872efa1 100644
--- a/arch/arm/boot/dts/microchip/aks-cdu.dts
+++ b/arch/arm/boot/dts/microchip/aks-cdu.dts
@@ -56,7 +56,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/animeo_ip.dts b/arch/arm/boot/dts/microchip/animeo_ip.dts
index 7f527622d3f2..c11f4f7dac94 100644
--- a/arch/arm/boot/dts/microchip/animeo_ip.dts
+++ b/arch/arm/boot/dts/microchip/animeo_ip.dts
@@ -136,7 +136,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			atmel,vbus-gpio = <&pioB 15 GPIO_ACTIVE_LOW>;
 			status = "okay";
diff --git a/arch/arm/boot/dts/microchip/at91-foxg20.dts b/arch/arm/boot/dts/microchip/at91-foxg20.dts
index 9dfd5de808d1..8e9e87665045 100644
--- a/arch/arm/boot/dts/microchip/at91-foxg20.dts
+++ b/arch/arm/boot/dts/microchip/at91-foxg20.dts
@@ -131,7 +131,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91-qil_a9260.dts b/arch/arm/boot/dts/microchip/at91-qil_a9260.dts
index 5ccb3c139592..892dbd8dbbed 100644
--- a/arch/arm/boot/dts/microchip/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/microchip/at91-qil_a9260.dts
@@ -114,7 +114,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91-sam9_l9260.dts b/arch/arm/boot/dts/microchip/at91-sam9_l9260.dts
index 2fb51b9aca2a..49dc1a4ccb36 100644
--- a/arch/arm/boot/dts/microchip/at91-sam9_l9260.dts
+++ b/arch/arm/boot/dts/microchip/at91-sam9_l9260.dts
@@ -105,7 +105,7 @@
 			status = "okay";
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
index f3ffb8f01d8a..45edf6214cf7 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d27_som1_ek.dts
@@ -37,7 +37,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@400000 {
+		usb1: usb@400000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0 /* &pioA PIN_PD20 GPIO_ACTIVE_HIGH */
 					   &pioA PIN_PA27 GPIO_ACTIVE_HIGH
@@ -48,7 +48,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@500000 {
+		usb2: usb@500000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d2_ptc_ek.dts
index e4ae60ef5f8a..10d69f6957cf 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d2_ptc_ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d2_ptc_ek.dts
@@ -47,7 +47,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@400000 {
+		usb1: usb@400000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0
 					   &pioA PIN_PB12 GPIO_ACTIVE_HIGH
@@ -58,7 +58,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@500000 {
+		usb2: usb@500000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/microchip/at91-sama5d2_xplained.dts
index 4bab3f25b855..7e77a55ed41d 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d2_xplained.dts
@@ -46,7 +46,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@400000 {
+		usb1: usb@400000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0 /* &pioA PIN_PB9 GPIO_ACTIVE_HIGH */
 					   &pioA PIN_PB10 GPIO_ACTIVE_HIGH
@@ -57,7 +57,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@500000 {
+		usb2: usb@500000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/microchip/at91-sama5d3_xplained.dts
index 5662992cf213..d2c43957497d 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d3_xplained.dts
@@ -283,7 +283,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@600000 {
+		usb1: usb@600000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0
 					   &pioE 3 GPIO_ACTIVE_LOW
@@ -294,7 +294,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@700000 {
+		usb2: usb@700000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d4_ma5d4evk.dts b/arch/arm/boot/dts/microchip/at91-sama5d4_ma5d4evk.dts
index 8adf567f2f0f..b9725e400501 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d4_ma5d4evk.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d4_ma5d4evk.dts
@@ -22,7 +22,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@500000 {
+		usb1: usb@500000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0
 					   &pioE 11 GPIO_ACTIVE_LOW
@@ -31,7 +31,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@600000 {
+		usb2: usb@600000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/microchip/at91-sama5d4_xplained.dts
index 95d701d13fef..0ecccb9a809d 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d4_xplained.dts
@@ -164,7 +164,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@500000 {
+		usb1: usb@500000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0
 					   &pioE 11 GPIO_ACTIVE_HIGH
@@ -175,7 +175,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@600000 {
+		usb2: usb@600000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama5d4ek.dts b/arch/arm/boot/dts/microchip/at91-sama5d4ek.dts
index 20ac775059ca..69107d6cd26c 100644
--- a/arch/arm/boot/dts/microchip/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama5d4ek.dts
@@ -198,7 +198,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@500000 {
+		usb1: usb@500000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0 /* &pioE 10 GPIO_ACTIVE_LOW */
 					   &pioE 11 GPIO_ACTIVE_LOW
@@ -207,7 +207,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@600000 {
+		usb2: usb@600000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
index 0f86360fb733..30fdc4f55a3b 100644
--- a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
@@ -32,6 +32,18 @@
 	};
 };
 
+&dma0 {
+	status = "okay";
+};
+
+&dma1 {
+	status = "okay";
+};
+
+&dma2 {
+	status = "okay";
+};
+
 &flx6 {
 	atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>;
 	status = "okay";
@@ -43,11 +55,63 @@
 	status = "okay";
 };
 
+&flx10 {
+	atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+	status = "okay";
+};
+
+&i2c10 {
+	dmas = <0>, <0>;
+	i2c-analog-filter;
+	i2c-digital-filter;
+	i2c-digital-filter-width-ns = <35>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c10_default>;
+	status = "okay";
+
+	power-monitor@10 {
+		compatible = "microchip,pac1934";
+		reg = <0x10>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		channel@1 {
+			reg = <0x1>;
+			shunt-resistor-micro-ohms = <47000>;
+			label = "VDD3V3";
+		};
+
+		channel@2 {
+			reg = <0x2>;
+			shunt-resistor-micro-ohms = <47000>;
+			label = "VDDIODDR";
+		};
+
+		channel@3 {
+			reg = <0x3>;
+			shunt-resistor-micro-ohms = <47000>;
+			label = "VDDCORE";
+		};
+
+		channel@4 {
+			reg = <0x4>;
+			shunt-resistor-micro-ohms = <47000>;
+			label = "VDDCPU";
+		};
+	};
+};
+
 &main_xtal {
 	clock-frequency = <24000000>;
 };
 
 &pioa {
+	pinctrl_i2c10_default: i2c10-default{
+		pinmux = <PIN_PB19__FLEXCOM10_IO1>,
+			 <PIN_PB20__FLEXCOM10_IO0>;
+		bias-pull-up;
+	};
+
 	pinctrl_sdmmc1_default: sdmmc1-default {
 		cmd-data {
 			pinmux = <PIN_PB22__SDMMC1_CMD>,
@@ -84,6 +148,15 @@
 	status = "okay";
 };
 
+&shdwc {
+	debounce-delay-us = <976>;
+	status = "okay";
+
+	input@0 {
+		reg = <0>;
+	};
+};
+
 &slow_xtal {
 	clock-frequency = <32768>;
 };
diff --git a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
index 0f5e6ad438dd..2543599013b1 100644
--- a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
@@ -137,6 +137,7 @@
 	vref-supply = <&vddout25>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_mikrobus1_an_default &pinctrl_mikrobus2_an_default>;
+	atmel,trigger-edge-type = <IRQ_TYPE_EDGE_RISING>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/microchip/at91-vinco.dts b/arch/arm/boot/dts/microchip/at91-vinco.dts
index ecbdacf48708..c5fc51667066 100644
--- a/arch/arm/boot/dts/microchip/at91-vinco.dts
+++ b/arch/arm/boot/dts/microchip/at91-vinco.dts
@@ -162,7 +162,7 @@
 			status = "disabled";
 		};
 
-		usb1: ohci@500000 {
+		usb1: usb@500000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <0
 					   &pioE 11 GPIO_ACTIVE_LOW
@@ -171,7 +171,7 @@
 			status = "disabled";
 		};
 
-		usb2: ehci@600000 {
+		usb2: usb@600000 {
 			/* 4G Modem */
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91rm9200.dtsi b/arch/arm/boot/dts/microchip/at91rm9200.dtsi
index 02a838541dc3..2a4c83d88733 100644
--- a/arch/arm/boot/dts/microchip/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/microchip/at91rm9200.dtsi
@@ -702,7 +702,7 @@
 			status = "disabled";
 		};
 
-		usb0: ohci@300000 {
+		usb0: usb@300000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00300000 0x100000>;
 			interrupts = <23 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91rm9200ek.dts b/arch/arm/boot/dts/microchip/at91rm9200ek.dts
index 0bf472b157a5..ce691c4692b9 100644
--- a/arch/arm/boot/dts/microchip/at91rm9200ek.dts
+++ b/arch/arm/boot/dts/microchip/at91rm9200ek.dts
@@ -89,7 +89,7 @@
 			};
 		};
 
-		usb0: ohci@300000 {
+		usb0: usb@300000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91sam9260.dtsi b/arch/arm/boot/dts/microchip/at91sam9260.dtsi
index 0038183e9a53..ec973f07a961 100644
--- a/arch/arm/boot/dts/microchip/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9260.dtsi
@@ -742,7 +742,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x100000>;
 			interrupts = <20 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91sam9260ek.dts b/arch/arm/boot/dts/microchip/at91sam9260ek.dts
index e8e65e60564d..8522a210b484 100644
--- a/arch/arm/boot/dts/microchip/at91sam9260ek.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9260ek.dts
@@ -131,7 +131,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91sam9261.dtsi b/arch/arm/boot/dts/microchip/at91sam9261.dtsi
index b57a7fd67197..0b556c234557 100644
--- a/arch/arm/boot/dts/microchip/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9261.dtsi
@@ -77,7 +77,7 @@
 		#size-cells = <1>;
 		ranges;
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x100000>;
 			interrupts = <20 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91sam9261ek.dts b/arch/arm/boot/dts/microchip/at91sam9261ek.dts
index a8f523131cd6..313bc2797fde 100644
--- a/arch/arm/boot/dts/microchip/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9261ek.dts
@@ -31,7 +31,7 @@
 	};
 
 	ahb {
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/microchip/at91sam9263.dtsi b/arch/arm/boot/dts/microchip/at91sam9263.dtsi
index b95d4016ae9f..3e9e5ce7c6c8 100644
--- a/arch/arm/boot/dts/microchip/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9263.dtsi
@@ -768,7 +768,7 @@
 			status = "disabled";
 		};
 
-		usb0: ohci@a00000 {
+		usb0: usb@a00000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00a00000 0x100000>;
 			interrupts = <29 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91sam9263ek.dts b/arch/arm/boot/dts/microchip/at91sam9263ek.dts
index f25692543d71..471ea25296aa 100644
--- a/arch/arm/boot/dts/microchip/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9263ek.dts
@@ -207,7 +207,7 @@
 			};
 		};
 
-		usb0: ohci@a00000 {
+		usb0: usb@a00000 {
 			num-ports = <2>;
 			status = "okay";
 			atmel,vbus-gpio = <&pioA 24 GPIO_ACTIVE_HIGH
diff --git a/arch/arm/boot/dts/microchip/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/microchip/at91sam9g20ek_common.dtsi
index 4e7cfbbd4241..84a7287107f8 100644
--- a/arch/arm/boot/dts/microchip/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9g20ek_common.dtsi
@@ -211,7 +211,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/at91sam9g45.dtsi b/arch/arm/boot/dts/microchip/at91sam9g45.dtsi
index 157d306ef5c9..535e26e05e99 100644
--- a/arch/arm/boot/dts/microchip/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9g45.dtsi
@@ -964,7 +964,7 @@
 			status = "disabled";
 		};
 
-		usb0: ohci@700000 {
+		usb0: usb@700000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -973,7 +973,7 @@
 			status = "disabled";
 		};
 
-		usb1: ehci@800000 {
+		usb1: usb@800000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00800000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91sam9m10g45ek.dts b/arch/arm/boot/dts/microchip/at91sam9m10g45ek.dts
index 071db4f16313..2a31b2f14893 100644
--- a/arch/arm/boot/dts/microchip/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9m10g45ek.dts
@@ -303,14 +303,14 @@
 			};
 		};
 
-		usb0: ohci@700000 {
+		usb0: usb@700000 {
 			status = "okay";
 			num-ports = <2>;
 			atmel,vbus-gpio = <&pioD 1 GPIO_ACTIVE_LOW
 					   &pioD 3 GPIO_ACTIVE_LOW>;
 		};
 
-		usb1: ehci@800000 {
+		usb1: usb@800000 {
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/microchip/at91sam9n12.dtsi b/arch/arm/boot/dts/microchip/at91sam9n12.dtsi
index 844bd50943fc..2f930c39ce4d 100644
--- a/arch/arm/boot/dts/microchip/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9n12.dtsi
@@ -748,7 +748,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x00100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/at91sam9n12ek.dts b/arch/arm/boot/dts/microchip/at91sam9n12ek.dts
index 643c3b2ab97e..b06a54e8e237 100644
--- a/arch/arm/boot/dts/microchip/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9n12ek.dts
@@ -180,7 +180,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <1>;
 			atmel,vbus-gpio = <&pioB 7 GPIO_ACTIVE_LOW>;
 			status = "okay";
diff --git a/arch/arm/boot/dts/microchip/at91sam9x5.dtsi b/arch/arm/boot/dts/microchip/at91sam9x5.dtsi
index 27c1f2861cc3..17bdf1e4db01 100644
--- a/arch/arm/boot/dts/microchip/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9x5.dtsi
@@ -886,7 +886,7 @@
 			};
 		};
 
-		usb0: ohci@600000 {
+		usb0: usb@600000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -895,7 +895,7 @@
 			status = "disabled";
 		};
 
-		usb1: ehci@700000 {
+		usb1: usb@700000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/ethernut5.dts b/arch/arm/boot/dts/microchip/ethernut5.dts
index ad7a0850252a..52ccef31b391 100644
--- a/arch/arm/boot/dts/microchip/ethernut5.dts
+++ b/arch/arm/boot/dts/microchip/ethernut5.dts
@@ -101,7 +101,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/evk-pro3.dts b/arch/arm/boot/dts/microchip/evk-pro3.dts
index 6d519d02d190..40c5111c2f0a 100644
--- a/arch/arm/boot/dts/microchip/evk-pro3.dts
+++ b/arch/arm/boot/dts/microchip/evk-pro3.dts
@@ -45,7 +45,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/mpa1600.dts b/arch/arm/boot/dts/microchip/mpa1600.dts
index 005c2758e229..2a97e2c0b894 100644
--- a/arch/arm/boot/dts/microchip/mpa1600.dts
+++ b/arch/arm/boot/dts/microchip/mpa1600.dts
@@ -57,7 +57,7 @@
 			};
 		};
 
-		usb0: ohci@300000 {
+		usb0: usb@300000 {
 			num-ports = <1>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/microchip/pm9g45.dts b/arch/arm/boot/dts/microchip/pm9g45.dts
index c349fd3758a6..2258e62f5864 100644
--- a/arch/arm/boot/dts/microchip/pm9g45.dts
+++ b/arch/arm/boot/dts/microchip/pm9g45.dts
@@ -139,12 +139,12 @@
 			};
 		};
 
-		usb0: ohci@700000 {
+		usb0: usb@700000 {
 			status = "okay";
 			num-ports = <2>;
 		};
 
-		usb1: ehci@800000 {
+		usb1: usb@800000 {
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi
index b8b2c1ddf3f1..b075865e6a76 100644
--- a/arch/arm/boot/dts/microchip/sam9x60.dtsi
+++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi
@@ -88,7 +88,7 @@
 			status = "disabled";
 		};
 
-		usb1: ohci@600000 {
+		usb1: usb@600000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -97,7 +97,7 @@
 			status = "disabled";
 		};
 
-		usb2: ehci@700000 {
+		usb2: usb@700000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/sama5d2.dtsi b/arch/arm/boot/dts/microchip/sama5d2.dtsi
index 3f99451aef83..dc22fb679333 100644
--- a/arch/arm/boot/dts/microchip/sama5d2.dtsi
+++ b/arch/arm/boot/dts/microchip/sama5d2.dtsi
@@ -136,7 +136,7 @@
 			status = "disabled";
 		};
 
-		usb1: ohci@400000 {
+		usb1: usb@400000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00400000 0x100000>;
 			interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -145,7 +145,7 @@
 			status = "disabled";
 		};
 
-		usb2: ehci@500000 {
+		usb2: usb@500000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00500000 0x100000>;
 			interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/sama5d3.dtsi b/arch/arm/boot/dts/microchip/sama5d3.dtsi
index 70f380c399ce..e95799c17fdb 100644
--- a/arch/arm/boot/dts/microchip/sama5d3.dtsi
+++ b/arch/arm/boot/dts/microchip/sama5d3.dtsi
@@ -1074,7 +1074,7 @@
 			status = "disabled";
 		};
 
-		usb1: ohci@600000 {
+		usb1: usb@600000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -1083,7 +1083,7 @@
 			status = "disabled";
 		};
 
-		usb2: ehci@700000 {
+		usb2: usb@700000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00700000 0x100000>;
 			interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/sama5d3xmb.dtsi b/arch/arm/boot/dts/microchip/sama5d3xmb.dtsi
index 3652c9e24124..90da04b84b39 100644
--- a/arch/arm/boot/dts/microchip/sama5d3xmb.dtsi
+++ b/arch/arm/boot/dts/microchip/sama5d3xmb.dtsi
@@ -172,7 +172,7 @@
 			status = "okay";
 		};
 
-		usb1: ohci@600000 {
+		usb1: usb@600000 {
 			num-ports = <3>;
 			atmel,vbus-gpio = <&pioD 25 GPIO_ACTIVE_HIGH
 					   &pioD 26 GPIO_ACTIVE_LOW
@@ -181,7 +181,7 @@
 			status = "okay";
 		};
 
-		usb2: ehci@700000 {
+		usb2: usb@700000 {
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/microchip/sama5d4.dtsi b/arch/arm/boot/dts/microchip/sama5d4.dtsi
index 355132628604..59a7d557c7cb 100644
--- a/arch/arm/boot/dts/microchip/sama5d4.dtsi
+++ b/arch/arm/boot/dts/microchip/sama5d4.dtsi
@@ -119,7 +119,7 @@
 			status = "disabled";
 		};
 
-		usb1: ohci@500000 {
+		usb1: usb@500000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x100000>;
 			interrupts = <46 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -128,7 +128,7 @@
 			status = "disabled";
 		};
 
-		usb2: ehci@600000 {
+		usb2: usb@600000 {
 			compatible = "atmel,at91sam9g45-ehci", "usb-ehci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <46 IRQ_TYPE_LEVEL_HIGH 2>;
diff --git a/arch/arm/boot/dts/microchip/sama7d65.dtsi b/arch/arm/boot/dts/microchip/sama7d65.dtsi
index 854b30d15dcd..b6710ccd4c36 100644
--- a/arch/arm/boot/dts/microchip/sama7d65.dtsi
+++ b/arch/arm/boot/dts/microchip/sama7d65.dtsi
@@ -9,6 +9,7 @@
  */
 
 #include <dt-bindings/clock/at91.h>
+#include <dt-bindings/dma/at91.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -52,6 +53,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
+		sfrbu: sfr@e0008000 {
+			compatible ="microchip,sama7d65-sfrbu", "atmel,sama5d2-sfrbu", "syscon";
+			reg = <0xe0008000 0x20>;
+		};
+
 		pioa: pinctrl@e0014000 {
 			compatible = "microchip,sama7d65-pinctrl", "microchip,sama7g5-pinctrl";
 			reg = <0xe0014000 0x800>;
@@ -76,6 +82,31 @@
 			clock-names = "td_slck", "md_slck", "main_xtal";
 		};
 
+		ps_wdt: watchdog@e001d000 {
+			compatible = "microchip,sama7d65-wdt", "microchip,sama7g5-wdt";
+			reg = <0xe001d000 0x30>;
+			interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk32k 0>;
+		};
+
+		reset_controller: reset-controller@e001d100 {
+			compatible = "microchip,sama7d65-rstc", "microchip,sama7g5-rstc";
+			reg = <0xe001d100 0xc>, <0xe001d1e4 0x4>;
+			#reset-cells = <1>;
+			clocks = <&clk32k 0>;
+		};
+
+		shdwc: poweroff@e001d200 {
+			compatible = "microchip,sama7d65-shdwc", "microchip,sama7g5-shdwc", "syscon";
+			reg = <0xe001d200 0x20>;
+			clocks = <&clk32k 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			atmel,wakeup-rtc-timer;
+			atmel,wakeup-rtt-timer;
+			status = "disabled";
+		};
+
 		clk32k: clock-controller@e001d500 {
 			compatible = "microchip,sama7d65-sckc", "microchip,sam9x60-sckc";
 			reg = <0xe001d500 0x4>;
@@ -83,6 +114,29 @@
 			#clock-cells = <1>;
 		};
 
+		rtc: rtc@e001d800 {
+			compatible = "microchip,sama7d65-rtc", "microchip,sam9x60-rtc";
+			reg = <0xe001d800 0x30>;
+			interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk32k 1>;
+		};
+
+		chipid@e0020000 {
+			compatible = "microchip,sama7d65-chipid";
+			reg = <0xe0020000 0x8>;
+		};
+
+		dma2: dma-controller@e1200000 {
+			compatible = "microchip,sama7d65-dma", "microchip,sama7g5-dma";
+			reg = <0xe1200000 0x1000>;
+			interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			clocks = <&pmc PMC_TYPE_PERIPHERAL 23>;
+			clock-names = "dma_clk";
+			dma-requests = <0>;
+			status = "disabled";
+		};
+
 		sdmmc1: mmc@e1208000 {
 			compatible = "microchip,sama7d65-sdhci", "microchip,sam9x60-sdhci";
 			reg = <0xe1208000 0x400>;
@@ -95,6 +149,26 @@
 			status = "disabled";
 		};
 
+		dma0: dma-controller@e1610000 {
+			compatible = "microchip,sama7d65-dma", "microchip,sama7g5-dma";
+			reg = <0xe1610000 0x1000>;
+			interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			clocks = <&pmc PMC_TYPE_PERIPHERAL 21>;
+			clock-names = "dma_clk";
+			status = "disabled";
+		};
+
+		dma1: dma-controller@e1614000 {
+			compatible = "microchip,sama7d65-dma", "microchip,sama7g5-dma";
+			reg = <0xe1614000 0x1000>;
+			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			clocks = <&pmc PMC_TYPE_PERIPHERAL 22>;
+			clock-names = "dma_clk";
+			status = "disabled";
+		};
+
 		pit64b0: timer@e1800000 {
 			compatible = "microchip,sama7d65-pit64b", "microchip,sam9x60-pit64b";
 			reg = <0xe1800000 0x100>;
@@ -132,6 +206,27 @@
 			};
 		};
 
+		flx10: flexcom@e2824000 {
+			compatible = "microchip,sama7d65-flexcom", "atmel,sama5d2-flexcom";
+			reg = <0xe2824000 0x200>;
+			ranges = <0x0 0xe2824000 0x800>;
+			clocks = <&pmc PMC_TYPE_PERIPHERAL 44>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+
+			i2c10: i2c@600 {
+				compatible = "microchip,sama7d65-i2c", "microchip,sam9x60-i2c";
+				reg = <0x600 0x200>;
+				interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&pmc PMC_TYPE_PERIPHERAL 44>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				atmel,fifo-size = <32>;
+				status = "disabled";
+			};
+		};
+
 		gic: interrupt-controller@e8c11000 {
 			compatible = "arm,cortex-a7-gic";
 			reg = <0xe8c11000 0x1000>,
diff --git a/arch/arm/boot/dts/microchip/tny_a9260.dts b/arch/arm/boot/dts/microchip/tny_a9260.dts
index ef6d586ce887..f0f2a787d669 100644
--- a/arch/arm/boot/dts/microchip/tny_a9260.dts
+++ b/arch/arm/boot/dts/microchip/tny_a9260.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tny_a9260.dts - Device Tree file for Caloa TNY A9260 board
+ * tny_a9260.dts - Device Tree file for Calao TNY A9260 board
  *
  * Copyright (C) 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/tny_a9260_common.dtsi b/arch/arm/boot/dts/microchip/tny_a9260_common.dtsi
index 70e5635c78ed..4d4377f51bec 100644
--- a/arch/arm/boot/dts/microchip/tny_a9260_common.dtsi
+++ b/arch/arm/boot/dts/microchip/tny_a9260_common.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tny_a9260_common.dtsi - Device Tree file for Caloa TNY A926x board
+ * tny_a9260_common.dtsi - Device Tree file for Calao TNY A926x board
  *
  * Copyright (C) 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/tny_a9263.dts b/arch/arm/boot/dts/microchip/tny_a9263.dts
index 62b7d9f9a926..3dd48b3e06da 100644
--- a/arch/arm/boot/dts/microchip/tny_a9263.dts
+++ b/arch/arm/boot/dts/microchip/tny_a9263.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * usb_a9263.dts - Device Tree file for Caloa USB A9293 board
+ * usb_a9263.dts - Device Tree file for Calao USB A9293 board
  *
  *  Copyright (C) 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/tny_a9g20.dts b/arch/arm/boot/dts/microchip/tny_a9g20.dts
index 118d766a1265..cebd5696a2c1 100644
--- a/arch/arm/boot/dts/microchip/tny_a9g20.dts
+++ b/arch/arm/boot/dts/microchip/tny_a9g20.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tny_a9g20.dts - Device Tree file for Caloa TNY A9G20 board
+ * tny_a9g20.dts - Device Tree file for Calao TNY A9G20 board
  *
  * Copyright (C) 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/usb_a9260.dts b/arch/arm/boot/dts/microchip/usb_a9260.dts
index 66f8da89007d..e7f7b259ccf3 100644
--- a/arch/arm/boot/dts/microchip/usb_a9260.dts
+++ b/arch/arm/boot/dts/microchip/usb_a9260.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * usb_a9260.dts - Device Tree file for Caloa USB A9260 board
+ * usb_a9260.dts - Device Tree file for Calao USB A9260 board
  *
  *  Copyright (C) 2011-2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/usb_a9260_common.dtsi b/arch/arm/boot/dts/microchip/usb_a9260_common.dtsi
index 8744b5f6f792..8c3530638c6d 100644
--- a/arch/arm/boot/dts/microchip/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/microchip/usb_a9260_common.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * usb_a926x.dts - Device Tree file for Caloa USB A926x board
+ * usb_a926x.dts - Device Tree file for Calao USB A926x board
  *
  *  Copyright (C) 2011-2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
@@ -111,7 +111,7 @@
 			};
 		};
 
-		usb0: ohci@500000 {
+		usb0: usb@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
@@ -122,17 +122,14 @@
 
 		user_led {
 			label = "user_led";
-			gpios = <&pioB 21 GPIO_ACTIVE_LOW>;
-			linux,default-trigger = "heartbeat";
+			gpios = <&pioB 21 GPIO_ACTIVE_HIGH>;
 		};
 	};
 
 	gpio_keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
-		user_pb {
+		button-user-pb {
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
diff --git a/arch/arm/boot/dts/microchip/usb_a9263.dts b/arch/arm/boot/dts/microchip/usb_a9263.dts
index 45745915b2e1..60d7936dc562 100644
--- a/arch/arm/boot/dts/microchip/usb_a9263.dts
+++ b/arch/arm/boot/dts/microchip/usb_a9263.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * usb_a9263.dts - Device Tree file for Caloa USB A9293 board
+ * usb_a9263.dts - Device Tree file for Calao USB A9293 board
  *
  *  Copyright (C) 2012 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
@@ -9,7 +9,7 @@
 
 / {
 	model = "Calao USB A9263";
-	compatible = "atmel,usb-a9263", "atmel,at91sam9263", "atmel,at91sam9";
+	compatible = "calao,usb-a9263", "atmel,at91sam9263", "atmel,at91sam9";
 
 	chosen {
 		bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock5 rw rootfstype=ubifs";
@@ -139,7 +139,7 @@
 			};
 		};
 
-		usb0: ohci@a00000 {
+		usb0: usb@a00000 {
 			num-ports = <2>;
 			status = "okay";
 		};
@@ -151,16 +151,13 @@
 		user_led {
 			label = "user_led";
 			gpios = <&pioB 21 GPIO_ACTIVE_HIGH>;
-			linux,default-trigger = "heartbeat";
 		};
 	};
 
 	gpio_keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
-		user_pb {
+		button-user-pb {
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
diff --git a/arch/arm/boot/dts/microchip/usb_a9g20-dab-mmx.dtsi b/arch/arm/boot/dts/microchip/usb_a9g20-dab-mmx.dtsi
index 08d58081201a..5b1d80c0ab26 100644
--- a/arch/arm/boot/dts/microchip/usb_a9g20-dab-mmx.dtsi
+++ b/arch/arm/boot/dts/microchip/usb_a9g20-dab-mmx.dtsi
@@ -65,28 +65,26 @@
 
 	gpio_keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
-		user_pb1 {
+		button-user-pb1 {
 			label = "user_pb1";
 			gpios = <&pioB 25 GPIO_ACTIVE_LOW>;
 			linux,code = <0x100>;
 		};
 
-		user_pb2 {
+		button-user-pb2 {
 			label = "user_pb2";
 			gpios = <&pioB 13 GPIO_ACTIVE_LOW>;
 			linux,code = <0x101>;
 		};
 
-		user_pb3 {
+		button-user-pb3 {
 			label = "user_pb3";
 			gpios = <&pioA 26 GPIO_ACTIVE_LOW>;
 			linux,code = <0x102>;
 		};
 
-		user_pb4 {
+		button-user-pb4 {
 			label = "user_pb4";
 			gpios = <&pioC 9 GPIO_ACTIVE_LOW>;
 			linux,code = <0x103>;
diff --git a/arch/arm/boot/dts/microchip/usb_a9g20.dts b/arch/arm/boot/dts/microchip/usb_a9g20.dts
index 2f667b083e81..a2f748141d4b 100644
--- a/arch/arm/boot/dts/microchip/usb_a9g20.dts
+++ b/arch/arm/boot/dts/microchip/usb_a9g20.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * usb_a9g20.dts - Device Tree file for Caloa USB A9G20 board
+ * usb_a9g20.dts - Device Tree file for Calao USB A9G20 board
  *
  *  Copyright (C) 2011 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/usb_a9g20_common.dtsi b/arch/arm/boot/dts/microchip/usb_a9g20_common.dtsi
index 7d10b36db1ee..f1946e0996b7 100644
--- a/arch/arm/boot/dts/microchip/usb_a9g20_common.dtsi
+++ b/arch/arm/boot/dts/microchip/usb_a9g20_common.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * usb_a9g20.dts - Device Tree file for Caloa USB A9G20 board
+ * usb_a9g20.dts - Device Tree file for Calao USB A9G20 board
  *
  *  Copyright (C) 2011 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
diff --git a/arch/arm/boot/dts/microchip/usb_a9g20_lpw.dts b/arch/arm/boot/dts/microchip/usb_a9g20_lpw.dts
index f65712015d40..4d104797176c 100644
--- a/arch/arm/boot/dts/microchip/usb_a9g20_lpw.dts
+++ b/arch/arm/boot/dts/microchip/usb_a9g20_lpw.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * usb_a9g20_lpw.dts - Device Tree file for Caloa USB A9G20 Low Power board
+ * usb_a9g20_lpw.dts - Device Tree file for Calao USB A9G20 Low Power board
  *
  *  Copyright (C) 2013 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
  */
@@ -16,7 +16,7 @@
 			spi1: spi@fffcc000 {
 				cs-gpios = <&pioB 3 GPIO_ACTIVE_HIGH>;
 				status = "okay";
-				mmc-slot@0 {
+				mmc@0 {
 					compatible = "mmc-spi-slot";
 					reg = <0>;
 					voltage-ranges = <3200 3400>;
diff --git a/arch/arm/boot/dts/nvidia/tegra114.dtsi b/arch/arm/boot/dts/nvidia/tegra114.dtsi
index 86f14e2fd29f..4caf2073c556 100644
--- a/arch/arm/boot/dts/nvidia/tegra114.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra114.dtsi
@@ -139,7 +139,7 @@
 			reg = <0x54400000 0x00040000>;
 			clocks = <&tegra_car TEGRA114_CLK_DSIB>,
 				 <&tegra_car TEGRA114_CLK_DSIBLP>,
-				 <&tegra_car TEGRA114_CLK_PLL_D2_OUT0>;
+				 <&tegra_car TEGRA114_CLK_PLL_D_OUT0>;
 			clock-names = "dsi", "lp", "parent";
 			resets = <&tegra_car 82>;
 			reset-names = "dsi";
@@ -577,6 +577,21 @@
 		#iommu-cells = <1>;
 	};
 
+	hda@70030000 {
+		compatible = "nvidia,tegra114-hda", "nvidia,tegra30-hda";
+		reg = <0x70030000 0x10000>;
+		interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA114_CLK_HDA>,
+			 <&tegra_car TEGRA114_CLK_HDA2HDMI>,
+			 <&tegra_car TEGRA114_CLK_HDA2CODEC_2X>;
+		clock-names = "hda", "hda2hdmi", "hda2codec_2x";
+		resets = <&tegra_car 125>, /* hda */
+			 <&tegra_car 128>, /* hda2hdmi */
+			 <&tegra_car 111>; /* hda2codec_2x */
+		reset-names = "hda", "hda2hdmi", "hda2codec_2x";
+		status = "disabled";
+	};
+
 	ahub@70080000 {
 		compatible = "nvidia,tegra114-ahub";
 		reg = <0x70080000 0x200>,
@@ -805,31 +820,40 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@0 {
+		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0>;
 		};
 
-		cpu@1 {
+		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <1>;
 		};
 
-		cpu@2 {
+		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <2>;
 		};
 
-		cpu@3 {
+		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <3>;
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a15-pmu";
+		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts =
diff --git a/arch/arm/boot/dts/nvidia/tegra124.dtsi b/arch/arm/boot/dts/nvidia/tegra124.dtsi
index 8f1fff373461..ec4f0e346b2b 100644
--- a/arch/arm/boot/dts/nvidia/tegra124.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra124.dtsi
@@ -165,6 +165,22 @@
 			status = "disabled";
 		};
 
+		dsia: dsi@54300000 {
+			compatible = "nvidia,tegra124-dsi";
+			reg = <0x0 0x54300000 0x0 0x00040000>;
+			clocks = <&tegra_car TEGRA124_CLK_DSIA>,
+				 <&tegra_car TEGRA124_CLK_DSIALP>,
+				 <&tegra_car TEGRA124_CLK_PLL_D_OUT0>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&tegra_car 48>;
+			reset-names = "dsi";
+			nvidia,mipi-calibrate = <&mipi 0x060>; /* DSIA & DSIB pads */
+			status = "disabled";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
 		vic@54340000 {
 			compatible = "nvidia,tegra124-vic";
 			reg = <0x0 0x54340000 0x0 0x00040000>;
@@ -177,6 +193,22 @@
 			iommus = <&mc TEGRA_SWGROUP_VIC>;
 		};
 
+		dsib: dsi@54400000 {
+			compatible = "nvidia,tegra124-dsi";
+			reg = <0x0 0x54400000 0x0 0x00040000>;
+			clocks = <&tegra_car TEGRA124_CLK_DSIB>,
+				 <&tegra_car TEGRA124_CLK_DSIBLP>,
+				 <&tegra_car TEGRA124_CLK_PLL_D_OUT0>;
+			clock-names = "dsi", "lp", "parent";
+			resets = <&tegra_car 82>;
+			reset-names = "dsi";
+			nvidia,mipi-calibrate = <&mipi 0x180>; /* DSIC & DSID pads */
+			status = "disabled";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
 		sor@54540000 {
 			compatible = "nvidia,tegra124-sor";
 			reg = <0x0 0x54540000 0x0 0x00040000>;
@@ -938,6 +970,14 @@
 		};
 	};
 
+	mipi: mipi@700e3000 {
+		compatible = "nvidia,tegra124-mipi";
+		reg = <0x0 0x700e3000 0x0 0x100>;
+		clocks = <&tegra_car TEGRA124_CLK_MIPI_CAL>;
+		clock-names = "mipi-cal";
+		#nvidia,mipi-calibrate-cells = <1>;
+	};
+
 	dfll: clock@70110000 {
 		compatible = "nvidia,tegra124-dfll";
 		reg = <0 0x70110000 0 0x100>, /* DFLL control */
diff --git a/arch/arm/boot/dts/nvidia/tegra20-asus-tf101.dts b/arch/arm/boot/dts/nvidia/tegra20-asus-tf101.dts
index e118809dc6d9..67764afeb013 100644
--- a/arch/arm/boot/dts/nvidia/tegra20-asus-tf101.dts
+++ b/arch/arm/boot/dts/nvidia/tegra20-asus-tf101.dts
@@ -1085,6 +1085,17 @@
 				sbs,poll-retry-count = <10>;
 				power-supplies = <&mains>;
 			};
+
+			/* Dynaimage ambient light sensor */
+			light-sensor@1c {
+				compatible = "dynaimage,al3000a";
+				reg = <0x1c>;
+
+				interrupt-parent = <&gpio>;
+				interrupts = <TEGRA_GPIO(Z, 2) IRQ_TYPE_LEVEL_HIGH>;
+
+				vdd-supply = <&vdd_1v8_sys>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/nxp/imx/Makefile b/arch/arm/boot/dts/nxp/imx/Makefile
index 39a153536d2a..8b3abe817e12 100644
--- a/arch/arm/boot/dts/nxp/imx/Makefile
+++ b/arch/arm/boot/dts/nxp/imx/Makefile
@@ -69,6 +69,10 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-colibri-eval-v3.dtb \
 	imx6dl-colibri-iris.dtb \
 	imx6dl-colibri-iris-v2.dtb \
+	imx6dl-colibri-v1.2-aster.dtb \
+	imx6dl-colibri-v1.2-eval-v3.dtb \
+	imx6dl-colibri-v1.2-iris.dtb \
+	imx6dl-colibri-v1.2-iris-v2.dtb \
 	imx6dl-cubox-i.dtb \
 	imx6dl-cubox-i-emmc-som-v15.dtb \
 	imx6dl-cubox-i-som-v15.dtb \
@@ -158,6 +162,11 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-apalis-ixora.dtb \
 	imx6q-apalis-ixora-v1.1.dtb \
 	imx6q-apalis-ixora-v1.2.dtb \
+	imx6q-apalis-v1.2-eval.dtb \
+	imx6q-apalis-v1.2-eval-v1.2.dtb \
+	imx6q-apalis-v1.2-ixora.dtb \
+	imx6q-apalis-v1.2-ixora-v1.1.dtb \
+	imx6q-apalis-v1.2-ixora-v1.2.dtb \
 	imx6q-apf6dev.dtb \
 	imx6q-arm2.dtb \
 	imx6q-b450v3.dtb \
@@ -329,6 +338,7 @@ dtb-$(CONFIG_SOC_IMX6UL) += \
 	imx6ul-tx6ul-0010.dtb \
 	imx6ul-tx6ul-0011.dtb \
 	imx6ul-tx6ul-mainboard.dtb \
+	imx6ul-var-som-concerto.dtb \
 	imx6ull-14x14-evk.dtb \
 	imx6ull-colibri-aster.dtb \
 	imx6ull-colibri-emmc-aster.dtb \
diff --git a/arch/arm/boot/dts/nxp/imx/imx31.dtsi b/arch/arm/boot/dts/nxp/imx/imx31.dtsi
index 00006c90d9a7..813a81558c40 100644
--- a/arch/arm/boot/dts/nxp/imx/imx31.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx31.dtsi
@@ -340,7 +340,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			nfc: nand@b8000000 {
+			nfc: nand-controller@b8000000 {
 				compatible = "fsl,imx31-nand", "fsl,imx27-nand";
 				reg = <0xb8000000 0x1000>;
 				interrupts = <33>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx50.dtsi b/arch/arm/boot/dts/nxp/imx/imx50.dtsi
index 1b6f444443dd..d76c496b3f71 100644
--- a/arch/arm/boot/dts/nxp/imx/imx50.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx50.dtsi
@@ -338,7 +338,7 @@
 			clks: ccm@53fd4000 {
 				compatible = "fsl,imx50-ccm";
 				reg = <0x53fd4000 0x4000>;
-				interrupts = <0 71 0x04 0 72 0x04>;
+				interrupts = <71>, <72>;
 				#clock-cells = <1>;
 			};
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx51.dtsi b/arch/arm/boot/dts/nxp/imx/imx51.dtsi
index cc88da4d7785..8323e3a56a1f 100644
--- a/arch/arm/boot/dts/nxp/imx/imx51.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx51.dtsi
@@ -458,7 +458,7 @@
 			clks: ccm@73fd4000 {
 				compatible = "fsl,imx51-ccm";
 				reg = <0x73fd4000 0x4000>;
-				interrupts = <0 71 0x04 0 72 0x04>;
+				interrupts = <71>, <72>;
 				#clock-cells = <1>;
 			};
 		};
diff --git a/arch/arm/boot/dts/nxp/imx/imx53-mba53.dts b/arch/arm/boot/dts/nxp/imx/imx53-mba53.dts
index c14eb7280f09..3cdb87ac1d7c 100644
--- a/arch/arm/boot/dts/nxp/imx/imx53-mba53.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx53-mba53.dts
@@ -162,7 +162,7 @@
 	};
 
 	expander: pca9554@20 {
-		compatible = "pca9554";
+		compatible = "nxp,pca9554";
 		reg = <0x20>;
 		interrupts = <109>;
 		#gpio-cells = <2>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx53-ppd.dts b/arch/arm/boot/dts/nxp/imx/imx53-ppd.dts
index e939acc1c88b..2892e457fea7 100644
--- a/arch/arm/boot/dts/nxp/imx/imx53-ppd.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx53-ppd.dts
@@ -593,7 +593,7 @@
 
 	touchscreen@4b {
 		compatible = "atmel,maxtouch";
-		reset-gpio = <&gpio5 19 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio5 19 GPIO_ACTIVE_LOW>;
 		reg = <0x4b>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx53.dtsi b/arch/arm/boot/dts/nxp/imx/imx53.dtsi
index 845e2bf8460a..faac7cc249d0 100644
--- a/arch/arm/boot/dts/nxp/imx/imx53.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx53.dtsi
@@ -598,7 +598,7 @@
 			clks: ccm@53fd4000 {
 				compatible = "fsl,imx53-ccm";
 				reg = <0x53fd4000 0x4000>;
-				interrupts = <0 71 0x04 0 72 0x04>;
+				interrupts = <71>, <72>;
 				#clock-cells = <1>;
 			};
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-aster.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-aster.dts
new file mode 100644
index 000000000000..44c78c07f431
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-aster.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6dl-colibri-aster.dts"
+#include "imx6qdl-colibri-v1.2.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX6DL/S V1.2+ on Colibri Aster Board";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-eval-v3.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-eval-v3.dts
new file mode 100644
index 000000000000..93fd0af53a3c
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-eval-v3.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6dl-colibri-eval-v3.dts"
+#include "imx6qdl-colibri-v1.2.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX6DL/S V1.2+ on Colibri Evaluation Board V3";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris-v2.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris-v2.dts
new file mode 100644
index 000000000000..92d41fc9a13f
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris-v2.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6dl-colibri-iris-v2.dts"
+#include "imx6qdl-colibri-v1.2.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX6DL/S V1.2+ on Colibri Iris V2 Board";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris.dts
new file mode 100644
index 000000000000..c8957948c887
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-colibri-v1.2-iris.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6dl-colibri-iris.dts"
+#include "imx6qdl-colibri-v1.2.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX6DL/S V1.2+ on Colibri Iris Board";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval-v1.2.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval-v1.2.dts
new file mode 100644
index 000000000000..908dab57fd87
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval-v1.2.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6q-apalis-eval-v1.2.dts"
+#include "imx6qdl-apalis-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module V1.2+ on Apalis Evaluation Board v1.2";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval.dts
new file mode 100644
index 000000000000..5463d4127382
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-eval.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6q-apalis-eval.dts"
+#include "imx6qdl-apalis-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module V1.2+ on Apalis Evaluation Board";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.1.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.1.dts
new file mode 100644
index 000000000000..84eabf81ba84
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.1.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6q-apalis-ixora-v1.1.dts"
+#include "imx6qdl-apalis-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module V1.2+ on Ixora Carrier Board V1.1";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.2.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.2.dts
new file mode 100644
index 000000000000..d7cfab4de457
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora-v1.2.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6q-apalis-ixora-v1.2.dts"
+#include "imx6qdl-apalis-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module V1.2+ on Ixora Carrier Board V1.2";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora.dts
new file mode 100644
index 000000000000..189b074e31ce
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-v1.2-ixora.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+/dts-v1/;
+
+#include "imx6q-apalis-ixora.dts"
+#include "imx6qdl-apalis-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module V1.2+ on Ixora Carrier Board";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis-v1.2.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis-v1.2.dtsi
new file mode 100644
index 000000000000..83fa04fc9f18
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis-v1.2.dtsi
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+&i2c2 {
+	/delete-node/ stmpe811@41;
+
+	ad7879_ts: touchscreen@2c {
+		compatible = "adi,ad7879-1";
+		reg = <0x2c>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touch_int>;
+		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-parent = <&gpio4>;
+		touchscreen-max-pressure = <4096>;
+		adi,resistance-plate-x = <120>;
+		adi,first-conversion-delay = /bits/ 8 <3>;
+		adi,acquisition-time = /bits/ 8 <1>;
+		adi,median-filter-size = /bits/ 8 <2>;
+		adi,averaging = /bits/ 8 <1>;
+		adi,conversion-interval = /bits/ 8 <255>;
+	};
+
+	tla2024_adc: adc@49 {
+		compatible = "ti,tla2024";
+		reg = <0x49>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* Apalis AN1_ADC0 */
+		channel@4 {
+			reg = <4>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Apalis AN1_ADC1 */
+		channel@5 {
+			reg = <5>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Apalis AN1_ADC2 */
+		channel@6 {
+			reg = <6>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Apalis AN1_TSWIP_ADC3 */
+		channel@7 {
+			reg = <7>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
index dffab5aa8b9c..b13000a62a7b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
@@ -10,7 +10,6 @@
 
 / {
 	model = "Toradex Apalis iMX6Q/D Module";
-	compatible = "toradex,apalis_imx6q", "fsl,imx6q";
 
 	aliases {
 		mmc0 = &usdhc3; /* eMMC */
@@ -108,6 +107,11 @@
 		};
 	};
 
+	poweroff {
+		compatible = "regulator-poweroff";
+		cpu-supply = <&vgen2_reg>;
+	};
+
 	reg_module_3v3: regulator-module-3v3 {
 		compatible = "regulator-fixed";
 		regulator-always-on;
@@ -236,10 +240,6 @@
 	status = "disabled";
 };
 
-&clks {
-	fsl,pmic-stby-poweroff;
-};
-
 /* Apalis SPI1 */
 &ecspi1 {
 	cs-gpios = <&gpio5 25 GPIO_ACTIVE_LOW>;
@@ -527,7 +527,6 @@
 
 	pmic: pmic@8 {
 		compatible = "fsl,pfuze100";
-		fsl,pmic-stby-poweroff;
 		reg = <0x08>;
 
 		regulators {
@@ -664,7 +663,6 @@
 			st,settling = <3>;
 			/* 5 ms touch detect interrupt delay */
 			st,touch-det-delay = <5>;
-			status = "disabled";
 		};
 
 		stmpe_adc: stmpe_adc {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri-v1.2.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri-v1.2.dtsi
new file mode 100644
index 000000000000..d11bf911b728
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri-v1.2.dtsi
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/* Copyright (c) 2025 Toradex */
+
+&i2c2 {
+	/delete-node/ stmpe811@41;
+
+	ad7879_ts: touchscreen@2c {
+		compatible = "adi,ad7879-1";
+		reg = <0x2c>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touch_int>;
+		interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-parent = <&gpio6>;
+		touchscreen-max-pressure = <4096>;
+		adi,resistance-plate-x = <120>;
+		adi,first-conversion-delay = /bits/ 8 <3>;
+		adi,acquisition-time = /bits/ 8 <1>;
+		adi,median-filter-size = /bits/ 8 <2>;
+		adi,averaging = /bits/ 8 <1>;
+		adi,conversion-interval = /bits/ 8 <255>;
+	};
+
+	tla2024_adc: adc@49 {
+		compatible = "ti,tla2024";
+		reg = <0x49>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* Colibri AIN0 */
+		channel@4 {
+			reg = <4>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Colibri AIN1 */
+		channel@5 {
+			reg = <5>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Colibri AIN2 */
+		channel@6 {
+			reg = <6>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+
+		/* Colibri AIN3 */
+		channel@7 {
+			reg = <7>;
+			ti,datarate = <4>;
+			ti,gain = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
index 9f33419c260b..3525cbcda57f 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
@@ -10,7 +10,6 @@
 
 / {
 	model = "Toradex Colibri iMX6DL/S Module";
-	compatible = "toradex,colibri_imx6dl", "fsl,imx6dl";
 
 	aliases {
 		mmc0 = &usdhc3; /* eMMC */
@@ -588,7 +587,6 @@
 			st,settling = <3>;
 			/* 5 ms touch detect interrupt delay */
 			st,touch-det-delay = <5>;
-			status = "disabled";
 		};
 
 		stmpe_adc: stmpe_adc {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
index 8cefda70db63..ee2c6bec92e8 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-mba6.dtsi
@@ -124,7 +124,7 @@
 		compatible = "fsl,imx-audio-tlv320aic32x4";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_audmux>;
-		model = "imx-audio-tlv320aic32x4";
+		model = "tqm-tlv320aic32";
 		ssi-controller = <&ssi1>;
 		audio-codec = <&tlv320aic32x4>;
 		audio-asrc = <&asrc>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6.dtsi
index 6152a9ed4768..07492f63a1f8 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6.dtsi
@@ -7,16 +7,6 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 
-/ {
-	reg_3p3v: regulator-3p3v {
-		compatible = "regulator-fixed";
-		regulator-name = "supply-3p3v";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-	};
-};
-
 &ecspi1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_ecspi1>;
@@ -25,11 +15,16 @@
 
 	m25p80: flash@0 {
 		compatible = "jedec,spi-nor";
-		spi-max-frequency = <50000000>;
 		reg = <0>;
-		#address-cells = <1>;
-		#size-cells = <1>;
+		spi-max-frequency = <50000000>;
+		vcc-supply = <&sw4_reg>;
 		m25p,fast-read;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
 	};
 };
 
@@ -119,7 +114,7 @@
 		};
 
 		sw4_reg: sw4 {
-			regulator-min-microvolt = <800000>;
+			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 			regulator-always-on;
 		};
@@ -183,7 +178,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	vmmc-supply = <&reg_3p3v>;
+	vmmc-supply = <&sw4_reg>;
 	non-removable;
 	disable-wp;
 	no-sd;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6a.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6a.dtsi
index 828996382f24..e8fd37dd8835 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6a.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6a.dtsi
@@ -30,14 +30,14 @@
 	temperature-sensor@48 {
 		compatible = "national,lm75a";
 		reg = <0x48>;
-		vs-supply = <&reg_3p3v>;
+		vs-supply = <&sw4_reg>;
 	};
 
 	eeprom@50 {
 		compatible = "st,24c64", "atmel,24c64";
 		reg = <0x50>;
 		pagesize = <32>;
-		vcc-supply = <&reg_3p3v>;
+		vcc-supply = <&sw4_reg>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6b.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6b.dtsi
index 1d0966b8d99e..0e404c1f62f2 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6b.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-tqma6b.dtsi
@@ -23,14 +23,14 @@
 	temperature-sensor@48 {
 		compatible = "national,lm75a";
 		reg = <0x48>;
-		vs-supply = <&reg_3p3v>;
+		vs-supply = <&sw4_reg>;
 	};
 
 	eeprom@50 {
 		compatible = "st,24c64", "atmel,24c64";
 		reg = <0x50>;
 		pagesize = <32>;
-		vcc-supply = <&reg_3p3v>;
+		vcc-supply = <&sw4_reg>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
index 0e839bbfea08..911ccbd132cf 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
@@ -62,6 +62,33 @@
 		gpios = <&gpio_spi 3 GPIO_ACTIVE_LOW>;
 	};
 
+	reg_audio_5v: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	sound-wm8960 {
 		compatible = "fsl,imx-audio-wm8960";
 		model = "wm8960-audio";
@@ -139,6 +166,11 @@
 		wlf,gpio-cfg = <1 3>;
 		clocks = <&clks IMX6UL_CLK_SAI2>;
 		clock-names = "mclk";
+		AVDD-supply = <&reg_audio_3v3>;
+		DBVDD-supply = <&reg_audio_1v8>;
+		DCVDD-supply = <&reg_audio_1v8>;
+		SPKVDD1-supply = <&reg_audio_5v>;
+		SPKVDD2-supply = <&reg_audio_5v>;
 	};
 
 	camera@3c {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
index f2386dcb9ff2..dda4fa91b2f2 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi
@@ -40,6 +40,9 @@
 			reg = <1>;
 			interrupt-parent = <&gpio4>;
 			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
+			micrel,led-mode = <1>;
+			clocks = <&clks IMX6UL_CLK_ENET_REF>;
+			clock-names = "rmii-ref";
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul-common.dtsi
index c9c0794f01a2..2dd635a615cb 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul-common.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul-common.dtsi
@@ -162,13 +162,18 @@
 	status = "okay";
 
 	flash0: flash@0 {
-		#address-cells = <1>;
-		#size-cells = <1>;
 		compatible = "jedec,spi-nor";
+		reg = <0>;
 		spi-max-frequency = <33000000>;
 		spi-rx-bus-width = <4>;
 		spi-tx-bus-width = <1>;
-		reg = <0>;
+		vcc-supply = <&reg_vldo4>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1-mba6ulx.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1-mba6ulx.dts
index f2a5f17f312e..2e7b96e7b791 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1-mba6ulx.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1-mba6ulx.dts
@@ -6,8 +6,9 @@
 
 /dts-v1/;
 
-#include "imx6ul-tqma6ul1.dtsi"
+#include "imx6ul-tqma6ul2.dtsi"
 #include "mba6ulx.dtsi"
+#include "imx6ul-tqma6ul1.dtsi"
 
 / {
 	model = "TQ-Systems TQMa6UL1 SoM on MBa6ULx board";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1.dtsi
index 24192d012ef7..79c8c5529135 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-tqma6ul1.dtsi
@@ -4,8 +4,6 @@
  * Author: Markus Niebel <Markus.Niebel@tq-group.com>
  */
 
-#include "imx6ul-tqma6ul2.dtsi"
-
 / {
 	model = "TQ-Systems TQMa6UL1 SoM";
 	compatible = "tq,imx6ul-tqma6ul1", "fsl,imx6ul";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-var-som-concerto.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-var-som-concerto.dts
new file mode 100644
index 000000000000..9ff3b374a2b3
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-var-som-concerto.dts
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Support for Variscite MX6 Concerto Carrier board with the VAR-SOM-MX6UL
+ * Variscite SoM mounted on it
+ *
+ * Copyright 2019 Variscite Ltd.
+ * Copyright 2025 Bootlin
+ */
+
+#include "imx6ul-var-som.dtsi"
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "Variscite VAR-SOM-MX6UL Concerto Board";
+	compatible = "variscite,mx6ulconcerto", "variscite,var-som-imx6ul", "fsl,imx6ul";
+
+	chosen {
+		stdout-path = &uart1;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_key_back>, <&pinctrl_gpio_key_wakeup>;
+
+		key-back {
+			gpios = <&gpio4 14 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_BACK>;
+		};
+
+		key-wakeup {
+			gpios = <&gpio5 8 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_WAKEUP>;
+			wakeup-source;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_leds>;
+
+		led-0 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+			label = "gpled2";
+			gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+};
+
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	status = "okay";
+};
+
+&fec1 {
+	status = "disabled";
+};
+
+&fec2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet2>, <&pinctrl_enet2_gpio>, <&pinctrl_enet2_mdio>;
+	phy-mode = "rmii";
+	phy-handle = <&ethphy1>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy1: ethernet-phy@3 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <3>;
+			clocks = <&rmii_ref_clk>;
+			clock-names = "rmii-ref";
+			reset-gpios = <&gpio5 5 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <100000>;
+			micrel,led-mode = <0>;
+			micrel,rmii-reference-clock-select-25-mhz = <1>;
+		};
+	};
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	status = "okay";
+
+	rtc@68 {
+		/*
+		 * To actually use this interrupt
+		 * connect pins J14.8 & J14.10 on the Concerto-Board.
+		 */
+		compatible = "dallas,ds1337";
+		reg = <0x68>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_rtc>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <10 IRQ_TYPE_EDGE_FALLING>;
+	};
+};
+
+&iomuxc {
+	pinctrl_enet2: enet2grp {
+		fsl,pins = <
+			MX6UL_PAD_ENET2_RX_EN__ENET2_RX_EN	0x1b0b0
+			MX6UL_PAD_ENET2_RX_ER__ENET2_RX_ER	0x1b0b0
+			MX6UL_PAD_ENET2_RX_DATA0__ENET2_RDATA00	0x1b0b0
+			MX6UL_PAD_ENET2_RX_DATA1__ENET2_RDATA01	0x1b0b0
+			MX6UL_PAD_ENET2_TX_EN__ENET2_TX_EN	0x1b0b0
+			MX6UL_PAD_ENET2_TX_DATA0__ENET2_TDATA00	0x1b0b0
+			MX6UL_PAD_ENET2_TX_DATA1__ENET2_TDATA01	0x1b0b0
+			MX6UL_PAD_ENET2_TX_CLK__ENET2_REF_CLK2	0x4001b031
+		>;
+	};
+
+	pinctrl_enet2_gpio: enet2-gpiogrp {
+		fsl,pins = <
+			MX6UL_PAD_SNVS_TAMPER5__GPIO5_IO05	0x1b0b0 /* fec2 reset */
+		>;
+	};
+
+	pinctrl_enet2_mdio: enet2-mdiogrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO06__ENET2_MDIO	0x1b0b0
+			MX6UL_PAD_GPIO1_IO07__ENET2_MDC		0x1b0b0
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX6UL_PAD_UART3_RTS_B__FLEXCAN1_RX	0x1b020
+			MX6UL_PAD_UART3_CTS_B__FLEXCAN1_TX	0x1b020
+		>;
+	};
+
+	pinctrl_gpio_key_back: gpio-key-backgrp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_CE1_B__GPIO4_IO14	0x17059
+		>;
+	};
+
+	pinctrl_gpio_leds: gpio-ledsgrp {
+		fsl,pins = <
+			MX6UL_PAD_UART3_RX_DATA__GPIO1_IO25	0x1b0b0	/* GPLED2 */
+		>;
+	};
+
+	pinctrl_gpio_key_wakeup: gpio-keys-wakeupgrp {
+		fsl,pins = <
+			MX6UL_PAD_SNVS_TAMPER8__GPIO5_IO08	0x17059
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX6UL_PAD_CSI_PIXCLK__I2C1_SCL		0x4001b8b0
+			MX6UL_PAD_CSI_MCLK__I2C1_SDA		0x4001b8b0
+		>;
+	};
+
+	pinctrl_pwm4: pwm4grp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO05__PWM4_OUT		0x110b0
+		>;
+	};
+
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX6UL_PAD_JTAG_MOD__GPIO1_IO10		0x1b0b0 /* RTC alarm IRQ */
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX6UL_PAD_UART1_TX_DATA__UART1_DCE_TX	0x1b0b1
+			MX6UL_PAD_UART1_RX_DATA__UART1_DCE_RX	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart5: uart5grp {
+		fsl,pins = <
+			MX6UL_PAD_CSI_DATA00__UART5_DCE_TX	0x1b0b1
+			MX6UL_PAD_CSI_DATA01__UART5_DCE_RX	0x1b0b1
+			MX6UL_PAD_GPIO1_IO09__UART5_DCE_CTS	0x1b0b1
+			MX6UL_PAD_GPIO1_IO08__UART5_DCE_RTS	0x1b0b1
+		>;
+	};
+
+	pinctrl_usb_otg1_id: usbotg1idgrp {
+		fsl,pins = <
+			MX6UL_PAD_UART3_TX_DATA__ANATOP_OTG1_ID	0x17059
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD		0x17059
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK		0x17059
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0	0x17059
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1	0x17059
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2	0x17059
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3	0x17059
+		>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1-100mhzgrp {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD		0x170b9
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK		0x100b9
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0	0x170b9
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1	0x170b9
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2	0x170b9
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3	0x170b9
+		>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1-200mhzgrp {
+		fsl,pins = <
+			MX6UL_PAD_SD1_CMD__USDHC1_CMD		0x170f9
+			MX6UL_PAD_SD1_CLK__USDHC1_CLK		0x100f9
+			MX6UL_PAD_SD1_DATA0__USDHC1_DATA0	0x170f9
+			MX6UL_PAD_SD1_DATA1__USDHC1_DATA1	0x170f9
+			MX6UL_PAD_SD1_DATA2__USDHC1_DATA2	0x170f9
+			MX6UL_PAD_SD1_DATA3__USDHC1_DATA3	0x170f9
+		>;
+	};
+
+	pinctrl_usdhc1_gpio: usdhc1-gpiogrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO00__GPIO1_IO00	0x1b0b1 /* CD */
+		>;
+	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO01__WDOG1_WDOG_B	0x78b0
+		>;
+	};
+};
+
+&pwm4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm4>;
+	status = "okay";
+};
+
+&snvs_pwrkey {
+	status = "disabled";
+};
+
+&snvs_rtc {
+	status = "disabled";
+};
+
+&tsc {
+	/*
+	 * Conflics with wdog1 ext-reset-output & SD CD pins,
+	 * so we keep it disabled by default.
+	 */
+	status = "disabled";
+};
+
+/* Console UART */
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+/* ttymxc4 UART */
+&uart5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart5>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&usbotg1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usb_otg1_id>;
+	dr_mode = "otg";
+	disable-over-current;
+	srp-disable;
+	hnp-disable;
+	adp-disable;
+	status = "okay";
+};
+
+&usbotg2 {
+	dr_mode = "host";
+	disable-over-current;
+	status = "okay";
+};
+
+&usdhc1 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc1>, <&pinctrl_usdhc1_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc1_100mhz>, <&pinctrl_usdhc1_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc1_200mhz>, <&pinctrl_usdhc1_gpio>;
+	cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
+	no-1-8-v;
+	keep-power-in-suspend;
+	wakeup-source;
+	status = "okay";
+};
+
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	/*
+	 * To actually use ext-reset-output
+	 * connect pins J17.3 & J17.8 on the Concerto-Board
+	 */
+	fsl,ext-reset-output;
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-var-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-var-som.dtsi
new file mode 100644
index 000000000000..4e536e0252de
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-var-som.dtsi
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Support for Variscite VAR-SOM-MX6UL Module
+ *
+ * Copyright 2019 Variscite Ltd.
+ * Copyright 2025 Bootlin
+ */
+
+/dts-v1/;
+
+#include "imx6ul.dtsi"
+#include <dt-bindings/clock/imx6ul-clock.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Variscite VAR-SOM-MX6UL module";
+	compatible = "variscite,var-som-imx6ul", "fsl,imx6ul";
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>;
+	};
+
+	reg_gpio_dvfs: reg-gpio-dvfs {
+		compatible = "regulator-gpio";
+		regulator-min-microvolt = <1300000>;
+		regulator-max-microvolt = <1400000>;
+		regulator-name = "gpio_dvfs";
+		regulator-type = "voltage";
+		gpios = <&gpio4 13 GPIO_ACTIVE_HIGH>;
+		states = <1300000 0x1
+			  1400000 0x0>;
+	};
+
+	rmii_ref_clk: rmii-ref-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+		clock-output-names = "rmii-ref";
+	};
+};
+
+&clks {
+	assigned-clocks = <&clks IMX6UL_CLK_PLL4_AUDIO_DIV>;
+	assigned-clock-rates = <786432000>;
+};
+
+&cpu0 {
+	dc-supply = <&reg_gpio_dvfs>;
+};
+
+&fec1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet1>, <&pinctrl_enet1_gpio>, <&pinctrl_enet1_mdio>;
+	phy-mode = "rmii";
+	phy-handle = <&ethphy0>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@1 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <1>;
+			clocks = <&rmii_ref_clk>;
+			clock-names = "rmii-ref";
+			reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <100000>;
+			micrel,led-mode = <1>;
+			micrel,rmii-reference-clock-select-25-mhz = <1>;
+		};
+	};
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	pinctrl_enet1: enet1grp {
+		fsl,pins = <
+			MX6UL_PAD_ENET1_RX_EN__ENET1_RX_EN	0x1b0b0
+			MX6UL_PAD_ENET1_RX_ER__ENET1_RX_ER	0x1b0b0
+			MX6UL_PAD_ENET1_RX_DATA0__ENET1_RDATA00	0x1b0b0
+			MX6UL_PAD_ENET1_RX_DATA1__ENET1_RDATA01	0x1b0b0
+			MX6UL_PAD_ENET1_TX_EN__ENET1_TX_EN	0x1b0b0
+			MX6UL_PAD_ENET1_TX_DATA0__ENET1_TDATA00	0x1b0b0
+			MX6UL_PAD_ENET1_TX_DATA1__ENET1_TDATA01	0x1b0b0
+			MX6UL_PAD_ENET1_TX_CLK__ENET1_REF_CLK1	0x4001b031
+		>;
+	};
+
+	pinctrl_enet1_gpio: enet1-gpiogrp {
+		fsl,pins = <
+			MX6UL_PAD_SNVS_TAMPER0__GPIO5_IO00	0x1b0b0 /* fec1 reset */
+		>;
+	};
+
+	pinctrl_enet1_mdio: enet1-mdiogrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO06__ENET1_MDIO	0x1b0b0
+			MX6UL_PAD_GPIO1_IO07__ENET1_MDC		0x1b0b0
+		>;
+	};
+
+	pinctrl_hog: hoggrp {
+		fsl,pins = <
+			MX6UL_PAD_SNVS_TAMPER4__GPIO5_IO04	0x1b0b0	/* BT Enable */
+			MX6UL_PAD_SNVS_TAMPER6__GPIO5_IO06	0x03029	/* WLAN Enable */
+		>;
+	};
+
+	pinctrl_sai2: sai2grp {
+		fsl,pins = <
+			MX6UL_PAD_JTAG_TDI__SAI2_TX_BCLK	0x17088
+			MX6UL_PAD_JTAG_TDO__SAI2_TX_SYNC	0x17088
+			MX6UL_PAD_JTAG_TRST_B__SAI2_TX_DATA	0x11088
+			MX6UL_PAD_JTAG_TCK__SAI2_RX_DATA	0x11088
+			MX6UL_PAD_JTAG_TMS__SAI2_MCLK		0x17088
+		>;
+	};
+
+	pinctrl_tsc: tscgrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO01__GPIO1_IO01	0xb0
+			MX6UL_PAD_GPIO1_IO02__GPIO1_IO02	0xb0
+			MX6UL_PAD_GPIO1_IO03__GPIO1_IO03	0xb0
+			MX6UL_PAD_GPIO1_IO04__GPIO1_IO04	0xb0
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6UL_PAD_UART2_TX_DATA__UART2_DCE_TX	0x1b0b1
+			MX6UL_PAD_UART2_RX_DATA__UART2_DCE_RX	0x1b0b1
+			MX6UL_PAD_UART2_CTS_B__UART2_DCE_CTS	0x1b0b1
+			MX6UL_PAD_UART2_RTS_B__UART2_DCE_RTS	0x1b0b1
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_RE_B__USDHC2_CLK		0x10069
+			MX6UL_PAD_NAND_WE_B__USDHC2_CMD		0x17059
+			MX6UL_PAD_NAND_DATA00__USDHC2_DATA0	0x17059
+			MX6UL_PAD_NAND_DATA01__USDHC2_DATA1	0x17059
+			MX6UL_PAD_NAND_DATA02__USDHC2_DATA2	0x17059
+			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3	0x17059
+			MX6UL_PAD_NAND_DATA04__USDHC2_DATA4	0x17059
+			MX6UL_PAD_NAND_DATA05__USDHC2_DATA5	0x17059
+			MX6UL_PAD_NAND_DATA06__USDHC2_DATA6	0x17059
+			MX6UL_PAD_NAND_DATA07__USDHC2_DATA7	0x17059
+		>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_RE_B__USDHC2_CLK		0x100b9
+			MX6UL_PAD_NAND_WE_B__USDHC2_CMD		0x170b9
+			MX6UL_PAD_NAND_DATA00__USDHC2_DATA0	0x170b9
+			MX6UL_PAD_NAND_DATA01__USDHC2_DATA1	0x170b9
+			MX6UL_PAD_NAND_DATA02__USDHC2_DATA2	0x170b9
+			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3	0x170b9
+			MX6UL_PAD_NAND_DATA04__USDHC2_DATA4	0x170b9
+			MX6UL_PAD_NAND_DATA05__USDHC2_DATA5	0x170b9
+			MX6UL_PAD_NAND_DATA06__USDHC2_DATA6	0x170b9
+			MX6UL_PAD_NAND_DATA07__USDHC2_DATA7	0x170b9
+		>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+		fsl,pins = <
+			MX6UL_PAD_NAND_RE_B__USDHC2_CLK		0x100f9
+			MX6UL_PAD_NAND_WE_B__USDHC2_CMD		0x170f9
+			MX6UL_PAD_NAND_DATA00__USDHC2_DATA0	0x170f9
+			MX6UL_PAD_NAND_DATA01__USDHC2_DATA1	0x170f9
+			MX6UL_PAD_NAND_DATA02__USDHC2_DATA2	0x170f9
+			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3	0x170f9
+			MX6UL_PAD_NAND_DATA04__USDHC2_DATA4	0x170f9
+			MX6UL_PAD_NAND_DATA05__USDHC2_DATA5	0x170f9
+			MX6UL_PAD_NAND_DATA06__USDHC2_DATA6	0x170f9
+			MX6UL_PAD_NAND_DATA07__USDHC2_DATA7	0x170f9
+		>;
+	};
+};
+
+&pxp {
+	status = "okay";
+};
+
+&sai2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai2>;
+	assigned-clocks = <&clks IMX6UL_CLK_SAI2_SEL>,
+			  <&clks IMX6UL_CLK_SAI2>;
+	assigned-clock-parents = <&clks IMX6UL_CLK_PLL4_AUDIO_DIV>;
+	assigned-clock-rates = <0>, <12288000>;
+	fsl,sai-mclk-direction-output;
+	status = "okay";
+};
+
+&snvs_poweroff {
+	status = "okay";
+};
+
+&tsc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_tsc>;
+	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
+	measure-delay-time = <0xffff>;
+	pre-charge-time = <0xfff>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>;
+	bus-width = <8>;
+	no-1-8-v;
+	non-removable;
+	keep-power-in-suspend;
+	wakeup-source;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
index 576a7df505d3..4d948a9757f9 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
@@ -170,7 +170,7 @@
 
 	sound {
 		compatible = "fsl,imx-audio-tlv320aic32x4";
-		model = "imx-audio-tlv320aic32x4";
+		model = "tqm-tlv320aic32";
 		ssi-controller = <&sai1>;
 		audio-codec = <&tlv320aic32x4>;
 		audio-routing =
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
index aa8f65cd4adf..2966a33bc528 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
@@ -265,6 +265,13 @@
 		spi-max-frequency = <29000000>;
 		spi-rx-bus-width = <4>;
 		spi-tx-bus-width = <4>;
+		vcc-supply = <&vgen4_reg>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts b/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts
index 6cde84636900..17236f90ab33 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-sdb.dts
@@ -143,6 +143,33 @@
 		gpio = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	};
 
+	reg_audio_5v: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	backlight: backlight {
 		compatible = "pwm-backlight";
 		pwms = <&pwm1 0 5000000 0>;
@@ -406,6 +433,11 @@
 				  <&clks IMX7D_AUDIO_MCLK_ROOT_DIV>;
 		assigned-clock-parents = <&clks IMX7D_PLL_AUDIO_POST_DIV>;
 		assigned-clock-rates = <0>, <884736000>, <12288000>;
+		AVDD-supply = <&reg_audio_3v3>;
+		DBVDD-supply = <&reg_audio_1v8>;
+		DCVDD-supply = <&reg_audio_1v8>;
+		SPKVDD1-supply = <&reg_audio_5v>;
+		SPKVDD2-supply = <&reg_audio_5v>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
index 22dd72499ef2..2629968001a7 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
@@ -176,6 +176,34 @@
 			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
+	video_mux: csi-mux {
+		compatible = "video-mux";
+		mux-controls = <&mux 0>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+
+		port@0 {
+			reg = <0>;
+		};
+
+		port@1 {
+			reg = <1>;
+
+			csi_mux_from_mipi_vc0: endpoint {
+				remote-endpoint = <&mipi_vc0_to_csi_mux>;
+			};
+		};
+
+		port@2 {
+			reg = <2>;
+
+			csi_mux_to_csi: endpoint {
+				remote-endpoint = <&csi_from_csi_mux>;
+			};
+		};
+	};
+
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -529,34 +557,6 @@
 					#mux-control-cells = <1>;
 					mux-reg-masks = <0x14 0x00000010>;
 				};
-
-				video_mux: csi-mux {
-					compatible = "video-mux";
-					mux-controls = <&mux 0>;
-					#address-cells = <1>;
-					#size-cells = <0>;
-					status = "disabled";
-
-					port@0 {
-						reg = <0>;
-					};
-
-					port@1 {
-						reg = <1>;
-
-						csi_mux_from_mipi_vc0: endpoint {
-							remote-endpoint = <&mipi_vc0_to_csi_mux>;
-						};
-					};
-
-					port@2 {
-						reg = <2>;
-
-						csi_mux_to_csi: endpoint {
-							remote-endpoint = <&csi_from_csi_mux>;
-						};
-					};
-				};
 			};
 
 			ocotp: efuse@30350000 {
diff --git a/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi b/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
index 941d9860218e..67a3d484bc9f 100644
--- a/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/mba6ulx.dtsi
@@ -142,7 +142,7 @@
 
 	sound {
 		compatible = "fsl,imx-audio-tlv320aic32x4";
-		model = "imx-audio-tlv320aic32x4";
+		model = "tqm-tlv320aic32";
 		ssi-controller = <&sai1>;
 		audio-codec = <&tlv320aic32x4>;
 		audio-asrc = <&asrc>;
diff --git a/arch/arm/boot/dts/nxp/mxs/Makefile b/arch/arm/boot/dts/nxp/mxs/Makefile
index a430d04f9c69..96dd31ea19ba 100644
--- a/arch/arm/boot/dts/nxp/mxs/Makefile
+++ b/arch/arm/boot/dts/nxp/mxs/Makefile
@@ -8,6 +8,9 @@ dtb-$(CONFIG_ARCH_MXS) += \
 	imx28-apf28.dtb \
 	imx28-apf28dev.dtb \
 	imx28-apx4devkit.dtb \
+	imx28-btt3-0.dtb \
+	imx28-btt3-1.dtb \
+	imx28-btt3-2.dtb \
 	imx28-cfa10036.dtb \
 	imx28-cfa10037.dtb \
 	imx28-cfa10049.dtb \
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-btt3-0.dts b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-0.dts
new file mode 100644
index 000000000000..6ac46e4b21bb
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-0.dts
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024
+ * Lukasz Majewski, DENX Software Engineering, lukma@denx.de
+ */
+
+/dts-v1/;
+#include "imx28-btt3.dtsi"
+
+&hog_pins_rev {
+	fsl,pull-up = <MXS_PULL_ENABLE>;
+};
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-btt3-1.dts b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-1.dts
new file mode 100644
index 000000000000..213fe931c58b
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-1.dts
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024
+ * Lukasz Majewski, DENX Software Engineering, lukma@denx.de
+ */
+
+/dts-v1/;
+#include "imx28-btt3.dtsi"
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-btt3-2.dts b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-2.dts
new file mode 100644
index 000000000000..4bccd784d065
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-btt3-2.dts
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024
+ * Lukasz Majewski, DENX Software Engineering, lukma@denx.de
+ */
+
+/dts-v1/;
+#include "imx28-btt3.dtsi"
+
+/ {
+	panel {
+		compatible = "powertip,st7272", "panel-dpi";
+		power-supply = <&reg_3v3>;
+		width-mm = <70>;
+		height-mm = <52>;
+
+		panel-timing {
+			clock-frequency = <6500000>;
+			hactive = <320>;
+			vactive = <240>;
+			hfront-porch = <20>;
+			hback-porch = <68>;
+			hsync-len = <30>;
+			vfront-porch = <4>;
+			vback-porch = <14>;
+			vsync-len = <4>;
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-btt3.dtsi b/arch/arm/boot/dts/nxp/mxs/imx28-btt3.dtsi
new file mode 100644
index 000000000000..2c52e67e5c14
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-btt3.dtsi
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024
+ * Lukasz Majewski, DENX Software Engineering, lukma@denx.de
+ */
+/dts-v1/;
+#include "imx28-lwe.dtsi"
+
+/ {
+	model = "BTT3";
+
+	compatible = "lwn,imx28-btt3", "fsl,imx28";
+
+	chosen {
+	       bootargs = "root=/dev/mmcblk0p2 rootfstype=ext4 ro rootwait console=ttyAMA0,115200 panic=1 quiet";
+	};
+
+	memory@40000000 {
+		reg = <0x40000000 0x10000000>;
+		device_type = "memory";
+	};
+
+	panel {
+		compatible = "powertip,hx8238a", "panel-dpi";
+		power-supply = <&reg_3v3>;
+		width-mm = <70>;
+		height-mm = <52>;
+
+		panel-timing {
+			clock-frequency = <6500000>;
+			hactive = <320>;
+			vactive = <240>;
+			hfront-porch = <20>;
+			hback-porch = <38>;
+			hsync-len = <30>;
+			vfront-porch = <4>;
+			vback-porch = <14>;
+			vsync-len = <4>;
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <0>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&display_out>;
+			};
+		};
+	};
+
+	poweroff {
+		compatible = "gpio-poweroff";
+		gpios = <&gpio0 24 GPIO_ACTIVE_HIGH>;
+	};
+
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "BTTC Audio";
+		simple-audio-card,widgets = "Speaker", "BTTC Speaker";
+		simple-audio-card,routing = "BTTC Speaker", "SPKOUTN", "BTTC Speaker", "SPKOUTP";
+
+		simple-audio-card,dai-link@0 {
+			format = "left_j";
+			bitclock-master = <&dai0_master>;
+			frame-master = <&dai0_master>;
+			mclk-fs = <256>;
+
+			dai0_master: cpu {
+				sound-dai = <&saif0>;
+			};
+
+			codec {
+				sound-dai = <&wm89xx>;
+				clocks = <&saif0>;
+			};
+		};
+	};
+
+	wifi_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_en_pin_bttc>;
+		reset-gpios = <&gpio0 27 GPIO_ACTIVE_LOW>;
+		/* W1-163 needs 60us for WL_EN to be low and */
+		/* 150ms after high before downloading FW is possible */
+		post-power-on-delay-ms = <200>;
+		power-off-delay-us = <100>;
+	};
+};
+
+&auart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&auart0_2pins_a>;
+	status = "okay";
+};
+
+&auart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&auart3_pins_a>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&i2c0 {
+	wm89xx: audio-codec@1a {
+		compatible = "wlf,wm8940";
+		reg = <0x1a>;
+		#sound-dai-cells = <0>;
+	};
+};
+
+&lcdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&lcdif_24bit_pins_a>, <&lcdif_sync_pins_bttc>,
+		    <&lcdif_reset_pins_bttc>;
+	status = "okay";
+
+	port {
+		display_out: endpoint {
+			remote-endpoint = <&panel_in>;
+		};
+	};
+};
+
+&mac0 {
+	clocks = <&clks 57>, <&clks 57>, <&clks 64>;
+	clock-names = "ipg", "ahb", "enet_out";
+	phy-handle = <&mac0_phy>;
+	phy-mode = "rmii";
+	phy-supply = <&reg_3v3>;
+	/*
+	 * This MAC address is adjusted during production.
+	 * Value specified below is used as a fallback during recovery.
+	 */
+	local-mac-address = [ 00 11 B8 00 BF 8A ];
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		mac0_phy: ethernet-phy@0 {
+			/* LAN8720Ai - PHY ID */
+			compatible = "ethernet-phy-id0007.c0f0","ethernet-phy-ieee802.3-c22";
+			reg = <0>;
+			smsc,disable-energy-detect;
+			max-speed = <100>;
+			reset-gpios = <&gpio4 12 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <1000>;
+			reset-deassert-us = <1000>;
+		};
+	};
+};
+
+&pinctrl {
+	pinctrl-names = "default";
+	pinctrl-0 = <&hog_pins_a>, <&hog_pins_rev>;
+
+	hog_pins_a: hog@0 {
+		reg = <0>;
+		fsl,pinmux-ids = <
+			MX28_PAD_GPMI_RDY2__GPIO_0_22
+			MX28_PAD_GPMI_RDY3__GPIO_0_23
+			MX28_PAD_GPMI_RDN__GPIO_0_24
+			MX28_PAD_LCD_VSYNC__GPIO_1_28
+			MX28_PAD_SSP2_SS1__GPIO_2_20
+			MX28_PAD_SSP2_SS2__GPIO_2_21
+			MX28_PAD_AUART2_CTS__GPIO_3_10
+			MX28_PAD_AUART2_RTS__GPIO_3_11
+			MX28_PAD_GPMI_WRN__GPIO_0_25
+			MX28_PAD_ENET0_RXD2__GPIO_4_9
+			MX28_PAD_ENET0_TXD2__GPIO_4_11
+		>;
+		fsl,drive-strength = <MXS_DRIVE_4mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_DISABLE>;
+	};
+
+	hog_pins_rev: hog@1 {
+		reg = <1>;
+		fsl,pinmux-ids = <
+			MX28_PAD_ENET0_RXD3__GPIO_4_10
+			MX28_PAD_ENET0_TX_CLK__GPIO_4_5
+			MX28_PAD_ENET0_COL__GPIO_4_14
+			MX28_PAD_ENET0_CRS__GPIO_4_15
+		>;
+		fsl,drive-strength = <MXS_DRIVE_4mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_DISABLE>;
+	};
+
+	keypad_pins_bttc: keypad-bttc@0 {
+		reg = <0>;
+		fsl,pinmux-ids = <
+			MX28_PAD_GPMI_D00__GPIO_0_0
+			MX28_PAD_AUART0_CTS__GPIO_3_2
+			MX28_PAD_AUART0_RTS__GPIO_3_3
+			MX28_PAD_GPMI_D03__GPIO_0_3
+			MX28_PAD_GPMI_D04__GPIO_0_4
+			MX28_PAD_GPMI_D05__GPIO_0_5
+			MX28_PAD_GPMI_D06__GPIO_0_6
+			MX28_PAD_GPMI_D07__GPIO_0_7
+			MX28_PAD_GPMI_CE1N__GPIO_0_17
+			MX28_PAD_GPMI_CE2N__GPIO_0_18
+			MX28_PAD_GPMI_CE3N__GPIO_0_19
+			MX28_PAD_GPMI_RDY0__GPIO_0_20
+		>;
+		fsl,drive-strength = <MXS_DRIVE_4mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_DISABLE>;
+	};
+
+	lcdif_sync_pins_bttc: lcdif-bttc@0 {
+		reg = <0>;
+		fsl,pinmux-ids = <
+			MX28_PAD_LCD_DOTCLK__LCD_DOTCLK
+			MX28_PAD_LCD_ENABLE__LCD_ENABLE
+			MX28_PAD_LCD_HSYNC__LCD_HSYNC
+			MX28_PAD_LCD_RD_E__LCD_VSYNC
+		>;
+		fsl,drive-strength = <MXS_DRIVE_4mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_DISABLE>;
+	};
+
+	lcdif_reset_pins_bttc: lcdif-bttc@1 {
+		reg = <1>;
+		fsl,pinmux-ids = <
+			MX28_PAD_LCD_RESET__GPIO_3_30
+		>;
+		fsl,drive-strength = <MXS_DRIVE_4mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_ENABLE>;
+	};
+
+	ssp1_sdio_pins_a: ssp1-sdio@0 {
+		reg = <0>;
+		fsl,pinmux-ids = <
+			MX28_PAD_SSP1_DATA0__SSP1_D0
+			MX28_PAD_GPMI_D01__SSP1_D1
+			MX28_PAD_GPMI_D02__SSP1_D2
+			MX28_PAD_SSP1_DATA3__SSP1_D3
+			MX28_PAD_SSP1_CMD__SSP1_CMD
+			MX28_PAD_SSP1_SCK__SSP1_SCK
+		>;
+		fsl,drive-strength = <MXS_DRIVE_8mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_ENABLE>;
+	};
+
+	wifi_en_pin_bttc: wifi-en-pin@0 {
+		reg = <0>;
+		fsl,pinmux-ids = <
+			MX28_PAD_GPMI_CLE__GPIO_0_27
+		>;
+		fsl,drive-strength = <MXS_DRIVE_8mA>;
+		fsl,voltage = <MXS_VOLTAGE_HIGH>;
+		fsl,pull-up = <MXS_PULL_ENABLE>;
+	};
+};
+
+&pwm {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm3_pins_a>;
+	status = "okay";
+};
+
+&reg_usb_5v {
+	gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+};
+
+&saif0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&saif0_pins_a>;
+	#sound-dai-cells = <0>;
+	assigned-clocks = <&clks 53>;
+	assigned-clock-rates = <12000000>;
+	status = "okay";
+};
+
+&saif1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&saif1_pins_a>;
+	#sound-dai-cells = <0>;
+	fsl,saif-master = <&saif0>;
+	status = "okay";
+};
+
+&ssp1 {
+	compatible = "fsl,imx28-mmc";
+	pinctrl-names = "default";
+	pinctrl-0 = <&ssp1_sdio_pins_a>;
+	bus-width = <4>;
+	no-1-8-v;       /* force 3.3V VIO */
+	non-removable;
+	vmmc-supply = <&reg_3v3>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	keep-power-in-suspend;
+	status = "okay";
+
+	wlan@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+	};
+};
+
+&ssp2 {
+	compatible = "fsl,imx28-spi";
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2_pins_a>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-sps1.dts b/arch/arm/boot/dts/nxp/mxs/imx28-sps1.dts
index 0f01dded4e3d..ca62e7933116 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-sps1.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-sps1.dts
@@ -24,30 +24,25 @@
 	};
 
 	leds {
-		#address-cells = <1>;
-		#size-cells = <0>;
 		compatible = "gpio-leds";
 		status = "okay";
 
-		led@1 {
+		led-1 {
 			label = "sps1-1:yellow:user";
 			gpios = <&gpio0 6 0>;
 			linux,default-trigger = "heartbeat";
-			reg = <0>;
 		};
 
-		led@2 {
+		led-2 {
 			label = "sps1-2:red:user";
 			gpios = <&gpio0 3 0>;
 			linux,default-trigger = "heartbeat";
-			reg = <1>;
 		};
 
-		led@3 {
+		led-3 {
 			label = "sps1-3:red:user";
 			gpios = <&gpio0 0 0>;
-			default-trigger = "heartbeat";
-			reg = <2>;
+			linux,default-trigger = "heartbeat";
 		};
 
 	};
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts b/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
index 722182f5fd17..2492fb99956c 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-bk4.dts
@@ -119,7 +119,7 @@
 	status = "okay";
 
 	spidev0@0 {
-		compatible = "lwn,bk4";
+		compatible = "lwn,bk4-spi";
 		spi-max-frequency = <30000000>;
 		reg = <0>;
 		fsl,spi-cs-sck-delay = <200>;
@@ -136,7 +136,7 @@
 	#address-cells = <0>;
 
 	slave {
-		compatible = "lwn,bk4";
+		compatible = "lwn,bk4-spi";
 		spi-max-frequency = <30000000>;
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-colibri.dtsi b/arch/arm/boot/dts/nxp/vf/vf610-colibri.dtsi
index 607cec2df861..20aed3946214 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/vf/vf610-colibri.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	model = "Toradex Colibri VF61 COM";
-	compatible = "toradex,vf610-colibri_vf61", "fsl,vf610";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-c.dts
index 6f9878f124c4..4f99044837f8 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-c.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-c.dts
@@ -392,7 +392,7 @@
 };
 
 &gpio0 {
-	eth0_intrp {
+	eth0-intrp-hog {
 		gpio-hog;
 		gpios = <23 GPIO_ACTIVE_HIGH>;
 		input;
@@ -401,7 +401,7 @@
 };
 
 &gpio3 {
-	eth0_intrp {
+	eth0-intrp-hog {
 		gpio-hog;
 		gpios = <2 GPIO_ACTIVE_HIGH>;
 		input;
diff --git a/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi b/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi
index acccf9a3c898..597f20be82f1 100644
--- a/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi
+++ b/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi
@@ -158,8 +158,8 @@
 				clocks = <&clks VF610_CLK_DSPI0>;
 				clock-names = "dspi";
 				spi-num-chipselects = <6>;
-				dmas = <&edma1 1 12>, <&edma1 1 13>;
-				dma-names = "rx", "tx";
+				dmas = <&edma1 1 13>, <&edma1 1 12>;
+				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 
@@ -172,8 +172,8 @@
 				clocks = <&clks VF610_CLK_DSPI1>;
 				clock-names = "dspi";
 				spi-num-chipselects = <4>;
-				dmas = <&edma1 1 14>, <&edma1 1 15>;
-				dma-names = "rx", "tx";
+				dmas = <&edma1 1 15>, <&edma1 1 14>;
+				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 
@@ -529,9 +529,8 @@
 				clocks = <&clks VF610_CLK_DSPI2>;
 				clock-names = "dspi";
 				spi-num-chipselects = <2>;
-				dmas = <&edma1 0 10>,
-					<&edma1 0 11>;
-				dma-names = "rx", "tx";
+				dmas = <&edma1 0 11>, <&edma1 0 10>;
+				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 
@@ -544,8 +543,8 @@
 				clocks = <&clks VF610_CLK_DSPI3>;
 				clock-names = "dspi";
 				spi-num-chipselects = <2>;
-				dmas = <&edma1 0 12>, <&edma1 0 13>;
-				dma-names = "rx", "tx";
+				dmas = <&edma1 0 13>, <&edma1 0 12>;
+				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 
@@ -725,13 +724,13 @@
 				clocks = <&clks VF610_CLK_CAAM>;
 				clock-names = "ipg";
 
-				sec_jr0: jr0@1000 {
+				sec_jr0: jr@1000 {
 					compatible = "fsl,sec-v4.0-job-ring";
 					reg = <0x1000 0x1000>;
 					interrupts = <102 IRQ_TYPE_LEVEL_HIGH>;
 				};
 
-				sec_jr1: jr1@2000 {
+				sec_jr1: jr@2000 {
 					compatible = "fsl,sec-v4.0-job-ring";
 					reg = <0x2000 0x1000>;
 					interrupts = <102 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
index 3bce5876a9d8..4f002aa7fbaf 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
@@ -754,6 +754,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
index d7c0a9574ce8..b1e20579e071 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
@@ -268,6 +268,7 @@
 &scifa0 {
 	pinctrl-0 = <&scifa0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7790.dtsi b/arch/arm/boot/dts/renesas/r8a7790.dtsi
index f746f0b9e686..4f97c09dbc9f 100644
--- a/arch/arm/boot/dts/renesas/r8a7790.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7790.dtsi
@@ -227,6 +227,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board. */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -265,6 +266,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -374,6 +376,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7790";
 			reg = <0 0xe6060000 0 0x250>;
+			bootph-all;
 		};
 
 		tpu: pwm@e60f0000 {
@@ -395,6 +398,7 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		apmu@e6151000 {
@@ -412,6 +416,7 @@
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7790-rst";
 			reg = <0 0xe6160000 0 0x0100>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1948,6 +1953,7 @@
 		prr: chipid@ff000044 {
 			compatible = "renesas,prr";
 			reg = <0 0xff000044 0 4>;
+			bootph-all;
 		};
 
 		cmt0: timer@ffca0000 {
@@ -2018,5 +2024,6 @@
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
+		bootph-all;
 	};
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
index e4e1d9c98c61..e9f90fa44d55 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
@@ -679,6 +679,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
index 08381498350a..f518eadd8b9c 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
@@ -312,6 +312,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7791.dtsi b/arch/arm/boot/dts/renesas/r8a7791.dtsi
index e57567adff55..5023b41c28b3 100644
--- a/arch/arm/boot/dts/renesas/r8a7791.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7791.dtsi
@@ -125,6 +125,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board. */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -152,6 +153,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -291,6 +293,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7791";
 			reg = <0 0xe6060000 0 0x250>;
+			bootph-all;
 		};
 
 		tpu: pwm@e60f0000 {
@@ -312,6 +315,7 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		apmu@e6152000 {
@@ -323,6 +327,7 @@
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7791-rst";
 			reg = <0 0xe6160000 0 0x0100>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1875,6 +1880,7 @@
 		prr: chipid@ff000044 {
 			compatible = "renesas,prr";
 			reg = <0 0xff000044 0 4>;
+			bootph-all;
 		};
 
 		cmt0: timer@ffca0000 {
@@ -1945,5 +1951,6 @@
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
+		bootph-all;
 	};
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
index a3986076d8e3..23ec0f8a6651 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
@@ -301,6 +301,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7792-wheat.dts b/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
index bfc780f7e396..93bd81723c8f 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-wheat.dts
@@ -183,6 +183,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7792.dtsi b/arch/arm/boot/dts/renesas/r8a7792.dtsi
index 08cbe6c13cee..7513afc1c958 100644
--- a/arch/arm/boot/dts/renesas/r8a7792.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7792.dtsi
@@ -82,6 +82,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board. */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	lbsc: bus {
@@ -109,6 +110,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -308,6 +310,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7792";
 			reg = <0 0xe6060000 0 0x144>;
+			bootph-all;
 		};
 
 		cpg: clock-controller@e6150000 {
@@ -318,6 +321,7 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		apmu@e6152000 {
@@ -329,6 +333,7 @@
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7792-rst";
 			reg = <0 0xe6160000 0 0x0100>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -947,6 +952,7 @@
 		prr: chipid@ff000044 {
 			compatible = "renesas,prr";
 			reg = <0 0xff000044 0 4>;
+			bootph-all;
 		};
 
 		cmt0: timer@ffca0000 {
diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
index 2c05d7c2b377..45b267ec2679 100644
--- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
@@ -642,6 +642,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7793.dtsi b/arch/arm/boot/dts/renesas/r8a7793.dtsi
index e48e43cc6b03..fc6d3bcca296 100644
--- a/arch/arm/boot/dts/renesas/r8a7793.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7793.dtsi
@@ -117,6 +117,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board. */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pmu {
@@ -137,6 +138,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -276,6 +278,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7793";
 			reg = <0 0xe6060000 0 0x250>;
+			bootph-all;
 		};
 
 		/* Special CPG clocks */
@@ -287,6 +290,7 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		apmu@e6152000 {
@@ -298,6 +302,7 @@
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7793-rst";
 			reg = <0 0xe6160000 0 0x0100>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1454,6 +1459,7 @@
 		prr: chipid@ff000044 {
 			compatible = "renesas,prr";
 			reg = <0 0xff000044 0 4>;
+			bootph-all;
 		};
 
 		cmt0: timer@ffca0000 {
@@ -1524,5 +1530,6 @@
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
+		bootph-all;
 	};
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
index f70e26aa83a0..3f06a7f67d62 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
@@ -479,6 +479,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
index 2a0819311a3c..342825605768 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
@@ -394,6 +394,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/renesas/r8a7794.dtsi b/arch/arm/boot/dts/renesas/r8a7794.dtsi
index bc16c896c0f9..92010d09f6c4 100644
--- a/arch/arm/boot/dts/renesas/r8a7794.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7794.dtsi
@@ -99,6 +99,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board. */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pmu {
@@ -119,6 +120,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -243,6 +245,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7794";
 			reg = <0 0xe6060000 0 0x11c>;
+			bootph-all;
 		};
 
 		cpg: clock-controller@e6150000 {
@@ -253,6 +256,7 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		apmu@e6151000 {
@@ -264,6 +268,7 @@
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7794-rst";
 			reg = <0 0xe6160000 0 0x0100>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1440,6 +1445,7 @@
 		prr: chipid@ff000044 {
 			compatible = "renesas,prr";
 			reg = <0 0xff000044 0 4>;
+			bootph-all;
 		};
 
 		cmt0: timer@ffca0000 {
@@ -1491,5 +1497,6 @@
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <48000000>;
+		bootph-all;
 	};
 };
diff --git a/arch/arm/boot/dts/renesas/r9a06g032.dtsi b/arch/arm/boot/dts/renesas/r9a06g032.dtsi
index 7548291c8d7e..87e03446fb4d 100644
--- a/arch/arm/boot/dts/renesas/r9a06g032.dtsi
+++ b/arch/arm/boot/dts/renesas/r9a06g032.dtsi
@@ -211,8 +211,8 @@
 			reg-io-width = <4>;
 			clocks = <&sysctrl R9A06G032_CLK_UART3>, <&sysctrl R9A06G032_HCLK_UART3>;
 			clock-names = "baudclk", "apb_pclk";
-			dmas = <&dmamux 0 0 0 0 0 1>, <&dmamux 1 0 0 0 1 1>;
-			dma-names = "rx", "tx";
+			dmas = <&dmamux 1 0 0 0 1 1>, <&dmamux 0 0 0 0 0 1>;
+			dma-names = "tx", "rx";
 			status = "disabled";
 		};
 
@@ -224,8 +224,8 @@
 			reg-io-width = <4>;
 			clocks = <&sysctrl R9A06G032_CLK_UART4>, <&sysctrl R9A06G032_HCLK_UART4>;
 			clock-names = "baudclk", "apb_pclk";
-			dmas = <&dmamux 2 0 0 0 2 1>, <&dmamux 3 0 0 0 3 1>;
-			dma-names = "rx", "tx";
+			dmas = <&dmamux 3 0 0 0 3 1>, <&dmamux 2 0 0 0 2 1>;
+			dma-names = "tx", "rx";
 			status = "disabled";
 		};
 
@@ -237,8 +237,8 @@
 			reg-io-width = <4>;
 			clocks = <&sysctrl R9A06G032_CLK_UART5>, <&sysctrl R9A06G032_HCLK_UART5>;
 			clock-names = "baudclk", "apb_pclk";
-			dmas = <&dmamux 4 0 0 0 4 1>, <&dmamux 5 0 0 0 5 1>;
-			dma-names = "rx", "tx";
+			dmas = <&dmamux 5 0 0 0 5 1>, <&dmamux 4 0 0 0 4 1>;
+			dma-names = "tx", "rx";
 			status = "disabled";
 		};
 
@@ -250,8 +250,8 @@
 			reg-io-width = <4>;
 			clocks = <&sysctrl R9A06G032_CLK_UART6>, <&sysctrl R9A06G032_HCLK_UART6>;
 			clock-names = "baudclk", "apb_pclk";
-			dmas = <&dmamux 6 0 0 0 6 1>, <&dmamux 7 0 0 0 7 1>;
-			dma-names = "rx", "tx";
+			dmas = <&dmamux 7 0 0 0 7 1>, <&dmamux 6 0 0 0 6 1>;
+			dma-names = "tx", "rx";
 			status = "disabled";
 		};
 
@@ -263,8 +263,8 @@
 			reg-io-width = <4>;
 			clocks = <&sysctrl R9A06G032_CLK_UART7>, <&sysctrl R9A06G032_HCLK_UART7>;
 			clock-names = "baudclk", "apb_pclk";
-			dmas = <&dmamux 4 0 0 0 20 1>, <&dmamux 5 0 0 0 21 1>;
-			dma-names = "rx", "tx";
+			dmas = <&dmamux 5 0 0 0 21 1>, <&dmamux 4 0 0 0 20 1>;
+			dma-names = "tx", "rx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/st/Makefile b/arch/arm/boot/dts/st/Makefile
index b7d5d305cbbe..60d55516f723 100644
--- a/arch/arm/boot/dts/st/Makefile
+++ b/arch/arm/boot/dts/st/Makefile
@@ -29,6 +29,7 @@ dtb-$(CONFIG_ARCH_STM32) += \
 	stm32h743i-eval.dtb \
 	stm32h743i-disco.dtb \
 	stm32h750i-art-pi.dtb \
+	stm32mp133c-prihmb.dtb \
 	stm32mp135f-dhcor-dhsbc.dtb \
 	stm32mp135f-dk.dtb \
 	stm32mp151a-prtt1a.dtb \
@@ -37,8 +38,11 @@ dtb-$(CONFIG_ARCH_STM32) += \
 	stm32mp151a-dhcor-testbench.dtb \
 	stm32mp151c-mecio1r0.dtb \
 	stm32mp151c-mect1s.dtb \
+	stm32mp151c-plyaqm.dtb \
 	stm32mp153c-dhcom-drc02.dtb \
 	stm32mp153c-dhcor-drc-compact.dtb \
+	stm32mp153c-lxa-fairytux2-gen1.dtb \
+	stm32mp153c-lxa-fairytux2-gen2.dtb \
 	stm32mp153c-lxa-tac-gen3.dtb \
 	stm32mp153c-mecio1r1.dtb \
 	stm32mp157a-avenger96.dtb \
diff --git a/arch/arm/boot/dts/st/stm32f746-disco.dts b/arch/arm/boot/dts/st/stm32f746-disco.dts
index 087de6f09629..b57dbdce2f40 100644
--- a/arch/arm/boot/dts/st/stm32f746-disco.dts
+++ b/arch/arm/boot/dts/st/stm32f746-disco.dts
@@ -78,6 +78,24 @@
 		serial0 = &usart1;
 	};
 
+	leds {
+		compatible = "gpio-leds";
+		led-usr {
+			gpios = <&gpioi 1 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		autorepeat;
+		button-0 {
+			label = "User";
+			linux,code = <KEY_HOME>;
+			gpios = <&gpioi 11 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
 	usbotg_hs_phy: usb-phy {
 		#phy-cells = <0>;
 		compatible = "usb-nop-xceiv";
diff --git a/arch/arm/boot/dts/st/stm32f769-disco.dts b/arch/arm/boot/dts/st/stm32f769-disco.dts
index 52c5baf58ab9..535cfdc4681c 100644
--- a/arch/arm/boot/dts/st/stm32f769-disco.dts
+++ b/arch/arm/boot/dts/st/stm32f769-disco.dts
@@ -79,13 +79,16 @@
 
 	leds {
 		compatible = "gpio-leds";
-		led-green {
+		led-usr2 {
 			gpios = <&gpioj 5 GPIO_ACTIVE_HIGH>;
 			linux,default-trigger = "heartbeat";
 		};
-		led-red {
+		led-usr1 {
 			gpios = <&gpioj 13 GPIO_ACTIVE_HIGH>;
 		};
+		led-usr3 {
+			gpios = <&gpioa 12 GPIO_ACTIVE_HIGH>;
+		};
 	};
 
 	gpio-keys {
diff --git a/arch/arm/boot/dts/st/stm32mp131.dtsi b/arch/arm/boot/dts/st/stm32mp131.dtsi
index 0019d12c3d3d..8512a6e46b33 100644
--- a/arch/arm/boot/dts/st/stm32mp131.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp131.dtsi
@@ -100,6 +100,31 @@
 		always-on;
 	};
 
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&dts>;
+
+			trips {
+				cpu_alert1: cpu-alert1 {
+					temperature = <85000>;
+					hysteresis = <0>;
+					type = "passive";
+				};
+
+				cpu-crit {
+					temperature = <120000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+			};
+		};
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -919,6 +944,16 @@
 			};
 		};
 
+		dts: thermal@50028000 {
+			compatible = "st,stm32-thermal";
+			reg = <0x50028000 0x100>;
+			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&rcc DTS>;
+			clock-names = "pclk";
+			#thermal-sensor-cells = <0>;
+			status = "disabled";
+		};
+
 		mdma: dma-controller@58000000 {
 			compatible = "st,stm32h7-mdma";
 			reg = <0x58000000 0x1000>;
diff --git a/arch/arm/boot/dts/st/stm32mp133c-prihmb.dts b/arch/arm/boot/dts/st/stm32mp133c-prihmb.dts
new file mode 100644
index 000000000000..663b6de1b814
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32mp133c-prihmb.dts
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/regulator/st,stm32mp13-regulator.h>
+#include "stm32mp133.dtsi"
+#include "stm32mp13xc.dtsi"
+#include "stm32mp13-pinctrl.dtsi"
+
+/ {
+	model = "Priva E-Measuringbox board";
+	compatible = "pri,prihmb", "st,stm32mp133";
+
+	aliases {
+		ethernet0 = &ethernet1;
+		mdio-gpio0 = &mdio0;
+		mmc0 = &sdmmc1;
+		mmc1 = &sdmmc2;
+		serial0 = &uart4;
+		serial1 = &usart6;
+		serial2 = &uart7;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	counter-0 {
+		compatible = "interrupt-counter";
+		gpios = <&gpioa 11 GPIO_ACTIVE_HIGH>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		autorepeat;
+
+		button-reset {
+			label = "reset-button";
+			linux,code = <BTN_1>;
+			gpios = <&gpioi 7 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-blue {
+			function = LED_FUNCTION_HEARTBEAT;
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&gpioa 14 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "heartbeat";
+			default-state = "off";
+		};
+	};
+
+	led-controller-0 {
+		compatible = "pwm-leds-multicolor";
+
+		multi-led {
+			color = <LED_COLOR_ID_RGB>;
+			function = LED_FUNCTION_STATUS;
+			max-brightness = <255>;
+
+			led-red {
+				active-low;
+				color = <LED_COLOR_ID_RED>;
+				pwms = <&pwm2 2 1000000 1>;
+			};
+
+			led-green {
+				active-low;
+				color = <LED_COLOR_ID_GREEN>;
+				pwms = <&pwm1 1 1000000 1>;
+			};
+
+			led-blue {
+				active-low;
+				color = <LED_COLOR_ID_BLUE>;
+				pwms = <&pwm1 2 1000000 1>;
+			};
+		};
+	};
+
+	led-controller-1 {
+		compatible = "pwm-leds-multicolor";
+
+		multi-led {
+			color = <LED_COLOR_ID_RGB>;
+			function = LED_FUNCTION_STATUS;
+			max-brightness = <255>;
+
+			led-red {
+				active-low;
+				color = <LED_COLOR_ID_RED>;
+				pwms = <&pwm1 0 1000000 1>;
+			};
+
+			led-green {
+				active-low;
+				color = <LED_COLOR_ID_GREEN>;
+				pwms = <&pwm2 0 1000000 1>;
+			};
+
+			led-blue {
+				active-low;
+				color = <LED_COLOR_ID_BLUE>;
+				pwms = <&pwm2 1 1000000 1>;
+			};
+		};
+	};
+
+	/* DP83TD510E PHYs have max MDC rate of 1.75MHz. Since we can't reduce
+	 * stmmac MDC clock without reducing system bus rate, we need to use
+	 * gpio based MDIO bus.
+	 */
+	mdio0: mdio {
+		compatible = "virtual,mdio-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		gpios = <&gpiog 2 GPIO_ACTIVE_HIGH
+			 &gpioa 2 GPIO_ACTIVE_HIGH>;
+
+		/* TI DP83TD510E */
+		phy0: ethernet-phy@0 {
+			compatible = "ethernet-phy-id2000.0181";
+			reg = <0>;
+			interrupts-extended = <&gpioa 4 IRQ_TYPE_LEVEL_LOW>;
+			reset-gpios = <&gpioa 3 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <10>;
+			reset-deassert-us = <35>;
+		};
+	};
+
+	memory@c0000000 {
+		device_type = "memory";
+		reg = <0xc0000000 0x10000000>;
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		optee@ce000000 {
+			reg = <0xce000000 0x02000000>;
+			no-map;
+		};
+	};
+};
+
+&adc_1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&adc_1_pins_a>;
+	vdda-supply = <&reg_3v3>;
+	vref-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&adc1 {
+	status = "okay";
+
+	channel@0 { /* Fan current PC0*/
+		reg = <0>;
+		st,min-sample-time-ns = <10000>;  /* 10µs sampling time */
+	};
+	channel@11 { /* Fan voltage */
+		reg = <11>;
+		st,min-sample-time-ns = <10000>;  /* 10µs sampling time */
+	};
+	channel@15 { /* Supply voltage */
+		reg = <15>;
+		st,min-sample-time-ns = <10000>;  /* 10µs sampling time */
+	};
+};
+
+&dts {
+	status = "okay";
+};
+
+&ethernet1 {
+	status = "okay";
+	pinctrl-0 = <&ethernet1_rmii_pins_a>;
+	pinctrl-1 = <&ethernet1_rmii_sleep_pins_a>;
+	pinctrl-names = "default", "sleep";
+	phy-mode = "rmii";
+	phy-handle = <&phy0>;
+};
+
+&i2c1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2c1_pins_a>;
+	pinctrl-1 = <&i2c1_sleep_pins_a>;
+	clock-frequency = <100000>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+
+	board-sensor@48 {
+		compatible = "ti,tmp1075";
+		reg = <0x48>;
+		vs-supply = <&reg_3v3>;
+	};
+};
+
+&{i2c1_pins_a/pins} {
+	pinmux = <STM32_PINMUX('D', 3, AF5)>, /* I2C1_SCL */
+		 <STM32_PINMUX('B', 8, AF4)>; /* I2C1_SDA */
+	bias-disable;
+	drive-open-drain;
+	slew-rate = <0>;
+};
+
+&{i2c1_sleep_pins_a/pins} {
+	pinmux = <STM32_PINMUX('D', 3, ANALOG)>, /* I2C1_SCL */
+		 <STM32_PINMUX('B', 8, ANALOG)>; /* I2C1_SDA */
+};
+
+&iwdg2 {
+	timeout-sec = <32>;
+	status = "okay";
+};
+
+/* SD card without Card-detect */
+&sdmmc1 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc1_b4_pins_a &sdmmc1_clk_pins_a>;
+	pinctrl-1 = <&sdmmc1_b4_od_pins_a &sdmmc1_clk_pins_a>;
+	pinctrl-2 = <&sdmmc1_b4_sleep_pins_a>;
+	broken-cd;
+	no-sdio;
+	no-1-8-v;
+	st,neg-edge;
+	bus-width = <4>;
+	vmmc-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+/* EMMC */
+&sdmmc2 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_a &sdmmc2_clk_pins_a>;
+	pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_a &sdmmc2_clk_pins_a>;
+	pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_a>;
+	non-removable;
+	no-sd;
+	no-sdio;
+	no-1-8-v;
+	st,neg-edge;
+	mmc-ddr-3_3v;
+	bus-width = <8>;
+	vmmc-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&timers1 {
+	status = "okay";
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	pwm1: pwm {
+		pinctrl-0 = <&pwm1_pins_a>;
+		pinctrl-1 = <&pwm1_sleep_pins_a>;
+		pinctrl-names = "default", "sleep";
+		status = "okay";
+	};
+};
+
+&timers4 {
+	status = "okay";
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	pwm2: pwm {
+		pinctrl-0 = <&pwm4_pins_a>;
+		pinctrl-1 = <&pwm4_sleep_pins_a>;
+		pinctrl-names = "default", "sleep";
+		status = "okay";
+	};
+};
+
+/* Fan PWM */
+&timers5 {
+	status = "okay";
+
+	pwm3: pwm {
+		pinctrl-0 = <&pwm5_pins_a>;
+		pinctrl-1 = <&pwm5_sleep_pins_a>;
+		pinctrl-names = "default", "sleep";
+		status = "okay";
+	};
+};
+
+&timers2 {
+	status = "okay";
+
+	timer@1 {
+		status = "okay";
+	};
+};
+
+&uart4 {
+	pinctrl-names = "default", "sleep", "idle";
+	pinctrl-0 = <&uart4_pins_a>;
+	pinctrl-1 = <&uart4_sleep_pins_a>;
+	pinctrl-2 = <&uart4_idle_pins_a>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
+
+&uart7 {
+	pinctrl-names = "default", "sleep", "idle";
+	pinctrl-0 = <&uart7_pins_a>;
+	pinctrl-1 = <&uart7_sleep_pins_a>;
+	pinctrl-2 = <&uart7_idle_pins_a>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
+
+&usart6 {
+	pinctrl-names = "default", "sleep", "idle";
+	pinctrl-0 = <&usart6_pins_a>;
+	pinctrl-1 = <&usart6_sleep_pins_a>;
+	pinctrl-2 = <&usart6_idle_pins_a>;
+	linux,rs485-enabled-at-boot-time;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
+
+&pinctrl {
+	adc_1_pins_a: adc1-0 {
+		pins {
+			pinmux = <STM32_PINMUX('C', 0, ANALOG)>, /* ADC1 in0 */
+				 <STM32_PINMUX('C', 2, ANALOG)>, /* ADC1 in15 */
+				 <STM32_PINMUX('F', 13, ANALOG)>; /* ADC1 in11 */
+		};
+	};
+
+	ethernet1_rmii_pins_a: rmii-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('G', 13, AF11)>, /* ETH1_RMII_TXD0 */
+				 <STM32_PINMUX('G', 14, AF11)>, /* ETH1_RMII_TXD1 */
+				 <STM32_PINMUX('B', 11, AF11)>, /* ETH1_RMII_TX_EN */
+				 <STM32_PINMUX('A', 1, AF11)>;   /* ETH1_RMII_REF_CLK */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <2>;
+		};
+		pins2 {
+			pinmux = <STM32_PINMUX('C', 4, AF11)>,  /* ETH1_RMII_RXD0 */
+				 <STM32_PINMUX('C', 5, AF11)>,  /* ETH1_RMII_RXD1 */
+				 <STM32_PINMUX('A', 7, AF11)>;  /* ETH1_RMII_CRS_DV */
+			bias-disable;
+		};
+	};
+
+	ethernet1_rmii_sleep_pins_a: rmii-sleep-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('G', 13, ANALOG)>, /* ETH1_RMII_TXD0 */
+				 <STM32_PINMUX('G', 14, ANALOG)>, /* ETH1_RMII_TXD1 */
+				 <STM32_PINMUX('B', 11, ANALOG)>, /* ETH1_RMII_TX_EN */
+				 <STM32_PINMUX('C', 4, ANALOG)>,  /* ETH1_RMII_RXD0 */
+				 <STM32_PINMUX('C', 5, ANALOG)>,  /* ETH1_RMII_RXD1 */
+				 <STM32_PINMUX('A', 1, ANALOG)>,  /* ETH1_RMII_REF_CLK */
+				 <STM32_PINMUX('A', 7, ANALOG)>;  /* ETH1_RMII_CRS_DV */
+		};
+	};
+
+	pwm1_pins_a: pwm1-0 {
+		pins {
+			pinmux = <STM32_PINMUX('E', 9, AF1)>, /* TIM1_CH1 */
+				 <STM32_PINMUX('E', 11, AF1)>, /* TIM1_CH2 */
+				 <STM32_PINMUX('E', 13, AF1)>; /* TIM1_CH3 */
+			bias-pull-down;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+	};
+
+	pwm1_sleep_pins_a: pwm1-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('E', 9, ANALOG)>, /* TIM1_CH1 */
+				 <STM32_PINMUX('E', 11, ANALOG)>, /* TIM1_CH2 */
+				 <STM32_PINMUX('E', 13, ANALOG)>; /* TIM1_CH3 */
+		};
+	};
+
+	pwm4_pins_a: pwm4-0 {
+		pins {
+			pinmux = <STM32_PINMUX('D', 12, AF2)>, /* TIM4_CH1 */
+				 <STM32_PINMUX('B', 7, AF2)>, /* TIM4_CH2 */
+				 <STM32_PINMUX('D', 14, AF2)>; /* TIM4_CH3 */
+			bias-pull-down;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+	};
+
+	pwm4_sleep_pins_a: pwm4-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('D', 12, ANALOG)>, /* TIM4_CH1 */
+				 <STM32_PINMUX('B', 7, ANALOG)>, /* TIM4_CH2 */
+				 <STM32_PINMUX('D', 14, ANALOG)>; /* TIM4_CH3 */
+		};
+	};
+	pwm5_pins_a: pwm5-0 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 0, AF2)>; /* TIM5_CH1 */
+		};
+	};
+
+	pwm5_sleep_pins_a: pwm5-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 0, ANALOG)>; /* TIM5_CH1 */
+		};
+	};
+
+	uart7_pins_a: uart7-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('E', 8, AF7)>; /* UART_TX */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+		pins2 {
+			pinmux = <STM32_PINMUX('E', 10, AF7)>; /* UART7_RX */
+			bias-pull-up;
+		};
+	};
+
+	uart7_idle_pins_a: uart7-idle-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('E', 8, ANALOG)>; /* UART7_TX */
+		};
+		pins2 {
+			pinmux = <STM32_PINMUX('E', 10, AF7)>; /* UART7_RX */
+			bias-pull-up;
+		};
+	};
+
+	uart7_sleep_pins_a: uart7-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('E', 8, ANALOG)>, /* UART7_TX */
+				 <STM32_PINMUX('E', 10, ANALOG)>; /* UART7_RX */
+		};
+	};
+
+	usart6_pins_a: usart6-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('F', 8, AF7)>, /* USART6_TX */
+				 <STM32_PINMUX('F', 10, AF7)>; /* USART6_DE */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+		pins2 {
+			pinmux = <STM32_PINMUX('H', 11, AF7)>; /* USART6_RX */
+			bias-disable;
+		};
+	};
+
+	usart6_idle_pins_a: usart6-idle-0 {
+		pins1 {
+			pinmux = <STM32_PINMUX('F', 8, ANALOG)>; /* USART6_TX */
+		};
+		pins2 {
+			pinmux = <STM32_PINMUX('F', 10, AF7)>; /* USART6_DE */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+		pins3 {
+			pinmux = <STM32_PINMUX('H', 11, AF7)>; /* USART6_RX */
+			bias-disable;
+		};
+	};
+
+	usart6_sleep_pins_a: usart6-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('F', 8, ANALOG)>, /* USART6_TX */
+				 <STM32_PINMUX('F', 10, ANALOG)>, /* USART6_DE */
+				 <STM32_PINMUX('H', 11, ANALOG)>; /* USART6_RX */
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/st/stm32mp135f-dhcor-dhsbc.dts b/arch/arm/boot/dts/st/stm32mp135f-dhcor-dhsbc.dts
index 853dc21449d9..9902849ed040 100644
--- a/arch/arm/boot/dts/st/stm32mp135f-dhcor-dhsbc.dts
+++ b/arch/arm/boot/dts/st/stm32mp135f-dhcor-dhsbc.dts
@@ -176,7 +176,7 @@
 	gpio-line-names = "", "", "", "",
 			  "", "DHSBC_USB_PWR_CC1", "", "",
 			  "", "", "", "DHSBC_nETH1_RST",
-			  "", "DHCOR_HW-CODING_0", "", "";
+			  "", "DHCOR_HW-CODING_0", "", "DHSBC_HW-CODE_2";
 };
 
 &gpiob {
@@ -197,7 +197,7 @@
 	gpio-line-names = "", "", "", "",
 			  "", "DHCOR_RAM-CODING_0", "", "",
 			  "", "DHCOR_RAM-CODING_1", "", "",
-			  "", "", "", "";
+			  "", "DHSBC_HW-CODE_1", "", "";
 };
 
 &gpioe {
@@ -221,6 +221,13 @@
 			  "DHSBC_ETH1_INTB", "", "", "DHSBC_ETH2_INTB";
 };
 
+&gpioh {
+	gpio-line-names = "", "", "", "DHSBC_HW-CODE_0",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "";
+};
+
 &gpioi {
 	gpio-line-names = "DHCOR_RTC_nINT", "DHCOR_HW-CODING_1",
 			  "DHCOR_BT_REG_ON", "DHCOR_PMIC_nINT",
@@ -296,6 +303,9 @@
 	st33htph: tpm@0 {
 		compatible = "st,st33htpm-spi", "tcg,tpm_tis-spi";
 		reg = <0>;
+		interrupt-parent = <&gpioe>;
+		interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&gpioe 12 GPIO_ACTIVE_LOW>;
 		spi-max-frequency = <24000000>;
 	};
 };
@@ -419,3 +429,19 @@
 		type = "micro";
 	};
 };
+
+/* LDO2 is expansion connector 3V3 supply on STM32MP13xx DHCOR DHSBC rev.200 */
+&vdd_ldo2 {
+	regulator-always-on;
+	regulator-boot-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+};
+
+/* LDO5 is carrier board 3V3 supply on STM32MP13xx DHCOR DHSBC rev.200 */
+&vdd_sd {
+	regulator-always-on;
+	regulator-boot-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+};
diff --git a/arch/arm/boot/dts/st/stm32mp15-pinctrl.dtsi b/arch/arm/boot/dts/st/stm32mp15-pinctrl.dtsi
index 95fafc51a1c8..40605ea85ee1 100644
--- a/arch/arm/boot/dts/st/stm32mp15-pinctrl.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15-pinctrl.dtsi
@@ -26,6 +26,13 @@
 	};
 
 	/omit-if-no-ref/
+	adc1_in10_pins_a: adc1-in10-0 {
+		pins {
+			pinmux = <STM32_PINMUX('C', 0, ANALOG)>;
+		};
+	};
+
+	/omit-if-no-ref/
 	adc12_ain_pins_a: adc12-ain-0 {
 		pins {
 			pinmux = <STM32_PINMUX('C', 3, ANALOG)>, /* ADC1 in13 */
@@ -585,6 +592,43 @@
 	};
 
 	/omit-if-no-ref/
+	ethernet0_rmii_pins_d: rmii-3 {
+		pins1 {
+			pinmux = <STM32_PINMUX('B', 12, AF11)>, /* ETH1_RMII_TXD0 */
+				 <STM32_PINMUX('B', 13, AF11)>, /* ETH1_RMII_TXD1 */
+				 <STM32_PINMUX('B', 11, AF11)>, /* ETH1_RMII_TX_EN */
+				 <STM32_PINMUX('A', 1, AF11)>, /* ETH1_RMII_REF_CLK */
+				 <STM32_PINMUX('A', 2, AF11)>, /* ETH1_MDIO */
+				 <STM32_PINMUX('C', 1, AF11)>; /* ETH1_MDC */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <2>;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('C', 4, AF11)>, /* ETH1_RMII_RXD0 */
+				 <STM32_PINMUX('C', 5, AF11)>, /* ETH1_RMII_RXD1 */
+				 <STM32_PINMUX('A', 7, AF11)>; /* ETH1_RMII_CRS_DV */
+			bias-disable;
+		};
+	};
+
+	/omit-if-no-ref/
+	ethernet0_rmii_sleep_pins_d: rmii-sleep-3 {
+		pins1 {
+			pinmux = <STM32_PINMUX('B', 12, ANALOG)>, /* ETH1_RMII_TXD0 */
+				 <STM32_PINMUX('B', 13, ANALOG)>, /* ETH1_RMII_TXD1 */
+				 <STM32_PINMUX('B', 11, ANALOG)>, /* ETH1_RMII_TX_EN */
+				 <STM32_PINMUX('A', 2, ANALOG)>, /* ETH1_MDIO */
+				 <STM32_PINMUX('C', 1, ANALOG)>, /* ETH1_MDC */
+				 <STM32_PINMUX('C', 4, ANALOG)>, /* ETH1_RMII_RXD0 */
+				 <STM32_PINMUX('C', 5, ANALOG)>, /* ETH1_RMII_RXD1 */
+				 <STM32_PINMUX('A', 1, ANALOG)>, /* ETH1_RMII_REF_CLK */
+				 <STM32_PINMUX('A', 7, ANALOG)>; /* ETH1_RMII_CRS_DV */
+		};
+	};
+
+	/omit-if-no-ref/
 	fmc_pins_a: fmc-0 {
 		pins1 {
 			pinmux = <STM32_PINMUX('D', 4, AF12)>, /* FMC_NOE */
@@ -726,6 +770,25 @@
 	};
 
 	/omit-if-no-ref/
+	i2c1_pins_c: i2c1-2 {
+		pins {
+			pinmux = <STM32_PINMUX('D', 12, AF5)>, /* I2C1_SCL */
+				 <STM32_PINMUX('D', 13, AF5)>; /* I2C1_SDA */
+			bias-disable;
+			drive-open-drain;
+			slew-rate = <0>;
+		};
+	};
+
+	/omit-if-no-ref/
+	i2c1_sleep_pins_c: i2c1-sleep-2 {
+		pins {
+			pinmux = <STM32_PINMUX('D', 12, ANALOG)>, /* I2C1_SCL */
+				 <STM32_PINMUX('D', 13, ANALOG)>; /* I2C1_SDA */
+		};
+	};
+
+	/omit-if-no-ref/
 	i2c2_pins_a: i2c2-0 {
 		pins {
 			pinmux = <STM32_PINMUX('H', 4, AF4)>, /* I2C2_SCL */
@@ -820,6 +883,27 @@
 	};
 
 	/omit-if-no-ref/
+	i2s1_pins_a: i2s1-0 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 6, AF5)>, /* I2S2_SDI */
+				 <STM32_PINMUX('A', 4, AF5)>, /* I2S2_WS */
+				 <STM32_PINMUX('A', 5, AF5)>; /* I2S2_CK */
+			slew-rate = <0>;
+			drive-push-pull;
+			bias-disable;
+		};
+	};
+
+	/omit-if-no-ref/
+	i2s1_sleep_pins_a: i2s1-sleep-0 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 6, ANALOG)>, /* I2S2_SDI */
+				 <STM32_PINMUX('A', 4, ANALOG)>, /* I2S2_WS */
+				 <STM32_PINMUX('A', 5, ANALOG)>; /* I2S2_CK */
+		};
+	};
+
+	/omit-if-no-ref/
 	i2s2_pins_a: i2s2-0 {
 		pins {
 			pinmux = <STM32_PINMUX('I', 3, AF5)>, /* I2S2_SDO */
@@ -1419,6 +1503,23 @@
 	};
 
 	/omit-if-no-ref/
+	pwm1_pins_d: pwm1-3 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 0, AF2)>; /* TIM5_CH1 */
+			bias-pull-down;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+	};
+
+	/omit-if-no-ref/
+	pwm1_sleep_pins_d: pwm1-sleep-3 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 0, ANALOG)>;
+		};
+	};
+
+	/omit-if-no-ref/
 	pwm2_pins_a: pwm2-0 {
 		pins {
 			pinmux = <STM32_PINMUX('A', 3, AF1)>; /* TIM2_CH4 */
@@ -2161,6 +2262,66 @@
 	};
 
 	/omit-if-no-ref/
+	sdmmc2_b4_pins_c: sdmmc2-b4-2 {
+		pins1 {
+			pinmux = <STM32_PINMUX('B', 14, AF9)>, /* SDMMC2_D0 */
+				 <STM32_PINMUX('B', 7, AF10)>, /* SDMMC2_D1 */
+				 <STM32_PINMUX('B', 3, AF9)>, /* SDMMC2_D2 */
+				 <STM32_PINMUX('B', 4, AF9)>, /* SDMMC2_D3 */
+				 <STM32_PINMUX('G', 6, AF10)>; /* SDMMC2_CMD */
+			slew-rate = <1>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('E', 3, AF9)>; /* SDMMC2_CK */
+			slew-rate = <2>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+	};
+
+	/omit-if-no-ref/
+	sdmmc2_b4_od_pins_c: sdmmc2-b4-od-2 {
+		pins1 {
+			pinmux = <STM32_PINMUX('B', 14, AF9)>, /* SDMMC2_D0 */
+				 <STM32_PINMUX('B', 7, AF10)>, /* SDMMC2_D1 */
+				 <STM32_PINMUX('B', 3, AF9)>, /* SDMMC2_D2 */
+				 <STM32_PINMUX('B', 4, AF9)>; /* SDMMC2_D3 */
+			slew-rate = <1>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('E', 3, AF9)>; /* SDMMC2_CK */
+			slew-rate = <2>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins3 {
+			pinmux = <STM32_PINMUX('G', 6, AF10)>; /* SDMMC2_CMD */
+			slew-rate = <1>;
+			drive-open-drain;
+			bias-pull-up;
+		};
+	};
+
+	/omit-if-no-ref/
+	sdmmc2_b4_sleep_pins_c: sdmmc2-b4-sleep-2 {
+		pins {
+			pinmux = <STM32_PINMUX('B', 14, ANALOG)>, /* SDMMC2_D0 */
+				 <STM32_PINMUX('B', 7, ANALOG)>, /* SDMMC2_D1 */
+				 <STM32_PINMUX('B', 3, ANALOG)>, /* SDMMC2_D2 */
+				 <STM32_PINMUX('B', 4, ANALOG)>, /* SDMMC2_D3 */
+				 <STM32_PINMUX('E', 3, ANALOG)>, /* SDMMC2_CK */
+				 <STM32_PINMUX('G', 6, ANALOG)>; /* SDMMC2_CMD */
+		};
+	};
+
+	/omit-if-no-ref/
 	sdmmc2_d47_pins_a: sdmmc2-d47-0 {
 		pins {
 			pinmux = <STM32_PINMUX('A', 8, AF9)>, /* SDMMC2_D4 */
@@ -2390,6 +2551,66 @@
 	};
 
 	/omit-if-no-ref/
+	sdmmc3_b4_pins_c: sdmmc3-b4-2 {
+		pins1 {
+			pinmux = <STM32_PINMUX('D', 1, AF10)>, /* SDMMC3_D0 */
+				 <STM32_PINMUX('D', 4, AF10)>, /* SDMMC3_D1 */
+				 <STM32_PINMUX('D', 5, AF10)>, /* SDMMC3_D2 */
+				 <STM32_PINMUX('D', 7, AF10)>, /* SDMMC3_D3 */
+				 <STM32_PINMUX('D', 0, AF10)>; /* SDMMC3_CMD */
+			slew-rate = <1>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('G', 15, AF10)>; /* SDMMC3_CK */
+			slew-rate = <2>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+	};
+
+	/omit-if-no-ref/
+	sdmmc3_b4_od_pins_c: sdmmc3-b4-od-2 {
+		pins1 {
+			pinmux = <STM32_PINMUX('D', 1, AF10)>, /* SDMMC3_D0 */
+				 <STM32_PINMUX('D', 4, AF10)>, /* SDMMC3_D1 */
+				 <STM32_PINMUX('D', 5, AF10)>, /* SDMMC3_D2 */
+				 <STM32_PINMUX('D', 7, AF10)>; /* SDMMC3_D3 */
+			slew-rate = <1>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('G', 15, AF10)>; /* SDMMC3_CK */
+			slew-rate = <2>;
+			drive-push-pull;
+			bias-pull-up;
+		};
+
+		pins3 {
+			pinmux = <STM32_PINMUX('D', 0, AF10)>; /* SDMMC3_CMD */
+			slew-rate = <1>;
+			drive-open-drain;
+			bias-pull-up;
+		};
+	};
+
+	/omit-if-no-ref/
+	sdmmc3_b4_sleep_pins_c: sdmmc3-b4-sleep-2 {
+		pins {
+			pinmux = <STM32_PINMUX('D', 1, ANALOG)>, /* SDMMC3_D0 */
+				 <STM32_PINMUX('D', 4, ANALOG)>, /* SDMMC3_D1 */
+				 <STM32_PINMUX('D', 5, ANALOG)>, /* SDMMC3_D2 */
+				 <STM32_PINMUX('D', 7, ANALOG)>, /* SDMMC3_D3 */
+				 <STM32_PINMUX('G', 15, ANALOG)>, /* SDMMC3_CK */
+				 <STM32_PINMUX('D', 0, ANALOG)>; /* SDMMC3_CMD */
+		};
+	};
+
+	/omit-if-no-ref/
 	spdifrx_pins_a: spdifrx-0 {
 		pins {
 			pinmux = <STM32_PINMUX('G', 12, AF8)>; /* SPDIF_IN1 */
@@ -2601,6 +2822,41 @@
 	};
 
 	/omit-if-no-ref/
+	uart4_pins_e: uart4-4 {
+		pins1 {
+			pinmux = <STM32_PINMUX('G', 11, AF6)>; /* UART4_TX */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('B', 8, AF8)>; /* UART4_RX */
+			bias-disable;
+		};
+	};
+
+	/omit-if-no-ref/
+	uart4_idle_pins_e: uart4-idle-4 {
+		pins1 {
+			pinmux = <STM32_PINMUX('G', 11, ANALOG)>; /* UART4_TX */
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('B', 8, AF8)>; /* UART4_RX */
+			bias-disable;
+		};
+	};
+
+	/omit-if-no-ref/
+	uart4_sleep_pins_e: uart4-sleep-4 {
+		pins {
+			pinmux = <STM32_PINMUX('G', 11, ANALOG)>, /* UART4_TX */
+				 <STM32_PINMUX('B', 8, ANALOG)>; /* UART4_RX */
+		};
+	};
+
+	/omit-if-no-ref/
 	uart5_pins_a: uart5-0 {
 		pins1 {
 			pinmux = <STM32_PINMUX('B', 13, AF14)>; /* UART5_TX */
@@ -2678,6 +2934,23 @@
 	};
 
 	/omit-if-no-ref/
+	uart7_pins_d: uart7-3 {
+		pins1 {
+			pinmux = <STM32_PINMUX('F', 7, AF7)>, /* UART7_TX */
+				 <STM32_PINMUX('F', 8, AF7)>; /* UART7_RTS */
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+
+		pins2 {
+			pinmux = <STM32_PINMUX('E', 7, AF7)>, /* UART7_RX */
+				 <STM32_PINMUX('F', 9, AF7)>; /* UART7_CTS */
+			bias-disable;
+		};
+	};
+
+	/omit-if-no-ref/
 	uart8_pins_a: uart8-0 {
 		pins1 {
 			pinmux = <STM32_PINMUX('E', 1, AF8)>; /* UART8_TX */
@@ -3119,6 +3392,25 @@
 	};
 
 	/omit-if-no-ref/
+	i2c6_pins_b: i2c6-1 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 11, AF2)>, /* I2C6_SCL */
+				 <STM32_PINMUX('A', 12, AF2)>; /* I2C6_SDA */
+			bias-disable;
+			drive-open-drain;
+			slew-rate = <0>;
+		};
+	};
+
+	/omit-if-no-ref/
+	i2c6_sleep_pins_b: i2c6-sleep-1 {
+		pins {
+			pinmux = <STM32_PINMUX('A', 11, ANALOG)>, /* I2C6_SCL */
+				 <STM32_PINMUX('A', 12, ANALOG)>; /* I2C6_SDA */
+		};
+	};
+
+	/omit-if-no-ref/
 	spi1_pins_a: spi1-0 {
 		pins1 {
 			pinmux = <STM32_PINMUX('Z', 0, AF5)>, /* SPI1_SCK */
diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi
index b9a87fbe971d..0daa8ffe2ff5 100644
--- a/arch/arm/boot/dts/st/stm32mp151.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp151.dtsi
@@ -1781,7 +1781,6 @@
 				st,syscon = <&syscfg 0x4>;
 				snps,mixed-burst;
 				snps,pbl = <2>;
-				snps,en-tx-lpi-clockgating;
 				snps,axi-config = <&stmmac_axi_config_0>;
 				snps,tso;
 				access-controllers = <&etzpc 94>;
diff --git a/arch/arm/boot/dts/st/stm32mp151c-plyaqm.dts b/arch/arm/boot/dts/st/stm32mp151c-plyaqm.dts
new file mode 100644
index 000000000000..39a3211c6133
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32mp151c-plyaqm.dts
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/dts-v1/;
+
+#include <arm/st/stm32mp151.dtsi>
+#include <arm/st/stm32mp15xc.dtsi>
+#include <arm/st/stm32mp15-pinctrl.dtsi>
+#include <arm/st/stm32mp15xxad-pinctrl.dtsi>
+#include <arm/st/stm32mp15-scmi.dtsi>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "Plymovent AQM board";
+	compatible = "ply,plyaqm", "st,stm32mp151";
+
+	aliases {
+		ethernet0 = &ethernet0;
+		serial0 = &uart4;
+		serial1 = &uart7;
+	};
+
+	codec {
+		compatible = "invensense,ics43432";
+
+		port {
+			codec_endpoint: endpoint {
+				remote-endpoint = <&i2s1_endpoint>;
+				dai-format = "i2s";
+			};
+		};
+	};
+
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			gpios = <&gpioa 3 GPIO_ACTIVE_HIGH>; /* WHITE_EN */
+			color = <LED_COLOR_ID_WHITE>;
+			default-state = "on";
+		};
+	};
+
+	v3v3: fixed-regulator-v3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "v3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	v5v_sw: fixed-regulator-v5sw {
+		compatible = "regulator-fixed";
+		regulator-name = "5v-switched";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpioe 10 GPIO_ACTIVE_HIGH>; /* 5V_SWITCHED_EN */
+		startup-delay-us = <100000>;
+		enable-active-high;
+		regulator-boot-on;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		optee@cfd00000 {
+			reg = <0xcfd00000 0x300000>;
+			no-map;
+		};
+	};
+
+	sound {
+		compatible = "audio-graph-card";
+		label = "STM32MP15";
+		dais = <&i2s1_port>;
+	};
+
+	wifi_pwrseq: wifi-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&gpioe 12 GPIO_ACTIVE_LOW>; /* WLAN_REG_ON */
+	};
+};
+
+&adc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&adc1_in10_pins_a>;
+	vdda-supply = <&v3v3>;
+	vref-supply = <&v3v3>;
+	status = "okay";
+
+	adc@0 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "okay";
+
+		channel@10 { /* NTC */
+			reg = <10>;
+			st,min-sample-time-ns = <10000>;  /* 10µs sampling time */
+		};
+	};
+};
+
+&cpu0 {
+	clocks = <&scmi_clk CK_SCMI_MPU>;
+};
+
+&cryp1 {
+	clocks = <&scmi_clk CK_SCMI_CRYP1>;
+	resets = <&scmi_reset RST_SCMI_CRYP1>;
+	status = "okay";
+};
+
+&ethernet0 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&ethernet0_rmii_pins_d>;
+	pinctrl-1 = <&ethernet0_rmii_sleep_pins_d>;
+	phy-mode = "rmii";
+	max-speed = <100>;
+	phy-handle = <&ethphy0>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "snps,dwmac-mdio";
+
+		/* KSZ8081RNA PHY */
+		ethphy0: ethernet-phy@0 {
+			reg = <0>;
+			interrupts-extended = <&gpiob 0 IRQ_TYPE_LEVEL_LOW>;
+			reset-gpios = <&gpiob 1 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <10000>;
+			reset-deassert-us = <300>;
+		};
+	};
+};
+
+&gpioa {
+	gpio-line-names =
+		"", "", "", "", "", "", "", "",
+		"", "", "", "", "", "HWID_PL_N", "HWID_CP", "";
+};
+
+&gpiob {
+	gpio-line-names =
+		"", "", "", "", "", "", "LED_LATCH", "",
+		"", "RELAY1_EN", "", "", "", "", "", "";
+};
+
+&gpioc {
+	gpio-line-names =
+		"", "", "", "", "", "", "", "",
+		"", "", "", "", "", "HWID_Q7", "", "";
+};
+
+&gpioe {
+	gpio-line-names =
+		"", "", "", "", "RELAY2_EN", "", "", "",
+		"", "", "", "", "", "", "", "";
+};
+
+&gpiog {
+	gpio-line-names =
+		"", "", "", "", "", "", "", "SW1",
+		"", "", "", "", "", "", "", "";
+};
+
+&gpioz {
+	clocks = <&scmi_clk CK_SCMI_GPIOZ>;
+};
+
+&hash1 {
+	clocks = <&scmi_clk CK_SCMI_HASH1>;
+	resets = <&scmi_reset RST_SCMI_HASH1>;
+};
+
+&i2c1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2c1_pins_c>;
+	pinctrl-1 = <&i2c1_sleep_pins_c>;
+	i2c-scl-rising-time-ns = <185>;
+	i2c-scl-falling-time-ns = <20>;
+	status = "okay";
+	/delete-property/dmas;
+	/delete-property/dma-names;
+};
+
+&i2c4 {
+	clocks = <&scmi_clk CK_SCMI_I2C4>;
+	resets = <&scmi_reset RST_SCMI_I2C4>;
+};
+
+&i2c6 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2c6_pins_b>;
+	pinctrl-1 = <&i2c6_sleep_pins_b>;
+	i2c-scl-rising-time-ns = <185>;
+	i2c-scl-falling-time-ns = <20>;
+	clocks = <&scmi_clk CK_SCMI_I2C6>;
+	resets = <&scmi_reset RST_SCMI_I2C6>;
+	status = "okay";
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	pressure-sensor@47 {
+		compatible = "bosch,bmp580";
+		reg = <0x47>;
+		vdda-supply = <&v5v_sw>;
+		vddd-supply = <&v5v_sw>;
+	};
+
+	co2-sensor@62 {
+		compatible = "sensirion,scd41";
+		reg = <0x62>;
+		vdd-supply = <&v5v_sw>;
+	};
+
+	pm-sensor@69 {
+		compatible = "sensirion,sps30";
+		reg = <0x69>;
+	};
+};
+
+&i2s1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2s1_pins_a>;
+	pinctrl-1 = <&i2s1_sleep_pins_a>;
+	clocks = <&rcc SPI1>, <&rcc SPI1_K>, <&rcc PLL3_Q>, <&rcc PLL3_R>;
+	clock-names = "pclk", "i2sclk", "x8k", "x11k";
+	#clock-cells = <0>; /* Set I2S2 as master clock provider */
+	status = "okay";
+
+	i2s1_port: port {
+		i2s1_endpoint: endpoint {
+			format = "i2s";
+			mclk-fs = <256>;
+			remote-endpoint = <&codec_endpoint>;
+		};
+	};
+};
+
+&iwdg2 {
+	clocks = <&rcc IWDG2>, <&scmi_clk CK_SCMI_LSI>;
+	status = "okay";
+};
+
+&m4_rproc {
+	/delete-property/ st,syscfg-holdboot;
+	resets = <&scmi_reset RST_SCMI_MCU>,
+		 <&scmi_reset RST_SCMI_MCU_HOLD_BOOT>;
+	reset-names =  "mcu_rst", "hold_boot";
+};
+
+&mdma1 {
+	resets = <&scmi_reset RST_SCMI_MDMA>;
+};
+
+&rcc {
+	compatible = "st,stm32mp1-rcc-secure", "syscon";
+	clock-names = "hse", "hsi", "csi", "lse", "lsi";
+	clocks = <&scmi_clk CK_SCMI_HSE>,
+		 <&scmi_clk CK_SCMI_HSI>,
+		 <&scmi_clk CK_SCMI_CSI>,
+		 <&scmi_clk CK_SCMI_LSE>,
+		 <&scmi_clk CK_SCMI_LSI>;
+};
+
+&rng1 {
+	clocks = <&scmi_clk CK_SCMI_RNG1>;
+	resets = <&scmi_reset RST_SCMI_RNG1>;
+	status = "okay";
+};
+
+&rtc {
+	clocks = <&scmi_clk CK_SCMI_RTCAPB>, <&scmi_clk CK_SCMI_RTC>;
+};
+
+/* SD card without Card-detect */
+&sdmmc1 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc1_b4_pins_a>;
+	pinctrl-1 = <&sdmmc1_b4_od_pins_a>;
+	pinctrl-2 = <&sdmmc1_b4_sleep_pins_a>;
+	broken-cd;
+	no-sdio;
+	no-1-8-v;
+	st,neg-edge;
+	bus-width = <4>;
+	vmmc-supply = <&v3v3>;
+	status = "okay";
+};
+
+/* EMMC */
+&sdmmc2 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc2_b4_pins_c &sdmmc2_d47_pins_b>;
+	pinctrl-1 = <&sdmmc2_b4_od_pins_c &sdmmc2_d47_pins_b>;
+	pinctrl-2 = <&sdmmc2_b4_sleep_pins_c &sdmmc2_d47_sleep_pins_b>;
+	non-removable;
+	no-sd;
+	no-sdio;
+	no-1-8-v;
+	st,neg-edge;
+	bus-width = <8>;
+	vmmc-supply = <&v3v3>;
+	status = "okay";
+};
+
+/* Wifi */
+&sdmmc3 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc3_b4_pins_c>;
+	pinctrl-1 = <&sdmmc3_b4_od_pins_c>;
+	pinctrl-2 = <&sdmmc3_b4_sleep_pins_c>;
+	non-removable;
+	st,neg-edge;
+	bus-width = <4>;
+	vmmc-supply = <&v3v3>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	wifi@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+	};
+};
+
+&timers5 {
+	status = "okay";
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	pwm {
+		pinctrl-0 = <&pwm1_pins_d>;
+		pinctrl-1 = <&pwm1_sleep_pins_d>;
+		pinctrl-names = "default", "sleep";
+		status = "okay";
+	};
+};
+
+&uart4 {
+	pinctrl-names = "default", "sleep", "idle";
+	pinctrl-0 = <&uart4_pins_e>;
+	pinctrl-1 = <&uart4_idle_pins_e>;
+	pinctrl-2 = <&uart4_sleep_pins_e>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
+
+&uart7 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart7_pins_d>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "brcm,bcm43438-bt";
+		shutdown-gpios = <&gpioe 11 GPIO_ACTIVE_HIGH>; /* BT_REG_ON */
+		max-speed = <4000000>;
+		vbat-supply = <&v3v3>;
+		vddio-supply = <&v3v3>;
+		interrupt-parent = <&gpiog>;
+		interrupts = <12 IRQ_TYPE_EDGE_RISING>; /* BT_HOST_WAKE */
+		interrupt-names = "host-wakeup";
+	};
+};
diff --git a/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen1.dts b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen1.dts
new file mode 100644
index 000000000000..3a0e84262424
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen1.dts
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (C) 2024 Leonard Göhrs, Pengutronix
+ */
+
+/dts-v1/;
+
+#include "stm32mp153c-lxa-fairytux2.dtsi"
+
+/ {
+	model = "Linux Automation GmbH FairyTux 2 Gen 1";
+	compatible = "lxa,stm32mp153c-fairytux2-gen1", "oct,stm32mp153x-osd32", "st,stm32mp153";
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-left {
+			label = "USER_BTN1";
+			linux,code = <KEY_ESC>;
+			gpios = <&gpioi 11 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+		};
+
+		button-right {
+			label = "USER_BTN2";
+			linux,code = <KEY_HOME>;
+			gpios = <&gpioe 9 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+		};
+	};
+};
+
+&gpiof {
+	gpio-line-names = "GPIO1", "GPIO2", "", "", "",			/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioh {
+	gpio-line-names = "", "", "", "", "LCD_RESET",			/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "GPIO3", "",			/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioi {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "", "ETH_", "",			/*  5 */
+			  "", "USER_BTN1";				/* 10 */
+};
+
+&i2c1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2c1_pins_b>;
+	pinctrl-1 = <&i2c1_sleep_pins_b>;
+	status = "okay";
+
+	io_board_gpio: gpio@20 {
+		compatible = "ti,tca6408";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		vcc-supply = <&v3v3_hdmi>;
+		gpio-line-names = "LED1_GA_YK", "LED2_GA_YK", "LED1_GK_YA", "LED2_GK_YA",
+				  "RS485_EN", "RS485_120R", "", "CAN_120R";
+	};
+};
+
+&led_controller_io {
+	/*
+	 * led-2 and led-3 are internally connected antiparallel to one
+	 * another inside the ethernet jack like this:
+	 * GPIO1 ---+---|led-2|>--+--- GPIO3
+	 *          +--<|led-3|---+
+	 * E.g. only one of the LEDs can be illuminated at a time while
+	 * the other output must be driven low.
+	 * This should likely be implemented using a multi color LED
+	 * driver for antiparallel LEDs.
+	 */
+	led-2 {
+		color = <LED_COLOR_ID_GREEN>;
+		function = LED_FUNCTION_ACTIVITY;
+		gpios = <&io_board_gpio 1 GPIO_ACTIVE_HIGH>;
+	};
+
+	led-3 {
+		color = <LED_COLOR_ID_ORANGE>;
+		function = LED_FUNCTION_ACTIVITY;
+		gpios = <&io_board_gpio 3 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&usart3 {
+	/*
+	 * On Gen 1 FairyTux 2 only RTS can be used and not CTS as well,
+	 * Because pins PD11 (CTS) and PI11 (USER_BTN1) share the same
+	 * interrupt and only one of them can be used at a time.
+	 */
+	rts-gpios = <&gpiod 12 GPIO_ACTIVE_LOW>;
+};
+
+&usbotg_hs {
+	dr_mode = "peripheral";
+};
diff --git a/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen2.dts b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen2.dts
new file mode 100644
index 000000000000..66e6da912508
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2-gen2.dts
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (C) 2024 Leonard Göhrs, Pengutronix
+ */
+
+/dts-v1/;
+
+#include "stm32mp153c-lxa-fairytux2.dtsi"
+
+/ {
+	model = "Linux Automation GmbH FairyTux 2 Gen 2";
+	compatible = "lxa,stm32mp153c-fairytux2-gen2", "oct,stm32mp153x-osd32", "st,stm32mp153";
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-left {
+			label = "USER_BTN1";
+			linux,code = <KEY_ESC>;
+			gpios = <&gpioi 10 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+		};
+
+		button-right {
+			label = "USER_BTN2";
+			linux,code = <KEY_HOME>;
+			gpios = <&gpioe 9 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+		};
+	};
+};
+
+&gpiof {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioh {
+	gpio-line-names = "", "", "", "", "LCD_RESET",			/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "GPIO1", "GPIO_INT", "",		/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioi {
+	gpio-line-names = "GPIO2", "", "", "", "",			/*  0 */
+			  "", "", "", "ETH_", "",			/*  5 */
+			  "", "USER_BTN1";				/* 10 */
+};
+
+&i2c1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&i2c1_pins_b>;
+	pinctrl-1 = <&i2c1_sleep_pins_b>;
+	status = "okay";
+
+	io_board_gpio: gpio@20 {
+		compatible = "ti,tca6408";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-parent = <&gpioh>;
+		interrupts = <13 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&board_tca6408_pins>;
+		#interrupt-cells = <2>;
+		vcc-supply = <&v3v3_hdmi>;
+		gpio-line-names = "LED1_GA_YK", "LED2_GA_YK", "LED1_GK_YA", "USB_CC_ALERT",
+				  "RS485_EN", "RS485_120R", "USB_CC_RESET", "CAN_120R";
+	};
+
+	usb_c: typec@28 {
+		compatible = "st,stusb1600";
+		reg = <0x28>;
+		interrupt-parent = <&io_board_gpio>;
+		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+		vdd-supply = <&reg_5v>;
+		vsys-supply = <&v3v3_hdmi>;
+
+		connector {
+			compatible = "usb-c-connector";
+			label = "USB-C";
+			power-role = "dual";
+			typec-power-opmode = "default";
+
+			port {
+				con_usbotg_hs_ep: endpoint {
+					remote-endpoint = <&usbotg_hs_ep>;
+				};
+			};
+		};
+	};
+
+	temperature-sensor@48 {
+		compatible = "national,lm75a";
+		reg = <0x48>;
+		/*
+		 * The sensor itself is powered by a voltage divider from the
+		 * always-on 5V supply.
+		 * The required pull-up resistors however are on v3v3_hdmi.
+		 */
+		vs-supply = <&v3v3_hdmi>;
+	};
+
+	io_board_eeprom: eeprom@56 {
+		compatible = "atmel,24c04";
+		reg = <0x56>;
+		vcc-supply = <&v3v3_hdmi>;
+	};
+};
+
+&rtc {
+	status = "okay";
+};
+
+&led_controller_io {
+	led-2 {
+		color = <LED_COLOR_ID_ORANGE>;
+		function = LED_FUNCTION_ACTIVITY;
+		gpios = <&io_board_gpio 1 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&usart3 {
+	rts-gpios = <&gpiod 12 GPIO_ACTIVE_LOW>;
+	cts-gpios = <&gpiod 11 GPIO_ACTIVE_LOW>;
+};
+
+&usbotg_hs {
+	usb-role-switch;
+
+	port {
+		usbotg_hs_ep: endpoint {
+			remote-endpoint = <&con_usbotg_hs_ep>;
+		};
+	};
+};
+
+&pinctrl {
+	board_tca6408_pins: stusb1600-0 {
+		pins {
+			pinmux = <STM32_PINMUX('H', 13, GPIO)>;
+			bias-pull-up;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2.dtsi b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2.dtsi
new file mode 100644
index 000000000000..9eeb9d6b5eb0
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32mp153c-lxa-fairytux2.dtsi
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause)
+/*
+ * Copyright (C) 2020 STMicroelectronics - All Rights Reserved
+ * Copyright (C) 2021 Rouven Czerwinski, Pengutronix
+ * Copyright (C) 2023, 2024 Leonard Göhrs, Pengutronix
+ */
+
+#include "stm32mp153.dtsi"
+#include "stm32mp15xc.dtsi"
+#include "stm32mp15xx-osd32.dtsi"
+#include "stm32mp15xxac-pinctrl.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pwm/pwm.h>
+
+/ {
+	aliases {
+		can0 = &m_can1;
+		ethernet0 = &ethernet0;
+		i2c0 = &i2c1;
+		i2c1 = &i2c4;
+		mmc1 = &sdmmc2;
+		serial0 = &uart4;
+		serial1 = &usart3;
+		spi0 = &spi4;
+	};
+
+	chosen {
+		stdout-path = &uart4;
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&v3v3>;
+
+		brightness-levels = <0 31 63 95 127 159 191 223 255>;
+		default-brightness-level = <7>;
+		pwms = <&led_pwm 3 1000000 0>;
+	};
+
+	led-controller-cpu {
+		compatible = "gpio-leds";
+
+		led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&gpioa 13 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	led_controller_io: led-controller-io {
+		compatible = "gpio-leds";
+
+		/*
+		 * led-0 and led-1 are internally connected antiparallel to one
+		 * another inside the ethernet jack like this:
+		 * GPIO0 ---+---|led-0|>--+--- GPIO2
+		 *          +--<|led-1|---+
+		 * E.g. only one of the LEDs can be illuminated at a time while
+		 * the other output must be driven low.
+		 * This should likely be implemented using a multi color LED
+		 * driver for antiparallel LEDs.
+		 */
+		led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_LAN;
+			gpios = <&io_board_gpio 0 GPIO_ACTIVE_HIGH>;
+		};
+
+		led-1 {
+			color = <LED_COLOR_ID_ORANGE>;
+			function = LED_FUNCTION_LAN;
+			gpios = <&io_board_gpio 2 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	reg_5v: regulator-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	reg_1v2: regulator-1v2 {
+		compatible = "regulator-fixed";
+		regulator-name = "1V2";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-always-on;
+		vin-supply = <&reg_5v>;
+	};
+};
+
+baseboard_eeprom: &sip_eeprom {
+};
+
+&crc1 {
+	status = "okay";
+};
+
+&cryp1 {
+	status = "okay";
+};
+
+&dts {
+	status = "okay";
+};
+
+&ethernet0 {
+	assigned-clocks = <&rcc ETHCK_K>, <&rcc PLL4_P>;
+	assigned-clock-parents = <&rcc PLL4_P>;
+	assigned-clock-rates = <125000000>; /* Clock PLL4 to 750Mhz in ATF */
+
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&ethernet0_rgmii_pins_b>;
+	pinctrl-1 = <&ethernet0_rgmii_sleep_pins_b>;
+
+	st,eth-clk-sel;
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethphy>;
+	status = "okay";
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy: ethernet-phy@3 { /* KSZ9031RN */
+			reg = <3>;
+			reset-gpios = <&gpioe 11 GPIO_ACTIVE_LOW>; /* ETH_RST# */
+			interrupt-parent = <&gpioa>;
+			interrupts = <6 IRQ_TYPE_EDGE_FALLING>; /* ETH_MDINT# */
+			reset-assert-us = <10000>;
+			reset-deassert-us = <300>;
+			micrel,force-master;
+		};
+	};
+};
+
+&gpioa {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "ETH_INT", "", "", "",			/*  5 */
+			  "", "", "", "BOOTROM_LED", "",		/* 10 */
+			  "";						/* 15 */
+};
+
+&gpiob {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioc {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "";					/* 10 */
+};
+
+&gpiod {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "LCD_TE", "", "",			/*  5 */
+			  "LCD_DC", "", "", "", "",			/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioe {
+	gpio-line-names = "LCD_CS", "", "", "", "",			/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpiof {
+	gpio-line-names = "GPIO1", "GPIO2", "", "", "",			/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpiog {
+	gpio-line-names = "", "", "", "", "",				/*  0 */
+			  "", "", "", "", "",				/*  5 */
+			  "", "", "", "", "",				/* 10 */
+			  "";						/* 15 */
+};
+
+&gpioz {
+	gpio-line-names = "HWID0", "HWID1", "HWID2", "HWID3", "",	/*  0 */
+			  "", "HWID4", "HWID5";				/*  5 */
+};
+
+&hash1 {
+	status = "okay";
+};
+
+&iwdg2 {
+	timeout-sec = <8>;
+	status = "okay";
+};
+
+&m_can1 {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&m_can1_pins_b>;
+	pinctrl-1 = <&m_can1_sleep_pins_b>;
+	status = "okay";
+	termination-gpios = <&io_board_gpio 7 GPIO_ACTIVE_HIGH>;
+	termination-ohms = <120>;
+};
+
+&pmic {
+	regulators {
+		buck1-supply = <&reg_5v>;	/* VIN */
+		buck2-supply = <&reg_5v>;	/* VIN */
+		buck3-supply = <&reg_5v>;	/* VIN */
+		buck4-supply = <&reg_5v>;	/* VIN */
+		ldo2-supply = <&reg_5v>;	/* PMIC_LDO25IN */
+		ldo4-supply = <&reg_5v>;	/* VIN */
+		ldo5-supply = <&reg_5v>;	/* PMIC_LDO25IN */
+		vref_ddr-supply = <&reg_5v>;	/* VIN */
+		boost-supply = <&reg_5v>;	/* PMIC_BSTIN */
+		pwr_sw2-supply = <&bst_out>;	/* PMIC_SWIN */
+	};
+};
+
+&pwr_regulators {
+	vdd-supply = <&vdd>;
+	vdd_3v3_usbfs-supply = <&vdd_usb>;
+};
+
+&sdmmc2 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_b>;
+	pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_b>;
+	pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_b>;
+	vmmc-supply = <&v3v3>;
+
+	bus-width = <8>;
+	mmc-ddr-3_3v;
+	no-1-8-v;
+	non-removable;
+	no-sd;
+	no-sdio;
+	st,neg-edge;
+
+	status = "okay";
+};
+
+&spi4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi4_pins_a>;
+	cs-gpios = <&gpioe 0 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	lcd: display@0 {
+		compatible = "shineworld,lh133k", "panel-mipi-dbi-spi";
+		reg = <0>;
+		power-supply = <&v3v3>;
+		io-supply = <&v3v3>;
+		backlight = <&backlight>;
+		dc-gpios = <&gpiod 10 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpioh 4 GPIO_ACTIVE_HIGH>;
+		spi-3wire;
+		spi-max-frequency = <32000000>;
+
+		width-mm = <23>;
+		height-mm = <23>;
+		rotation = <180>;
+
+		panel-timing {
+			hactive = <240>;
+			vactive = <240>;
+			hback-porch = <0>;
+			vback-porch = <0>;
+
+			clock-frequency = <0>;
+			hfront-porch = <0>;
+			hsync-len = <0>;
+			vfront-porch = <0>;
+			vsync-len = <0>;
+		};
+	};
+};
+
+&timers2 {
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+
+	timer@1 {
+		status = "okay";
+	};
+};
+
+&timers3 {
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+
+	timer@2 {
+		status = "okay";
+	};
+};
+
+&timers4 {
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+
+	timer@3 {
+		status = "okay";
+	};
+};
+
+&timers8 {
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+
+	led_pwm: pwm {
+		pinctrl-names = "default", "sleep";
+		pinctrl-0 = <&pwm8_pins_b>;
+		pinctrl-1 = <&pwm8_sleep_pins_b>;
+		status = "okay";
+	};
+};
+
+&uart4 {
+	label = "debug";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart4_pins_a>;
+
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+};
+
+&usart3 {
+	label = "external";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&usart3_pins_a>;
+
+	/* spare dmas for other usage */
+	/delete-property/dmas;
+	/delete-property/dma-names;
+
+	status = "okay";
+};
+
+&usbh_ehci {
+	phys = <&usbphyc_port0>;
+	phy-names = "usb";
+
+	status = "okay";
+};
+
+&usbotg_hs {
+	phys = <&usbphyc_port1 0>;
+	phy-names = "usb2-phy";
+
+	vusb_d-supply = <&vdd_usb>;
+	vusb_a-supply = <&reg18>;
+
+	status = "okay";
+};
+
+&usbphyc {
+	status = "okay";
+};
+
+&usbphyc_port0 {
+	phy-supply = <&vdd_usb>;
+};
+
+&usbphyc_port1 {
+	phy-supply = <&vdd_usb>;
+};
+
+&v3v3_hdmi {
+	regulator-enable-ramp-delay = <1000>;
+};
diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
index 5f9c0160a9c4..324f7bb988d1 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
@@ -67,7 +67,7 @@
 	touchscreen@38 {
 		compatible = "focaltech,ft6236";
 		reg = <0x38>;
-		interrupts = <2 2>;
+		interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-parent = <&gpiof>;
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <800>;
diff --git a/arch/arm/boot/dts/ti/davinci/da850-lego-ev3.dts b/arch/arm/boot/dts/ti/davinci/da850-lego-ev3.dts
index 4df10379ff22..173401c58d53 100644
--- a/arch/arm/boot/dts/ti/davinci/da850-lego-ev3.dts
+++ b/arch/arm/boot/dts/ti/davinci/da850-lego-ev3.dts
@@ -412,14 +412,14 @@
 	status = "okay";
 
 	/* Don't pull down battery voltage adc io channel */
-	batt_volt_en {
+	batt-volt-en-hog {
 		gpio-hog;
 		gpios = <6 GPIO_ACTIVE_HIGH>;
 		output-high;
 	};
 
 	/* Don't impede Bluetooth clock signal */
-	bt_clock_en {
+	bt-clock-en-hog {
 		gpio-hog;
 		gpios = <5 GPIO_ACTIVE_HIGH>;
 		input;
@@ -433,19 +433,19 @@
 	 * anything, but they are present in the source code from LEGO.
 	 */
 
-	bt_pic_en {
+	bt-pic-en-hog {
 		gpio-hog;
 		gpios = <51 GPIO_ACTIVE_HIGH>;
 		output-low;
 	};
 
-	bt_pic_rst {
+	bt-pic-rst-hog {
 		gpio-hog;
 		gpios = <78 GPIO_ACTIVE_HIGH>;
 		output-high;
 	};
 
-	bt_pic_cts {
+	bt-pic-cts-hog {
 		gpio-hog;
 		gpios = <87 GPIO_ACTIVE_HIGH>;
 		input;
diff --git a/arch/arm/boot/dts/ti/omap/omap3-evm-processor-common.dtsi b/arch/arm/boot/dts/ti/omap/omap3-evm-processor-common.dtsi
index e27837093e43..70e33cdd519a 100644
--- a/arch/arm/boot/dts/ti/omap/omap3-evm-processor-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap3-evm-processor-common.dtsi
@@ -205,7 +205,7 @@
 
 /* T2_GPIO_2 low to route GPIO_61 to on-board devices */
 &twl_gpio {
-	en_on_board_gpio_61 {
+	en-on-board-gpio-61-hog {
 		gpio-hog;
 		gpios = <2 GPIO_ACTIVE_HIGH>;
 		output-low;
diff --git a/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi b/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
index 3fcef3080eae..150dd84c9e0f 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
@@ -1414,7 +1414,7 @@
 			uart3: serial@0 {
 				compatible = "ti,omap4-uart";
 				reg = <0x0 0x100>;
-				interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
 				clock-frequency = <48000000>;
 			};
 		};
@@ -1765,7 +1765,7 @@
 			uart1: serial@0 {
 				compatible = "ti,omap4-uart";
 				reg = <0x0 0x100>;
-				interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts-extended = <&wakeupgen GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
 				clock-frequency = <48000000>;
 			};
 		};
@@ -1794,7 +1794,7 @@
 			uart2: serial@0 {
 				compatible = "ti,omap4-uart";
 				reg = <0x0 0x100>;
-				interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts-extended = <&wakeupgen GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
 				clock-frequency = <48000000>;
 			};
 		};
@@ -1823,7 +1823,7 @@
 			uart4: serial@0 {
 				compatible = "ti,omap4-uart";
 				reg = <0x0 0x100>;
-				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts-extended = <&wakeupgen GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
 				clock-frequency = <48000000>;
 			};
 		};
diff --git a/arch/arm/boot/dts/ti/omap/omap4-panda-a4.dts b/arch/arm/boot/dts/ti/omap/omap4-panda-a4.dts
index 8fd076e5d1b0..4b8bfd0188ad 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-panda-a4.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-panda-a4.dts
@@ -7,6 +7,11 @@
 #include "omap443x.dtsi"
 #include "omap4-panda-common.dtsi"
 
+/ {
+	model = "TI OMAP4 PandaBoard (A4)";
+	compatible = "ti,omap4-panda-a4", "ti,omap4-panda", "ti,omap4430", "ti,omap4";
+};
+
 /* Pandaboard Rev A4+ have external pullups on SCL & SDA */
 &dss_hdmi_pins {
 	pinctrl-single,pins = <
diff --git a/arch/arm/boot/dts/xilinx/zynq-7000.dtsi b/arch/arm/boot/dts/xilinx/zynq-7000.dtsi
index a7db3f3009f2..153b8d93cbee 100644
--- a/arch/arm/boot/dts/xilinx/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/xilinx/zynq-7000.dtsi
@@ -8,6 +8,13 @@
 	#size-cells = <1>;
 	compatible = "xlnx,zynq-7000";
 
+	options {
+		u-boot {
+			compatible = "u-boot,config";
+			bootscr-address = /bits/ 64 <0x3000000>;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -34,7 +41,7 @@
 		};
 	};
 
-	fpga_full: fpga-full {
+	fpga_full: fpga-region {
 		compatible = "fpga-region";
 		fpga-mgr = <&devcfg>;
 		#address-cells = <1>;
@@ -93,6 +100,7 @@
 	};
 
 	amba: axi {
+		bootph-all;
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -190,6 +198,17 @@
 			reg = <0xf8006000 0x1000>;
 		};
 
+		ocm: sram@fffc0000 {
+			compatible = "mmio-sram";
+			reg = <0xfffc0000 0x10000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0xfffc0000 0x10000>;
+			ocm-sram@0 {
+				reg = <0x0 0x10000>;
+			};
+		};
+
 		uart0: serial@e0000000 {
 			compatible = "xlnx,xuartps", "cdns,uart-r1p8";
 			status = "disabled";
@@ -277,13 +296,18 @@
 				  0x2 0x0 0xe4000000 0x2000000>; /* SRAM/NOR CS1 region */
 			#address-cells = <2>;
 			#size-cells = <1>;
+			interrupt-parent = <&intc>;
+			interrupts = <0 18 4>;
 
 			nfc0: nand-controller@0,0 {
 				compatible = "arm,pl353-nand-r2p1";
 				reg = <0 0 0x1000000>;
 				status = "disabled";
-				#address-cells = <1>;
-				#size-cells = <0>;
+			};
+			nor0: flash@1,0 {
+				status = "disabled";
+				compatible = "cfi-flash";
+				reg = <1 0 0x2000000>;
 			};
 		};
 
@@ -308,12 +332,14 @@
 		};
 
 		slcr: slcr@f8000000 {
+			bootph-all;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "xlnx,zynq-slcr", "syscon", "simple-mfd";
 			reg = <0xF8000000 0x1000>;
 			ranges;
 			clkc: clkc@100 {
+				bootph-all;
 				#clock-cells = <1>;
 				compatible = "xlnx,ps7-clkc";
 				fclk-enable = <0>;
@@ -398,6 +424,7 @@
 		};
 
 		scutimer: timer@f8f00600 {
+			bootph-all;
 			interrupt-parent = <&intc>;
 			interrupts = <1 13 0x301>;
 			compatible = "arm,cortex-a9-twd-timer";
diff --git a/arch/arm/boot/dts/xilinx/zynq-cc108.dts b/arch/arm/boot/dts/xilinx/zynq-cc108.dts
index 8b9ab9bba23b..f5525c048426 100644
--- a/arch/arm/boot/dts/xilinx/zynq-cc108.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-cc108.dts
@@ -18,6 +18,7 @@
 	aliases {
 		ethernet0 = &gem0;
 		serial0 = &uart0;
+		spi0 = &qspi;
 	};
 
 	chosen {
@@ -48,7 +49,44 @@
 
 	ethernet_phy: ethernet-phy@1 {
 		reg = <1>;
-		device_type = "ethernet-phy";
+	};
+};
+
+&qspi {
+	status = "okay";
+	num-cs = <1>;
+	flash@0 { /* 16 MB */
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-max-frequency = <50000000>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		partition@0 {
+			label = "qspi-fsbl-uboot-bs";
+			reg = <0x0 0x400000>; /* 4MB */
+		};
+		partition@400000 {
+			label = "qspi-linux";
+			reg = <0x400000 0x400000>; /* 4MB */
+		};
+		partition@800000 {
+			label = "qspi-rootfs";
+			reg = <0x800000 0x400000>; /* 4MB */
+		};
+		partition@c00000 {
+			label = "qspi-devicetree";
+			reg = <0xc00000 0x100000>; /* 1MB */
+		};
+		partition@d00000 {
+			label = "qspi-scratch";
+			reg = <0xd00000 0x200000>; /* 2MB */
+		};
+		partition@f00000 {
+			label = "qspi-uboot-env";
+			reg = <0xf00000 0x100000>; /* 1MB */
+		};
 	};
 };
 
@@ -59,6 +97,7 @@
 };
 
 &uart0 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-ebaz4205.dts b/arch/arm/boot/dts/xilinx/zynq-ebaz4205.dts
index 53fa6dbfd8fd..14f644156a6f 100644
--- a/arch/arm/boot/dts/xilinx/zynq-ebaz4205.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-ebaz4205.dts
@@ -51,6 +51,8 @@
 &nfc0 {
 	status = "okay";
 
+	#address-cells = <1>;
+	#size-cells = <0>;
 	nand@0 {
 		reg = <0>;
 	};
diff --git a/arch/arm/boot/dts/xilinx/zynq-microzed.dts b/arch/arm/boot/dts/xilinx/zynq-microzed.dts
index 6ed84fb15902..68b867e8369e 100644
--- a/arch/arm/boot/dts/xilinx/zynq-microzed.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-microzed.dts
@@ -11,8 +11,9 @@
 	compatible = "avnet,zynq-microzed", "xlnx,zynq-microzed", "xlnx,zynq-7000";
 
 	aliases {
-		ethernet0 = &gem0;
 		serial0 = &uart1;
+		spi0 = &qspi;
+		mmc0 = &sdhci0;
 	};
 
 	memory@0 {
@@ -35,6 +36,11 @@
 	ps-clk-frequency = <33333333>;
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+};
+
 &gem0 {
 	status = "okay";
 	phy-mode = "rgmii-id";
@@ -46,10 +52,12 @@
 };
 
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-parallella.dts b/arch/arm/boot/dts/xilinx/zynq-parallella.dts
index 54592aeb92b9..366af4fcf8d9 100644
--- a/arch/arm/boot/dts/xilinx/zynq-parallella.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-parallella.dts
@@ -46,7 +46,6 @@
 		compatible = "ethernet-phy-id0141.0e90",
 		             "ethernet-phy-ieee802.3-c22";
 		reg = <0>;
-		device_type = "ethernet-phy";
 		marvell,reg-init = <0x3 0x10 0xff00 0x1e>,
 		                   <0x3 0x11 0xfff0 0xa>;
 	};
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc702.dts b/arch/arm/boot/dts/xilinx/zynq-zc702.dts
index 6efdbca9d3ef..6955637c5b1a 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc702.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc702.dts
@@ -15,7 +15,10 @@
 		ethernet0 = &gem0;
 		i2c0 = &i2c0;
 		serial0 = &uart1;
+		spi0 = &qspi;
 		mmc0 = &sdhci0;
+		nvmem0 = &eeprom;
+		rtc0 = &rtc;
 	};
 
 	memory@0 {
@@ -63,19 +66,6 @@
 	};
 };
 
-&amba {
-	ocm: sram@fffc0000 {
-		compatible = "mmio-sram";
-		reg = <0xfffc0000 0x10000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0xfffc0000 0x10000>;
-		ocm-sram@0 {
-			reg = <0x0 0x10000>;
-		};
-	};
-};
-
 &can0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -95,7 +85,6 @@
 
 	ethernet_phy: ethernet-phy@7 {
 		reg = <7>;
-		device_type = "ethernet-phy";
 	};
 };
 
@@ -152,7 +141,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <2>;
-			eeprom@54 {
+			eeprom: eeprom@54 {
 				compatible = "atmel,24c08";
 				reg = <0x54>;
 			};
@@ -174,7 +163,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <4>;
-			rtc@51 {
+			rtc: rtc@51 {
 				compatible = "nxp,pcf8563";
 				reg = <0x51>;
 			};
@@ -210,7 +199,7 @@
 		conf {
 			groups = "can0_9_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-rx {
@@ -233,7 +222,7 @@
 		conf {
 			groups = "ethernet0_0_grp";
 			slew-rate = <0>;
-			io-standard = <4>;
+			power-source = <4>;
 		};
 
 		conf-rx {
@@ -256,7 +245,7 @@
 		conf-mdio {
 			groups = "mdio0_0_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 			bias-disable;
 		};
 	};
@@ -274,7 +263,7 @@
 				 "gpio0_10_grp", "gpio0_11_grp", "gpio0_12_grp",
 				 "gpio0_13_grp", "gpio0_14_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-pull-up {
@@ -298,11 +287,11 @@
 			groups = "i2c0_10_grp";
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_50_grp", "gpio0_51_grp";
 			function = "gpio0";
@@ -311,7 +300,7 @@
 		conf {
 			groups = "gpio0_50_grp", "gpio0_51_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 	};
 
@@ -324,7 +313,7 @@
 		conf {
 			groups = "sdio0_2_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 			bias-disable;
 		};
 
@@ -338,7 +327,7 @@
 			bias-high-impedance;
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		mux-wp {
@@ -351,7 +340,7 @@
 			bias-high-impedance;
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 	};
 
@@ -364,7 +353,7 @@
 		conf {
 			groups = "uart1_10_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-rx {
@@ -387,7 +376,7 @@
 		conf {
 			groups = "usb0_0_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-rx {
@@ -403,13 +392,53 @@
 	};
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+	num-cs = <1>;
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <50000000>;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "qspi-fsbl-uboot";
+				reg = <0x0 0x100000>;
+			};
+			partition@100000 {
+				label = "qspi-linux";
+				reg = <0x100000 0x500000>;
+			};
+			partition@600000 {
+				label = "qspi-device-tree";
+				reg = <0x600000 0x20000>;
+			};
+			partition@620000 {
+				label = "qspi-rootfs";
+				reg = <0x620000 0x5e0000>;
+			};
+			partition@c00000 {
+				label = "qspi-bitstream";
+				reg = <0xc00000 0x400000>;
+			};
+		};
+	};
+};
+
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdhci0_default>;
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1_default>;
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc706.dts b/arch/arm/boot/dts/xilinx/zynq-zc706.dts
index 77943c16d33f..3b803c698473 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc706.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc706.dts
@@ -14,7 +14,10 @@
 		ethernet0 = &gem0;
 		i2c0 = &i2c0;
 		serial0 = &uart1;
+		spi0 = &qspi;
 		mmc0 = &sdhci0;
+		nvmem0 = &eeprom;
+		rtc0 = &rtc;
 	};
 
 	memory@0 {
@@ -46,7 +49,6 @@
 
 	ethernet_phy: ethernet-phy@7 {
 		reg = <7>;
-		device_type = "ethernet-phy";
 	};
 };
 
@@ -100,7 +102,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <2>;
-			eeprom@54 {
+			eeprom: eeprom@54 {
 				compatible = "atmel,24c08";
 				reg = <0x54>;
 			};
@@ -122,7 +124,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <4>;
-			rtc@51 {
+			rtc: rtc@51 {
 				compatible = "nxp,pcf8563";
 				reg = <0x51>;
 			};
@@ -150,7 +152,7 @@
 		conf {
 			groups = "ethernet0_0_grp";
 			slew-rate = <0>;
-			io-standard = <4>;
+			power-source = <4>;
 		};
 
 		conf-rx {
@@ -173,7 +175,7 @@
 		conf-mdio {
 			groups = "mdio0_0_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 			bias-disable;
 		};
 	};
@@ -187,7 +189,7 @@
 		conf {
 			groups = "gpio0_7_grp", "gpio0_46_grp", "gpio0_47_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-pull-up {
@@ -211,7 +213,7 @@
 			groups = "i2c0_10_grp";
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 	};
 
@@ -224,7 +226,7 @@
 		conf {
 			groups = "sdio0_2_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 			bias-disable;
 		};
 
@@ -238,7 +240,7 @@
 			bias-high-impedance;
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		mux-wp {
@@ -251,7 +253,7 @@
 			bias-high-impedance;
 			bias-pull-up;
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 	};
 
@@ -264,7 +266,7 @@
 		conf {
 			groups = "uart1_10_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-rx {
@@ -287,7 +289,7 @@
 		conf {
 			groups = "usb0_0_grp";
 			slew-rate = <0>;
-			io-standard = <1>;
+			power-source = <1>;
 		};
 
 		conf-rx {
@@ -303,13 +305,54 @@
 	};
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+	num-cs = <2>;
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>, <1>;
+		parallel-memories = /bits/ 64 <0x1000000 0x1000000>; /* 16MB */
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <50000000>;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "qspi-fsbl-uboot";
+				reg = <0x0 0x100000>;
+			};
+			partition@100000 {
+				label = "qspi-linux";
+				reg = <0x100000 0x500000>;
+			};
+			partition@600000 {
+				label = "qspi-device-tree";
+				reg = <0x600000 0x20000>;
+			};
+			partition@620000 {
+				label = "qspi-rootfs";
+				reg = <0x620000 0x5e0000>;
+			};
+			partition@c00000 {
+				label = "qspi-bitstream";
+				reg = <0xc00000 0x400000>;
+			};
+		};
+	};
+};
+
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdhci0_default>;
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1_default>;
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc770-xm010.dts b/arch/arm/boot/dts/xilinx/zynq-zc770-xm010.dts
index 0dd352289a45..5fe799c3c7cf 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc770-xm010.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc770-xm010.dts
@@ -15,6 +15,7 @@
 		ethernet0 = &gem0;
 		i2c0 = &i2c0;
 		serial0 = &uart1;
+		spi0 = &qspi;
 		spi1 = &spi1;
 	};
 
@@ -45,7 +46,6 @@
 
 	ethernet_phy: ethernet-phy@7 {
 		reg = <7>;
-		device_type = "ethernet-phy";
 	};
 };
 
@@ -57,7 +57,43 @@
 		compatible = "atmel,24c02";
 		reg = <0x52>;
 	};
+};
 
+&qspi {
+	status = "okay";
+	num-cs = <1>;
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <50000000>;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "qspi-fsbl-uboot";
+				reg = <0x0 0x100000>;
+			};
+			partition@100000 {
+				label = "qspi-linux";
+				reg = <0x100000 0x500000>;
+			};
+			partition@600000 {
+				label = "qspi-device-tree";
+				reg = <0x600000 0x20000>;
+			};
+			partition@620000 {
+				label = "qspi-rootfs";
+				reg = <0x620000 0x5e0000>;
+			};
+			partition@c00000 {
+				label = "qspi-bitstream";
+				reg = <0xc00000 0x400000>;
+			};
+		};
+	};
 };
 
 &sdhci0 {
@@ -85,6 +121,7 @@
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc770-xm011.dts b/arch/arm/boot/dts/xilinx/zynq-zc770-xm011.dts
index 56732e8f6ca1..f9a086fe66d3 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc770-xm011.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc770-xm011.dts
@@ -47,6 +47,36 @@
 	};
 };
 
+&nfc0 {
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	nand@0 {
+		reg = <0>;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "nand-fsbl-uboot";
+				reg = <0x0 0x1000000>;
+			};
+			partition@1000000 {
+				label = "nand-linux";
+				reg = <0x1000000 0x2000000>;
+			};
+			partition@3000000 {
+				label = "nand-rootfs";
+				reg = <0x3000000 0x200000>;
+			};
+		};
+	};
+};
+
+&smcc {
+	status = "okay";
+};
+
 &spi0 {
 	status = "okay";
 	num-cs = <4>;
@@ -54,6 +84,7 @@
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc770-xm012.dts b/arch/arm/boot/dts/xilinx/zynq-zc770-xm012.dts
index d2359b789eb8..24520e7d3965 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc770-xm012.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc770-xm012.dts
@@ -53,6 +53,40 @@
 	};
 };
 
+&nor0 {
+	status = "okay";
+	bank-width = <1>;
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		partition@0 {
+			label = "nor-fsbl-uboot";
+			reg = <0x0 0x100000>;
+		};
+		partition@100000 {
+			label = "nor-linux";
+			reg = <0x100000 0x500000>;
+		};
+		partition@600000 {
+			label = "nor-device-tree";
+			reg = <0x600000 0x20000>;
+		};
+		partition@620000 {
+			label = "nor-rootfs";
+			reg = <0x620000 0x5e0000>;
+		};
+		partition@c00000 {
+			label = "nor-bitstream";
+			reg = <0xc00000 0x400000>;
+		};
+	};
+};
+
+&smcc {
+	status = "okay";
+};
+
 &spi1 {
 	status = "okay";
 	num-cs = <4>;
@@ -60,5 +94,6 @@
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/xilinx/zynq-zc770-xm013.dts b/arch/arm/boot/dts/xilinx/zynq-zc770-xm013.dts
index 38d96adc870c..103e87ea7253 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zc770-xm013.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zc770-xm013.dts
@@ -15,6 +15,7 @@
 		ethernet0 = &gem1;
 		i2c0 = &i2c1;
 		serial0 = &uart0;
+		spi0 = &qspi;
 		spi1 = &spi0;
 	};
 
@@ -40,7 +41,6 @@
 
 	ethernet_phy: ethernet-phy@7 {
 		reg = <7>;
-		device_type = "ethernet-phy";
 	};
 };
 
@@ -58,6 +58,44 @@
 	};
 };
 
+&qspi {
+	status = "okay";
+	num-cs = <2>;
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>, <1>;
+		parallel-memories = /bits/ 64 <0x1000000 0x1000000>; /* 16MB */
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <50000000>;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "qspi-fsbl-uboot";
+				reg = <0x0 0x100000>;
+			};
+			partition@100000 {
+				label = "qspi-linux";
+				reg = <0x100000 0x500000>;
+			};
+			partition@600000 {
+				label = "qspi-device-tree";
+				reg = <0x600000 0x20000>;
+			};
+			partition@620000 {
+				label = "qspi-rootfs";
+				reg = <0x620000 0x5e0000>;
+			};
+			partition@c00000 {
+				label = "qspi-bitstream";
+				reg = <0xc00000 0x400000>;
+			};
+		};
+	};
+};
+
 &spi0 {
 	status = "okay";
 	num-cs = <4>;
@@ -73,5 +111,6 @@
 };
 
 &uart0 {
+	bootph-all;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/xilinx/zynq-zed.dts b/arch/arm/boot/dts/xilinx/zynq-zed.dts
index 6a5a93aa6552..52ba569b2b9f 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zed.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zed.dts
@@ -13,6 +13,7 @@
 	aliases {
 		ethernet0 = &gem0;
 		serial0 = &uart1;
+		spi0 = &qspi;
 		mmc0 = &sdhci0;
 	};
 
@@ -43,15 +44,55 @@
 
 	ethernet_phy: ethernet-phy@0 {
 		reg = <0>;
-		device_type = "ethernet-phy";
+	};
+};
+
+&qspi {
+	bootph-all;
+	status = "okay";
+	num-cs = <1>;
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+		spi-max-frequency = <50000000>;
+		m25p,fast-read;
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			partition@0 {
+				label = "qspi-fsbl-uboot";
+				reg = <0x0 0x100000>;
+			};
+			partition@100000 {
+				label = "qspi-linux";
+				reg = <0x100000 0x500000>;
+			};
+			partition@600000 {
+				label = "qspi-device-tree";
+				reg = <0x600000 0x20000>;
+			};
+			partition@620000 {
+				label = "qspi-rootfs";
+				reg = <0x620000 0x5e0000>;
+			};
+			partition@c00000 {
+				label = "qspi-bitstream";
+				reg = <0xc00000 0x400000>;
+			};
+		};
 	};
 };
 
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-zturn-common.dtsi b/arch/arm/boot/dts/xilinx/zynq-zturn-common.dtsi
index 33b02e05ce82..defef9c8da13 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zturn-common.dtsi
+++ b/arch/arm/boot/dts/xilinx/zynq-zturn-common.dtsi
@@ -63,6 +63,11 @@
 	ps-clk-frequency = <33333333>;
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+};
+
 &gem0 {
 	status = "okay";
 	phy-mode = "rgmii-id";
@@ -73,14 +78,17 @@
 };
 
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-zybo-z7.dts b/arch/arm/boot/dts/xilinx/zynq-zybo-z7.dts
index 7b87e10d3953..56b917eec783 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zybo-z7.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zybo-z7.dts
@@ -10,6 +10,8 @@
 	aliases {
 		ethernet0 = &gem0;
 		serial0 = &uart1;
+		spi0 = &qspi;
+		mmc0 = &sdhci0;
 	};
 
 	memory@0 {
@@ -49,15 +51,21 @@
 
 	ethernet_phy: ethernet-phy@0 {
 		reg = <0>;
-		device_type = "ethernet-phy";
 	};
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+};
+
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/xilinx/zynq-zybo.dts b/arch/arm/boot/dts/xilinx/zynq-zybo.dts
index 755f6f109d5a..fbc7d1b12e94 100644
--- a/arch/arm/boot/dts/xilinx/zynq-zybo.dts
+++ b/arch/arm/boot/dts/xilinx/zynq-zybo.dts
@@ -13,6 +13,7 @@
 	aliases {
 		ethernet0 = &gem0;
 		serial0 = &uart1;
+		spi0 = &qspi;
 		mmc0 = &sdhci0;
 	};
 
@@ -44,15 +45,21 @@
 
 	ethernet_phy: ethernet-phy@0 {
 		reg = <0>;
-		device_type = "ethernet-phy";
 	};
 };
 
+&qspi {
+	bootph-all;
+	status = "okay";
+};
+
 &sdhci0 {
+	bootph-all;
 	status = "okay";
 };
 
 &uart1 {
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 9846f30990f7..02eda44a6faa 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -416,9 +416,9 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	writel_relaxed(~0, irqbase + SA1111_INTSTATCLR0);
 	writel_relaxed(~0, irqbase + SA1111_INTSTATCLR1);
 
-	sachip->irqdomain = irq_domain_add_linear(NULL, SA1111_IRQ_NR,
-						  &sa1111_irqdomain_ops,
-						  sachip);
+	sachip->irqdomain = irq_domain_create_linear(NULL, SA1111_IRQ_NR,
+						     &sa1111_irqdomain_ops,
+						     sachip);
 	if (!sachip->irqdomain) {
 		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
 		return -ENOMEM;
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index f2596a1b2f7d..ff13e1ecf4bb 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -232,7 +232,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_DEV_ATMEL_AES=y
 CONFIG_CRYPTO_DEV_ATMEL_TDES=y
 CONFIG_CRYPTO_DEV_ATMEL_SHA=y
-CONFIG_CRC_CCITT=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_ACORN_8x8=y
diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig
index b5f0bd8dd536..27dc3bf6b124 100644
--- a/arch/arm/configs/bcm2835_defconfig
+++ b/arch/arm/configs/bcm2835_defconfig
@@ -7,7 +7,6 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index 42cb1c854118..578c6a4af620 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -78,7 +78,6 @@ CONFIG_ROMFS_FS=y
 CONFIG_NLS_DEFAULT="cp437"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_FONTS=y
 CONFIG_FONT_MINI_4x6=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 3474e475373a..70b8c78386f4 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -249,7 +249,6 @@ CONFIG_NLS_ASCII=m
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=m
 CONFIG_DMA_CMA=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_RT_MUTEXES=y
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index 2849d17f5856..d76eb12d29a7 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -128,8 +128,6 @@ CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
-CONFIG_LIBCRC32C=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/ep93xx_defconfig b/arch/arm/configs/ep93xx_defconfig
index 7dece9d98828..2248afaf35b5 100644
--- a/arch/arm/configs/ep93xx_defconfig
+++ b/arch/arm/configs/ep93xx_defconfig
@@ -113,7 +113,6 @@ CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_LIBCRC32C=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SLAB=y
 CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 7ad48fdda1da..e81964cce516 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -349,7 +349,7 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_XTS=m
@@ -364,13 +364,11 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
-CONFIG_CRYPTO_SHA256_ARM=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_CHACHA20_NEON=m
 CONFIG_CRYPTO_DEV_EXYNOS_RNG=y
 CONFIG_CRYPTO_DEV_S5P=y
-CONFIG_CRC_CCITT=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=96
 CONFIG_FONTS=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 87841e5cafe2..062c1eb8dd60 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -481,10 +481,6 @@ CONFIG_SECURITYFS=y
 CONFIG_CRYPTO_DEV_FSL_CAAM=y
 CONFIG_CRYPTO_DEV_SAHARA=y
 CONFIG_CRYPTO_DEV_MXS_DCP=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
-CONFIG_CRC7=m
-CONFIG_LIBCRC32C=m
 CONFIG_CMA_SIZE_MBYTES=64
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig
index f55c231e0870..2d489186e945 100644
--- a/arch/arm/configs/lpc18xx_defconfig
+++ b/arch/arm/configs/lpc18xx_defconfig
@@ -147,8 +147,6 @@ CONFIG_EXT2_FS=y
 # CONFIG_INOTIFY_USER is not set
 CONFIG_JFFS2_FS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_CRC_ITU_T=y
-CONFIG_CRC7=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/arm/configs/lpc32xx_defconfig b/arch/arm/configs/lpc32xx_defconfig
index 98e267213b21..9afccd76446b 100644
--- a/arch/arm/configs/lpc32xx_defconfig
+++ b/arch/arm/configs/lpc32xx_defconfig
@@ -179,7 +179,6 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
index acd16204f8d7..242e7d5a3f68 100644
--- a/arch/arm/configs/milbeaut_m10v_defconfig
+++ b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -93,23 +93,19 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_KEYS=y
-CONFIG_CRYPTO_MANAGER=y
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_SELFTESTS=y
 # CONFIG_CRYPTO_ECHAINIV is not set
 CONFIG_CRYPTO_AES=y
 CONFIG_CRYPTO_SEQIV=m
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
 CONFIG_CRYPTO_SHA1_ARM_CE=m
-CONFIG_CRYPTO_SHA2_ARM_CE=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_AES_ARM_CE=m
 CONFIG_CRYPTO_CHACHA20_NEON=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_ITU_T=m
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=64
 CONFIG_PRINTK_TIME=y
diff --git a/arch/arm/configs/mmp2_defconfig b/arch/arm/configs/mmp2_defconfig
index f6f9e135353e..842a989baa27 100644
--- a/arch/arm/configs/mmp2_defconfig
+++ b/arch/arm/configs/mmp2_defconfig
@@ -67,7 +67,6 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig
index 34d079e03b3c..fa06d98e43fc 100644
--- a/arch/arm/configs/moxart_defconfig
+++ b/arch/arm/configs/moxart_defconfig
@@ -118,7 +118,6 @@ CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=y
 CONFIG_JFFS2_FS=y
 CONFIG_KEYS=y
-CONFIG_CRC32_BIT=y
 CONFIG_DMA_API_DEBUG=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig
index 27d650635d9b..1a86dc305523 100644
--- a/arch/arm/configs/multi_v4t_defconfig
+++ b/arch/arm/configs/multi_v4t_defconfig
@@ -91,6 +91,5 @@ CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_CRAMFS=y
 CONFIG_MINIX_FS=y
-CONFIG_CRC_CCITT=y
 # CONFIG_FTRACE is not set
 CONFIG_DEBUG_USER=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 3f4ddcf49ec7..cf6180b4296e 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -289,8 +289,6 @@ CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
-CONFIG_LIBCRC32C=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 37e3baa33b67..aca01ad6aafc 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -714,10 +714,10 @@ CONFIG_VIDEO_ADV7604_CEC=y
 CONFIG_VIDEO_ML86V7667=m
 CONFIG_IMX_IPUV3_CORE=m
 CONFIG_DRM=y
-# CONFIG_DRM_I2C_CH7006 is not set
-# CONFIG_DRM_I2C_SIL164 is not set
 CONFIG_DRM_I2C_NXP_TDA998X=m
 CONFIG_DRM_NOUVEAU=m
+# CONFIG_DRM_NOUVEAU_CH7006 is not set
+# CONFIG_DRM_NOUVEAU_SIL164 is not set
 CONFIG_DRM_EXYNOS=m
 CONFIG_DRM_EXYNOS_FIMD=y
 CONFIG_DRM_EXYNOS_MIXER=y
@@ -1121,25 +1121,6 @@ CONFIG_QCOM_SMSM=y
 CONFIG_QCOM_SOCINFO=m
 CONFIG_QCOM_STATS=m
 CONFIG_QCOM_WCNSS_CTRL=m
-CONFIG_ARCH_EMEV2=y
-CONFIG_ARCH_R8A7794=y
-CONFIG_ARCH_R8A7779=y
-CONFIG_ARCH_R8A7790=y
-CONFIG_ARCH_R8A7778=y
-CONFIG_ARCH_R8A7793=y
-CONFIG_ARCH_R8A7791=y
-CONFIG_ARCH_R8A7792=y
-CONFIG_ARCH_R8A7740=y
-CONFIG_ARCH_R8A73A4=y
-CONFIG_ARCH_R7S72100=y
-CONFIG_ARCH_R7S9210=y
-CONFIG_ARCH_R8A77470=y
-CONFIG_ARCH_R8A7745=y
-CONFIG_ARCH_R8A7742=y
-CONFIG_ARCH_R8A7743=y
-CONFIG_ARCH_R8A7744=y
-CONFIG_ARCH_R9A06G032=y
-CONFIG_ARCH_SH73A0=y
 CONFIG_ROCKCHIP_IODOMAIN=y
 CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y
@@ -1203,7 +1184,7 @@ CONFIG_PWM_BCM2835=y
 CONFIG_PWM_BRCMSTB=m
 CONFIG_PWM_FSL_FTM=m
 CONFIG_PWM_MESON=m
-CONFIG_PWM_RCAR=m
+CONFIG_PWM_RENESAS_RCAR=m
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PWM_ROCKCHIP=m
 CONFIG_PWM_SAMSUNG=m
@@ -1301,7 +1282,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
 CONFIG_CRYPTO_SHA1_ARM_CE=m
-CONFIG_CRYPTO_SHA2_ARM_CE=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig
index 2467afd32146..23dbb80fcc2e 100644
--- a/arch/arm/configs/mvebu_v5_defconfig
+++ b/arch/arm/configs/mvebu_v5_defconfig
@@ -187,8 +187,6 @@ CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_CCITT=y
-CONFIG_LIBCRC32C=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index 43bc1255a5db..c76d66135abb 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -160,8 +160,6 @@ CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_CRYPTO_DEV_MXS_DCP=y
-CONFIG_CRC_ITU_T=m
-CONFIG_CRC7=m
 CONFIG_FONTS=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 025b595dd837..661e5d6894bd 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -221,7 +221,6 @@ CONFIG_CRYPTO_PCBC=y
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_LIBCRC32C=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 6de45d7f6078..317f977e509e 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -13,7 +13,6 @@ CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_DEVICE=y
@@ -698,7 +697,6 @@ CONFIG_SECURITY=y
 CONFIG_CRYPTO_MICHAEL_MIC=y
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
-CONFIG_CRYPTO_SHA256_ARM=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
@@ -707,11 +705,6 @@ CONFIG_CRYPTO_DEV_OMAP=m
 CONFIG_CRYPTO_DEV_OMAP_SHAM=m
 CONFIG_CRYPTO_DEV_OMAP_AES=m
 CONFIG_CRYPTO_DEV_OMAP_DES=m
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_CRC_ITU_T=y
-CONFIG_CRC7=y
-CONFIG_LIBCRC32C=y
 CONFIG_DMA_CMA=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index 0629b088a584..62b9c6102789 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -136,7 +136,6 @@ CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_DEV_MARVELL_CESA=y
-CONFIG_CRC_T10DIF=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/pxa168_defconfig b/arch/arm/configs/pxa168_defconfig
index ce10fe2104bf..4748c7d33cb8 100644
--- a/arch/arm/configs/pxa168_defconfig
+++ b/arch/arm/configs/pxa168_defconfig
@@ -41,7 +41,6 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/pxa910_defconfig b/arch/arm/configs/pxa910_defconfig
index 1f28aea86014..49b59c600ae1 100644
--- a/arch/arm/configs/pxa910_defconfig
+++ b/arch/arm/configs/pxa910_defconfig
@@ -50,7 +50,6 @@ CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index de0ac8f521d7..ded4b9a5accf 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -636,10 +636,9 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_UTF8=m
 CONFIG_TIMER_STATS=y
 CONFIG_SECURITY=y
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
@@ -660,11 +659,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 CONFIG_CRYPTO_SHA1_ARM=m
-CONFIG_CRYPTO_SHA256_ARM=m
 CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=m
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/s5pv210_defconfig b/arch/arm/configs/s5pv210_defconfig
index 5dbe85c263de..02121eec3658 100644
--- a/arch/arm/configs/s5pv210_defconfig
+++ b/arch/arm/configs/s5pv210_defconfig
@@ -113,7 +113,6 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index ea7ddf640ba7..e14720a9a5ac 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -227,8 +227,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_DEV_ATMEL_AES=y
 CONFIG_CRYPTO_DEV_ATMEL_TDES=y
 CONFIG_CRYPTO_DEV_ATMEL_SHA=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_ITU_T=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=32
 CONFIG_CMA_ALIGNMENT=9
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index fd28f3176c6b..7c3d6a8f0038 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -14,6 +14,7 @@ CONFIG_SCHED_MC=y
 CONFIG_NR_CPUS=8
 CONFIG_HIGHMEM=y
 CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -62,6 +63,7 @@ CONFIG_SMSC_PHY=y
 CONFIG_CAN_RCAR=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_GPIO_POLLED=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_EDT_FT5X06=y
@@ -83,6 +85,7 @@ CONFIG_SERIAL_8250_EM=y
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DEMUX_PINCTRL=y
+CONFIG_I2C_DESIGNWARE_CORE=y
 CONFIG_I2C_EMEV2=y
 CONFIG_I2C_GPIO=y
 CONFIG_I2C_RIIC=y
@@ -103,7 +106,7 @@ CONFIG_GPIO_PCF857X=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_POWER_SUPPLY=y
-# CONFIG_HWMON is not set
+CONFIG_SENSORS_LM75=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_RCAR_THERMAL=y
@@ -173,6 +176,9 @@ CONFIG_USB_RENESAS_USBHS_UDC=y
 CONFIG_USB_RENESAS_USBF=y
 CONFIG_USB_ETH=y
 CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_SDHCI_OF_ARASAN=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_SH_MMCIF=y
 CONFIG_NEW_LEDS=y
@@ -194,29 +200,10 @@ CONFIG_RCAR_DMAC=y
 CONFIG_RENESAS_USB_DMAC=y
 CONFIG_RZ_DMAC=y
 # CONFIG_IOMMU_SUPPORT is not set
-CONFIG_ARCH_EMEV2=y
-CONFIG_ARCH_R8A7794=y
-CONFIG_ARCH_R8A7779=y
-CONFIG_ARCH_R8A7790=y
-CONFIG_ARCH_R8A7778=y
-CONFIG_ARCH_R8A7793=y
-CONFIG_ARCH_R8A7791=y
-CONFIG_ARCH_R8A7792=y
-CONFIG_ARCH_R8A7740=y
-CONFIG_ARCH_R8A73A4=y
-CONFIG_ARCH_R7S72100=y
-CONFIG_ARCH_R7S9210=y
-CONFIG_ARCH_R8A77470=y
-CONFIG_ARCH_R8A7745=y
-CONFIG_ARCH_R8A7742=y
-CONFIG_ARCH_R8A7743=y
-CONFIG_ARCH_R8A7744=y
-CONFIG_ARCH_R9A06G032=y
-CONFIG_ARCH_SH73A0=y
 CONFIG_IIO=y
 CONFIG_AK8975=y
 CONFIG_PWM=y
-CONFIG_PWM_RCAR=y
+CONFIG_PWM_RENESAS_RCAR=y
 CONFIG_PWM_RENESAS_TPU=y
 CONFIG_PHY_RCAR_GEN2=y
 CONFIG_PHY_RCAR_GEN3_USB2=y
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index 294d16ddeb18..ac2a0f998c73 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -215,7 +215,7 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_CRYPTO_NULL=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_AES=m
@@ -234,8 +234,6 @@ CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_WP512=m
-CONFIG_CRC_CCITT=y
-CONFIG_LIBCRC32C=m
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index 77048b5e1ec4..dcd9c316072e 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -74,8 +74,6 @@ CONFIG_EXT3_FS=y
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
 CONFIG_NLS=y
-CONFIG_CRC_ITU_T=y
-CONFIG_CRC7=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index d2a094ad360c..3a9bda2bf422 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -6,7 +6,6 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEBUG=y
diff --git a/arch/arm/configs/wpcm450_defconfig b/arch/arm/configs/wpcm450_defconfig
index 45483deab034..cd4b3e70ff68 100644
--- a/arch/arm/configs/wpcm450_defconfig
+++ b/arch/arm/configs/wpcm450_defconfig
@@ -191,9 +191,6 @@ CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
 CONFIG_X509_CERTIFICATE_PARSER=y
 CONFIG_PKCS7_MESSAGE_PARSER=y
 CONFIG_SYSTEM_TRUSTED_KEYRING=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_ITU_T=m
-CONFIG_LIBCRC32C=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 32650c8431d9..7efb9a8596e4 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -3,10 +3,12 @@
 menu "Accelerated Cryptographic Algorithms for CPU (arm)"
 
 config CRYPTO_CURVE25519_NEON
-	tristate "Public key crypto: Curve25519 (NEON)"
+	tristate
 	depends on KERNEL_MODE_NEON
+	select CRYPTO_KPP
 	select CRYPTO_LIB_CURVE25519_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+	default CRYPTO_LIB_CURVE25519_INTERNAL
 	help
 	  Curve25519 algorithm
 
@@ -44,29 +46,6 @@ config CRYPTO_NHPOLY1305_NEON
 	  Architecture: arm using:
 	  - NEON (Advanced SIMD) extensions
 
-config CRYPTO_POLY1305_ARM
-	tristate "Hash functions: Poly1305 (NEON)"
-	select CRYPTO_HASH
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
-	help
-	  Poly1305 authenticator algorithm (RFC7539)
-
-	  Architecture: arm optionally using
-	  - NEON (Advanced SIMD) extensions
-
-config CRYPTO_BLAKE2S_ARM
-	bool "Hash functions: BLAKE2s"
-	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
-	help
-	  BLAKE2s cryptographic hash function (RFC 7693)
-
-	  Architecture: arm
-
-	  This is faster than the generic implementations of BLAKE2s and
-	  BLAKE2b, but slower than the NEON implementation of BLAKE2b.
-	  There is no NEON implementation of BLAKE2s, since NEON doesn't
-	  really help with it.
-
 config CRYPTO_BLAKE2B_NEON
 	tristate "Hash functions: BLAKE2b (NEON)"
 	depends on KERNEL_MODE_NEON
@@ -114,27 +93,6 @@ config CRYPTO_SHA1_ARM_CE
 
 	  Architecture: arm using ARMv8 Crypto Extensions
 
-config CRYPTO_SHA2_ARM_CE
-	tristate "Hash functions: SHA-224 and SHA-256 (ARMv8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_SHA256_ARM
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: arm using
-	  - ARMv8 Crypto Extensions
-
-config CRYPTO_SHA256_ARM
-	tristate "Hash functions: SHA-224 and SHA-256 (NEON)"
-	select CRYPTO_HASH
-	depends on !CPU_V7M
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: arm using
-	  - NEON (Advanced SIMD) extensions
-
 config CRYPTO_SHA512_ARM
 	tristate "Hash functions: SHA-384 and SHA-512 (NEON)"
 	select CRYPTO_HASH
@@ -169,7 +127,6 @@ config CRYPTO_AES_ARM_BS
 	select CRYPTO_AES_ARM
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
-	select CRYPTO_SIMD
 	help
 	  Length-preserving ciphers: AES cipher algorithms (FIPS-197)
 	  with block cipher modes:
@@ -197,7 +154,6 @@ config CRYPTO_AES_ARM_CE
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
-	select CRYPTO_SIMD
 	help
 	  Length-preserving ciphers: AES cipher algorithms (FIPS-197)
 	   with block cipher modes:
@@ -211,16 +167,5 @@ config CRYPTO_AES_ARM_CE
 	  Architecture: arm using:
 	  - ARMv8 Crypto Extensions
 
-config CRYPTO_CHACHA20_NEON
-	tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (NEON)"
-	select CRYPTO_SKCIPHER
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
-	  stream cipher algorithms
-
-	  Architecture: arm using:
-	  - NEON (Advanced SIMD) extensions
-
 endmenu
 
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 3d0e23ff9e74..8479137c6e80 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,37 +7,25 @@ obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
-obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
-obj-$(CONFIG_CRYPTO_BLAKE2S_ARM) += libblake2s-arm.o
 obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
-obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
-obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
 obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
-obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
 obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
 
 aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
 aes-arm-bs-y	:= aes-neonbs-core.o aes-neonbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
-sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
-sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
 sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
 sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
-libblake2s-arm-y:= blake2s-core.o blake2s-glue.o
 blake2b-neon-y  := blake2b-neon-core.o blake2b-neon-glue.o
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
-sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
-chacha-neon-y := chacha-scalar-core.o chacha-glue.o
-chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
-poly1305-arm-y := poly1305-core.o poly1305-glue.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
 curve25519-neon-y := curve25519-core.o curve25519-glue.o
 
@@ -47,14 +35,8 @@ quiet_cmd_perl = PERL    $@
 $(obj)/%-core.S: $(src)/%-armv4.pl
 	$(call cmd,perl)
 
-clean-files += poly1305-core.S sha256-core.S sha512-core.S
+clean-files += sha512-core.S
 
 aflags-thumb2-$(CONFIG_THUMB2_KERNEL)  := -U__thumb2__ -D__thumb2__=1
 
-AFLAGS_sha256-core.o += $(aflags-thumb2-y)
 AFLAGS_sha512-core.o += $(aflags-thumb2-y)
-
-# massage the perlasm code a bit so we only get the NEON routine if we need it
-poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
-poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
-AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index 21df5e7f51f9..00591895d540 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -10,8 +10,6 @@
 #include <asm/simd.h>
 #include <linux/unaligned.h>
 #include <crypto/aes.h>
-#include <crypto/ctr.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
@@ -399,9 +397,9 @@ static int ctr_encrypt(struct skcipher_request *req)
 	}
 	if (walk.nbytes) {
 		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+		const u8 *tsrc = walk.src.virt.addr;
 		unsigned int nbytes = walk.nbytes;
 		u8 *tdst = walk.dst.virt.addr;
-		u8 *tsrc = walk.src.virt.addr;
 
 		/*
 		 * Tell aes_ctr_encrypt() to process a tail block.
@@ -418,29 +416,6 @@ static int ctr_encrypt(struct skcipher_request *req)
 	return err;
 }
 
-static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
-{
-	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	unsigned long flags;
-
-	/*
-	 * Temporarily disable interrupts to avoid races where
-	 * cachelines are evicted when the CPU is interrupted
-	 * to do something else.
-	 */
-	local_irq_save(flags);
-	aes_encrypt(ctx, dst, src);
-	local_irq_restore(flags);
-}
-
-static int ctr_encrypt_sync(struct skcipher_request *req)
-{
-	if (!crypto_simd_usable())
-		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
-
-	return ctr_encrypt(req);
-}
-
 static int xts_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -586,10 +561,9 @@ static int xts_decrypt(struct skcipher_request *req)
 }
 
 static struct skcipher_alg aes_algs[] = { {
-	.base.cra_name		= "__ecb(aes)",
-	.base.cra_driver_name	= "__ecb-aes-ce",
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-ce",
 	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
 	.base.cra_module	= THIS_MODULE,
@@ -600,10 +574,9 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ecb_encrypt,
 	.decrypt		= ecb_decrypt,
 }, {
-	.base.cra_name		= "__cbc(aes)",
-	.base.cra_driver_name	= "__cbc-aes-ce",
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-ce",
 	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
 	.base.cra_module	= THIS_MODULE,
@@ -615,10 +588,9 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= cbc_encrypt,
 	.decrypt		= cbc_decrypt,
 }, {
-	.base.cra_name		= "__cts(cbc(aes))",
-	.base.cra_driver_name	= "__cts-cbc-aes-ce",
+	.base.cra_name		= "cts(cbc(aes))",
+	.base.cra_driver_name	= "cts-cbc-aes-ce",
 	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
 	.base.cra_module	= THIS_MODULE,
@@ -631,10 +603,9 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= cts_cbc_encrypt,
 	.decrypt		= cts_cbc_decrypt,
 }, {
-	.base.cra_name		= "__ctr(aes)",
-	.base.cra_driver_name	= "__ctr-aes-ce",
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-ce",
 	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
 	.base.cra_module	= THIS_MODULE,
@@ -647,25 +618,9 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ctr_encrypt,
 	.decrypt		= ctr_encrypt,
 }, {
-	.base.cra_name		= "ctr(aes)",
-	.base.cra_driver_name	= "ctr-aes-ce-sync",
-	.base.cra_priority	= 300 - 1,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct crypto_aes_ctx),
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.chunksize		= AES_BLOCK_SIZE,
-	.setkey			= ce_aes_setkey,
-	.encrypt		= ctr_encrypt_sync,
-	.decrypt		= ctr_encrypt_sync,
-}, {
-	.base.cra_name		= "__xts(aes)",
-	.base.cra_driver_name	= "__xts-aes-ce",
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "xts-aes-ce",
 	.base.cra_priority	= 300,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct crypto_aes_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
@@ -679,51 +634,14 @@ static struct skcipher_alg aes_algs[] = { {
 	.decrypt		= xts_decrypt,
 } };
 
-static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
-
 static void aes_exit(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(aes_simd_algs) && aes_simd_algs[i]; i++)
-		simd_skcipher_free(aes_simd_algs[i]);
-
 	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
 static int __init aes_init(void)
 {
-	struct simd_skcipher_alg *simd;
-	const char *basename;
-	const char *algname;
-	const char *drvname;
-	int err;
-	int i;
-
-	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
-			continue;
-
-		algname = aes_algs[i].base.cra_name + 2;
-		drvname = aes_algs[i].base.cra_driver_name + 2;
-		basename = aes_algs[i].base.cra_driver_name;
-		simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename);
-		err = PTR_ERR(simd);
-		if (IS_ERR(simd))
-			goto unregister_simds;
-
-		aes_simd_algs[i] = simd;
-	}
-
-	return 0;
-
-unregister_simds:
-	aes_exit();
-	return err;
+	return crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
 module_cpu_feature_match(AES, aes_init);
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index f6be80b5938b..c60104dc1585 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -8,8 +8,6 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/aes.h>
-#include <crypto/ctr.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/xts.h>
@@ -59,11 +57,6 @@ struct aesbs_xts_ctx {
 	struct crypto_aes_ctx	tweak_key;
 };
 
-struct aesbs_ctr_ctx {
-	struct aesbs_ctx	key;		/* must be first member */
-	struct crypto_aes_ctx	fallback;
-};
-
 static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			unsigned int key_len)
 {
@@ -200,25 +193,6 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
-static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
-				 unsigned int key_len)
-{
-	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err;
-
-	err = aes_expandkey(&ctx->fallback, in_key, key_len);
-	if (err)
-		return err;
-
-	ctx->key.rounds = 6 + key_len / 4;
-
-	kernel_neon_begin();
-	aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
-	kernel_neon_end();
-
-	return 0;
-}
-
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -254,21 +228,6 @@ static int ctr_encrypt(struct skcipher_request *req)
 	return err;
 }
 
-static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
-{
-	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	__aes_arm_encrypt(ctx->fallback.key_enc, ctx->key.rounds, src, dst);
-}
-
-static int ctr_encrypt_sync(struct skcipher_request *req)
-{
-	if (!crypto_simd_usable())
-		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
-
-	return ctr_encrypt(req);
-}
-
 static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
@@ -374,13 +333,12 @@ static int xts_decrypt(struct skcipher_request *req)
 }
 
 static struct skcipher_alg aes_algs[] = { {
-	.base.cra_name		= "__ecb(aes)",
-	.base.cra_driver_name	= "__ecb-aes-neonbs",
+	.base.cra_name		= "ecb(aes)",
+	.base.cra_driver_name	= "ecb-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -389,13 +347,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ecb_encrypt,
 	.decrypt		= ecb_decrypt,
 }, {
-	.base.cra_name		= "__cbc(aes)",
-	.base.cra_driver_name	= "__cbc-aes-neonbs",
+	.base.cra_name		= "cbc(aes)",
+	.base.cra_driver_name	= "cbc-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -405,13 +362,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= cbc_encrypt,
 	.decrypt		= cbc_decrypt,
 }, {
-	.base.cra_name		= "__ctr(aes)",
-	.base.cra_driver_name	= "__ctr-aes-neonbs",
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -422,29 +378,12 @@ static struct skcipher_alg aes_algs[] = { {
 	.encrypt		= ctr_encrypt,
 	.decrypt		= ctr_encrypt,
 }, {
-	.base.cra_name		= "ctr(aes)",
-	.base.cra_driver_name	= "ctr-aes-neonbs-sync",
-	.base.cra_priority	= 250 - 1,
-	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct aesbs_ctr_ctx),
-	.base.cra_module	= THIS_MODULE,
-
-	.min_keysize		= AES_MIN_KEY_SIZE,
-	.max_keysize		= AES_MAX_KEY_SIZE,
-	.chunksize		= AES_BLOCK_SIZE,
-	.walksize		= 8 * AES_BLOCK_SIZE,
-	.ivsize			= AES_BLOCK_SIZE,
-	.setkey			= aesbs_ctr_setkey_sync,
-	.encrypt		= ctr_encrypt_sync,
-	.decrypt		= ctr_encrypt_sync,
-}, {
-	.base.cra_name		= "__xts(aes)",
-	.base.cra_driver_name	= "__xts-aes-neonbs",
+	.base.cra_name		= "xts(aes)",
+	.base.cra_driver_name	= "xts-aes-neonbs",
 	.base.cra_priority	= 250,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
-	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -455,55 +394,18 @@ static struct skcipher_alg aes_algs[] = { {
 	.decrypt		= xts_decrypt,
 } };
 
-static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
-
 static void aes_exit(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
-		if (aes_simd_algs[i])
-			simd_skcipher_free(aes_simd_algs[i]);
-
 	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
 static int __init aes_init(void)
 {
-	struct simd_skcipher_alg *simd;
-	const char *basename;
-	const char *algname;
-	const char *drvname;
-	int err;
-	int i;
-
 	if (!(elf_hwcap & HWCAP_NEON))
 		return -ENODEV;
 
-	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
-		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
-			continue;
-
-		algname = aes_algs[i].base.cra_name + 2;
-		drvname = aes_algs[i].base.cra_driver_name + 2;
-		basename = aes_algs[i].base.cra_driver_name;
-		simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename);
-		err = PTR_ERR(simd);
-		if (IS_ERR(simd))
-			goto unregister_simds;
-
-		aes_simd_algs[i] = simd;
-	}
-	return 0;
-
-unregister_simds:
-	aes_exit();
-	return err;
+	return crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
 }
 
-late_initcall(aes_init);
+module_init(aes_init);
 module_exit(aes_exit);
diff --git a/arch/arm/crypto/blake2b-neon-glue.c b/arch/arm/crypto/blake2b-neon-glue.c
index 4b59d027ba4a..2ff443a91724 100644
--- a/arch/arm/crypto/blake2b-neon-glue.c
+++ b/arch/arm/crypto/blake2b-neon-glue.c
@@ -7,7 +7,6 @@
 
 #include <crypto/internal/blake2b.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 
 #include <linux/module.h>
 #include <linux/sizes.h>
@@ -21,11 +20,6 @@ asmlinkage void blake2b_compress_neon(struct blake2b_state *state,
 static void blake2b_compress_arch(struct blake2b_state *state,
 				  const u8 *block, size_t nblocks, u32 inc)
 {
-	if (!crypto_simd_usable()) {
-		blake2b_compress_generic(state, block, nblocks, inc);
-		return;
-	}
-
 	do {
 		const size_t blocks = min_t(size_t, nblocks,
 					    SZ_4K / BLAKE2B_BLOCK_SIZE);
@@ -42,12 +36,14 @@ static void blake2b_compress_arch(struct blake2b_state *state,
 static int crypto_blake2b_update_neon(struct shash_desc *desc,
 				      const u8 *in, unsigned int inlen)
 {
-	return crypto_blake2b_update(desc, in, inlen, blake2b_compress_arch);
+	return crypto_blake2b_update_bo(desc, in, inlen, blake2b_compress_arch);
 }
 
-static int crypto_blake2b_final_neon(struct shash_desc *desc, u8 *out)
+static int crypto_blake2b_finup_neon(struct shash_desc *desc, const u8 *in,
+				     unsigned int inlen, u8 *out)
 {
-	return crypto_blake2b_final(desc, out, blake2b_compress_arch);
+	return crypto_blake2b_finup(desc, in, inlen, out,
+				    blake2b_compress_arch);
 }
 
 #define BLAKE2B_ALG(name, driver_name, digest_size)			\
@@ -55,7 +51,9 @@ static int crypto_blake2b_final_neon(struct shash_desc *desc, u8 *out)
 		.base.cra_name		= name,				\
 		.base.cra_driver_name	= driver_name,			\
 		.base.cra_priority	= 200,				\
-		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,	\
+		.base.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY |	\
+					  CRYPTO_AHASH_ALG_BLOCK_ONLY |	\
+					  CRYPTO_AHASH_ALG_FINAL_NONZERO, \
 		.base.cra_blocksize	= BLAKE2B_BLOCK_SIZE,		\
 		.base.cra_ctxsize	= sizeof(struct blake2b_tfm_ctx), \
 		.base.cra_module	= THIS_MODULE,			\
@@ -63,8 +61,9 @@ static int crypto_blake2b_final_neon(struct shash_desc *desc, u8 *out)
 		.setkey			= crypto_blake2b_setkey,	\
 		.init			= crypto_blake2b_init,		\
 		.update			= crypto_blake2b_update_neon,	\
-		.final			= crypto_blake2b_final_neon,	\
+		.finup			= crypto_blake2b_finup_neon,	\
 		.descsize		= sizeof(struct blake2b_state),	\
+		.statesize		= BLAKE2B_STATE_SIZE,		\
 	}
 
 static struct shash_alg blake2b_neon_algs[] = {
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
deleted file mode 100644
index cdde8fd01f8f..000000000000
--- a/arch/arm/crypto/chacha-glue.c
+++ /dev/null
@@ -1,358 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/cputype.h>
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				      int nrounds);
-asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
-				       int nrounds, unsigned int nbytes);
-asmlinkage void hchacha_block_arm(const u32 *state, u32 *out, int nrounds);
-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
-
-asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
-			     const u32 *state, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
-
-static inline bool neon_usable(void)
-{
-	return static_branch_likely(&use_neon) && crypto_simd_usable();
-}
-
-static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
-			  unsigned int bytes, int nrounds)
-{
-	u8 buf[CHACHA_BLOCK_SIZE];
-
-	while (bytes > CHACHA_BLOCK_SIZE) {
-		unsigned int l = min(bytes, CHACHA_BLOCK_SIZE * 4U);
-
-		chacha_4block_xor_neon(state, dst, src, nrounds, l);
-		bytes -= l;
-		src += l;
-		dst += l;
-		state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
-	}
-	if (bytes) {
-		const u8 *s = src;
-		u8 *d = dst;
-
-		if (bytes != CHACHA_BLOCK_SIZE)
-			s = d = memcpy(buf, src, bytes);
-		chacha_block_xor_neon(state, d, s, nrounds);
-		if (d != dst)
-			memcpy(dst, buf, bytes);
-		state[12]++;
-	}
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
-	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
-		hchacha_block_arm(state, stream, nrounds);
-	} else {
-		kernel_neon_begin();
-		hchacha_block_neon(state, stream, nrounds);
-		kernel_neon_end();
-	}
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
-		       int nrounds)
-{
-	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
-	    bytes <= CHACHA_BLOCK_SIZE) {
-		chacha_doarm(dst, src, bytes, state, nrounds);
-		state[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
-		return;
-	}
-
-	do {
-		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
-		kernel_neon_begin();
-		chacha_doneon(state, dst, src, todo, nrounds);
-		kernel_neon_end();
-
-		bytes -= todo;
-		src += todo;
-		dst += todo;
-	} while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_stream_xor(struct skcipher_request *req,
-			     const struct chacha_ctx *ctx, const u8 *iv,
-			     bool neon)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	chacha_init_generic(state, ctx->key, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon) {
-			chacha_doarm(walk.dst.virt.addr, walk.src.virt.addr,
-				     nbytes, state, ctx->nrounds);
-			state[12] += DIV_ROUND_UP(nbytes, CHACHA_BLOCK_SIZE);
-		} else {
-			kernel_neon_begin();
-			chacha_doneon(state, walk.dst.virt.addr,
-				      walk.src.virt.addr, nbytes, ctx->nrounds);
-			kernel_neon_end();
-		}
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int do_chacha(struct skcipher_request *req, bool neon)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return chacha_stream_xor(req, ctx, req->iv, neon);
-}
-
-static int chacha_arm(struct skcipher_request *req)
-{
-	return do_chacha(req, false);
-}
-
-static int chacha_neon(struct skcipher_request *req)
-{
-	return do_chacha(req, neon_usable());
-}
-
-static int do_xchacha(struct skcipher_request *req, bool neon)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 state[16];
-	u8 real_iv[16];
-
-	chacha_init_generic(state, ctx->key, req->iv);
-
-	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon) {
-		hchacha_block_arm(state, subctx.key, ctx->nrounds);
-	} else {
-		kernel_neon_begin();
-		hchacha_block_neon(state, subctx.key, ctx->nrounds);
-		kernel_neon_end();
-	}
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_stream_xor(req, &subctx, real_iv, neon);
-}
-
-static int xchacha_arm(struct skcipher_request *req)
-{
-	return do_xchacha(req, false);
-}
-
-static int xchacha_neon(struct skcipher_request *req)
-{
-	return do_xchacha(req, neon_usable());
-}
-
-static struct skcipher_alg arm_algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-arm",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_arm,
-		.decrypt		= chacha_arm,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-arm",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_arm,
-		.decrypt		= xchacha_arm,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-arm",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_arm,
-		.decrypt		= xchacha_arm,
-	},
-};
-
-static struct skcipher_alg neon_algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_neon,
-		.decrypt		= chacha_neon,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 4 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	int err = 0;
-
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
-		err = crypto_register_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
-		if (err)
-			return err;
-	}
-
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
-		int i;
-
-		switch (read_cpuid_part()) {
-		case ARM_CPU_PART_CORTEX_A7:
-		case ARM_CPU_PART_CORTEX_A5:
-			/*
-			 * The Cortex-A7 and Cortex-A5 do not perform well with
-			 * the NEON implementation but do incredibly with the
-			 * scalar one and use less power.
-			 */
-			for (i = 0; i < ARRAY_SIZE(neon_algs); i++)
-				neon_algs[i].base.cra_priority = 0;
-			break;
-		default:
-			static_branch_enable(&use_neon);
-		}
-
-		if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
-			err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
-			if (err)
-				crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
-		}
-	}
-	return err;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
-		crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
-		if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON))
-			crypto_unregister_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
-	}
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (scalar and NEON accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-arm");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-arm");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-arm");
-#ifdef CONFIG_KERNEL_MODE_NEON
-MODULE_ALIAS_CRYPTO("chacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha12-neon");
-#endif
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 3af997082534..a52dcc8c1e33 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -8,22 +8,22 @@
 
 #include <asm/hwcap.h>
 #include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/aes.h>
-#include <crypto/gcm.h>
 #include <crypto/b128ops.h>
-#include <crypto/cryptd.h>
+#include <crypto/gcm.h>
+#include <crypto/gf128mul.h>
+#include <crypto/ghash.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
-#include <crypto/gf128mul.h>
 #include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/errno.h>
 #include <linux/jump_label.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
 MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ardb@kernel.org>");
@@ -32,9 +32,6 @@ MODULE_ALIAS_CRYPTO("ghash");
 MODULE_ALIAS_CRYPTO("gcm(aes)");
 MODULE_ALIAS_CRYPTO("rfc4106(gcm(aes))");
 
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
-
 #define RFC4106_NONCE_SIZE	4
 
 struct ghash_key {
@@ -49,14 +46,8 @@ struct gcm_key {
 	u8	nonce[];	// for RFC4106 nonce
 };
 
-struct ghash_desc_ctx {
+struct arm_ghash_desc_ctx {
 	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
-	u8 buf[GHASH_BLOCK_SIZE];
-	u32 count;
-};
-
-struct ghash_async_ctx {
-	struct cryptd_ahash *cryptd_tfm;
 };
 
 asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
@@ -69,94 +60,69 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_p64);
 
 static int ghash_init(struct shash_desc *desc)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	*ctx = (struct ghash_desc_ctx){};
+	*ctx = (struct arm_ghash_desc_ctx){};
 	return 0;
 }
 
 static void ghash_do_update(int blocks, u64 dg[], const char *src,
 			    struct ghash_key *key, const char *head)
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_neon_begin();
-		if (static_branch_likely(&use_p64))
-			pmull_ghash_update_p64(blocks, dg, src, key->h, head);
-		else
-			pmull_ghash_update_p8(blocks, dg, src, key->h, head);
-		kernel_neon_end();
-	} else {
-		be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
-
-		do {
-			const u8 *in = src;
-
-			if (head) {
-				in = head;
-				blocks++;
-				head = NULL;
-			} else {
-				src += GHASH_BLOCK_SIZE;
-			}
-
-			crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
-			gf128mul_lle(&dst, &key->k);
-		} while (--blocks);
-
-		dg[0] = be64_to_cpu(dst.b);
-		dg[1] = be64_to_cpu(dst.a);
-	}
+	kernel_neon_begin();
+	if (static_branch_likely(&use_p64))
+		pmull_ghash_update_p64(blocks, dg, src, key->h, head);
+	else
+		pmull_ghash_update_p8(blocks, dg, src, key->h, head);
+	kernel_neon_end();
 }
 
 static int ghash_update(struct shash_desc *desc, const u8 *src,
 			unsigned int len)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+	struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	int blocks;
 
-	ctx->count += len;
-
-	if ((partial + len) >= GHASH_BLOCK_SIZE) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
-		int blocks;
+	blocks = len / GHASH_BLOCK_SIZE;
+	ghash_do_update(blocks, ctx->digest, src, key, NULL);
+	return len - blocks * GHASH_BLOCK_SIZE;
+}
 
-		if (partial) {
-			int p = GHASH_BLOCK_SIZE - partial;
+static int ghash_export(struct shash_desc *desc, void *out)
+{
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	u8 *dst = out;
 
-			memcpy(ctx->buf + partial, src, p);
-			src += p;
-			len -= p;
-		}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+	return 0;
+}
 
-		blocks = len / GHASH_BLOCK_SIZE;
-		len %= GHASH_BLOCK_SIZE;
+static int ghash_import(struct shash_desc *desc, const void *in)
+{
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	const u8 *src = in;
 
-		ghash_do_update(blocks, ctx->digest, src, key,
-				partial ? ctx->buf : NULL);
-		src += blocks * GHASH_BLOCK_SIZE;
-		partial = 0;
-	}
-	if (len)
-		memcpy(ctx->buf + partial, src, len);
+	ctx->digest[1] = get_unaligned_be64(src);
+	ctx->digest[0] = get_unaligned_be64(src + 8);
 	return 0;
 }
 
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *dst)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+	struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	if (partial) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
 
-		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
-		ghash_do_update(1, ctx->digest, ctx->buf, key, NULL);
+		memcpy(buf, src, len);
+		ghash_do_update(1, ctx->digest, buf, key, NULL);
+		memzero_explicit(buf, sizeof(buf));
 	}
-	put_unaligned_be64(ctx->digest[1], dst);
-	put_unaligned_be64(ctx->digest[0], dst + 8);
-
-	*ctx = (struct ghash_desc_ctx){};
-	return 0;
+	return ghash_export(desc, dst);
 }
 
 static void ghash_reflect(u64 h[], const be128 *k)
@@ -201,167 +167,22 @@ static struct shash_alg ghash_alg = {
 	.digestsize		= GHASH_DIGEST_SIZE,
 	.init			= ghash_init,
 	.update			= ghash_update,
-	.final			= ghash_final,
+	.finup			= ghash_finup,
 	.setkey			= ghash_setkey,
-	.descsize		= sizeof(struct ghash_desc_ctx),
+	.export			= ghash_export,
+	.import			= ghash_import,
+	.descsize		= sizeof(struct arm_ghash_desc_ctx),
+	.statesize		= sizeof(struct ghash_desc_ctx),
 
 	.base.cra_name		= "ghash",
-	.base.cra_driver_name	= "ghash-ce-sync",
-	.base.cra_priority	= 300 - 1,
+	.base.cra_driver_name	= "ghash-ce",
+	.base.cra_priority	= 300,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
 };
 
-static int ghash_async_init(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-	desc->tfm = child;
-	return crypto_shash_init(desc);
-}
-
-static int ghash_async_update(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_update(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return shash_ahash_update(req, desc);
-	}
-}
-
-static int ghash_async_final(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_final(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return crypto_shash_final(desc, req->result);
-	}
-}
-
-static int ghash_async_digest(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_digest(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		return shash_ahash_digest(req, desc);
-	}
-}
-
-static int ghash_async_import(struct ahash_request *req, const void *in)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-
-	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
-
-	return crypto_shash_import(desc, in);
-}
-
-static int ghash_async_export(struct ahash_request *req, void *out)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-
-	return crypto_shash_export(desc, out);
-}
-
-static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct crypto_ahash *child = &ctx->cryptd_tfm->base;
-
-	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
-			       & CRYPTO_TFM_REQ_MASK);
-	return crypto_ahash_setkey(child, key, keylen);
-}
-
-static int ghash_async_init_tfm(struct crypto_tfm *tfm)
-{
-	struct cryptd_ahash *cryptd_tfm;
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_tfm = cryptd_alloc_ahash("ghash-ce-sync", 0, 0);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-	ctx->cryptd_tfm = cryptd_tfm;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct ahash_request) +
-				 crypto_ahash_reqsize(&cryptd_tfm->base));
-
-	return 0;
-}
-
-static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ahash(ctx->cryptd_tfm);
-}
-
-static struct ahash_alg ghash_async_alg = {
-	.init			= ghash_async_init,
-	.update			= ghash_async_update,
-	.final			= ghash_async_final,
-	.setkey			= ghash_async_setkey,
-	.digest			= ghash_async_digest,
-	.import			= ghash_async_import,
-	.export			= ghash_async_export,
-	.halg.digestsize	= GHASH_DIGEST_SIZE,
-	.halg.statesize		= sizeof(struct ghash_desc_ctx),
-	.halg.base		= {
-		.cra_name	= "ghash",
-		.cra_driver_name = "ghash-ce",
-		.cra_priority	= 300,
-		.cra_flags	= CRYPTO_ALG_ASYNC,
-		.cra_blocksize	= GHASH_BLOCK_SIZE,
-		.cra_ctxsize	= sizeof(struct ghash_async_ctx),
-		.cra_module	= THIS_MODULE,
-		.cra_init	= ghash_async_init_tfm,
-		.cra_exit	= ghash_async_exit_tfm,
-	},
-};
-
-
 void pmull_gcm_encrypt(int blocks, u64 dg[], const char *src,
 		       struct gcm_key const *k, char *dst,
 		       const char *iv, int rounds, u32 counter);
@@ -459,17 +280,11 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[], u32 len)
 	scatterwalk_start(&walk, req->src);
 
 	do {
-		u32 n = scatterwalk_clamp(&walk, len);
-		u8 *p;
-
-		if (!n) {
-			scatterwalk_start(&walk, sg_next(walk.sg));
-			n = scatterwalk_clamp(&walk, len);
-		}
+		unsigned int n;
 
-		p = scatterwalk_map(&walk);
-		gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
-		scatterwalk_unmap(p);
+		n = scatterwalk_next(&walk, len);
+		gcm_update_mac(dg, walk.addr, n, buf, &buf_count, ctx);
+		scatterwalk_done_src(&walk,  n);
 
 		if (unlikely(len / SZ_4K > (len - n) / SZ_4K)) {
 			kernel_neon_end();
@@ -477,8 +292,6 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[], u32 len)
 		}
 
 		len -= n;
-		scatterwalk_advance(&walk, n);
-		scatterwalk_done(&walk, 0, len);
 	} while (len);
 
 	if (buf_count) {
@@ -500,9 +313,6 @@ static int gcm_encrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
 	u8 *tag, *dst;
 	int tail, err;
 
-	if (WARN_ON_ONCE(!may_use_simd()))
-		return -EBUSY;
-
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
 	kernel_neon_begin();
@@ -592,9 +402,6 @@ static int gcm_decrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
 	u8 *tag, *dst;
 	int tail, err, ret;
 
-	if (WARN_ON_ONCE(!may_use_simd()))
-		return -EBUSY;
-
 	scatterwalk_map_and_copy(otag, req->src,
 				 req->assoclen + req->cryptlen - authsize,
 				 authsize, 0);
@@ -767,14 +574,9 @@ static int __init ghash_ce_mod_init(void)
 	err = crypto_register_shash(&ghash_alg);
 	if (err)
 		goto err_aead;
-	err = crypto_register_ahash(&ghash_async_alg);
-	if (err)
-		goto err_shash;
 
 	return 0;
 
-err_shash:
-	crypto_unregister_shash(&ghash_alg);
 err_aead:
 	if (elf_hwcap2 & HWCAP2_PMULL)
 		crypto_unregister_aeads(gcm_aes_algs,
@@ -784,7 +586,6 @@ err_aead:
 
 static void __exit ghash_ce_mod_exit(void)
 {
-	crypto_unregister_ahash(&ghash_async_alg);
 	crypto_unregister_shash(&ghash_alg);
 	if (elf_hwcap2 & HWCAP2_PMULL)
 		crypto_unregister_aeads(gcm_aes_algs,
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
deleted file mode 100644
index 4464ffbf8fd1..000000000000
--- a/arch/arm/crypto/poly1305-glue.c
+++ /dev/null
@@ -1,274 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/jump_label.h>
-#include <linux/module.h>
-
-void poly1305_init_arm(void *state, const u8 *key);
-void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
-void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
-void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);
-
-void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
-{
-}
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	poly1305_init_arm(&dctx->h, key);
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static int arm_poly1305_init(struct shash_desc *desc)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	dctx->buflen = 0;
-	dctx->rset = 0;
-	dctx->sset = false;
-
-	return 0;
-}
-
-static void arm_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
-				 u32 len, u32 hibit, bool do_neon)
-{
-	if (unlikely(!dctx->sset)) {
-		if (!dctx->rset) {
-			poly1305_init_arm(&dctx->h, src);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (len >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(src +  0);
-			dctx->s[1] = get_unaligned_le32(src +  4);
-			dctx->s[2] = get_unaligned_le32(src +  8);
-			dctx->s[3] = get_unaligned_le32(src + 12);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-		if (len < POLY1305_BLOCK_SIZE)
-			return;
-	}
-
-	len &= ~(POLY1305_BLOCK_SIZE - 1);
-
-	if (static_branch_likely(&have_neon) && likely(do_neon))
-		poly1305_blocks_neon(&dctx->h, src, len, hibit);
-	else
-		poly1305_blocks_arm(&dctx->h, src, len, hibit);
-}
-
-static void arm_poly1305_do_update(struct poly1305_desc_ctx *dctx,
-				    const u8 *src, u32 len, bool do_neon)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		len -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			arm_poly1305_blocks(dctx, dctx->buf,
-					    POLY1305_BLOCK_SIZE, 1, false);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(len >= POLY1305_BLOCK_SIZE)) {
-		arm_poly1305_blocks(dctx, src, len, 1, do_neon);
-		src += round_down(len, POLY1305_BLOCK_SIZE);
-		len %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(len)) {
-		dctx->buflen = len;
-		memcpy(dctx->buf, src, len);
-	}
-}
-
-static int arm_poly1305_update(struct shash_desc *desc,
-			       const u8 *src, unsigned int srclen)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	arm_poly1305_do_update(dctx, src, srclen, false);
-	return 0;
-}
-
-static int __maybe_unused arm_poly1305_update_neon(struct shash_desc *desc,
-						   const u8 *src,
-						   unsigned int srclen)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	bool do_neon = crypto_simd_usable() && srclen > 128;
-
-	if (static_branch_likely(&have_neon) && do_neon)
-		kernel_neon_begin();
-	arm_poly1305_do_update(dctx, src, srclen, do_neon);
-	if (static_branch_likely(&have_neon) && do_neon)
-		kernel_neon_end();
-	return 0;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	bool do_neon = IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
-		       crypto_simd_usable();
-
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_arm(&dctx->h, dctx->buf,
-					    POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
-
-		if (static_branch_likely(&have_neon) && do_neon) {
-			do {
-				unsigned int todo = min_t(unsigned int, len, SZ_4K);
-
-				kernel_neon_begin();
-				poly1305_blocks_neon(&dctx->h, src, todo, 1);
-				kernel_neon_end();
-
-				len -= todo;
-				src += todo;
-			} while (len);
-		} else {
-			poly1305_blocks_arm(&dctx->h, src, len, 1);
-			src += len;
-		}
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arm(&dctx->h, dst, dctx->s);
-	*dctx = (struct poly1305_desc_ctx){};
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int arm_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(!dctx->sset))
-		return -ENOKEY;
-
-	poly1305_final_arch(dctx, dst);
-	return 0;
-}
-
-static struct shash_alg arm_poly1305_algs[] = {{
-	.init			= arm_poly1305_init,
-	.update			= arm_poly1305_update,
-	.final			= arm_poly1305_final,
-	.digestsize		= POLY1305_DIGEST_SIZE,
-	.descsize		= sizeof(struct poly1305_desc_ctx),
-
-	.base.cra_name		= "poly1305",
-	.base.cra_driver_name	= "poly1305-arm",
-	.base.cra_priority	= 150,
-	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-#ifdef CONFIG_KERNEL_MODE_NEON
-}, {
-	.init			= arm_poly1305_init,
-	.update			= arm_poly1305_update_neon,
-	.final			= arm_poly1305_final,
-	.digestsize		= POLY1305_DIGEST_SIZE,
-	.descsize		= sizeof(struct poly1305_desc_ctx),
-
-	.base.cra_name		= "poly1305",
-	.base.cra_driver_name	= "poly1305-neon",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-#endif
-}};
-
-static int __init arm_poly1305_mod_init(void)
-{
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
-	    (elf_hwcap & HWCAP_NEON))
-		static_branch_enable(&have_neon);
-	else if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
-		/* register only the first entry */
-		return crypto_register_shash(&arm_poly1305_algs[0]);
-
-	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
-		crypto_register_shashes(arm_poly1305_algs,
-					ARRAY_SIZE(arm_poly1305_algs)) : 0;
-}
-
-static void __exit arm_poly1305_mod_exit(void)
-{
-	if (!IS_REACHABLE(CONFIG_CRYPTO_HASH))
-		return;
-	if (!static_branch_likely(&have_neon)) {
-		crypto_unregister_shash(&arm_poly1305_algs[0]);
-		return;
-	}
-	crypto_unregister_shashes(arm_poly1305_algs,
-				  ARRAY_SIZE(arm_poly1305_algs));
-}
-
-module_init(arm_poly1305_mod_init);
-module_exit(arm_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Accelerated Poly1305 transform for ARM");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-arm");
-MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index de9100c67b37..fac07a4799de 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -5,20 +5,14 @@
  * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
+#include <asm/neon.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-#include "sha1.h"
-
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -29,50 +23,36 @@ asmlinkage void sha1_ce_transform(struct sha1_state *sst, u8 const *src,
 static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
-		return sha1_update_arm(desc, data, len);
+	int remain;
 
 	kernel_neon_begin();
-	sha1_base_do_update(desc, data, len, sha1_ce_transform);
+	remain = sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
 	kernel_neon_end();
 
-	return 0;
+	return remain;
 }
 
 static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable())
-		return sha1_finup_arm(desc, data, len, out);
-
 	kernel_neon_begin();
-	if (len)
-		sha1_base_do_update(desc, data, len, sha1_ce_transform);
-	sha1_base_do_finalize(desc, sha1_ce_transform);
+	sha1_base_do_finup(desc, data, len, sha1_ce_transform);
 	kernel_neon_end();
 
 	return sha1_base_finish(desc, out);
 }
 
-static int sha1_ce_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_ce_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg alg = {
 	.init			= sha1_base_init,
 	.update			= sha1_ce_update,
-	.final			= sha1_ce_final,
 	.finup			= sha1_ce_finup,
-	.descsize		= sizeof(struct sha1_state),
+	.descsize		= SHA1_STATE_SIZE,
 	.digestsize		= SHA1_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-ce",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha1.h b/arch/arm/crypto/sha1.h
deleted file mode 100644
index b1b7e21da2c3..000000000000
--- a/arch/arm/crypto/sha1.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_ARM_CRYPTO_SHA1_H
-#define ASM_ARM_CRYPTO_SHA1_H
-
-#include <linux/crypto.h>
-#include <crypto/sha1.h>
-
-extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
-			   unsigned int len);
-
-extern int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
-			   unsigned int len, u8 *out);
-
-#endif
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 95a727bcd664..255da00c7d98 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -12,53 +12,42 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <asm/byteorder.h>
-
-#include "sha1.h"
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 asmlinkage void sha1_block_data_order(struct sha1_state *digest,
 		const u8 *data, int rounds);
 
-int sha1_update_arm(struct shash_desc *desc, const u8 *data,
-		    unsigned int len)
+static int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+			   unsigned int len)
 {
 	/* make sure signature matches sha1_block_fn() */
 	BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
 
-	return sha1_base_do_update(desc, data, len, sha1_block_data_order);
+	return sha1_base_do_update_blocks(desc, data, len,
+					  sha1_block_data_order);
 }
-EXPORT_SYMBOL_GPL(sha1_update_arm);
 
-static int sha1_final(struct shash_desc *desc, u8 *out)
+static int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
+			  unsigned int len, u8 *out)
 {
-	sha1_base_do_finalize(desc, sha1_block_data_order);
+	sha1_base_do_finup(desc, data, len, sha1_block_data_order);
 	return sha1_base_finish(desc, out);
 }
 
-int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
-		   unsigned int len, u8 *out)
-{
-	sha1_base_do_update(desc, data, len, sha1_block_data_order);
-	return sha1_final(desc, out);
-}
-EXPORT_SYMBOL_GPL(sha1_finup_arm);
-
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_update_arm,
-	.final		=	sha1_final,
 	.finup		=	sha1_finup_arm,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-asm",
 		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 9c70b87e69f7..d321850f22a6 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -13,18 +13,12 @@
  *  Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
  */
 
+#include <asm/neon.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-#include "sha1.h"
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 asmlinkage void sha1_transform_neon(struct sha1_state *state_h,
 				    const u8 *data, int rounds);
@@ -32,50 +26,37 @@ asmlinkage void sha1_transform_neon(struct sha1_state *state_h,
 static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
-		return sha1_update_arm(desc, data, len);
+	int remain;
 
 	kernel_neon_begin();
-	sha1_base_do_update(desc, data, len, sha1_transform_neon);
+	remain = sha1_base_do_update_blocks(desc, data, len,
+					    sha1_transform_neon);
 	kernel_neon_end();
 
-	return 0;
+	return remain;
 }
 
 static int sha1_neon_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable())
-		return sha1_finup_arm(desc, data, len, out);
-
 	kernel_neon_begin();
-	if (len)
-		sha1_base_do_update(desc, data, len, sha1_transform_neon);
-	sha1_base_do_finalize(desc, sha1_transform_neon);
+	sha1_base_do_finup(desc, data, len, sha1_transform_neon);
 	kernel_neon_end();
 
 	return sha1_base_finish(desc, out);
 }
 
-static int sha1_neon_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_neon_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_neon_update,
-	.final		=	sha1_neon_final,
 	.finup		=	sha1_neon_finup,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize		= SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-neon",
 		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
deleted file mode 100644
index aeac45bfbf9f..000000000000
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ /dev/null
@@ -1,109 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/module.h>
-
-#include <asm/hwcap.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-#include <linux/unaligned.h>
-
-#include "sha256_glue.h"
-
-MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-
-asmlinkage void sha2_ce_transform(struct sha256_state *sst, u8 const *src,
-				  int blocks);
-
-static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
-			  unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
-		return crypto_sha256_arm_update(desc, data, len);
-
-	kernel_neon_begin();
-	sha256_base_do_update(desc, data, len,
-			      (sha256_block_fn *)sha2_ce_transform);
-	kernel_neon_end();
-
-	return 0;
-}
-
-static int sha2_ce_finup(struct shash_desc *desc, const u8 *data,
-			 unsigned int len, u8 *out)
-{
-	if (!crypto_simd_usable())
-		return crypto_sha256_arm_finup(desc, data, len, out);
-
-	kernel_neon_begin();
-	if (len)
-		sha256_base_do_update(desc, data, len,
-				      (sha256_block_fn *)sha2_ce_transform);
-	sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
-	kernel_neon_end();
-
-	return sha256_base_finish(desc, out);
-}
-
-static int sha2_ce_final(struct shash_desc *desc, u8 *out)
-{
-	return sha2_ce_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg algs[] = { {
-	.init			= sha224_base_init,
-	.update			= sha2_ce_update,
-	.final			= sha2_ce_final,
-	.finup			= sha2_ce_finup,
-	.descsize		= sizeof(struct sha256_state),
-	.digestsize		= SHA224_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha224",
-		.cra_driver_name	= "sha224-ce",
-		.cra_priority		= 300,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-}, {
-	.init			= sha256_base_init,
-	.update			= sha2_ce_update,
-	.final			= sha2_ce_final,
-	.finup			= sha2_ce_finup,
-	.descsize		= sizeof(struct sha256_state),
-	.digestsize		= SHA256_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha256",
-		.cra_driver_name	= "sha256-ce",
-		.cra_priority		= 300,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-} };
-
-static int __init sha2_ce_mod_init(void)
-{
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha2_ce_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_cpu_feature_match(SHA2, sha2_ce_mod_init);
-module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
deleted file mode 100644
index f85933fdec75..000000000000
--- a/arch/arm/crypto/sha256_glue.c
+++ /dev/null
@@ -1,117 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
- * using optimized ARM assembler and NEON instructions.
- *
- * Copyright © 2015 Google Inc.
- *
- * This file is based on sha256_ssse3_glue.c:
- *   Copyright (C) 2013 Intel Corporation
- *   Author: Tim Chen <tim.c.chen@linux.intel.com>
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-#include "sha256_glue.h"
-
-asmlinkage void sha256_block_data_order(struct sha256_state *state,
-					const u8 *data, int num_blks);
-
-int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
-{
-	/* make sure casting to sha256_block_fn() is safe */
-	BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
-
-	return sha256_base_do_update(desc, data, len, sha256_block_data_order);
-}
-EXPORT_SYMBOL(crypto_sha256_arm_update);
-
-static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out)
-{
-	sha256_base_do_finalize(desc, sha256_block_data_order);
-	return sha256_base_finish(desc, out);
-}
-
-int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
-			    unsigned int len, u8 *out)
-{
-	sha256_base_do_update(desc, data, len, sha256_block_data_order);
-	return crypto_sha256_arm_final(desc, out);
-}
-EXPORT_SYMBOL(crypto_sha256_arm_finup);
-
-static struct shash_alg algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	crypto_sha256_arm_update,
-	.final		=	crypto_sha256_arm_final,
-	.finup		=	crypto_sha256_arm_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-asm",
-		.cra_priority	=	150,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	crypto_sha256_arm_update,
-	.final		=	crypto_sha256_arm_final,
-	.finup		=	crypto_sha256_arm_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-asm",
-		.cra_priority	=	150,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init sha256_mod_init(void)
-{
-	int res = crypto_register_shashes(algs, ARRAY_SIZE(algs));
-
-	if (res < 0)
-		return res;
-
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
-		res = crypto_register_shashes(sha256_neon_algs,
-					      ARRAY_SIZE(sha256_neon_algs));
-
-		if (res < 0)
-			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-	}
-
-	return res;
-}
-
-static void __exit sha256_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
-		crypto_unregister_shashes(sha256_neon_algs,
-					  ARRAY_SIZE(sha256_neon_algs));
-}
-
-module_init(sha256_mod_init);
-module_exit(sha256_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm (ARM), including NEON");
-
-MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/arm/crypto/sha256_glue.h b/arch/arm/crypto/sha256_glue.h
deleted file mode 100644
index 9f0d578bab5f..000000000000
--- a/arch/arm/crypto/sha256_glue.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _CRYPTO_SHA256_GLUE_H
-#define _CRYPTO_SHA256_GLUE_H
-
-#include <linux/crypto.h>
-
-extern struct shash_alg sha256_neon_algs[2];
-
-int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len);
-
-int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
-			    unsigned int len, u8 *hash);
-
-#endif /* _CRYPTO_SHA256_GLUE_H */
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
deleted file mode 100644
index ccdcfff71910..000000000000
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ /dev/null
@@ -1,92 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
- * using NEON instructions.
- *
- * Copyright © 2015 Google Inc.
- *
- * This file is based on sha512_neon_glue.c:
- *   Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- */
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <asm/byteorder.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-#include "sha256_glue.h"
-
-asmlinkage void sha256_block_data_order_neon(struct sha256_state *digest,
-					     const u8 *data, int num_blks);
-
-static int crypto_sha256_neon_update(struct shash_desc *desc, const u8 *data,
-				     unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
-		return crypto_sha256_arm_update(desc, data, len);
-
-	kernel_neon_begin();
-	sha256_base_do_update(desc, data, len, sha256_block_data_order_neon);
-	kernel_neon_end();
-
-	return 0;
-}
-
-static int crypto_sha256_neon_finup(struct shash_desc *desc, const u8 *data,
-				    unsigned int len, u8 *out)
-{
-	if (!crypto_simd_usable())
-		return crypto_sha256_arm_finup(desc, data, len, out);
-
-	kernel_neon_begin();
-	if (len)
-		sha256_base_do_update(desc, data, len,
-				      sha256_block_data_order_neon);
-	sha256_base_do_finalize(desc, sha256_block_data_order_neon);
-	kernel_neon_end();
-
-	return sha256_base_finish(desc, out);
-}
-
-static int crypto_sha256_neon_final(struct shash_desc *desc, u8 *out)
-{
-	return crypto_sha256_neon_finup(desc, NULL, 0, out);
-}
-
-struct shash_alg sha256_neon_algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	crypto_sha256_neon_update,
-	.final		=	crypto_sha256_neon_final,
-	.finup		=	crypto_sha256_neon_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-neon",
-		.cra_priority	=	250,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	crypto_sha256_neon_update,
-	.final		=	crypto_sha256_neon_final,
-	.finup		=	crypto_sha256_neon_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-neon",
-		.cra_priority	=	250,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
index 1be5bd498af3..f8a6480889b1 100644
--- a/arch/arm/crypto/sha512-glue.c
+++ b/arch/arm/crypto/sha512-glue.c
@@ -5,15 +5,14 @@
  * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
+#include <asm/hwcap.h>
+#include <asm/neon.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-
 #include "sha512.h"
 
 MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
@@ -28,50 +27,47 @@ MODULE_ALIAS_CRYPTO("sha512-arm");
 asmlinkage void sha512_block_data_order(struct sha512_state *state,
 					u8 const *src, int blocks);
 
-int sha512_arm_update(struct shash_desc *desc, const u8 *data,
-		      unsigned int len)
+static int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
 {
-	return sha512_base_do_update(desc, data, len, sha512_block_data_order);
+	return sha512_base_do_update_blocks(desc, data, len,
+					    sha512_block_data_order);
 }
 
-static int sha512_arm_final(struct shash_desc *desc, u8 *out)
+static int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+			    unsigned int len, u8 *out)
 {
-	sha512_base_do_finalize(desc, sha512_block_data_order);
+	sha512_base_do_finup(desc, data, len, sha512_block_data_order);
 	return sha512_base_finish(desc, out);
 }
 
-int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
-		     unsigned int len, u8 *out)
-{
-	sha512_base_do_update(desc, data, len, sha512_block_data_order);
-	return sha512_arm_final(desc, out);
-}
-
 static struct shash_alg sha512_arm_algs[] = { {
 	.init			= sha384_base_init,
 	.update			= sha512_arm_update,
-	.final			= sha512_arm_final,
 	.finup			= sha512_arm_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA384_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "sha384-arm",
 		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					  CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
 },  {
 	.init			= sha512_base_init,
 	.update			= sha512_arm_update,
-	.final			= sha512_arm_final,
 	.finup			= sha512_arm_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA512_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "sha512-arm",
 		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					  CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
index c6e58fe475ac..bd528077fefb 100644
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -5,16 +5,13 @@
  * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
+#include <asm/neon.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
-#include <asm/simd.h>
-#include <asm/neon.h>
-
 #include "sha512.h"
 
 MODULE_ALIAS_CRYPTO("sha384-neon");
@@ -26,51 +23,36 @@ asmlinkage void sha512_block_data_order_neon(struct sha512_state *state,
 static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
 			      unsigned int len)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
-		return sha512_arm_update(desc, data, len);
+	int remain;
 
 	kernel_neon_begin();
-	sha512_base_do_update(desc, data, len, sha512_block_data_order_neon);
+	remain = sha512_base_do_update_blocks(desc, data, len,
+					      sha512_block_data_order_neon);
 	kernel_neon_end();
-
-	return 0;
+	return remain;
 }
 
 static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
 			     unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable())
-		return sha512_arm_finup(desc, data, len, out);
-
 	kernel_neon_begin();
-	if (len)
-		sha512_base_do_update(desc, data, len,
-				      sha512_block_data_order_neon);
-	sha512_base_do_finalize(desc, sha512_block_data_order_neon);
+	sha512_base_do_finup(desc, data, len, sha512_block_data_order_neon);
 	kernel_neon_end();
-
 	return sha512_base_finish(desc, out);
 }
 
-static int sha512_neon_final(struct shash_desc *desc, u8 *out)
-{
-	return sha512_neon_finup(desc, NULL, 0, out);
-}
-
 struct shash_alg sha512_neon_algs[] = { {
 	.init			= sha384_base_init,
 	.update			= sha512_neon_update,
-	.final			= sha512_neon_final,
 	.finup			= sha512_neon_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA384_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "sha384-neon",
 		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					  CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 
@@ -78,14 +60,15 @@ struct shash_alg sha512_neon_algs[] = { {
 },  {
 	.init			= sha512_base_init,
 	.update			= sha512_neon_update,
-	.final			= sha512_neon_final,
 	.finup			= sha512_neon_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA512_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "sha512-neon",
 		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					  CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
index e14572be76d1..eeaee52cda69 100644
--- a/arch/arm/crypto/sha512.h
+++ b/arch/arm/crypto/sha512.h
@@ -1,9 +1,3 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-int sha512_arm_update(struct shash_desc *desc, const u8 *data,
-		      unsigned int len);
-
-int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
-		     unsigned int len, u8 *out);
-
 extern struct shash_alg sha512_neon_algs[2];
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1815748f5d2a..bae5edf348ef 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -381,7 +381,7 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 void iounmap(volatile void __iomem *io_addr);
 #define iounmap iounmap
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size);
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
 #define arch_memremap_wb arch_memremap_wb
 
 /*
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index be91e376df79..6b986ef6042f 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -19,14 +19,13 @@ extern struct page *empty_zero_page;
 #define ZERO_PAGE(vaddr)	(empty_zero_page)
 #endif
 
-#ifndef CONFIG_MMU
-
 #include <asm-generic/pgtable-nopud.h>
+
+#ifndef CONFIG_MMU
 #include <asm/pgtable-nommu.h>
 
 #else
 
-#include <asm-generic/pgtable-nopud.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 
diff --git a/arch/arm/include/asm/simd.h b/arch/arm/include/asm/simd.h
index 82191dbd7e78..d37559762180 100644
--- a/arch/arm/include/asm/simd.h
+++ b/arch/arm/include/asm/simd.h
@@ -1,8 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SIMD_H
+#define _ASM_SIMD_H
 
-#include <linux/hardirq.h>
+#include <linux/compiler_attributes.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
 
 static __must_check inline bool may_use_simd(void)
 {
 	return IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && !in_hardirq();
 }
+
+#endif	/* _ASM_SIMD_H */
diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 5b85889f82ee..88364a6727ff 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -4,6 +4,8 @@
 
 #ifdef __KERNEL__
 
+#define __VDSO_PAGES	4
+
 #ifndef __ASSEMBLY__
 
 struct mm_struct;
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 592d3d015ca7..1e9f81639c88 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -112,7 +112,7 @@ static inline bool arm_vdso_hres_capable(void)
 #define __arch_vdso_hres_capable arm_vdso_hres_capable
 
 static __always_inline u64 __arch_get_hw_counter(int clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 #ifdef CONFIG_ARM_ARCH_TIMER
 	u64 cycle_now;
@@ -135,11 +135,6 @@ static __always_inline u64 __arch_get_hw_counter(int clock_mode,
 #endif
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h
index 705414710dcd..4e7226ad02ec 100644
--- a/arch/arm/include/asm/vdso/vsyscall.h
+++ b/arch/arm/include/asm/vdso/vsyscall.h
@@ -7,22 +7,14 @@
 #include <vdso/datapage.h>
 #include <asm/cacheflush.h>
 
-extern struct vdso_data *vdso_data;
 extern bool cntvct_ok;
 
 static __always_inline
-struct vdso_data *__arm_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __arm_get_k_vdso_data
-
-static __always_inline
-void __arm_sync_vdso_data(struct vdso_data *vdata)
+void __arch_sync_vdso_time_data(struct vdso_time_data *vdata)
 {
 	flush_dcache_page(virt_to_page(vdata));
 }
-#define __arch_sync_vdso_data __arm_sync_vdso_data
+#define __arch_sync_vdso_time_data __arch_sync_vdso_time_data
 
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h
index d60f6e83a9f7..0341973e30e1 100644
--- a/arch/arm/include/asm/vmlinux.lds.h
+++ b/arch/arm/include/asm/vmlinux.lds.h
@@ -19,7 +19,7 @@
 #endif
 
 #ifdef CONFIG_MMU
-#define ARM_MMU_KEEP(x)		x
+#define ARM_MMU_KEEP(x)		KEEP(x)
 #define ARM_MMU_DISCARD(x)
 #else
 #define ARM_MMU_KEEP(x)
@@ -34,6 +34,12 @@
 #define NOCROSSREFS
 #endif
 
+#ifdef CONFIG_LD_CAN_USE_KEEP_IN_OVERLAY
+#define OVERLAY_KEEP(x)		KEEP(x)
+#else
+#define OVERLAY_KEEP(x)		x
+#endif
+
 /* Set start/end symbol names to the LMA for the section */
 #define ARM_LMA(sym, section)						\
 	sym##_start = LOADADDR(section);				\
@@ -125,13 +131,13 @@
 	__vectors_lma = .;						\
 	OVERLAY 0xffff0000 : NOCROSSREFS AT(__vectors_lma) {		\
 		.vectors {						\
-			*(.vectors)					\
+			OVERLAY_KEEP(*(.vectors))			\
 		}							\
 		.vectors.bhb.loop8 {					\
-			*(.vectors.bhb.loop8)				\
+			OVERLAY_KEEP(*(.vectors.bhb.loop8))		\
 		}							\
 		.vectors.bhb.bpiall {					\
-			*(.vectors.bhb.bpiall)				\
+			OVERLAY_KEEP(*(.vectors.bhb.bpiall))		\
 		}							\
 	}								\
 	ARM_LMA(__vectors, .vectors);					\
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 4853875740d0..123f4a8ef446 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -153,10 +153,6 @@ int main(void)
   DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER);
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
-#ifdef CONFIG_VDSO
-  DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
-#endif
-  BLANK();
 #ifdef CONFIG_ARM_MPU
   DEFINE(MPU_RNG_INFO_RNGS,	offsetof(struct mpu_rgn_info, rgns));
   DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
index da2ee8d6ef1a..354ce16d83cb 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -285,11 +285,9 @@ bool in_module_plt(unsigned long loc)
 	struct module *mod;
 	bool ret;
 
-	preempt_disable();
+	guard(rcu)();
 	mod = __module_text_address(loc);
 	ret = mod && (loc - (u32)mod->arch.core.plt_ent < mod->arch.core.plt_count * PLT_ENT_SIZE ||
 		      loc - (u32)mod->arch.init.plt_ent < mod->arch.init.plt_count * PLT_ENT_SIZE);
-	preempt_enable();
-
 	return ret;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 3431c0553f45..50999886a8b5 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -551,7 +551,8 @@ void show_ipi_list(struct seq_file *p, int prec)
 		if (!ipi_desc[i])
 			continue;
 
-		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
+		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+			   prec >= 4 ? " " : "");
 
 		for_each_online_cpu(cpu)
 			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 6ea645939573..afbd2ebe5c39 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -258,13 +258,6 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 	barrier();
 }
 
-#ifdef CONFIG_PREEMPT
-#define S_PREEMPT " PREEMPT"
-#elif defined(CONFIG_PREEMPT_RT)
-#define S_PREEMPT " PREEMPT_RT"
-#else
-#define S_PREEMPT ""
-#endif
 #ifdef CONFIG_SMP
 #define S_SMP " SMP"
 #else
@@ -282,8 +275,8 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 	static int die_counter;
 	int ret;
 
-	pr_emerg("Internal error: %s: %x [#%d]" S_PREEMPT S_SMP S_ISA "\n",
-	         str, err, ++die_counter);
+	pr_emerg("Internal error: %s: %x [#%d]" S_SMP S_ISA "\n",
+		 str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 29dd2f3c62fe..325448ffbba0 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/cache.h>
+#include <linux/vdso_datastore.h>
 #include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -33,15 +34,6 @@ extern char vdso_start[], vdso_end[];
 /* Total number of pages needed for the data and text portions of the VDSO. */
 unsigned int vdso_total_pages __ro_after_init;
 
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
-
-static struct page *vdso_data_page __ro_after_init;
-static const struct vm_special_mapping vdso_data_mapping = {
-	.name = "[vvar]",
-	.pages = &vdso_data_page,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
@@ -192,9 +184,6 @@ static int __init vdso_init(void)
 	if (vdso_text_pagelist == NULL)
 		return -ENOMEM;
 
-	/* Grab the VDSO data page. */
-	vdso_data_page = virt_to_page(vdso_data);
-
 	/* Grab the VDSO text pages. */
 	for (i = 0; i < text_pages; i++) {
 		struct page *page;
@@ -205,7 +194,7 @@ static int __init vdso_init(void)
 
 	vdso_text_mapping.pages = vdso_text_pagelist;
 
-	vdso_total_pages = 1; /* for the data/vvar page */
+	vdso_total_pages = VDSO_NR_PAGES; /* for the data/vvar pages */
 	vdso_total_pages += text_pages;
 
 	cntvct_ok = cntvct_functional();
@@ -216,16 +205,7 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-static int install_vvar(struct mm_struct *mm, unsigned long addr)
-{
-	struct vm_area_struct *vma;
-
-	vma = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ | VM_MAYREAD,
-				       &vdso_data_mapping);
-
-	return PTR_ERR_OR_ZERO(vma);
-}
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
 
 /* assumes mmap_lock is write-locked */
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
@@ -238,12 +218,12 @@ void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 	if (vdso_text_pagelist == NULL)
 		return;
 
-	if (install_vvar(mm, addr))
+	if (IS_ERR(vdso_install_vvar_mapping(mm, addr)))
 		return;
 
-	/* Account for vvar page. */
-	addr += PAGE_SIZE;
-	len = (vdso_total_pages - 1) << PAGE_SHIFT;
+	/* Account for vvar pages. */
+	addr += VDSO_NR_PAGES * PAGE_SIZE;
+	len = (vdso_total_pages - VDSO_NR_PAGES) << PAGE_SHIFT;
 
 	vma = _install_special_mapping(mm, addr, len,
 		VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 5eddb75a7174..f2e8d4fac068 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -63,7 +63,7 @@ SECTIONS
 	. = ALIGN(4);
 	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
 		__start___ex_table = .;
-		ARM_MMU_KEEP(KEEP(*(__ex_table)))
+		ARM_MMU_KEEP(*(__ex_table))
 		__stop___ex_table = .;
 	}
 
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index de373c6c2ae8..d592a203f9c6 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -74,7 +74,7 @@ SECTIONS
 	. = ALIGN(4);
 	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
 		__start___ex_table = .;
-		ARM_MMU_KEEP(KEEP(*(__ex_table)))
+		ARM_MMU_KEEP(*(__ex_table))
 		__stop___ex_table = .;
 	}
 
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 007874320937..91ea0e29107a 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -5,6 +5,8 @@
 # Copyright (C) 1995-2000 Russell King
 #
 
+obj-y += crypto/
+
 lib-y		:= changebit.o csumipv6.o csumpartial.o               \
 		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
 		   delay.o delay-loop.o findbit.o memchr.o memcpy.o   \
@@ -47,7 +49,7 @@ endif
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-arm.o
-crc32-arm-y := crc32-glue.o crc32-core.o
+crc32-arm-y := crc32.o crc32-core.o
 
 obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm.o
-crc-t10dif-arm-y := crc-t10dif-glue.o crc-t10dif-core.o
+crc-t10dif-arm-y := crc-t10dif.o crc-t10dif-core.o
diff --git a/arch/arm/lib/crc-t10dif-glue.c b/arch/arm/lib/crc-t10dif.c
index d24dee62670e..1093f8ec13b0 100644
--- a/arch/arm/lib/crc-t10dif-glue.c
+++ b/arch/arm/lib/crc-t10dif.c
@@ -16,8 +16,8 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 
-static DEFINE_STATIC_KEY_FALSE(have_neon);
-static DEFINE_STATIC_KEY_FALSE(have_pmull);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
 
 #define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
 
@@ -44,9 +44,7 @@ u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
 			crc_t10dif_pmull8(crc, data, length, buf);
 			kernel_neon_end();
 
-			crc = 0;
-			data = buf;
-			length = sizeof(buf);
+			return crc_t10dif_generic(0, buf, sizeof(buf));
 		}
 	}
 	return crc_t10dif_generic(crc, data, length);
@@ -62,19 +60,13 @@ static int __init crc_t10dif_arm_init(void)
 	}
 	return 0;
 }
-arch_initcall(crc_t10dif_arm_init);
+subsys_initcall(crc_t10dif_arm_init);
 
 static void __exit crc_t10dif_arm_exit(void)
 {
 }
 module_exit(crc_t10dif_arm_exit);
 
-bool crc_t10dif_is_optimized(void)
-{
-	return static_key_enabled(&have_neon);
-}
-EXPORT_SYMBOL(crc_t10dif_is_optimized);
-
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_DESCRIPTION("Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/lib/crc32-glue.c b/arch/arm/lib/crc32.c
index 2c30ba3d80e6..f2bef8849c7c 100644
--- a/arch/arm/lib/crc32-glue.c
+++ b/arch/arm/lib/crc32.c
@@ -18,8 +18,8 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 
-static DEFINE_STATIC_KEY_FALSE(have_crc32);
-static DEFINE_STATIC_KEY_FALSE(have_pmull);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
 
 #define PMULL_MIN_LEN	64	/* min size of buffer for pmull functions */
 
@@ -59,14 +59,14 @@ u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
-static u32 crc32c_le_scalar(u32 crc, const u8 *p, size_t len)
+static u32 crc32c_scalar(u32 crc, const u8 *p, size_t len)
 {
 	if (static_branch_likely(&have_crc32))
 		return crc32c_armv8_le(crc, p, len);
-	return crc32c_le_base(crc, p, len);
+	return crc32c_base(crc, p, len);
 }
 
-u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (len >= PMULL_MIN_LEN + 15 &&
 	    static_branch_likely(&have_pmull) && crypto_simd_usable()) {
@@ -74,7 +74,7 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 
 		/* align p to 16-byte boundary */
 		if (n) {
-			crc = crc32c_le_scalar(crc, p, n);
+			crc = crc32c_scalar(crc, p, n);
 			p += n;
 			len -= n;
 		}
@@ -85,9 +85,9 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 		p += n;
 		len -= n;
 	}
-	return crc32c_le_scalar(crc, p, len);
+	return crc32c_scalar(crc, p, len);
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -103,7 +103,7 @@ static int __init crc32_arm_init(void)
 		static_branch_enable(&have_pmull);
 	return 0;
 }
-arch_initcall(crc32_arm_init);
+subsys_initcall(crc32_arm_init);
 
 static void __exit crc32_arm_exit(void)
 {
diff --git a/arch/arm/lib/crypto/.gitignore b/arch/arm/lib/crypto/.gitignore
new file mode 100644
index 000000000000..12d74d8b03d0
--- /dev/null
+++ b/arch/arm/lib/crypto/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+poly1305-core.S
+sha256-core.S
diff --git a/arch/arm/lib/crypto/Kconfig b/arch/arm/lib/crypto/Kconfig
new file mode 100644
index 000000000000..d1ad664f0c67
--- /dev/null
+++ b/arch/arm/lib/crypto/Kconfig
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_BLAKE2S_ARM
+	bool "Hash functions: BLAKE2s"
+	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+	help
+	  BLAKE2s cryptographic hash function (RFC 7693)
+
+	  Architecture: arm
+
+	  This is faster than the generic implementations of BLAKE2s and
+	  BLAKE2b, but slower than the NEON implementation of BLAKE2b.
+	  There is no NEON implementation of BLAKE2s, since NEON doesn't
+	  really help with it.
+
+config CRYPTO_CHACHA20_NEON
+	tristate
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_ARM
+	tristate
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+config CRYPTO_SHA256_ARM
+	tristate
+	depends on !CPU_V7M
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD
diff --git a/arch/arm/lib/crypto/Makefile b/arch/arm/lib/crypto/Makefile
new file mode 100644
index 000000000000..431f77c3ff6f
--- /dev/null
+++ b/arch/arm/lib/crypto/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_BLAKE2S_ARM) += libblake2s-arm.o
+libblake2s-arm-y := blake2s-core.o blake2s-glue.o
+
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+chacha-neon-y := chacha-scalar-core.o chacha-glue.o
+chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
+poly1305-arm-y := poly1305-core.o poly1305-glue.o
+
+obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
+sha256-arm-y := sha256.o sha256-core.o
+sha256-arm-$(CONFIG_KERNEL_MODE_NEON) += sha256-ce.o
+
+quiet_cmd_perl = PERL    $@
+      cmd_perl = $(PERL) $(<) > $(@)
+
+$(obj)/%-core.S: $(src)/%-armv4.pl
+	$(call cmd,perl)
+
+clean-files += poly1305-core.S sha256-core.S
+
+aflags-thumb2-$(CONFIG_THUMB2_KERNEL)  := -U__thumb2__ -D__thumb2__=1
+
+# massage the perlasm code a bit so we only get the NEON routine if we need it
+poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
+poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
+
+AFLAGS_sha256-core.o += $(aflags-thumb2-y)
diff --git a/arch/arm/crypto/blake2s-core.S b/arch/arm/lib/crypto/blake2s-core.S
index df40e46601f1..df40e46601f1 100644
--- a/arch/arm/crypto/blake2s-core.S
+++ b/arch/arm/lib/crypto/blake2s-core.S
diff --git a/arch/arm/crypto/blake2s-glue.c b/arch/arm/lib/crypto/blake2s-glue.c
index 0238a70d9581..0238a70d9581 100644
--- a/arch/arm/crypto/blake2s-glue.c
+++ b/arch/arm/lib/crypto/blake2s-glue.c
diff --git a/arch/arm/lib/crypto/chacha-glue.c b/arch/arm/lib/crypto/chacha-glue.c
new file mode 100644
index 000000000000..88ec96415283
--- /dev/null
+++ b/arch/arm/lib/crypto/chacha-glue.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ChaCha and HChaCha functions (ARM optimized)
+ *
+ * Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cputype.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
+				      u8 *dst, const u8 *src, int nrounds);
+asmlinkage void chacha_4block_xor_neon(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       int nrounds, unsigned int nbytes);
+asmlinkage void hchacha_block_arm(const struct chacha_state *state,
+				  u32 out[HCHACHA_OUT_WORDS], int nrounds);
+asmlinkage void hchacha_block_neon(const struct chacha_state *state,
+				   u32 out[HCHACHA_OUT_WORDS], int nrounds);
+
+asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+			     const struct chacha_state *state, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
+
+static inline bool neon_usable(void)
+{
+	return static_branch_likely(&use_neon) && crypto_simd_usable();
+}
+
+static void chacha_doneon(struct chacha_state *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	u8 buf[CHACHA_BLOCK_SIZE];
+
+	while (bytes > CHACHA_BLOCK_SIZE) {
+		unsigned int l = min(bytes, CHACHA_BLOCK_SIZE * 4U);
+
+		chacha_4block_xor_neon(state, dst, src, nrounds, l);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
+	}
+	if (bytes) {
+		const u8 *s = src;
+		u8 *d = dst;
+
+		if (bytes != CHACHA_BLOCK_SIZE)
+			s = d = memcpy(buf, src, bytes);
+		chacha_block_xor_neon(state, d, s, nrounds);
+		if (d != dst)
+			memcpy(dst, buf, bytes);
+		state->x[12]++;
+	}
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
+		hchacha_block_arm(state, out, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, out, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE) {
+		chacha_doarm(dst, src, bytes, state, nrounds);
+		state->x[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
+		return;
+	}
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	/* We always can use at least the ARM scalar implementation. */
+	return true;
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_arm_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
+		switch (read_cpuid_part()) {
+		case ARM_CPU_PART_CORTEX_A7:
+		case ARM_CPU_PART_CORTEX_A5:
+			/*
+			 * The Cortex-A7 and Cortex-A5 do not perform well with
+			 * the NEON implementation but do incredibly with the
+			 * scalar one and use less power.
+			 */
+			break;
+		default:
+			static_branch_enable(&use_neon);
+		}
+	}
+	return 0;
+}
+subsys_initcall(chacha_arm_mod_init);
+
+static void __exit chacha_arm_mod_exit(void)
+{
+}
+module_exit(chacha_arm_mod_exit);
+
+MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM optimized)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/crypto/chacha-neon-core.S b/arch/arm/lib/crypto/chacha-neon-core.S
index 13d12f672656..ddd62b6294a5 100644
--- a/arch/arm/crypto/chacha-neon-core.S
+++ b/arch/arm/lib/crypto/chacha-neon-core.S
@@ -1,5 +1,5 @@
 /*
- * ChaCha/XChaCha NEON helper functions
+ * ChaCha/HChaCha NEON helper functions
  *
  * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
  *
diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/lib/crypto/chacha-scalar-core.S
index 083fe1ab96d0..4951df05c158 100644
--- a/arch/arm/crypto/chacha-scalar-core.S
+++ b/arch/arm/lib/crypto/chacha-scalar-core.S
@@ -367,7 +367,7 @@
 
 /*
  * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
- *		     const u32 *state, int nrounds);
+ *		     const struct chacha_state *state, int nrounds);
  */
 ENTRY(chacha_doarm)
 	cmp		r2, #0			// len == 0?
@@ -407,7 +407,8 @@ ENTRY(chacha_doarm)
 ENDPROC(chacha_doarm)
 
 /*
- * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
+ * void hchacha_block_arm(const struct chacha_state *state,
+ *			  u32 out[HCHACHA_OUT_WORDS], int nrounds);
  */
 ENTRY(hchacha_block_arm)
 	push		{r1,r4-r11,lr}
diff --git a/arch/arm/crypto/poly1305-armv4.pl b/arch/arm/lib/crypto/poly1305-armv4.pl
index 6d79498d3115..d57c6e2fc84a 100644
--- a/arch/arm/crypto/poly1305-armv4.pl
+++ b/arch/arm/lib/crypto/poly1305-armv4.pl
@@ -43,9 +43,9 @@ $code.=<<___;
 #else
 # define __ARM_ARCH__ __LINUX_ARM_ARCH__
 # define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
-# define poly1305_init   poly1305_init_arm
+# define poly1305_init   poly1305_block_init_arch
 # define poly1305_blocks poly1305_blocks_arm
-# define poly1305_emit   poly1305_emit_arm
+# define poly1305_emit   poly1305_emit_arch
 .globl	poly1305_blocks_neon
 #endif
 
diff --git a/arch/arm/lib/crypto/poly1305-glue.c b/arch/arm/lib/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..2603b0771f2c
--- /dev/null
+++ b/arch/arm/lib/crypto/poly1305-glue.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_block_init_arch(
+	struct poly1305_block_state *state,
+	const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks_arm(struct poly1305_block_state *state,
+				    const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
+				     const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
+				   u8 digest[POLY1305_DIGEST_SIZE],
+				   const u32 nonce[4]);
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+void __weak poly1305_blocks_neon(struct poly1305_block_state *state,
+				 const u8 *src, u32 len, u32 hibit)
+{
+}
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
+			  unsigned int len, u32 padbit)
+{
+	len = round_down(len, POLY1305_BLOCK_SIZE);
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon)) {
+		do {
+			unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+			kernel_neon_begin();
+			poly1305_blocks_neon(state, src, todo, padbit);
+			kernel_neon_end();
+
+			len -= todo;
+			src += todo;
+		} while (len);
+	} else
+		poly1305_blocks_arm(state, src, len, padbit);
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	/* We always can use at least the ARM scalar implementation. */
+	return true;
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init arm_poly1305_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    (elf_hwcap & HWCAP_NEON))
+		static_branch_enable(&have_neon);
+	return 0;
+}
+subsys_initcall(arm_poly1305_mod_init);
+
+static void __exit arm_poly1305_mod_exit(void)
+{
+}
+module_exit(arm_poly1305_mod_exit);
+
+MODULE_DESCRIPTION("Accelerated Poly1305 transform for ARM");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/lib/crypto/sha256-armv4.pl
index f3a2b54efd4e..8122db7fd599 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/lib/crypto/sha256-armv4.pl
@@ -204,18 +204,18 @@ K256:
 .word	0				@ terminator
 #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 .LOPENSSL_armcap:
-.word	OPENSSL_armcap_P-sha256_block_data_order
+.word	OPENSSL_armcap_P-sha256_blocks_arch
 #endif
 .align	5
 
-.global	sha256_block_data_order
-.type	sha256_block_data_order,%function
-sha256_block_data_order:
-.Lsha256_block_data_order:
+.global	sha256_blocks_arch
+.type	sha256_blocks_arch,%function
+sha256_blocks_arch:
+.Lsha256_blocks_arch:
 #if __ARM_ARCH__<7
-	sub	r3,pc,#8		@ sha256_block_data_order
+	sub	r3,pc,#8		@ sha256_blocks_arch
 #else
-	adr	r3,.Lsha256_block_data_order
+	adr	r3,.Lsha256_blocks_arch
 #endif
 #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 	ldr	r12,.LOPENSSL_armcap
@@ -282,7 +282,7 @@ $code.=<<___;
 	moveq	pc,lr			@ be binary compatible with V4, yet
 	bx	lr			@ interoperable with Thumb ISA:-)
 #endif
-.size	sha256_block_data_order,.-sha256_block_data_order
+.size	sha256_blocks_arch,.-sha256_blocks_arch
 ___
 ######################################################################
 # NEON stuff
@@ -470,8 +470,8 @@ sha256_block_data_order_neon:
 	stmdb	sp!,{r4-r12,lr}
 
 	sub	$H,sp,#16*4+16
-	adr	$Ktbl,.Lsha256_block_data_order
-	sub	$Ktbl,$Ktbl,#.Lsha256_block_data_order-K256
+	adr	$Ktbl,.Lsha256_blocks_arch
+	sub	$Ktbl,$Ktbl,#.Lsha256_blocks_arch-K256
 	bic	$H,$H,#15		@ align for 128-bit stores
 	mov	$t2,sp
 	mov	sp,$H			@ alloca
diff --git a/arch/arm/crypto/sha2-ce-core.S b/arch/arm/lib/crypto/sha256-ce.S
index b6369d2440a1..ac2c9b01b22d 100644
--- a/arch/arm/crypto/sha2-ce-core.S
+++ b/arch/arm/lib/crypto/sha256-ce.S
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * sha2-ce-core.S - SHA-224/256 secure hash using ARMv8 Crypto Extensions
+ * sha256-ce.S - SHA-224/256 secure hash using ARMv8 Crypto Extensions
  *
  * Copyright (C) 2015 Linaro Ltd.
  * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
@@ -67,10 +67,10 @@
 	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
 
 	/*
-	 * void sha2_ce_transform(struct sha256_state *sst, u8 const *src,
-				  int blocks);
+	 * void sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+	 *			    const u8 *data, size_t nblocks);
 	 */
-ENTRY(sha2_ce_transform)
+ENTRY(sha256_ce_transform)
 	/* load state */
 	vld1.32		{dga-dgb}, [r0]
 
@@ -120,4 +120,4 @@ ENTRY(sha2_ce_transform)
 	/* store new state */
 	vst1.32		{dga-dgb}, [r0]
 	bx		lr
-ENDPROC(sha2_ce_transform)
+ENDPROC(sha256_ce_transform)
diff --git a/arch/arm/lib/crypto/sha256.c b/arch/arm/lib/crypto/sha256.c
new file mode 100644
index 000000000000..109192e54b0f
--- /dev/null
+++ b/arch/arm/lib/crypto/sha256.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized for ARM
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/neon.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+				   const u8 *data, size_t nblocks);
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+asmlinkage void sha256_block_data_order_neon(u32 state[SHA256_STATE_WORDS],
+					     const u8 *data, size_t nblocks);
+asmlinkage void sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+				    const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon)) {
+		kernel_neon_begin();
+		if (static_branch_likely(&have_ce))
+			sha256_ce_transform(state, data, nblocks);
+		else
+			sha256_block_data_order_neon(state, data, nblocks);
+		kernel_neon_end();
+	} else {
+		sha256_blocks_arch(state, data, nblocks);
+	}
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+bool sha256_is_arch_optimized(void)
+{
+	/* We always can use at least the ARM scalar implementation. */
+	return true;
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_arm_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
+		static_branch_enable(&have_neon);
+		if (elf_hwcap2 & HWCAP2_SHA2)
+			static_branch_enable(&have_ce);
+	}
+	return 0;
+}
+subsys_initcall(sha256_arm_mod_init);
+
+static void __exit sha256_arm_mod_exit(void)
+{
+}
+module_exit(sha256_arm_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 optimized for ARM");
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 05a1547642b6..3aa20038ad93 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -222,13 +222,16 @@ static const struct of_device_id sam9x60_ws_ids[] = {
 	{ /* sentinel */ }
 };
 
-static const struct of_device_id sama7g5_ws_ids[] = {
+static const struct of_device_id sama7_ws_ids[] = {
+	{ .compatible = "microchip,sama7d65-rtc",	.data = &ws_info[1] },
 	{ .compatible = "microchip,sama7g5-rtc",	.data = &ws_info[1] },
 	{ .compatible = "microchip,sama7g5-ohci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ohci",			.data = &ws_info[2] },
 	{ .compatible = "atmel,at91sam9g45-ehci",	.data = &ws_info[2] },
 	{ .compatible = "usb-ehci",			.data = &ws_info[2] },
+	{ .compatible = "microchip,sama7d65-sdhci",	.data = &ws_info[3] },
 	{ .compatible = "microchip,sama7g5-sdhci",	.data = &ws_info[3] },
+	{ .compatible = "microchip,sama7d65-rtt",	.data = &ws_info[4] },
 	{ .compatible = "microchip,sama7g5-rtt",	.data = &ws_info[4] },
 	{ /* sentinel */ }
 };
@@ -545,11 +548,12 @@ extern u32 at91_pm_suspend_in_sram_sz;
 
 static int at91_suspend_finish(unsigned long val)
 {
-	unsigned char modified_gray_code[] = {
-		0x00, 0x01, 0x02, 0x03, 0x06, 0x07, 0x04, 0x05, 0x0c, 0x0d,
-		0x0e, 0x0f, 0x0a, 0x0b, 0x08, 0x09, 0x18, 0x19, 0x1a, 0x1b,
-		0x1e, 0x1f, 0x1c, 0x1d, 0x14, 0x15, 0x16, 0x17, 0x12, 0x13,
-		0x10, 0x11,
+	/* SYNOPSYS workaround to fix a bug in the calibration logic */
+	unsigned char modified_fix_code[] = {
+		0x00, 0x01, 0x01, 0x06, 0x07, 0x0c, 0x06, 0x07, 0x0b, 0x18,
+		0x0a, 0x0b, 0x0c, 0x0d, 0x0d, 0x0a, 0x13, 0x13, 0x12, 0x13,
+		0x14, 0x15, 0x15, 0x12, 0x18, 0x19, 0x19, 0x1e, 0x1f, 0x14,
+		0x1e, 0x1f,
 	};
 	unsigned int tmp, index;
 	int i;
@@ -560,25 +564,25 @@ static int at91_suspend_finish(unsigned long val)
 		 * restore the ZQ0SR0 with the value saved here. But the
 		 * calibration is buggy and restoring some values from ZQ0SR0
 		 * is forbidden and risky thus we need to provide processed
-		 * values for these (modified gray code values).
+		 * values for these.
 		 */
 		tmp = readl(soc_pm.data.ramc_phy + DDR3PHY_ZQ0SR0);
 
 		/* Store pull-down output impedance select. */
 		index = (tmp >> DDR3PHY_ZQ0SR0_PDO_OFF) & 0x1f;
-		soc_pm.bu->ddr_phy_calibration[0] = modified_gray_code[index];
+		soc_pm.bu->ddr_phy_calibration[0] = modified_fix_code[index] << DDR3PHY_ZQ0SR0_PDO_OFF;
 
 		/* Store pull-up output impedance select. */
 		index = (tmp >> DDR3PHY_ZQ0SR0_PUO_OFF) & 0x1f;
-		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SR0_PUO_OFF;
 
 		/* Store pull-down on-die termination impedance select. */
 		index = (tmp >> DDR3PHY_ZQ0SR0_PDODT_OFF) & 0x1f;
-		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SR0_PDODT_OFF;
 
 		/* Store pull-up on-die termination impedance select. */
 		index = (tmp >> DDR3PHY_ZQ0SRO_PUODT_OFF) & 0x1f;
-		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_fix_code[index] << DDR3PHY_ZQ0SRO_PUODT_OFF;
 
 		/*
 		 * The 1st 8 words of memory might get corrupted in the process
@@ -643,6 +647,11 @@ static void at91_pm_suspend(suspend_state_t state)
 		at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn,
 					     &at91_pm_suspend_in_sram,
 					     at91_pm_suspend_in_sram_sz);
+
+		if (IS_ENABLED(CONFIG_SOC_SAMA7D65)) {
+			/* SHDWC.SR */
+			readl(soc_pm.data.shdwc + 0x08);
+		}
 	} else {
 		at91_suspend_finish(0);
 	}
@@ -1061,7 +1070,8 @@ static int __init at91_pm_backup_init(void)
 	int ret = -ENODEV, located = 0;
 
 	if (!IS_ENABLED(CONFIG_SOC_SAMA5D2) &&
-	    !IS_ENABLED(CONFIG_SOC_SAMA7G5))
+	    !IS_ENABLED(CONFIG_SOC_SAMA7G5) &&
+	    !IS_ENABLED(CONFIG_SOC_SAMA7D65))
 		return -EPERM;
 
 	if (!at91_is_pm_mode_active(AT91_PM_BACKUP))
@@ -1329,6 +1339,7 @@ struct pmc_info {
 	unsigned long uhp_udp_mask;
 	unsigned long mckr;
 	unsigned long version;
+	unsigned long mcks;
 };
 
 static const struct pmc_info pmc_infos[] __initconst = {
@@ -1360,8 +1371,14 @@ static const struct pmc_info pmc_infos[] __initconst = {
 	{
 		.mckr = 0x28,
 		.version = AT91_PMC_V2,
+		.mcks = 4,
+	},
+	{
+		.uhp_udp_mask = AT91SAM926x_PMC_UHP,
+		.mckr = 0x28,
+		.version = AT91_PMC_V2,
+		.mcks = 9,
 	},
-
 };
 
 static const struct of_device_id atmel_pmc_ids[] __initconst = {
@@ -1378,6 +1395,7 @@ static const struct of_device_id atmel_pmc_ids[] __initconst = {
 	{ .compatible = "atmel,sama5d2-pmc", .data = &pmc_infos[1] },
 	{ .compatible = "microchip,sam9x60-pmc", .data = &pmc_infos[4] },
 	{ .compatible = "microchip,sam9x7-pmc", .data = &pmc_infos[4] },
+	{ .compatible = "microchip,sama7d65-pmc", .data = &pmc_infos[6] },
 	{ .compatible = "microchip,sama7g5-pmc", .data = &pmc_infos[5] },
 	{ /* sentinel */ },
 };
@@ -1448,6 +1466,7 @@ static void __init at91_pm_init(void (*pm_idle)(void))
 	soc_pm.data.uhp_udp_mask = pmc->uhp_udp_mask;
 	soc_pm.data.pmc_mckr_offset = pmc->mckr;
 	soc_pm.data.pmc_version = pmc->version;
+	soc_pm.data.pmc_mcks = pmc->mcks;
 
 	if (pm_idle)
 		arm_pm_idle = pm_idle;
@@ -1671,7 +1690,7 @@ void __init sama7_pm_init(void)
 	at91_pm_modes_init(iomaps, ARRAY_SIZE(iomaps));
 	at91_pm_init(NULL);
 
-	soc_pm.ws_ids = sama7g5_ws_ids;
+	soc_pm.ws_ids = sama7_ws_ids;
 	soc_pm.config_pmc_ws = at91_sam9x60_config_pmc_ws;
 
 	soc_pm.sfrbu_regs.pswbu.key = (0x4BD20C << 8);
diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h
index 53bdc9000e44..50c3a425d140 100644
--- a/arch/arm/mach-at91/pm.h
+++ b/arch/arm/mach-at91/pm.h
@@ -39,6 +39,7 @@ struct at91_pm_data {
 	unsigned int suspend_mode;
 	unsigned int pmc_mckr_offset;
 	unsigned int pmc_version;
+	unsigned int pmc_mcks;
 };
 #endif
 
diff --git a/arch/arm/mach-at91/pm_data-offsets.c b/arch/arm/mach-at91/pm_data-offsets.c
index 40bd4e8fe40a..0ca5da66dc26 100644
--- a/arch/arm/mach-at91/pm_data-offsets.c
+++ b/arch/arm/mach-at91/pm_data-offsets.c
@@ -18,6 +18,8 @@ int main(void)
 						 pmc_mckr_offset));
 	DEFINE(PM_DATA_PMC_VERSION,	offsetof(struct at91_pm_data,
 						 pmc_version));
+	DEFINE(PM_DATA_PMC_MCKS,	offsetof(struct at91_pm_data,
+						 pmc_mcks));
 
 	return 0;
 }
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S
index e5869cca5e79..e23b86834096 100644
--- a/arch/arm/mach-at91/pm_suspend.S
+++ b/arch/arm/mach-at91/pm_suspend.S
@@ -814,18 +814,20 @@ sr_dis_exit:
 .endm
 
 /**
- * at91_mckx_ps_enable:	save MCK1..4 settings and switch it to main clock
+ * at91_mckx_ps_enable:	save MCK settings and switch it to main clock
  *
- * Side effects: overwrites tmp1, tmp2
+ * Side effects: overwrites tmp1, tmp2, tmp3
  */
 .macro at91_mckx_ps_enable
 #ifdef CONFIG_SOC_SAMA7
 	ldr	pmc, .pmc_base
+	ldr	tmp3, .mcks
 
-	/* There are 4 MCKs we need to handle: MCK1..4 */
+	/* Start at MCK1 and go until MCKs */
 	mov	tmp1, #1
-e_loop:	cmp	tmp1, #5
-	beq	e_done
+e_loop:
+	cmp	tmp1, tmp3
+	bgt	e_done
 
 	/* Write MCK ID to retrieve the settings. */
 	str	tmp1, [pmc, #AT91_PMC_MCR_V2]
@@ -850,7 +852,37 @@ e_save_mck3:
 	b	e_ps
 
 e_save_mck4:
+	cmp	tmp1, #4
+	bne	e_save_mck5
 	str	tmp2, .saved_mck4
+	b	e_ps
+
+e_save_mck5:
+	cmp	tmp1, #5
+	bne	e_save_mck6
+	str	tmp2, .saved_mck5
+	b	e_ps
+
+e_save_mck6:
+	cmp	tmp1, #6
+	bne	e_save_mck7
+	str	tmp2, .saved_mck6
+	b	e_ps
+
+e_save_mck7:
+	cmp	tmp1, #7
+	bne	e_save_mck8
+	str	tmp2, .saved_mck7
+	b	e_ps
+
+e_save_mck8:
+	cmp	tmp1, #8
+	bne	e_save_mck9
+	str	tmp2, .saved_mck8
+	b	e_ps
+
+e_save_mck9:
+	str	tmp2, .saved_mck9
 
 e_ps:
 	/* Use CSS=MAINCK and DIV=1. */
@@ -870,18 +902,20 @@ e_done:
 .endm
 
 /**
- * at91_mckx_ps_restore: restore MCK1..4 settings
+ * at91_mckx_ps_restore: restore MCKx settings
  *
  * Side effects: overwrites tmp1, tmp2
  */
 .macro at91_mckx_ps_restore
 #ifdef CONFIG_SOC_SAMA7
 	ldr	pmc, .pmc_base
+	ldr	tmp2, .mcks
 
-	/* There are 4 MCKs we need to handle: MCK1..4 */
+	/* Start from MCK1 and go up to MCKs */
 	mov	tmp1, #1
-r_loop:	cmp	tmp1, #5
-	beq	r_done
+r_loop:
+	cmp	tmp1, tmp2
+	bgt	r_done
 
 r_save_mck1:
 	cmp	tmp1, #1
@@ -902,7 +936,37 @@ r_save_mck3:
 	b	r_ps
 
 r_save_mck4:
+	cmp	tmp1, #4
+	bne	r_save_mck5
 	ldr	tmp2, .saved_mck4
+	b	r_ps
+
+r_save_mck5:
+	cmp	tmp1, #5
+	bne	r_save_mck6
+	ldr	tmp2, .saved_mck5
+	b	r_ps
+
+r_save_mck6:
+	cmp	tmp1, #6
+	bne	r_save_mck7
+	ldr	tmp2, .saved_mck6
+	b	r_ps
+
+r_save_mck7:
+	cmp	tmp1, #7
+	bne	r_save_mck8
+	ldr	tmp2, .saved_mck7
+	b	r_ps
+
+r_save_mck8:
+	cmp	tmp1, #8
+	bne	r_save_mck9
+	ldr	tmp2, .saved_mck8
+	b	r_ps
+
+r_save_mck9:
+	ldr	tmp2, .saved_mck9
 
 r_ps:
 	/* Write MCK ID to retrieve the settings. */
@@ -921,6 +985,7 @@ r_ps:
 	wait_mckrdy tmp1
 
 	add	tmp1, tmp1, #1
+	ldr	tmp2, .mcks
 	b	r_loop
 r_done:
 #endif
@@ -1045,6 +1110,10 @@ ENTRY(at91_pm_suspend_in_sram)
 	str	tmp1, .memtype
 	ldr	tmp1, [r0, #PM_DATA_MODE]
 	str	tmp1, .pm_mode
+#ifdef CONFIG_SOC_SAMA7
+	ldr	tmp1, [r0, #PM_DATA_PMC_MCKS]
+	str	tmp1, .mcks
+#endif
 
 	/*
 	 * ldrne below are here to preload their address in the TLB as access
@@ -1132,6 +1201,10 @@ ENDPROC(at91_pm_suspend_in_sram)
 	.word 0
 .pmc_version:
 	.word 0
+#ifdef CONFIG_SOC_SAMA7
+.mcks:
+	.word 0
+#endif
 .saved_mckr:
 	.word 0
 .saved_pllar:
@@ -1155,6 +1228,16 @@ ENDPROC(at91_pm_suspend_in_sram)
 	.word 0
 .saved_mck4:
 	.word 0
+.saved_mck5:
+	.word 0
+.saved_mck6:
+	.word 0
+.saved_mck7:
+	.word 0
+.saved_mck8:
+	.word 0
+.saved_mck9:
+	.word 0
 #endif
 
 ENTRY(at91_pm_suspend_in_sram_sz)
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 2a8a9fe46586..8f66de0405d9 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -4,6 +4,7 @@ menuconfig ARCH_DAVINCI
 	bool "TI DaVinci"
 	depends on ARCH_MULTI_V5
 	depends on CPU_LITTLE_ENDIAN
+	select ARCH_DAVINCI_DA850
 	select CPU_ARM926T
 	select DAVINCI_TIMER
 	select ZONE_DMA
@@ -27,6 +28,7 @@ config ARCH_DAVINCI_DA830
 
 config ARCH_DAVINCI_DA850
 	bool "DA850/OMAP-L138/AM18x based system"
+	select ARCH_DAVINCI_DA8XX
 	select DAVINCI_CP_INTC
 
 config ARCH_DAVINCI_DA8XX
diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c
index 2e497745b624..a044ea5cb4f1 100644
--- a/arch/arm/mach-davinci/da830.c
+++ b/arch/arm/mach-davinci/da830.c
@@ -11,7 +11,6 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/irqchip/irq-davinci-cp-intc.h>
 
 #include <clocksource/timer-davinci.h>
 
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index cac4e82f6c82..150a1e56dcae 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -209,9 +209,8 @@ static int __init exynos_pmu_irq_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
-	domain = irq_domain_add_hierarchy(parent_domain, 0, 0,
-					  node, &exynos_pmu_domain_ops,
-					  NULL);
+	domain = irq_domain_create_hierarchy(parent_domain, 0, 0, of_fwnode_handle(node),
+					     &exynos_pmu_domain_ops, NULL);
 	if (!domain) {
 		iounmap(pmu_base_addr);
 		pmu_base_addr = NULL;
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index f8920d0010de..6521ab3d24fa 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -135,7 +135,7 @@ static struct timer_list perr_timer;
 
 static void dc21285_enable_error(struct timer_list *timer)
 {
-	del_timer(timer);
+	timer_delete(timer);
 
 	if (timer == &serr_timer)
 		enable_irq(IRQ_PCI_SERR);
diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index cf6546ddc7a3..3067c06b4b8e 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -201,8 +201,8 @@ static void __init mxc_init_irq(void __iomem *irqbase)
 	WARN_ON(irq_base < 0);
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,avic");
-	domain = irq_domain_add_legacy(np, AVIC_NUM_IRQS, irq_base, 0,
-				       &irq_domain_simple_ops, NULL);
+	domain = irq_domain_create_legacy(of_fwnode_handle(np), AVIC_NUM_IRQS, irq_base, 0,
+					  &irq_domain_simple_ops, NULL);
 	WARN_ON(!domain);
 
 	for (i = 0; i < AVIC_NUM_IRQS / 32; i++, irq_base += 32)
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 13f3068e9845..45c1a2a7b35f 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -98,7 +98,7 @@ extern const u32 imx53_suspend_sz;
 void imx6_suspend(void __iomem *ocram_vbase);
 #else
 static inline void imx53_suspend(void __iomem *ocram_vbase) {}
-static const u32 imx53_suspend_sz;
+static __maybe_unused const u32 imx53_suspend_sz;
 static inline void imx6_suspend(void __iomem *ocram_vbase) {}
 #endif
 
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 5909088d5482..2e633569d2f8 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -245,9 +245,8 @@ static int __init imx_gpc_init(struct device_node *node,
 	if (WARN_ON(!gpc_base))
 	        return -ENOMEM;
 
-	domain = irq_domain_add_hierarchy(parent_domain, 0, GPC_MAX_IRQS,
-					  node, &imx_gpc_domain_ops,
-					  NULL);
+	domain = irq_domain_create_hierarchy(parent_domain, 0, GPC_MAX_IRQS, of_fwnode_handle(node),
+					     &imx_gpc_domain_ops, NULL);
 	if (!domain) {
 		iounmap(gpc_base);
 		return -ENOMEM;
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index e898f7c2733e..94e4f4a2f73f 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -509,9 +509,8 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 	pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk;
 	pmu_mmdc->devtype_data = device_get_match_data(&pdev->dev);
 
-	hrtimer_init(&pmu_mmdc->hrtimer, CLOCK_MONOTONIC,
-			HRTIMER_MODE_REL);
-	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
+	hrtimer_setup(&pmu_mmdc->hrtimer, mmdc_pmu_timer_handler, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
 
diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c
index 8b3d98d288d9..50a5668e65d2 100644
--- a/arch/arm/mach-imx/tzic.c
+++ b/arch/arm/mach-imx/tzic.c
@@ -175,8 +175,8 @@ static int __init tzic_init_dt(struct device_node *np, struct device_node *p)
 	irq_base = irq_alloc_descs(-1, 0, TZIC_NUM_IRQS, numa_node_id());
 	WARN_ON(irq_base < 0);
 
-	domain = irq_domain_add_legacy(np, TZIC_NUM_IRQS, irq_base, 0,
-				       &irq_domain_simple_ops, NULL);
+	domain = irq_domain_create_legacy(of_fwnode_handle(np), TZIC_NUM_IRQS, irq_base, 0,
+					  &irq_domain_simple_ops, NULL);
 	WARN_ON(!domain);
 
 	for (i = 0; i < 4; i++, irq_base += 32)
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index a643b71e30a3..08ec6bd84ada 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -8,6 +8,7 @@ menuconfig ARCH_OMAP1
 	select ARCH_OMAP
 	select CLKSRC_MMIO
 	select FORCE_PCI if PCCARD
+	select GENERIC_IRQ_CHIP
 	select GPIOLIB
 	help
 	  Support for older TI OMAP1 (omap7xx, omap15xx or omap16xx)
diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c
index 9b587ecebb1c..bb1bc060ecd8 100644
--- a/arch/arm/mach-omap1/irq.c
+++ b/arch/arm/mach-omap1/irq.c
@@ -220,8 +220,7 @@ void __init omap1_init_irq(void)
 	omap_l2_irq = irq_base;
 	omap_l2_irq -= NR_IRQS_LEGACY;
 
-	domain = irq_domain_add_legacy(NULL, nr_irqs, irq_base, 0,
-				       &irq_domain_simple_ops, NULL);
+	domain = irq_domain_create_legacy(NULL, nr_irqs, irq_base, 0, &irq_domain_simple_ops, NULL);
 
 	pr_info("Total of %lu interrupts in %i interrupt banks\n",
 		nr_irqs, irq_bank_count);
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 6f0d6120c174..a66b1dc61571 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -585,9 +585,8 @@ static int __init wakeupgen_init(struct device_node *node,
 		wakeupgen_ops = &am43xx_wakeupgen_ops;
 	}
 
-	domain = irq_domain_add_hierarchy(parent_domain, 0, max_irqs,
-					  node, &wakeupgen_domain_ops,
-					  NULL);
+	domain = irq_domain_create_hierarchy(parent_domain, 0, max_irqs, of_fwnode_handle(node),
+					     &wakeupgen_domain_ops, NULL);
 	if (!domain) {
 		iounmap(wakeupgen_base);
 		return -ENOMEM;
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index a9ef71008147..5bfce8aa4102 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -147,12 +147,11 @@ pxa_init_irq_common(struct device_node *node, int irq_nr,
 	int n;
 
 	pxa_internal_irq_nr = irq_nr;
-	pxa_irq_domain = irq_domain_add_legacy(node, irq_nr,
-					       PXA_IRQ(0), 0,
-					       &pxa_irq_ops, NULL);
+	pxa_irq_domain = irq_domain_create_legacy(of_fwnode_handle(node), irq_nr, PXA_IRQ(0), 0,
+						  &pxa_irq_ops, NULL);
 	if (!pxa_irq_domain)
 		panic("Unable to add PXA IRQ domain\n");
-	irq_set_default_host(pxa_irq_domain);
+	irq_set_default_domain(pxa_irq_domain);
 
 	for (n = 0; n < irq_nr; n += 32) {
 		void __iomem *base = irq_base(n >> 5);
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index dd930e3a61a4..71b282b146d0 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -913,8 +913,8 @@ static void sharpsl_pm_remove(struct platform_device *pdev)
 	if (sharpsl_pm.machinfo->exit)
 		sharpsl_pm.machinfo->exit();
 
-	del_timer_sync(&sharpsl_pm.chrg_full_timer);
-	del_timer_sync(&sharpsl_pm.ac_timer);
+	timer_delete_sync(&sharpsl_pm.chrg_full_timer);
+	timer_delete_sync(&sharpsl_pm.ac_timer);
 }
 
 static struct platform_driver sharpsl_pm_driver = {
diff --git a/arch/arm/mach-s3c/devs.c b/arch/arm/mach-s3c/devs.c
index 8c26d592d2a3..bab2abd8a34a 100644
--- a/arch/arm/mach-s3c/devs.c
+++ b/arch/arm/mach-s3c/devs.c
@@ -19,7 +19,6 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/dma-mapping.h>
-#include <linux/fb.h>
 #include <linux/gfp.h>
 #include <linux/mmc/host.h>
 #include <linux/ioport.h>
diff --git a/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c b/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
index cfa34b55ca21..c3269cd6a848 100644
--- a/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
@@ -9,7 +9,6 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/fb.h>
 #include <linux/gpio.h>
 
 #include "fb.h"
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index a956b489b6ea..2bc7e73a8582 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -136,6 +136,7 @@ ENDPROC(shmobile_smp_sleep)
 	.long	shmobile_smp_arg - 1b
 
 	.bss
+	.align	2
 	.globl	shmobile_smp_mpidr
 shmobile_smp_mpidr:
 	.space	NR_CPUS * 4
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index c38367a10c79..3cd34a42e39b 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -8,19 +8,15 @@
  */
 
 #include <linux/clocksource.h>
-#include <linux/device.h>
-#include <linux/dma-map-ops.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_clk.h>
-#include <linux/of_fdt.h>
 #include <linux/psci.h>
 #include <asm/mach/arch.h>
 #include <asm/secure_cntvoff.h>
 #include "common.h"
-#include "rcar-gen2.h"
 
 static const struct of_device_id cpg_matches[] __initconst = {
 	{ .compatible = "renesas,r8a7742-cpg-mssr", .data = "extal" },
@@ -122,76 +118,6 @@ skip_update:
 	timer_probe();
 }
 
-struct memory_reserve_config {
-	u64 reserved;
-	u64 base, size;
-};
-
-static int __init rcar_gen2_scan_mem(unsigned long node, const char *uname,
-				     int depth, void *data)
-{
-	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	const __be32 *reg, *endp;
-	int l;
-	struct memory_reserve_config *mrc = data;
-	u64 lpae_start = 1ULL << 32;
-
-	/* We are scanning "memory" nodes only */
-	if (type == NULL || strcmp(type, "memory"))
-		return 0;
-
-	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
-	if (reg == NULL)
-		reg = of_get_flat_dt_prop(node, "reg", &l);
-	if (reg == NULL)
-		return 0;
-
-	endp = reg + (l / sizeof(__be32));
-	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
-		u64 base, size;
-
-		base = dt_mem_next_cell(dt_root_addr_cells, &reg);
-		size = dt_mem_next_cell(dt_root_size_cells, &reg);
-
-		if (base >= lpae_start)
-			continue;
-
-		if ((base + size) >= lpae_start)
-			size = lpae_start - base;
-
-		if (size < mrc->reserved)
-			continue;
-
-		if (base < mrc->base)
-			continue;
-
-		/* keep the area at top near the 32-bit legacy limit */
-		mrc->base = base + size - mrc->reserved;
-		mrc->size = mrc->reserved;
-	}
-
-	return 0;
-}
-
-static void __init rcar_gen2_reserve(void)
-{
-	struct memory_reserve_config mrc;
-
-	/* reserve 256 MiB at the top of the physical legacy 32-bit space */
-	memset(&mrc, 0, sizeof(mrc));
-	mrc.reserved = SZ_256M;
-
-	of_scan_flat_dt(rcar_gen2_scan_mem, &mrc);
-#ifdef CONFIG_DMA_CMA
-	if (mrc.size && memblock_is_region_memory(mrc.base, mrc.size)) {
-		static struct cma *rcar_gen2_dma_contiguous;
-
-		dma_contiguous_reserve_area(mrc.size, mrc.base, 0,
-					    &rcar_gen2_dma_contiguous, true);
-	}
-#endif
-}
-
 static const char * const rcar_gen2_boards_compat_dt[] __initconst = {
 	"renesas,r8a7790",
 	"renesas,r8a7791",
@@ -204,7 +130,6 @@ static const char * const rcar_gen2_boards_compat_dt[] __initconst = {
 DT_MACHINE_START(RCAR_GEN2_DT, "Generic R-Car Gen2 (Flattened Device Tree)")
 	.init_late	= shmobile_init_late,
 	.init_time	= rcar_gen2_timer_init,
-	.reserve	= rcar_gen2_reserve,
 	.dt_compat	= rcar_gen2_boards_compat_dt,
 MACHINE_END
 
@@ -220,6 +145,5 @@ static const char * const rz_g1_boards_compat_dt[] __initconst = {
 DT_MACHINE_START(RZ_G1_DT, "Generic RZ/G1 (Flattened Device Tree)")
 	.init_late	= shmobile_init_late,
 	.init_time	= rcar_gen2_timer_init,
-	.reserve	= rcar_gen2_reserve,
 	.dt_compat	= rz_g1_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 2b6f50dd5478..5c1023a6d78c 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -928,6 +928,7 @@ config VDSO
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_32
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	help
 	  Place in the process address space an ELF shared object
 	  providing fast implementations of gettimeofday and
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 993fefdc167a..93ef0502b7ff 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -539,8 +539,7 @@ static __init int l2x0_pmu_init(void)
 	 * at higher frequencies.
 	 */
 	l2x0_pmu_poll_period = ms_to_ktime(1000);
-	hrtimer_init(&l2x0_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	l2x0_pmu_hrtimer.function = l2x0_pmu_poll;
+	hrtimer_setup(&l2x0_pmu_hrtimer, l2x0_pmu_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2bec87c3327d..39fd5df73317 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ again:
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ again:
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ again:
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -142,6 +142,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
+		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
 		 * that we are fixing up.
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 5345d218899a..54bdca025c9f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -237,56 +237,17 @@ static inline void poison_init_mem(void *s, size_t count)
 		*p++ = 0xe7fddef0;
 }
 
-static void __init free_highpages(void)
-{
-#ifdef CONFIG_HIGHMEM
-	unsigned long max_low = max_low_pfn;
-	phys_addr_t range_start, range_end;
-	u64 i;
-
-	/* set highmem page free */
-	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
-				&range_start, &range_end, NULL) {
-		unsigned long start = PFN_UP(range_start);
-		unsigned long end = PFN_DOWN(range_end);
-
-		/* Ignore complete lowmem entries */
-		if (end <= max_low)
-			continue;
-
-		/* Truncate partial highmem entries */
-		if (start < max_low)
-			start = max_low;
-
-		for (; start < end; start++)
-			free_highmem_page(pfn_to_page(start));
-	}
-#endif
-}
-
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much
- * memory is free.  This is done after various parts of the system have
- * claimed their memory after the kernel image.
- */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 #ifdef CONFIG_ARM_LPAE
 	swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
 #endif
 
-	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
-
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
-	free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, -1, NULL);
+	memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
 #endif
 
-	free_highpages();
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can
 	 * be detected at build time already.
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 89f1c97f3079..748698e91a4b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -436,7 +436,7 @@ void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
 	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
 }
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
 						   MT_MEMORY_RW,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 1a8f6914ee59..d638cc87807e 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -248,7 +248,7 @@ void __iomem *pci_remap_cfgspace(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL_GPL(pci_remap_cfgspace);
 #endif
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (void *)phys_addr;
 }
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 595e9cb33c1d..326616fbdc44 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -496,11 +496,10 @@ static void orion_gpio_unmask_irq(struct irq_data *d)
 	u32 reg_val;
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	reg_val = irq_reg_readl(gc, ct->regs.mask);
 	reg_val |= mask;
 	irq_reg_writel(gc, reg_val, ct->regs.mask);
-	irq_gc_unlock(gc);
 }
 
 static void orion_gpio_mask_irq(struct irq_data *d)
@@ -510,11 +509,10 @@ static void orion_gpio_mask_irq(struct irq_data *d)
 	u32 mask = d->mask;
 	u32 reg_val;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	reg_val = irq_reg_readl(gc, ct->regs.mask);
 	reg_val &= ~mask;
 	irq_reg_writel(gc, reg_val, ct->regs.mask);
-	irq_gc_unlock(gc);
 }
 
 void __init orion_gpio_init(int gpio_base, int ngpio,
@@ -602,12 +600,12 @@ void __init orion_gpio_init(int gpio_base, int ngpio,
 			       IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE);
 
 	/* Setup irq domain on top of the generic chip. */
-	ochip->domain = irq_domain_add_legacy(NULL,
-					      ochip->chip.ngpio,
-					      ochip->secondary_irq_base,
-					      ochip->secondary_irq_base,
-					      &irq_domain_simple_ops,
-					      ochip);
+	ochip->domain = irq_domain_create_legacy(NULL,
+						 ochip->chip.ngpio,
+						 ochip->secondary_irq_base,
+						 ochip->secondary_irq_base,
+						 &irq_domain_simple_ops,
+						 ochip);
 	if (!ochip->domain)
 		panic("%s: couldn't allocate irq domain (DT).\n",
 		      ochip->chip.label);
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 49eeb2ad8dbd..27c1d5ebcd91 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -481,3 +481,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 8a306bbec4a0..cb044bfd145d 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 hostprogs := vdsomunge
 
diff --git a/arch/arm/vdso/vdso.lds.S b/arch/arm/vdso/vdso.lds.S
index 9bfa0f52923c..7c08371f4400 100644
--- a/arch/arm/vdso/vdso.lds.S
+++ b/arch/arm/vdso/vdso.lds.S
@@ -11,16 +11,16 @@
  */
 
 #include <linux/const.h>
-#include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
 OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - VDSO_DATA_SIZE);
+	VDSO_VVAR_SYMS
 
 	. = SIZEOF_HEADERS;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 940343beb3d4..a182295e6f08 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -38,9 +38,11 @@ config ARM64
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEM_ENCRYPT
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
+	select ARCH_HAS_PTDUMP
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_HW_PTE_YOUNG
@@ -157,11 +159,11 @@ config ARM64
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_LIB_DEVMEM_IS_ALLOWED
 	select GENERIC_PCI_IOMAP
-	select GENERIC_PTDUMP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT
@@ -217,6 +219,7 @@ config ARM64
 		if DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+	select HAVE_BUILDTIME_MCOUNT_SORT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
 	select HAVE_FTRACE_GRAPH_FUNC
@@ -250,6 +253,7 @@ config ARM64
 	select HAVE_KRETPROBES
 	select HAVE_GENERIC_VDSO
 	select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
+	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
 	select KASAN_VMALLOC if KASAN
@@ -323,7 +327,7 @@ config ARCH_MMAP_RND_BITS_MIN
 	default 18
 
 # max bits determined by the following formula:
-#  VA_BITS - PAGE_SHIFT - 3
+#  VA_BITS - PTDESC_TABLE_SHIFT
 config ARCH_MMAP_RND_BITS_MAX
 	default 19 if ARM64_VA_BITS=36
 	default 24 if ARM64_VA_BITS=39
@@ -1302,6 +1306,15 @@ config NVIDIA_CARMEL_CNP_ERRATUM
 
 	  If unsure, say Y.
 
+config ROCKCHIP_ERRATUM_3568002
+	bool "Rockchip 3568002: GIC600 can not access physical addresses higher than 4GB"
+	default y
+	help
+	  The Rockchip RK3566 and RK3568 GIC600 SoC integrations have AXI
+	  addressing limited to the first 32bit of physical address space.
+
+	  If unsure, say Y.
+
 config ROCKCHIP_ERRATUM_3588001
 	bool "Rockchip 3588001: GIC600 can not support shareability attributes"
 	default y
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 02f9248f7c84..8b76821f190f 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -321,6 +321,10 @@ config ARCH_STM32
 	help
 	  This enables support for ARMv8 based STMicroelectronics
 	  STM32 family, including:
+		- STM32MP21:
+			- STM32MP211, STM32MP213, STM32MP215.
+		- STM32MP23:
+			- STM32MP231, STM32MP233, STM32MP235.
 		- STM32MP25:
 			- STM32MP251, STM32MP253, STM32MP255 and STM32MP257.
 
@@ -374,13 +378,12 @@ config ARCH_UNIPHIER
 	  This enables support for Socionext UniPhier SoC family.
 
 config ARCH_VEXPRESS
-	bool "ARMv8 software model (Versatile Express)"
+	bool "ARM Ltd Platforms"
 	select GPIOLIB
 	select PM
 	select PM_GENERIC_DOMAINS
 	help
-	  This enables support for the ARMv8 software model (Versatile
-	  Express).
+	  This enables support for the ARM Ltd Platforms.
 
 config ARCH_VISCONTI
 	bool "Toshiba Visconti SoC Family"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2b25d671365f..1d5dfcd1c13e 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -48,7 +48,7 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_NO_FPU) \
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)
 
-ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y)
+ifeq ($(call rustc-min-version, 108500),y)
 KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat
 else
 KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon"
diff --git a/arch/arm64/boot/dts/airoha/en7581-evb.dts b/arch/arm64/boot/dts/airoha/en7581-evb.dts
index cf58e43dd5b2..d53b72d18242 100644
--- a/arch/arm64/boot/dts/airoha/en7581-evb.dts
+++ b/arch/arm64/boot/dts/airoha/en7581-evb.dts
@@ -24,3 +24,47 @@
 		reg = <0x0 0x80000000 0x2 0x00000000>;
 	};
 };
+
+&spi_nand {
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		bootloader@0 {
+			label = "bootloader";
+			reg = <0x00000000 0x00080000>;
+			read-only;
+		};
+
+		art@200000 {
+			label = "art";
+			reg = <0x00200000 0x00400000>;
+		};
+
+		tclinux@600000 {
+			label = "tclinux";
+			reg = <0x00600000 0x03200000>;
+		};
+
+		tclinux_slave@3800000 {
+			label = "tclinux_alt";
+			reg = <0x03800000 0x03200000>;
+		};
+
+		rootfs_data@6a00000 {
+			label = "rootfs_data";
+			reg = <0x06a00000 0x01400000>;
+		};
+
+		reserved_bmt@7e00000 {
+			label = "reserved_bmt";
+			reg = <0x07e00000 0x00200000>;
+			read-only;
+		};
+	};
+};
+
+&i2c0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/airoha/en7581.dtsi b/arch/arm64/boot/dts/airoha/en7581.dtsi
index 55eb1762fb11..26b136940917 100644
--- a/arch/arm64/boot/dts/airoha/en7581.dtsi
+++ b/arch/arm64/boot/dts/airoha/en7581.dtsi
@@ -2,6 +2,8 @@
 
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/clock/en7523-clk.h>
+#include <dt-bindings/reset/airoha,en7581-reset.h>
 
 / {
 	interrupt-parent = <&gic>;
@@ -122,6 +124,12 @@
 			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
 	};
 
+	clk20m: clock-20000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <20000000>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -142,6 +150,36 @@
 			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
 		};
 
+		spi@1fa10000 {
+			compatible = "airoha,en7581-snand";
+			reg = <0x0 0x1fa10000 0x0 0x140>,
+			      <0x0 0x1fa11000 0x0 0x160>;
+
+			clocks = <&scuclk EN7523_CLK_SPI>;
+			clock-names = "spi";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			spi_nand: nand@0 {
+				compatible = "spi-nand";
+				reg = <0>;
+
+				spi-max-frequency = <50000000>;
+				spi-tx-bus-width = <1>;
+				spi-rx-bus-width = <2>;
+			};
+		};
+
+		scuclk: clock-controller@1fb00000 {
+			compatible = "airoha,en7581-scu";
+			reg = <0x0 0x1fb00000 0x0 0x970>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		uart1: serial@1fbf0000 {
 			compatible = "ns16550";
 			reg = <0x0 0x1fbf0000 0x0 0x30>;
@@ -150,5 +188,58 @@
 			interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <1843200>;
 		};
+
+		rng@1faa1000 {
+			compatible = "airoha,en7581-trng";
+			reg = <0x0 0x1faa1000 0x0 0xc04>;
+			interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		system-controller@1fbf0200 {
+			compatible = "airoha,en7581-gpio-sysctl", "syscon",
+				     "simple-mfd";
+			reg = <0x0 0x1fbf0200 0x0 0xc0>;
+
+			en7581_pinctrl: pinctrl {
+				compatible = "airoha,en7581-pinctrl";
+
+				interrupt-parent = <&gic>;
+				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+
+				gpio-controller;
+				#gpio-cells = <2>;
+
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+		};
+
+		i2c0: i2c@1fbf8000 {
+			compatible = "mediatek,mt7621-i2c";
+			reg = <0x0 0x1fbf8000 0x0 0x100>;
+
+			resets = <&scuclk EN7581_I2C2_RST>;
+
+			clocks = <&clk20m>;
+			clock-frequency = <100000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+
+		i2c1: i2c@1fbf8100 {
+			compatible = "mediatek,mt7621-i2c";
+			reg = <0x0 0x1fbf8100 0x0 0x100>;
+
+			resets = <&scuclk EN7581_I2C_MASTER_RST>;
+
+			clocks = <&clk20m>;
+			clock-frequency = <100000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a100-allwinner-perf1.dts b/arch/arm64/boot/dts/allwinner/sun50i-a100-allwinner-perf1.dts
index a387bccdcefd..a7e3be0155a8 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a100-allwinner-perf1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a100-allwinner-perf1.dts
@@ -6,6 +6,7 @@
 /dts-v1/;
 
 #include "sun50i-a100.dtsi"
+#include "sun50i-a100-cpu-opp.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
 
@@ -38,6 +39,10 @@
 	status = "okay";
 };
 
+&cpu0 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
 &pio {
 	vcc-pb-supply = <&reg_dcdc1>;
 	vcc-pc-supply = <&reg_eldo1>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a100-cpu-opp.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a100-cpu-opp.dtsi
new file mode 100644
index 000000000000..c6a2efa037dc
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a100-cpu-opp.dtsi
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+// Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+// Copyright (c) 2020 ShuoSheng Huang <huangshuosheng@allwinnertech.com>
+
+/ {
+	cpu_opp_table: opp-table-cpu {
+		compatible = "allwinner,sun50i-a100-operating-points";
+		nvmem-cells = <&cpu_speed_grade>;
+		opp-shared;
+
+		opp-408000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <408000000>;
+
+			opp-microvolt-speed0 = <900000>;
+			opp-microvolt-speed1 = <900000>;
+			opp-microvolt-speed2 = <900000>;
+		};
+
+		opp-600000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <600000000>;
+
+			opp-microvolt-speed0 = <900000>;
+			opp-microvolt-speed1 = <900000>;
+			opp-microvolt-speed2 = <900000>;
+		};
+
+		opp-816000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <816000000>;
+
+			opp-microvolt-speed0 = <940000>;
+			opp-microvolt-speed1 = <900000>;
+			opp-microvolt-speed2 = <900000>;
+		};
+
+		opp-1080000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <1080000000>;
+
+			opp-microvolt-speed0 = <1020000>;
+			opp-microvolt-speed1 = <980000>;
+			opp-microvolt-speed2 = <950000>;
+		};
+
+		opp-1200000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <1200000000>;
+
+			opp-microvolt-speed0 = <1100000>;
+			opp-microvolt-speed1 = <1020000>;
+			opp-microvolt-speed2 = <1000000>;
+		};
+
+		opp-1320000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <1320000000>;
+
+			opp-microvolt-speed0 = <1160000>;
+			opp-microvolt-speed1 = <1060000>;
+			opp-microvolt-speed2 = <1030000>;
+		};
+
+		opp-1464000000 {
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			opp-hz = /bits/ 64 <1464000000>;
+
+			opp-microvolt-speed0 = <1180000>;
+			opp-microvolt-speed1 = <1180000>;
+			opp-microvolt-speed2 = <1130000>;
+		};
+	};
+};
+
+&cpu0 {
+	operating-points-v2 = <&cpu_opp_table>;
+};
+
+&cpu1 {
+	operating-points-v2 = <&cpu_opp_table>;
+};
+
+&cpu2 {
+	operating-points-v2 = <&cpu_opp_table>;
+};
+
+&cpu3 {
+	operating-points-v2 = <&cpu_opp_table>;
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi
index a24adba201af..f9f6fea03b74 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a100.dtsi
@@ -23,6 +23,7 @@
 			device_type = "cpu";
 			reg = <0x0>;
 			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
 		};
 
 		cpu1: cpu@1 {
@@ -30,6 +31,7 @@
 			device_type = "cpu";
 			reg = <0x1>;
 			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
 		};
 
 		cpu2: cpu@2 {
@@ -37,6 +39,7 @@
 			device_type = "cpu";
 			reg = <0x2>;
 			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
 		};
 
 		cpu3: cpu@3 {
@@ -44,6 +47,7 @@
 			device_type = "cpu";
 			reg = <0x3>;
 			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
 		};
 	};
 
@@ -175,6 +179,10 @@
 			ths_calibration: calib@14 {
 				reg = <0x14 8>;
 			};
+
+			cpu_speed_grade: cpu-speed-grade@1c {
+				reg = <0x1c 0x2>;
+			};
 		};
 
 		watchdog@30090a0 {
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 13a0e63afeaf..2c64d834a2c4 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -152,28 +152,12 @@
 	vcc-pg-supply = <&reg_aldo1>;
 };
 
-&r_ir {
-	linux,rc-map-name = "rc-beelink-gs1";
-	status = "okay";
-};
-
-&r_pio {
-	/*
-	 * FIXME: We can't add that supply for now since it would
-	 * create a circular dependency between pinctrl, the regulator
-	 * and the RSB Bus.
-	 *
-	 * vcc-pl-supply = <&reg_aldo1>;
-	 */
-	vcc-pm-supply = <&reg_aldo1>;
-};
-
-&r_rsb {
+&r_i2c {
 	status = "okay";
 
-	axp805: pmic@745 {
+	axp805: pmic@36 {
 		compatible = "x-powers,axp805", "x-powers,axp806";
-		reg = <0x745>;
+		reg = <0x36>;
 		interrupt-parent = <&r_intc>;
 		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
@@ -291,6 +275,22 @@
 	};
 };
 
+&r_ir {
+	linux,rc-map-name = "rc-beelink-gs1";
+	status = "okay";
+};
+
+&r_pio {
+	/*
+	 * PL0 and PL1 are used for PMIC I2C
+	 * don't enable the pl-supply else
+	 * it will fail at boot
+	 *
+	 * vcc-pl-supply = <&reg_aldo1>;
+	 */
+	vcc-pm-supply = <&reg_aldo1>;
+};
+
 &spdif {
 	pinctrl-names = "default";
 	pinctrl-0 = <&spdif_tx_pin>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts
index ab87c3447cd7..f005072c68a1 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts
@@ -176,16 +176,12 @@
 	vcc-pg-supply = <&reg_vcc_wifi_io>;
 };
 
-&r_ir {
-	status = "okay";
-};
-
-&r_rsb {
+&r_i2c {
 	status = "okay";
 
-	axp805: pmic@745 {
+	axp805: pmic@36 {
 		compatible = "x-powers,axp805", "x-powers,axp806";
-		reg = <0x745>;
+		reg = <0x36>;
 		interrupt-parent = <&r_intc>;
 		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
@@ -296,6 +292,10 @@
 	};
 };
 
+&r_ir {
+	status = "okay";
+};
+
 &rtc {
 	clocks = <&ext_osc32k>;
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi
index d05dc5d6e6b9..e34dbb992021 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi
@@ -113,20 +113,12 @@
 	vcc-pg-supply = <&reg_aldo1>;
 };
 
-&r_ir {
-	status = "okay";
-};
-
-&r_pio {
-	vcc-pm-supply = <&reg_bldo3>;
-};
-
-&r_rsb {
+&r_i2c {
 	status = "okay";
 
-	axp805: pmic@745 {
+	axp805: pmic@36 {
 		compatible = "x-powers,axp805", "x-powers,axp806";
-		reg = <0x745>;
+		reg = <0x36>;
 		interrupt-parent = <&r_intc>;
 		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
@@ -241,6 +233,14 @@
 	};
 };
 
+&r_ir {
+	status = "okay";
+};
+
+&r_pio {
+	vcc-pm-supply = <&reg_bldo3>;
+};
+
 &rtc {
 	clocks = <&ext_osc32k>;
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-2024.dts b/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-2024.dts
index a231abf1684a..7e17ca07892d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-2024.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-2024.dts
@@ -167,6 +167,12 @@
 			gpios = <&pio 8 12 GPIO_ACTIVE_HIGH>; /* PI12 */
 			default-state = "on";
 		};
+
+		led-1 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&pio 8 11 GPIO_ACTIVE_HIGH>; /* PI11 */
+		};
 	};
 
 	reg_vcc5v: regulator-vcc5v { /* USB-C power input */
@@ -237,6 +243,7 @@
 		battery_power: battery-power {
 			compatible = "x-powers,axp717-battery-power-supply";
 			monitored-battery = <&battery>;
+			x-powers,no-thermistor;
 		};
 
 		regulators {
@@ -328,8 +335,17 @@
 				regulator-name = "boost";
 			};
 
+			/*
+			 * Regulator function is unknown, but reading
+			 * GPIO values in bootloader is inconsistent
+			 * on reboot if this is disabled. Setting to
+			 * default value from regulator OTP mem.
+			 */
 			reg_cpusldo: cpusldo {
-				/* unused */
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-h.dts b/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-h.dts
index ff453336eab1..bef4d107482f 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-h.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h700-anbernic-rg35xx-h.dts
@@ -71,6 +71,25 @@
 			    <&pio 8 2 GPIO_ACTIVE_LOW>;
 		#mux-control-cells = <0>;
 	};
+
+	reg_vcc3v8_usb: regulator-vcc3v8-usb {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&pio 4 5 GPIO_ACTIVE_HIGH>; /* PE5 */
+		regulator-min-microvolt = <3800000>;
+		regulator-max-microvolt = <3800000>;
+		regulator-name = "vcc3v8-usb";
+	};
+
+	reg_vcc5v0_usb: regulator-vcc5v0-usb {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&pio 8 7 GPIO_ACTIVE_HIGH>; /* PI7 */
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc5v0-usb";
+		vin-supply = <&reg_vcc3v8_usb>;
+	};
 };
 
 &gpadc {
@@ -113,3 +132,7 @@
 		function = "gpio_out";
 	};
 };
+
+&usbphy {
+	usb1_vbus-supply = <&reg_vcc5v0_usb>;
+};
diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
index da9de4986660..5a72f0b64247 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
@@ -151,7 +151,7 @@
 			al,msi-num-spis = <160>;
 		};
 
-		io-fabric@fc000000 {
+		io-bus@fc000000 {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
index 8b6156b5af65..dea60d136c2e 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
@@ -361,7 +361,7 @@
 			interrupt-parent = <&gic>;
 		};
 
-		io-fabric@fc000000 {
+		io-bus@fc000000 {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
index 7c82d90e940d..8862adae44e9 100644
--- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
+++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
@@ -58,7 +58,7 @@
 
 &spi1 {
 	status = "okay";
-	sdcard0: sdcard@0 {
+	sdcard0: mmc@0 {
 		compatible = "mmc-spi-slot";
 		reg = <0>;
 		spi-max-frequency = <20000000>;
diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
index 58e2b0a6f841..b34dd8d5d1b1 100644
--- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
+++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
@@ -8,32 +8,10 @@
 
 /dts-v1/;
 
-/include/ "amd-seattle-soc.dtsi"
-/include/ "amd-seattle-cpus.dtsi"
+/include/ "amd-overdrive-rev-b0.dts"
 
 / {
 	model = "AMD Seattle (Rev.B1) Development Board (Overdrive)";
-	compatible = "amd,seattle-overdrive", "amd,seattle";
-
-	chosen {
-		stdout-path = &serial0;
-	};
-
-	psci {
-		compatible = "arm,psci-0.2";
-		method = "smc";
-	};
-};
-
-&ccp0 {
-	status = "okay";
-};
-
-/**
- * NOTE: In Rev.B, gpio0 is reserved.
- */
-&gpio1 {
-	status = "okay";
 };
 
 &gpio2 {
@@ -44,48 +22,11 @@
 	status = "okay";
 };
 
-&gpio4 {
-	status = "okay";
-};
-
-&i2c0 {
-	status = "okay";
-};
-
-&i2c1 {
-	status = "okay";
-};
-
-&pcie0 {
-	status = "okay";
-};
-
 &sata1 {
 	status = "okay";
 };
 
-&spi0 {
-	status = "okay";
-};
-
-&spi1 {
-	status = "okay";
-	sdcard0: sdcard@0 {
-		compatible = "mmc-spi-slot";
-		reg = <0>;
-		spi-max-frequency = <20000000>;
-		voltage-ranges = <3200 3400>;
-		pl022,interface = <0>;
-		pl022,com-mode = <0x0>;
-		pl022,rx-level-trig = <0>;
-		pl022,tx-level-trig = <0>;
-	};
-};
-
 &ipmi_kcs {
 	status = "okay";
 };
 
-&smb0 {
-	/include/ "amd-seattle-xgbe-b.dtsi"
-};
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-clks.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-clks.dtsi
index 2dd2c28171ee..73f687773ce6 100644
--- a/arch/arm64/boot/dts/amd/amd-seattle-clks.dtsi
+++ b/arch/arm64/boot/dts/amd/amd-seattle-clks.dtsi
@@ -5,51 +5,39 @@
  * Copyright (C) 2014 Advanced Micro Devices, Inc.
  */
 
-	adl3clk_100mhz: clk100mhz_0 {
+	adl3clk_100mhz: uartspiclk_100mhz: clock-100000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <100000000>;
 		clock-output-names = "adl3clk_100mhz";
 	};
 
-	ccpclk_375mhz: clk375mhz {
+	ccpclk_375mhz: clock-375000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <375000000>;
 		clock-output-names = "ccpclk_375mhz";
 	};
 
-	sataclk_333mhz: clk333mhz {
+	sataclk_333mhz: clock-333000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <333000000>;
 		clock-output-names = "sataclk_333mhz";
 	};
 
-	pcieclk_500mhz: clk500mhz_0 {
+	dmaclk_500mhz: pcieclk_500mhz: clock-500000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <500000000>;
 		clock-output-names = "pcieclk_500mhz";
 	};
 
-	dmaclk_500mhz: clk500mhz_1 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <500000000>;
-		clock-output-names = "dmaclk_500mhz";
-	};
-
-	miscclk_250mhz: clk250mhz_4 {
+	xgmacclk0_dma_250mhz: xgmacclk0_ptp_250mhz: xgmacclk1_dma_250mhz: xgmacclk1_ptp_250mhz:
+	miscclk_250mhz: clock-250000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <250000000>;
 		clock-output-names = "miscclk_250mhz";
 	};
 
-	uartspiclk_100mhz: clk100mhz_1 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
-		clock-output-names = "uartspiclk_100mhz";
-	};
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
index d3d931eb7677..a611f8288b3e 100644
--- a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
+++ b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
@@ -11,6 +11,8 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	/include/ "amd-seattle-clks.dtsi"
+
 	gic0: interrupt-controller@e1101000 {
 		compatible = "arm,gic-400", "arm,cortex-a15-gic";
 		interrupt-controller;
@@ -38,7 +40,7 @@
 			     <1 10 0xff04>;
 	};
 
-	smb0: smb {
+	smb0: bus {
 		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -51,8 +53,6 @@
 		 */
 		dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x0>;
 
-		/include/ "amd-seattle-clks.dtsi"
-
 		sata0: sata@e0300000 {
 			compatible = "snps,dwc-ahci";
 			reg = <0 0xe0300000 0 0xf0000>;
@@ -121,7 +121,6 @@
 			status = "disabled";
 			compatible = "arm,pl022", "arm,primecell";
 			reg = <0 0xe1020000 0 0x1000>;
-			spi-controller;
 			interrupts = <0 330 4>;
 			clocks = <&uartspiclk_100mhz>, <&uartspiclk_100mhz>;
 			clock-names = "sspclk", "apb_pclk";
@@ -131,7 +130,6 @@
 			status = "disabled";
 			compatible = "arm,pl022", "arm,primecell";
 			reg = <0 0xe1030000 0 0x1000>;
-			spi-controller;
 			interrupts = <0 329 4>;
 			clocks = <&uartspiclk_100mhz>, <&uartspiclk_100mhz>;
 			clock-names = "sspclk", "apb_pclk";
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
index 9259e547e2e8..18b0c2dd1b2d 100644
--- a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
+++ b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
@@ -5,35 +5,7 @@
  * Copyright (C) 2015 Advanced Micro Devices, Inc.
  */
 
-	xgmacclk0_dma_250mhz: clk250mhz_0 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <250000000>;
-		clock-output-names = "xgmacclk0_dma_250mhz";
-	};
-
-	xgmacclk0_ptp_250mhz: clk250mhz_1 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <250000000>;
-		clock-output-names = "xgmacclk0_ptp_250mhz";
-	};
-
-	xgmacclk1_dma_250mhz: clk250mhz_2 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <250000000>;
-		clock-output-names = "xgmacclk1_dma_250mhz";
-	};
-
-	xgmacclk1_ptp_250mhz: clk250mhz_3 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <250000000>;
-		clock-output-names = "xgmacclk1_ptp_250mhz";
-	};
-
-	xgmac0: xgmac@e0700000 {
+	xgmac0: ethernet@e0700000 {
 		compatible = "amd,xgbe-seattle-v1a";
 		reg = <0 0xe0700000 0 0x80000>,
 		      <0 0xe0780000 0 0x80000>,
@@ -59,7 +31,7 @@
 		dma-coherent;
 	};
 
-	xgmac1: xgmac@e0900000 {
+	xgmac1: ethernet@e0900000 {
 		compatible = "amd,xgbe-seattle-v1a";
 		reg = <0 0xe0900000 0 0x80000>,
 		      <0 0xe0980000 0 0x80000>,
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-a4.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-a4.dtsi
index de10e7aebf21..a06838552f21 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-a4.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-a4.dtsi
@@ -48,3 +48,24 @@
 		};
 	};
 };
+
+&apb {
+	gpio_intc: interrupt-controller@4080 {
+		compatible = "amlogic,a4-gpio-intc",
+			     "amlogic,meson-gpio-intc";
+		reg = <0x0 0x4080 0x0 0x20>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		amlogic,channel-interrupts =
+			<10 11 12 13 14 15 16 17 18 19 20 21>;
+	};
+
+	gpio_ao_intc: interrupt-controller@8e72c {
+		compatible = "amlogic,a4-gpio-ao-intc",
+			     "amlogic,meson-gpio-intc";
+		reg = <0x0 0x8e72c 0x0 0x0c>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		amlogic,channel-interrupts = <140 141>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-a5.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-a5.dtsi
index 17a6316de891..32ed1776891b 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-a5.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-a5.dtsi
@@ -48,3 +48,15 @@
 		};
 	};
 };
+
+&apb {
+	gpio_intc: interrupt-controller@4080 {
+		compatible = "amlogic,a5-gpio-intc",
+			     "amlogic,meson-gpio-intc";
+		reg = <0x0 0x4080 0x0 0x20>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		amlogic,channel-interrupts =
+			<10 11 12 13 14 15 16 17 18 19 20 21>;
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index e9b22868983d..a6924d246bb1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -1693,8 +1693,12 @@
 			};
 
 			pwm_AO_cd: pwm@2000 {
-				compatible = "amlogic,meson-axg-ao-pwm";
+				compatible = "amlogic,meson-axg-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x02000  0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc_AO CLKID_AO_CLK81>,
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV5>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -1728,8 +1732,12 @@
 			};
 
 			pwm_AO_ab: pwm@7000 {
-				compatible = "amlogic,meson-axg-ao-pwm";
+				compatible = "amlogic,meson-axg-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x07000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc_AO CLKID_AO_CLK81>,
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV5>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -1806,15 +1814,23 @@
 			};
 
 			pwm_ab: pwm@1b000 {
-				compatible = "amlogic,meson-axg-ee-pwm";
+				compatible = "amlogic,meson-axg-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1b000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc CLKID_FCLK_DIV5>,
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
 
 			pwm_cd: pwm@1a000 {
-				compatible = "amlogic,meson-axg-ee-pwm";
+				compatible = "amlogic,meson-axg-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1a000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc CLKID_FCLK_DIV5>,
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index 49b51c54013f..69834b49673d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -2060,8 +2060,11 @@
 			};
 
 			pwm_AO_cd: pwm@2000 {
-				compatible = "amlogic,meson-g12a-ao-pwm-cd";
+				compatible = "amlogic,meson-g12-pwm-v2",
+					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x2000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc_AO CLKID_AO_CLK81>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -2099,8 +2102,13 @@
 			};
 
 			pwm_AO_ab: pwm@7000 {
-				compatible = "amlogic,meson-g12a-ao-pwm-ab";
+				compatible = "amlogic,meson-g12-pwm-v2",
+					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x7000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <&clkc_AO CLKID_AO_CLK81>,
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV5>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -2301,22 +2309,37 @@
 			};
 
 			pwm_ef: pwm@19000 {
-				compatible = "amlogic,meson-g12a-ee-pwm";
+				compatible = "amlogic,meson-g12-pwm-v2",
+					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x19000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
 
 			pwm_cd: pwm@1a000 {
-				compatible = "amlogic,meson-g12a-ee-pwm";
+				compatible = "amlogic,meson-g12-pwm-v2",
+					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1a000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
 
 			pwm_ab: pwm@1b000 {
-				compatible = "amlogic,meson-g12a-ee-pwm";
+				compatible = "amlogic,meson-g12-pwm-v2",
+					     "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x1b000 0x0 0x20>;
+				clocks = <&xtal>,
+					 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+					 <&clkc CLKID_FCLK_DIV4>,
+					 <&clkc CLKID_FCLK_DIV3>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts
index a457b3f4397b..9aa36f17ffa2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts
@@ -346,8 +346,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -355,8 +353,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &pdm {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
index c779a5da7d1e..952b8d02e5c2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
@@ -284,8 +284,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -293,8 +291,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
index ea51341f031b..52fbc5103e45 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
@@ -389,8 +389,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -398,8 +396,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &pdm {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
index f70a46967e2b..5407049d2647 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
@@ -502,8 +502,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
index 32f98a192494..01da83658ae3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
@@ -328,8 +328,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -363,8 +361,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &uart_A {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d-libretech-cc.dts
index 65b963d794cd..adedc1340c78 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d-libretech-cc.dts
@@ -116,6 +116,4 @@
 
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>, <&pwm_b_x7_pins>;
-	clocks = <&xtal>, <&xtal>;
-	clock-names = "clkin0", "clkin1";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
index 08c33ec7e9f1..92e8b26ecccc 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi-cm4.dtsi
@@ -257,8 +257,6 @@
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 
 	status = "okay";
 };
@@ -273,8 +271,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
index d4e1990b5f26..54663c55a20e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-bananapi.dtsi
@@ -367,8 +367,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &pwm_ef {
@@ -380,8 +378,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
index de35fa2d7a6d..8e3e3354ed67 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi
@@ -116,6 +116,10 @@
 	status = "okay";
 };
 
+&clkc_audio {
+	status = "okay";
+};
+
 &frddr_a {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
index 16dd409051b4..48650bad230d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
@@ -92,16 +92,12 @@
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
index 09d959aefb18..7e8964bacfce 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
@@ -327,16 +327,12 @@
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-radxa-zero2.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-radxa-zero2.dts
index 39feba7f2d08..fc05ecf90714 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-radxa-zero2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-radxa-zero2.dts
@@ -379,32 +379,24 @@
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_ef {
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_AO_ab {
 	pinctrl-0 = <&pwm_ao_a_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
index 4cb6930ffb19..a7a0fc264cdc 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
@@ -304,24 +304,18 @@
 &pwm_ab {
 	pinctrl-0 = <&pwm_a_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
 &pwm_ef {
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
index d38c3a224fbe..2da49cfbde77 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
@@ -345,24 +345,18 @@
 &pwm_AO_ab {
 	pinctrl-0 = <&pwm_ao_a_3_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_ab {
 	pinctrl-0 = <&pwm_b_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
 &pwm_ef {
 	pinctrl-0 = <&pwm_e_pins>, <&pwm_f_clk_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 45ccddd1aaf0..6da1316d97c6 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -240,8 +240,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 2673f0dbafe7..7d99ca44e660 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -329,14 +329,14 @@
 			};
 
 			pwm_ab: pwm@8550 {
-				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				compatible = "amlogic,meson-gxbb-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x08550 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
 
 			pwm_cd: pwm@8650 {
-				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				compatible = "amlogic,meson-gxbb-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x08650 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
@@ -351,7 +351,7 @@
 			};
 
 			pwm_ef: pwm@86c0 {
-				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				compatible = "amlogic,meson-gxbb-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x086c0 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
@@ -498,7 +498,7 @@
 			};
 
 			pwm_AO_ab: pwm@550 {
-				compatible = "amlogic,meson-gx-ao-pwm", "amlogic,meson-gxbb-ao-pwm";
+				compatible = "amlogic,meson-gxbb-pwm-v2", "amlogic,meson8-pwm-v2";
 				reg = <0x0 0x00550 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
index cf2e2ef81680..2ecc6ebd5a43 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts
@@ -298,8 +298,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
index 7d7dde93fff3..c09da40ff7b0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
@@ -241,8 +241,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* Wireless SDIO Module */
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index 1736bd2e96e2..6f67364fd63f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -150,8 +150,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* Wireless SDIO Module */
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index 3807a184810b..6ff567225fee 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -222,8 +222,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
index deb295227189..bfedfc1472ec 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
@@ -185,8 +185,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index ed00e67e6923..6c134592c7bb 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -739,6 +739,31 @@
 	};
 };
 
+&pwm_ab {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
+&pwm_AO_ab {
+	clocks = <&xtal>, <&clkc CLKID_CLK81>;
+};
+
+&pwm_cd {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
+&pwm_ef {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
 &pwrc {
 	resets = <&reset RESET_VIU>,
 		 <&reset RESET_VENC>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
index c5e2306ad7a4..ca7c4e8e7cac 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
@@ -280,8 +280,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* This is connected to the Bluetooth module: */
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
index 2b94b6e5285e..4ca90ac947b7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
@@ -116,8 +116,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
index 89fe5110f7a2..62a2da766a00 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
@@ -115,8 +115,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* SD card */
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
index a80f0ea2773b..4e89d6f6bb57 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
@@ -211,8 +211,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_3_pins>, <&pwm_ao_b_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal> , <&xtal>;
-	clock-names = "clkin0", "clkin1" ;
 };
 
 &pwm_ef {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index c79f9f2099bf..236cedec9f19 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -145,8 +145,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* Wireless SDIO Module */
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index b52a830efcce..05a0d4de3ad7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -101,8 +101,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index f58d1790de1c..19b8a39de6a0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -809,6 +809,31 @@
 	};
 };
 
+&pwm_ab {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
+&pwm_AO_ab {
+	clocks = <&xtal>, <&clkc CLKID_CLK81>;
+};
+
+&pwm_cd {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
+&pwm_ef {
+	clocks = <&xtal>,
+		 <0>, /* unknown/untested, the datasheet calls it "vid_pll" */
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_FCLK_DIV3>;
+};
+
 &pwrc {
 	resets = <&reset RESET_VIU>,
 		 <&reset RESET_VENC>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 96a3dd2d8a99..2a09b3d550e2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -289,16 +289,12 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_3_pins>, <&pwm_ao_b_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &pwm_ef {
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>, <&pwm_f_clk_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 &sd_emmc_a {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
index 7356d3b628b1..ecaf678b23dd 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts
@@ -192,8 +192,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
 };
 
 /* Wireless SDIO Module */
diff --git a/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi b/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
index 929e4720ae76..ac9c4c2673b1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
@@ -458,24 +458,18 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 };
 
 &pwm_ab {
 	status = "okay";
 	pinctrl-0 = <&pwm_b_x7_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 };
 
 &pwm_cd {
 	status = "okay";
 	pinctrl-0 = <&pwm_d_x3_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
index d1fa8b8bf795..a3463149db3d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
@@ -199,15 +199,11 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -215,8 +211,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
index 81dce862902a..40db95f64636 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
@@ -367,8 +367,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-khadas-vim3l.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-khadas-vim3l.dts
index 9c0b544e2209..5d75ad3f3e46 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-khadas-vim3l.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-khadas-vim3l.dts
@@ -78,8 +78,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
index 7b0e9817a615..ad8d07883760 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
@@ -392,8 +392,6 @@
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
index 2e3397e55da2..37d7f64b6d5d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
@@ -435,15 +435,11 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &pwm_AO_cd {
 	pinctrl-0 = <&pwm_ao_d_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin1";
 	status = "okay";
 };
 
@@ -451,8 +447,6 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_e_pins>;
 	pinctrl-names = "default";
-	clocks = <&xtal>;
-	clock-names = "clkin0";
 };
 
 &saradc {
diff --git a/arch/arm64/boot/dts/apple/Makefile b/arch/arm64/boot/dts/apple/Makefile
index ab6ebb53218a..4f337bff36cd 100644
--- a/arch/arm64/boot/dts/apple/Makefile
+++ b/arch/arm64/boot/dts/apple/Makefile
@@ -46,6 +46,22 @@ dtb-$(CONFIG_ARCH_APPLE) += t8011-j120.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8011-j121.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8011-j207.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8011-j208.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j132.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j137.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j140a.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j140k.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j152f.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j160.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j174.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j185.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j185f.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j213.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j215.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j223.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j230k.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j214k.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j680.dtb
+dtb-$(CONFIG_ARCH_APPLE) += t8012-j780.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8015-d201.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8015-d20.dtb
 dtb-$(CONFIG_ARCH_APPLE) += t8015-d211.dtb
diff --git a/arch/arm64/boot/dts/apple/s5l8960x-5s.dtsi b/arch/arm64/boot/dts/apple/s5l8960x-5s.dtsi
index 0b16adf07f79..8868df1538d6 100644
--- a/arch/arm64/boot/dts/apple/s5l8960x-5s.dtsi
+++ b/arch/arm64/boot/dts/apple/s5l8960x-5s.dtsi
@@ -8,6 +8,7 @@
 
 #include "s5l8960x.dtsi"
 #include "s5l8960x-common.dtsi"
+#include "s5l8960x-opp.dtsi"
 #include <dt-bindings/input/input.h>
 
 / {
@@ -49,3 +50,11 @@
 		};
 	};
 };
+
+&dwi_bl {
+	status = "okay";
+};
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_mipi_dsi>;
+};
diff --git a/arch/arm64/boot/dts/apple/s5l8960x-air1.dtsi b/arch/arm64/boot/dts/apple/s5l8960x-air1.dtsi
index 741c5a9f21dd..dd57eb1d34c0 100644
--- a/arch/arm64/boot/dts/apple/s5l8960x-air1.dtsi
+++ b/arch/arm64/boot/dts/apple/s5l8960x-air1.dtsi
@@ -8,6 +8,7 @@
 
 #include "s5l8960x.dtsi"
 #include "s5l8960x-common.dtsi"
+#include "s5l8965x-opp.dtsi"
 #include <dt-bindings/input/input.h>
 
 / {
@@ -49,3 +50,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_dp>;
+};
diff --git a/arch/arm64/boot/dts/apple/s5l8960x-mini2.dtsi b/arch/arm64/boot/dts/apple/s5l8960x-mini2.dtsi
index b27ef5680626..f3696d22e71c 100644
--- a/arch/arm64/boot/dts/apple/s5l8960x-mini2.dtsi
+++ b/arch/arm64/boot/dts/apple/s5l8960x-mini2.dtsi
@@ -8,6 +8,7 @@
 
 #include "s5l8960x.dtsi"
 #include "s5l8960x-common.dtsi"
+#include "s5l8960x-opp.dtsi"
 #include <dt-bindings/input/input.h>
 
 / {
@@ -49,3 +50,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_dp>;
+};
diff --git a/arch/arm64/boot/dts/apple/s5l8960x-opp.dtsi b/arch/arm64/boot/dts/apple/s5l8960x-opp.dtsi
new file mode 100644
index 000000000000..e4d568c4a119
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s5l8960x-opp.dtsi
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Operating points for Apple S5L8960X "A7" SoC, Up to 1296 MHz
+ *
+ * target-type: N51, N53, J85, J86. J87, J85m, J86m, J87m
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/ {
+	cyclone_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <15500>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <43000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <3>;
+			clock-latency-ns = <26000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <840000000>;
+			opp-level = <4>;
+			clock-latency-ns = <30000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1128000000>;
+			opp-level = <5>;
+			clock-latency-ns = <39500>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1296000000>;
+			opp-level = <6>;
+			clock-latency-ns = <45500>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/s5l8960x-pmgr.dtsi b/arch/arm64/boot/dts/apple/s5l8960x-pmgr.dtsi
new file mode 100644
index 000000000000..da265f484307
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s5l8960x-pmgr.dtsi
@@ -0,0 +1,610 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple S5L8960X "A7" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@20000 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@20008 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_secuart0: power-controller@200f0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "secuart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_secuart1: power-controller@200f8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "secuart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_cpm: power-controller@20010 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_lio: power-controller@20018 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "lio";
+		apple,always-on; /* Core device */
+	};
+
+	ps_iomux: power-controller@20020 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "iomux";
+		apple,always-on; /* Core device */
+	};
+
+	ps_aic: power-controller@20028 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_debug: power-controller@20030 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20030 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_dwi: power-controller@20038 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20038 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@20040 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_mca0: power-controller@20048 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20048 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@20050 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@20058 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20058 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@20060 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20060 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@20068 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20068 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@20070 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20070 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@20078 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20078 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@20080 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20080 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@20088 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20088 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@20090 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20090 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@20098 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20098 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@200a0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@200a8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@200b0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@200b8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@200c0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@200c8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@200d0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@200d8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@200e0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@200e8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x200e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio_p: power-controller@20110 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+	};
+
+	ps_usb: power-controller@20158 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@20160 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@20170 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@20180 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_disp_busmux: power-controller@201a8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp_busmux";
+	};
+
+	ps_media: power-controller@201d8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp: power-controller@201d0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp";
+	};
+
+	ps_msr: power-controller@201e0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@201e8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0: power-controller@201b0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_aes0: power-controller@20100 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aes0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@20108 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsic0_phy: power-controller@20118 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_hsic1_phy: power-controller@20120 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic1_phy";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_hsic2_phy: power-controller@20128 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic2_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_ispsens0: power-controller@20130 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens0";
+	};
+
+	ps_ispsens1: power-controller@20138 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens1";
+	};
+
+	ps_mcc: power-controller@20140 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Core device */
+	};
+
+	ps_mcu: power-controller@20148 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcu";
+		apple,always-on; /* Core device */
+	};
+
+	ps_amp: power-controller@20150 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "amp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb2host0_ohci: power-controller@20168 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usb2host1_ohci: power-controller@20178 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1_ohci";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_usbotg: power-controller@20188 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@20190 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@20198 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_cp: power-controller@201a0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_mipi_dsi: power-controller@201b8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_dp: power-controller@201c0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0>;
+	};
+
+	ps_disp1: power-controller@201c8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_vdec: power-controller@201f0 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec";
+		power-domains = <&ps_media>;
+	};
+
+	ps_venc: power-controller@201f8 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc";
+		power-domains = <&ps_media>;
+	};
+
+	ps_ans: power-controller@20200 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans";
+	};
+
+	ps_ans_dll: power-controller@20208 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans_dll";
+		power-domains = <&ps_ans>;
+	};
+
+	ps_gfx: power-controller@20218 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@20268 {
+		compatible = "apple,s5l8960x-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		power-domains = <&ps_secuart1>, <&ps_secuart0>;
+		apple,always-on; /* Locked on */
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/s5l8960x.dtsi b/arch/arm64/boot/dts/apple/s5l8960x.dtsi
index 0218ecac1d83..d820b0e43050 100644
--- a/arch/arm64/boot/dts/apple/s5l8960x.dtsi
+++ b/arch/arm64/boot/dts/apple/s5l8960x.dtsi
@@ -33,6 +33,8 @@
 			compatible = "apple,cyclone";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&cyclone_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -41,6 +43,8 @@
 			compatible = "apple,cyclone";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&cyclone_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -53,6 +57,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202220000 {
+			compatible = "apple,s5l8960x-cluster-cpufreq";
+			reg = <0x2 0x02220000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0a0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0a0000 0x0 0x4000>;
@@ -62,9 +72,18 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,s5l8960x-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x24000>;
+		};
+
 		wdt: watchdog@20e027000 {
 			compatible = "apple,s5l8960x-wdt", "apple,wdt";
 			reg = <0x2 0x0e027000 0x0 0x1000>;
@@ -78,11 +97,20 @@
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		dwi_bl: backlight@20e200010 {
+			compatible = "apple,s5l8960x-dwi-bl", "apple,dwi-bl";
+			reg = <0x2 0x0e200010 0x0 0x8>;
+			power-domains = <&ps_dwi>;
+			status = "disabled";
 		};
 
 		pinctrl: pinctrl@20e300000 {
 			compatible = "apple,s5l8960x-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0e300000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -111,3 +139,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "s5l8960x-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/s5l8965x-opp.dtsi b/arch/arm64/boot/dts/apple/s5l8965x-opp.dtsi
new file mode 100644
index 000000000000..d34dae74a90c
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s5l8965x-opp.dtsi
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Operating points for Apple S5L8965X "A7" Rev A SoC, Up to 1392 MHz
+ *
+ * target-type: J71, J72, J73
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/ {
+	cyclone_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <10000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <2>;
+			clock-latency-ns = <49000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <840000000>;
+			opp-level = <3>;
+			clock-latency-ns = <30000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <1128000000>;
+			opp-level = <4>;
+			clock-latency-ns = <39500>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1296000000>;
+			opp-level = <5>;
+			clock-latency-ns = <45500>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1392000000>;
+			opp-level = <6>;
+			clock-latency-ns = <46500>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/s800-0-3-common.dtsi b/arch/arm64/boot/dts/apple/s800-0-3-common.dtsi
index 4276bd890e81..cb42c5f2c1b6 100644
--- a/arch/arm64/boot/dts/apple/s800-0-3-common.dtsi
+++ b/arch/arm64/boot/dts/apple/s800-0-3-common.dtsi
@@ -43,6 +43,10 @@
 	};
 };
 
+&dwi_bl {
+	status = "okay";
+};
+
 &serial0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/apple/s800-0-3-pmgr.dtsi b/arch/arm64/boot/dts/apple/s800-0-3-pmgr.dtsi
new file mode 100644
index 000000000000..196b8e745a95
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s800-0-3-pmgr.dtsi
@@ -0,0 +1,757 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple S8000/3 "A9" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80150 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80158 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dwi: power-controller@80110 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@80118 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pms: power-controller@80120 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_pcie_ref: power-controller@80148 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_mca0: power-controller@80168 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80170 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80178 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80180 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80188 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@80190 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@80198 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@801a0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801a8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801b0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801b8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801c0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801c8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801d0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@801d8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@801e0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@801e8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@801f0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@801f8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80160 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsic0_phy: power-controller@80128 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_hsic1_phy: power-controller@80130 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic1_phy";
+		power-domains = <&ps_usb2host2>;
+	};
+
+	ps_isp_sens0: power-controller@80138 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens0";
+	};
+
+	ps_isp_sens1: power-controller@80140 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens1";
+	};
+
+	ps_usb: power-controller@80250 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@80258 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@80260 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@80270 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host2: power-controller@80280 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host2";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_rtmux: power-controller@802a8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "rtmux";
+	};
+
+	ps_media: power-controller@802d0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp: power-controller@802c8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_msr: power-controller@802e0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@802d8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0: power-controller@802b0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_pmp: power-controller@802e8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pms_sram: power-controller@802f0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_uart5: power-controller@80200 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@80208 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@80210 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@80218 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_aes0: power-controller@80220 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aes0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80228 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80228 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80230 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs1: power-controller@80238 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs2: power-controller@80240 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs3: power-controller@80248 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_usb2host0_ohci: power-controller@80268 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usb2host1_ohci: power-controller@80278 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1_ohci";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_usb2host2_ohci: power-controller@80288 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host2_ohci";
+		power-domains = <&ps_usb2host2>;
+	};
+
+	ps_usbotg: power-controller@80290 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@80298 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802a0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_mipi_dsi: power-controller@802b8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_dp: power-controller@802c0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0>;
+	};
+
+	ps_vdec: power-controller@802f8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec";
+		power-domains = <&ps_media>;
+	};
+
+	ps_venc: power-controller@80308 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie: power-controller@80310 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@80318 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_pcie_link0: power-controller@80320 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link0";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link1: power-controller@80328 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link1";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link2: power-controller@80330 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80330 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link2";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link3: power-controller@80338 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80338 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link3";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_gfx: power-controller@80340 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80340 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_venc_pipe: power-controller@88000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me0: power-controller@88008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88010 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_aop: power-controller@80000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop";
+		power-domains = <&ps_aop_busif &ps_aop_cpu &ps_aop_filter>;
+		apple,always-on; /* Always on processor */
+	};
+
+	ps_debug: power-controller@80008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_aop_gpio: power-controller@80010 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_gpio";
+		power-domains = <&ps_aop>;
+	};
+
+	ps_aop_cpu: power-controller@80040 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_cpu";
+	};
+
+	ps_aop_filter: power-controller@80048 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80048 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_filter";
+	};
+
+	ps_aop_busif: power-controller@80050 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_busif";
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/s800-0-3.dtsi b/arch/arm64/boot/dts/apple/s800-0-3.dtsi
new file mode 100644
index 000000000000..c0e9ae45627c
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s800-0-3.dtsi
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple S8000/S8003 "A9" SoC
+ *
+ * This file contains parts common to both variants of A9
+ *
+ * Copyright (c) 2022, Konrad Dybcio <konradybcio@kernel.org>
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/apple-aic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/apple.h>
+
+/ {
+	interrupt-parent = <&aic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	clkref: clock-ref {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "clkref";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "apple,twister";
+			reg = <0x0 0x0>;
+			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			operating-points-v2 = <&twister_opp>;
+			performance-domains = <&cpufreq>;
+			enable-method = "spin-table";
+			device_type = "cpu";
+		};
+
+		cpu1: cpu@1 {
+			compatible = "apple,twister";
+			reg = <0x0 0x1>;
+			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			operating-points-v2 = <&twister_opp>;
+			performance-domains = <&cpufreq>;
+			enable-method = "spin-table";
+			device_type = "cpu";
+		};
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		nonposted-mmio;
+		ranges;
+
+		cpufreq: performance-controller@202220000 {
+			compatible = "apple,s8000-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x02220000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
+		serial0: serial@20a0c0000 {
+			compatible = "apple,s5l-uart";
+			reg = <0x2 0x0a0c0000 0x0 0x4000>;
+			reg-io-width = <4>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 192 IRQ_TYPE_LEVEL_HIGH>;
+			/* Use the bootloader-enabled clocks for now. */
+			clocks = <&clkref>, <&clkref>;
+			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
+			status = "disabled";
+		};
+
+		pmgr: power-management@20e000000 {
+			compatible = "apple,s8000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x8c000>;
+		};
+
+		aic: interrupt-controller@20e100000 {
+			compatible = "apple,s8000-aic", "apple,aic";
+			reg = <0x2 0x0e100000 0x0 0x100000>;
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		dwi_bl: backlight@20e200080 {
+			compatible = "apple,s8000-dwi-bl", "apple,dwi-bl";
+			reg = <0x2 0x0e200080 0x0 0x8>;
+			power-domains = <&ps_dwi>;
+			status = "disabled";
+		};
+
+		pinctrl_ap: pinctrl@20f100000 {
+			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x0f100000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_ap 0 0 208>;
+			apple,npins = <208>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 42 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 43 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 44 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 45 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 46 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 48 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_aop: pinctrl@2100f0000 {
+			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x100f0000 0x0 0x100000>;
+			power-domains = <&ps_aop_gpio>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_aop 0 0 42>;
+			apple,npins = <42>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 113 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 114 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 115 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 116 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 117 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 118 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 119 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pmgr_mini: power-management@210200000 {
+			compatible = "apple,s8000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x10200000 0 0x84000>;
+		};
+
+		wdt: watchdog@2102b0000 {
+			compatible = "apple,s8000-wdt", "apple,wdt";
+			reg = <0x2 0x102b0000 0x0 0x4000>;
+			clocks = <&clkref>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 4 IRQ_TYPE_LEVEL_HIGH>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&aic>;
+		interrupt-names = "phys", "virt";
+		/* Note that A9 doesn't actually have a hypervisor (EL2 is not implemented). */
+		interrupts = <AIC_FIQ AIC_TMR_GUEST_PHYS IRQ_TYPE_LEVEL_HIGH>,
+			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
+	};
+};
+
+#include "s800-0-3-pmgr.dtsi"
+
+/*
+ * The A9 was made by two separate fabs on two different process
+ * nodes: Samsung made the S8000 (APL0898) on 14nm and TSMC made
+ * the S8003 (APL1022) on 16nm. There are some minor differences
+ * such as timing in cpufreq state transistions.
+ */
diff --git a/arch/arm64/boot/dts/apple/s8000.dtsi b/arch/arm64/boot/dts/apple/s8000.dtsi
index 6e9046ea106c..72322f5677ab 100644
--- a/arch/arm64/boot/dts/apple/s8000.dtsi
+++ b/arch/arm64/boot/dts/apple/s8000.dtsi
@@ -4,141 +4,65 @@
  *
  * Other names: H8P, "Maui"
  *
- * Copyright (c) 2022, Konrad Dybcio <konradybcio@kernel.org>
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
  */
 
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/interrupt-controller/apple-aic.h>
-#include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/pinctrl/apple.h>
+#include "s800-0-3.dtsi"
 
 / {
-	interrupt-parent = <&aic>;
-	#address-cells = <2>;
-	#size-cells = <2>;
+	twister_opp: opp-table {
+		compatible = "operating-points-v2";
 
-	clkref: clock-ref {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <24000000>;
-		clock-output-names = "clkref";
-	};
-
-	cpus {
-		#address-cells = <2>;
-		#size-cells = <0>;
-
-		cpu0: cpu@0 {
-			compatible = "apple,twister";
-			reg = <0x0 0x0>;
-			cpu-release-addr = <0 0>; /* To be filled in by loader */
-			enable-method = "spin-table";
-			device_type = "cpu";
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <650>;
 		};
-
-		cpu1: cpu@1 {
-			compatible = "apple,twister";
-			reg = <0x0 0x1>;
-			cpu-release-addr = <0 0>; /* To be filled in by loader */
-			enable-method = "spin-table";
-			device_type = "cpu";
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <75000>;
 		};
-	};
-
-	soc {
-		compatible = "simple-bus";
-		#address-cells = <2>;
-		#size-cells = <2>;
-		nonposted-mmio;
-		ranges;
-
-		serial0: serial@20a0c0000 {
-			compatible = "apple,s5l-uart";
-			reg = <0x2 0x0a0c0000 0x0 0x4000>;
-			reg-io-width = <4>;
-			interrupt-parent = <&aic>;
-			interrupts = <AIC_IRQ 192 IRQ_TYPE_LEVEL_HIGH>;
-			/* Use the bootloader-enabled clocks for now. */
-			clocks = <&clkref>, <&clkref>;
-			clock-names = "uart", "clk_uart_baud0";
-			status = "disabled";
+		opp03 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <3>;
+			clock-latency-ns = <27000>;
 		};
-
-		aic: interrupt-controller@20e100000 {
-			compatible = "apple,s8000-aic", "apple,aic";
-			reg = <0x2 0x0e100000 0x0 0x100000>;
-			#interrupt-cells = <3>;
-			interrupt-controller;
+		opp04 {
+			opp-hz = /bits/ 64 <912000000>;
+			opp-level = <4>;
+			clock-latency-ns = <32000>;
 		};
-
-		pinctrl_ap: pinctrl@20f100000 {
-			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
-			reg = <0x2 0x0f100000 0x0 0x100000>;
-
-			gpio-controller;
-			#gpio-cells = <2>;
-			gpio-ranges = <&pinctrl_ap 0 0 208>;
-			apple,npins = <208>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-			interrupt-parent = <&aic>;
-			interrupts = <AIC_IRQ 42 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 43 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 44 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 45 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 46 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 47 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 48 IRQ_TYPE_LEVEL_HIGH>;
+		opp05 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-level = <5>;
+			clock-latency-ns = <35000>;
 		};
-
-		pinctrl_aop: pinctrl@2100f0000 {
-			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
-			reg = <0x2 0x100f0000 0x0 0x100000>;
-
-			gpio-controller;
-			#gpio-cells = <2>;
-			gpio-ranges = <&pinctrl_aop 0 0 42>;
-			apple,npins = <42>;
-
-			interrupt-controller;
-			#interrupt-cells = <2>;
-			interrupt-parent = <&aic>;
-			interrupts = <AIC_IRQ 113 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 114 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 115 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 116 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 117 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 118 IRQ_TYPE_LEVEL_HIGH>,
-				     <AIC_IRQ 119 IRQ_TYPE_LEVEL_HIGH>;
+		opp06 {
+			opp-hz = /bits/ 64 <1512000000>;
+			opp-level = <6>;
+			clock-latency-ns = <45000>;
 		};
-
-		wdt: watchdog@2102b0000 {
-			compatible = "apple,s8000-wdt", "apple,wdt";
-			reg = <0x2 0x102b0000 0x0 0x4000>;
-			clocks = <&clkref>;
-			interrupt-parent = <&aic>;
-			interrupts = <AIC_IRQ 4 IRQ_TYPE_LEVEL_HIGH>;
+		opp07 {
+			opp-hz = /bits/ 64 <1800000000>;
+			opp-level = <7>;
+			clock-latency-ns = <58000>;
 		};
-	};
-
-	timer {
-		compatible = "arm,armv8-timer";
-		interrupt-parent = <&aic>;
-		interrupt-names = "phys", "virt";
-		/* Note that A9 doesn't actually have a hypervisor (EL2 is not implemented). */
-		interrupts = <AIC_FIQ AIC_TMR_GUEST_PHYS IRQ_TYPE_LEVEL_HIGH>,
-			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp08 {
+			opp-hz = /bits/ 64 <1844000000>;
+			opp-level = <8>;
+			clock-latency-ns = <58000>;
+			turbo-mode;
+		};
+#endif
 	};
 };
 
 /*
  * The A9 was made by two separate fabs on two different process
  * nodes: Samsung made the S8000 (APL0898) on 14nm and TSMC made
- * the S8003 (APL1022) on 16nm. While they are seemingly the same,
- * they do have distinct part numbers and devices using them have
- * distinct model names. There are currently no known differences
- * between these as far as Linux is concerned, but let's keep things
- * structured properly to make it easier to alter the behaviour of
- * one of the chips if need be.
+ * the S8003 (APL1022) on 16nm. There are some minor differences
+ * such as timing in cpufreq state transistions.
  */
diff --git a/arch/arm64/boot/dts/apple/s8001-common.dtsi b/arch/arm64/boot/dts/apple/s8001-common.dtsi
index e94d0e77653a..91b06e113894 100644
--- a/arch/arm64/boot/dts/apple/s8001-common.dtsi
+++ b/arch/arm64/boot/dts/apple/s8001-common.dtsi
@@ -24,6 +24,7 @@
 		framebuffer0: framebuffer@0 {
 			compatible = "apple,simple-framebuffer", "simple-framebuffer";
 			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0 &ps_dp0>;
 			/* Format properties will be added by loader */
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/apple/s8001-j98a-j99a.dtsi b/arch/arm64/boot/dts/apple/s8001-j98a-j99a.dtsi
new file mode 100644
index 000000000000..e66a4c1c138f
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s8001-j98a-j99a.dtsi
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple iPad Pro (12.9-inch)
+ *
+ * This file contains parts common to iPad Pro (12.9-inch).
+ *
+ * target-type: J98a, J99a
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+&ps_dcs4 {
+	apple,always-on; /* LPDDR4 interface */
+};
+
+&ps_dcs5 {
+	apple,always-on; /* LPDDR4 interface */
+};
+
+&ps_dcs6 {
+	apple,always-on; /* LPDDR4 interface */
+};
+
+&ps_dcs7 {
+	apple,always-on; /* LPDDR4 interface */
+};
diff --git a/arch/arm64/boot/dts/apple/s8001-j98a.dts b/arch/arm64/boot/dts/apple/s8001-j98a.dts
index 6d6b841e7ab0..162eca05c2d9 100644
--- a/arch/arm64/boot/dts/apple/s8001-j98a.dts
+++ b/arch/arm64/boot/dts/apple/s8001-j98a.dts
@@ -7,6 +7,7 @@
 /dts-v1/;
 
 #include "s8001-pro.dtsi"
+#include "s8001-j98a-j99a.dtsi"
 
 / {
 	compatible = "apple,j98a", "apple,s8001", "apple,arm-platform";
diff --git a/arch/arm64/boot/dts/apple/s8001-j99a.dts b/arch/arm64/boot/dts/apple/s8001-j99a.dts
index d20194b1cae7..7b765820c69e 100644
--- a/arch/arm64/boot/dts/apple/s8001-j99a.dts
+++ b/arch/arm64/boot/dts/apple/s8001-j99a.dts
@@ -7,6 +7,7 @@
 /dts-v1/;
 
 #include "s8001-pro.dtsi"
+#include "s8001-j98a-j99a.dtsi"
 
 / {
 	compatible = "apple,j99a", "apple,s8001", "apple,arm-platform";
diff --git a/arch/arm64/boot/dts/apple/s8001-pmgr.dtsi b/arch/arm64/boot/dts/apple/s8001-pmgr.dtsi
new file mode 100644
index 000000000000..859ab77ae92b
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/s8001-pmgr.dtsi
@@ -0,0 +1,822 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple S8001 "A9X" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80148 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80150 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dwi: power-controller@80110 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@80118 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pcie_ref: power-controller@80140 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_mca0: power-controller@80160 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80168 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80170 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80178 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80180 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@80188 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@80190 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@80198 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801a0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801a8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801b0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801b8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801c0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801c8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@801d0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@801d8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@801e0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@801e8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@801f0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@801f8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80158 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsic0_phy: power-controller@80128 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_isp_sens0: power-controller@80130 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens0";
+	};
+
+	ps_isp_sens1: power-controller@80138 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens1";
+	};
+
+	ps_pms: power-controller@80120 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb: power-controller@80278 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@80280 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@80288 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@80298 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host2: power-controller@802a8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host2";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_rtmux: power-controller@802d0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "rtmux";
+		apple,always-on; /* Core device */
+	};
+
+	ps_disp1mux: power-controller@802e8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1mux";
+	};
+
+	ps_disp0: power-controller@802d8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_disp1: power-controller@802f0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1";
+		power-domains = <&ps_disp1mux>;
+	};
+
+	ps_uart6: power-controller@80200 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@80208 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@80210 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_aes0: power-controller@80218 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aes0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80230 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80238 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs1: power-controller@80240 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs2: power-controller@80248 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs3: power-controller@80250 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs4: power-controller@80258 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs4";
+	};
+
+	ps_dcs5: power-controller@80260 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs5";
+	};
+
+	ps_dcs6: power-controller@80268 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs6";
+	};
+
+	ps_dcs7: power-controller@80270 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs7";
+	};
+
+	ps_usb2host0_ohci: power-controller@80290 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usbotg: power-controller@802b8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@802c0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802c8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_dp0: power-controller@802e0 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp0";
+		power-domains = <&ps_disp0>;
+	};
+
+	ps_dp1: power-controller@802f8 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp1";
+		power-domains = <&ps_disp1>;
+	};
+
+	ps_dpa0: power-controller@80220 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dpa0";
+	};
+
+	ps_dpa1: power-controller@80228 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80228 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dpa1";
+	};
+
+	ps_media: power-controller@80308 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp: power-controller@80300 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_msr: power-controller@80318 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@80310 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_venc: power-controller@80340 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80340 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie: power-controller@80348 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80348 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_srs: power-controller@80390 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80390 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "srs";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie_aux: power-controller@80350 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80350 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_pcie_link0: power-controller@80358 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80358 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link0";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link1: power-controller@80360 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80360 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link1";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link2: power-controller@80368 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80368 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link2";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link3: power-controller@80370 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80370 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link3";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link4: power-controller@80378 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80378 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link4";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_pcie_link5: power-controller@80380 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80380 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_link5";
+		power-domains = <&ps_pcie>;
+	};
+
+	ps_vdec: power-controller@80330 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80330 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec";
+		power-domains = <&ps_media>;
+	};
+
+	ps_gfx: power-controller@80388 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80388 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_pmp: power-controller@80320 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pms_sram: power-controller@80328 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on*/
+	};
+
+	ps_venc_pipe: power-controller@88000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me0: power-controller@88008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88010 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_aop: power-controller@80000 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop";
+		power-domains = <&ps_aop_cpu &ps_aop_filter &ps_aop_busif>;
+		apple,always-on; /* Always on processor */
+	};
+
+	ps_debug: power-controller@80008 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_aop_gpio: power-controller@80010 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_gpio";
+	};
+
+	ps_aop_cpu: power-controller@80040 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_cpu";
+	};
+
+	ps_aop_filter: power-controller@80048 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80048 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_filter";
+	};
+
+	ps_aop_busif: power-controller@80050 {
+		compatible = "apple,s8000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_busif";
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/s8001.dtsi b/arch/arm64/boot/dts/apple/s8001.dtsi
index 23ee3238844d..d56d49c048bb 100644
--- a/arch/arm64/boot/dts/apple/s8001.dtsi
+++ b/arch/arm64/boot/dts/apple/s8001.dtsi
@@ -32,6 +32,8 @@
 			compatible = "apple,twister";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			operating-points-v2 = <&twister_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -40,11 +42,62 @@
 			compatible = "apple,twister";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			operating-points-v2 = <&twister_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	twister_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <800>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <53000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <792000000>;
+			opp-level = <3>;
+			clock-latency-ns = <18000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <1080000000>;
+			opp-level = <4>;
+			clock-latency-ns = <21000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1440000000>;
+			opp-level = <5>;
+			clock-latency-ns = <25000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1800000000>;
+			opp-level = <6>;
+			clock-latency-ns = <33000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <2160000000>;
+			opp-level = <7>;
+			clock-latency-ns = <45000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp08 {
+			opp-hz = /bits/ 64 <2160000000>;
+			opp-level = <8>;
+			clock-latency-ns = <45000>;
+			turbo-mode;
+		};
+#endif
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -52,6 +105,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202220000 {
+			compatible = "apple,s8000-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x02220000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0c0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0c0000 0x0 0x4000>;
@@ -61,19 +120,30 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,s8000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x8c000>;
+		};
+
 		aic: interrupt-controller@20e100000 {
 			compatible = "apple,s8000-aic", "apple,aic";
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
 		};
 
 		pinctrl_ap: pinctrl@20f100000 {
 			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0f100000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -95,6 +165,7 @@
 		pinctrl_aop: pinctrl@2100f0000 {
 			compatible = "apple,s8000-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x100f0000 0x0 0x100000>;
+			power-domains = <&ps_aop_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -113,6 +184,14 @@
 				     <AIC_IRQ 134 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		pmgr_mini: power-management@210200000 {
+			compatible = "apple,s8000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x10200000 0 0x84000>;
+		};
+
 		wdt: watchdog@2102b0000 {
 			compatible = "apple,s8000-wdt", "apple,wdt";
 			reg = <0x2 0x102b0000 0x0 0x4000>;
@@ -131,3 +210,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "s8001-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/s8003.dtsi b/arch/arm64/boot/dts/apple/s8003.dtsi
index 7e4ad4f7e499..79df5c783260 100644
--- a/arch/arm64/boot/dts/apple/s8003.dtsi
+++ b/arch/arm64/boot/dts/apple/s8003.dtsi
@@ -4,18 +4,65 @@
  *
  * Other names: H8P, "Malta"
  *
- * Copyright (c) 2022, Konrad Dybcio <konradybcio@kernel.org>
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
  */
 
-#include "s8000.dtsi"
+#include "s800-0-3.dtsi"
+
+/ {
+	twister_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <500>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <45000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <3>;
+			clock-latency-ns = <22000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <912000000>;
+			opp-level = <4>;
+			clock-latency-ns = <25000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-level = <5>;
+			clock-latency-ns = <28000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1512000000>;
+			opp-level = <6>;
+			clock-latency-ns = <35000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <1800000000>;
+			opp-level = <7>;
+			clock-latency-ns = <38000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp08 {
+			opp-hz = /bits/ 64 <1844000000>;
+			opp-level = <8>;
+			clock-latency-ns = <38000>;
+			turbo-mode;
+		};
+#endif
+	};
+};
 
 /*
  * The A9 was made by two separate fabs on two different process
  * nodes: Samsung made the S8000 (APL0898) on 14nm and TSMC made
- * the S8003 (APL1022) on 16nm. While they are seemingly the same,
- * they do have distinct part numbers and devices using them have
- * distinct model names. There are currently no known differences
- * between these as far as Linux is concerned, but let's keep things
- * structured properly to make it easier to alter the behaviour of
- * one of the chips if need be.
+ * the S8003 (APL1022) on 16nm. There are some minor differences
+ * such as timing in cpufreq state transistions.
  */
diff --git a/arch/arm64/boot/dts/apple/s800x-6s.dtsi b/arch/arm64/boot/dts/apple/s800x-6s.dtsi
index 49b04db310c6..1dcf80cc2920 100644
--- a/arch/arm64/boot/dts/apple/s800x-6s.dtsi
+++ b/arch/arm64/boot/dts/apple/s800x-6s.dtsi
@@ -47,3 +47,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_mipi_dsi>;
+};
diff --git a/arch/arm64/boot/dts/apple/s800x-ipad5.dtsi b/arch/arm64/boot/dts/apple/s800x-ipad5.dtsi
index 32570ed3cdf0..c1701e81f0c1 100644
--- a/arch/arm64/boot/dts/apple/s800x-ipad5.dtsi
+++ b/arch/arm64/boot/dts/apple/s800x-ipad5.dtsi
@@ -41,3 +41,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_dp>;
+};
diff --git a/arch/arm64/boot/dts/apple/s800x-se.dtsi b/arch/arm64/boot/dts/apple/s800x-se.dtsi
index a1a5690e8371..deb7c7cc90f6 100644
--- a/arch/arm64/boot/dts/apple/s800x-se.dtsi
+++ b/arch/arm64/boot/dts/apple/s800x-se.dtsi
@@ -47,3 +47,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_mipi_dsi>;
+};
diff --git a/arch/arm64/boot/dts/apple/spi1-nvram.dtsi b/arch/arm64/boot/dts/apple/spi1-nvram.dtsi
new file mode 100644
index 000000000000..3df2fd3993b5
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/spi1-nvram.dtsi
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+//
+// Devicetree include for common spi-nor nvram flash.
+//
+// Apple uses a consistent configiguration for the nvram on all known M1* and
+// M2* devices.
+//
+// Copyright The Asahi Linux Contributors
+
+/ {
+	aliases {
+		nvram = &nvram;
+	};
+};
+
+&spi1 {
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-max-frequency = <25000000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			nvram: partition@700000 {
+				label = "nvram";
+				/* To be filled by the loader */
+				reg = <0x0 0x0>;
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t600x-common.dtsi b/arch/arm64/boot/dts/apple/t600x-common.dtsi
index fa8ead699363..87dfc13d7417 100644
--- a/arch/arm64/boot/dts/apple/t600x-common.dtsi
+++ b/arch/arm64/boot/dts/apple/t600x-common.dtsi
@@ -362,6 +362,13 @@
 		clock-output-names = "clkref";
 	};
 
+	clk_200m: clock-200m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+		clock-output-names = "clk_200m";
+	};
+
 	/*
 	 * This is a fabulated representation of the input clock
 	 * to NCO since we don't know the true clock tree.
diff --git a/arch/arm64/boot/dts/apple/t600x-die0.dtsi b/arch/arm64/boot/dts/apple/t600x-die0.dtsi
index b1c875e692c8..e9b3140ba1a9 100644
--- a/arch/arm64/boot/dts/apple/t600x-die0.dtsi
+++ b/arch/arm64/boot/dts/apple/t600x-die0.dtsi
@@ -163,6 +163,34 @@
 		status = "disabled";
 	};
 
+	spi1: spi@39b104000 {
+		compatible = "apple,t6000-spi", "apple,spi";
+		reg = <0x3 0x9b104000 0x0 0x4000>;
+		interrupt-parent = <&aic>;
+		interrupts = <AIC_IRQ 0 1107 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clocks = <&clk_200m>;
+		pinctrl-0 = <&spi1_pins>;
+		pinctrl-names = "default";
+		power-domains = <&ps_spi1>;
+		status = "disabled";
+	};
+
+	spi3: spi@39b10c000 {
+		compatible = "apple,t6000-spi", "apple,spi";
+		reg = <0x3 0x9b10c000 0x0 0x4000>;
+		interrupt-parent = <&aic>;
+		interrupts = <AIC_IRQ 0 1109 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clocks = <&clkref>;
+		pinctrl-0 = <&spi3_pins>;
+		pinctrl-names = "default";
+		power-domains = <&ps_spi3>;
+		status = "disabled";
+	};
+
 	serial0: serial@39b200000 {
 		compatible = "apple,s5l-uart";
 		reg = <0x3 0x9b200000 0x0 0x1000>;
diff --git a/arch/arm64/boot/dts/apple/t600x-gpio-pins.dtsi b/arch/arm64/boot/dts/apple/t600x-gpio-pins.dtsi
index b31f1a7a2b3f..1a994c3c1b79 100644
--- a/arch/arm64/boot/dts/apple/t600x-gpio-pins.dtsi
+++ b/arch/arm64/boot/dts/apple/t600x-gpio-pins.dtsi
@@ -36,6 +36,20 @@
 			<APPLE_PINMUX(101, 1)>;
 	};
 
+	spi1_pins: spi1-pins {
+		pinmux = <APPLE_PINMUX(10, 1)>,
+			<APPLE_PINMUX(11, 1)>,
+			<APPLE_PINMUX(32, 1)>,
+			<APPLE_PINMUX(33, 1)>;
+	};
+
+	spi3_pins: spi3-pins {
+		pinmux = <APPLE_PINMUX(52, 1)>,
+			<APPLE_PINMUX(53, 1)>,
+			<APPLE_PINMUX(54, 1)>,
+			<APPLE_PINMUX(55, 1)>;
+	};
+
 	pcie_pins: pcie-pins {
 		pinmux = <APPLE_PINMUX(0, 1)>,
 				<APPLE_PINMUX(1, 1)>,
diff --git a/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi b/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi
index 2e471dfe43cf..22ebc78e120b 100644
--- a/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi
+++ b/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi
@@ -119,3 +119,5 @@
 &fpwm0 {
 	status = "okay";
 };
+
+#include "spi1-nvram.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t600x-j375.dtsi b/arch/arm64/boot/dts/apple/t600x-j375.dtsi
index 1e5a19e49b08..d5b985ad5679 100644
--- a/arch/arm64/boot/dts/apple/t600x-j375.dtsi
+++ b/arch/arm64/boot/dts/apple/t600x-j375.dtsi
@@ -126,3 +126,5 @@
 &pcie0_dart_3 {
 	status = "okay";
 };
+
+#include "spi1-nvram.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t7000-6.dtsi b/arch/arm64/boot/dts/apple/t7000-6.dtsi
index f60ea4a4a387..7048d7383982 100644
--- a/arch/arm64/boot/dts/apple/t7000-6.dtsi
+++ b/arch/arm64/boot/dts/apple/t7000-6.dtsi
@@ -48,3 +48,11 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_mipi_dsi>;
+};
+
+&typhoon_opp06 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t7000-handheld.dtsi b/arch/arm64/boot/dts/apple/t7000-handheld.dtsi
index 8984c9ec6cc8..7b58aa648b53 100644
--- a/arch/arm64/boot/dts/apple/t7000-handheld.dtsi
+++ b/arch/arm64/boot/dts/apple/t7000-handheld.dtsi
@@ -22,6 +22,10 @@
 	};
 };
 
+&dwi_bl {
+	status = "okay";
+};
+
 &serial0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/apple/t7000-j42d.dts b/arch/arm64/boot/dts/apple/t7000-j42d.dts
index 2231db6a739d..2ec9e06cc63f 100644
--- a/arch/arm64/boot/dts/apple/t7000-j42d.dts
+++ b/arch/arm64/boot/dts/apple/t7000-j42d.dts
@@ -20,6 +20,7 @@
 		framebuffer0: framebuffer@0 {
 			compatible = "apple,simple-framebuffer", "simple-framebuffer";
 			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0 &ps_dp>;
 			/* Format properties will be added by loader */
 			status = "disabled";
 		};
@@ -29,3 +30,7 @@
 &serial6 {
 	status = "okay";
 };
+
+&typhoon_opp06 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t7000-mini4.dtsi b/arch/arm64/boot/dts/apple/t7000-mini4.dtsi
index c64ddc402fda..cc235c5a0c43 100644
--- a/arch/arm64/boot/dts/apple/t7000-mini4.dtsi
+++ b/arch/arm64/boot/dts/apple/t7000-mini4.dtsi
@@ -49,3 +49,15 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_dp>;
+};
+
+&typhoon_opp06 {
+	status = "okay";
+};
+
+&typhoon_opp07 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t7000-n102.dts b/arch/arm64/boot/dts/apple/t7000-n102.dts
index 9c55d339ba4e..99eb8a2b8c73 100644
--- a/arch/arm64/boot/dts/apple/t7000-n102.dts
+++ b/arch/arm64/boot/dts/apple/t7000-n102.dts
@@ -46,3 +46,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0 &ps_mipi_dsi>;
+};
diff --git a/arch/arm64/boot/dts/apple/t7000-pmgr.dtsi b/arch/arm64/boot/dts/apple/t7000-pmgr.dtsi
new file mode 100644
index 000000000000..5948fa7afffc
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t7000-pmgr.dtsi
@@ -0,0 +1,641 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T7000 "A8" SoC
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+&pmgr {
+	ps_cpu0: power-controller@20000 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@20008 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@20040 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_p: power-controller@201f8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+	};
+
+	ps_lio: power-controller@20100 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "lio";
+		apple,always-on; /* Core device */
+	};
+
+	ps_iomux: power-controller@20108 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "iomux";
+		apple,always-on; /* Core device */
+	};
+
+	ps_aic: power-controller@20110 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_debug: power-controller@20118 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_dwi: power-controller@20120 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@20128 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_mca0: power-controller@20130 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@20138 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@20140 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@20148 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@20150 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@20158 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@20160 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@20168 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@20170 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@20178 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@20180 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@20188 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@20190 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@20198 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@201a0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@201a8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@201b0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@201b8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@201c0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@201c8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@201d0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@201d8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@201e0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_aes0: power-controller@201e8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aes0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@201f0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb: power-controller@20248 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@20250 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@20258 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@20268 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host2: power-controller@20278 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host2";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_disp_busmux: power-controller@202a8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp_busmux";
+	};
+
+	ps_media: power-controller@202d8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp: power-controller@202d0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp";
+	};
+
+	ps_msr: power-controller@202e0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@202e8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0: power-controller@202b0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_disp1: power-controller@202c8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_pcie_ref: power-controller@20220 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_hsic0_phy: power-controller@20200 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_hsic1_phy: power-controller@20208 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic1_phy";
+		power-domains = <&ps_usb2host2>;
+	};
+
+	ps_ispsens0: power-controller@20210 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens0";
+	};
+
+	ps_ispsens1: power-controller@20218 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens1";
+	};
+
+	ps_mcc: power-controller@20230 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_mcu: power-controller@20238 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcu";
+		apple,always-on; /* Core device */
+	};
+
+	ps_amp: power-controller@20240 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "amp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb2host0_ohci: power-controller@20260 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usbotg: power-controller@20288 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@20290 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple Fabric, critical block */
+	};
+
+	ps_sf: power-controller@20298 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple Fabric, critical block */
+	};
+
+	ps_cp: power-controller@202a0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_mipi_dsi: power-controller@202b8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_dp: power-controller@202c0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0>;
+	};
+
+	ps_vdec: power-controller@202f0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec";
+		power-domains = <&ps_media>;
+	};
+
+	ps_ans: power-controller@20318 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans";
+	};
+
+	ps_venc: power-controller@20300 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie: power-controller@20308 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@20310 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_gfx: power-controller@20320 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@20400 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_venc_pipe: power-controller@21000 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me0: power-controller@21008 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me1: power-controller@21010 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+		power-domains = <&ps_venc>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t7000.dtsi b/arch/arm64/boot/dts/apple/t7000.dtsi
index a7cc29e84c84..85a34dc7bc01 100644
--- a/arch/arm64/boot/dts/apple/t7000.dtsi
+++ b/arch/arm64/boot/dts/apple/t7000.dtsi
@@ -33,6 +33,8 @@
 			compatible = "apple,typhoon";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			performance-domains = <&cpufreq>;
+			operating-points-v2 = <&typhoon_opp>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -41,11 +43,55 @@
 			compatible = "apple,typhoon";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			performance-domains = <&cpufreq>;
+			operating-points-v2 = <&typhoon_opp>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	typhoon_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <300>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <50000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <3>;
+			clock-latency-ns = <29000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <840000000>;
+			opp-level = <4>;
+			clock-latency-ns = <29000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1128000000>;
+			opp-level = <5>;
+			clock-latency-ns = <36000>;
+		};
+		typhoon_opp06: opp06 {
+			opp-hz = /bits/ 64 <1392000000>;
+			opp-level = <6>;
+			clock-latency-ns = <42000>;
+			status = "disabled"; /* Not available on N102 */
+		};
+		typhoon_opp07: opp07 {
+			opp-hz = /bits/ 64 <1512000000>;
+			opp-level = <7>;
+			clock-latency-ns = <49000>;
+			status = "disabled"; /* J96 and J97 only */
+		};
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -53,6 +99,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202220000 {
+			compatible = "apple,t7000-cluster-cpufreq", "apple,s5l8960x-cluster-cpufreq";
+			reg = <0x2 0x02220000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0c0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0c0000 0x0 0x4000>;
@@ -62,6 +114,7 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
@@ -74,9 +127,18 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart6>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,t7000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x24000>;
+		};
+
 		wdt: watchdog@20e027000 {
 			compatible = "apple,t7000-wdt", "apple,wdt";
 			reg = <0x2 0x0e027000 0x0 0x1000>;
@@ -90,11 +152,20 @@
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		dwi_bl: backlight@20e200010 {
+			compatible = "apple,t7000-dwi-bl", "apple,dwi-bl";
+			reg = <0x2 0x0e200010 0x0 0x8>;
+			power-domains = <&ps_dwi>;
+			status = "disabled";
 		};
 
 		pinctrl: pinctrl@20e300000 {
 			compatible = "apple,t7000-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0e300000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -123,3 +194,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "t7000-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t7001-air2.dtsi b/arch/arm64/boot/dts/apple/t7001-air2.dtsi
index 19fabd425c52..e4ec8c1977de 100644
--- a/arch/arm64/boot/dts/apple/t7001-air2.dtsi
+++ b/arch/arm64/boot/dts/apple/t7001-air2.dtsi
@@ -20,6 +20,7 @@
 		framebuffer0: framebuffer@0 {
 			compatible = "apple,simple-framebuffer", "simple-framebuffer";
 			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0 &ps_dp>;
 			/* Format properties will be added by loader */
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/apple/t7001-pmgr.dtsi b/arch/arm64/boot/dts/apple/t7001-pmgr.dtsi
new file mode 100644
index 000000000000..7321cfdcd189
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t7001-pmgr.dtsi
@@ -0,0 +1,650 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T7001 "A8X" SoC
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@20000 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@20008 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu2: power-controller@20010 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu2";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@20040 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_p: power-controller@201f8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+	};
+
+	ps_lio: power-controller@20100 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "lio";
+		apple,always-on; /* Core device */
+	};
+
+	ps_iomux: power-controller@20108 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "iomux";
+		apple,always-on; /* Core device */
+	};
+
+	ps_aic: power-controller@20110 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_debug: power-controller@20118 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_dwi: power-controller@20120 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@20128 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_mca0: power-controller@20130 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@20138 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@20140 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@20148 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@20150 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@20158 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@20160 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@20168 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@20170 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@20178 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@20180 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@20188 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@20190 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@20198 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@201a0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@201a8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@201b0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@201b8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@201c0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@201c8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@201d0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@201d8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@201e0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_aes0: power-controller@201e8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aes0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@201f0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x201f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb: power-controller@20248 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@20250 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@20258 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@20268 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host2: power-controller@20278 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host2";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_disp_busmux: power-controller@202a8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp_busmux";
+	};
+
+	ps_disp1_busmux: power-controller@202c0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1_busmux";
+	};
+
+	ps_media: power-controller@202d8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp: power-controller@202d0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp";
+	};
+
+	ps_msr: power-controller@202e0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@202e8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0: power-controller@202b0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0";
+		power-domains = <&ps_disp_busmux>;
+	};
+
+	ps_disp1: power-controller@202c8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp1";
+		power-domains = <&ps_disp1_busmux>;
+	};
+
+	ps_pcie_ref: power-controller@20220 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_hsic0_phy: power-controller@20200 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_hsic1_phy: power-controller@20208 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic1_phy";
+		power-domains = <&ps_usb2host2>;
+	};
+
+	ps_ispsens0: power-controller@20210 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens0";
+	};
+
+	ps_ispsens1: power-controller@20218 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens1";
+	};
+
+	ps_mcc: power-controller@20230 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_mcu: power-controller@20238 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcu";
+		apple,always-on; /* Core device */
+	};
+
+	ps_amp: power-controller@20240 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "amp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_usb2host0_ohci: power-controller@20260 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usbotg: power-controller@20288 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@20290 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@20298 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_cp: power-controller@202a0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cp";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dp: power-controller@202b8 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0>;
+	};
+
+	ps_vdec: power-controller@202f0 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x202f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec";
+		power-domains = <&ps_media>;
+	};
+
+	ps_ans: power-controller@20318 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans";
+	};
+
+	ps_venc: power-controller@20300 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie: power-controller@20308 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@20310 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_gfx: power-controller@20320 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@20400 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x20400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_venc_pipe: power-controller@21000 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me0: power-controller@21008 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+		power-domains = <&ps_venc>;
+	};
+
+	ps_venc_me1: power-controller@21010 {
+		compatible = "apple,t7000-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x21010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+		power-domains = <&ps_venc>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t7001.dtsi b/arch/arm64/boot/dts/apple/t7001.dtsi
index a76e034c85e3..8e2c67e19c41 100644
--- a/arch/arm64/boot/dts/apple/t7001.dtsi
+++ b/arch/arm64/boot/dts/apple/t7001.dtsi
@@ -35,6 +35,8 @@
 			compatible = "apple,typhoon";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			performance-domains = <&cpufreq>;
+			operating-points-v2 = <&typhoon_opp>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -43,6 +45,8 @@
 			compatible = "apple,typhoon";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled in by loader */
+			performance-domains = <&cpufreq>;
+			operating-points-v2 = <&typhoon_opp>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -51,11 +55,53 @@
 			compatible = "apple,typhoon";
 			reg = <0x0 0x2>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq>;
+			operating-points-v2 = <&typhoon_opp>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	typhoon_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <300>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <396000000>;
+			opp-level = <2>;
+			clock-latency-ns = <49000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-level = <3>;
+			clock-latency-ns = <31000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <840000000>;
+			opp-level = <4>;
+			clock-latency-ns = <32000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1128000000>;
+			opp-level = <5>;
+			clock-latency-ns = <32000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1392000000>;
+			opp-level = <6>;
+			clock-latency-ns = <37000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <1512000000>;
+			opp-level = <7>;
+			clock-latency-ns = <41000>;
+		};
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -63,6 +109,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202220000 {
+			compatible = "apple,t7000-cluster-cpufreq", "apple,s5l8960x-cluster-cpufreq";
+			reg = <0x2 0x02220000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0c0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0c0000 0x0 0x4000>;
@@ -72,9 +124,18 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,t7000-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x24000>;
+		};
+
 		wdt: watchdog@20e027000 {
 			compatible = "apple,t7000-wdt", "apple,wdt";
 			reg = <0x2 0x0e027000 0x0 0x1000>;
@@ -88,11 +149,13 @@
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
 		};
 
 		pinctrl: pinctrl@20e300000 {
 			compatible = "apple,t7000-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0e300000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -121,3 +184,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "t7001-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8010-7.dtsi b/arch/arm64/boot/dts/apple/t8010-7.dtsi
index 1332fd73f50f..1913b7b2c1fe 100644
--- a/arch/arm64/boot/dts/apple/t8010-7.dtsi
+++ b/arch/arm64/boot/dts/apple/t8010-7.dtsi
@@ -41,3 +41,15 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0_fe &ps_disp0_be &ps_mipi_dsi>;
+};
+
+&hurricane_opp09 {
+	status = "okay";
+};
+
+&hurricane_opp10 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t8010-common.dtsi b/arch/arm64/boot/dts/apple/t8010-common.dtsi
index 6613fb57c92f..44dc968638b1 100644
--- a/arch/arm64/boot/dts/apple/t8010-common.dtsi
+++ b/arch/arm64/boot/dts/apple/t8010-common.dtsi
@@ -43,6 +43,10 @@
 	};
 };
 
+&dwi_bl {
+	status = "okay";
+};
+
 &serial0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/apple/t8010-ipad6.dtsi b/arch/arm64/boot/dts/apple/t8010-ipad6.dtsi
index 81696c6e302c..1e46e4a3a7f4 100644
--- a/arch/arm64/boot/dts/apple/t8010-ipad6.dtsi
+++ b/arch/arm64/boot/dts/apple/t8010-ipad6.dtsi
@@ -42,3 +42,15 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0_fe &ps_disp0_be &ps_dp>;
+};
+
+&hurricane_opp09 {
+	status = "okay";
+};
+
+&hurricane_opp10 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t8010-n112.dts b/arch/arm64/boot/dts/apple/t8010-n112.dts
index 6e71c3cb5d92..48fdbedf74da 100644
--- a/arch/arm64/boot/dts/apple/t8010-n112.dts
+++ b/arch/arm64/boot/dts/apple/t8010-n112.dts
@@ -45,3 +45,7 @@
 		};
 	};
 };
+
+&framebuffer0 {
+	power-domains = <&ps_disp0_fe &ps_disp0_be &ps_mipi_dsi>;
+};
diff --git a/arch/arm64/boot/dts/apple/t8010-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8010-pmgr.dtsi
new file mode 100644
index 000000000000..6d451088616a
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8010-pmgr.dtsi
@@ -0,0 +1,772 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T8010 "A10" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80160 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80168 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dwi: power-controller@80110 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@80118 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pms: power-controller@80120 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_pcie_ref: power-controller@80148 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_socuvd: power-controller@80150 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "socuvd";
+	};
+
+	ps_mca0: power-controller@80178 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80180 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80188 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80190 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80198 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@801a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@801a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@801b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801c0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@801e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@801f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@801f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80170 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsic0_phy: power-controller@80128 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_isp_sens0: power-controller@80130 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens0";
+	};
+
+	ps_isp_sens1: power-controller@80138 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens1";
+	};
+
+	ps_isp_sens2: power-controller@80140 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens2";
+	};
+
+	ps_usb: power-controller@80268 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@80270 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@80278 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@80288 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_rtmux: power-controller@802a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "rtmux";
+	};
+
+	ps_media: power-controller@802d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp_sys: power-controller@802d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sys";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_msr: power-controller@802e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@802e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0_fe: power-controller@802b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_fe";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_disp0_be: power-controller@802b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_be";
+		power-domains = <&ps_disp0_fe>;
+	};
+
+	ps_pmp: power-controller@802f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pms_sram: power-controller@802f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_uart3: power-controller@80200 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@80208 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@80210 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@80218 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@80220 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@80228 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80228 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_hfd0: power-controller@80238 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hfd0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80240 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80248 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs1: power-controller@80250 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs2: power-controller@80258 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs3: power-controller@80260 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_usb2host0_ohci: power-controller@80280 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usbotg: power-controller@80290 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@80298 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_mipi_dsi: power-controller@802c0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_dp: power-controller@802c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_venc_sys: power-controller@80310 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_sys";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pcie: power-controller@80318 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@80320 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_vdec0: power-controller@80300 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec0";
+		power-domains = <&ps_media>;
+	};
+
+	ps_gfx: power-controller@80328 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_isp_rsts0: power-controller@84000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts0";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_rsts1: power-controller@84008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts1";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_vis: power-controller@84010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_vis";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_be: power-controller@84018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_be";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_pearl: power-controller@84020 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_pearl";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_dprx: power-controller@84028 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dprx";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_venc_pipe4: power-controller@88000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe4";
+		power-domains = <&ps_venc_sys>;
+	};
+
+	ps_venc_pipe5: power-controller@88008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe5";
+		power-domains = <&ps_venc_sys>;
+	};
+
+	ps_venc_me0: power-controller@88010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_aop: power-controller@80000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop";
+		power-domains = <&ps_aop_cpu &ps_aop_busif &ps_aop_filter>;
+		apple,always-on; /* Always on processor */
+	};
+
+	ps_debug: power-controller@80008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_aop_gpio: power-controller@80010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_gpio";
+	};
+
+	ps_aop_cpu: power-controller@80048 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80048 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_cpu";
+	};
+
+	ps_aop_filter: power-controller@80050 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_filter";
+	};
+
+	ps_aop_busif: power-controller@80058 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80058 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_busif";
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8010.dtsi b/arch/arm64/boot/dts/apple/t8010.dtsi
index e3d6a8354103..17e294bd7c44 100644
--- a/arch/arm64/boot/dts/apple/t8010.dtsi
+++ b/arch/arm64/boot/dts/apple/t8010.dtsi
@@ -32,6 +32,8 @@
 			compatible = "apple,hurricane-zephyr";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -40,11 +42,89 @@
 			compatible = "apple,hurricane-zephyr";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	fusion_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		/*
+		 * Apple Fusion Architecture: Hardware big.LITTLE switcher
+		 * that use p-state transitions to switch between cores.
+		 * Only one type of core can be active at a given time.
+		 *
+		 * The E-core frequencies are adjusted so performance scales
+		 * linearly with reported clock speed.
+		 */
+
+		opp01 {
+			opp-hz = /bits/ 64 <172000000>; /* 300 MHz, E-core */
+			opp-level = <1>;
+			clock-latency-ns = <11000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <230000000>; /* 396 MHz, E-core */
+			opp-level = <2>;
+			clock-latency-ns = <49000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <425000000>; /* 732 MHz, E-core */
+			opp-level = <3>;
+			clock-latency-ns = <13000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <637000000>; /* 1092 MHz, E-core */
+			opp-level = <4>;
+			clock-latency-ns = <18000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <756000000>;
+			opp-level = <5>;
+			clock-latency-ns = <35000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1056000000>;
+			opp-level = <6>;
+			clock-latency-ns = <31000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <1356000000>;
+			opp-level = <7>;
+			clock-latency-ns = <37000>;
+		};
+		opp08 {
+			opp-hz = /bits/ 64 <1644000000>;
+			opp-level = <8>;
+			clock-latency-ns = <39500>;
+		};
+		hurricane_opp09: opp09 {
+			opp-hz = /bits/ 64 <1944000000>;
+			opp-level = <9>;
+			clock-latency-ns = <46000>;
+			status = "disabled"; /* Not available on N112 */
+		};
+		hurricane_opp10: opp10 {
+			opp-hz = /bits/ 64 <2244000000>;
+			opp-level = <10>;
+			clock-latency-ns = <56000>;
+			status = "disabled"; /* Not available on N112 */
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		hurricane_opp11: opp11 {
+			opp-hz = /bits/ 64 <2340000000>;
+			opp-level = <11>;
+			clock-latency-ns = <56000>;
+			turbo-mode;
+			status = "disabled"; /* Not available on N112 */
+		};
+#endif
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -52,6 +132,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202f20000 {
+			compatible = "apple,t8010-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x02f20000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0c0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0c0000 0x0 0x4000>;
@@ -61,19 +147,37 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x8c000>;
+		};
+
 		aic: interrupt-controller@20e100000 {
 			compatible = "apple,t8010-aic", "apple,aic";
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		dwi_bl: backlight@20e200080 {
+			compatible = "apple,t8010-dwi-bl", "apple,dwi-bl";
+			reg = <0x2 0x0e200080 0x0 0x8>;
+			power-domains = <&ps_dwi>;
+			status = "disabled";
 		};
 
 		pinctrl_ap: pinctrl@20f100000 {
 			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0f100000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -95,6 +199,7 @@
 		pinctrl_aop: pinctrl@2100f0000 {
 			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x100f0000 0x0 0x100000>;
+			power-domains = <&ps_aop_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -113,6 +218,14 @@
 				     <AIC_IRQ 134 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		pmgr_mini: power-management@210200000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x10200000 0 0x84000>;
+		};
+
 		wdt: watchdog@2102b0000 {
 			compatible = "apple,t8010-wdt", "apple,wdt";
 			reg = <0x2 0x102b0000 0x0 0x4000>;
@@ -131,3 +244,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "t8010-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8011-common.dtsi b/arch/arm64/boot/dts/apple/t8011-common.dtsi
index 44a0d0ea2ee3..2010b56246f1 100644
--- a/arch/arm64/boot/dts/apple/t8011-common.dtsi
+++ b/arch/arm64/boot/dts/apple/t8011-common.dtsi
@@ -22,6 +22,7 @@
 		framebuffer0: framebuffer@0 {
 			compatible = "apple,simple-framebuffer", "simple-framebuffer";
 			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0_fe &ps_disp0_be &ps_dp>;
 			/* Format properties will be added by loader */
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/apple/t8011-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8011-pmgr.dtsi
new file mode 100644
index 000000000000..c44e3f9d7087
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8011-pmgr.dtsi
@@ -0,0 +1,806 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T8011 "A10X" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu2: power-controller@80010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu2";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80158 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80160 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dwi: power-controller@80110 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@80118 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pms: power-controller@80120 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_pcie_ref: power-controller@80148 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_mca0: power-controller@80170 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80178 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80180 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80188 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80190 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@80198 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@801a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@801a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801c0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@801e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@801e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@801f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@801f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80168 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsic0_phy: power-controller@80128 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsic0_phy";
+		power-domains = <&ps_usb3host>;
+	};
+
+	ps_isp_sens0: power-controller@80130 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens0";
+	};
+
+	ps_isp_sens1: power-controller@80138 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens1";
+	};
+
+	ps_isp_sens2: power-controller@80140 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens2";
+	};
+
+	ps_usb: power-controller@80288 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@80290 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host: power-controller@80298 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2dev: power-controller@802a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2dev";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb3host: power-controller@802a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb3host";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb3dev: power-controller@802b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb3dev";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_media: power-controller@802e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp_sys: power-controller@802e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sys";
+	};
+
+	ps_msr: power-controller@802f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@802f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0_fe: power-controller@802c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_fe";
+	};
+
+	ps_disp0_be: power-controller@802d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_be";
+		power-domains = <&ps_disp0_fe>;
+	};
+
+	ps_dpa: power-controller@80230 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dpa";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@80200 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@80208 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@80210 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@80218 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@80220 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_hfd0: power-controller@80238 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hfd0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80240 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80248 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs1: power-controller@80250 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs2: power-controller@80258 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs3: power-controller@80260 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs4: power-controller@80268 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs4";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs5: power-controller@80270 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs5";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs6: power-controller@80278 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs6";
+	};
+
+	ps_dcs7: power-controller@80280 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs7";
+	};
+
+	ps_smx: power-controller@802b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802c0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_dp: power-controller@802d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_venc_sys: power-controller@80320 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_sys";
+		power-domains = <&ps_media>;
+	};
+
+	ps_srs: power-controller@80390 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80390 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "srs";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pms_sram: power-controller@80308 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_pmp: power-controller@80300 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pcie: power-controller@80328 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@80330 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80330 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_vdec0: power-controller@80310 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec0";
+		power-domains = <&ps_media>;
+	};
+
+	ps_gfx: power-controller@80338 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80338 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_isp_rsts0: power-controller@84000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts0";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_rsts1: power-controller@84008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts1";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_vis: power-controller@84010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_vis";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_be: power-controller@84018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_be";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_pearl: power-controller@84020 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_pearl";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_dprx: power-controller@84028 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dprx";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_venc_pipe4: power-controller@88000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe4";
+		power-domains = <&ps_venc_sys>;
+	};
+
+	ps_venc_pipe5: power-controller@88008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe5";
+		power-domains = <&ps_venc_sys>;
+	};
+
+	ps_venc_me0: power-controller@88010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_aop: power-controller@80000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop";
+		power-domains = <&ps_aop_cpu &ps_aop_filter &ps_aop_busif>;
+		apple,always-on; /* Always on processor */
+	};
+
+	ps_debug: power-controller@80008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_aop_gpio: power-controller@80010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_gpio";
+	};
+
+	ps_aop_cpu: power-controller@80048 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80048 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_cpu";
+	};
+
+	ps_aop_filter: power-controller@80050 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_filter";
+	};
+
+	ps_aop_busif: power-controller@80058 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80058 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_busif";
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8011-pro2.dtsi b/arch/arm64/boot/dts/apple/t8011-pro2.dtsi
index f4e707415003..5eaa0a73350f 100644
--- a/arch/arm64/boot/dts/apple/t8011-pro2.dtsi
+++ b/arch/arm64/boot/dts/apple/t8011-pro2.dtsi
@@ -40,3 +40,11 @@
 		};
 	};
 };
+
+&ps_dcs6 {
+	apple,always-on; /* LPDDR4 interface */
+};
+
+&ps_dcs7 {
+	apple,always-on; /* LPDDR4 interface */
+};
diff --git a/arch/arm64/boot/dts/apple/t8011.dtsi b/arch/arm64/boot/dts/apple/t8011.dtsi
index 6c4ed9dc4a50..5b280c896b76 100644
--- a/arch/arm64/boot/dts/apple/t8011.dtsi
+++ b/arch/arm64/boot/dts/apple/t8011.dtsi
@@ -32,6 +32,8 @@
 			compatible = "apple,hurricane-zephyr";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -40,6 +42,8 @@
 			compatible = "apple,hurricane-zephyr";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -48,11 +52,80 @@
 			compatible = "apple,hurricane-zephyr";
 			reg = <0x0 0x2>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	fusion_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		/*
+		 * Apple Fusion Architecture: Hardwired big.LITTLE switcher
+		 * that use p-state transitions to switch between cores.
+		 *
+		 * The E-core frequencies are adjusted so performance scales
+		 * linearly with reported clock speed.
+		 */
+
+		opp01 {
+			opp-hz = /bits/ 64 <172000000>; /* 300 MHz, E-core */
+			opp-level = <1>;
+			clock-latency-ns = <12000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <230000000>; /* 396 MHz, E-core */
+			opp-level = <2>;
+			clock-latency-ns = <135000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <448000000>; /* 768 MHz, E-core */
+			opp-level = <3>;
+			clock-latency-ns = <105000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <662000000>; /* 1152 MHz, E-core */
+			opp-level = <4>;
+			clock-latency-ns = <115000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <804000000>;
+			opp-level = <5>;
+			clock-latency-ns = <122000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1140000000>;
+			opp-level = <6>;
+			clock-latency-ns = <120000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <1548000000>;
+			opp-level = <7>;
+			clock-latency-ns = <125000>;
+		};
+		opp08 {
+			opp-hz = /bits/ 64 <1956000000>;
+			opp-level = <8>;
+			clock-latency-ns = <135000>;
+		};
+		opp09 {
+			opp-hz = /bits/ 64 <2316000000>;
+			opp-level = <9>;
+			clock-latency-ns = <140000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp10 {
+			opp-hz = /bits/ 64 <2400000000>;
+			opp-level = <10>;
+			clock-latency-ns = <140000>;
+			turbo-mode;
+		};
+#endif
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -60,6 +133,12 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq: performance-controller@202f20000 {
+			compatible = "apple,t8010-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x02f20000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@20a0c0000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x0a0c0000 0x0 0x4000>;
@@ -69,19 +148,30 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
+		pmgr: power-management@20e000000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x8c000>;
+		};
+
 		aic: interrupt-controller@20e100000 {
 			compatible = "apple,t8010-aic", "apple,aic";
 			reg = <0x2 0x0e100000 0x0 0x100000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
 		};
 
 		pinctrl_ap: pinctrl@20f100000 {
 			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x0f100000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -103,6 +193,7 @@
 		pinctrl_aop: pinctrl@2100f0000 {
 			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x100f0000 0x0 0x100000>;
+			power-domains = <&ps_aop_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -121,6 +212,14 @@
 				     <AIC_IRQ 131 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		pmgr_mini: power-management@210200000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x10200000 0 0x84000>;
+		};
+
 		wdt: watchdog@2102b0000 {
 			compatible = "apple,t8010-wdt", "apple,wdt";
 			reg = <0x2 0x102b0000 0x0 0x4000>;
@@ -139,3 +238,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "t8011-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8012-j132.dts b/arch/arm64/boot/dts/apple/t8012-j132.dts
new file mode 100644
index 000000000000..778a69be18dd
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j132.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro15,2 (j132), J132, iBridge2,4
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro15,2 (j132)";
+	compatible = "apple,j132", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j137.dts b/arch/arm64/boot/dts/apple/t8012-j137.dts
new file mode 100644
index 000000000000..dbde1ad7ce14
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j137.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 iMacPro1,1 (j137), J137, iBridge2,1
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 iMacPro1,1 (j137)";
+	compatible = "apple,j137", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j140a.dts b/arch/arm64/boot/dts/apple/t8012-j140a.dts
new file mode 100644
index 000000000000..5df1ff74d2df
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j140a.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookAir8,2 (j140a), J140a, iBridge2,12
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 MacBookAir8,2 (j140a)";
+	compatible = "apple,j140a", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j140k.dts b/arch/arm64/boot/dts/apple/t8012-j140k.dts
new file mode 100644
index 000000000000..a0ef1585e5c2
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j140k.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookAir8,1 (j140k), J140k, iBridge2,8
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 MacBookAir8,1 (j140k)";
+	compatible = "apple,j140k", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j152f.dts b/arch/arm64/boot/dts/apple/t8012-j152f.dts
new file mode 100644
index 000000000000..261416eaf97e
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j152f.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro16,1 (j152f), J152f, iBridge2,14
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro16,1 (j152f)";
+	compatible = "apple,j152f", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j160.dts b/arch/arm64/boot/dts/apple/t8012-j160.dts
new file mode 100644
index 000000000000..fbcc0604f4a0
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j160.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacPro7,1 (j160), J160, iBridge2,6
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 MacPro7,1 (j160)";
+	compatible = "apple,j160", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j174.dts b/arch/arm64/boot/dts/apple/t8012-j174.dts
new file mode 100644
index 000000000000..d11c70f84a71
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j174.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 Macmini8,1 (j174), J174, iBridge2,5
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 Macmini8,1 (j174)";
+	compatible = "apple,j174", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j185.dts b/arch/arm64/boot/dts/apple/t8012-j185.dts
new file mode 100644
index 000000000000..33492f5db46d
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j185.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 iMac20,1 (j185), J185, iBridge2,19
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 iMac20,1 (j185)";
+	compatible = "apple,j185", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j185f.dts b/arch/arm64/boot/dts/apple/t8012-j185f.dts
new file mode 100644
index 000000000000..3a4abdd8f7d7
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j185f.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 iMac20,2 (j185f), J185f, iBridge2,20
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 iMac20,2 (j185f)";
+	compatible = "apple,j185f", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j213.dts b/arch/arm64/boot/dts/apple/t8012-j213.dts
new file mode 100644
index 000000000000..8270812b9a68
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j213.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro15,4 (j213), J213, iBridge2,10
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro15,4 (j213)";
+	compatible = "apple,j213", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j214k.dts b/arch/arm64/boot/dts/apple/t8012-j214k.dts
new file mode 100644
index 000000000000..5b8e42512060
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j214k.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro16,2 (j214k), J214k, iBridge2,16
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro16,2 (j214k)";
+	compatible = "apple,j214k", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j215.dts b/arch/arm64/boot/dts/apple/t8012-j215.dts
new file mode 100644
index 000000000000..ad574fbf7f92
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j215.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro16,4 (j215), J215, iBridge2,22
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro16,4 (j215)";
+	compatible = "apple,j215", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j223.dts b/arch/arm64/boot/dts/apple/t8012-j223.dts
new file mode 100644
index 000000000000..de75d775aac5
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j223.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro16,3 (j223), J223, iBridge2,21
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro16,3 (j223)";
+	compatible = "apple,j223", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j230k.dts b/arch/arm64/boot/dts/apple/t8012-j230k.dts
new file mode 100644
index 000000000000..4b19bc70ab0f
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j230k.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookAir9,1 (j230k), J230k, iBridge2,15
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+
+/ {
+	model = "Apple T2 MacBookAir9,1 (j230k)";
+	compatible = "apple,j230k", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j680.dts b/arch/arm64/boot/dts/apple/t8012-j680.dts
new file mode 100644
index 000000000000..aa5a72e07d3f
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j680.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro15,1 (j680), J680, iBridge2,3
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro15,1 (j680)";
+	compatible = "apple,j680", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-j780.dts b/arch/arm64/boot/dts/apple/t8012-j780.dts
new file mode 100644
index 000000000000..9cee891cb16d
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-j780.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T2 MacBookPro15,3 (j780), J780, iBridge2,7
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/dts-v1/;
+
+#include "t8012-jxxx.dtsi"
+#include "t8012-touchbar.dtsi"
+
+/ {
+	model = "Apple T2 MacBookPro15,3 (j780)";
+	compatible = "apple,j780", "apple,t8012", "apple,arm-platform";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8012-jxxx.dtsi
new file mode 100644
index 000000000000..36e82633bc52
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-jxxx.dtsi
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Common Device Tree for all T2 devices
+ *
+ * target-type: J132, J137, J140a, J140k, J152f, J160, J174, J185, J185f
+ * J213, J214k, J215, J223, J230k, J680, J780
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+#include "t8012.dtsi"
+
+/ {
+	chassis-type = "embedded";
+
+	aliases {
+		serial0 = &serial0;
+	};
+
+	chosen {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		stdout-path = "serial0";
+	};
+
+	memory@800000000 {
+		device_type = "memory";
+		reg = <0x8 0 0 0>; /* To be filled by loader */
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* To be filled by loader */
+	};
+};
+
+&serial0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8012-pmgr.dtsi
new file mode 100644
index 000000000000..35a462edd4af
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-pmgr.dtsi
@@ -0,0 +1,837 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T8012 "T2" SoC
+ *
+ * Copyright (c) 2024 Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80158 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80160 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_iomux: power-controller@80150 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80150 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "iomux";
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_gpio: power-controller@80110 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pcie_down_ref: power-controller@80138 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_down_ref";
+	};
+
+	ps_pcie_stg0_ref: power-controller@80140 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg0_ref";
+	};
+
+	ps_pcie_stg1_ref: power-controller@80148 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg1_ref";
+	};
+
+	ps_mca0: power-controller@80170 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80178 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80180 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80188 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80190 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca5: power-controller@80198 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@801a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@801b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801c0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@801a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80168 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_isp_sens0: power-controller@80120 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens0";
+	};
+
+	ps_isp_sens1: power-controller@80128 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens1";
+	};
+
+	ps_isp_sens2: power-controller@80130 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sens2";
+	};
+
+	ps_pms: power-controller@80118 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_i2c4: power-controller@801c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c5: power-controller@801d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c6: power-controller@801d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_usb: power-controller@80268 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctrl: power-controller@80270 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctrl";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@80278 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_usb2host1: power-controller@80288 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_rtmux: power-controller@802a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "rtmux";
+	};
+
+	ps_media: power-controller@802d8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_isp_sys: power-controller@802d0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sys";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_msr: power-controller@802e8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_jpg: power-controller@802e0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0_fe: power-controller@802b0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_fe";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_disp0_be: power-controller@802b8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_be";
+		power-domains = <&ps_disp0_fe>;
+	};
+
+	ps_uart0: power-controller@80200 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@80208 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@80210 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart3: power-controller@80218 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@80220 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_dpa: power-controller@80228 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80228 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dpa";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_hfd0: power-controller@80230 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hfd0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80240 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80240 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80248 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs1: power-controller@80250 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs2: power-controller@80258 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		/* Not used on some devicecs, to be disabled by loader */
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_dcs3: power-controller@80260 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		/* Not used on some devicecs, to be disabled by loader */
+		apple,always-on; /* LPDDR4 interface */
+	};
+
+	ps_usb2host0_ohci: power-controller@80280 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usbotg: power-controller@80290 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbotg";
+		power-domains = <&ps_usbctrl>;
+	};
+
+	ps_smx: power-controller@80298 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_mipi_dsi: power-controller@802c8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_pmp: power-controller@802f0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pms_sram: power-controller@802f8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_pcie_up_af: power-controller@80320 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_up_af";
+		power-domains = <&ps_iomux>;
+	};
+
+	ps_pcie_up: power-controller@80328 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_up";
+		power-domains = <&ps_pcie_up_af>;
+	};
+
+	ps_venc_sys: power-controller@80300 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_sys";
+		power-domains = <&ps_media>;
+	};
+
+	ps_ans2: power-controller@80308 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans2";
+		power-domains = <&ps_iomux>;
+	};
+
+	ps_pcie_down: power-controller@80310 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_down";
+		power-domains = <&ps_iomux>;
+	};
+
+	ps_pcie_down_aux: power-controller@80318 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_down_aux";
+	};
+
+	ps_pcie_up_aux: power-controller@80330 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80330 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_up_aux";
+		power-domains = <&ps_pcie_up>;
+	};
+
+	ps_pcie_stg0: power-controller@80338 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80338 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg0";
+		power-domains = <&ps_ans2>;
+	};
+
+	ps_pcie_stg0_aux: power-controller@80340 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80340 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg0_aux";
+	};
+
+	ps_pcie_stg1: power-controller@80348 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80348 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg1";
+		power-domains = <&ps_ans2>;
+	};
+
+	ps_pcie_stg1_aux: power-controller@80350 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80350 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_stg1_aux";
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_isp_rsts0: power-controller@84000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts0";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_rsts1: power-controller@84008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts1";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_vis: power-controller@84010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_vis";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_be: power-controller@84018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_be";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_pearl: power-controller@84020 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_pearl";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_venc_pipe4: power-controller@88000 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe4";
+	};
+
+	ps_venc_pipe5: power-controller@88008 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe5";
+	};
+
+	ps_venc_me0: power-controller@88010 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88018 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_spmi: power-controller@80058 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80058 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spmi";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_nub_aon: power-controller@80060 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80060 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "nub_aon";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_smc_fabric: power-controller@80030 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80030 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_fabric";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_smc_aon: power-controller@80088 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80088 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_aon";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_debug: power-controller@80050 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_nub_sram: power-controller@801a0 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "nub_sram";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_nub_fabric: power-controller@80198 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "nub_fabric";
+		apple,always-on; /* Core AON device */
+	};
+
+	ps_smc_cpu: power-controller@801a8 {
+		compatible = "apple,t8010-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_cpu";
+		power-domains = <&ps_smc_fabric &ps_smc_aon>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8012-touchbar.dtsi b/arch/arm64/boot/dts/apple/t8012-touchbar.dtsi
new file mode 100644
index 000000000000..fc4a80d0c787
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012-touchbar.dtsi
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Common Device Tree for T2 devices with a Touch Bar
+ *
+ * target-type: J152f, J213, J214k, J215, J223, J680, J780
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+/ {
+	chosen {
+		framebuffer0: framebuffer@0 {
+			compatible = "apple,simple-framebuffer", "simple-framebuffer";
+			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0_fe &ps_disp0_be &ps_mipi_dsi>;
+			/* Format properties will be added by loader */
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8012.dtsi b/arch/arm64/boot/dts/apple/t8012.dtsi
new file mode 100644
index 000000000000..42df2f51ad7b
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8012.dtsi
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Apple T8012 "T2" SoC
+ *
+ * Other names: H9M, "Gibraltar"
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/apple-aic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/apple.h>
+
+/ {
+	interrupt-parent = <&aic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	clkref: clock-ref {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "clkref";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@10000 {
+			compatible = "apple,hurricane-zephyr";
+			reg = <0x0 0x10000>;
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
+			enable-method = "spin-table";
+			device_type = "cpu";
+		};
+
+		cpu1: cpu@10001 {
+			compatible = "apple,hurricane-zephyr";
+			reg = <0x0 0x10001>;
+			cpu-release-addr = <0 0>; /* To be filled by loader */
+			operating-points-v2 = <&fusion_opp>;
+			performance-domains = <&cpufreq>;
+			enable-method = "spin-table";
+			device_type = "cpu";
+		};
+	};
+
+	fusion_opp: opp-table {
+		compatible = "operating-points-v2";
+
+		/*
+		 * Apple Fusion Architecture: Hardware big.LITTLE switcher
+		 * that use p-state transitions to switch between cores.
+		 * Only one type of core can be active at a given time.
+		 *
+		 * The E-core frequencies are adjusted so performance scales
+		 * linearly with reported clock speed.
+		 */
+
+		opp01 {
+			opp-hz = /bits/ 64 <172000000>; /* 300 MHz, E-core */
+			opp-level = <1>;
+			clock-latency-ns = <11000>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <230000000>; /* 396 MHz, E-core */
+			opp-level = <2>;
+			clock-latency-ns = <140000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <425000000>; /* 732 MHz, E-core */
+			opp-level = <3>;
+			clock-latency-ns = <110000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <637000000>; /* 1092 MHz, E-core */
+			opp-level = <4>;
+			clock-latency-ns = <130000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <756000000>;
+			opp-level = <5>;
+			clock-latency-ns = <130000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1056000000>;
+			opp-level = <6>;
+			clock-latency-ns = <130000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <1356000000>;
+			opp-level = <7>;
+			clock-latency-ns = <130000>;
+		};
+		opp08 {
+			opp-hz = /bits/ 64 <1644000000>;
+			opp-level = <8>;
+			clock-latency-ns = <135000>;
+		};
+		opp09 {
+			opp-hz = /bits/ 64 <1944000000>;
+			opp-level = <9>;
+			clock-latency-ns = <140000>;
+		};
+		opp10 {
+			opp-hz = /bits/ 64 <2244000000>;
+			opp-level = <10>;
+			clock-latency-ns = <150000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp11 {
+			opp-hz = /bits/ 64 <2340000000>;
+			opp-level = <11>;
+			clock-latency-ns = <150000>;
+			turbo-mode;
+		};
+#endif
+	};
+
+	soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		nonposted-mmio;
+		ranges;
+
+		cpufreq: performance-controller@202f20000 {
+			compatible = "apple,t8010-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x02f20000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
+		serial0: serial@20a600000 {
+			compatible = "apple,s5l-uart";
+			reg = <0x2 0x0a600000 0x0 0x4000>;
+			reg-io-width = <4>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 271 IRQ_TYPE_LEVEL_HIGH>;
+			/* Use the bootloader-enabled clocks for now. */
+			clocks = <&clkref>, <&clkref>;
+			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
+			status = "disabled";
+		};
+
+		pmgr: power-management@20e000000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0xe000000 0 0x8c000>;
+		};
+
+		aic: interrupt-controller@20e100000 {
+			compatible = "apple,t8010-aic", "apple,aic";
+			reg = <0x2 0x0e100000 0x0 0x100000>;
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		pinctrl_ap: pinctrl@20f100000 {
+			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x0f100000 0x0 0x100000>;
+			power-domains = <&ps_gpio>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_ap 0 0 221>;
+			apple,npins = <221>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 45 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 46 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 48 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 49 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 50 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 51 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_aop: pinctrl@2100f0000 {
+			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x0100f0000 0x0 0x10000>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_aop 0 0 41>;
+			apple,npins = <41>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 131 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 132 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 133 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 135 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 136 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 137 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_nub: pinctrl@2111f0000 {
+			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x111f0000 0x0 0x1000>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_nub 0 0 19>;
+			apple,npins = <19>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 164 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 165 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 166 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pmgr_mini: power-management@211200000 {
+			compatible = "apple,t8010-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x11200000 0 0x84000>;
+		};
+
+		wdt: watchdog@2112b0000 {
+			compatible = "apple,t8010-wdt", "apple,wdt";
+			reg = <0x2 0x112b0000 0x0 0x4000>;
+			clocks = <&clkref>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 168 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		pinctrl_smc: pinctrl@212024000 {
+			compatible = "apple,t8010-pinctrl", "apple,pinctrl";
+			reg = <0x2 0x12024000 0x0 0x1000>;
+			power-domains = <&ps_smc_cpu>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&pinctrl_smc 0 0 81>;
+			apple,npins = <81>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 195 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 196 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 197 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 198 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 199 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 200 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 201 IRQ_TYPE_LEVEL_HIGH>;
+			/*
+			 * SMC is not yet supported and accessing this pinctrl while SMC is
+			 * suspended results in a hang.
+			 */
+			status = "disabled";
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&aic>;
+		interrupt-names = "phys", "virt";
+		/* Note that T2 doesn't actually have a hypervisor (EL2 is not implemented). */
+		interrupts = <AIC_FIQ AIC_TMR_GUEST_PHYS IRQ_TYPE_LEVEL_HIGH>,
+			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
+	};
+};
+
+#include "t8012-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8015-8.dtsi b/arch/arm64/boot/dts/apple/t8015-8.dtsi
index b6505b5185bd..0300ee1a2ffb 100644
--- a/arch/arm64/boot/dts/apple/t8015-8.dtsi
+++ b/arch/arm64/boot/dts/apple/t8015-8.dtsi
@@ -11,3 +11,7 @@
 / {
 	chassis-type = "handset";
 };
+
+&dwi_bl {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t8015-common.dtsi b/arch/arm64/boot/dts/apple/t8015-common.dtsi
index 69258a33ea50..498f58fb9715 100644
--- a/arch/arm64/boot/dts/apple/t8015-common.dtsi
+++ b/arch/arm64/boot/dts/apple/t8015-common.dtsi
@@ -24,6 +24,7 @@
 		framebuffer0: framebuffer@0 {
 			compatible = "apple,simple-framebuffer", "simple-framebuffer";
 			reg = <0 0 0 0>; /* To be filled by loader */
+			power-domains = <&ps_disp0_be &ps_mipi_dsi &ps_disp0_hilo &ps_disp0_ppp>;
 			/* Format properties will be added by loader */
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/apple/t8015-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8015-pmgr.dtsi
new file mode 100644
index 000000000000..e238c2d2732f
--- /dev/null
+++ b/arch/arm64/boot/dts/apple/t8015-pmgr.dtsi
@@ -0,0 +1,931 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * PMGR Power domains for the Apple T8015 "A11" SoC
+ *
+ * Copyright (c) 2024, Nick Chan <towinchenmi@gmail.com>
+ */
+
+&pmgr {
+	ps_cpu0: power-controller@80000 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu0";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu1: power-controller@80008 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu1";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu2: power-controller@80010 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu2";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu3: power-controller@80018 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu3";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu4: power-controller@80020 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu4";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpu5: power-controller@80028 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpu5";
+		apple,always-on; /* Core device */
+	};
+
+	ps_cpm: power-controller@80040 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80040 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "cpm";
+		apple,always-on; /* Core device */
+	};
+
+	ps_sio_busif: power-controller@80158 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80158 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_busif";
+	};
+
+	ps_sio_p: power-controller@80160 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80160 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio_p";
+		power-domains = <&ps_sio_busif>;
+	};
+
+	ps_sbr: power-controller@80100 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80100 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sbr";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_aic: power-controller@80108 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80108 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aic";
+		apple,always-on; /* Core device */
+	};
+
+	ps_dwi: power-controller@80110 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80110 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dwi";
+	};
+
+	ps_gpio: power-controller@80118 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80118 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gpio";
+	};
+
+	ps_pms: power-controller@80120 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80120 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms";
+		apple,always-on; /* Core device */
+	};
+
+	ps_pcie_ref: power-controller@80148 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80148 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_ref";
+	};
+
+	ps_mca0: power-controller@80170 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80170 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca1: power-controller@80178 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80178 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca2: power-controller@80180 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80180 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca3: power-controller@80188 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80188 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mca4: power-controller@80190 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80190 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_pwm0: power-controller@801a0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pwm0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c0: power-controller@801a8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c1: power-controller@801b0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c2: power-controller@801b8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_i2c3: power-controller@801c0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "i2c3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi0: power-controller@801c8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi1: power-controller@801d0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi2: power-controller@801d8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_spi3: power-controller@801e0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart0: power-controller@801e8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801e8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart1: power-controller@801f0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart1";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart2: power-controller@801f8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x801f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart2";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_sio: power-controller@80168 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80168 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sio";
+		power-domains = <&ps_sio_p>;
+		apple,always-on; /* Core device */
+	};
+
+	ps_hsicphy: power-controller@80128 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80128 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hsicphy";
+		power-domains = <&ps_usb2host1>;
+	};
+
+	ps_ispsens0: power-controller@80130 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80130 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens0";
+	};
+
+	ps_ispsens1: power-controller@80138 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80138 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens1";
+	};
+
+	ps_ispsens2: power-controller@80140 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ispsens2";
+	};
+
+	ps_mca5: power-controller@80198 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80198 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mca5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_usb: power-controller@80270 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80270 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb";
+	};
+
+	ps_usbctlreg: power-controller@80278 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80278 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usbctlreg";
+		power-domains = <&ps_usb>;
+	};
+
+	ps_usb2host0: power-controller@80280 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80280 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0";
+		power-domains = <&ps_usbctlreg>;
+	};
+
+	ps_usb2host1: power-controller@80290 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80290 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host1";
+		power-domains = <&ps_usbctlreg>;
+	};
+
+	ps_rtmux: power-controller@802b0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "rtmux";
+	};
+
+	ps_media: power-controller@802f0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "media";
+	};
+
+	ps_jpg: power-controller@802f8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802f8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "jpg";
+		power-domains = <&ps_media>;
+	};
+
+	ps_disp0_fe: power-controller@802b8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802b8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_fe";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_disp0_be: power-controller@802c0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_be";
+		power-domains = <&ps_disp0_fe>;
+	};
+
+	ps_disp0_gp: power-controller@802c8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802c8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_gp";
+		power-domains = <&ps_disp0_be>;
+		status = "disabled";
+	};
+
+	ps_uart3: power-controller@80200 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80200 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart3";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart4: power-controller@80208 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80208 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart4";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart5: power-controller@80210 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80210 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart5";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart6: power-controller@80218 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80218 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart6";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart7: power-controller@80220 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80220 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart7";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_uart8: power-controller@80228 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80228 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "uart8";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_hfd0: power-controller@80238 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80238 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "hfd0";
+		power-domains = <&ps_sio_p>;
+	};
+
+	ps_mcc: power-controller@80248 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80248 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mcc";
+		apple,always-on; /* Memory cache controller */
+	};
+
+	ps_dcs0: power-controller@80250 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80250 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs0";
+		apple,always-on; /* LPDDR4X interface */
+	};
+
+	ps_dcs1: power-controller@80258 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80258 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs1";
+		apple,always-on; /* LPDDR4X interface */
+	};
+
+	ps_dcs2: power-controller@80260 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs2";
+		apple,always-on; /* LPDDR4X interface */
+	};
+
+	ps_dcs3: power-controller@80268 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80268 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dcs3";
+		apple,always-on; /* LPDDR4X interface */
+	};
+
+	ps_usb2host0_ohci: power-controller@80288 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80288 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2host0_ohci";
+		power-domains = <&ps_usb2host0>;
+	};
+
+	ps_usb2dev: power-controller@80298 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80298 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "usb2dev";
+		power-domains = <&ps_usbctlreg>;
+	};
+
+	ps_smx: power-controller@802a0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smx";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_sf: power-controller@802a8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sf";
+		apple,always-on; /* Apple fabric, critical block */
+	};
+
+	ps_mipi_dsi: power-controller@802d8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "mipi_dsi";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_dp: power-controller@802e0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802e0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dp";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_dpa: power-controller@80230 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80230 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dpa";
+	};
+
+	ps_disp0_be_2x: power-controller@802d0 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x802d0 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_be_2x";
+		power-domains = <&ps_disp0_be>;
+	};
+
+	ps_isp_sys: power-controller@80350 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80350 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_sys";
+		power-domains = <&ps_rtmux>;
+	};
+
+	ps_msr: power-controller@80300 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80300 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "msr";
+		power-domains = <&ps_media>;
+	};
+
+	ps_venc_sys: power-controller@80398 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80398 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_sys";
+		power-domains = <&ps_media>;
+	};
+
+	ps_pmp: power-controller@80308 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80308 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pmp";
+	};
+
+	ps_pms_sram: power-controller@80310 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80310 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pms_sram";
+	};
+
+	ps_pcie: power-controller@80318 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80318 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie";
+	};
+
+	ps_pcie_aux: power-controller@80320 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80320 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_aux";
+	};
+
+	ps_vdec0: power-controller@80388 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80388 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "vdec0";
+		power-domains = <&ps_media>;
+	};
+
+	ps_gfx: power-controller@80338 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80338 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "gfx";
+	};
+
+	ps_ans2: power-controller@80328 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80328 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "ans2";
+		apple,always-on;
+	};
+
+	ps_pcie_direct: power-controller@80330 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80330 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "pcie_direct";
+		apple,always-on;
+	};
+
+	ps_avd_sys: power-controller@803a8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x803a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "avd_sys";
+		power-domains = <&ps_media>;
+	};
+
+	ps_sep: power-controller@80400 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80400 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "sep";
+		apple,always-on; /* Locked on */
+	};
+
+	ps_disp0_gp0: power-controller@80830 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80830 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_gp0";
+		power-domains = <&ps_disp0_gp>;
+		status = "disabled";
+	};
+
+	ps_disp0_gp1: power-controller@80838 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80838 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_gp1";
+		status = "disabled";
+	};
+
+	ps_disp0_ppp: power-controller@80840 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80840 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_ppp";
+	};
+
+	ps_disp0_hilo: power-controller@80848 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80848 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "disp0_hilo";
+	};
+
+	ps_isp_rsts0: power-controller@84000 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts0";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_rsts1: power-controller@84008 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_rsts1";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_vis: power-controller@84010 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_vis";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_be: power-controller@84018 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_be";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_pearl: power-controller@84020 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_pearl";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_dprx: power-controller@84028 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "dprx";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_isp_cnv: power-controller@84030 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x84030 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "isp_cnv";
+		power-domains = <&ps_isp_sys>;
+	};
+
+	ps_venc_dma: power-controller@88000 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_dma";
+	};
+
+	ps_venc_pipe4: power-controller@88010 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88010 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe4";
+	};
+
+	ps_venc_pipe5: power-controller@88018 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88018 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_pipe5";
+	};
+
+	ps_venc_me0: power-controller@88020 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me0";
+	};
+
+	ps_venc_me1: power-controller@88028 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x88028 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "venc_me1";
+	};
+};
+
+&pmgr_mini {
+	ps_aop_base: power-controller@80008 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80008 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_base";
+		power-domains = <&ps_aop_cpu &ps_aop_filter>;
+		apple,always-on; /* Always on processor */
+	};
+
+	ps_debug: power-controller@80050 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80050 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "debug";
+	};
+
+	ps_aop_cpu: power-controller@80020 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80020 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_cpu";
+	};
+
+	ps_aop_filter: power-controller@80000 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80000 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "aop_filter";
+	};
+
+	ps_spmi: power-controller@80058 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80058 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spmi";
+		apple,always-on; /* System Power Management Interface */
+	};
+
+	ps_smc_i2cm1: power-controller@800a8 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x800a8 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_i2cm1";
+	};
+
+	ps_smc_fabric: power-controller@80030 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80030 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_fabric";
+	};
+
+	ps_smc_cpu: power-controller@80140 {
+		compatible = "apple,t8015-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x80140 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "smc_cpu";
+		power-domains = <&ps_smc_fabric &ps_smc_i2cm1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8015.dtsi b/arch/arm64/boot/dts/apple/t8015.dtsi
index 8828d830e5be..4d54afcecd50 100644
--- a/arch/arm64/boot/dts/apple/t8015.dtsi
+++ b/arch/arm64/boot/dts/apple/t8015.dtsi
@@ -58,6 +58,9 @@
 			compatible = "apple,mistral";
 			reg = <0x0 0x0>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_e>;
+			operating-points-v2 = <&mistral_opp>;
+			capacity-dmips-mhz = <633>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -66,6 +69,9 @@
 			compatible = "apple,mistral";
 			reg = <0x0 0x1>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_e>;
+			operating-points-v2 = <&mistral_opp>;
+			capacity-dmips-mhz = <633>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -74,6 +80,9 @@
 			compatible = "apple,mistral";
 			reg = <0x0 0x2>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_e>;
+			operating-points-v2 = <&mistral_opp>;
+			capacity-dmips-mhz = <633>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -82,6 +91,9 @@
 			compatible = "apple,mistral";
 			reg = <0x0 0x3>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_e>;
+			operating-points-v2 = <&mistral_opp>;
+			capacity-dmips-mhz = <633>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -90,6 +102,9 @@
 			compatible = "apple,monsoon";
 			reg = <0x0 0x10004>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_p>;
+			operating-points-v2 = <&monsoon_opp>;
+			capacity-dmips-mhz = <1024>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
@@ -98,11 +113,107 @@
 			compatible = "apple,monsoon";
 			reg = <0x0 0x10005>;
 			cpu-release-addr = <0 0>; /* To be filled by loader */
+			performance-domains = <&cpufreq_p>;
+			operating-points-v2 = <&monsoon_opp>;
+			capacity-dmips-mhz = <1024>;
 			enable-method = "spin-table";
 			device_type = "cpu";
 		};
 	};
 
+	mistral_opp: opp-table-0 {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <1800>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <453000000>;
+			opp-level = <2>;
+			clock-latency-ns = <140000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <672000000>;
+			opp-level = <3>;
+			clock-latency-ns = <105000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <972000000>;
+			opp-level = <4>;
+			clock-latency-ns = <115000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1272000000>;
+			opp-level = <5>;
+			clock-latency-ns = <125000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <1572000000>;
+			opp-level = <6>;
+			clock-latency-ns = <135000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp07 {
+			opp-hz = /bits/ 64 <1680000000>;
+			opp-level = <7>;
+			clock-latency-ns = <135000>;
+			turbo-mode;
+		};
+#endif
+	};
+
+	monsoon_opp: opp-table-1 {
+		compatible = "operating-points-v2";
+
+		opp01 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-level = <1>;
+			clock-latency-ns = <1400>;
+		};
+		opp02 {
+			opp-hz = /bits/ 64 <453000000>;
+			opp-level = <2>;
+			clock-latency-ns = <140000>;
+		};
+		opp03 {
+			opp-hz = /bits/ 64 <853000000>;
+			opp-level = <3>;
+			clock-latency-ns = <110000>;
+		};
+		opp04 {
+			opp-hz = /bits/ 64 <1332000000>;
+			opp-level = <4>;
+			clock-latency-ns = <110000>;
+		};
+		opp05 {
+			opp-hz = /bits/ 64 <1812000000>;
+			opp-level = <5>;
+			clock-latency-ns = <125000>;
+		};
+		opp06 {
+			opp-hz = /bits/ 64 <2064000000>;
+			opp-level = <6>;
+			clock-latency-ns = <130000>;
+		};
+		opp07 {
+			opp-hz = /bits/ 64 <2304000000>;
+			opp-level = <7>;
+			clock-latency-ns = <140000>;
+		};
+#if 0
+		/* Not available until CPU deep sleep is implemented */
+		opp08 {
+			opp-hz = /bits/ 64 <2376000000>;
+			opp-level = <8>;
+			clock-latency-ns = <140000>;
+			turbo-mode;
+		};
+#endif
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;
@@ -110,6 +221,18 @@
 		nonposted-mmio;
 		ranges;
 
+		cpufreq_e: performance-controller@208e20000 {
+			compatible = "apple,t8015-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x08e20000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
+		cpufreq_p: performance-controller@208ea0000 {
+			compatible = "apple,t8015-cluster-cpufreq", "apple,t8103-cluster-cpufreq", "apple,cluster-cpufreq";
+			reg = <0x2 0x08ea0000 0 0x1000>;
+			#performance-domain-cells = <0>;
+		};
+
 		serial0: serial@22e600000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x2e600000 0x0 0x4000>;
@@ -119,6 +242,7 @@
 			/* Use the bootloader-enabled clocks for now. */
 			clocks = <&clkref>, <&clkref>;
 			clock-names = "uart", "clk_uart_baud0";
+			power-domains = <&ps_uart0>;
 			status = "disabled";
 		};
 
@@ -127,11 +251,28 @@
 			reg = <0x2 0x32100000 0x0 0x8000>;
 			#interrupt-cells = <3>;
 			interrupt-controller;
+			power-domains = <&ps_aic>;
+		};
+
+		pmgr: power-management@232000000 {
+			compatible = "apple,t8015-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x32000000 0 0x8c000>;
+		};
+
+		dwi_bl: backlight@232200080 {
+			compatible = "apple,t8015-dwi-bl", "apple,dwi-bl";
+			reg = <0x2 0x32200080 0x0 0x8>;
+			power-domains = <&ps_dwi>;
+			status = "disabled";
 		};
 
 		pinctrl_ap: pinctrl@233100000 {
 			compatible = "apple,t8015-pinctrl", "apple,pinctrl";
 			reg = <0x2 0x33100000 0x0 0x1000>;
+			power-domains = <&ps_gpio>;
 
 			gpio-controller;
 			#gpio-cells = <2>;
@@ -188,6 +329,14 @@
 				     <AIC_IRQ 170 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		pmgr_mini: power-management@235200000 {
+			compatible = "apple,t8015-pmgr", "apple,pmgr", "syscon", "simple-mfd";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			reg = <0x2 0x35200000 0 0x84000>;
+		};
+
 		wdt: watchdog@2352b0000 {
 			compatible = "apple,t8015-wdt", "apple,wdt";
 			reg = <0x2 0x352b0000 0x0 0x4000>;
@@ -232,3 +381,5 @@
 			     <AIC_FIQ AIC_TMR_GUEST_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+#include "t8015-pmgr.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts
index 56b0c67bfcda..e2d9439397f7 100644
--- a/arch/arm64/boot/dts/apple/t8103-j293.dts
+++ b/arch/arm64/boot/dts/apple/t8103-j293.dts
@@ -17,6 +17,14 @@
 	compatible = "apple,j293", "apple,t8103", "apple,arm-platform";
 	model = "Apple MacBook Pro (13-inch, M1, 2020)";
 
+	/*
+	 * All of those are used by the bootloader to pass calibration
+	 * blobs and other device-specific properties
+	 */
+	aliases {
+		touchbar0 = &touchbar0;
+	};
+
 	led-controller {
 		compatible = "pwm-leds";
 		led-0 {
@@ -49,3 +57,63 @@
 &fpwm1 {
 	status = "okay";
 };
+
+&spi0 {
+	cs-gpios = <&pinctrl_ap 109 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	touchbar0: touchbar@0 {
+		compatible = "apple,j293-touchbar";
+		reg = <0>;
+		spi-max-frequency = <11500000>;
+		spi-cs-setup-delay-ns = <2000>;
+		spi-cs-hold-delay-ns = <2000>;
+		reset-gpios = <&pinctrl_ap 139 GPIO_ACTIVE_LOW>;
+		interrupts-extended = <&pinctrl_ap 194 IRQ_TYPE_EDGE_FALLING>;
+		firmware-name = "apple/dfrmtfw-j293.bin";
+		touchscreen-size-x = <23045>;
+		touchscreen-size-y = <640>;
+		touchscreen-inverted-y;
+	};
+};
+
+/*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+	apple,always-on;
+};
+
+&display_dfr {
+	status = "okay";
+};
+
+&dfr_mipi_out {
+	dfr_mipi_out_panel: endpoint@0 {
+		reg = <0>;
+		remote-endpoint = <&dfr_panel_in>;
+	};
+};
+
+&displaydfr_mipi {
+	status = "okay";
+
+	dfr_panel: panel@0 {
+		compatible = "apple,j293-summit", "apple,summit";
+		reg = <0>;
+		max-brightness = <255>;
+
+		port {
+			dfr_panel_in: endpoint {
+				remote-endpoint = <&dfr_mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&displaydfr_dart {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
index 5988a4eb6efa..8e82231acab5 100644
--- a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
@@ -90,3 +90,5 @@
 &nco_clkref {
 	clock-frequency = <900000000>;
 };
+
+#include "spi1-nvram.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi
index 9645861a858c..c41c57d63997 100644
--- a/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi
@@ -387,6 +387,15 @@
 		power-domains = <&ps_sio>, <&ps_spi_p>;
 	};
 
+	ps_spi4: power-controller@260 {
+		compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate";
+		reg = <0x260 4>;
+		#power-domain-cells = <0>;
+		#reset-cells = <0>;
+		label = "spi4";
+		power-domains = <&ps_sio>, <&ps_spi_p>;
+	};
+
 	ps_uart_n: power-controller@268 {
 		compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate";
 		reg = <0x268 4>;
@@ -558,15 +567,6 @@
 		apple,always-on; /* Memory controller */
 	};
 
-	ps_spi4: power-controller@260 {
-		compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate";
-		reg = <0x260 4>;
-		#power-domain-cells = <0>;
-		#reset-cells = <0>;
-		label = "spi4";
-		power-domains = <&ps_sio>, <&ps_spi_p>;
-	};
-
 	ps_dcs0: power-controller@300 {
 		compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate";
 		reg = <0x300 4>;
diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi
index 9b0dad6b6184..97b6a067394e 100644
--- a/arch/arm64/boot/dts/apple/t8103.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103.dtsi
@@ -326,6 +326,20 @@
 		clock-output-names = "clkref";
 	};
 
+	clk_120m: clock-120m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <120000000>;
+		clock-output-names = "clk_120m";
+	};
+
+	clk_200m: clock-200m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+		clock-output-names = "clk_200m";
+	};
+
 	/*
 	 * This is a fabulated representation of the input clock
 	 * to NCO since we don't know the true clock tree.
@@ -356,6 +370,67 @@
 			#performance-domain-cells = <0>;
 		};
 
+		display_dfr: display-pipe@228200000 {
+			compatible = "apple,t8103-display-pipe", "apple,h7-display-pipe";
+			reg = <0x2 0x28200000 0x0 0xc000>,
+			      <0x2 0x28400000 0x0 0x4000>;
+			reg-names = "be", "fe";
+			power-domains = <&ps_dispdfr_fe>, <&ps_dispdfr_be>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 502 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 506 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "be", "fe";
+			iommus = <&displaydfr_dart 0>;
+			status = "disabled";
+
+			port {
+				dfr_adp_out_mipi: endpoint {
+					remote-endpoint = <&dfr_mipi_in_adp>;
+				};
+			};
+		};
+
+		displaydfr_dart: iommu@228304000 {
+			compatible = "apple,t8103-dart";
+			reg = <0x2 0x28304000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 504 IRQ_TYPE_LEVEL_HIGH>;
+			#iommu-cells = <1>;
+			power-domains = <&ps_dispdfr_fe>;
+			status = "disabled";
+		};
+
+		displaydfr_mipi: dsi@228600000 {
+			compatible = "apple,t8103-display-pipe-mipi", "apple,h7-display-pipe-mipi";
+			reg = <0x2 0x28600000 0x0 0x100000>;
+			power-domains = <&ps_mipi_dsi>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				dfr_mipi_in: port@0 {
+					reg = <0>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					dfr_mipi_in_adp: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&dfr_adp_out_mipi>;
+					};
+				};
+
+				dfr_mipi_out: port@1 {
+					reg = <1>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+			};
+		};
+
 		sio_dart: iommu@235004000 {
 			compatible = "apple,t8103-dart";
 			reg = <0x2 0x35004000 0x0 0x4000>;
@@ -441,6 +516,48 @@
 			status = "disabled";
 		};
 
+		spi0: spi@235100000 {
+			compatible = "apple,t8103-spi", "apple,spi";
+			reg = <0x2 0x35100000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 614 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_200m>;
+			pinctrl-0 = <&spi0_pins>;
+			pinctrl-names = "default";
+			power-domains = <&ps_spi0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		spi1: spi@235104000 {
+			compatible = "apple,t8103-spi", "apple,spi";
+			reg = <0x2 0x35104000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 615 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_200m>;
+			pinctrl-0 = <&spi1_pins>;
+			pinctrl-names = "default";
+			power-domains = <&ps_spi1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		spi3: spi@23510c000 {
+			compatible = "apple,t8103-spi", "apple,spi";
+			reg = <0x2 0x3510c000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 617 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_120m>;
+			pinctrl-0 = <&spi3_pins>;
+			pinctrl-names = "default";
+			power-domains = <&ps_spi3>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		serial0: serial@235200000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x35200000 0x0 0x1000>;
@@ -597,6 +714,26 @@
 					 <APPLE_PINMUX(134, 1)>;
 			};
 
+			spi0_pins: spi0-pins {
+				pinmux = <APPLE_PINMUX(67, 1)>, /* CLK */
+					<APPLE_PINMUX(68, 1)>,  /* MOSI */
+					<APPLE_PINMUX(69, 1)>;  /* MISO */
+			};
+
+			spi1_pins: spi1-pins {
+				pinmux = <APPLE_PINMUX(42, 1)>,
+					<APPLE_PINMUX(43, 1)>,
+					<APPLE_PINMUX(44, 1)>,
+					<APPLE_PINMUX(45, 1)>;
+			};
+
+			spi3_pins: spi3-pins {
+				pinmux = <APPLE_PINMUX(46, 1)>,
+					<APPLE_PINMUX(47, 1)>,
+					<APPLE_PINMUX(48, 1)>,
+					<APPLE_PINMUX(49, 1)>;
+			};
+
 			pcie_pins: pcie-pins {
 				pinmux = <APPLE_PINMUX(150, 1)>,
 					 <APPLE_PINMUX(151, 1)>,
diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts
index 0ad908349f55..be86d34c6696 100644
--- a/arch/arm64/boot/dts/apple/t8112-j493.dts
+++ b/arch/arm64/boot/dts/apple/t8112-j493.dts
@@ -17,8 +17,13 @@
 	compatible = "apple,j493", "apple,t8112", "apple,arm-platform";
 	model = "Apple MacBook Pro (13-inch, M2, 2022)";
 
+	/*
+	 * All of those are used by the bootloader to pass calibration
+	 * blobs and other device-specific properties
+	 */
 	aliases {
 		bluetooth0 = &bluetooth0;
+		touchbar0 = &touchbar0;
 		wifi0 = &wifi0;
 	};
 
@@ -36,6 +41,47 @@
 };
 
 /*
+ * The driver depends on boot loader initialized state which resets when this
+ * power-domain is powered off. This happens on suspend or when the driver is
+ * missing during boot. Mark the domain as always on until the driver can
+ * handle this.
+ */
+&ps_dispdfr_be {
+	apple,always-on;
+};
+
+&display_dfr {
+	status = "okay";
+};
+
+&dfr_mipi_out {
+	dfr_mipi_out_panel: endpoint@0 {
+		reg = <0>;
+		remote-endpoint = <&dfr_panel_in>;
+	};
+};
+
+&displaydfr_mipi {
+	status = "okay";
+
+	dfr_panel: panel@0 {
+		compatible = "apple,j493-summit", "apple,summit";
+		reg = <0>;
+		max-brightness = <255>;
+
+		port {
+			dfr_panel_in: endpoint {
+				remote-endpoint = <&dfr_mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&displaydfr_dart {
+	status = "okay";
+};
+
+/*
  * Force the bus number assignments so that we can declare some of the
  * on-board devices and properties that are populated by the bootloader
  * (such as MAC addresses).
@@ -67,3 +113,21 @@
 &fpwm1 {
 	status = "okay";
 };
+
+&spi3 {
+	status = "okay";
+
+	touchbar0: touchbar@0 {
+		compatible = "apple,j493-touchbar";
+		reg = <0>;
+		spi-max-frequency = <8000000>;
+		spi-cs-setup-delay-ns = <2000>;
+		spi-cs-hold-delay-ns = <2000>;
+		reset-gpios = <&pinctrl_ap 170 GPIO_ACTIVE_LOW>;
+		interrupts-extended = <&pinctrl_ap 174 IRQ_TYPE_EDGE_FALLING>;
+		firmware-name = "apple/dfrmtfw-j493.bin";
+		touchscreen-size-x = <23045>;
+		touchscreen-size-y = <640>;
+		touchscreen-inverted-y;
+	};
+};
diff --git a/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi
index f5edf61113e7..6da35496a4c8 100644
--- a/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi
+++ b/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi
@@ -79,3 +79,5 @@
 &nco_clkref {
 	clock-frequency = <900000000>;
 };
+
+#include "spi1-nvram.dtsi"
diff --git a/arch/arm64/boot/dts/apple/t8112.dtsi b/arch/arm64/boot/dts/apple/t8112.dtsi
index 1666e6ab250b..d9b966d68e4f 100644
--- a/arch/arm64/boot/dts/apple/t8112.dtsi
+++ b/arch/arm64/boot/dts/apple/t8112.dtsi
@@ -349,6 +349,13 @@
 		clock-output-names = "clkref";
 	};
 
+	clk_200m: clock-200m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+		clock-output-names = "clk_200m";
+	};
+
 	/*
 	 * This is a fabulated representation of the input clock
 	 * to NCO since we don't know the true clock tree.
@@ -379,6 +386,67 @@
 			#performance-domain-cells = <0>;
 		};
 
+		display_dfr: display-pipe@228200000 {
+			compatible = "apple,t8112-display-pipe", "apple,h7-display-pipe";
+			reg = <0x2 0x28200000 0x0 0xc000>,
+			      <0x2 0x28400000 0x0 0x4000>;
+			reg-names = "be", "fe";
+			power-domains = <&ps_dispdfr_fe>, <&ps_dispdfr_be>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 614 IRQ_TYPE_LEVEL_HIGH>,
+				     <AIC_IRQ 618 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "be", "fe";
+			iommus = <&displaydfr_dart 0>;
+			status = "disabled";
+
+			port {
+				dfr_adp_out_mipi: endpoint {
+					remote-endpoint = <&dfr_mipi_in_adp>;
+				};
+			};
+		};
+
+		displaydfr_dart: iommu@228304000 {
+			compatible = "apple,t8110-dart";
+			reg = <0x2 0x28304000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 616 IRQ_TYPE_LEVEL_HIGH>;
+			#iommu-cells = <1>;
+			power-domains = <&ps_dispdfr_fe>;
+			status = "disabled";
+		};
+
+		displaydfr_mipi: dsi@228600000 {
+			compatible = "apple,t8112-display-pipe-mipi", "apple,h7-display-pipe-mipi";
+			reg = <0x2 0x28600000 0x0 0x100000>;
+			power-domains = <&ps_mipi_dsi>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				dfr_mipi_in: port@0 {
+					reg = <0>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					dfr_mipi_in_adp: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&dfr_adp_out_mipi>;
+					};
+				};
+
+				dfr_mipi_out: port@1 {
+					reg = <1>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+			};
+		};
+
 		sio_dart: iommu@235004000 {
 			compatible = "apple,t8110-dart";
 			reg = <0x2 0x35004000 0x0 0x4000>;
@@ -467,6 +535,34 @@
 			status = "disabled";
 		};
 
+		spi1: spi@235104000 {
+			compatible = "apple,t8112-spi", "apple,spi";
+			reg = <0x2 0x35104000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 749 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_200m>;
+			pinctrl-0 = <&spi1_pins>;
+			pinctrl-names = "default";
+			power-domains = <&ps_spi1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		spi3: spi@23510c000 {
+			compatible = "apple,t8112-spi", "apple,spi";
+			reg = <0x2 0x3510c000 0x0 0x4000>;
+			interrupt-parent = <&aic>;
+			interrupts = <AIC_IRQ 751 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clkref>;
+			pinctrl-0 = <&spi3_pins>;
+			pinctrl-names = "default";
+			power-domains = <&ps_spi3>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled"; /* only used in J493 */
+		};
+
 		serial0: serial@235200000 {
 			compatible = "apple,s5l-uart";
 			reg = <0x2 0x35200000 0x0 0x1000>;
@@ -626,13 +722,20 @@
 					 <APPLE_PINMUX(130, 1)>;
 			};
 
-			spi3_pins: spi3-pins {
+			spi1_pins: spi1-pins {
 				pinmux = <APPLE_PINMUX(46, 1)>,
 					<APPLE_PINMUX(47, 1)>,
 					<APPLE_PINMUX(48, 1)>,
 					<APPLE_PINMUX(49, 1)>;
 			};
 
+			spi3_pins: spi3-pins {
+				pinmux = <APPLE_PINMUX(93, 1)>,
+					<APPLE_PINMUX(94, 1)>,
+					<APPLE_PINMUX(95, 1)>,
+					<APPLE_PINMUX(96, 1)>;
+			};
+
 			pcie_pins: pcie-pins {
 				pinmux = <APPLE_PINMUX(162, 1)>,
 					 <APPLE_PINMUX(163, 1)>,
diff --git a/arch/arm64/boot/dts/arm/Makefile b/arch/arm64/boot/dts/arm/Makefile
index d908e96d7ddc..f30ee045dc95 100644
--- a/arch/arm64/boot/dts/arm/Makefile
+++ b/arch/arm64/boot/dts/arm/Makefile
@@ -7,3 +7,4 @@ dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2f-1xv7-ca53x2.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += fvp-base-revc.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += corstone1000-fvp.dtb corstone1000-mps3.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += morello-sdp.dtb morello-fvp.dtb
diff --git a/arch/arm64/boot/dts/arm/corstone1000-fvp.dts b/arch/arm64/boot/dts/arm/corstone1000-fvp.dts
index abd013562995..66ba6b027193 100644
--- a/arch/arm64/boot/dts/arm/corstone1000-fvp.dts
+++ b/arch/arm64/boot/dts/arm/corstone1000-fvp.dts
@@ -49,3 +49,29 @@
 		clock-names = "smclk", "apb_pclk";
 	};
 };
+
+&cpus {
+	cpu1: cpu@1 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a35";
+		reg = <0x1>;
+		enable-method = "psci";
+		next-level-cache = <&L2_0>;
+	};
+
+	cpu2: cpu@2 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a35";
+		reg = <0x2>;
+		enable-method = "psci";
+		next-level-cache = <&L2_0>;
+	};
+
+	cpu3: cpu@3 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a35";
+		reg = <0x3>;
+		enable-method = "psci";
+		next-level-cache = <&L2_0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/arm/corstone1000.dtsi b/arch/arm64/boot/dts/arm/corstone1000.dtsi
index bb9b96fb5314..56ada8728b60 100644
--- a/arch/arm64/boot/dts/arm/corstone1000.dtsi
+++ b/arch/arm64/boot/dts/arm/corstone1000.dtsi
@@ -21,7 +21,7 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	cpus {
+	cpus: cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
@@ -29,6 +29,7 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a35";
 			reg = <0>;
+			enable-method = "psci";
 			next-level-cache = <&L2_0>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/arm/morello-fvp.dts b/arch/arm64/boot/dts/arm/morello-fvp.dts
new file mode 100644
index 000000000000..2072c0b72325
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/morello-fvp.dts
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * Copyright (c) 2021-2024, Arm Limited. All rights reserved.
+ */
+
+/dts-v1/;
+#include "morello.dtsi"
+
+/ {
+	model = "Arm Morello Fixed Virtual Platform";
+	compatible = "arm,morello-fvp", "arm,morello";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	bp_refclock24mhz: clock-24000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "bp:clock24mhz";
+	};
+
+	block_0: virtio_block@1c170000 {
+		compatible = "virtio,mmio";
+		reg = <0x0 0x1c170000 0x0 0x200>;
+		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	net_0: virtio_net@1c180000 {
+		compatible = "virtio,mmio";
+		reg = <0x0 0x1c180000 0x0 0x200>;
+		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	rng_0: virtio_rng@1c190000 {
+		compatible = "virtio,mmio";
+		reg = <0x0 0x1c190000 0x0 0x200>;
+		interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	p9_0: virtio_p9@1c1a0000 {
+		compatible = "virtio,mmio";
+		reg = <0x0 0x1c1a0000 0x0 0x200>;
+		interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	kmi_0: kmi@1c150000 {
+		compatible = "arm,pl050", "arm,primecell";
+		reg = <0x0 0x1c150000 0x0 0x1000>;
+		interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&bp_refclock24mhz>, <&bp_refclock24mhz>;
+		clock-names = "KMIREFCLK", "apb_pclk";
+	};
+
+	kmi_1: kmi@1c160000 {
+		compatible = "arm,pl050", "arm,primecell";
+		reg = <0x0 0x1c160000 0x0 0x1000>;
+		interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&bp_refclock24mhz>, <&bp_refclock24mhz>;
+		clock-names = "KMIREFCLK", "apb_pclk";
+	};
+
+	eth_0: ethernet@1d100000 {
+		compatible = "smsc,lan91c111";
+		reg = <0x0 0x1d100000 0x0 0x10000>;
+		interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/arm/morello-sdp.dts b/arch/arm64/boot/dts/arm/morello-sdp.dts
new file mode 100644
index 000000000000..cee49dee7571
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/morello-sdp.dts
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * Copyright (c) 2021-2024, Arm Limited. All rights reserved.
+ */
+
+/dts-v1/;
+#include "morello.dtsi"
+
+/ {
+	model = "Arm Morello System Development Platform";
+	compatible = "arm,morello-sdp", "arm,morello";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	dpu_aclk: clock-350000000 {
+		/* 77.1 MHz derived from 24 MHz reference clock */
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <350000000>;
+		clock-output-names = "aclk";
+	};
+
+	dpu_pixel_clk: clock-148500000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <148500000>;
+		clock-output-names = "pxclk";
+	};
+
+	i2c0: i2c@1c0f0000 {
+		compatible = "cdns,i2c-r1p14";
+		reg = <0x0 0x1c0f0000 0x0 0x1000>;
+		interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&dpu_aclk>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		clock-frequency = <100000>;
+
+		hdmi_tx: hdmi-transmitter@70 {
+			compatible = "nxp,tda998x";
+			reg = <0x70>;
+			video-ports = <0x234501>;
+			port {
+				tda998x_0_input: endpoint {
+					remote-endpoint = <&dp_pl0_out0>;
+				};
+			};
+		};
+	};
+
+	dp0: display@2cc00000 {
+		compatible = "arm,mali-d32", "arm,mali-d71";
+		reg = <0x0 0x2cc00000 0x0 0x20000>;
+		interrupts = <0 69 4>;
+		clocks = <&dpu_aclk>;
+		clock-names = "aclk";
+		iommus = <&smmu_dp 0>, <&smmu_dp 1>, <&smmu_dp 2>, <&smmu_dp 3>,
+			 <&smmu_dp 8>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		pl0: pipeline@0 {
+			reg = <0>;
+			clocks = <&dpu_pixel_clk>;
+			clock-names = "pxclk";
+			port {
+				dp_pl0_out0: endpoint {
+					remote-endpoint = <&tda998x_0_input>;
+				};
+			};
+		};
+	};
+
+	smmu_ccix: iommu@4f000000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x0 0x4f000000 0x0 0x40000>;
+
+		interrupts = <GIC_SPI 228 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 230 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 41 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 229 IRQ_TYPE_EDGE_RISING>;
+		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
+		msi-parent = <&its1 0>;
+		#iommu-cells = <1>;
+		dma-coherent;
+	};
+
+	smmu_pcie: iommu@4f400000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x0 0x4f400000 0x0 0x40000>;
+
+		interrupts = <GIC_SPI 235 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 237 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 40 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 236 IRQ_TYPE_EDGE_RISING>;
+		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
+		msi-parent = <&its2 0>;
+		#iommu-cells = <1>;
+		dma-coherent;
+	};
+
+	pcie_ctlr: pcie@28c0000000 {
+		device_type = "pci";
+		compatible = "pci-host-ecam-generic";
+		reg = <0x28 0xC0000000 0 0x10000000>;
+		ranges = <0x01000000 0x00 0x00000000 0x00 0x6f000000 0x00 0x00800000>,
+				<0x02000000 0x00 0x60000000 0x00 0x60000000 0x00 0x0f000000>,
+				<0x42000000 0x09 0x00000000 0x09 0x00000000 0x1f 0xc0000000>;
+		bus-range = <0 255>;
+		linux,pci-domain = <0>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		dma-coherent;
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &gic 0 0 0 169 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &gic 0 0 0 170 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &gic 0 0 0 171 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &gic 0 0 0 172 IRQ_TYPE_LEVEL_HIGH>;
+		msi-map = <0 &its_pcie 0 0x10000>;
+		iommu-map = <0 &smmu_pcie 0 0x10000>;
+	};
+
+	ccix_pcie_ctlr: pcie@4fc0000000 {
+		device_type = "pci";
+		compatible = "pci-host-ecam-generic";
+		reg = <0x4f 0xC0000000 0 0x10000000>;
+		ranges = <0x01000000 0x00 0x00000000 0x00 0x7f000000 0x00 0x00800000>,
+				<0x02000000 0x00 0x70000000 0x00 0x70000000 0x00 0x0f000000>,
+				<0x42000000 0x30 0x00000000 0x30 0x00000000 0x1f 0xc0000000>;
+		linux,pci-domain = <1>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		dma-coherent;
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &gic 0 0 0 201 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &gic 0 0 0 202 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &gic 0 0 0 203 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &gic 0 0 0 204 IRQ_TYPE_LEVEL_HIGH>;
+		msi-map = <0 &its_ccix 0 0x10000>;
+		iommu-map = <0 &smmu_ccix 0 0x10000>;
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/arm/morello.dtsi b/arch/arm64/boot/dts/arm/morello.dtsi
new file mode 100644
index 000000000000..5bc1c725dc86
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/morello.dtsi
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * Copyright (c) 2020-2024, Arm Limited. All rights reserved.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	interrupt-parent = <&gic>;
+
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	soc_refclk50mhz: clock-50000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "apb_pclk";
+	};
+
+	soc_refclk85mhz: clock-85000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <85000000>;
+		clock-output-names = "iofpga:aclk";
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,rainier";
+			reg = <0x0 0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+			/* 4 ways set associative */
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <512>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <512>;
+			next-level-cache = <&l2_0>;
+			clocks = <&scmi_dvfs 0>;
+
+			l2_0: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				/* 8 ways set associative */
+				cache-size = <0x100000>;
+				cache-line-size = <64>;
+				cache-sets = <2048>;
+				cache-unified;
+				next-level-cache = <&l3_0>;
+			};
+		};
+
+		cpu1: cpu@100 {
+			compatible = "arm,rainier";
+			reg = <0x0 0x100>;
+			device_type = "cpu";
+			enable-method = "psci";
+			/* 4 ways set associative */
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <512>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <512>;
+			next-level-cache = <&l2_1>;
+			clocks = <&scmi_dvfs 0>;
+
+			l2_1: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				/* 8 ways set associative */
+				cache-size = <0x100000>;
+				cache-line-size = <64>;
+				cache-sets = <2048>;
+				cache-unified;
+				next-level-cache = <&l3_0>;
+			};
+		};
+
+		cpu2: cpu@10000 {
+			compatible = "arm,rainier";
+			reg = <0x0 0x10000>;
+			device_type = "cpu";
+			enable-method = "psci";
+			/* 4 ways set associative */
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <512>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <512>;
+			next-level-cache = <&l2_2>;
+			clocks = <&scmi_dvfs 1>;
+
+			l2_2: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				/* 8 ways set associative */
+				cache-size = <0x100000>;
+				cache-line-size = <64>;
+				cache-sets = <2048>;
+				cache-unified;
+				next-level-cache = <&l3_0>;
+			};
+		};
+
+		cpu3: cpu@10100 {
+			compatible = "arm,rainier";
+			reg = <0x0 0x10100>;
+			device_type = "cpu";
+			enable-method = "psci";
+			/* 4 ways set associative */
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <512>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <512>;
+			next-level-cache = <&l2_3>;
+			clocks = <&scmi_dvfs 1>;
+
+			l2_3: l2-cache {
+				compatible = "cache";
+				cache-level = <2>;
+				/* 8 ways set associative */
+				cache-size = <0x100000>;
+				cache-line-size = <64>;
+				cache-sets = <2048>;
+				cache-unified;
+				next-level-cache = <&l3_0>;
+			};
+		};
+
+		l3_0: l3-cache {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-size = <0x100000>;
+			cache-unified;
+		};
+	};
+
+	firmware {
+		interrupt-parent = <&gic>;
+
+		scmi {
+			compatible = "arm,scmi";
+			mbox-names = "tx", "rx";
+			mboxes = <&mailbox 1 0>, <&mailbox 1 1>;
+			shmem = <&cpu_scp_hpri0>, <&cpu_scp_hpri1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			scmi_dvfs: protocol@13 {
+				reg = <0x13>;
+				#clock-cells = <1>;
+			};
+
+			scmi_clk: protocol@14 {
+				reg = <0x14>;
+				#clock-cells = <1>;
+			};
+		};
+	};
+
+	/* The first bank of memory, memory map is actually provided by UEFI. */
+	memory@80000000 {
+		device_type = "memory";
+		/* [0x80000000-0xffffffff] */
+		reg = <0x00000000 0x80000000 0x0 0x7f000000>;
+	};
+
+	memory@8080000000 {
+		device_type = "memory";
+		/* [0x8080000000-0x83f7ffffff] */
+		reg = <0x00000080 0x80000000 0x3 0x78000000>;
+	};
+
+	pmu {
+		compatible = "arm,rainier-pmu";
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		secure-firmware@ff000000 {
+			reg = <0x0 0xff000000 0x0 0x01000000>;
+			no-map;
+		};
+	};
+
+	spe-pmu {
+		compatible = "arm,statistical-profiling-extension-v1";
+		interrupts = <GIC_PPI 5 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	soc: soc {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		interrupt-parent = <&gic>;
+		ranges;
+
+		uart0: serial@2a400000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x0 0x2a400000 0x0 0x1000>;
+			interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&soc_refclk50mhz>, <&soc_refclk50mhz>;
+			clock-names = "uartclk", "apb_pclk";
+
+			status = "disabled";
+		};
+
+		gic: interrupt-controller@30000000 {
+			compatible = "arm,gic-v3";
+			reg = <0x0 0x30000000 0x0 0x10000>,	/* GICD */
+			      <0x0 0x300c0000 0x0 0x80000>;	/* GICR */
+
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+
+			#interrupt-cells = <3>;
+			interrupt-controller;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			its1: msi-controller@30040000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0x0 0x30040000 0x0 0x20000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+			};
+
+			its2: msi-controller@30060000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0x0 0x30060000 0x0 0x20000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+			};
+
+			its_ccix: msi-controller@30080000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0x0 0x30080000 0x0 0x20000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+			};
+
+			its_pcie: msi-controller@300a0000 {
+				compatible = "arm,gic-v3-its";
+				reg = <0x0 0x300a0000 0x0 0x20000>;
+
+				msi-controller;
+				#msi-cells = <1>;
+			};
+		};
+
+		smmu_dp: iommu@2ce00000 {
+			compatible = "arm,smmu-v3";
+			reg = <0x0 0x2ce00000 0x0 0x40000>;
+
+			interrupts = <GIC_SPI 76 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 80 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 78 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "eventq", "gerror", "cmdq-sync";
+			#iommu-cells = <1>;
+		};
+
+		mailbox: mhu@45000000 {
+			compatible = "arm,mhu-doorbell", "arm,primecell";
+			reg = <0x0 0x45000000 0x0 0x1000>;
+
+			interrupts = <GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 316 IRQ_TYPE_LEVEL_HIGH>;
+			#mbox-cells = <2>;
+			clocks = <&soc_refclk50mhz>;
+			clock-names = "apb_pclk";
+		};
+
+		sram: sram@6000000 {
+			compatible = "mmio-sram";
+			reg = <0x0 0x06000000 0x0 0x8000>;
+			ranges = <0 0x0 0x06000000 0x8000>;
+
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			cpu_scp_hpri0: scp-sram@0 {
+				compatible = "arm,scmi-shmem";
+				reg = <0x0 0x80>;
+			};
+
+			cpu_scp_hpri1: scp-sram@80 {
+				compatible = "arm,scmi-shmem";
+				reg = <0x80 0x80>;
+			};
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
index 689c82b7f596..9e610a89a337 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
@@ -227,7 +227,7 @@
 			interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clk_uart>, <&clk_vpu>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/exynos/exynos8895-dreamlte.dts b/arch/arm64/boot/dts/exynos/exynos8895-dreamlte.dts
index 3a376ab2bb9e..61e064af3337 100644
--- a/arch/arm64/boot/dts/exynos/exynos8895-dreamlte.dts
+++ b/arch/arm64/boot/dts/exynos/exynos8895-dreamlte.dts
@@ -10,12 +10,17 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/soc/samsung,exynos-usi.h>
 
 / {
 	model = "Samsung Galaxy S8 (SM-G950F)";
 	compatible = "samsung,dreamlte", "samsung,exynos8895";
 	chassis-type = "handset";
 
+	aliases {
+		mmc0 = &mmc;
+	};
+
 	chosen {
 		#address-cells = <2>;
 		#size-cells = <1>;
@@ -89,12 +94,60 @@
 			wakeup-source;
 		};
 	};
+
+	/* TODO: Remove once PMIC is implemented  */
+	reg_placeholder: regulator-0 {
+		compatible = "regulator-fixed";
+		regulator-name = "reg-placeholder";
+	};
+};
+
+&hsi2c_23 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	touchscreen@48 {
+		compatible = "samsung,s6sy761";
+		reg = <0x48>;
+
+		/* TODO: Update once PMIC is implemented */
+		avdd-supply = <&reg_placeholder>;
+		vdd-supply = <&reg_placeholder>;
+
+		interrupt-parent = <&gpa1>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+
+		pinctrl-0 = <&ts_int>;
+		pinctrl-names = "default";
+	};
 };
 
 &oscclk {
 	clock-frequency = <26000000>;
 };
 
+&mmc {
+	pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_bus1 &sd2_bus4 &sd2_cd>;
+	pinctrl-names = "default";
+
+	bus-width = <4>;
+	card-detect-delay = <200>;
+	cd-gpios = <&gpa1 5 GPIO_ACTIVE_LOW>;
+	clock-frequency = <800000000>;
+	disable-wp;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+
+	/* TODO: Add regulators once PMIC is implemented */
+
+	samsung,dw-mshc-ciu-div = <3>;
+	samsung,dw-mshc-ddr-timing = <1 2>;
+	samsung,dw-mshc-sdr-timing = <0 3>;
+
+	status = "okay";
+};
+
 &pinctrl_alive {
 	key_power: key-power-pins {
 		samsung,pins = "gpa2-4";
@@ -123,4 +176,23 @@
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
 		samsung,pin-drv = <EXYNOS7_PIN_DRV_LV1>;
 	};
+
+	sd2_cd: sd2-cd-pins {
+		samsung,pins = "gpa1-5";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_UP>;
+		samsung,pin-drv = <EXYNOS7_PIN_DRV_LV4>;
+	};
+
+	ts_int: ts-int-pins {
+		samsung,pins = "gpa1-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_EINT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+		samsung,pin-drv = <EXYNOS7_PIN_DRV_LV1>;
+	};
+};
+
+&usi9 {
+	samsung,mode = <USI_MODE_I2C0_1>;
+	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/exynos/exynos8895.dtsi b/arch/arm64/boot/dts/exynos/exynos8895.dtsi
index 36657abfc615..f92d2a8a20a2 100644
--- a/arch/arm64/boot/dts/exynos/exynos8895.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos8895.dtsi
@@ -26,30 +26,6 @@
 		pinctrl7 = &pinctrl_peric1;
 	};
 
-	arm-a53-pmu {
-		compatible = "arm,cortex-a53-pmu";
-		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-affinity = <&cpu0>,
-				     <&cpu1>,
-				     <&cpu2>,
-				     <&cpu3>;
-	};
-
-	mongoose-m2-pmu {
-		compatible = "samsung,mongoose-pmu";
-		interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-affinity = <&cpu4>,
-				     <&cpu5>,
-				     <&cpu6>,
-				     <&cpu7>;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -149,6 +125,30 @@
 		clock-output-names = "oscclk";
 	};
 
+	pmu-a53 {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>,
+				     <&cpu2>,
+				     <&cpu3>;
+	};
+
+	pmu-mongoose-m2 {
+		compatible = "samsung,mongoose-pmu";
+		interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu4>,
+				     <&cpu5>,
+				     <&cpu6>,
+				     <&cpu7>;
+	};
+
 	psci {
 		compatible = "arm,psci";
 		method = "smc";
@@ -228,6 +228,12 @@
 				      "usi1", "usi2", "usi3";
 		};
 
+		syscon_peric0: syscon@10420000 {
+			compatible = "samsung,exynos8895-peric0-sysreg", "syscon";
+			reg = <0x10420000 0x2000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_SYSREG_PERIC0_PCLK>;
+		};
+
 		serial_0: serial@10430000 {
 			compatible = "samsung,exynos8895-uart";
 			reg = <0x10430000 0x100>;
@@ -241,6 +247,254 @@
 			status = "disabled";
 		};
 
+		usi0: usi@10440000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10440000 0x11000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_PCLK>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric0 0x1000>;
+			status = "disabled";
+
+			hsi2c_5: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 364 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c5_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_2: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 366 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart2_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_2: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi2_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_6: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI00_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 365 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c6_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi1: usi@10460000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10460000 0x11000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_PCLK>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric0 0x1004>;
+			status = "disabled";
+
+			hsi2c_7: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 368 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c5_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_3: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart3_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_3: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi3_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_8: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI01_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c8_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi2: usi@10480000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10480000 0x11000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_PCLK>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric0 0x1008>;
+			status = "disabled";
+
+			hsi2c_9: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c9_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_4: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart4_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_4: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi4_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_10: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI02_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c10_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi3: usi@104a0000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x104a0000 0x11000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_PCLK>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric0 0x100c>;
+			status = "disabled";
+
+			hsi2c_11: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c11_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_5: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart5_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_5: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_PCLK>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi5_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_12: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_USI03_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c12_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
 		pinctrl_peric0: pinctrl@104d0000 {
 			compatible = "samsung,exynos8895-pinctrl";
 			reg = <0x104d0000 0x1000>;
@@ -273,6 +527,12 @@
 				      "usi10", "usi11", "usi12", "usi13";
 		};
 
+		syscon_peric1: syscon@10820000 {
+			compatible = "samsung,exynos8895-peric1-sysreg", "syscon";
+			reg = <0x10820000 0x2000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_SYSREG_PERIC1_PCLK>;
+		};
+
 		serial_1: serial@10830000 {
 			compatible = "samsung,exynos8895-uart";
 			reg = <0x10830000 0x100>;
@@ -286,6 +546,626 @@
 			status = "disabled";
 		};
 
+		usi4: usi@10840000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10840000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1008>;
+			status = "disabled";
+
+			hsi2c_13: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 390 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c13_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_6: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 392 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart6_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_6: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 393 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi6_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_14: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI04_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 391 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c14_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi5: usi@10860000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10860000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x100c>;
+			status = "disabled";
+
+			hsi2c_15: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 394 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c15_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_7: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 396 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart7_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_7: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 397 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi7_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_16: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI05_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c16_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi6: usi@10880000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10880000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1010>;
+			status = "disabled";
+
+			hsi2c_17: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 398 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c17_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_8: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart8_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_8: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 401 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi8_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_18: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI06_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 399 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c18_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi7: usi@108a0000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x108a0000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1014>;
+			status = "disabled";
+
+			hsi2c_19: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 402 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c19_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_9: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 404 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart9_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_9: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 405 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi9_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_20: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI07_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 403 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c20_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi8: usi@108c0000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x108c0000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1018>;
+			status = "disabled";
+
+			hsi2c_21: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c21_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_10: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart10_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_10: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0x0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi10_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_22: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI08_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c22_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi9: usi@108e0000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x108e0000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x101c>;
+			status = "disabled";
+
+			hsi2c_23: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 410 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c23_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_11: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 412 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart11_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_11: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 413 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi11_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_24: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI09_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 411 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c24_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi10: usi@10900000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10900000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1020>;
+			status = "disabled";
+
+			hsi2c_25: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 414 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c25_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_12: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 416 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart12_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_12: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 417 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi12_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_26: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI10_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 415 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c26_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi11: usi@10920000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10920000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1024>;
+			status = "disabled";
+
+			hsi2c_27: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 418 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c27_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_13: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 420 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart13_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_13: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi13_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_28: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI11_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c28_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi12: usi@10940000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10940000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x1028>;
+			status = "disabled";
+
+			hsi2c_29: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c29_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_14: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart14_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_14: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi14_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_30: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI12_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c30_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
+		usi13: usi@10960000 {
+			compatible = "samsung,exynos8895-usi";
+			ranges = <0x0 0x10960000 0x11000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_PCLK>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_SCLK_USI>;
+			clock-names = "pclk", "ipclk";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			samsung,sysreg = <&syscon_peric1 0x102c>;
+			status = "disabled";
+
+			hsi2c_31: i2c@0 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x0 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c31_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+
+			serial_15: serial@0 {
+				compatible = "samsung,exynos8895-uart";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_SCLK_USI>;
+				clock-names = "uart", "clk_uart_baud0";
+				interrupts = <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&uart15_bus>;
+				pinctrl-names = "default";
+				samsung,uart-fifosize = <64>;
+				status = "disabled";
+			};
+
+			spi_15: spi@0 {
+				compatible = "samsung,exynos8895-spi",
+					     "samsung,exynos850-spi";
+				reg = <0 0x100>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_PCLK>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_SCLK_USI>;
+				clock-names = "spi", "spi_busclk0";
+				interrupts = <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi15_bus>;
+				pinctrl-names = "default";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+
+			hsi2c_32: i2c@10000 {
+				compatible = "samsung,exynos8895-hsi2c";
+				reg = <0x10000 0x1000>;
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_USI13_I_PCLK>;
+				clock-names = "hsi2c";
+				interrupts = <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&hsi2c32_bus>;
+				pinctrl-names = "default";
+				status = "disabled";
+			};
+		};
+
 		pinctrl_peric1: pinctrl@10980000 {
 			compatible = "samsung,exynos8895-pinctrl";
 			reg = <0x10980000 0x1000>;
@@ -380,6 +1260,12 @@
 				      "ufs", "usbdrd30";
 		};
 
+		syscon_fsys0: syscon@11020000 {
+			compatible = "samsung,exynos8895-fsys0-sysreg", "syscon";
+			reg = <0x11020000 0x2000>;
+			clocks = <&cmu_fsys0 CLK_GOUT_FSYS0_SYSREG_FSYS0_PCLK>;
+		};
+
 		pinctrl_fsys0: pinctrl@11050000 {
 			compatible = "samsung,exynos8895-pinctrl";
 			reg = <0x11050000 0x1000>;
@@ -398,12 +1284,34 @@
 			clock-names = "oscclk", "bus", "pcie", "ufs", "mmc";
 		};
 
+		syscon_fsys1: syscon@11420000 {
+			compatible = "samsung,exynos8895-fsys1-sysreg", "syscon";
+			reg = <0x11420000 0x2000>;
+			clocks = <&cmu_fsys1 CLK_GOUT_FSYS1_SYSREG_FSYS1_PCLK>;
+		};
+
 		pinctrl_fsys1: pinctrl@11430000 {
 			compatible = "samsung,exynos8895-pinctrl";
 			reg = <0x11430000 0x1000>;
 			interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		mmc: mmc@11500000 {
+			compatible = "samsung,exynos8895-dw-mshc-smu",
+				     "samsung,exynos7-dw-mshc-smu";
+			reg = <0x11500000 0x2000>;
+			assigned-clocks = <&cmu_top CLK_MOUT_CMU_FSYS1_MMC_CARD>;
+			assigned-clock-parents = <&cmu_top CLK_FOUT_SHARED4_PLL>;
+			clocks = <&cmu_fsys1 CLK_GOUT_FSYS1_MMC_CARD_I_ACLK>,
+				 <&cmu_fsys1 CLK_GOUT_FSYS1_MMC_CARD_SDCLKIN>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <64>;
+			interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		pinctrl_abox: pinctrl@13e60000 {
 			compatible = "samsung,exynos8895-pinctrl";
 			reg = <0x13e60000 0x1000>;
diff --git a/arch/arm64/boot/dts/exynos/exynos990.dtsi b/arch/arm64/boot/dts/exynos/exynos990.dtsi
index 9d017dbed952..dd7f99f51a75 100644
--- a/arch/arm64/boot/dts/exynos/exynos990.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos990.dtsi
@@ -25,37 +25,6 @@
 		pinctrl6 = &pinctrl_vts;
 	};
 
-	arm-a55-pmu {
-		compatible = "arm,cortex-a55-pmu";
-		interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
-
-		interrupt-affinity = <&cpu0>,
-				     <&cpu1>,
-				     <&cpu2>,
-				     <&cpu3>;
-	};
-
-	arm-a76-pmu {
-		compatible = "arm,cortex-a76-pmu";
-		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
-
-		interrupt-affinity = <&cpu4>,
-				     <&cpu5>;
-	};
-
-	mongoose-m5-pmu {
-		compatible = "samsung,mongoose-pmu";
-		interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>;
-
-		interrupt-affinity = <&cpu6>,
-				     <&cpu7>;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -163,6 +132,37 @@
 		clock-output-names = "oscclk";
 	};
 
+	pmu-a55 {
+		compatible = "arm,cortex-a55-pmu";
+		interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
+
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>,
+				     <&cpu2>,
+				     <&cpu3>;
+	};
+
+	pmu-a76 {
+		compatible = "arm,cortex-a76-pmu";
+		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
+
+		interrupt-affinity = <&cpu4>,
+				     <&cpu5>;
+	};
+
+	pmu-mongoose-m5 {
+		compatible = "samsung,mongoose-pmu";
+		interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>;
+
+		interrupt-affinity = <&cpu6>,
+				     <&cpu7>;
+	};
+
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "hvc";
@@ -181,6 +181,36 @@
 			reg = <0x10000000 0x100>;
 		};
 
+		cmu_peris: clock-controller@10020000 {
+			compatible = "samsung,exynos990-cmu-peris";
+			reg = <0x10020000 0x8000>;
+			#clock-cells = <1>;
+
+			clocks = <&oscclk>,
+				 <&cmu_top CLK_DOUT_CMU_PERIS_BUS>;
+			clock-names = "oscclk", "bus";
+		};
+
+		timer@10040000 {
+			compatible = "samsung,exynos990-mct",
+				     "samsung,exynos4210-mct";
+			reg = <0x10040000 0x800>;
+			clocks = <&oscclk>, <&cmu_peris CLK_GOUT_PERIS_MCT_PCLK>;
+			clock-names = "fin_pll", "mct";
+			interrupts = <GIC_SPI 466 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 467 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 468 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 471 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 476 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 477 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
 		gic: interrupt-controller@10101000 {
 			compatible = "arm,gic-400";
 			reg = <0x10101000 0x1000>,
diff --git a/arch/arm64/boot/dts/exynos/exynosautov920.dtsi b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi
index eb446cdc4ab6..fc6ac531d597 100644
--- a/arch/arm64/boot/dts/exynos/exynosautov920.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynosautov920.dtsi
@@ -89,6 +89,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x0>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl0>;
 		};
 
 		cpu1: cpu@100 {
@@ -96,6 +103,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x100>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl0>;
 		};
 
 		cpu2: cpu@200 {
@@ -103,6 +117,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x200>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl0>;
 		};
 
 		cpu3: cpu@300 {
@@ -110,6 +131,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x300>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl0>;
 		};
 
 		cpu4: cpu@10000 {
@@ -117,6 +145,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x10000>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl1>;
 		};
 
 		cpu5: cpu@10100 {
@@ -124,6 +159,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x10100>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl1>;
 		};
 
 		cpu6: cpu@10200 {
@@ -131,6 +173,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x10200>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl1>;
 		};
 
 		cpu7: cpu@10300 {
@@ -138,6 +187,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x10300>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl1>;
 		};
 
 		cpu8: cpu@20000 {
@@ -145,6 +201,13 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x20000>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl2>;
 		};
 
 		cpu9: cpu@20100 {
@@ -152,6 +215,70 @@
 			compatible = "arm,cortex-a78ae";
 			reg = <0x0 0x20100>;
 			enable-method = "psci";
+			i-cache-size = <0x10000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x10000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_cl2>;
+		};
+
+		l2_cache_cl0: l2-cache0 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+			cache-size = <0x40000>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+			next-level-cache = <&l3_cache_cl0>;
+		};
+
+		l2_cache_cl1: l2-cache1 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+			cache-size = <0x40000>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+			next-level-cache = <&l3_cache_cl1>;
+		};
+
+		l2_cache_cl2: l2-cache2 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+			cache-size = <0x40000>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+			next-level-cache = <&l3_cache_cl2>;
+		};
+
+		l3_cache_cl0: l3-cache0 {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-unified;
+			cache-size = <0x200000>;/* 2MB L3 cache for cpu cluster-0 */
+			cache-line-size = <64>;
+			cache-sets = <2048>;
+		};
+
+		l3_cache_cl1: l3-cache1 {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-unified;
+			cache-size = <0x200000>;/* 2MB L3 cache for cpu cluster-1 */
+			cache-line-size = <64>;
+			cache-sets = <2048>;
+		};
+
+		l3_cache_cl2: l3-cache2 {
+			compatible = "cache";
+			cache-level = <3>;
+			cache-unified;
+			cache-size = <0x100000>;/* 1MB L3 cache for cpu cluster-2 */
+			cache-line-size = <64>;
+			cache-sets = <1365>;
 		};
 	};
 
@@ -440,6 +567,17 @@
 			interrupts = <GIC_SPI 603 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		ufs_0_phy: phy@16e04000 {
+			compatible = "samsung,exynosautov920-ufs-phy";
+			reg = <0x16e04000 0x4000>;
+			reg-names = "phy-pma";
+			clocks = <&xtcxo>;
+			clock-names = "ref_clk";
+			samsung,pmu-syscon = <&pmu_system_controller>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
 		pinctrl_aud: pinctrl@1a460000 {
 			compatible = "samsung,exynosautov920-pinctrl";
 			reg = <0x1a460000 0x10000>;
diff --git a/arch/arm64/boot/dts/exynos/google/Makefile b/arch/arm64/boot/dts/exynos/google/Makefile
index 0a6d5e1fe4ee..7385f82b03c9 100644
--- a/arch/arm64/boot/dts/exynos/google/Makefile
+++ b/arch/arm64/boot/dts/exynos/google/Makefile
@@ -2,3 +2,4 @@
 
 dtb-$(CONFIG_ARCH_EXYNOS) += \
 	gs101-oriole.dtb \
+	gs101-raven.dtb
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
index e58881c61d53..8df42bedbc03 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
+++ b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
@@ -8,273 +8,22 @@
 
 /dts-v1/;
 
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/usb/pd.h>
-#include "gs101-pinctrl.h"
-#include "gs101.dtsi"
+#include "gs101-pixel-common.dtsi"
 
 / {
 	model = "Oriole";
 	compatible = "google,gs101-oriole", "google,gs101";
-
-	aliases {
-		serial0 = &serial_0;
-	};
-
-	chosen {
-		/* Bootloader expects bootargs specified otherwise it crashes */
-		bootargs = "";
-		stdout-path = &serial_0;
-	};
-
-	gpio-keys {
-		compatible = "gpio-keys";
-		pinctrl-0 = <&key_voldown>, <&key_volup>, <&key_power>;
-		pinctrl-names = "default";
-
-		button-vol-down {
-			label = "KEY_VOLUMEDOWN";
-			linux,code = <KEY_VOLUMEDOWN>;
-			gpios = <&gpa7 3 GPIO_ACTIVE_LOW>;
-			wakeup-source;
-		};
-
-		button-vol-up {
-			label = "KEY_VOLUMEUP";
-			linux,code = <KEY_VOLUMEUP>;
-			gpios = <&gpa8 1 GPIO_ACTIVE_LOW>;
-			wakeup-source;
-		};
-
-		button-power {
-			label = "KEY_POWER";
-			linux,code = <KEY_POWER>;
-			gpios = <&gpa10 1 GPIO_ACTIVE_LOW>;
-			wakeup-source;
-		};
-	};
-
-	/* TODO: Remove this once PMIC is implemented  */
-	reg_placeholder: regulator-0 {
-		compatible = "regulator-fixed";
-		regulator-name = "placeholder_reg";
-	};
-
-	/* TODO: Remove this once S2MPG11 slave PMIC is implemented  */
-	ufs_0_fixed_vcc_reg: regulator-1 {
-		compatible = "regulator-fixed";
-		regulator-name = "ufs-vcc";
-		gpio = <&gpp0 1 GPIO_ACTIVE_HIGH>;
-		regulator-boot-on;
-		enable-active-high;
-	};
-};
-
-&ext_24_5m {
-	clock-frequency = <24576000>;
-};
-
-&ext_200m {
-	clock-frequency = <200000000>;
-};
-
-&hsi2c_8 {
-	status = "okay";
-
-	eeprom: eeprom@50 {
-		compatible = "atmel,24c08";
-		reg = <0x50>;
-	};
-};
-
-&hsi2c_12 {
-	status = "okay";
-	/* TODO: add the devices once drivers exist */
-
-	usb-typec@25 {
-		compatible = "maxim,max77759-tcpci", "maxim,max33359";
-		reg = <0x25>;
-		interrupts-extended = <&gpa8 2 IRQ_TYPE_LEVEL_LOW>;
-		pinctrl-0 = <&typec_int>;
-		pinctrl-names = "default";
-
-		connector {
-			compatible = "usb-c-connector";
-			label = "USB-C";
-			data-role = "dual";
-			power-role = "dual";
-			self-powered;
-			try-power-role = "sink";
-			op-sink-microwatt = <2600000>;
-			slow-charger-loop;
-			/*
-			 * max77759 operating in reverse boost mode (0xA) can
-			 * source up to 1.5A while extboost can only do ~1A.
-			 * Since extboost is the primary path, advertise 900mA.
-			 */
-			source-pdos = <PDO_FIXED(5000, 900,
-						 (PDO_FIXED_SUSPEND
-						  | PDO_FIXED_USB_COMM
-						  | PDO_FIXED_DATA_SWAP
-						  | PDO_FIXED_DUAL_ROLE))>;
-			sink-pdos = <PDO_FIXED(5000, 3000,
-					       (PDO_FIXED_DATA_SWAP
-						| PDO_FIXED_USB_COMM
-						| PDO_FIXED_HIGHER_CAP
-						| PDO_FIXED_DUAL_ROLE))
-				     PDO_FIXED(9000, 2200, 0)
-				     PDO_PPS_APDO(5000, 11000, 3000)>;
-			sink-vdos = <VDO_IDH(1, 1, IDH_PTYPE_PERIPH, 0,
-					     IDH_PTYPE_DFP_HOST, 2, 0x18d1)
-				     VDO_CERT(0x0)
-				     VDO_PRODUCT(0x4ee1, 0x0)
-				     VDO_UFP(UFP_VDO_VER1_2,
-					     (DEV_USB2_CAPABLE
-					      | DEV_USB3_CAPABLE),
-					     UFP_RECEPTACLE, 0,
-					     AMA_VCONN_NOT_REQ, 0,
-					     UFP_ALTMODE_NOT_SUPP,
-					     UFP_USB32_GEN1)
-				     /* padding */ 0
-				     VDO_DFP(DFP_VDO_VER1_1,
-					     (HOST_USB2_CAPABLE
-					      | HOST_USB3_CAPABLE),
-					     DFP_RECEPTACLE, 0)>;
-			sink-vdos-v1 = <VDO_IDH(1, 1, IDH_PTYPE_PERIPH, 0,
-						0, 0, 0x18d1)
-					VDO_CERT(0x0)
-					VDO_PRODUCT(0x4ee1, 0x0)>;
-			/*
-			 * Until bootloader is updated to set those two when
-			 * console is enabled, we disable PD here.
-			 */
-			pd-disable;
-			typec-power-opmode = "default";
-
-			ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				port@0 {
-					reg = <0>;
-
-					usbc0_orien_sw: endpoint {
-						remote-endpoint = <&usbdrd31_phy_orien_switch>;
-					};
-				};
-
-				port@1 {
-					reg = <1>;
-
-					usbc0_role_sw: endpoint {
-						remote-endpoint = <&usbdrd31_dwc3_role_switch>;
-					};
-				};
-			};
-		};
-	};
-};
-
-&pinctrl_far_alive {
-	key_voldown: key-voldown-pins {
-		samsung,pins = "gpa7-3";
-		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
-		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
-		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
-	};
-
-	key_volup: key-volup-pins {
-		samsung,pins = "gpa8-1";
-		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
-		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
-		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
-	};
-
-	typec_int: typec-int-pins {
-		samsung,pins = "gpa8-2";
-		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
-		samsung,pin-pud = <GS101_PIN_PULL_UP>;
-		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
-	};
-};
-
-&pinctrl_gpio_alive {
-	key_power: key-power-pins {
-		samsung,pins = "gpa10-1";
-		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
-		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
-		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
-	};
-};
-
-&serial_0 {
-	status = "okay";
-};
-
-&ufs_0 {
-	status = "okay";
-	vcc-supply = <&ufs_0_fixed_vcc_reg>;
-};
-
-&ufs_0_phy {
-	status = "okay";
-};
-
-&usbdrd31 {
-	vdd10-supply = <&reg_placeholder>;
-	vdd33-supply = <&reg_placeholder>;
-	status = "okay";
-};
-
-&usbdrd31_dwc3 {
-	dr_mode = "otg";
-	usb-role-switch;
-	role-switch-default-mode = "peripheral";
-	maximum-speed = "super-speed-plus";
-	status = "okay";
-
-	port {
-		usbdrd31_dwc3_role_switch: endpoint {
-			remote-endpoint = <&usbc0_role_sw>;
-		};
-	};
-};
-
-&usbdrd31_phy {
-	orientation-switch;
-	/* TODO: Update these once PMIC is implemented */
-	pll-supply = <&reg_placeholder>;
-	dvdd-usb20-supply = <&reg_placeholder>;
-	vddh-usb20-supply = <&reg_placeholder>;
-	vdd33-usb20-supply = <&reg_placeholder>;
-	vdda-usbdp-supply = <&reg_placeholder>;
-	vddh-usbdp-supply = <&reg_placeholder>;
-	status = "okay";
-
-	port {
-		usbdrd31_phy_orien_switch: endpoint {
-			remote-endpoint = <&usbc0_orien_sw>;
-		};
-	};
-};
-
-&usi_uart {
-	samsung,clkreq-on; /* needed for UART mode */
-	status = "okay";
-};
-
-&usi8 {
-	samsung,mode = <USI_V2_I2C>;
-	status = "okay";
 };
 
-&usi12 {
-	samsung,mode = <USI_V2_I2C>;
+&cont_splash_mem {
+	reg = <0x0 0xfac00000 (1080 * 2400 * 4)>;
 	status = "okay";
 };
 
-&watchdog_cl0 {
-	timeout-sec = <30>;
+&framebuffer0 {
+	width = <1080>;
+	height = <2400>;
+	stride = <(1080 * 4)>;
+	format = "a8r8g8b8";
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-pixel-common.dtsi b/arch/arm64/boot/dts/exynos/google/gs101-pixel-common.dtsi
new file mode 100644
index 000000000000..b25230495c64
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101-pixel-common.dtsi
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Device Tree nodes common for all GS101-based Pixel
+ *
+ * Copyright 2021-2023 Google LLC
+ * Copyright 2023 Linaro Ltd - <peter.griffin@linaro.org>
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/usb/pd.h>
+#include "gs101-pinctrl.h"
+#include "gs101.dtsi"
+
+/ {
+	aliases {
+		serial0 = &serial_0;
+	};
+
+	chosen {
+		/* Bootloader expects bootargs specified otherwise it crashes */
+		bootargs = "";
+		stdout-path = &serial_0;
+
+		/* Use display framebuffer as setup by bootloader */
+		framebuffer0: framebuffer-0 {
+			compatible = "simple-framebuffer";
+			memory-region = <&cont_splash_mem>;
+			/* format properties to be added by actual board */
+			status = "disabled";
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-0 = <&key_voldown>, <&key_volup>, <&key_power>;
+		pinctrl-names = "default";
+
+		button-vol-down {
+			label = "KEY_VOLUMEDOWN";
+			linux,code = <KEY_VOLUMEDOWN>;
+			gpios = <&gpa7 3 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		button-vol-up {
+			label = "KEY_VOLUMEUP";
+			linux,code = <KEY_VOLUMEUP>;
+			gpios = <&gpa8 1 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		button-power {
+			label = "KEY_POWER";
+			linux,code = <KEY_POWER>;
+			gpios = <&gpa10 1 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+	};
+
+	/* TODO: Remove this once PMIC is implemented  */
+	reg_placeholder: regulator-0 {
+		compatible = "regulator-fixed";
+		regulator-name = "placeholder_reg";
+	};
+
+	/* TODO: Remove this once S2MPG11 slave PMIC is implemented  */
+	ufs_0_fixed_vcc_reg: regulator-1 {
+		compatible = "regulator-fixed";
+		regulator-name = "ufs-vcc";
+		gpio = <&gpp0 1 GPIO_ACTIVE_HIGH>;
+		regulator-boot-on;
+		enable-active-high;
+	};
+
+	reserved-memory {
+		cont_splash_mem: splash@fac00000 {
+			/* size to be updated by actual board */
+			reg = <0x0 0xfac00000 0x0>;
+			no-map;
+			status = "disabled";
+		};
+	};
+};
+
+&ext_24_5m {
+	clock-frequency = <24576000>;
+};
+
+&ext_200m {
+	clock-frequency = <200000000>;
+};
+
+&hsi2c_8 {
+	status = "okay";
+
+	eeprom: eeprom@50 {
+		compatible = "atmel,24c08";
+		reg = <0x50>;
+	};
+};
+
+&hsi2c_12 {
+	status = "okay";
+	/* TODO: add the devices once drivers exist */
+
+	usb-typec@25 {
+		compatible = "maxim,max77759-tcpci", "maxim,max33359";
+		reg = <0x25>;
+		interrupts-extended = <&gpa8 2 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-0 = <&typec_int>;
+		pinctrl-names = "default";
+
+		connector {
+			compatible = "usb-c-connector";
+			label = "USB-C";
+			data-role = "dual";
+			power-role = "dual";
+			self-powered;
+			try-power-role = "sink";
+			op-sink-microwatt = <2600000>;
+			slow-charger-loop;
+			/*
+			 * max77759 operating in reverse boost mode (0xA) can
+			 * source up to 1.5A while extboost can only do ~1A.
+			 * Since extboost is the primary path, advertise 900mA.
+			 */
+			source-pdos = <PDO_FIXED(5000, 900,
+						 (PDO_FIXED_SUSPEND
+						  | PDO_FIXED_USB_COMM
+						  | PDO_FIXED_DATA_SWAP
+						  | PDO_FIXED_DUAL_ROLE))>;
+			sink-pdos = <PDO_FIXED(5000, 3000,
+					       (PDO_FIXED_DATA_SWAP
+						| PDO_FIXED_USB_COMM
+						| PDO_FIXED_HIGHER_CAP
+						| PDO_FIXED_DUAL_ROLE))
+				     PDO_FIXED(9000, 2200, 0)
+				     PDO_PPS_APDO(5000, 11000, 3000)>;
+			sink-vdos = <VDO_IDH(1, 1, IDH_PTYPE_PERIPH, 0,
+					     IDH_PTYPE_DFP_HOST, 2, 0x18d1)
+				     VDO_CERT(0x0)
+				     VDO_PRODUCT(0x4ee1, 0x0)
+				     VDO_UFP(UFP_VDO_VER1_2,
+					     (DEV_USB2_CAPABLE
+					      | DEV_USB3_CAPABLE),
+					     UFP_RECEPTACLE, 0,
+					     AMA_VCONN_NOT_REQ, 0,
+					     UFP_ALTMODE_NOT_SUPP,
+					     UFP_USB32_GEN1)
+				     /* padding */ 0
+				     VDO_DFP(DFP_VDO_VER1_1,
+					     (HOST_USB2_CAPABLE
+					      | HOST_USB3_CAPABLE),
+					     DFP_RECEPTACLE, 0)>;
+			sink-vdos-v1 = <VDO_IDH(1, 1, IDH_PTYPE_PERIPH, 0,
+						0, 0, 0x18d1)
+					VDO_CERT(0x0)
+					VDO_PRODUCT(0x4ee1, 0x0)>;
+			/*
+			 * Until bootloader is updated to set those two when
+			 * console is enabled, we disable PD here.
+			 */
+			pd-disable;
+			typec-power-opmode = "default";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usbc0_orien_sw: endpoint {
+						remote-endpoint = <&usbdrd31_phy_orien_switch>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usbc0_role_sw: endpoint {
+						remote-endpoint = <&usbdrd31_dwc3_role_switch>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&pinctrl_far_alive {
+	key_voldown: key-voldown-pins {
+		samsung,pins = "gpa7-3";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	key_volup: key-volup-pins {
+		samsung,pins = "gpa8-1";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+
+	typec_int: typec-int-pins {
+		samsung,pins = "gpa8-2";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_UP>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&pinctrl_gpio_alive {
+	key_power: key-power-pins {
+		samsung,pins = "gpa10-1";
+		samsung,pin-function = <GS101_PIN_FUNC_EINT>;
+		samsung,pin-pud = <GS101_PIN_PULL_NONE>;
+		samsung,pin-drv = <GS101_PIN_DRV_2_5_MA>;
+	};
+};
+
+&serial_0 {
+	status = "okay";
+};
+
+&ufs_0 {
+	status = "okay";
+	vcc-supply = <&ufs_0_fixed_vcc_reg>;
+};
+
+&ufs_0_phy {
+	status = "okay";
+};
+
+&usbdrd31 {
+	vdd10-supply = <&reg_placeholder>;
+	vdd33-supply = <&reg_placeholder>;
+	status = "okay";
+};
+
+&usbdrd31_dwc3 {
+	dr_mode = "otg";
+	usb-role-switch;
+	role-switch-default-mode = "peripheral";
+	maximum-speed = "super-speed-plus";
+	status = "okay";
+
+	port {
+		usbdrd31_dwc3_role_switch: endpoint {
+			remote-endpoint = <&usbc0_role_sw>;
+		};
+	};
+};
+
+&usbdrd31_phy {
+	orientation-switch;
+	/* TODO: Update these once PMIC is implemented */
+	pll-supply = <&reg_placeholder>;
+	dvdd-usb20-supply = <&reg_placeholder>;
+	vddh-usb20-supply = <&reg_placeholder>;
+	vdd33-usb20-supply = <&reg_placeholder>;
+	vdda-usbdp-supply = <&reg_placeholder>;
+	vddh-usbdp-supply = <&reg_placeholder>;
+	status = "okay";
+
+	port {
+		usbdrd31_phy_orien_switch: endpoint {
+			remote-endpoint = <&usbc0_orien_sw>;
+		};
+	};
+};
+
+&usi_uart {
+	samsung,clkreq-on; /* needed for UART mode */
+	status = "okay";
+};
+
+&usi8 {
+	samsung,mode = <USI_V2_I2C>;
+	status = "okay";
+};
+
+&usi12 {
+	samsung,mode = <USI_V2_I2C>;
+	status = "okay";
+};
+
+&watchdog_cl0 {
+	timeout-sec = <30>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-raven.dts b/arch/arm64/boot/dts/exynos/google/gs101-raven.dts
new file mode 100644
index 000000000000..1e7e6b34b864
--- /dev/null
+++ b/arch/arm64/boot/dts/exynos/google/gs101-raven.dts
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Raven Device Tree
+ *
+ * Copyright 2021-2023 Google LLC
+ * Copyright 2023-2025 Linaro Ltd
+ */
+
+/dts-v1/;
+
+#include "gs101-pixel-common.dtsi"
+
+/ {
+	model = "Raven";
+	compatible = "google,gs101-raven", "google,gs101";
+};
+
+&cont_splash_mem {
+	reg = <0x0 0xfac00000 (1440 * 3120 * 4)>;
+	status = "okay";
+};
+
+&framebuffer0 {
+	width = <1440>;
+	height = <3120>;
+	stride = <(1440 * 4)>;
+	format = "a8r8g8b8";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
index c5335dd59dfe..3de3a758f113 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi
+++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
@@ -73,7 +73,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0000>;
 			enable-method = "psci";
-			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ananke_cpu_sleep>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -83,7 +83,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0100>;
 			enable-method = "psci";
-			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ananke_cpu_sleep>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -93,7 +93,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0200>;
 			enable-method = "psci";
-			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ananke_cpu_sleep>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -103,7 +103,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0300>;
 			enable-method = "psci";
-			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ananke_cpu_sleep>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -113,7 +113,7 @@
 			compatible = "arm,cortex-a76";
 			reg = <0x0400>;
 			enable-method = "psci";
-			cpu-idle-states = <&ENYO_CPU_SLEEP>;
+			cpu-idle-states = <&enyo_cpu_sleep>;
 			capacity-dmips-mhz = <620>;
 			dynamic-power-coefficient = <284>;
 		};
@@ -123,7 +123,7 @@
 			compatible = "arm,cortex-a76";
 			reg = <0x0500>;
 			enable-method = "psci";
-			cpu-idle-states = <&ENYO_CPU_SLEEP>;
+			cpu-idle-states = <&enyo_cpu_sleep>;
 			capacity-dmips-mhz = <620>;
 			dynamic-power-coefficient = <284>;
 		};
@@ -133,7 +133,7 @@
 			compatible = "arm,cortex-x1";
 			reg = <0x0600>;
 			enable-method = "psci";
-			cpu-idle-states = <&HERA_CPU_SLEEP>;
+			cpu-idle-states = <&hera_cpu_sleep>;
 			capacity-dmips-mhz = <1024>;
 			dynamic-power-coefficient = <650>;
 		};
@@ -143,7 +143,7 @@
 			compatible = "arm,cortex-x1";
 			reg = <0x0700>;
 			enable-method = "psci";
-			cpu-idle-states = <&HERA_CPU_SLEEP>;
+			cpu-idle-states = <&hera_cpu_sleep>;
 			capacity-dmips-mhz = <1024>;
 			dynamic-power-coefficient = <650>;
 		};
@@ -151,7 +151,7 @@
 		idle-states {
 			entry-method = "psci";
 
-			ANANKE_CPU_SLEEP: cpu-ananke-sleep {
+			ananke_cpu_sleep: cpu-ananke-sleep {
 				idle-state-name = "c2";
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x0010000>;
@@ -160,7 +160,7 @@
 				min-residency-us = <2000>;
 			};
 
-			ENYO_CPU_SLEEP: cpu-enyo-sleep {
+			enyo_cpu_sleep: cpu-enyo-sleep {
 				idle-state-name = "c2";
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x0010000>;
@@ -169,7 +169,7 @@
 				min-residency-us = <2500>;
 			};
 
-			HERA_CPU_SLEEP: cpu-hera-sleep {
+			hera_cpu_sleep: cpu-hera-sleep {
 				idle-state-name = "c2";
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x0010000>;
@@ -196,6 +196,14 @@
 		clock-output-names = "ext-200m";
 	};
 
+	firmware {
+		acpm_ipc: power-management {
+			compatible = "google,gs101-acpm-ipc";
+			mboxes = <&ap2apm_mailbox>;
+			shmem = <&apm_sram>;
+		};
+	};
+
 	pmu-0 {
 		compatible = "arm,cortex-a55-pmu";
 		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_cluster0>;
@@ -1400,18 +1408,30 @@
 
 			poweroff: syscon-poweroff {
 				compatible = "syscon-poweroff";
-				regmap = <&pmu_system_controller>;
 				offset = <0x3e9c>; /* PAD_CTRL_PWR_HOLD */
-				mask = <0x100>; /* reset value */
+				mask = <0x00000100>;
+				value = <0x0>;
 			};
 
 			reboot: syscon-reboot {
 				compatible = "syscon-reboot";
-				regmap = <&pmu_system_controller>;
 				offset = <0x3a00>; /* SYSTEM_CONFIGURATION */
 				mask = <0x2>; /* SWRESET_SYSTEM */
 				value = <0x2>; /* reset value */
 			};
+
+			reboot-mode {
+				compatible = "syscon-reboot-mode";
+				offset = <0x0810>; /* EXYNOS_PMU_SYSIP_DAT0 */
+				mode-bootloader = <0xfc>;
+				mode-charge = <0x0a>;
+				mode-fastboot = <0xfa>;
+				mode-reboot-ab-update = <0x52>;
+				mode-recovery = <0xff>;
+				mode-rescue = <0xf9>;
+				mode-shutdown-thermal = <0x51>;
+				mode-shutdown-thermal-battery = <0x51>;
+			};
 		};
 
 		pinctrl_gpio_alive: pinctrl@174d0000 {
@@ -1440,6 +1460,15 @@
 			};
 		};
 
+		ap2apm_mailbox: mailbox@17610000 {
+			compatible = "google,gs101-mbox";
+			reg = <0x17610000 0x1000>;
+			clocks = <&cmu_apm CLK_GOUT_APM_MAILBOX_APM_AP_PCLK>;
+			clock-names = "pclk";
+			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH 0>;
+			#mbox-cells = <0>;
+		};
+
 		pinctrl_gsactrl: pinctrl@17940000 {
 			compatible = "google,gs101-pinctrl";
 			reg = <0x17940000 0x00001000>;
@@ -1454,6 +1483,7 @@
 			/* TODO: update once support for this CMU exists */
 			clocks = <0>;
 			clock-names = "pclk";
+			status = "disabled";
 		};
 
 		cmu_top: clock-controller@1e080000 {
@@ -1466,6 +1496,14 @@
 		};
 	};
 
+	apm_sram: sram@2039000 {
+		compatible = "mmio-sram";
+		reg = <0x0 0x2039000 0x40000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x0 0x2039000 0x40000>;
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts =
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index 839432153cc7..b6d3fe26d621 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -122,6 +122,19 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-mx8menlo.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-nitrogen-r2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-phg.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-rdk.dtb
+
+imx8mm-phyboard-polis-peb-av-10-dtbs += imx8mm-phyboard-polis-rdk.dtb imx8mm-phyboard-polis-peb-av-10.dtbo
+imx8mm-phyboard-polis-peb-eval-01-dtbs += imx8mm-phyboard-polis-rdk.dtb imx8mm-phyboard-polis-peb-eval-01.dtbo
+imx8mm-phycore-no-eth-dtbs += imx8mm-phyboard-polis-rdk.dtb imx8mm-phycore-no-eth.dtbo
+imx8mm-phycore-no-spiflash-dtbs += imx8mm-phyboard-polis-rdk.dtb imx8mm-phycore-no-spiflash.dtbo
+imx8mm-phycore-rpmsg-dtbs += imx8mm-phyboard-polis-rdk.dtb imx8mm-phycore-rpmsg.dtbo
+
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-peb-av-10.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-peb-eval-01.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-phycore-no-eth.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-phycore-no-spiflash.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-phycore-rpmsg.dtb
+
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-phygate-tauri-l.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-prt8mm.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx.dtb
@@ -193,9 +206,12 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mp-nitrogen-smarc-universal-board.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-phyboard-pollux-rdk.dtb
 imx8mp-phyboard-pollux-rdk-no-eth-dtbs += imx8mp-phyboard-pollux-rdk.dtb imx8mp-phycore-no-eth.dtbo
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-phyboard-pollux-rdk-no-eth.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-basic.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-hdmi.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-lt6.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revb-mi1010ait-1cp1.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revc-bd500.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mp-skov-revc-tian-g07017.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-tqma8mpql-mba8mpxl.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-tqma8mpql-mba8mp-ras314.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-var-som-symphony.dtb
@@ -267,6 +283,10 @@ dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-eval-v3.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-iris.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-iris-v2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-mek.dtb
+
+imx8qxp-mek-pcie-ep-dtbs += imx8qxp-mek.dtb imx8qxp-mek-pcie-ep.dtbo
+dtb-$(CONFIG_ARCH_MXC) += imx8qxp-mek-pcie-ep.dtb
+
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-tqma8xqp-mba8xx.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8ulp-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-9x9-qsb.dtb
@@ -281,6 +301,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx93-phyboard-segin.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxca.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxla.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-var-som-symphony.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx95-15x15-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx95-19x19-evk.dtb
 
 imx8mm-kontron-dl-dtbs			:= imx8mm-kontron-bl.dtb imx8mm-kontron-dl.dtbo
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
index bc0d89427fbe..3a11068f2212 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
@@ -87,6 +87,22 @@
 		los-gpios = <&sfpgpio 7 GPIO_ACTIVE_HIGH>;
 		maximum-power-milliwatt = <2000>;
 	};
+
+	usb1v2_supply: regulator-usbhub-1v2 {
+		compatible = "regulator-fixed";
+		regulator-name = "usbhub_1v2";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-always-on;
+	};
+
+	system3v3_supply: regulator-system-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "system_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
 };
 
 /* XG1 - Upper SFP */
@@ -231,6 +247,12 @@
 		compatible = "atmel,at97sc3204t";
 		reg = <0x29>;
 	};
+
+	usbhub: usb-hub@2d {
+		compatible = "microchip,usb5744";
+		reg = <0x2d>;
+	};
+
 };
 
 &i2c2 {
@@ -378,10 +400,32 @@
 	};
 };
 
+/* LS1088A USB Port 0 - direct to bottom USB-A port */
 &usb0 {
 	status = "okay";
 };
 
+/* LS1088A USB Port 1 - to Microchip USB5744 USB Hub */
 &usb1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
 	status = "okay";
+
+	hub_2_0: hub@1 {
+		compatible = "usb424,2744";
+		reg = <1>;
+		peer-hub = <&hub_3_0>;
+		i2c-bus = <&usbhub>;
+		vdd-supply = <&system3v3_supply>;
+		vdd2-supply = <&usb1v2_supply>;
+	};
+
+	hub_3_0: hub@2 {
+		compatible = "usb424,5744";
+		reg = <2>;
+		peer-hub = <&hub_2_0>;
+		i2c-bus = <&usbhub>;
+		vdd-supply = <&system3v3_supply>;
+		vdd2-supply = <&usb1v2_supply>;
+	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
index a3fc945aea16..dbea1eefdeec 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
@@ -790,6 +790,22 @@
 	status = "okay";
 };
 
+/* Apalis HDMI Audio */
+&sai5 {
+	assigned-clocks = <&acm IMX_ADMA_ACM_SAI5_MCLK_SEL>,
+			  <&acm IMX_ADMA_ACM_AUD_CLK1_SEL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_PLL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_SLV_BUS>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_MST_BUS>,
+			  <&clk IMX_SC_R_AUDIO_PLL_1 IMX_SC_PM_CLK_PLL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_1 IMX_SC_PM_CLK_SLV_BUS>,
+			  <&clk IMX_SC_R_AUDIO_PLL_1 IMX_SC_PM_CLK_MST_BUS>,
+			  <&sai5_lpcg 0>;
+	assigned-clock-parents = <&aud_pll_div0_lpcg 0>, <&aud_rec1_lpcg 0>;
+	assigned-clock-rates = <0>, <0>, <786432000>, <49152000>, <12288000>,
+			       <722534400>, <45158400>, <11289600>, <49152000>;
+};
+
 /* TODO: Apalis SATA1 */
 
 /* Apalis SPDIF1 */
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-hsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-hsio.dtsi
index 70a8aa1a6791..9b8b1380c4c2 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-hsio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-hsio.dtsi
@@ -57,8 +57,9 @@ hsio_subsys: bus@5f000000 {
 		ranges = <0x81000000 0 0x00000000 0x8ff80000 0 0x00010000>,
 			 <0x82000000 0 0x80000000 0x80000000 0 0x0ff00000>;
 		#interrupt-cells = <1>;
-		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "msi";
+		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "msi", "dma";
 		#address-cells = <3>;
 		#size-cells = <2>;
 		clocks = <&pcieb_lpcg IMX_LPCG_CLK_6>,
@@ -68,9 +69,9 @@ hsio_subsys: bus@5f000000 {
 		bus-range = <0x00 0xff>;
 		device_type = "pci";
 		interrupt-map = <0 0 0 1 &gic 0 105 4>,
-				 <0 0 0 2 &gic 0 106 4>,
-				 <0 0 0 3 &gic 0 107 4>,
-				 <0 0 0 4 &gic 0 108 4>;
+				<0 0 0 2 &gic 0 106 4>,
+				<0 0 0 3 &gic 0 107 4>,
+				<0 0 0 4 &gic 0 108 4>;
 		interrupt-map-mask = <0 0 0 0x7>;
 		num-lanes = <1>;
 		num-viewport = <4>;
@@ -79,6 +80,25 @@ hsio_subsys: bus@5f000000 {
 		status = "disabled";
 	};
 
+	pcieb_ep: pcie-ep@5f010000 {
+		compatible = "fsl,imx8q-pcie-ep";
+		reg = <0x5f010000 0x00010000>,
+		      <0x80000000 0x10000000>;
+		reg-names = "dbi", "addr_space";
+		num-lanes = <1>;
+		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "dma";
+		clocks = <&pcieb_lpcg IMX_LPCG_CLK_6>,
+			 <&pcieb_lpcg IMX_LPCG_CLK_4>,
+			 <&pcieb_lpcg IMX_LPCG_CLK_5>;
+		clock-names = "dbi", "mstr", "slv";
+		power-domains = <&pd IMX_SC_R_PCIE_B>;
+		fsl,max-link-speed = <3>;
+		num-ib-windows = <6>;
+		num-ob-windows = <6>;
+		status = "disabled";
+	};
+
 	pcieb_lpcg: clock-controller@5f060000 {
 		compatible = "fsl,imx8qxp-lpcg";
 		reg = <0x5f060000 0x10000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
index 6259186cd4d9..5f3b4014e152 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
@@ -191,6 +191,33 @@
 		enable-active-high;
 	};
 
+	reg_audio_5v: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	bt_sco_codec: audio-codec-bt {
 		compatible = "linux,bt-sco";
 		#sound-dai-cells = <1>;
@@ -420,6 +447,11 @@
 				wlf,shared-lrclk;
 				wlf,hp-cfg = <2 2 3>;
 				wlf,gpio-cfg = <1 3>;
+				AVDD-supply = <&reg_audio_3v3>;
+				DBVDD-supply = <&reg_audio_1v8>;
+				DCVDD-supply = <&reg_audio_1v8>;
+				SPKVDD1-supply = <&reg_audio_5v>;
+				SPKVDD2-supply = <&reg_audio_5v>;
 			};
 		};
 
@@ -444,6 +476,11 @@
 				wlf,shared-lrclk;
 				wlf,hp-cfg = <2 2 3>;
 				wlf,gpio-cfg = <1 3>;
+				AVDD-supply = <&reg_audio_3v3>;
+				DBVDD-supply = <&reg_audio_1v8>;
+				DCVDD-supply = <&reg_audio_1v8>;
+				SPKVDD1-supply = <&reg_audio_5v>;
+				SPKVDD2-supply = <&reg_audio_5v>;
 			};
 		};
 
@@ -468,6 +505,11 @@
 				wlf,shared-lrclk;
 				wlf,hp-cfg = <2 2 3>;
 				wlf,gpio-cfg = <1 3>;
+				AVDD-supply = <&reg_audio_3v3>;
+				DBVDD-supply = <&reg_audio_1v8>;
+				DCVDD-supply = <&reg_audio_1v8>;
+				SPKVDD1-supply = <&reg_audio_5v>;
+				SPKVDD2-supply = <&reg_audio_5v>;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
index a8ef4fba16a9..d16490d87687 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
@@ -254,6 +254,10 @@
 	status = "okay";
 };
 
+&reg_nvcc_sd {
+	sd-vsel-gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+};
+
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
@@ -454,7 +458,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d0
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d0
 			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000d0
 		>;
 	};
 
@@ -467,7 +471,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d4
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d4
 			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000d0
 		>;
 	};
 
@@ -480,7 +484,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d6
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d6
 			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000d0
 		>;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
index 663ae52b4852..d45542965230 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
@@ -342,6 +342,7 @@
 				regulator-name = "NVCC_SD (LDO5)";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
+				sd-vsel-gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
 			};
 		};
 	};
@@ -794,7 +795,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d0 /* SDIO_A_D2 */
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d0 /* SDIO_A_D3 */
 			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000090
 		>;
 	};
 
@@ -807,7 +808,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d4 /* SDIO_A_D2 */
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d4 /* SDIO_A_D3 */
 			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000090
 		>;
 	};
 
@@ -820,7 +821,7 @@
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d6 /* SDIO_A_D2 */
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d6 /* SDIO_A_D3 */
 			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x40000090
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-av-10.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-av-10.dtso
new file mode 100644
index 000000000000..840f83293452
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-av-10.dtso
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/clock/imx8mm-clock.h>
+#include <dt-bindings/gpio/gpio.h>
+#include "imx8mm-pinfunc.h"
+
+&{/} {
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_lcd>;
+		default-brightness-level = <6>;
+		pwms = <&pwm4 0 50000 0>;
+		power-supply = <&reg_vdd_3v3_s>;
+		enable-gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>;
+		brightness-levels= <0 4 8 16 32 64 128 255>;
+	};
+
+	panel {
+		compatible = "edt,etml1010g3dra";
+		backlight = <&backlight>;
+		power-supply = <&reg_vcc_3v3>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&bridge_out>;
+			};
+		};
+	};
+
+	reg_sound_1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_1V8_Audio";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	reg_sound_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_3V3_Analog";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	sound-peb-av-10 {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "snd-peb-av-10";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&dailink_master>;
+		simple-audio-card,frame-master = <&dailink_master>;
+		simple-audio-card,mclk-fs = <32>;
+		simple-audio-card,widgets =
+			"Line", "Line In",
+			"Speaker", "Speaker",
+			"Microphone", "Microphone Jack",
+			"Headphone", "Headphone Jack";
+		simple-audio-card,routing =
+			"Speaker", "SPOP",
+			"Speaker", "SPOM",
+			"Headphone Jack", "HPLOUT",
+			"Headphone Jack", "HPROUT",
+			"LINE1L", "Line In",
+			"LINE1R", "Line In",
+			"MIC3R", "Microphone Jack",
+			"Microphone Jack", "Mic Bias";
+
+		simple-audio-card,cpu {
+			sound-dai = <&sai5>;
+		};
+
+		dailink_master: simple-audio-card,codec {
+			sound-dai = <&codec>;
+			clocks = <&clk IMX8MM_CLK_SAI5>;
+		};
+	};
+};
+
+&i2c3 {
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	pinctrl-1 = <&pinctrl_i2c3_gpio>;
+	sda-gpios = <&gpio5 19 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	scl-gpios = <&gpio5 18 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	codec: codec@18 {
+		compatible = "ti,tlv320aic3007";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_tlv320>;
+		#sound-dai-cells = <0>;
+		reg = <0x18>;
+		reset-gpios = <&gpio4 28 GPIO_ACTIVE_LOW>;
+		ai3x-gpio-func = <0xd 0x0>;
+		ai3x-micbias-vg = <2>;
+		AVDD-supply = <&reg_sound_3v3>;
+		IOVDD-supply = <&reg_sound_3v3>;
+		DRVDD-supply = <&reg_sound_3v3>;
+		DVDD-supply = <&reg_sound_1v8>;
+	};
+
+	eeprom@57 {
+		compatible = "atmel,24c32";
+		pagesize = <32>;
+		reg = <0x57>;
+		vcc-supply = <&reg_vdd_3v3_s>;
+	};
+
+	eeprom@5f {
+		compatible = "atmel,24c32";
+		pagesize = <32>;
+		reg = <0x5f>;
+		size = <32>;
+		vcc-supply = <&reg_vdd_3v3_s>;
+	};
+};
+
+&lcdif {
+	status = "okay";
+};
+
+&mipi_dsi {
+	samsung,esc-clock-frequency = <10000000>;
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		port@1 {
+			reg = <1>;
+			dsi_out: endpoint {
+				remote-endpoint = <&bridge_in>;
+			};
+		};
+	};
+};
+
+&pwm4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm4>;
+	status = "okay";
+};
+
+&sai5 {
+	assigned-clocks = <&clk IMX8MM_CLK_SAI5>;
+	assigned-clock-parents = <&clk IMX8MM_AUDIO_PLL2_OUT>;
+	assigned-clock-rates = <11289600>;
+	clocks = <&clk IMX8MM_CLK_SAI5_IPG>, <&clk IMX8MM_CLK_DUMMY>,
+		<&clk IMX8MM_CLK_SAI5_ROOT>, <&clk IMX8MM_CLK_DUMMY>,
+		<&clk IMX8MM_CLK_DUMMY>, <&clk IMX8MM_AUDIO_PLL1_OUT>,
+		<&clk IMX8MM_AUDIO_PLL2_OUT>;
+	clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3", "pll8k",
+			"pll11k";
+	fsl,sai-mclk-direction-output;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai5>;
+	#sound-dai-cells = <0>;
+	status = "okay";
+};
+
+&sn65dsi83 {
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			bridge_in: endpoint {
+				remote-endpoint = <&dsi_out>;
+				data-lanes = <1 2 3 4>;
+			};
+		};
+
+		port@2 {
+			reg = <2>;
+			bridge_out: endpoint {
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
+};
+
+&iomuxc {
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_I2C3_SCL_I2C3_SCL          0x400001c2
+			MX8MM_IOMUXC_I2C3_SDA_I2C3_SDA          0x400001c2
+		>;
+	};
+
+	pinctrl_i2c3_gpio: i2c3gpiogrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_I2C3_SCL_GPIO5_IO18        0x1e2
+			MX8MM_IOMUXC_I2C3_SDA_GPIO5_IO19        0x1e2
+		>;
+	};
+	pinctrl_lcd: lcd0grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI3_TXD_GPIO5_IO1		0x12
+		>;
+	};
+
+	pinctrl_pwm4: pwm4grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI3_MCLK_PWM4_OUT		0x12
+		>;
+	};
+
+	pinctrl_sai5: sai5grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI5_MCLK_SAI5_MCLK        0xd6
+			MX8MM_IOMUXC_SAI5_RXD0_SAI5_RX_DATA0    0xd6
+			MX8MM_IOMUXC_SAI5_RXD1_SAI5_TX_SYNC     0xd6
+			MX8MM_IOMUXC_SAI5_RXD2_SAI5_TX_BCLK     0xd6
+			MX8MM_IOMUXC_SAI5_RXD3_SAI5_TX_DATA0    0xd6
+		>;
+	};
+
+	pinctrl_tlv320: tlv320grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28       0x16
+			MX8MM_IOMUXC_SAI5_RXC_GPIO3_IO20        0x16
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-eval-01.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-eval-01.dtso
new file mode 100644
index 000000000000..a28f51ece93b
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-peb-eval-01.dtso
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Author: Janine Hagemann <j.hagemann@phytec.de>
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include "imx8mm-pinfunc.h"
+
+&{/} {
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_keys>;
+
+		button-0 {
+			label = "home";
+			linux,code = <KEY_HOME>;
+			gpios = <&gpio4 17 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		button-1 {
+			label = "menu";
+			linux,code = <KEY_MENU>;
+			gpios = <&gpio5 29 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+	};
+
+	user-leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_user_leds>;
+
+		user-led1 {
+			gpios = <&gpio4 14 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+
+		user-led2 {
+			gpios = <&gpio4 15 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+
+		user-led3 {
+			gpios = <&gpio5 28 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+	};
+};
+
+&iomuxc {
+	pinctrl_gpio_keys: gpio_keysgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_TXD5_GPIO4_IO17	0x16
+			MX8MM_IOMUXC_UART4_TXD_GPIO5_IO29	0x16
+		>;
+	};
+
+	pinctrl_user_leds: user_ledsgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15	0x16
+			MX8MM_IOMUXC_UART4_RXD_GPIO5_IO28	0x16
+			MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14	0x16
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts
index 5eacbd9611ee..be470cfb03d7 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts
@@ -219,9 +219,15 @@
 	status = "okay";
 };
 
+/* RTC */
 &rv3028 {
+	interrupt-parent = <&gpio1>;
+	interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+	pinctrl-0 = <&pinctrl_rtc>;
+	pinctrl-names = "default";
 	aux-voltage-chargeable = <1>;
 	trickle-resistor-ohms = <3000>;
+	wakeup-source;
 };
 
 &snvs_pwrkey {
@@ -255,11 +261,12 @@
 		device-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>;
 		interrupt-names = "host-wakeup";
 		interrupt-parent = <&gpio2>;
-		interrupts = <9 IRQ_TYPE_EDGE_BOTH>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
 		max-speed = <2000000>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_bt>;
 		shutdown-gpios = <&gpio2 6 GPIO_ACTIVE_HIGH>;
+		vbat-supply = <&reg_vcc_3v3>;
 		vddio-supply = <&reg_vcc_3v3>;
 	};
 };
@@ -332,7 +339,7 @@
 		fsl,pins = <
 			MX8MM_IOMUXC_SD1_DATA4_GPIO2_IO6	0x00
 			MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8	0x00
-			MX8MM_IOMUXC_SD1_DATA7_GPIO2_IO9	0x00
+			MX8MM_IOMUXC_SD1_DATA7_GPIO2_IO9	0x140
 		>;
 	};
 
@@ -408,6 +415,12 @@
 		>;
 	};
 
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x1c0
+		>;
+	};
+
 	pinctrl_tpm: tpmgrp {
 		fsl,pins = <
 			MX8MM_IOMUXC_SD1_STROBE_GPIO2_IO11      0x140
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-eth.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-eth.dtso
new file mode 100644
index 000000000000..0fb4b6da6c10
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-eth.dtso
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ */
+
+/dts-v1/;
+/plugin/;
+
+&ethphy0 {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-spiflash.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-spiflash.dtso
new file mode 100644
index 000000000000..7bfc366c1689
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-no-spiflash.dtso
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Author: Teresa Remmet <t.remmet@phytec.de>
+ */
+
+/dts-v1/;
+/plugin/;
+
+&flexspi {
+	status = "disabled";
+};
+
+&som_flash {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-rpmsg.dtso b/arch/arm64/boot/dts/freescale/imx8mm-phycore-rpmsg.dtso
new file mode 100644
index 000000000000..43d5905f3d72
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-rpmsg.dtso
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Author: Dominik Haller <d.haller@phytec.de>
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/clock/imx8mm-clock.h>
+
+&{/} {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		m4_reserved: m4@80000000 {
+			reg = <0 0x80000000 0 0x1000000>;
+			no-map;
+		};
+
+		vdev0vring0: vdev0vring0@b8000000 {
+			reg = <0 0xb8000000 0 0x8000>;
+			no-map;
+		};
+
+		vdev0vring1: vdev0vring1@b8008000 {
+			reg = <0 0xb8008000 0 0x8000>;
+			no-map;
+		};
+
+		rsc_table: rsc_table@b80ff000 {
+			reg = <0 0xb80ff000 0 0x1000>;
+			no-map;
+		};
+
+		vdevbuffer: vdevbuffer@b8400000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0xb8400000 0 0x100000>;
+			no-map;
+		};
+	};
+
+	core-m4 {
+		compatible = "fsl,imx8mm-cm4";
+		clocks = <&clk IMX8MM_CLK_M4_DIV>;
+		mboxes = <&mu 0 1
+			&mu 1 1
+			&mu 3 1>;
+		mbox-names = "tx", "rx", "rxdb";
+		memory-region = <&vdevbuffer>, <&vdev0vring0>, <&vdev0vring1>, <&rsc_table>;
+		syscon = <&src>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi
index 6069678244f3..672baba4c8d0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi
@@ -69,7 +69,6 @@
 
 /* Ethernet */
 &fec1 {
-	fsl,magic-packet;
 	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	pinctrl-names = "default";
@@ -161,11 +160,13 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-max-microvolt = <2500000>;
-				regulator-min-microvolt = <1500000>;
+				regulator-min-microvolt = <2500000>;
 				regulator-name = "VCC_ENET_2V5 (LDO3)";
 
 				regulator-state-mem {
-					regulator-off-in-suspend;
+					regulator-on-in-suspend;
+					regulator-suspend-max-microvolt = <2500000>;
+					regulator-suspend-min-microvolt = <2500000>;
 				};
 			};
 
@@ -285,9 +286,11 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_sn65dsi83>;
 		reg = <0x2d>;
+		vcc-supply = <&reg_vdd_1v8>;
 		status = "disabled";
 	};
 
+	/* EEPROM */
 	eeprom@51 {
 		compatible = "atmel,24c32";
 		pagesize = <32>;
@@ -295,17 +298,14 @@
 		vcc-supply = <&reg_vdd_3v3_s>;
 	};
 
+	/* RTC */
 	rv3028: rtc@52 {
 		compatible = "microcrystal,rv3028";
-		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-parent = <&gpio1>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_rtc>;
 		reg = <0x52>;
 	};
 };
 
-/* EMMC */
+/* eMMC */
 &usdhc3 {
 	assigned-clocks = <&clk IMX8MM_CLK_USDHC3_ROOT>;
 	assigned-clock-rates = <400000000>;
@@ -373,12 +373,6 @@
 		>;
 	};
 
-	pinctrl_rtc: rtcgrp {
-		fsl,pins = <
-			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x1c0
-		>;
-	};
-
 	pinctrl_sn65dsi83: sn65dsi83grp {
 		fsl,pins = <
 			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10		0x0
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
index c3835b2d860a..755cf9cacd22 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-phygate-tauri-l.dts
@@ -215,8 +215,13 @@
 
 /* RTC */
 &rv3028 {
+	interrupt-parent = <&gpio1>;
+	interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+	pinctrl-0 = <&pinctrl_rtc>;
+	pinctrl-names = "default";
 	aux-voltage-chargeable = <1>;
 	trickle-resistor-ohms = <3000>;
+	wakeup-source;
 };
 
 &uart1 {
@@ -394,6 +399,12 @@
 		>;
 	};
 
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x1c0
+		>;
+	};
+
 	pinctrl_tempsense: tempsensegrp {
 		fsl,pins = <
 			MX8MM_IOMUXC_SAI3_TXFS_GPIO4_IO31	0x00
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
index 8f58c84e14c8..b82e9790ea20 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
@@ -65,6 +65,7 @@
 		spi-max-frequency = <84000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <4>;
+		vcc-supply = <&buck5_reg>;
 
 		partitions {
 			compatible = "fixed-partitions";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
index ce20de259805..3d0b14968131 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
@@ -16,10 +16,10 @@
 			"Headphone Jack", "HPOUTR",
 			"IN2L", "Line In Jack",
 			"IN2R", "Line In Jack",
-			"Headphone Jack", "MICBIAS",
-			"IN1L", "Headphone Jack";
+			"Microphone Jack", "MICBIAS",
+			"IN1L", "Microphone Jack";
 		simple-audio-card,widgets =
-			"Microphone", "Headphone Jack",
+			"Microphone", "Microphone Jack",
 			"Headphone", "Headphone Jack",
 			"Line", "Line In Jack";
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
index c528594ac442..b46566f3ce20 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
@@ -18,20 +18,6 @@
 		rtc1 = &snvs_rtc;
 	};
 
-	backlight: backlight {
-		compatible = "pwm-backlight";
-		brightness-levels = <0 45 63 88 119 158 203 255>;
-		default-brightness-level = <4>;
-		/* Verdin I2S_2_D_OUT (DSI_1_BKL_EN/DSI_1_BKL_EN_LVDS, SODIMM 46) */
-		enable-gpios = <&gpio3 24 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_i2s_2_d_out_dsi_1_bkl_en>;
-		power-supply = <&reg_3p3v>;
-		/* Verdin PWM_3_DSI/PWM_3_DSI_LVDS (SODIMM 19) */
-		pwms = <&pwm1 0 6666667 PWM_POLARITY_INVERTED>;
-		status = "disabled";
-	};
-
 	/* Fixed clock dedicated to SPI CAN controller */
 	clk40m: oscillator {
 		compatible = "fixed-clock";
@@ -66,13 +52,6 @@
 		status = "disabled";
 	};
 
-	panel_lvds: panel-lvds {
-		compatible = "panel-lvds";
-		backlight = <&backlight>;
-		data-mapping = "vesa-24";
-		status = "disabled";
-	};
-
 	/* Carrier Board Supplies */
 	reg_1p8v: regulator-1p8v {
 		compatible = "regulator-fixed";
@@ -165,6 +144,19 @@
 		startup-delay-us = <20000>;
 	};
 
+	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+		compatible = "regulator-gpio";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usdhc2_vsel>;
+		gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <1800000>;
+		states = <1800000 0x1>,
+			 <3300000 0x0>;
+		regulator-name = "PMIC_USDHC_VSELECT";
+		vin-supply = <&reg_nvcc_sd>;
+	};
+
 	reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -290,7 +282,7 @@
 			  "SODIMM_19",
 			  "",
 			  "",
-			  "",
+			  "PMIC_USDHC_VSELECT",
 			  "",
 			  "",
 			  "",
@@ -806,6 +798,7 @@
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
 	pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>;
 	vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&reg_usdhc2_vqmmc>;
 };
 
 &wdog1 {
@@ -1227,13 +1220,17 @@
 			<MX8MM_IOMUXC_NAND_CLE_GPIO3_IO5		0x6>;	/* SODIMM 76 */
 	};
 
+	pinctrl_usdhc2_vsel: usdhc2vselgrp {
+		fsl,pins =
+			<MX8MM_IOMUXC_GPIO1_IO04_GPIO1_IO4	0x10>; /* PMIC_USDHC_VSELECT */
+	};
+
 	/*
 	 * Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the
 	 * on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here.
 	 */
 	pinctrl_usdhc2: usdhc2grp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x90>,	/* SODIMM 78 */
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x90>,	/* SODIMM 74 */
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x90>,	/* SODIMM 80 */
@@ -1244,7 +1241,6 @@
 
 	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x94>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x94>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x94>,
@@ -1255,7 +1251,6 @@
 
 	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x10>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x96>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x96>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x96>,
@@ -1267,7 +1262,6 @@
 	/* Avoid backfeeding with removed card power */
 	pinctrl_usdhc2_sleep: usdhc2slpgrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x0>,
 			<MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK		0x0>,
 			<MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD		0x0>,
 			<MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x0>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2pro.dts b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2pro.dts
index c6ad65becc97..475cbf9e0d1e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2pro.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-bsh-smm-s2pro.dts
@@ -64,7 +64,6 @@
 		DVDD-supply = <&buck5_reg>;
 		reset-gpios = <&gpio1 6 GPIO_ACTIVE_LOW>;
 		ai31xx-micbias-vg = <MICBIAS_AVDDV>;
-		clocks = <&clk IMX8MN_CLK_SAI3_ROOT>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi
index e68a3fd73e17..640c41b51af9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl.dtsi
@@ -63,6 +63,7 @@
 		spi-max-frequency = <84000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <4>;
+		vcc-supply = <&buck5_reg>;
 
 		partitions {
 			compatible = "fixed-partitions";
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index 68e12a752edd..c26954e5a605 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -74,6 +74,24 @@
 		clock-frequency = <100000000>;
 	};
 
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	reg_audio_pwr: regulator-audio-pwr {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -586,7 +604,11 @@
 		wlf,shared-lrclk;
 		wlf,hp-cfg = <3 2 3>;
 		wlf,gpio-cfg = <1 3>;
+		AVDD-supply = <&reg_audio_3v3>;
+		DBVDD-supply = <&reg_audio_1v8>;
+		DCVDD-supply = <&reg_audio_1v8>;
 		SPKVDD1-supply = <&reg_audio_pwr>;
+		SPKVDD2-supply = <&reg_audio_pwr>;
 	};
 
 	pca6416: gpio@20 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi
index e0e9f6f7616d..b97bfeb1c30f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-kontron-osm-s.dtsi
@@ -311,6 +311,7 @@
 				regulator-name = "NVCC_SD (LDO5)";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
+				sd-vsel-gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
 			};
 		};
 	};
@@ -808,7 +809,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1		0x1d0 /* SDIO_A_D1 */
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2		0x1d0 /* SDIO_A_D2 */
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3		0x1d0 /* SDIO_A_D3 */
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x1d0
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x400001d0
 		>;
 	};
 
@@ -820,7 +821,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1		0x1d4 /* SDIO_A_D1 */
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2		0x1d4 /* SDIO_A_D2 */
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3		0x1d4 /* SDIO_A_D3 */
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x1d0
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x400001d0
 		>;
 	};
 
@@ -832,7 +833,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1		0x1d6 /* SDIO_A_D1 */
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2		0x1d6 /* SDIO_A_D2 */
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3		0x1d6 /* SDIO_A_D3 */
-			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x1d0
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT		0x400001d0
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
new file mode 100644
index 000000000000..2ce1860b244d
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2024 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de>
+ */
+
+&clk {
+	assigned-clocks = <&clk IMX8MP_CLK_A53_SRC>,
+			  <&clk IMX8MP_CLK_A53_CORE>,
+			  <&clk IMX8MP_SYS_PLL3>,
+			  <&clk IMX8MP_CLK_NOC>,
+			  <&clk IMX8MP_CLK_NOC_IO>,
+			  <&clk IMX8MP_CLK_GIC>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_ARM_PLL_OUT>,
+				 <0>,
+				 <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL3_OUT>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <0>, <0>,
+			       <600000000>,
+			       <800000000>,
+			       <600000000>,
+			       <400000000>;
+	fsl,operating-mode = "nominal";
+};
+
+&gpu2d {
+	assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>;
+};
+
+&gpu3d {
+	assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>,
+			  <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>, <800000000>;
+};
+
+&pgc_hdmimix {
+	assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>,
+			  <&clk IMX8MP_CLK_HDMI_APB>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_133M>;
+	assigned-clock-rates = <400000000>, <133000000>;
+};
+
+&pgc_hsiomix {
+	assigned-clocks = <&clk IMX8MP_CLK_HSIO_AXI>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <400000000>;
+};
+
+&pgc_gpumix {
+	assigned-clocks = <&clk IMX8MP_CLK_GPU_AXI>,
+			  <&clk IMX8MP_CLK_GPU_AHB>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL3_OUT>,
+				 <&clk IMX8MP_SYS_PLL3_OUT>;
+	assigned-clock-rates = <600000000>, <300000000>;
+};
+
+&pgc_mlmix {
+	assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+			  <&clk IMX8MP_CLK_ML_AXI>,
+			  <&clk IMX8MP_CLK_ML_AHB>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <800000000>,
+			       <800000000>,
+			       <300000000>;
+};
+
+&media_blk_ctrl {
+	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>,
+			  <&clk IMX8MP_CLK_MEDIA_APB>,
+			  <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>,
+			  <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>,
+			  <&clk IMX8MP_CLK_MEDIA_ISP>,
+			  <&clk IMX8MP_VIDEO_PLL1>;
+	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_SYS_PLL1_800M>,
+				 <&clk IMX8MP_VIDEO_PLL1_OUT>,
+				 <&clk IMX8MP_VIDEO_PLL1_OUT>,
+				 <&clk IMX8MP_SYS_PLL1_800M>;
+	assigned-clock-rates = <400000000>, <200000000>,
+			       <0>, <0>, <400000000>,
+			       <1039500000>;
+};
+
+/delete-node/ &{noc_opp_table/opp-1000000000};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-basic.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-basic.dts
new file mode 100644
index 000000000000..5a2629f3567c
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-basic.dts
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU basic/fallback";
+	compatible = "skov,imx8mp-skov-basic", "fsl,imx8mp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi
index 59813ef8e2bb..020f20c8ce66 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-reva.dtsi
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0 OR MIT)
 
 #include "imx8mp.dtsi"
+#include "imx8mp-nominal.dtsi"
 
 #include <dt-bindings/leds/common.h>
 
@@ -116,6 +117,11 @@
 		regulator-name = "24V";
 		regulator-min-microvolt = <24000000>;
 		regulator-max-microvolt = <24000000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg24v>;
+		interrupts-extended = <&gpio4 23 IRQ_TYPE_EDGE_FALLING>;
+		system-critical-regulator;
+		regulator-uv-less-critical-window-ms = <50>;
 	};
 
 	reg_can2rs: regulator-can2rs {
@@ -163,6 +169,19 @@
 	};
 };
 
+/*
+ * Board is passively cooled and heatsink is specced for continuous operation
+ * at 1.2 GHz only. Short bouts of 1.6 GHz are ok, but these should be done
+ * intentionally, not as part of suspend/resume cycles.
+ */
+&{/opp-table/opp-1600000000} {
+	/delete-property/ opp-suspend;
+};
+
+&{/opp-table/opp-1800000000} {
+	/delete-property/ opp-suspend;
+};
+
 &A53_0 {
 	cpu-supply = <&reg_vdd_arm>;
 };
@@ -197,7 +216,7 @@
 &eqos {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_eqos>;
-	phy-mode = "rgmii-txid";
+	phy-mode = "rgmii-rxid";
 	status = "okay";
 
 	fixed-link {
@@ -222,8 +241,11 @@
 
 &i2c1 {
 	clock-frequency = <100000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c1>;
+	pinctrl-1 = <&pinctrl_i2c1_gpio>;
+	scl-gpios = <&gpio5 14 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 
 	pmic@25 {
@@ -232,13 +254,12 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupts-extended = <&gpio1 3 IRQ_TYPE_EDGE_RISING>;
-		sd-vsel-gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
 
 		regulators {
 			reg_vdd_soc: BUCK1 {
 				regulator-name = "VDD_SOC";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <2187500>;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -247,20 +268,20 @@
 
 			reg_vdd_arm: BUCK2 {
 				regulator-name = "VDD_ARM";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <2187500>;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1000000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
 				regulator-ramp-delay = <3125>;
-				nxp,dvs-run-voltage = <950000>;
+				nxp,dvs-run-voltage = <850000>;
 				nxp,dvs-standby-voltage = <850000>;
 			};
 
 			reg_vdd_3v3: BUCK4 {
 				regulator-name = "VDD_3V3";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <3400000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -268,8 +289,8 @@
 
 			reg_vdd_1v8: BUCK5 {
 				regulator-name = "VDD_1V8";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <3400000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -277,8 +298,8 @@
 
 			reg_nvcc_dram_1v1: BUCK6 {
 				regulator-name = "NVCC_DRAM_1V1";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <3400000>;
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -286,8 +307,8 @@
 
 			reg_nvcc_snvs_1v8: LDO1 {
 				regulator-name = "NVCC_SNVS_1V8";
-				regulator-min-microvolt = <1600000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -295,8 +316,8 @@
 
 			reg_vdda_1v8: LDO3 {
 				regulator-name = "VDDA_1V8";
-				regulator-min-microvolt = <800000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
 				vin-supply = <&reg_5v_p>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -314,10 +335,21 @@
 	};
 };
 
+&i2c2 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	pinctrl-1 = <&pinctrl_i2c2_gpio>;
+	scl-gpios = <&gpio5 16 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+};
+
 &i2c3 {
-	clock-frequency = <100000>;
-	pinctrl-names = "default";
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c3>;
+	pinctrl-1 = <&pinctrl_i2c3_gpio>;
+	scl-gpios = <&gpio5 18 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio5 19 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 
 	i2c_rtc: rtc@51 {
@@ -332,8 +364,11 @@
 
 &i2c4 {
 	clock-frequency = <380000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c4>;
+	pinctrl-1 = <&pinctrl_i2c4_gpio>;
+	scl-gpios = <&gpio5 20 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio5 21 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 
 	switch: switch@5f {
@@ -391,6 +426,13 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
 	status = "okay";
+	/*
+	 * While there is no CTS line, the property "uart-has-rtscts" is still
+	 * the right thing to do to enable the UART to do RS485. In RS485-Mode
+	 * CTS isn't used anyhow and there is no dedicated property
+	 * "uart-has-rts-but-no-cts".
+	 */
+	uart-has-rtscts;
 };
 
 &uart2 {
@@ -538,6 +580,27 @@
 		>;
 	};
 
+	pinctrl_i2c1_gpio: i2c1gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C1_SCL__GPIO5_IO14			0x400001c2
+			MX8MP_IOMUXC_I2C1_SDA__GPIO5_IO15			0x400001c2
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL				0x400001c2
+			MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA				0x400001c2
+		>;
+	};
+
+	pinctrl_i2c2_gpio: i2c2gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C2_SCL__GPIO5_IO16			0x400001c2
+			MX8MP_IOMUXC_I2C2_SDA__GPIO5_IO17			0x400001c2
+		>;
+	};
+
 	pinctrl_i2c3: i2c3grp {
 		fsl,pins = <
 			MX8MP_IOMUXC_I2C3_SCL__I2C3_SCL				0x400001c2
@@ -545,6 +608,13 @@
 		>;
 	};
 
+	pinctrl_i2c3_gpio: i2c3gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C3_SCL__GPIO5_IO18			0x400001c2
+			MX8MP_IOMUXC_I2C3_SDA__GPIO5_IO19			0x400001c2
+		>;
+	};
+
 	pinctrl_i2c4: i2c4grp {
 		fsl,pins = <
 			MX8MP_IOMUXC_I2C4_SCL__I2C4_SCL				0x400001c3
@@ -552,10 +622,16 @@
 		>;
 	};
 
+	pinctrl_i2c4_gpio: i2c4gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_I2C4_SCL__GPIO5_IO20			0x400001c3
+			MX8MP_IOMUXC_I2C4_SDA__GPIO5_IO21			0x400001c3
+		>;
+	};
+
 	pinctrl_pmic: pmicirqgrp {
 		fsl,pins = <
 			MX8MP_IOMUXC_GPIO1_IO03__GPIO1_IO03			0x41
-			MX8MP_IOMUXC_GPIO1_IO04__GPIO1_IO04			0x41
 		>;
 	};
 
@@ -571,6 +647,12 @@
 		>;
 	};
 
+	pinctrl_reg24v: reg24vgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI2_RXD0__GPIO4_IO23			0x154
+		>;
+	};
+
 	pinctrl_reg_vsd_3v3: regvsd3v3grp {
 		fsl,pins = <
 			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x40
@@ -605,6 +687,8 @@
 			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX			0x140
 			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX			0x140
 			MX8MP_IOMUXC_UART3_RXD__UART1_DTE_RTS			0x140
+			/* CTS pin is not connected, but needed as workaround */
+			MX8MP_IOMUXC_UART3_TXD__UART1_DTE_CTS			0x140
 		>;
 	};
 
@@ -623,6 +707,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d0
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d0
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d0
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT			0xc0
 		>;
 	};
 
@@ -634,6 +719,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d4
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d4
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d4
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT			0xc0
 		>;
 	};
 
@@ -645,6 +731,7 @@
 			MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1			0x1d6
 			MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2			0x1d6
 			MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3			0x1d6
+			MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT			0xc0
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts
index c1ca69da3cb8..32a429437cbd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-hdmi.dts
@@ -9,12 +9,53 @@
 	compatible = "skov,imx8mp-skov-revb-hdmi", "fsl,imx8mp";
 };
 
+&hdmi_pvi {
+	status = "okay";
+};
+
+&hdmi_tx {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hdmi>;
+	ddc-i2c-bus = <&i2c5>;
+	status = "okay";
+};
+
+&hdmi_tx_phy {
+	status = "okay";
+};
+
+&i2c5 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c5>;
+	pinctrl-1 = <&pinctrl_i2c5_gpio>;
+	scl-gpios = <&gpio3 26 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio3 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&lcdif3 {
+	status = "okay";
+};
+
 &iomuxc {
 	pinctrl_hdmi: hdmigrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_HDMI_DDC_SCL__HDMIMIX_HDMI_SCL		0x1c3
-			MX8MP_IOMUXC_HDMI_DDC_SDA__HDMIMIX_HDMI_SDA		0x1c3
 			MX8MP_IOMUXC_HDMI_HPD__HDMIMIX_HDMI_HPD			0x19
 		>;
 	};
+
+	pinctrl_i2c5: i2c5grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_HDMI_DDC_SCL__I2C5_SCL			0x400001c2
+			MX8MP_IOMUXC_HDMI_DDC_SDA__I2C5_SDA			0x400001c2
+		>;
+	};
+
+	pinctrl_i2c5_gpio: i2c5gpiogrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_HDMI_DDC_SCL__GPIO3_IO26			0x400001c2
+			MX8MP_IOMUXC_HDMI_DDC_SDA__GPIO3_IO27			0x400001c2
+		>;
+	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts
index ccbd3abedd69..baecf768a2ee 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-lt6.dts
@@ -8,6 +8,45 @@
 	model = "SKOV IMX8MP CPU revB - LT6";
 	compatible = "skov,imx8mp-skov-revb-lt6", "fsl,imx8mp";
 
+	lvds-decoder {
+		compatible = "ti,sn65lvds822", "lvds-decoder";
+		power-supply = <&reg_3v3>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				in_lvds1: endpoint {
+					data-mapping = "vesa-24";
+					remote-endpoint = <&ldb_lvds_ch1>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lvds_decoder_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+	};
+
+	panel {
+		compatible = "logictechno,lttd800480070-l6wh-rt";
+		backlight = <&backlight>;
+		power-supply = <&reg_tft_vcom>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&lvds_decoder_out>;
+			};
+		};
+	};
+
 	touchscreen {
 		compatible = "resistive-adc-touch";
 		io-channels = <&adc_ts 1>, <&adc_ts 3>, <&adc_ts 4>, <&adc_ts 5>;
@@ -78,6 +117,27 @@
 	};
 };
 
+&lcdif2 {
+	status = "okay";
+};
+
+&lvds_bridge {
+	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>,
+				 <&clk IMX8MP_VIDEO_PLL1>;
+	assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
+	/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_DISP2_PIX * 2 * 7 */
+	assigned-clock-rates = <0>, <462000000>;
+	status = "okay";
+
+	ports {
+		port@2 {
+			ldb_lvds_ch1: endpoint {
+				remote-endpoint = <&in_lvds1>;
+			};
+		};
+	};
+};
+
 &pwm1 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
index 2c75da5f064f..45c9a6d55bc9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
@@ -27,8 +27,6 @@
 
 &i2c2 {
 	clock-frequency = <100000>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_i2c2>;
 	status = "okay";
 
 	touchscreen@38 {
@@ -51,8 +49,11 @@
 };
 
 &lvds_bridge {
-	/* IMX8MP_CLK_MEDIA_LDB = IMX8MP_CLK_MEDIA_DISP2_PIX * 7 */
-	assigned-clock-rates = <490000000>;
+	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>,
+				 <&clk IMX8MP_VIDEO_PLL1>;
+	assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
+	/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_DISP2_PIX * 2 * 7 */
+	assigned-clock-rates = <0>, <980000000>;
 	status = "okay";
 
 	ports {
@@ -64,18 +65,6 @@
 	};
 };
 
-&media_blk_ctrl {
-	/* currently it is not possible to let display clocks confugure
-	 * automatically, so we need to set them manually
-	 */
-	assigned-clock-rates = <500000000>, <200000000>, <0>,
-		/* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */
-		<70000000>,
-		<500000000>,
-		/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB */
-		<490000000>;
-};
-
 &pwm4 {
 	status = "okay";
 };
@@ -90,12 +79,3 @@
 	voltage-table = <3160000 73>;
 	status = "okay";
 };
-
-&iomuxc {
-	pinctrl_i2c2: i2c2grp {
-		fsl,pins = <
-			MX8MP_IOMUXC_I2C2_SCL__I2C2_SCL				0x400001c2
-			MX8MP_IOMUXC_I2C2_SDA__I2C2_SDA				0x400001c2
-		>;
-	};
-};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-bd500.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-bd500.dts
new file mode 100644
index 000000000000..b816c6cd3bca
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-bd500.dts
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU revC - bd500";
+	compatible = "skov,imx8mp-skov-revc-bd500", "fsl,imx8mp";
+
+	leds {
+		led_system_red: led-3 {
+			label = "bd500:system:red";
+			color = <LED_COLOR_ID_RED>;
+			/* Inverted compared to others due to NMOS inverter */
+			gpios = <&gpioexp 3 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led_system_green: led-4 {
+			label = "bd500:system:green";
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&gpioexp 2 GPIO_ACTIVE_LOW>;
+			default-state = "on";
+		};
+
+		led_lan1_red: led-5 {
+			label = "bd500:lan1:act";
+			color = <LED_COLOR_ID_RED>;
+			linux,default-trigger = "netdev";
+			gpios = <&gpioexp 1 GPIO_ACTIVE_LOW>;
+		};
+
+		led_lan1_green: led-6 {
+			label = "bd500:lan1:link";
+			color = <LED_COLOR_ID_GREEN>;
+			linux,default-trigger = "netdev";
+			gpios = <&gpioexp 0 GPIO_ACTIVE_LOW>;
+		};
+
+		led_lan2_red: led-7 {
+			label = "bd500:lan2:act";
+			color = <LED_COLOR_ID_RED>;
+			linux,default-trigger = "netdev";
+			gpios = <&gpioexp 6 GPIO_ACTIVE_LOW>;
+		};
+
+		led_lan2_green: led-8 {
+			label = "bd500:lan2:link";
+			color = <LED_COLOR_ID_GREEN>;
+			linux,default-trigger = "netdev";
+			gpios = <&gpioexp 7 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-1 {
+			label = "S1";
+			linux,code = <KEY_CONFIG>;
+			gpios = <&gpioexp 5 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	status = "okay";
+
+	gpioexp: gpio@20 {
+		compatible = "nxp,pca6408";
+		reg = <0x20>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_exp>;
+		interrupts-extended = <&gpio4 28 IRQ_TYPE_EDGE_FALLING>;
+		reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>;
+		vcc-supply = <&reg_vdd_3v3>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+};
+
+&iomuxc {
+	pinctrl_gpio_exp: gpioexpgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28	0x0
+			MX8MP_IOMUXC_SAI3_RXC__GPIO4_IO29	0x0
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-tian-g07017.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-tian-g07017.dts
new file mode 100644
index 000000000000..9a562c011f2c
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revc-tian-g07017.dts
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/dts-v1/;
+
+#include "imx8mp-skov-reva.dtsi"
+
+/ {
+	model = "SKOV IMX8MP CPU revC - TIAN G07017";
+	compatible = "skov,imx8mp-skov-revc-tian-g07017", "fsl,imx8mp";
+
+	panel {
+		compatible = "topland,tian-g07017-01";
+		backlight = <&backlight>;
+		power-supply = <&reg_tft_vcom>;
+
+		port {
+			in_lvds0: endpoint {
+				remote-endpoint = <&ldb_lvds_ch0>;
+			};
+		};
+	};
+};
+
+&backlight {
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	status = "okay";
+
+	touchscreen@38 {
+		compatible = "edt,edt-ft5506";
+		reg = <0x38>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touchscreen>;
+		interrupts-extended = <&gpio4 28 IRQ_TYPE_EDGE_FALLING>;
+		reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>;
+		touchscreen-size-x = <1024>;
+		touchscreen-size-y = <600>;
+		vcc-supply = <&reg_vdd_3v3>;
+		iovcc-supply = <&reg_vdd_3v3>;
+		wakeup-source;
+	};
+};
+
+&lcdif2 {
+	status = "okay";
+};
+
+&lvds_bridge {
+	assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>,
+				 <&clk IMX8MP_VIDEO_PLL1>;
+	assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
+	/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_DISP2_PIX * 2 * 7 */
+	assigned-clock-rates = <0>, <358400000>;
+	status = "okay";
+
+	ports {
+		port@1 {
+			ldb_lvds_ch0: endpoint {
+				remote-endpoint = <&in_lvds0>;
+			};
+		};
+	};
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&reg_tft_vcom {
+	regulator-min-microvolt = <3160000>;
+	regulator-max-microvolt = <3160000>;
+	voltage-table = <3160000 73>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index ae64731266f3..23c612e80dd3 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -234,7 +234,7 @@
 
 	sound {
 		compatible = "fsl,imx-audio-tlv320aic32x4";
-		model = "tq-tlv320aic32x";
+		model = "tqm-tlv320aic32";
 		audio-cpu = <&sai3>;
 		audio-codec = <&tlv320aic3x04>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
index 336785a9fba8..6067ca3be814 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-or-later OR MIT
 /*
- * Copyright 2021-2022 TQ-Systems GmbH
- * Author: Alexander Stein <alexander.stein@tq-group.com>
+ * Copyright 2021-2025 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
  */
 
 #include "imx8mp.dtsi"
@@ -23,15 +24,6 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 	};
-
-	/* e-MMC IO, needed for HS modes */
-	reg_vcc1v8: regulator-vcc1v8 {
-		compatible = "regulator-fixed";
-		regulator-name = "VCC1V8";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-		regulator-always-on;
-	};
 };
 
 &A53_0 {
@@ -49,6 +41,7 @@
 		spi-max-frequency = <80000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <4>;
+		vcc-supply = <&buck5_reg>;
 
 		partitions {
 			compatible = "fixed-partitions";
@@ -197,7 +190,7 @@
 	no-sd;
 	no-sdio;
 	vmmc-supply = <&reg_vcc3v3>;
-	vqmmc-supply = <&reg_vcc1v8>;
+	vqmmc-supply = <&buck5_reg>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
index b2ac2583a592..b59da91fdd04 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi
@@ -35,7 +35,6 @@
 		      <0x1 0x00000000 0 0xc0000000>;
 	};
 
-
 	reg_usdhc2_vmmc: regulator-usdhc2-vmmc {
 	        compatible = "regulator-fixed";
 	        regulator-name = "VSD_3V3";
@@ -46,6 +45,16 @@
 	        startup-delay-us = <100>;
 	        off-on-delay-us = <12000>;
 	};
+
+	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+		compatible = "regulator-gpio";
+		regulator-name = "VSD_VSEL";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&gpio2 12 GPIO_ACTIVE_HIGH>;
+		states = <3300000 0x0 1800000 0x1>;
+		vin-supply = <&ldo5>;
+	};
 };
 
 &A53_0 {
@@ -205,6 +214,7 @@
         pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
         cd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
         vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&reg_usdhc2_vqmmc>;
         bus-width = <4>;
         status = "okay";
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
index da8902c5f7e5..1493319aa748 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
@@ -28,10 +28,10 @@
 			"Headphone Jack", "HPOUTR",
 			"IN2L", "Line In Jack",
 			"IN2R", "Line In Jack",
-			"Headphone Jack", "MICBIAS",
-			"IN1L", "Headphone Jack";
+			"Microphone Jack", "MICBIAS",
+			"IN1L", "Microphone Jack";
 		simple-audio-card,widgets =
-			"Microphone", "Headphone Jack",
+			"Microphone", "Microphone Jack",
 			"Headphone", "Headphone Jack",
 			"Line", "Line In Jack";
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index e0d3b8cba221..7c1c87eab54c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -816,12 +816,12 @@
 						assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
 								  <&clk IMX8MP_CLK_ML_AXI>,
 								  <&clk IMX8MP_CLK_ML_AHB>;
-						assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+						assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>,
 									 <&clk IMX8MP_SYS_PLL1_800M>,
 									 <&clk IMX8MP_SYS_PLL1_800M>;
-						assigned-clock-rates = <800000000>,
+						assigned-clock-rates = <1000000000>,
 								       <800000000>,
-								       <300000000>;
+								       <400000000>;
 					};
 
 					pgc_audio: power-domain@5 {
@@ -834,7 +834,7 @@
 						assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
 									 <&clk IMX8MP_SYS_PLL1_800M>;
 						assigned-clock-rates = <400000000>,
-								       <600000000>;
+								       <800000000>;
 					};
 
 					pgc_gpu2d: power-domain@6 {
@@ -1619,10 +1619,11 @@
 					 <&clk IMX8MP_CLK_SAI3>,
 					 <&clk IMX8MP_CLK_SAI5>,
 					 <&clk IMX8MP_CLK_SAI6>,
-					 <&clk IMX8MP_CLK_SAI7>;
+					 <&clk IMX8MP_CLK_SAI7>,
+					 <&clk IMX8MP_CLK_AUDIO_AXI_ROOT>;
 				clock-names = "ahb",
 					      "sai1", "sai2", "sai3",
-					      "sai5", "sai6", "sai7";
+					      "sai5", "sai6", "sai7", "axi";
 				power-domains = <&pgc_audio>;
 				assigned-clocks = <&clk IMX8MP_AUDIO_PLL1>,
 						  <&clk IMX8MP_AUDIO_PLL2>;
@@ -1644,6 +1645,12 @@
 					opp-hz = /bits/ 64 <200000000>;
 				};
 
+				/* Nominal drive mode maximum */
+				opp-800000000 {
+					opp-hz = /bits/ 64 <800000000>;
+				};
+
+				/* Overdrive mode maximum */
 				opp-1000000000 {
 					opp-hz = /bits/ 64 <1000000000>;
 				};
@@ -2232,9 +2239,9 @@
 			clock-names = "core", "shader", "bus", "reg";
 			assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>,
 					  <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>;
-			assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
-						 <&clk IMX8MP_SYS_PLL1_800M>;
-			assigned-clock-rates = <800000000>, <800000000>;
+			assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>,
+						 <&clk IMX8MP_SYS_PLL2_1000M>;
+			assigned-clock-rates = <1000000000>, <1000000000>;
 			power-domains = <&pgc_gpu3d>;
 		};
 
@@ -2247,8 +2254,8 @@
 				 <&clk IMX8MP_CLK_GPU_AHB>;
 			clock-names = "core", "bus", "reg";
 			assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>;
-			assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>;
-			assigned-clock-rates = <800000000>;
+			assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>;
+			assigned-clock-rates = <1000000000>;
 			power-domains = <&pgc_gpu2d>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
index 9d8e7231b7c6..d9f203c79519 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5-devkit.dts
@@ -979,24 +979,27 @@
 };
 
 &usb_dwc3_0 {
-	#address-cells = <1>;
-	#size-cells = <0>;
 	dr_mode = "otg";
 	status = "okay";
 
-	port@0 {
-		reg = <0>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
-		typec_hs: endpoint {
-			remote-endpoint = <&usb_con_hs>;
+		port@0 {
+			reg = <0>;
+
+			typec_hs: endpoint {
+				remote-endpoint = <&usb_con_hs>;
+			};
 		};
-	};
 
-	port@1 {
-		reg = <1>;
+		port@1 {
+			reg = <1>;
 
-		typec_ss: endpoint {
-			remote-endpoint = <&usb_con_ss>;
+			typec_ss: endpoint {
+				remote-endpoint = <&usb_con_ss>;
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
index bb37a32ce461..9e0e2d7271ef 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
@@ -794,7 +794,6 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-names = "irq";
-		extcon = <&usb3_phy0>;
 		wakeup-source;
 
 		connector {
@@ -1322,25 +1321,28 @@
 };
 
 &usb_dwc3_0 {
-	#address-cells = <1>;
-	#size-cells = <0>;
 	dr_mode = "otg";
 	usb-role-switch;
 	status = "okay";
 
-	port@0 {
-		reg = <0>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
-		typec_hs: endpoint {
-			remote-endpoint = <&usb_con_hs>;
+		port@0 {
+			reg = <0>;
+
+			typec_hs: endpoint {
+				remote-endpoint = <&usb_con_hs>;
+			};
 		};
-	};
 
-	port@1 {
-		reg = <1>;
+		port@1 {
+			reg = <1>;
 
-		typec_ss: endpoint {
-			remote-endpoint = <&usb_con_ss>;
+			typec_ss: endpoint {
+				remote-endpoint = <&usb_con_ss>;
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
index 01e5092e4c40..c92001c80f11 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
@@ -254,6 +254,7 @@
 		spi-max-frequency = <84000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <4>;
+		vcc-supply = <&nvcc_1v8_reg>;
 
 		partitions {
 			compatible = "fixed-partitions";
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1.dtsi
index 81ba8b2831ac..b1c3f331c4ed 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1.dtsi
@@ -9,8 +9,6 @@
 
 / {
 	model = "Toradex Apalis iMX8QM V1.1";
-	compatible = "toradex,apalis-imx8-v1.1",
-		     "fsl,imx8qm";
 };
 
 /* TODO: Cooling Maps */
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-apalis.dtsi
index 4d6427fbe875..c18f57039f6e 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-apalis.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis.dtsi
@@ -7,8 +7,6 @@
 
 / {
 	model = "Toradex Apalis iMX8QM";
-	compatible = "toradex,apalis-imx8",
-		     "fsl,imx8qm";
 };
 
 &ethphy0 {
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
index 50fd3370f7dc..353f825a8ac5 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
@@ -155,6 +155,13 @@
 		enable-active-high;
 	};
 
+	reg_audio: regulator-audio {
+		compatible = "regulator-fixed";
+		regulator-name = "cs42888_supply";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
 	reg_fec2_supply: regulator-fec2-nvcc {
 		compatible = "regulator-fixed";
 		regulator-name = "fec2_nvcc";
@@ -220,6 +227,33 @@
 		regulator-max-microvolt = <1800000>;
 	};
 
+	reg_audio_5v: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	bt_sco_codec: audio-codec-bt {
 		compatible = "linux,bt-sco";
 		#sound-dai-cells = <1>;
@@ -244,6 +278,26 @@
 		};
 	};
 
+	sound-cs42888 {
+		compatible = "fsl,imx-audio-cs42888";
+		model = "imx-cs42888";
+		audio-cpu = <&esai0>;
+		audio-codec = <&cs42888>;
+		audio-asrc = <&asrc0>;
+		audio-routing = "Line Out Jack", "AOUT1L",
+				"Line Out Jack", "AOUT1R",
+				"Line Out Jack", "AOUT2L",
+				"Line Out Jack", "AOUT2R",
+				"Line Out Jack", "AOUT3L",
+				"Line Out Jack", "AOUT3R",
+				"Line Out Jack", "AOUT4L",
+				"Line Out Jack", "AOUT4R",
+				"AIN1L", "Line In Jack",
+				"AIN1R", "Line In Jack",
+				"AIN2L", "Line In Jack",
+				"AIN2R", "Line In Jack";
+	};
+
 	sound-wm8960 {
 		compatible = "fsl,imx-audio-wm8960";
 		model = "wm8960-audio";
@@ -322,12 +376,44 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 	};
+
+	cs42888: audio-codec@48 {
+		compatible = "cirrus,cs42888";
+		reg = <0x48>;
+		clocks = <&mclkout0_lpcg IMX_LPCG_CLK_0>;
+		clock-names = "mclk";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_cs42888_reset>;
+		VA-supply = <&reg_audio>;
+		VD-supply = <&reg_audio>;
+		VLS-supply = <&reg_audio>;
+		VLC-supply = <&reg_audio>;
+		reset-gpios = <&lsio_gpio4 25 GPIO_ACTIVE_LOW>;
+		assigned-clocks = <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_PLL>,
+				  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_SLV_BUS>,
+				  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_MST_BUS>,
+				  <&mclkout0_lpcg IMX_LPCG_CLK_0>;
+		assigned-clock-rates = <786432000>, <49152000>, <12288000>, <12288000>;
+	};
 };
 
 &cm41_intmux {
 	status = "okay";
 };
 
+&esai0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_esai0>;
+	assigned-clocks = <&acm IMX_ADMA_ACM_ESAI0_MCLK_SEL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_PLL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_SLV_BUS>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_MST_BUS>,
+			  <&esai0_lpcg IMX_LPCG_CLK_4>;
+	assigned-clock-parents = <&aud_pll_div0_lpcg IMX_LPCG_CLK_0>;
+	assigned-clock-rates = <0>, <786432000>, <49152000>, <12288000>, <49152000>;
+	status = "okay";
+};
+
 &hsio_phy {
 	fsl,hsio-cfg = "pciea-pcieb-sata";
 	fsl,refclk-pad-mode = "input";
@@ -439,6 +525,11 @@
 		wlf,shared-lrclk;
 		wlf,hp-cfg = <2 2 3>;
 		wlf,gpio-cfg = <1 3>;
+		AVDD-supply = <&reg_audio_3v3>;
+		DBVDD-supply = <&reg_audio_1v8>;
+		DCVDD-supply = <&reg_audio_1v8>;
+		SPKVDD1-supply = <&reg_audio_5v>;
+		SPKVDD2-supply = <&reg_audio_5v>;
 	};
 };
 
@@ -718,6 +809,12 @@
 		>;
 	};
 
+	pinctrl_cs42888_reset: cs42888_resetgrp {
+		fsl,pins = <
+			IMX8QM_QSPI1A_DATA1_LSIO_GPIO4_IO25			0x0600004c
+		>;
+	};
+
 	pinctrl_i2c0: i2c0grp {
 		fsl,pins = <
 			IMX8QM_HDMI_TX0_TS_SCL_DMA_I2C0_SCL			0x06000021
@@ -752,6 +849,21 @@
 		>;
 	};
 
+	pinctrl_esai0: esai0grp {
+		fsl,pins = <
+			IMX8QM_ESAI0_FSR_AUD_ESAI0_FSR				0xc6000040
+			IMX8QM_ESAI0_FST_AUD_ESAI0_FST				0xc6000040
+			IMX8QM_ESAI0_SCKR_AUD_ESAI0_SCKR			0xc6000040
+			IMX8QM_ESAI0_SCKT_AUD_ESAI0_SCKT			0xc6000040
+			IMX8QM_ESAI0_TX0_AUD_ESAI0_TX0				0xc6000040
+			IMX8QM_ESAI0_TX1_AUD_ESAI0_TX1				0xc6000040
+			IMX8QM_ESAI0_TX2_RX3_AUD_ESAI0_TX2_RX3			0xc6000040
+			IMX8QM_ESAI0_TX3_RX2_AUD_ESAI0_TX3_RX2			0xc6000040
+			IMX8QM_ESAI0_TX4_RX1_AUD_ESAI0_TX4_RX1			0xc6000040
+			IMX8QM_ESAI0_TX5_RX0_AUD_ESAI0_TX5_RX0			0xc6000040
+		>;
+	};
+
 	pinctrl_fec1: fec1grp {
 		fsl,pins = <
 			IMX8QM_ENET0_MDC_CONN_ENET0_MDC				0x06000020
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-hsio.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-hsio.dtsi
index b1d0189a1725..e80f722dbe65 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-hsio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-hsio.dtsi
@@ -42,6 +42,25 @@
 		status = "disabled";
 	};
 
+	pciea_ep: pcie-ep@5f000000 {
+		compatible = "fsl,imx8q-pcie-ep";
+		reg = <0x5f000000 0x00010000>,
+		      <0x40000000 0x10000000>;
+		reg-names = "dbi", "addr_space";
+		num-lanes = <1>;
+		interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "dma";
+		clocks = <&pciea_lpcg IMX_LPCG_CLK_6>,
+			 <&pciea_lpcg IMX_LPCG_CLK_4>,
+			 <&pciea_lpcg IMX_LPCG_CLK_5>;
+		clock-names = "dbi", "mstr", "slv";
+		power-domains = <&pd IMX_SC_R_PCIE_A>;
+		fsl,max-link-speed = <3>;
+		num-ib-windows = <6>;
+		num-ob-windows = <6>;
+		status = "disabled";
+	};
+
 	pcieb: pcie@5f010000 {
 		compatible = "fsl,imx8q-pcie";
 		reg = <0x5f010000 0x10000>,
@@ -50,8 +69,9 @@
 		ranges = <0x81000000 0 0x00000000 0x8ff80000 0 0x00010000>,
 			 <0x82000000 0 0x80000000 0x80000000 0 0x0ff00000>;
 		#interrupt-cells = <1>;
-		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "msi";
+		interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "msi", "dma";
 		#address-cells = <3>;
 		#size-cells = <2>;
 		clocks = <&pcieb_lpcg IMX_LPCG_CLK_6>,
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek-pcie-ep.dtso b/arch/arm64/boot/dts/freescale/imx8qxp-mek-pcie-ep.dtso
new file mode 100644
index 000000000000..4f562eb5c5b1
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek-pcie-ep.dtso
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2025 NXP
+ */
+
+#include <dt-bindings/phy/phy.h>
+
+/dts-v1/;
+/plugin/;
+
+&pcieb {
+	status = "disabled";
+};
+
+&pcieb_ep {
+	phys = <&hsio_phy 0 PHY_TYPE_PCIE 0>;
+	phy-names = "pcie-phy";
+	pinctrl-0 = <&pinctrl_pcieb>;
+	pinctrl-names = "default";
+	vpcie-supply = <&reg_pcieb>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
index be79c793213a..a669a5d500d3 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
@@ -98,6 +98,33 @@
 		regulator-name = "cs42888_supply";
 	};
 
+	reg_audio_5v: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_3v3: regulator-audio-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_audio_1v8: regulator-audio-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "audio-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	reg_can_en: regulator-can-en {
 		compatible = "regulator-fixed";
 		regulator-max-microvolt = <3300000>;
@@ -418,6 +445,11 @@
 		wlf,shared-lrclk;
 		wlf,hp-cfg = <2 2 3>;
 		wlf,gpio-cfg = <1 3>;
+		AVDD-supply = <&reg_audio_3v3>;
+		DBVDD-supply = <&reg_audio_1v8>;
+		DCVDD-supply = <&reg_audio_1v8>;
+		SPKVDD1-supply = <&reg_audio_5v>;
+		SPKVDD2-supply = <&reg_audio_5v>;
 	};
 
 	pca6416: gpio@20 {
diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi
index d5abfdb8ede2..ecb35c6b67f5 100644
--- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi
@@ -295,8 +295,8 @@
 			  "",
 			  "SODIMM_61",
 			  "SODIMM_103",
-			  "",
-			  "",
+			  "SODIMM_79",
+			  "SODIMM_97",
 			  "",
 			  "SODIMM_25",
 			  "SODIMM_27",
diff --git a/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
index 47c1363a2f99..119a16207059 100644
--- a/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-kontron-osm-s.dtsi
@@ -189,6 +189,7 @@
 				regulator-name = "NVCC_SD (LDO5)";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
+				nxp,sd-vsel-fixed-low;
 			};
 		};
 	};
@@ -282,6 +283,7 @@
 	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>;
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
 	vmmc-supply = <&reg_usdhc2_vcc>;
+	vqmmc-supply = <&reg_nvcc_sd>;
 	cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
 };
 
@@ -553,7 +555,6 @@
 			MX93_PAD_SD2_DATA1__USDHC2_DATA1		0x40001382 /* SDIO_A_D1 */
 			MX93_PAD_SD2_DATA2__USDHC2_DATA2		0x40001382 /* SDIO_A_D2 */
 			MX93_PAD_SD2_DATA3__USDHC2_DATA3		0x40001382 /* SDIO_A_D3 */
-			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT		0x1d0
 		>;
 	};
 
@@ -565,7 +566,6 @@
 			MX93_PAD_SD2_DATA1__USDHC2_DATA1		0x4000138e /* SDIO_A_D1 */
 			MX93_PAD_SD2_DATA2__USDHC2_DATA2		0x4000138e /* SDIO_A_D2 */
 			MX93_PAD_SD2_DATA3__USDHC2_DATA3		0x4000138e /* SDIO_A_D3 */
-			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT		0x1d0
 		>;
 	};
 
@@ -577,7 +577,6 @@
 			MX93_PAD_SD2_DATA1__USDHC2_DATA1		0x400013fe /* SDIO_A_D1 */
 			MX93_PAD_SD2_DATA2__USDHC2_DATA2		0x400013fe /* SDIO_A_D2 */
 			MX93_PAD_SD2_DATA3__USDHC2_DATA3		0x400013fe /* SDIO_A_D3 */
-			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT		0x1d0
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts
index 8e939d716aac..ebbac5f8d2b2 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
 /*
- * Copyright (c) 2022-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * Copyright (c) 2022-2024 TQ-Systems GmbH <linux@ew.tq-group.com>,
  * D-82229 Seefeld, Germany.
  * Author: Markus Niebel
  * Author: Alexander Stein
@@ -26,8 +26,8 @@
 
 	aliases {
 		eeprom0 = &eeprom0;
-		ethernet0 = &fec;
-		ethernet1 = &eqos;
+		ethernet0 = &eqos;
+		ethernet1 = &fec;
 		rtc0 = &pcf85063;
 		rtc1 = &bbnsm_rtc;
 	};
@@ -448,38 +448,38 @@
 				  "WLAN_PERST#", "12V_EN";
 
 		/*
-		 * Controls the WiFi card PD pin which is low active
-		 * as power down signal. The output-high states, the signal
-		 * is active, e.g. card is powered down
+		 * Controls the WiFi card's low-active power down pin.
+		 * The output-low states, the signal is inactive,
+		 * resulting in high signal at power-down pin
 		 */
 		wlan-pd-hog {
 			gpio-hog;
 			gpios = <4 GPIO_ACTIVE_LOW>;
-			output-high;
+			output-low;
 			line-name = "WLAN_PD#";
 		};
 
 		/*
-		 * Controls the WiFi card disable pin which is low active
-		 * as disable signal. The output-high states, the signal
-		 * is active, e.g. card is disabled
+		 * Controls the WiFi card's low-active disable pin.
+		 * The output-low states, the signal is inactive,
+		 * resulting in high signal at power-down pin
 		 */
 		wlan-wdisable-hog {
 			gpio-hog;
 			gpios = <5 GPIO_ACTIVE_LOW>;
-			output-high;
+			output-low;
 			line-name = "WLAN_W_DISABLE#";
 		};
 
 		/*
-		 * Controls the WiFi card reset pin which is low active
-		 * as reset signal. The output-high states, the signal
-		 * is active, e.g. card in reset
+		 * Controls the WiFi card's reset pin.
+		 * The output-low states, the signal is inactive,
+		 * resulting in high signal at power-down pin
 		 */
 		wlan-perst-hog {
 			gpio-hog;
 			gpios = <6 GPIO_ACTIVE_LOW>;
-			output-high;
+			output-low;
 			line-name = "WLAN_PERST#";
 		};
 	};
@@ -755,12 +755,6 @@
 		>;
 	};
 
-	pinctrl_pcf85063: pcf85063grp {
-		fsl,pins = <
-			MX93_PAD_SAI1_RXD0__GPIO1_IO14			0x1000
-		>;
-	};
-
 	pinctrl_mipi_csi: mipicsigrp {
 		fsl,pins = <
 			MX93_PAD_CCM_CLKO3__CCMSRCGPCMIX_CLKO3		0x051e /* MCLK */
@@ -769,6 +763,12 @@
 		>;
 	};
 
+	pinctrl_pcf85063: pcf85063grp {
+		fsl,pins = <
+			MX93_PAD_SAI1_RXD0__GPIO1_IO14			0x1000
+		>;
+	};
+
 	pinctrl_pexp_irq: pexpirqgrp {
 		fsl,pins = <
 			/* HYS | FSEL_0 | No DSE */
@@ -783,17 +783,17 @@
 		>;
 	};
 
-	pinctrl_temp_sensor_som: tempsensorsomgrp {
+	pinctrl_tc9595: tc9595-grp {
 		fsl,pins = <
-			/* HYS | FSEL_0 | no DSE */
-			MX93_PAD_SAI1_TXFS__GPIO1_IO11			0x1000
+			/* HYS | PD | FSEL_0 | no DSE */
+			MX93_PAD_CCM_CLKO4__GPIO4_IO29			0x1400
 		>;
 	};
 
-	pinctrl_tc9595: tc9595-grp {
+	pinctrl_temp_sensor_som: tempsensorsomgrp {
 		fsl,pins = <
-			/* HYS | PD | FSEL_0 | no DSE */
-			MX93_PAD_CCM_CLKO4__GPIO4_IO29			0x1400
+			/* HYS | FSEL_0 | no DSE */
+			MX93_PAD_SAI1_TXFS__GPIO1_IO11			0x1000
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
index 2e953a05c590..9e88c42c3d17 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
 /*
- * Copyright (c) 2022-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * Copyright (c) 2022-2024 TQ-Systems GmbH <linux@ew.tq-group.com>,
  * D-82229 Seefeld, Germany.
  * Author: Markus Niebel
  * Author: Alexander Stein
@@ -26,8 +26,8 @@
 
 	aliases {
 		eeprom0 = &eeprom0;
-		ethernet0 = &fec;
-		ethernet1 = &eqos;
+		ethernet0 = &eqos;
+		ethernet1 = &fec;
 		rtc0 = &pcf85063;
 		rtc1 = &bbnsm_rtc;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index 56766fdb0b1e..64cd0776b43d 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -1334,6 +1334,14 @@
 			#index-cells = <1>;
 		};
 
+		memory-controller@4e300000 {
+			compatible = "nxp,imx9-memory-controller";
+			reg = <0x4e300000 0x800>, <0x4e301000 0x1000>;
+			reg-names = "ctrl", "inject";
+			interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+			little-endian;
+		};
+
 		ddr-pmu@4e300dc0 {
 			compatible = "fsl,imx93-ddr-pmu";
 			reg = <0x4e300dc0 0x200>;
diff --git a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts
new file mode 100644
index 000000000000..514f2429dcbc
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts
@@ -0,0 +1,1130 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2025 NXP
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/i3c/i3c.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/phy/phy-imx8-pcie.h>
+#include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/usb/pd.h>
+#include "imx95.dtsi"
+
+#define FALLING_EDGE		BIT(0)
+#define RISING_EDGE		BIT(1)
+
+#define BRD_SM_CTRL_SD3_WAKE		0x8000
+#define BRD_SM_CTRL_PCIE1_WAKE		0x8001
+#define BRD_SM_CTRL_BT_WAKE		0x8002
+#define BRD_SM_CTRL_PCIE2_WAKE		0x8003
+#define BRD_SM_CTRL_BUTTON		0x8004
+
+/ {
+	compatible = "fsl,imx95-15x15-evk", "fsl,imx95";
+	model = "NXP i.MX95 15X15 board";
+
+	aliases {
+		ethernet0 = &enetc_port0;
+		ethernet1 = &enetc_port1;
+		serial0 = &lpuart1;
+	};
+
+	bt_sco_codec: bt-sco-codec {
+		compatible = "linux,bt-sco";
+		#sound-dai-cells = <1>;
+	};
+
+	chosen {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		stdout-path = &lpuart1;
+	};
+
+	fan0: pwm-fan {
+		compatible = "pwm-fan";
+		#cooling-cells = <2>;
+		cooling-levels = <64 128 192 255>;
+		pwms = <&tpm6 0 4000000 PWM_POLARITY_INVERTED>;
+	};
+
+	reg_1p8v: regulator-1p8v {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <1800000>;
+		regulator-min-microvolt = <1800000>;
+		regulator-name = "+V1.8_SW";
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "+V3.3_SW";
+	};
+
+	reg_vref_1v8: regulator-adc-vref {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <1800000>;
+		regulator-min-microvolt = <1800000>;
+		regulator-name = "vref_1v8";
+	};
+
+	reg_audio_pwr: regulator-audio-pwr {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "audio-pwr";
+		gpio = <&pcal6524 13 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_audio_switch1: regulator-audio-switch1 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "audio-switch1";
+		gpio = <&pcal6524 0 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_can2_stby: regulator-can2-stby {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "can2-stby";
+		gpio = <&pcal6524 14 GPIO_ACTIVE_LOW>;
+	};
+
+	reg_m2_pwr: regulator-m2-pwr {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "M.2-power";
+		gpio = <&pcal6524 10 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usdhc2_vmmc: regulator-usdhc2 {
+		compatible = "regulator-fixed";
+		off-on-delay-us = <12000>;
+		pinctrl-0 = <&pinctrl_reg_usdhc2_vmmc>;
+		pinctrl-names = "default";
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "VDD_SD2_3V3";
+		gpio = <&gpio3 7 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usdhc3_vmmc: regulator-usdhc3 {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "WLAN_EN";
+		vin-supply = <&reg_m2_pwr>;
+		gpio = <&pcal6524 11 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		/*
+		 * IW612 wifi chip needs more delay than other wifi chips to complete
+		 * the host interface initialization after power up, otherwise the
+		 * internal state of IW612 may be unstable, resulting in the failure of
+		 * the SDIO3.0 switch voltage.
+		 */
+		startup-delay-us = <20000>;
+	};
+
+	reg_vcc_12v: regulator-vcc-12v {
+		compatible = "regulator-fixed";
+		regulator-max-microvolt = <12000000>;
+		regulator-min-microvolt = <12000000>;
+		regulator-name = "VCC_12V";
+		gpio = <&pcal6524 1 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reserved-memory {
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		linux_cma: linux,cma {
+			compatible = "shared-dma-pool";
+			alloc-ranges = <0 0x80000000 0 0x7F000000>;
+			reusable;
+			size = <0 0x3c000000>;
+			linux,cma-default;
+		};
+
+		vdev0vring0: vdev0vring0@88000000 {
+			reg = <0 0x88000000 0 0x8000>;
+			no-map;
+		};
+
+		vdev0vring1: vdev0vring1@88008000 {
+			reg = <0 0x88008000 0 0x8000>;
+			no-map;
+		};
+
+		vdev1vring0: vdev1vring0@88010000 {
+			reg = <0 0x88010000 0 0x8000>;
+			no-map;
+		};
+
+		vdev1vring1: vdev1vring1@88018000 {
+			reg = <0 0x88018000 0 0x8000>;
+			no-map;
+		};
+
+		vdevbuffer: vdevbuffer@88020000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x88020000 0 0x100000>;
+			no-map;
+		};
+
+		rsc_table: rsc-table@88220000 {
+			reg = <0 0x88220000 0 0x1000>;
+			no-map;
+		};
+
+		vpu_boot: vpu_boot@a0000000 {
+			reg = <0 0xa0000000 0 0x100000>;
+			no-map;
+		};
+	};
+
+	sound-bt-sco {
+		compatible = "simple-audio-card";
+		simple-audio-card,bitclock-inversion;
+		simple-audio-card,bitclock-master = <&btcpu>;
+		simple-audio-card,format = "dsp_a";
+		simple-audio-card,frame-master = <&btcpu>;
+		simple-audio-card,name = "bt-sco-audio";
+
+		simple-audio-card,codec {
+			sound-dai = <&bt_sco_codec 1>;
+		};
+
+		btcpu: simple-audio-card,cpu {
+			dai-tdm-slot-num = <2>;
+			dai-tdm-slot-width = <16>;
+			sound-dai = <&sai1>;
+		};
+	};
+
+	sound-micfil {
+		compatible = "fsl,imx-audio-card";
+		model = "micfil-audio";
+
+		pri-dai-link {
+			format = "i2s";
+			link-name = "micfil hifi";
+
+			cpu {
+				sound-dai = <&micfil>;
+			};
+		};
+	};
+
+	sound-wm8962 {
+		compatible = "fsl,imx-audio-wm8962";
+		audio-codec = <&wm8962>;
+		audio-cpu = <&sai3>;
+		audio-routing = "Headphone Jack", "HPOUTL", "Headphone Jack", "HPOUTR",
+				"Ext Spk", "SPKOUTL", "Ext Spk", "SPKOUTR", "AMIC", "MICBIAS",
+				"IN3R", "AMIC", "IN1R", "AMIC";
+		hp-det-gpio = <&gpio2 21 GPIO_ACTIVE_HIGH>;
+		model = "wm8962-audio";
+		pinctrl-0 = <&pinctrl_hp>;
+		pinctrl-names = "default";
+	};
+
+	sound-xcvr {
+		compatible = "fsl,imx-audio-card";
+		model = "imx-audio-xcvr";
+
+		pri-dai-link {
+			link-name = "XCVR PCM";
+
+			cpu {
+				sound-dai = <&xcvr>;
+			};
+		};
+	};
+
+	usdhc3_pwrseq: usdhc3-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-0 = <&pinctrl_usdhc3_pwrseq>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+	};
+
+	memory@80000000 {
+		reg = <0x0 0x80000000 0 0x80000000>;
+		device_type = "memory";
+	};
+};
+
+&adc1 {
+	vref-supply = <&reg_vref_1v8>;
+	status = "okay";
+};
+
+&enetc_port0 {
+	phy-handle = <&ethphy0>;
+	phy-mode = "rgmii-id";
+	pinctrl-0 = <&pinctrl_enetc0>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&enetc_port1 {
+	phy-handle = <&ethphy1>;
+	phy-mode = "rgmii-id";
+	pinctrl-0 = <&pinctrl_enetc1>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&flexcan2 {
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	pinctrl-names = "default";
+	xceiver-supply = <&reg_can2_stby>;
+	status = "okay";
+};
+
+&i3c2 {
+	i2c-scl-hz = <400000>;
+	pinctrl-0 = <&pinctrl_i3c2>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	pca9570: gpio@24 {
+		compatible = "nxp,pca9570";
+		reg = <0x24 0 (I2C_FILTER)>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-line-names = "OUT1", "OUT2", "OUT3", "OUT4";
+	};
+};
+
+&lpi2c2 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&pinctrl_lpi2c2>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	wm8962: codec@1a {
+		compatible = "wlf,wm8962";
+		reg = <0x1a>;
+		clocks = <&scmi_clk IMX95_CLK_SAI3>;
+		AVDD-supply = <&reg_audio_pwr>;
+		CPVDD-supply = <&reg_audio_pwr>;
+		DBVDD-supply = <&reg_audio_pwr>;
+		DCVDD-supply = <&reg_audio_pwr>;
+		gpio-cfg = <
+			0x0000
+			0x0000
+			0x0000
+			0x0000
+			0x0000
+			0x0000
+		>;
+		MICVDD-supply = <&reg_audio_pwr>;
+		PLLVDD-supply = <&reg_audio_pwr>;
+		SPKVDD1-supply = <&reg_audio_pwr>;
+		SPKVDD2-supply = <&reg_audio_pwr>;
+	};
+
+	pcal6524: gpio@22 {
+		compatible = "nxp,pcal6524";
+		reg = <0x22>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		interrupt-parent = <&gpio5>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		pinctrl-0 = <&pinctrl_pcal6524>;
+		pinctrl-names = "default";
+	};
+};
+
+&lpi2c3 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&pinctrl_lpi2c3>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	ptn5110: tcpc@50 {
+		compatible = "nxp,ptn5110", "tcpci";
+		reg = <0x50>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-0 = <&pinctrl_ptn5110>;
+		pinctrl-names = "default";
+
+		typec_con: connector {
+			compatible = "usb-c-connector";
+			data-role = "dual";
+			label = "USB-C";
+			op-sink-microwatt = <15000000>;
+			power-role = "dual";
+			self-powered;
+			sink-pdos = <PDO_FIXED(5000, 3000, PDO_FIXED_USB_COMM)
+				     PDO_VAR(5000, 20000, 3000)>;
+			source-pdos = <PDO_FIXED(5000, 3000, PDO_FIXED_USB_COMM)>;
+			try-power-role = "sink";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					typec_con_hs: endpoint {
+						remote-endpoint = <&usb3_data_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					typec_con_ss: endpoint {
+						remote-endpoint = <&usb3_data_ss>;
+					};
+				};
+			};
+		};
+	};
+
+	pca9632: led-controller@62 {
+		compatible = "nxp,pca9632";
+		reg = <0x62>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		nxp,inverted-out;
+
+		led_backlight0: led@0 {
+			reg = <0>;
+			color = <LED_COLOR_ID_WHITE>;
+			function = LED_FUNCTION_BACKLIGHT;
+			function-enumerator = <0>;
+		};
+
+		led_backlight1: led@1 {
+			reg = <1>;
+			color = <LED_COLOR_ID_WHITE>;
+			function = LED_FUNCTION_BACKLIGHT;
+			function-enumerator = <1>;
+		};
+	};
+};
+
+&lpi2c4 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&pinctrl_lpi2c4>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&lpi2c6 {
+	clock-frequency = <100000>;
+	pinctrl-0 = <&pinctrl_lpi2c6>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&lpuart1 {
+	pinctrl-0 = <&pinctrl_uart1>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&lpuart5 {
+	pinctrl-0 = <&pinctrl_uart5>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	bluetooth {
+		compatible = "nxp,88w8987-bt";
+	};
+};
+
+&micfil {
+	assigned-clocks = <&scmi_clk IMX95_CLK_AUDIOPLL1_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2>,
+			  <&scmi_clk IMX95_CLK_PDM>;
+	assigned-clock-parents = <0>, <0>, <0>, <0>, <&scmi_clk IMX95_CLK_AUDIOPLL1>;
+	assigned-clock-rates = <3932160000>, <3612672000>, <393216000>, <361267200>, <49152000>;
+	#sound-dai-cells = <0>;
+	pinctrl-0 = <&pinctrl_pdm>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&mu7 {
+	status = "okay";
+};
+
+&netc_blk_ctrl {
+	status = "okay";
+};
+
+&netc_bus0 {
+	msi-map = <0x00 &its 0x60 0x1>,	//ENETC0 PF
+		  <0x10 &its 0x61 0x1>, //ENETC0 VF0
+		  <0x20 &its 0x62 0x1>, //ENETC0 VF1
+		  <0x40 &its 0x63 0x1>, //ENETC1 PF
+		  <0x50 &its 0x65 0x1>, //ENETC1 VF0
+		  <0x60 &its 0x66 0x1>, //ENETC1 VF1
+		  <0x80 &its 0x64 0x1>, //ENETC2 PF
+		  <0xc0 &its 0x67 0x1>;
+};
+
+&netc_emdio {
+	pinctrl-0 = <&pinctrl_emdio>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	ethphy0: ethernet-phy@1 {
+		reg = <1>;
+		reset-assert-us = <10000>;
+		reset-deassert-us = <80000>;
+		reset-gpios = <&pcal6524 4 GPIO_ACTIVE_LOW>;
+		realtek,clkout-disable;
+	};
+
+	ethphy1: ethernet-phy@2 {
+		reg = <2>;
+		reset-assert-us = <10000>;
+		reset-deassert-us = <80000>;
+		reset-gpios = <&pcal6524 5 GPIO_ACTIVE_LOW>;
+		realtek,clkout-disable;
+	};
+};
+
+&netc_timer {
+	status = "okay";
+};
+
+&netcmix_blk_ctrl {
+	status = "okay";
+};
+
+&pcie0 {
+	pinctrl-0 = <&pinctrl_pcie0>;
+	pinctrl-names = "default";
+	reset-gpio = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	vpcie-supply = <&reg_m2_pwr>;
+	status = "okay";
+};
+
+&sai1 {
+	assigned-clocks = <&scmi_clk IMX95_CLK_AUDIOPLL1_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2>,
+			  <&scmi_clk IMX95_CLK_SAI1>;
+	assigned-clock-parents = <0>, <0>, <0>, <0>, <&scmi_clk IMX95_CLK_AUDIOPLL1>;
+	assigned-clock-rates = <3932160000>, <3612672000>, <393216000>, <361267200>, <12288000>;
+	#sound-dai-cells = <0>;
+	pinctrl-0 = <&pinctrl_sai1>;
+	pinctrl-names = "default";
+	fsl,sai-mclk-direction-output;
+	status = "okay";
+};
+
+&sai3 {
+	assigned-clocks = <&scmi_clk IMX95_CLK_AUDIOPLL1_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2>,
+			  <&scmi_clk IMX95_CLK_SAI3>;
+	assigned-clock-parents = <0>, <0>, <0>, <0>, <&scmi_clk IMX95_CLK_AUDIOPLL1>;
+	assigned-clock-rates = <3932160000>, <3612672000>, <393216000>, <361267200>, <12288000>;
+	#sound-dai-cells = <0>;
+	pinctrl-0 = <&pinctrl_sai3>;
+	pinctrl-names = "default";
+	fsl,sai-mclk-direction-output;
+	status = "okay";
+};
+
+&scmi_iomuxc {
+	pinctrl_emdio: emdiogrp {
+		fsl,pins = <
+			IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC		0x57e
+			IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO		0x97e
+		>;
+	};
+
+	pinctrl_enetc0: enetc0grp {
+		fsl,pins = <
+			IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3		0x57e
+			IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2		0x57e
+			IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1		0x57e
+			IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0		0x57e
+			IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL	0x57e
+			IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK	0x58e
+			IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL	0x57e
+			IMX95_PAD_ENET1_RXC__NETCMIX_TOP_ETH0_RGMII_RX_CLK	0x58e
+			IMX95_PAD_ENET1_RD0__NETCMIX_TOP_ETH0_RGMII_RD0		0x57e
+			IMX95_PAD_ENET1_RD1__NETCMIX_TOP_ETH0_RGMII_RD1		0x57e
+			IMX95_PAD_ENET1_RD2__NETCMIX_TOP_ETH0_RGMII_RD2		0x57e
+			IMX95_PAD_ENET1_RD3__NETCMIX_TOP_ETH0_RGMII_RD3		0x57e
+		>;
+	};
+
+	pinctrl_enetc1: enetc1grp {
+		fsl,pins = <
+			IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3		0x57e
+			IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2		0x57e
+			IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1		0x57e
+			IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0		0x57e
+			IMX95_PAD_ENET2_TX_CTL__NETCMIX_TOP_ETH1_RGMII_TX_CTL	0x57e
+			IMX95_PAD_ENET2_TXC__NETCMIX_TOP_ETH1_RGMII_TX_CLK	0x58e
+			IMX95_PAD_ENET2_RX_CTL__NETCMIX_TOP_ETH1_RGMII_RX_CTL	0x57e
+			IMX95_PAD_ENET2_RXC__NETCMIX_TOP_ETH1_RGMII_RX_CLK	0x58e
+			IMX95_PAD_ENET2_RD0__NETCMIX_TOP_ETH1_RGMII_RD0		0x57e
+			IMX95_PAD_ENET2_RD1__NETCMIX_TOP_ETH1_RGMII_RD1		0x57e
+			IMX95_PAD_ENET2_RD2__NETCMIX_TOP_ETH1_RGMII_RD2		0x57e
+			IMX95_PAD_ENET2_RD3__NETCMIX_TOP_ETH1_RGMII_RD3		0x57e
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO25__CAN2_TX				0x39e
+			IMX95_PAD_GPIO_IO27__CAN2_RX				0x39e
+		>;
+	};
+
+	pinctrl_hp: hpgrp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO21__GPIO2_IO_BIT21			0x31e
+		>;
+	};
+
+	pinctrl_i3c2: i3c2grp {
+		fsl,pins = <
+			IMX95_PAD_ENET1_MDC__I3C2_SCL				0x40000186
+			IMX95_PAD_ENET1_MDIO__I3C2_SDA				0x40000186
+		>;
+	};
+
+	pinctrl_lpi2c1: lpi2c1grp {
+		fsl,pins = <
+			IMX95_PAD_I2C1_SCL__AONMIX_TOP_LPI2C1_SCL		0x40000b9e
+			IMX95_PAD_I2C1_SDA__AONMIX_TOP_LPI2C1_SDA		0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c2: lpi2c2grp {
+		fsl,pins = <
+			IMX95_PAD_I2C2_SCL__AONMIX_TOP_LPI2C2_SCL		0x40000b9e
+			IMX95_PAD_I2C2_SDA__AONMIX_TOP_LPI2C2_SDA		0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c3: lpi2c3grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO28__LPI2C3_SDA				0x40000b9e
+			IMX95_PAD_GPIO_IO29__LPI2C3_SCL				0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c4: lpi2c4grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO30__LPI2C4_SDA				0x40000b9e
+			IMX95_PAD_GPIO_IO31__LPI2C4_SCL				0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c6: lpi2c6grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO02__LPI2C6_SDA				0x40000b9e
+			IMX95_PAD_GPIO_IO03__LPI2C6_SCL				0x40000b9e
+		>;
+	};
+
+	pinctrl_mipi_dsi_csi: mipidsigrp {
+		fsl,pins = <
+			IMX95_PAD_XSPI1_DATA6__GPIO5_IO_BIT6			0x31e
+		>;
+	};
+
+	pinctrl_pcal6524: pcal6524grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO34__GPIO5_IO_BIT14			0x31e
+		>;
+	};
+
+	pinctrl_pcie0: pcie0grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO32__HSIOMIX_TOP_PCIE1_CLKREQ_B		0x40000b1e
+			IMX95_PAD_GPIO_IO33__GPIO5_IO_BIT13			0x31e
+		>;
+	};
+
+	pinctrl_pdm: pdmgrp {
+		fsl,pins = <
+			IMX95_PAD_PDM_CLK__AONMIX_TOP_PDM_CLK				0x31e
+			IMX95_PAD_PDM_BIT_STREAM0__AONMIX_TOP_PDM_BIT_STREAM_BIT0	0x31e
+		>;
+	};
+
+	pinctrl_ptn5110: ptn5110grp {
+		fsl,pins = <
+			IMX95_PAD_XSPI1_SS1_B__GPIO5_IO_BIT11			0x31e
+		>;
+	};
+
+	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
+		fsl,pins = <
+			IMX95_PAD_SD2_RESET_B__GPIO3_IO_BIT7			0x31e
+		>;
+	};
+
+	pinctrl_sai1: sai1grp {
+		fsl,pins = <
+			IMX95_PAD_SAI1_RXD0__AONMIX_TOP_SAI1_RX_DATA_BIT0	0x31e
+			IMX95_PAD_SAI1_TXC__AONMIX_TOP_SAI1_TX_BCLK		0x31e
+			IMX95_PAD_SAI1_TXFS__AONMIX_TOP_SAI1_TX_SYNC		0x31e
+			IMX95_PAD_SAI1_TXD0__AONMIX_TOP_SAI1_TX_DATA_BIT0	0x31e
+		>;
+	};
+
+	pinctrl_sai2: sai2grp {
+		fsl,pins = <
+			IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_SAI2_RX_BCLK		0x31e
+			IMX95_PAD_ENET2_MDC__NETCMIX_TOP_SAI2_RX_SYNC		0x31e
+			IMX95_PAD_ENET2_TD3__NETCMIX_TOP_SAI2_RX_DATA_BIT0	0x31e
+			IMX95_PAD_ENET2_TD2__NETCMIX_TOP_SAI2_RX_DATA_BIT1	0x31e
+			IMX95_PAD_ENET2_TXC__NETCMIX_TOP_SAI2_TX_BCLK		0x31e
+			IMX95_PAD_ENET2_TX_CTL__NETCMIX_TOP_SAI2_TX_SYNC	0x31e
+			IMX95_PAD_ENET2_RX_CTL__NETCMIX_TOP_SAI2_TX_DATA_BIT0	0x31e
+			IMX95_PAD_ENET2_RXC__NETCMIX_TOP_SAI2_TX_DATA_BIT1	0x31e
+			IMX95_PAD_ENET2_RD0__NETCMIX_TOP_SAI2_TX_DATA_BIT2	0x31e
+			IMX95_PAD_ENET2_RD1__NETCMIX_TOP_SAI2_TX_DATA_BIT3	0x31e
+			IMX95_PAD_ENET2_RD2__NETCMIX_TOP_SAI2_MCLK		0x31e
+		>;
+	};
+
+	pinctrl_sai3: sai3grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO17__SAI3_MCLK				0x31e
+			IMX95_PAD_GPIO_IO16__SAI3_TX_BCLK			0x31e
+			IMX95_PAD_GPIO_IO26__SAI3_TX_SYNC			0x31e
+			IMX95_PAD_GPIO_IO20__SAI3_RX_DATA_BIT0			0x31e
+			IMX95_PAD_GPIO_IO19__SAI3_TX_DATA_BIT0			0x31e
+		>;
+	};
+
+	pinctrl_spdif: spdifgrp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO22__SPDIF_IN				0x3fe
+			IMX95_PAD_GPIO_IO23__SPDIF_OUT				0x3fe
+		>;
+	};
+
+	pinctrl_tpm3: tpm3grp {
+		fsl,pins = <
+			IMX95_PAD_CCM_CLKO2__GPIO3_IO_BIT27			0x51e
+		>;
+	};
+
+	pinctrl_tpm6: tpm6grp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO08__TPM6_CH0				0x51e
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			IMX95_PAD_UART1_RXD__AONMIX_TOP_LPUART1_RX		0x31e
+			IMX95_PAD_UART1_TXD__AONMIX_TOP_LPUART1_TX		0x31e
+		>;
+	};
+
+	pinctrl_uart5: uart5grp {
+		fsl,pins = <
+			IMX95_PAD_DAP_TDO_TRACESWO__LPUART5_TX			0x31e
+			IMX95_PAD_DAP_TDI__LPUART5_RX				0x31e
+			IMX95_PAD_DAP_TMS_SWDIO__LPUART5_RTS_B			0x31e
+			IMX95_PAD_DAP_TCLK_SWCLK__LPUART5_CTS_B			0x31e
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			IMX95_PAD_SD1_CLK__USDHC1_CLK				0x158e
+			IMX95_PAD_SD1_CMD__USDHC1_CMD				0x138e
+			IMX95_PAD_SD1_DATA0__USDHC1_DATA0			0x138e
+			IMX95_PAD_SD1_DATA1__USDHC1_DATA1			0x138e
+			IMX95_PAD_SD1_DATA2__USDHC1_DATA2			0x138e
+			IMX95_PAD_SD1_DATA3__USDHC1_DATA3			0x138e
+			IMX95_PAD_SD1_DATA4__USDHC1_DATA4			0x138e
+			IMX95_PAD_SD1_DATA5__USDHC1_DATA5			0x138e
+			IMX95_PAD_SD1_DATA6__USDHC1_DATA6			0x138e
+			IMX95_PAD_SD1_DATA7__USDHC1_DATA7			0x138e
+			IMX95_PAD_SD1_STROBE__USDHC1_STROBE			0x158e
+		>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1-100mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD1_CLK__USDHC1_CLK				0x158e
+			IMX95_PAD_SD1_CMD__USDHC1_CMD				0x138e
+			IMX95_PAD_SD1_DATA0__USDHC1_DATA0			0x138e
+			IMX95_PAD_SD1_DATA1__USDHC1_DATA1			0x138e
+			IMX95_PAD_SD1_DATA2__USDHC1_DATA2			0x138e
+			IMX95_PAD_SD1_DATA3__USDHC1_DATA3			0x138e
+			IMX95_PAD_SD1_DATA4__USDHC1_DATA4			0x138e
+			IMX95_PAD_SD1_DATA5__USDHC1_DATA5			0x138e
+			IMX95_PAD_SD1_DATA6__USDHC1_DATA6			0x138e
+			IMX95_PAD_SD1_DATA7__USDHC1_DATA7			0x138e
+			IMX95_PAD_SD1_STROBE__USDHC1_STROBE			0x158e
+		>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1-200mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD1_CLK__USDHC1_CLK				0x15fe
+			IMX95_PAD_SD1_CMD__USDHC1_CMD				0x13fe
+			IMX95_PAD_SD1_DATA0__USDHC1_DATA0			0x13fe
+			IMX95_PAD_SD1_DATA1__USDHC1_DATA1			0x13fe
+			IMX95_PAD_SD1_DATA2__USDHC1_DATA2			0x13fe
+			IMX95_PAD_SD1_DATA3__USDHC1_DATA3			0x13fe
+			IMX95_PAD_SD1_DATA4__USDHC1_DATA4			0x13fe
+			IMX95_PAD_SD1_DATA5__USDHC1_DATA5			0x13fe
+			IMX95_PAD_SD1_DATA6__USDHC1_DATA6			0x13fe
+			IMX95_PAD_SD1_DATA7__USDHC1_DATA7			0x13fe
+			IMX95_PAD_SD1_STROBE__USDHC1_STROBE			0x15fe
+		>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			IMX95_PAD_SD2_CD_B__GPIO3_IO_BIT0			0x31e
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			IMX95_PAD_SD2_CLK__USDHC2_CLK				0x158e
+			IMX95_PAD_SD2_CMD__USDHC2_CMD				0x138e
+			IMX95_PAD_SD2_DATA0__USDHC2_DATA0			0x138e
+			IMX95_PAD_SD2_DATA1__USDHC2_DATA1			0x138e
+			IMX95_PAD_SD2_DATA2__USDHC2_DATA2			0x138e
+			IMX95_PAD_SD2_DATA3__USDHC2_DATA3			0x138e
+			IMX95_PAD_SD2_VSELECT__USDHC2_VSELECT			0x51e
+		>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD2_CLK__USDHC2_CLK				0x158e
+			IMX95_PAD_SD2_CMD__USDHC2_CMD				0x138e
+			IMX95_PAD_SD2_DATA0__USDHC2_DATA0			0x138e
+			IMX95_PAD_SD2_DATA1__USDHC2_DATA1			0x138e
+			IMX95_PAD_SD2_DATA2__USDHC2_DATA2			0x138e
+			IMX95_PAD_SD2_DATA3__USDHC2_DATA3			0x138e
+			IMX95_PAD_SD2_VSELECT__USDHC2_VSELECT			0x51e
+		>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD2_CLK__USDHC2_CLK				0x15fe
+			IMX95_PAD_SD2_CMD__USDHC2_CMD				0x13fe
+			IMX95_PAD_SD2_DATA0__USDHC2_DATA0			0x13fe
+			IMX95_PAD_SD2_DATA1__USDHC2_DATA1			0x13fe
+			IMX95_PAD_SD2_DATA2__USDHC2_DATA2			0x13fe
+			IMX95_PAD_SD2_DATA3__USDHC2_DATA3			0x13fe
+			IMX95_PAD_SD2_VSELECT__USDHC2_VSELECT			0x51e
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			IMX95_PAD_SD3_CLK__USDHC3_CLK				0x158e
+			IMX95_PAD_SD3_CMD__USDHC3_CMD				0x138e
+			IMX95_PAD_SD3_DATA0__USDHC3_DATA0			0x138e
+			IMX95_PAD_SD3_DATA1__USDHC3_DATA1			0x138e
+			IMX95_PAD_SD3_DATA2__USDHC3_DATA2			0x138e
+			IMX95_PAD_SD3_DATA3__USDHC3_DATA3			0x138e
+		>;
+	};
+
+	pinctrl_usdhc3_pwrseq: usdhc3pwrseqgrp {
+		fsl,pins = <
+			IMX95_PAD_XSPI1_SCLK__GPIO5_IO_BIT9			0x31e
+		>;
+	};
+
+	pinctrl_usdhc3_100mhz: usdhc3-100mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD3_CLK__USDHC3_CLK				0x158e
+			IMX95_PAD_SD3_CMD__USDHC3_CMD				0x138e
+			IMX95_PAD_SD3_DATA0__USDHC3_DATA0			0x138e
+			IMX95_PAD_SD3_DATA1__USDHC3_DATA1			0x138e
+			IMX95_PAD_SD3_DATA2__USDHC3_DATA2			0x138e
+			IMX95_PAD_SD3_DATA3__USDHC3_DATA3			0x138e
+		>;
+	};
+
+	pinctrl_usdhc3_200mhz: usdhc3-200mhzgrp {
+		fsl,pins = <
+			IMX95_PAD_SD3_CLK__USDHC3_CLK				0x15fe
+			IMX95_PAD_SD3_CMD__USDHC3_CMD				0x13fe
+			IMX95_PAD_SD3_DATA0__USDHC3_DATA0			0x13fe
+			IMX95_PAD_SD3_DATA1__USDHC3_DATA1			0x13fe
+			IMX95_PAD_SD3_DATA2__USDHC3_DATA2			0x13fe
+			IMX95_PAD_SD3_DATA3__USDHC3_DATA3			0x13fe
+		>;
+	};
+};
+
+&scmi_misc {
+	nxp,ctrl-ids = <BRD_SM_CTRL_SD3_WAKE		1>,
+		       <BRD_SM_CTRL_PCIE1_WAKE		1>,
+		       <BRD_SM_CTRL_BT_WAKE		1>,
+		       <BRD_SM_CTRL_PCIE2_WAKE		1>,
+		       <BRD_SM_CTRL_BUTTON		1>;
+};
+
+&thermal_zones {
+	a55-thermal {
+		cooling-maps {
+			map1 {
+				cooling-device = <&fan0 0 1>;
+				trip = <&atrip2>;
+			};
+
+			map2 {
+				cooling-device = <&fan0 1 2>;
+				trip = <&atrip3>;
+			};
+
+			map3 {
+				cooling-device = <&fan0 2 3>;
+				trip = <&atrip4>;
+			};
+		};
+
+		trips {
+			atrip2: trip2 {
+				hysteresis = <2000>;
+				temperature = <55000>;
+				type = "active";
+			};
+
+			atrip3: trip3 {
+				hysteresis = <2000>;
+				temperature = <65000>;
+				type = "active";
+			};
+
+			atrip4: trip4 {
+				hysteresis = <2000>;
+				temperature = <75000>;
+				type = "active";
+			};
+		};
+	};
+
+	pf09-thermal {
+		polling-delay = <2000>;
+		polling-delay-passive = <250>;
+		thermal-sensors = <&scmi_sensor 2>;
+
+		trips {
+			pf09_alert: trip0 {
+				hysteresis = <2000>;
+				temperature = <140000>;
+				type = "passive";
+			};
+
+			pf09_crit: trip1 {
+				hysteresis = <2000>;
+				temperature = <155000>;
+				type = "critical";
+			};
+		};
+	};
+
+	pf53arm-thermal {
+		polling-delay = <2000>;
+		polling-delay-passive = <250>;
+		thermal-sensors = <&scmi_sensor 4>;
+
+		cooling-maps {
+			map0 {
+				cooling-device = <&A55_0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						 <&A55_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						 <&A55_2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						 <&A55_3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						 <&A55_4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						 <&A55_5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				trip = <&pf5301_alert>;
+			};
+		};
+
+		trips {
+			pf5301_alert: trip0 {
+				hysteresis = <2000>;
+				temperature = <140000>;
+				type = "passive";
+			};
+
+			pf5301_crit: trip1 {
+				hysteresis = <2000>;
+				temperature = <155000>;
+				type = "critical";
+			};
+		};
+	};
+
+	pf53soc-thermal {
+		polling-delay = <2000>;
+		polling-delay-passive = <250>;
+		thermal-sensors = <&scmi_sensor 3>;
+
+		trips {
+			pf5302_alert: trip0 {
+				hysteresis = <2000>;
+				temperature = <140000>;
+				type = "passive";
+			};
+
+			pf5302_crit: trip1 {
+				hysteresis = <2000>;
+				temperature = <155000>;
+				type = "critical";
+			};
+		};
+	};
+};
+
+&tpm3 {
+	pinctrl-0 = <&pinctrl_tpm3>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&tpm6 {
+	pinctrl-0 = <&pinctrl_tpm6>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&usb3 {
+	status = "okay";
+};
+
+&usb3_dwc3 {
+	adp-disable;
+	dr_mode = "otg";
+	hnp-disable;
+	role-switch-default-mode = "peripheral";
+	srp-disable;
+	usb-role-switch;
+	snps,dis-u1-entry-quirk;
+	snps,dis-u2-entry-quirk;
+	status = "okay";
+
+	port {
+		usb3_data_hs: endpoint {
+			remote-endpoint = <&typec_con_hs>;
+		};
+	};
+};
+
+&usb3_phy {
+	orientation-switch;
+	fsl,phy-tx-preemp-amp-tune-microamp = <600>;
+	status = "okay";
+
+	port {
+		usb3_data_ss: endpoint {
+			remote-endpoint = <&typec_con_ss>;
+		};
+	};
+};
+
+&usdhc1 {
+	bus-width = <8>;
+	non-removable;
+	no-sd;
+	no-sdio;
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
+	pinctrl-3 = <&pinctrl_usdhc1>;
+	pinctrl-names = "default", "state_100mhz", "state_200mhz", "sleep";
+	fsl,tuning-step = <1>;
+	status = "okay";
+};
+
+&usdhc2 {
+	bus-width = <4>;
+	cd-gpios = <&gpio3 00 GPIO_ACTIVE_LOW>;
+	pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-3 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-names = "default", "state_100mhz", "state_200mhz", "sleep";
+	vmmc-supply = <&reg_usdhc2_vmmc>;
+	fsl,tuning-step = <1>;
+	status = "okay";
+};
+
+&usdhc3 {
+	bus-width = <4>;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&usdhc3_pwrseq>;
+	non-removable;
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	pinctrl-3 = <&pinctrl_usdhc3>;
+	pinctrl-names = "default", "state_100mhz", "state_200mhz", "sleep";
+	vmmc-supply = <&reg_usdhc3_vmmc>;
+	wakeup-source;
+	status = "okay";
+};
+
+&wdog3 {
+	status = "okay";
+};
+
+&xcvr {
+	clocks = <&scmi_clk IMX95_CLK_BUSWAKEUP>,
+		 <&scmi_clk IMX95_CLK_SPDIF>,
+		 <&dummy>,
+		 <&scmi_clk IMX95_CLK_AUDIOXCVR>,
+		 <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+		 <&scmi_clk IMX95_CLK_AUDIOPLL2>;
+	clock-names = "ipg", "phy", "spba", "pll_ipg", "pll8k", "pll11k";
+	assigned-clocks = <&scmi_clk IMX95_CLK_AUDIOPLL1_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2_VCO>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+			  <&scmi_clk IMX95_CLK_AUDIOPLL2>,
+			  <&scmi_clk IMX95_CLK_SPDIF>,
+			  <&scmi_clk IMX95_CLK_AUDIOXCVR>;
+	assigned-clock-parents = <0>, <0>, <0>, <0>,
+				 <&scmi_clk IMX95_CLK_AUDIOPLL1>,
+				 <&scmi_clk IMX95_CLK_SYSPLL1_PFD1_DIV2>;
+	assigned-clock-rates = <3932160000>, <3612672000>,
+			       <393216000>, <361267200>,
+			       <12288000>, <0>;
+	#sound-dai-cells = <0>;
+	pinctrl-0 = <&pinctrl_spdif>;
+	pinctrl-names = "default";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
index 8bc066c3760c..25ac331f0318 100644
--- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
@@ -6,6 +6,7 @@
 /dts-v1/;
 
 #include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/usb/pd.h>
 #include "imx95.dtsi"
 
 #define FALLING_EDGE			1
@@ -317,6 +318,48 @@
 		interrupt-parent = <&gpio5>;
 		interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 	};
+
+	ptn5110: tcpc@50 {
+		compatible = "nxp,ptn5110", "tcpci";
+		reg = <0x50>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_typec>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
+
+		typec_con: connector {
+			compatible = "usb-c-connector";
+			label = "USB-C";
+			power-role = "dual";
+			data-role = "dual";
+			try-power-role = "sink";
+			source-pdos = <PDO_FIXED(5000, 3000, PDO_FIXED_USB_COMM)>;
+			sink-pdos = <PDO_FIXED(5000, 0, PDO_FIXED_USB_COMM)>;
+			op-sink-microwatt = <0>;
+			self-powered;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					typec_con_hs: endpoint {
+						remote-endpoint = <&usb3_data_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					typec_con_ss: endpoint {
+						remote-endpoint = <&usb3_data_ss>;
+					};
+				};
+			};
+		};
+	};
 };
 
 &lpuart1 {
@@ -418,6 +461,40 @@
 	status = "okay";
 };
 
+&usb3 {
+	status = "okay";
+};
+
+&usb3_dwc3 {
+	dr_mode = "otg";
+	hnp-disable;
+	srp-disable;
+	adp-disable;
+	usb-role-switch;
+	role-switch-default-mode = "peripheral";
+	snps,dis-u1-entry-quirk;
+	snps,dis-u2-entry-quirk;
+	status = "okay";
+
+	port {
+		usb3_data_hs: endpoint {
+			remote-endpoint = <&typec_con_hs>;
+		};
+	};
+};
+
+&usb3_phy {
+	fsl,phy-tx-preemp-amp-tune-microamp = <600>;
+	orientation-switch;
+	status = "okay";
+
+	port {
+		usb3_data_ss: endpoint {
+			remote-endpoint = <&typec_con_ss>;
+		};
+	};
+};
+
 &usdhc1 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz", "sleep";
 	pinctrl-0 = <&pinctrl_usdhc1>;
@@ -676,6 +753,12 @@
 		>;
 	};
 
+	pinctrl_typec: typecgrp {
+		fsl,pins = <
+			IMX95_PAD_GPIO_IO34__GPIO5_IO_BIT14			0x31e
+		>;
+	};
+
 	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
 		fsl,pins = <
 			IMX95_PAD_SD2_CD_B__GPIO3_IO_BIT0		0x31e
diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 6b8470cb3461..59f057ba6fa7 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -291,6 +291,13 @@
 		clock-output-names = "sai5_mclk";
 	};
 
+	clk_sys100m: clock-sys100m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "clk_sys100m";
+	};
+
 	osc_24m: clock-24m {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
@@ -673,6 +680,19 @@
 				status = "disabled";
 			};
 
+			i3c2: i3c@42520000 {
+				compatible = "silvaco,i3c-master-v1";
+				reg = <0x42520000 0x10000>;
+				interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <3>;
+				#size-cells = <0>;
+				clocks = <&scmi_clk IMX95_CLK_BUSAON>,
+					 <&scmi_clk IMX95_CLK_I3C2>,
+					 <&scmi_clk IMX95_CLK_I3C2SLOW>;
+				clock-names = "pclk", "fast_clk", "slow_clk";
+				status = "disabled";
+			};
+
 			lpi2c3: i2c@42530000 {
 				compatible = "fsl,imx95-lpi2c", "fsl,imx7ulp-lpi2c";
 				reg = <0x42530000 0x10000>;
@@ -1245,6 +1265,19 @@
 				status = "disabled";
 			};
 
+			i3c1: i3c@44330000 {
+				compatible = "silvaco,i3c-master-v1";
+				reg = <0x44330000 0x10000>;
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <3>;
+				#size-cells = <0>;
+				clocks = <&scmi_clk IMX95_CLK_BUSAON>,
+					 <&scmi_clk IMX95_CLK_I3C1>,
+					 <&scmi_clk IMX95_CLK_I3C1SLOW>;
+				clock-names = "pclk", "fast_clk", "slow_clk";
+				status = "disabled";
+			};
+
 			lpi2c1: i2c@44340000 {
 				compatible = "fsl,imx95-lpi2c", "fsl,imx7ulp-lpi2c";
 				reg = <0x44340000 0x10000>;
@@ -1379,6 +1412,7 @@
 					     <GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&scmi_clk IMX95_CLK_ADC>;
 				clock-names = "ipg";
+				#io-channel-cells = <1>;
 				status = "disabled";
 			};
 
@@ -1537,12 +1571,62 @@
 			};
 		};
 
+		usb3: usb@4c010010 {
+			compatible = "fsl,imx95-dwc3", "fsl,imx8mp-dwc3";
+			reg = <0x0 0x4c010010 0x0 0x04>,
+			      <0x0 0x4c1f0000 0x0 0x20>;
+			clocks = <&scmi_clk IMX95_CLK_HSIO>,
+				 <&scmi_clk IMX95_CLK_32K>;
+			clock-names = "hsio", "suspend";
+			interrupts = <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>;
+			dma-ranges = <0x0 0x0 0x0 0x0 0x10 0x0>;
+			status = "disabled";
+
+			usb3_dwc3: usb@4c100000 {
+				compatible = "snps,dwc3";
+				reg = <0x0 0x4c100000 0x0 0x10000>;
+				clocks = <&scmi_clk IMX95_CLK_HSIO>,
+					 <&scmi_clk IMX95_CLK_24M>,
+					 <&scmi_clk IMX95_CLK_32K>;
+				clock-names = "bus_early", "ref", "suspend";
+				interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
+				phys = <&usb3_phy>, <&usb3_phy>;
+				phy-names = "usb2-phy", "usb3-phy";
+				snps,gfladj-refclk-lpm-sel-quirk;
+				snps,parkmode-disable-ss-quirk;
+				iommus = <&smmu 0xe>;
+			};
+		};
+
+		hsio_blk_ctl: syscon@4c0100c0 {
+			compatible = "nxp,imx95-hsio-blk-ctl", "syscon";
+			reg = <0x0 0x4c0100c0 0x0 0x1>;
+			#clock-cells = <1>;
+			clocks = <&clk_sys100m>;
+			power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>;
+		};
+
+		usb3_phy: phy@4c1f0040 {
+			compatible = "fsl,imx95-usb-phy", "fsl,imx8mp-usb-phy";
+			reg = <0x0 0x4c1f0040 0x0 0x40>,
+			      <0x0 0x4c1fc000 0x0 0x100>;
+			clocks = <&scmi_clk IMX95_CLK_HSIO>;
+			clock-names = "phy";
+			#phy-cells = <0>;
+			power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>;
+			status = "disabled";
+		};
+
 		pcie0: pcie@4c300000 {
 			compatible = "fsl,imx95-pcie";
 			reg = <0 0x4c300000 0 0x10000>,
 			      <0 0x60100000 0 0xfe00000>,
 			      <0 0x4c360000 0 0x10000>,
-			      <0 0x4c340000 0 0x2000>;
+			      <0 0x4c340000 0 0x4000>;
 			reg-names = "dbi", "config", "atu", "app";
 			ranges = <0x81000000 0x0 0x00000000 0x0 0x6ff00000 0 0x00100000>,
 				 <0x82000000 0x0 0x10000000 0x9 0x10000000 0 0x10000000>;
@@ -1564,8 +1648,9 @@
 			clocks = <&scmi_clk IMX95_CLK_HSIO>,
 				 <&scmi_clk IMX95_CLK_HSIOPLL>,
 				 <&scmi_clk IMX95_CLK_HSIOPLL_VCO>,
-				 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>;
-			clock-names = "pcie", "pcie_bus", "pcie_phy", "pcie_aux";
+				 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>,
+				 <&hsio_blk_ctl 0>;
+			clock-names = "pcie", "pcie_bus", "pcie_phy", "pcie_aux", "ref";
 			assigned-clocks =<&scmi_clk IMX95_CLK_HSIOPLL_VCO>,
 					 <&scmi_clk IMX95_CLK_HSIOPLL>,
 					 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>;
@@ -1573,6 +1658,12 @@
 			assigned-clock-parents = <0>, <0>,
 						 <&scmi_clk IMX95_CLK_SYSPLL1_PFD1_DIV2>;
 			power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>;
+			/* pcie0's Devid(BIT[7:6]) is 0x00, stream id(BIT[5:0]) is 0x10~0x17 */
+			msi-map = <0x0 &its 0x10 0x1>,
+				  <0x100 &its 0x11 0x7>;
+			iommu-map = <0x000 &smmu 0x10 0x1>,
+				    <0x100 &smmu 0x11 0x7>;
+			iommu-map-mask = <0x1ff>;
 			fsl,max-link-speed = <3>;
 			status = "disabled";
 		};
@@ -1582,7 +1673,7 @@
 			reg = <0 0x4c300000 0 0x10000>,
 			      <0 0x4c360000 0 0x1000>,
 			      <0 0x4c320000 0 0x1000>,
-			      <0 0x4c340000 0 0x2000>,
+			      <0 0x4c340000 0 0x4000>,
 			      <0 0x4c370000 0 0x10000>,
 			      <0x9 0 1 0>;
 			reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space";
@@ -1609,7 +1700,7 @@
 			reg = <0 0x4c380000 0 0x10000>,
 			      <8 0x80100000 0 0xfe00000>,
 			      <0 0x4c3e0000 0 0x10000>,
-			      <0 0x4c3c0000 0 0x2000>;
+			      <0 0x4c3c0000 0 0x4000>;
 			reg-names = "dbi", "config", "atu", "app";
 			ranges = <0x81000000 0 0x00000000 0x8 0x8ff00000 0 0x00100000>,
 				 <0x82000000 0 0x10000000 0xa 0x10000000 0 0x10000000>;
@@ -1631,8 +1722,9 @@
 			clocks = <&scmi_clk IMX95_CLK_HSIO>,
 				 <&scmi_clk IMX95_CLK_HSIOPLL>,
 				 <&scmi_clk IMX95_CLK_HSIOPLL_VCO>,
-				 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>;
-			clock-names = "pcie", "pcie_bus", "pcie_phy", "pcie_aux";
+				 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>,
+				 <&hsio_blk_ctl 0>;
+			clock-names = "pcie", "pcie_bus", "pcie_phy", "pcie_aux", "ref";
 			assigned-clocks =<&scmi_clk IMX95_CLK_HSIOPLL_VCO>,
 					 <&scmi_clk IMX95_CLK_HSIOPLL>,
 					 <&scmi_clk IMX95_CLK_HSIOPCIEAUX>;
@@ -1640,6 +1732,14 @@
 			assigned-clock-parents = <0>, <0>,
 						 <&scmi_clk IMX95_CLK_SYSPLL1_PFD1_DIV2>;
 			power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>;
+			/* pcie1's Devid(BIT[7:6]) is 0x10, stream id(BIT[5:0]) is 0x18~0x1f */
+			msi-map = <0x0 &its 0x98 0x1>,
+				  <0x100 &its 0x99 0x7>;
+			msi-map-mask = <0x1ff>;
+			/* smmu have not Devid(BIT[7:6]) */
+			iommu-map = <0x000 &smmu 0x18 0x1>,
+				    <0x100 &smmu 0x19 0x7>;
+			iommu-map-mask = <0x1ff>;
 			fsl,max-link-speed = <3>;
 			status = "disabled";
 		};
@@ -1649,7 +1749,7 @@
 			reg = <0 0x4c380000 0 0x10000>,
 			      <0 0x4c3e0000 0 0x1000>,
 			      <0 0x4c3a0000 0 0x1000>,
-			      <0 0x4c3c0000 0 0x2000>,
+			      <0 0x4c3c0000 0 0x4000>,
 			      <0 0x4c3f0000 0 0x10000>,
 			      <0xa 0 1 0>;
 			reg-names = "dbi", "atu", "dbi2", "app", "dma", "addr_space";
diff --git a/arch/arm64/boot/dts/freescale/mba8mx.dtsi b/arch/arm64/boot/dts/freescale/mba8mx.dtsi
index 58e3865c2889..7ee1228a50f4 100644
--- a/arch/arm64/boot/dts/freescale/mba8mx.dtsi
+++ b/arch/arm64/boot/dts/freescale/mba8mx.dtsi
@@ -138,7 +138,7 @@
 
 	sound {
 		compatible = "fsl,imx-audio-tlv320aic32x4";
-		model = "imx-audio-tlv320aic32x4";
+		model = "tqm-tlv320aic32";
 		ssi-controller = <&sai3>;
 		audio-codec = <&tlv320aic3x04>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/mba8xx.dtsi b/arch/arm64/boot/dts/freescale/mba8xx.dtsi
index 276d1683b03b..c4b5663949ad 100644
--- a/arch/arm64/boot/dts/freescale/mba8xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/mba8xx.dtsi
@@ -36,6 +36,13 @@
 		stdout-path = &lpuart1;
 	};
 
+	/* Non-controllable PCIe reference clock generator */
+	pcie_refclk: clock-pcie-ref {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 		pinctrl-names = "default";
@@ -208,6 +215,12 @@
 	status = "okay";
 };
 
+&hsio_phy {
+	fsl,hsio-cfg = "pciea-x2-pcieb";
+	fsl,refclk-pad-mode = "input";
+	status = "okay";
+};
+
 &i2c1 {
 	tlv320aic3x04: audio-codec@18 {
 		compatible = "ti,tlv320aic32x4";
@@ -309,7 +322,15 @@
 			  "", "", "", "";
 };
 
-/* TODO: Mini-PCIe */
+&pcieb {
+	phys = <&hsio_phy 0 PHY_TYPE_PCIE 0>;
+	phy-names = "pcie-phy";
+	pinctrl-0 = <&pinctrl_pcieb>;
+	pinctrl-names = "default";
+	reset-gpios = <&lsio_gpio4 0 GPIO_ACTIVE_LOW>;
+	vpcie-supply = <&reg_pcie_1v5>;
+	status = "okay";
+};
 
 &sai1 {
 	assigned-clocks = <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_PLL>,
@@ -467,10 +488,10 @@
 		fsl,pins = <IMX8QXP_USDHC1_RESET_B_LSIO_GPIO4_IO19	0x00000020>;
 	};
 
-	pinctrl_pcieb: pcieagrp {
-		fsl,pins = <IMX8QXP_PCIE_CTRL0_PERST_B_LSIO_GPIO4_IO00	0x06000041>,
-			   <IMX8QXP_PCIE_CTRL0_CLKREQ_B_LSIO_GPIO4_IO01	0x06000041>,
-			   <IMX8QXP_PCIE_CTRL0_WAKE_B_LSIO_GPIO4_IO02	0x04000041>;
+	pinctrl_pcieb: pciebgrp {
+		fsl,pins = <IMX8QXP_PCIE_CTRL0_PERST_B_LSIO_GPIO4_IO00		0x06000041>,
+			   <IMX8QXP_PCIE_CTRL0_CLKREQ_B_HSIO_PCIE0_CLKREQ_B	0x06000041>,
+			   <IMX8QXP_PCIE_CTRL0_WAKE_B_LSIO_GPIO4_IO02		0x04000041>;
 	};
 
 	pinctrl_reg_pcie_1v5: regpcie1v5grp {
diff --git a/arch/arm64/boot/dts/freescale/s32g2.dtsi b/arch/arm64/boot/dts/freescale/s32g2.dtsi
index 7be430b78c83..ea1456d361a3 100644
--- a/arch/arm64/boot/dts/freescale/s32g2.dtsi
+++ b/arch/arm64/boot/dts/freescale/s32g2.dtsi
@@ -317,6 +317,49 @@
 			};
 		};
 
+		edma0: dma-controller@40144000 {
+			compatible = "nxp,s32g2-edma";
+			reg = <0x40144000 0x24000>,
+			      <0x4012c000 0x3000>,
+			      <0x40130000 0x3000>;
+			#dma-cells = <2>;
+			dma-channels = <32>;
+			interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tx-0-15",
+					  "tx-16-31",
+					  "err";
+			clocks = <&clks 63>, <&clks 64>;
+			clock-names = "dmamux0", "dmamux1";
+		};
+
+		can0: can@401b4000 {
+			compatible = "nxp,s32g2-flexcan";
+			reg = <0x401b4000 0xa000>;
+			interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
+		can1: can@401be000 {
+			compatible = "nxp,s32g2-flexcan";
+			reg = <0x401be000 0xa000>;
+			interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
 		uart0: serial@401c8000 {
 			compatible = "nxp,s32g2-linflexuart",
 				     "fsl,s32v234-linflexuart";
@@ -333,6 +376,82 @@
 			status = "disabled";
 		};
 
+		i2c0: i2c@401e4000 {
+			compatible = "nxp,s32g2-i2c";
+			reg = <0x401e4000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c1: i2c@401e8000 {
+			compatible = "nxp,s32g2-i2c";
+			reg = <0x401e8000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c2: i2c@401ec000 {
+			compatible = "nxp,s32g2-i2c";
+			reg = <0x401ec000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		edma1: dma-controller@40244000 {
+			compatible = "nxp,s32g2-edma";
+			reg = <0x40244000 0x24000>,
+			      <0x4022c000 0x3000>,
+			      <0x40230000 0x3000>;
+			#dma-cells = <2>;
+			dma-channels = <32>;
+			interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tx-0-15",
+					  "tx-16-31",
+					  "err";
+			clocks = <&clks 63>, <&clks 64>;
+			clock-names = "dmamux0", "dmamux1";
+		};
+
+		can2: can@402a8000 {
+			compatible = "nxp,s32g2-flexcan";
+			reg = <0x402a8000 0xa000>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
+		can3: can@402b2000 {
+			compatible = "nxp,s32g2-flexcan";
+			reg = <0x402b2000 0xa000>;
+			interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
 		uart2: serial@402bc000 {
 			compatible = "nxp,s32g2-linflexuart",
 				     "fsl,s32v234-linflexuart";
@@ -341,6 +460,28 @@
 			status = "disabled";
 		};
 
+		i2c3: i2c@402d8000 {
+			compatible = "nxp,s32g2-i2c";
+			reg = <0x402d8000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c4: i2c@402dc000 {
+			compatible = "nxp,s32g2-i2c";
+			reg = <0x402dc000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
 		usdhc0: mmc@402f0000 {
 			compatible = "nxp,s32g2-usdhc";
 			reg = <0x402f0000 0x1000>;
diff --git a/arch/arm64/boot/dts/freescale/s32g274a-evb.dts b/arch/arm64/boot/dts/freescale/s32g274a-evb.dts
index b9a119eea2b7..c4a195dd67bf 100644
--- a/arch/arm64/boot/dts/freescale/s32g274a-evb.dts
+++ b/arch/arm64/boot/dts/freescale/s32g274a-evb.dts
@@ -7,6 +7,7 @@
 /dts-v1/;
 
 #include "s32g2.dtsi"
+#include "s32gxxxa-evb.dtsi"
 
 / {
 	model = "NXP S32G2 Evaluation Board (S32G-VNP-EVB)";
diff --git a/arch/arm64/boot/dts/freescale/s32g274a-rdb2.dts b/arch/arm64/boot/dts/freescale/s32g274a-rdb2.dts
index aaa61a8ad0da..b5ba51696f43 100644
--- a/arch/arm64/boot/dts/freescale/s32g274a-rdb2.dts
+++ b/arch/arm64/boot/dts/freescale/s32g274a-rdb2.dts
@@ -7,6 +7,7 @@
 /dts-v1/;
 
 #include "s32g2.dtsi"
+#include "s32gxxxa-rdb.dtsi"
 
 / {
 	model = "NXP S32G2 Reference Design Board 2 (S32G-VNP-RDB2)";
diff --git a/arch/arm64/boot/dts/freescale/s32g3.dtsi b/arch/arm64/boot/dts/freescale/s32g3.dtsi
index 6c572ffe37ca..991dbfbfa203 100644
--- a/arch/arm64/boot/dts/freescale/s32g3.dtsi
+++ b/arch/arm64/boot/dts/freescale/s32g3.dtsi
@@ -374,6 +374,51 @@
 			};
 		};
 
+		edma0: dma-controller@40144000 {
+			compatible = "nxp,s32g3-edma", "nxp,s32g2-edma";
+			reg = <0x40144000 0x24000>,
+			      <0x4012c000 0x3000>,
+			      <0x40130000 0x3000>;
+			#dma-cells = <2>;
+			dma-channels = <32>;
+			interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tx-0-15",
+					  "tx-16-31",
+					  "err";
+			clocks = <&clks 63>, <&clks 64>;
+			clock-names = "dmamux0", "dmamux1";
+		};
+
+		can0: can@401b4000 {
+			compatible = "nxp,s32g3-flexcan",
+					   "nxp,s32g2-flexcan";
+			reg = <0x401b4000 0xa000>;
+			interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
+		can1: can@401be000 {
+			compatible = "nxp,s32g3-flexcan",
+					   "nxp,s32g2-flexcan";
+			reg = <0x401be000 0xa000>;
+			interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
 		uart0: serial@401c8000 {
 			compatible = "nxp,s32g3-linflexuart",
 				     "fsl,s32v234-linflexuart";
@@ -390,6 +435,87 @@
 			status = "disabled";
 		};
 
+		i2c0: i2c@401e4000 {
+			compatible = "nxp,s32g3-i2c",
+				     "nxp,s32g2-i2c";
+			reg = <0x401e4000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c1: i2c@401e8000 {
+			compatible = "nxp,s32g3-i2c",
+				     "nxp,s32g2-i2c";
+			reg = <0x401e8000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c2: i2c@401ec000 {
+			compatible = "nxp,s32g3-i2c",
+				     "nxp,s32g2-i2c";
+			reg = <0x401ec000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		edma1: dma-controller@40244000 {
+			compatible = "nxp,s32g3-edma", "nxp,s32g2-edma";
+			reg = <0x40244000 0x24000>,
+			      <0x4022c000 0x3000>,
+			      <0x40230000 0x3000>;
+			#dma-cells = <2>;
+			dma-channels = <32>;
+			interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tx-0-15",
+					  "tx-16-31",
+					  "err";
+			clocks = <&clks 63>, <&clks 64>;
+			clock-names = "dmamux0", "dmamux1";
+		};
+
+		can2: can@402a8000 {
+			compatible = "nxp,s32g3-flexcan",
+					   "nxp,s32g2-flexcan";
+			reg = <0x402a8000 0xa000>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
+		can3: can@402b2000 {
+			compatible = "nxp,s32g3-flexcan",
+					   "nxp,s32g2-flexcan";
+			reg = <0x402b2000 0xa000>;
+			interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "mb-0", "state", "berr", "mb-1";
+			clocks = <&clks 9>, <&clks 11>;
+			clock-names = "ipg", "per";
+			status = "disabled";
+		};
+
 		uart2: serial@402bc000 {
 			compatible = "nxp,s32g3-linflexuart",
 				     "fsl,s32v234-linflexuart";
@@ -398,6 +524,30 @@
 			status = "disabled";
 		};
 
+		i2c3: i2c@402d8000 {
+			compatible = "nxp,s32g3-i2c",
+				     "nxp,s32g2-i2c";
+			reg = <0x402d8000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
+		i2c4: i2c@402dc000 {
+			compatible = "nxp,s32g3-i2c",
+				     "nxp,s32g2-i2c";
+			reg = <0x402dc000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clks 40>;
+			clock-names = "ipg";
+			status = "disabled";
+		};
+
 		usdhc0: mmc@402f0000 {
 			compatible = "nxp,s32g3-usdhc",
 				     "nxp,s32g2-usdhc";
diff --git a/arch/arm64/boot/dts/freescale/s32g399a-rdb3.dts b/arch/arm64/boot/dts/freescale/s32g399a-rdb3.dts
index 828e353455b5..802f543cae4a 100644
--- a/arch/arm64/boot/dts/freescale/s32g399a-rdb3.dts
+++ b/arch/arm64/boot/dts/freescale/s32g399a-rdb3.dts
@@ -8,6 +8,7 @@
 /dts-v1/;
 
 #include "s32g3.dtsi"
+#include "s32gxxxa-rdb.dtsi"
 
 / {
 	model = "NXP S32G3 Reference Design Board 3 (S32G-VNP-RDB3)";
@@ -39,6 +40,14 @@
 	status = "okay";
 };
 
+&i2c4 {
+	current-sensor@40 {
+		compatible = "ti,ina231";
+		reg = <0x40>;
+		shunt-resistor = <1000>;
+	};
+};
+
 &usdhc0 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc0>;
diff --git a/arch/arm64/boot/dts/freescale/s32gxxxa-evb.dtsi b/arch/arm64/boot/dts/freescale/s32gxxxa-evb.dtsi
new file mode 100644
index 000000000000..d26af0fb8be7
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/s32gxxxa-evb.dtsi
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * Copyright 2024 NXP
+ *
+ * Authors: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
+ *          Ghennadi Procopciuc <ghennadi.procopciuc@oss.nxp.com>
+ *          Larisa Grigore <larisa.grigore@nxp.com>
+ */
+
+&pinctrl {
+	can0_pins: can0-pins {
+		can0-grp0 {
+			pinmux = <0x2c1>;
+			output-enable;
+			slew-rate = <133>;
+		};
+
+		can0-grp1 {
+			pinmux = <0x2b0>;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		can0-grp2 {
+			pinmux = <0x2012>;
+		};
+	};
+
+	can2_pins: can2-pins {
+		can2-grp0 {
+			pinmux = <0x1b2>;
+			output-enable;
+			slew-rate = <133>;
+		};
+
+		can2-grp1 {
+			pinmux = <0x1c0>;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		can2-grp2 {
+			pinmux = <0x2782>;
+		};
+	};
+
+	can3_pins: can3-pins {
+		can3-grp0 {
+			pinmux = <0x192>;
+			output-enable;
+			slew-rate = <133>;
+		};
+
+		can3-grp1 {
+			pinmux = <0x1a0>;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		can3-grp2 {
+			pinmux = <0x2792>;
+		};
+	};
+
+	i2c0_pins: i2c0-pins {
+		i2c0-grp0 {
+			pinmux = <0x101>, <0x111>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c0-grp1 {
+			pinmux = <0x2352>, <0x2362>;
+		};
+	};
+
+	i2c0_gpio_pins: i2c0-gpio-pins {
+		i2c0-gpio-grp0 {
+			pinmux = <0x100>, <0x110>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c0-gpio-grp1 {
+			pinmux = <0x2350>, <0x2360>;
+		};
+	};
+
+	i2c1_pins: i2c1-pins {
+		i2c1-grp0 {
+			pinmux = <0x131>, <0x141>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c1-grp1 {
+			pinmux = <0x2cd2>, <0x2ce2>;
+		};
+	};
+
+	i2c1_gpio_pins: i2c1-gpio-pins {
+		i2c1-gpio-grp0 {
+			pinmux = <0x130>, <0x140>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c1-gpio-grp1 {
+			pinmux = <0x2cd0>, <0x2ce0>;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		i2c2-grp0 {
+			pinmux = <0x151>, <0x161>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c2-grp1 {
+			pinmux = <0x2cf2>, <0x2d02>;
+		};
+	};
+
+	i2c2_gpio_pins: i2c2-gpio-pins {
+		i2c2-gpio-grp0 {
+			pinmux = <0x150>, <0x160>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c2-gpio-grp1 {
+			pinmux = <0x2cf0>, <0x2d00>;
+		};
+	};
+
+	i2c4_pins: i2c4-pins {
+		i2c4-grp0 {
+			pinmux = <0x211>, <0x222>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c4-grp1 {
+			pinmux = <0x2d43>, <0x2d33>;
+		};
+	};
+
+	i2c4_gpio_pins: i2c4-gpio-pins {
+		i2c4-gpio-grp0 {
+			pinmux = <0x210>, <0x220>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c4-gpio-grp1 {
+			pinmux = <0x2d40>, <0x2d30>;
+		};
+	};
+};
+
+&can0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&can0_pins>;
+	status = "okay";
+};
+
+&can2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&can2_pins>;
+	status = "okay";
+};
+
+&can3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&can3_pins>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c0_pins>;
+	pinctrl-1 = <&i2c0_gpio_pins>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c1_pins>;
+	pinctrl-1 = <&i2c1_gpio_pins>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c2_pins>;
+	pinctrl-1 = <&i2c2_gpio_pins>;
+	status = "okay";
+};
+
+&i2c4 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c4_pins>;
+	pinctrl-1 = <&i2c4_gpio_pins>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/s32gxxxa-rdb.dtsi b/arch/arm64/boot/dts/freescale/s32gxxxa-rdb.dtsi
new file mode 100644
index 000000000000..ba53ec622f0b
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/s32gxxxa-rdb.dtsi
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * Copyright 2024 NXP
+ *
+ * Authors: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
+ *          Ghennadi Procopciuc <ghennadi.procopciuc@oss.nxp.com>
+ *          Larisa Grigore <larisa.grigore@nxp.com>
+ */
+
+&pinctrl {
+	can0_pins: can0-pins {
+		can0-grp0 {
+			pinmux = <0x112>;
+			output-enable;
+			slew-rate = <133>;
+		};
+
+		can0-grp1 {
+			pinmux = <0x120>;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		can0-grp2 {
+			pinmux = <0x2013>;
+		};
+	};
+
+	can1_pins: can1-pins {
+		can1-grp0 {
+			pinmux = <0x132>;
+			output-enable;
+			slew-rate = <133>;
+		};
+
+		can1-grp1 {
+			pinmux = <0x140>;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		can1-grp2 {
+			pinmux = <0x2772>;
+		};
+	};
+
+	i2c0_pins: i2c0-pins {
+		i2c0-grp0 {
+			pinmux = <0x1f2>, <0x201>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c0-grp1 {
+			pinmux = <0x2353>, <0x2363>;
+		};
+	};
+
+	i2c0_gpio_pins: i2c0-gpio-pins {
+		i2c0-gpio-grp0 {
+			pinmux = <0x1f0>, <0x200>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c0-gpio-grp1 {
+			pinmux = <0x2350>, <0x2360>;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		i2c2-grp0 {
+			pinmux = <0x151>, <0x161>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c2-grp1 {
+			pinmux = <0x2cf2>, <0x2d02>;
+		};
+	};
+
+	i2c2_gpio_pins: i2c2-gpio-pins {
+		i2c2-gpio-grp0 {
+			pinmux = <0x2cf0>, <0x2d00>;
+		};
+
+		i2c2-gpio-grp1 {
+			pinmux = <0x150>, <0x160>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+	};
+
+	i2c4_pins: i2c4-pins {
+		i2c4-grp0 {
+			pinmux = <0x211>, <0x222>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c4-grp1 {
+			pinmux = <0x2d43>, <0x2d33>;
+		};
+	};
+
+	i2c4_gpio_pins: i2c4-gpio-pins {
+		i2c4-gpio-grp0 {
+			pinmux = <0x210>, <0x220>;
+			drive-open-drain;
+			output-enable;
+			input-enable;
+			slew-rate = <133>;
+		};
+
+		i2c4-gpio-grp1 {
+			pinmux = <0x2d40>, <0x2d30>;
+		};
+	};
+};
+
+&can0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&can0_pins>;
+	status = "okay";
+};
+
+&can1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&can1_pins>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c0_pins>;
+	pinctrl-1 = <&i2c0_gpio_pins>;
+	status = "okay";
+
+	pcal6524: gpio-expander@22 {
+		compatible = "nxp,pcal6524";
+		reg = <0x22>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+};
+
+&i2c2 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c2_pins>;
+	pinctrl-1 = <&i2c2_gpio_pins>;
+	status = "okay";
+};
+
+&i2c4 {
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&i2c4_pins>;
+	pinctrl-1 = <&i2c4_gpio_pins>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/tqma8xx.dtsi b/arch/arm64/boot/dts/freescale/tqma8xx.dtsi
index 366912bf3d5e..58693b774d4c 100644
--- a/arch/arm64/boot/dts/freescale/tqma8xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/tqma8xx.dtsi
@@ -65,6 +65,7 @@
 		spi-max-frequency = <66000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <4>;
+		vcc-supply = <&reg_1v8>;
 
 		partitions {
 			compatible = "fixed-partitions";
@@ -74,8 +75,6 @@
 	};
 };
 
-/* TODO GPU */
-
 &i2c1 {
 	#address-cells = <1>;
 	#size-cells = <0>;
@@ -114,6 +113,15 @@
 	};
 };
 
+&jpegdec {
+	status = "okay";
+};
+
+&jpegenc {
+	status = "okay";
+};
+
+
 &mu_m0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-coresight.dtsi b/arch/arm64/boot/dts/hisilicon/hi3660-coresight.dtsi
index 79a55a0fa2f1..4c6a075908d1 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660-coresight.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3660-coresight.dtsi
@@ -17,6 +17,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu0>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -34,6 +35,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu1>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -51,6 +53,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu2>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -68,6 +71,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu3>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -160,6 +164,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu4>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -177,6 +182,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu5>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -194,6 +200,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu6>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
@@ -211,6 +218,7 @@
 			clocks = <&crg_ctrl HI3660_PCLK>;
 			clock-names = "apb_pclk";
 			cpu = <&cpu7>;
+			arm,coresight-loses-context-with-cpu;
 
 			out-ports {
 				port {
diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
index 75377c292bcb..605f5be1538c 100644
--- a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
@@ -78,7 +78,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		internal-regs@7f000000 {
+		bus@7f000000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "simple-bus";
diff --git a/arch/arm64/boot/dts/marvell/armada-371x.dtsi b/arch/arm64/boot/dts/marvell/armada-371x.dtsi
deleted file mode 100644
index dc1182ec9fa1..000000000000
--- a/arch/arm64/boot/dts/marvell/armada-371x.dtsi
+++ /dev/null
@@ -1,17 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
-/*
- * Device Tree Include file for Marvell Armada 371x family of SoCs
- * (also named 88F3710)
- *
- * Copyright (C) 2016 Marvell
- *
- * Gregory CLEMENT <gregory.clement@free-electrons.com>
- *
- */
-
-#include "armada-37xx.dtsi"
-
-/ {
-	model = "Marvell Armada 3710 SoC";
-	compatible = "marvell,armada3710", "marvell,armada3700";
-};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
index 0cfb38492021..bd4e61d5448e 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
@@ -18,7 +18,7 @@
 
 / {
 	model = "Marvell Armada 3720 Development Board DB-88F3720-DDR3";
-	compatible = "marvell,armada-3720-db", "marvell,armada3720", "marvell,armada3700";
+	compatible = "marvell,armada-3720-db", "marvell,armada3720", "marvell,armada3710";
 
 	chosen {
 		stdout-path = "serial0:115200n8";
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-emmc.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-emmc.dts
index 6715a19c1483..5c4d8f379704 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-emmc.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-emmc.dts
@@ -18,7 +18,7 @@
 / {
 	model = "Globalscale Marvell ESPRESSOBin Board (eMMC)";
 	compatible = "globalscale,espressobin-emmc", "globalscale,espressobin",
-		     "marvell,armada3720", "marvell,armada3700";
+		     "marvell,armada3720", "marvell,armada3710";
 };
 
 &sdhci0 {
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
index b3cc2b7b5d19..97a180c8dcd9 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-ultra.dts
@@ -13,7 +13,7 @@
 / {
 	model = "Globalscale Marvell ESPRESSOBin Ultra Board";
 	compatible = "globalscale,espressobin-ultra", "globalscale,espressobin",
-		     "marvell,armada3720", "marvell,armada3700";
+		     "marvell,armada3720", "marvell,armada3710";
 
 	aliases {
 		/* ethernet1 is WAN port */
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
index 2a8aa3901a9f..75401eab4d42 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts
@@ -19,7 +19,7 @@
 	model = "Globalscale Marvell ESPRESSOBin Board V7 (eMMC)";
 	compatible = "globalscale,espressobin-v7-emmc", "globalscale,espressobin-v7",
 		     "globalscale,espressobin", "marvell,armada3720",
-		     "marvell,armada3700";
+		     "marvell,armada3710";
 
 	aliases {
 		/* ethernet1 is wan port */
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
index b03af87611a9..48a7f50fb427 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts
@@ -18,7 +18,7 @@
 / {
 	model = "Globalscale Marvell ESPRESSOBin Board V7";
 	compatible = "globalscale,espressobin-v7", "globalscale,espressobin",
-		     "marvell,armada3720", "marvell,armada3700";
+		     "marvell,armada3720", "marvell,armada3710";
 
 	aliases {
 		/* ethernet1 is wan port */
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
index c5a834b33b77..1542d836c090 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
@@ -16,5 +16,5 @@
 
 / {
 	model = "Globalscale Marvell ESPRESSOBin Board";
-	compatible = "globalscale,espressobin", "marvell,armada3720", "marvell,armada3700";
+	compatible = "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710";
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts b/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
index 56930f2ce481..9f4bafeddd82 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-gl-mv1000.dts
@@ -7,7 +7,7 @@
 
 / {
 	model = "GL.iNet GL-MV1000";
-	compatible = "glinet,gl-mv1000", "marvell,armada3720";
+	compatible = "glinet,gl-mv1000", "marvell,armada3720", "marvell,armada3710";
 
 	aliases {
 		led-boot = &led_power;
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index 54453b0a91f9..f4d73c8b1a6d 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -14,7 +14,7 @@
 / {
 	model = "CZ.NIC Turris Mox Board";
 	compatible = "cznic,turris-mox", "marvell,armada3720",
-		     "marvell,armada3700";
+		     "marvell,armada3710";
 
 	aliases {
 		spi0 = &spi0;
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi
index 3a9b6907185d..242820845707 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi
@@ -26,6 +26,8 @@
 
 	leds {
 		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi_quad_pins>;
 
 		led-power1 {
 			label = "udpu:green:power";
@@ -82,8 +84,6 @@
 
 &spi0 {
 	status = "okay";
-	pinctrl-names = "default";
-	pinctrl-0 = <&spi_quad_pins>;
 
 	flash@0 {
 		compatible = "jedec,spi-nor";
@@ -108,6 +108,10 @@
 	};
 };
 
+&spi_quad_pins {
+	function = "gpio";
+};
+
 &pinctrl_nb {
 	i2c2_recovery_pins: i2c2-recovery-pins {
 		groups = "i2c2";
diff --git a/arch/arm64/boot/dts/marvell/armada-372x.dtsi b/arch/arm64/boot/dts/marvell/armada-372x.dtsi
index 02ae1e153288..b99ac4c03a48 100644
--- a/arch/arm64/boot/dts/marvell/armada-372x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-372x.dtsi
@@ -12,9 +12,6 @@
 #include "armada-37xx.dtsi"
 
 / {
-	model = "Marvell Armada 3720 SoC";
-	compatible = "marvell,armada3720", "marvell,armada3700";
-
 	cpus {
 		cpu1: cpu@1 {
 			device_type = "cpu";
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index 9603223dd761..75b0fdc3efb2 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -11,8 +11,6 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 
 / {
-	model = "Marvell Armada 37xx SoC";
-	compatible = "marvell,armada3700";
 	interrupt-parent = <&gic>;
 	#address-cells = <2>;
 	#size-cells = <2>;
@@ -78,7 +76,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		internal-regs@d0000000 {
+		bus@d0000000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "simple-bus";
diff --git a/arch/arm64/boot/dts/marvell/armada-7020.dtsi b/arch/arm64/boot/dts/marvell/armada-7020.dtsi
index 4e46326dd123..570f901b4f4a 100644
--- a/arch/arm64/boot/dts/marvell/armada-7020.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-7020.dtsi
@@ -8,9 +8,3 @@
 
 #include "armada-ap806-dual.dtsi"
 #include "armada-70x0.dtsi"
-
-/ {
-	model = "Marvell Armada 7020";
-	compatible = "marvell,armada7020", "marvell,armada-ap806-dual",
-		     "marvell,armada-ap806";
-};
diff --git a/arch/arm64/boot/dts/marvell/armada-7040.dtsi b/arch/arm64/boot/dts/marvell/armada-7040.dtsi
index 2f440711d21d..710ac44870bd 100644
--- a/arch/arm64/boot/dts/marvell/armada-7040.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-7040.dtsi
@@ -9,12 +9,6 @@
 #include "armada-ap806-quad.dtsi"
 #include "armada-70x0.dtsi"
 
-/ {
-	model = "Marvell Armada 7040";
-	compatible = "marvell,armada7040", "marvell,armada-ap806-quad",
-		     "marvell,armada-ap806";
-};
-
 &cp0_pcie0 {
 	iommu-map =
 		<0x0   &smmu 0x480 0x20>,
diff --git a/arch/arm64/boot/dts/marvell/armada-8020.dtsi b/arch/arm64/boot/dts/marvell/armada-8020.dtsi
index ba1307c0fadb..b6fc18876093 100644
--- a/arch/arm64/boot/dts/marvell/armada-8020.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-8020.dtsi
@@ -9,12 +9,6 @@
 #include "armada-ap806-dual.dtsi"
 #include "armada-80x0.dtsi"
 
-/ {
-	model = "Marvell Armada 8020";
-	compatible = "marvell,armada8020", "marvell,armada-ap806-dual",
-		     "marvell,armada-ap806";
-};
-
 /* The RTC requires external oscillator. But on Aramda 80x0, the RTC clock
  * in CP master is not connected (by package) to the oscillator. So
  * disable it. However, the RTC clock in CP slave is connected to the
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index 225a54ab688d..90ae93274a16 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -371,25 +371,25 @@
 };
 
 &cp0_gpio2 {
-	sata_reset {
+	sata-reset-hog {
 		gpio-hog;
 		gpios = <1 GPIO_ACTIVE_HIGH>;
 		output-high;
 	};
 
-	lte_reset {
+	lte-reset-hog {
 		gpio-hog;
 		gpios = <2 GPIO_ACTIVE_LOW>;
 		output-low;
 	};
 
-	wlan_disable {
+	wlan_disable-hog {
 		gpio-hog;
 		gpios = <19 GPIO_ACTIVE_LOW>;
 		output-low;
 	};
 
-	lte_disable {
+	lte-disable-hog {
 		gpio-hog;
 		gpios = <21 GPIO_ACTIVE_LOW>;
 		output-low;
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts b/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts
index 9c25a88581e4..def25d51c4bf 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-puzzle-m801.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "IEI-Puzzle-M801";
-	compatible = "marvell,armada8040", "marvell,armada-ap806-quad", "marvell,armada-ap806";
+	compatible = "iei,puzzle-m801", "marvell,armada8040", "marvell,armada-ap806-quad", "marvell,armada-ap806";
 
 	aliases {
 		ethernet0 = &cp0_eth0;
diff --git a/arch/arm64/boot/dts/marvell/armada-8040.dtsi b/arch/arm64/boot/dts/marvell/armada-8040.dtsi
index 22c2d6ebf381..3efd9b9e6892 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-8040.dtsi
@@ -9,12 +9,6 @@
 #include "armada-ap806-quad.dtsi"
 #include "armada-80x0.dtsi"
 
-/ {
-	model = "Marvell Armada 8040";
-	compatible = "marvell,armada8040", "marvell,armada-ap806-quad",
-		     "marvell,armada-ap806";
-};
-
 &cp0_pcie0 {
 	iommu-map =
 		<0x0   &smmu 0x480 0x20>,
diff --git a/arch/arm64/boot/dts/marvell/armada-8080.dtsi b/arch/arm64/boot/dts/marvell/armada-8080.dtsi
index 299e814d1ded..32bb56f2fe3f 100644
--- a/arch/arm64/boot/dts/marvell/armada-8080.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-8080.dtsi
@@ -6,9 +6,3 @@
  */
 
 #include "armada-ap810-ap0-octa-core.dtsi"
-
-/ {
-	model = "Marvell 8080 board";
-	compatible = "marvell,armada-8080", "marvell,armada-ap810-octa",
-				"marvell,armada-ap810";
-};
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806-dual.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806-dual.dtsi
index 3ed6fba1f438..82f4dedfc25e 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806-dual.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806-dual.dtsi
@@ -8,9 +8,6 @@
 #include "armada-ap806.dtsi"
 
 / {
-	model = "Marvell Armada AP806 Dual";
-	compatible = "marvell,armada-ap806-dual", "marvell,armada-ap806";
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi
index cf6a96ddcf40..f37f49c79a50 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi
@@ -8,9 +8,6 @@
 #include "armada-ap806.dtsi"
 
 / {
-	model = "Marvell Armada AP806 Quad";
-	compatible = "marvell,armada-ap806-quad", "marvell,armada-ap806";
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 866628679ac7..73a570cf1010 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -5,14 +5,8 @@
  * Device Tree file for Marvell Armada AP806.
  */
 
-#define AP_NAME		ap806
 #include "armada-ap80x.dtsi"
 
-/ {
-	model = "Marvell Armada AP806";
-	compatible = "marvell,armada-ap806";
-};
-
 &ap_syscon0 {
 	ap_clk: clock {
 		compatible = "marvell,ap806-clock";
diff --git a/arch/arm64/boot/dts/marvell/armada-ap807-quad.dtsi b/arch/arm64/boot/dts/marvell/armada-ap807-quad.dtsi
index 8848238f9565..e8af7546e893 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap807-quad.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap807-quad.dtsi
@@ -8,9 +8,6 @@
 #include "armada-ap807.dtsi"
 
 / {
-	model = "Marvell Armada AP807 Quad";
-	compatible = "marvell,armada-ap807-quad", "marvell,armada-ap807";
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap807.dtsi b/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
index a3328d05fc94..196793d8715c 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
@@ -5,14 +5,8 @@
  * Copyright (C) 2019 Marvell Technology Group Ltd.
  */
 
-#define AP_NAME		ap807
 #include "armada-ap80x.dtsi"
 
-/ {
-	model = "Marvell Armada AP807";
-	compatible = "marvell,armada-ap807";
-};
-
 &ap_syscon0 {
 	ap_clk: clock {
 		compatible = "marvell,ap807-clock";
diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
index fdf88cd0eb02..40e146982921 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
@@ -48,14 +48,29 @@
 		};
 	};
 
-	AP_NAME {
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+				<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+				<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+				<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	pmu {
+		compatible = "arm,cortex-a72-pmu";
+		interrupt-parent = <&pic>;
+		interrupts = <17>;
+	};
+
+	soc {
 		#address-cells = <2>;
 		#size-cells = <2>;
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
 		ranges;
 
-		config-space@f0000000 {
+		bus@f0000000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "simple-bus";
@@ -122,20 +137,6 @@
 				};
 			};
 
-			timer {
-				compatible = "arm,armv8-timer";
-				interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-					     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-					     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-					     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
-			};
-
-			pmu {
-				compatible = "arm,cortex-a72-pmu";
-				interrupt-parent = <&pic>;
-				interrupts = <17>;
-			};
-
 			odmi: odmi@300000 {
 				compatible = "marvell,odmi-controller";
 				msi-controller;
diff --git a/arch/arm64/boot/dts/marvell/armada-ap810-ap0-octa-core.dtsi b/arch/arm64/boot/dts/marvell/armada-ap810-ap0-octa-core.dtsi
index d1a7143ef3d4..2e719ffc8289 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap810-ap0-octa-core.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap810-ap0-octa-core.dtsi
@@ -11,7 +11,6 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		compatible = "marvell,armada-ap810-octa";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
diff --git a/arch/arm64/boot/dts/marvell/armada-ap810-ap0.dtsi b/arch/arm64/boot/dts/marvell/armada-ap810-ap0.dtsi
index 2f9ab6b4a2c9..abb37e5fc2c0 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap810-ap0.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap810-ap0.dtsi
@@ -10,10 +10,9 @@
 /dts-v1/;
 
 / {
-	model = "Marvell Armada AP810";
-	compatible = "marvell,armada-ap810";
 	#address-cells = <2>;
 	#size-cells = <2>;
+	interrupt-parent = <&gic>;
 
 	aliases {
 		serial0 = &uart0_ap0;
@@ -25,14 +24,21 @@
 		method = "smc";
 	};
 
-	ap810-ap0 {
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+				<GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+				<GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+				<GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	soc {
 		#address-cells = <2>;
 		#size-cells = <2>;
 		compatible = "simple-bus";
-		interrupt-parent = <&gic>;
 		ranges;
 
-		config-space@e8000000 {
+		bus@e8000000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
 			compatible = "simple-bus";
@@ -62,14 +68,6 @@
 				};
 			};
 
-			timer {
-				compatible = "arm,armv8-timer";
-				interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
-					     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
-					     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
-					     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
-			};
-
 			xor@400000 {
 				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
 				reg = <0x400000 0x1000>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 4fd33b0fa56e..e3cfd168becc 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -5,8 +5,4 @@
  * Device Tree file for Marvell Armada CP110.
  */
 
-#define CP11X_TYPE cp110
-
 #include "armada-cp11x.dtsi"
-
-#undef CP11X_TYPE
diff --git a/arch/arm64/boot/dts/marvell/armada-cp115.dtsi b/arch/arm64/boot/dts/marvell/armada-cp115.dtsi
index 1d0a9653e681..ec6432c8db7c 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp115.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp115.dtsi
@@ -5,8 +5,4 @@
  * Device Tree file for Marvell Armada CP115.
  */
 
-#define CP11X_TYPE cp115
-
 #include "armada-cp11x.dtsi"
-
-#undef CP11X_TYPE
diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
index 161beec0b6b0..a057e119492f 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
@@ -17,7 +17,7 @@
 	 * The contents of the node are defined below, in order to
 	 * save one indentation level
 	 */
-	CP11X_NAME: CP11X_NAME { };
+	CP11X_NAME: CP11X_NODE_NAME(bus) { };
 
 	/*
 	 * CPs only have one sensor in the thermal IC.
@@ -51,7 +51,7 @@
 	interrupt-parent = <&CP11X_LABEL(icu_nsr)>;
 	ranges;
 
-	config-space@CP11X_BASE {
+	bus@CP11X_BASE {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
diff --git a/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi b/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
index cb8d54895a77..a997bbabedd8 100644
--- a/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
+++ b/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
@@ -7,9 +7,6 @@
 #include <dt-bindings/gpio/gpio.h>
 
 / {
-	model = "SolidRun CN9130 SoM";
-	compatible = "solidrun,cn9130-sr-som", "marvell,cn9130";
-
 	aliases {
 		ethernet0 = &cp0_eth0;
 		ethernet1 = &cp0_eth1;
diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile
index b763b73788a4..58484e830063 100644
--- a/arch/arm64/boot/dts/mediatek/Makefile
+++ b/arch/arm64/boot/dts/mediatek/Makefile
@@ -95,13 +95,16 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-cherry-tomato-r3.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-demo.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8365-evk.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8370-genio-510-evk.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-genio-1200-evk.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8390-genio-700-evk.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-kontron-3-5-sbc-i1200.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l-8-hd-panel.dtbo
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8516-pumpkin.dtb
 
 # Device tree overlays support
 DTC_FLAGS_mt7986a-bananapi-bpi-r3 := -@
 DTC_FLAGS_mt7986a-bananapi-bpi-r3-mini := -@
 DTC_FLAGS_mt7988a-bananapi-bpi-r4 := -@
+DTC_FLAGS_mt8395-radxa-nio-12l := -@
diff --git a/arch/arm64/boot/dts/mediatek/mt6359.dtsi b/arch/arm64/boot/dts/mediatek/mt6359.dtsi
index 150ad84d5d2b..7b10f9c59819 100644
--- a/arch/arm64/boot/dts/mediatek/mt6359.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt6359.dtsi
@@ -15,7 +15,8 @@
 			#io-channel-cells = <1>;
 		};
 
-		mt6359codec: mt6359codec {
+		mt6359codec: audio-codec {
+			compatible = "mediatek,mt6359-codec";
 		};
 
 		regulators {
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
index b5d4b5baf478..0d995b342d46 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
@@ -925,8 +925,6 @@
 &pwrap {
 	pmic: pmic {
 		compatible = "mediatek,mt6397";
-		#address-cells = <1>;
-		#size-cells = <1>;
 		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 3458be7f7f61..6d1d8877b43f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -352,14 +352,14 @@
 			#clock-cells = <1>;
 		};
 
-		infracfg: power-controller@10001000 {
+		infracfg: clock-controller@10001000 {
 			compatible = "mediatek,mt8173-infracfg", "syscon";
 			reg = <0 0x10001000 0 0x1000>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
 		};
 
-		pericfg: power-controller@10003000 {
+		pericfg: clock-controller@10003000 {
 			compatible = "mediatek,mt8173-pericfg", "syscon";
 			reg = <0 0x10003000 0 0x1000>;
 			#clock-cells = <1>;
@@ -564,7 +564,7 @@
 			memory-region = <&vpu_dma_reserved>;
 		};
 
-		sysirq: intpol-controller@10200620 {
+		sysirq: interrupt-controller@10200620 {
 			compatible = "mediatek,mt8173-sysirq",
 				     "mediatek,mt6577-sysirq";
 			interrupt-controller;
@@ -1255,8 +1255,7 @@
 		};
 
 		pwm0: pwm@1401e000 {
-			compatible = "mediatek,mt8173-disp-pwm",
-				     "mediatek,mt6595-disp-pwm";
+			compatible = "mediatek,mt8173-disp-pwm";
 			reg = <0 0x1401e000 0 0x1000>;
 			#pwm-cells = <2>;
 			clocks = <&mmsys CLK_MM_DISP_PWM026M>,
@@ -1266,8 +1265,7 @@
 		};
 
 		pwm1: pwm@1401f000 {
-			compatible = "mediatek,mt8173-disp-pwm",
-				     "mediatek,mt6595-disp-pwm";
+			compatible = "mediatek,mt8173-disp-pwm";
 			reg = <0 0x1401f000 0 0x1000>;
 			#pwm-cells = <2>;
 			clocks = <&mmsys CLK_MM_DISP_PWM126M>,
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
index 3935d83a047e..7bc7c2687d6f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-damu.dts
@@ -14,16 +14,13 @@
 };
 
 &touchscreen {
-	status = "okay";
+	compatible = "elan,ekth6a12nay";
 
-	compatible = "hid-over-i2c";
-	reg = <0x10>;
-	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
-	post-power-on-delay-ms = <10>;
-	hid-descr-addr = <0x0001>;
+	vcc33-supply = <&pp3300_alw>;
+	vccio-supply = <&pp1800_alw>;
 };
 
 &mt6358codec {
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
index 72852b760038..863f3e403de8 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku1.dts
@@ -27,16 +27,12 @@
 };
 
 &touchscreen {
-	status = "okay";
+	compatible = "elan,ekth6a12nay";
 
-	compatible = "hid-over-i2c";
-	reg = <0x10>;
-	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
-	post-power-on-delay-ms = <10>;
-	hid-descr-addr = <0x0001>;
+	vcc33-supply = <&pp3300_alw>;
 };
 
 &qca_wifi {
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
index 757d0afd14fb..e0a583ce4a0b 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku6.dts
@@ -14,16 +14,12 @@
 };
 
 &touchscreen {
-	status = "okay";
+	compatible = "elan,ekth6a12nay";
 
-	compatible = "hid-over-i2c";
-	reg = <0x10>;
-	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
-	post-power-on-delay-ms = <10>;
-	hid-descr-addr = <0x0001>;
+	vcc33-supply = <&pp3300_alw>;
 };
 
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
index 6641b087e7c5..7874c9a20e12 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-fennel-sku7.dts
@@ -14,16 +14,12 @@
 };
 
 &touchscreen {
-	status = "okay";
+	compatible = "elan,ekth6a12nay";
 
-	compatible = "hid-over-i2c";
-	reg = <0x10>;
-	interrupts-extended = <&pio 155 IRQ_TYPE_LEVEL_LOW>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&touchscreen_pins>;
 
-	post-power-on-delay-ms = <10>;
-	hid-descr-addr = <0x0001>;
+	vcc33-supply = <&pp3300_alw>;
 };
 
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
index b6abecbcfa81..c5254ae0bb99 100644
--- a/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
@@ -9,6 +9,7 @@
 
 / {
 	aliases {
+		dsi0 = &disp_dsi0;
 		i2c0 = &i2c0;
 		i2c1 = &i2c1;
 		i2c2 = &i2c2;
@@ -273,14 +274,27 @@
 
 		port {
 			dsi_panel_in: endpoint {
-				remote-endpoint = <&dsi_out>;
+				remote-endpoint = <&dsi0_out>;
 			};
 		};
 	};
 
-	port {
-		dsi_out: endpoint {
-			remote-endpoint = <&dsi_panel_in>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dsi0_in: endpoint {
+				remote-endpoint = <&dither0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dsi0_out: endpoint {
+				remote-endpoint = <&dsi_panel_in>;
+			};
 		};
 	};
 };
@@ -296,12 +310,74 @@
 	pinctrl-0 = <&disp_pwm1_pins>;
 };
 
+&dither0_in {
+	remote-endpoint = <&postmask0_out>;
+};
+
+&dither0_out {
+	remote-endpoint = <&dsi0_in>;
+};
+
+&ethdr0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			ethdr0_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&vdosys1_ep_ext>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			ethdr0_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&merge5_in>;
+			};
+		};
+	};
+};
+
+&gamma0_out {
+	remote-endpoint = <&postmask0_in>;
+};
+
 &dp_intf1 {
 	status = "okay";
 
-	port {
-		dp_intf1_out: endpoint {
-			remote-endpoint = <&dptx_in>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			dp_intf1_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&merge5_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			dp_intf1_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&dptx_in>;
+			};
 		};
 	};
 };
@@ -394,6 +470,35 @@
 	status = "okay";
 };
 
+&merge5 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			merge5_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&ethdr0_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			merge5_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&dp_intf1_in>;
+			};
+		};
+	};
+};
+
 &mfg0 {
 	domain-supply = <&mt6359_vproc2_buck_reg>;
 };
@@ -513,6 +618,10 @@
 	};
 };
 
+&ovl0_in {
+	remote-endpoint = <&vdosys0_ep_main>;
+};
+
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_pins>;
@@ -1029,6 +1138,14 @@
 	interrupts-extended = <&pio 222 IRQ_TYPE_LEVEL_HIGH>;
 };
 
+&postmask0_in {
+	remote-endpoint = <&gamma0_out>;
+};
+
+&postmask0_out {
+	remote-endpoint = <&dither0_in>;
+};
+
 &sound {
 	pinctrl-names = "aud_etdm_hp_on", "aud_etdm_hp_off",
 			"aud_etdm_spk_on", "aud_etdm_spk_off",
@@ -1103,6 +1220,12 @@
 };
 
 /* USB detachable base */
+&ssusb0 {
+	dr_mode = "host";
+	vusb33-supply = <&pp3300_s3>;
+	status = "okay";
+};
+
 &xhci0 {
 	/* controlled by EC */
 	vbus-supply = <&pp3300_z1>;
@@ -1110,6 +1233,12 @@
 };
 
 /* USB3 hub */
+&ssusb1 {
+	dr_mode = "host";
+	vusb33-supply = <&pp3300_s3>;
+	status = "okay";
+};
+
 &xhci1 {
 	vusb33-supply = <&pp3300_s3>;
 	vbus-supply = <&pp5000_usb_vbus>;
@@ -1117,6 +1246,36 @@
 };
 
 /* USB BT */
+&ssusb2 {
+	dr_mode = "host";
+	vusb33-supply = <&pp3300_s3>;
+	status = "okay";
+};
+
+&vdosys0 {
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdosys0_ep_main: endpoint@0 {
+			reg = <0>;
+			remote-endpoint = <&ovl0_in>;
+		};
+	};
+};
+
+&vdosys1 {
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdosys1_ep_ext: endpoint@1 {
+			reg = <1>;
+			remote-endpoint = <&ethdr0_in>;
+		};
+	};
+};
+
 &xhci2 {
 	/* no power supply since MT7921's power is controlled by PCIe */
 	/* MT7921's USB BT has issues with USB2 LPM */
diff --git a/arch/arm64/boot/dts/mediatek/mt8188.dtsi b/arch/arm64/boot/dts/mediatek/mt8188.dtsi
index 338120930b81..69a8423d3858 100644
--- a/arch/arm64/boot/dts/mediatek/mt8188.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8188.dtsi
@@ -26,9 +26,11 @@
 	aliases {
 		dp-intf0 = &dp_intf0;
 		dp-intf1 = &dp_intf1;
+		dsc0 = &dsc0;
 		ethdr0 = &ethdr0;
 		gce0 = &gce0;
 		gce1 = &gce1;
+		merge0 = &merge0;
 		merge1 = &merge1;
 		merge2 = &merge2;
 		merge3 = &merge3;
@@ -492,7 +494,7 @@
 			};
 
 			cooling-maps {
-				map0 {
+				cpu_little0_cooling_map0: map0 {
 					trip = <&cpu_little0_alert0>;
 					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
 							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
@@ -530,7 +532,7 @@
 			};
 
 			cooling-maps {
-				map0 {
+				cpu_little1_cooling_map0: map0 {
 					trip = <&cpu_little1_alert0>;
 					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
 							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
@@ -568,7 +570,7 @@
 			};
 
 			cooling-maps {
-				map0 {
+				cpu_little2_cooling_map0: map0 {
 					trip = <&cpu_little2_alert0>;
 					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
 							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
@@ -606,7 +608,7 @@
 			};
 
 			cooling-maps {
-				map0 {
+				cpu_little3_cooling_map0: map0 {
 					trip = <&cpu_little3_alert0>;
 					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
 							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
@@ -1392,7 +1394,7 @@
 			compatible = "mediatek,mt8188-afe";
 			reg = <0 0x10b10000 0 0x10000>;
 			assigned-clocks = <&topckgen CLK_TOP_A1SYS_HP>;
-			assigned-clock-parents =  <&clk26m>;
+			assigned-clock-parents = <&topckgen CLK_TOP_APLL1_D4>;
 			clocks = <&clk26m>,
 				 <&apmixedsys CLK_APMIXED_APLL1>,
 				 <&apmixedsys CLK_APMIXED_APLL2>,
@@ -1647,6 +1649,38 @@
 			status = "disabled";
 		};
 
+		ssusb1: usb@11201000 {
+			compatible = "mediatek,mt8188-mtu3", "mediatek,mtu3";
+			reg = <0 0x11201000 0 0x2dff>, <0 0x11203e00 0 0x0100>;
+			reg-names = "mac", "ippc";
+			ranges = <0 0 0 0x11200000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH 0>;
+			assigned-clocks = <&topckgen CLK_TOP_USB_TOP>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_BUS>,
+				 <&topckgen CLK_TOP_SSUSB_TOP_REF>,
+				 <&pericfg_ao CLK_PERI_AO_SSUSB_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			phys = <&u2port1 PHY_TYPE_USB2>, <&u3port1 PHY_TYPE_USB3>;
+			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x468 2>;
+			status = "disabled";
+
+			xhci1: usb@0 {
+				compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_XHCI>;
+				clock-names = "sys_ck";
+				status = "disabled";
+			};
+		};
+
 		eth: ethernet@11021000 {
 			compatible = "mediatek,mt8188-gmac", "mediatek,mt8195-gmac",
 				     "snps,dwmac-5.10a";
@@ -1744,27 +1778,6 @@
 			};
 		};
 
-		xhci1: usb@11200000 {
-			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
-			reg = <0 0x11200000 0 0x1000>,
-			      <0 0x11203e00 0 0x0100>;
-			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port1 PHY_TYPE_USB2>,
-			       <&u3port1 PHY_TYPE_USB3>;
-			assigned-clocks = <&topckgen CLK_TOP_USB_TOP>,
-					  <&topckgen CLK_TOP_SSUSB_XHCI>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
-			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_BUS>,
-				 <&topckgen CLK_TOP_SSUSB_TOP_REF>,
-				 <&pericfg_ao CLK_PERI_AO_SSUSB_XHCI>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck";
-			mediatek,syscon-wakeup = <&pericfg 0x468 2>;
-			wakeup-source;
-			status = "disabled";
-		};
-
 		mmc0: mmc@11230000 {
 			compatible = "mediatek,mt8188-mmc", "mediatek,mt8183-mmc";
 			reg = <0 0x11230000 0 0x10000>,
@@ -1792,6 +1805,20 @@
 			status = "disabled";
 		};
 
+		mmc2: mmc@11250000 {
+			compatible = "mediatek,mt8188-mmc", "mediatek,mt8183-mmc";
+			reg = <0 0x11250000 0 0x1000>,
+			      <0 0x11e60000 0 0x1000>;
+			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&topckgen CLK_TOP_MSDC30_2>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC2>,
+				 <&infracfg_ao CLK_INFRA_AO_MSDC30_2>;
+			clock-names = "source", "hclk", "source_cg";
+			assigned-clocks = <&topckgen CLK_TOP_MSDC30_2>;
+			assigned-clock-parents = <&topckgen CLK_TOP_MSDCPLL_D2>;
+			status = "disabled";
+		};
+
 		lvts_mcu: thermal-sensor@11278000 {
 			compatible = "mediatek,mt8188-lvts-mcu";
 			reg = <0 0x11278000 0 0x1000>;
@@ -1851,42 +1878,68 @@
 			#clock-cells = <1>;
 		};
 
-		xhci2: usb@112a0000 {
-			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
-			reg = <0 0x112a0000 0 0x1000>,
-			      <0 0x112a3e00 0 0x0100>;
+		ssusb2: usb@112a1000 {
+			compatible = "mediatek,mt8188-mtu3", "mediatek,mtu3";
+			reg = <0 0x112a1000 0 0x2dff>, <0 0x112a3e00 0 0x0100>;
 			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port2 PHY_TYPE_USB2>;
-			assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_3P>,
-					  <&topckgen CLK_TOP_USB_TOP_3P>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			ranges = <0 0 0 0x112a0000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 535 IRQ_TYPE_LEVEL_HIGH 0>;
+			assigned-clocks = <&topckgen CLK_TOP_USB_TOP_3P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
 			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_3P_BUS>,
 				 <&topckgen CLK_TOP_SSUSB_TOP_P3_REF>,
 				 <&pericfg_ao CLK_PERI_AO_SSUSB_3P_XHCI>;
 			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			phys = <&u2port2 PHY_TYPE_USB2>;
+			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x470 2>;
 			status = "disabled";
+
+			xhci2: usb@0 {
+				compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_3P>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_3P_XHCI>;
+				clock-names = "sys_ck";
+				status = "disabled";
+			};
 		};
 
-		xhci0: usb@112b0000 {
-			compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
-			reg = <0 0x112b0000 0 0x1000>,
-			      <0 0x112b3e00 0 0x0100>;
+		ssusb0: usb@112b1000 {
+			compatible = "mediatek,mt8188-mtu3", "mediatek,mtu3";
+			reg = <0 0x112b1000 0 0x2dff>, <0 0x112b3e00 0 0x0100>;
 			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 533 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port0 PHY_TYPE_USB2>;
-			assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_2P>,
-					  <&topckgen CLK_TOP_USB_TOP_2P>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			ranges = <0 0 0 0x112b0000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 532 IRQ_TYPE_LEVEL_HIGH 0>;
+			assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_2P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
 			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_2P_BUS>,
 				 <&topckgen CLK_TOP_SSUSB_TOP_P2_REF>,
 				 <&pericfg_ao CLK_PERI_AO_SSUSB_2P_XHCI>;
 			clock-names = "sys_ck", "ref_ck", "mcu_ck";
-			mediatek,syscon-wakeup = <&pericfg 0x460 2>;
+			phys = <&u2port0 PHY_TYPE_USB2>;
 			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x460 2>;
 			status = "disabled";
+
+			xhci0: usb@0 {
+				compatible = "mediatek,mt8188-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 533 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_USB_TOP_2P>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_2P_XHCI>;
+				clock-names = "sys_ck";
+				status = "disabled";
+			};
 		};
 
 		pcie: pcie@112f0000 {
@@ -2502,6 +2555,23 @@
 			iommus = <&vdo_iommu M4U_PORT_L0_DISP_OVL0_RDMA0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x0000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					ovl0_in: endpoint { };
+				};
+
+				port@1 {
+					reg = <1>;
+					ovl0_out: endpoint {
+						remote-endpoint = <&rdma0_in>;
+					};
+				};
+			};
 		};
 
 		rdma0: rdma@1c002000 {
@@ -2512,6 +2582,25 @@
 			iommus = <&vdo_iommu M4U_PORT_L1_DISP_RDMA0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x2000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					rdma0_in: endpoint {
+						remote-endpoint = <&ovl0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					rdma0_out: endpoint {
+						remote-endpoint = <&color0_in>;
+					};
+				};
+			};
 		};
 
 		color0: color@1c003000 {
@@ -2521,6 +2610,25 @@
 			interrupts = <GIC_SPI 639 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x3000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					color0_in: endpoint {
+						remote-endpoint = <&rdma0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					color0_out: endpoint {
+						remote-endpoint = <&ccorr0_in>;
+					};
+				};
+			};
 		};
 
 		ccorr0: ccorr@1c004000 {
@@ -2530,6 +2638,25 @@
 			interrupts = <GIC_SPI 640 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x4000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					ccorr0_in: endpoint {
+						remote-endpoint = <&color0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					ccorr0_out: endpoint {
+						remote-endpoint = <&aal0_in>;
+					};
+				};
+			};
 		};
 
 		aal0: aal@1c005000 {
@@ -2539,6 +2666,25 @@
 			interrupts = <GIC_SPI 641 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x5000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					aal0_in: endpoint {
+						remote-endpoint = <&ccorr0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					aal0_out: endpoint {
+						remote-endpoint = <&gamma0_in>;
+					};
+				};
+			};
 		};
 
 		gamma0: gamma@1c006000 {
@@ -2548,6 +2694,23 @@
 			interrupts = <GIC_SPI 642 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x6000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					gamma0_in: endpoint {
+						remote-endpoint = <&aal0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					gamma0_out: endpoint { };
+				};
+			};
 		};
 
 		dither0: dither@1c007000 {
@@ -2557,6 +2720,21 @@
 			interrupts = <GIC_SPI 643 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x7000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dither0_in: endpoint { };
+				};
+
+				port@1 {
+					reg = <1>;
+					dither0_out: endpoint { };
+				};
+			};
 		};
 
 		disp_dsi0: dsi@1c008000 {
@@ -2574,6 +2752,15 @@
 			status = "disabled";
 		};
 
+		dsc0: dsc@1c009000 {
+			compatible = "mediatek,mt8188-disp-dsc", "mediatek,mt8195-disp-dsc";
+			reg = <0 0x1c009000 0 0x1000>;
+			clocks = <&vdosys0 CLK_VDO0_DSC_WRAP0>;
+			interrupts = <GIC_SPI 645 IRQ_TYPE_LEVEL_HIGH 0>;
+			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
+			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x9000 0x1000>;
+		};
+
 		disp_dsi1: dsi@1c012000 {
 			compatible = "mediatek,mt8188-dsi";
 			reg = <0 0x1c012000 0 0x1000>;
@@ -2589,6 +2776,17 @@
 			status = "disabled";
 		};
 
+		merge0: merge0@1c014000 {
+			compatible = "mediatek,mt8188-disp-merge", "mediatek,mt8195-disp-merge";
+			reg = <0 0x1c014000 0 0x1000>;
+			clocks = <&vdosys0 CLK_VDO0_VPP_MERGE0>,
+				 <&vdosys1 CLK_VDO1_MERGE_VDO1_DL_ASYNC>;
+			clock-names = "merge", "merge_async";
+			interrupts = <GIC_SPI 656 IRQ_TYPE_LEVEL_HIGH 0>;
+			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
+			mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x4000 0x1000>;
+		};
+
 		dp_intf0: dp-intf@1c015000 {
 			compatible = "mediatek,mt8188-dp-intf";
 			reg = <0 0x1c015000 0 0x1000>;
@@ -2619,6 +2817,21 @@
 			interrupts = <GIC_SPI 661 IRQ_TYPE_LEVEL_HIGH 0>;
 			power-domains = <&spm MT8188_POWER_DOMAIN_VDOSYS0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					postmask0_in: endpoint { };
+				};
+
+				port@1 {
+					reg = <1>;
+					postmask0_out: endpoint { };
+				};
+			};
 		};
 
 		vdosys0: syscon@1c01d000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index 5056e07399e2..e70599807bb1 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -297,12 +297,29 @@
 	cpu-supply = <&mt6315_6_vbuck1>;
 };
 
+&dither0_out {
+	remote-endpoint = <&dsc0_in>;
+};
+
 &dp_intf0 {
 	status = "okay";
 
-	port {
-		dp_intf0_out: endpoint {
-			remote-endpoint = <&edp_in>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dp_intf0_in: endpoint {
+				remote-endpoint = <&merge0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dp_intf0_out: endpoint {
+				remote-endpoint = <&edp_in>;
+			};
 		};
 	};
 };
@@ -310,9 +327,51 @@
 &dp_intf1 {
 	status = "okay";
 
-	port {
-		dp_intf1_out: endpoint {
-			remote-endpoint = <&dptx_in>;
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			dp_intf1_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&merge5_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			dp_intf1_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&dptx_in>;
+			};
+		};
+	};
+};
+
+&dsc0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dsc0_in: endpoint {
+				remote-endpoint = <&dither0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dsc0_out: endpoint {
+				remote-endpoint = <&merge0_in>;
+			};
 		};
 	};
 };
@@ -357,6 +416,35 @@
 	};
 };
 
+&ethdr0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			ethdr0_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&vdosys1_ep_ext>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			ethdr0_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&merge5_in>;
+			};
+		};
+	};
+};
+
 &disp_pwm0 {
 	status = "okay";
 
@@ -376,8 +464,12 @@
 		#size-cells = <0>;
 
 		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
 			reg = <0>;
-			dptx_in: endpoint {
+
+			dptx_in: endpoint@1 {
+				reg = <1>;
 				remote-endpoint = <&dp_intf1_out>;
 			};
 		};
@@ -511,6 +603,56 @@
 	};
 };
 
+&merge0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			merge0_in: endpoint {
+				remote-endpoint = <&dsc0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			merge0_out: endpoint {
+				remote-endpoint = <&dp_intf0_in>;
+			};
+		};
+	};
+};
+
+&merge5 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			merge5_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&ethdr0_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			merge5_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&dp_intf1_in>;
+			};
+		};
+	};
+};
+
 &mfg0 {
 	domain-supply = <&mt6315_7_vbuck1>;
 };
@@ -612,6 +754,10 @@
 	};
 };
 
+&ovl0_in {
+	remote-endpoint = <&vdosys0_ep_main>;
+};
+
 &pcie1 {
 	status = "okay";
 
@@ -1363,6 +1509,18 @@
 	status = "okay";
 };
 
+&vdosys0 {
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdosys0_ep_main: endpoint@0 {
+			reg = <0>;
+			remote-endpoint = <&ovl0_in>;
+		};
+	};
+};
+
 /*
  * For the USB Type-C ports the role and alternate modes switching is
  * done by the EC so we set dr_mode to host to avoid interfering.
@@ -1385,6 +1543,18 @@
 	status = "okay";
 };
 
+&vdosys1 {
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdosys1_ep_ext: endpoint@1 {
+			reg = <1>;
+			remote-endpoint = <&ethdr0_in>;
+		};
+	};
+};
+
 &xhci0 {
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index f013dbad9dc4..4f2dc0a75566 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -3142,6 +3142,23 @@
 			clocks = <&vdosys0 CLK_VDO0_DISP_OVL0>;
 			iommus = <&iommu_vdo M4U_PORT_L0_DISP_OVL0_RDMA0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x0000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					ovl0_in: endpoint { };
+				};
+
+				port@1 {
+					reg = <1>;
+					ovl0_out: endpoint {
+						remote-endpoint = <&rdma0_in>;
+					};
+				};
+			};
 		};
 
 		rdma0: rdma@1c002000 {
@@ -3152,6 +3169,25 @@
 			clocks = <&vdosys0 CLK_VDO0_DISP_RDMA0>;
 			iommus = <&iommu_vdo M4U_PORT_L0_DISP_RDMA0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x2000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					rdma0_in: endpoint {
+						remote-endpoint = <&ovl0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					rdma0_out: endpoint {
+						remote-endpoint = <&color0_in>;
+					};
+				};
+			};
 		};
 
 		color0: color@1c003000 {
@@ -3161,6 +3197,25 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
 			clocks = <&vdosys0 CLK_VDO0_DISP_COLOR0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x3000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					color0_in: endpoint {
+						remote-endpoint = <&rdma0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					color0_out: endpoint {
+						remote-endpoint = <&ccorr0_in>;
+					};
+				};
+			};
 		};
 
 		ccorr0: ccorr@1c004000 {
@@ -3170,6 +3225,25 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
 			clocks = <&vdosys0 CLK_VDO0_DISP_CCORR0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x4000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					ccorr0_in: endpoint {
+						remote-endpoint = <&color0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					ccorr0_out: endpoint {
+						remote-endpoint = <&aal0_in>;
+					};
+				};
+			};
 		};
 
 		aal0: aal@1c005000 {
@@ -3179,6 +3253,25 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
 			clocks = <&vdosys0 CLK_VDO0_DISP_AAL0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x5000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					aal0_in: endpoint {
+						remote-endpoint = <&ccorr0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					aal0_out: endpoint {
+						remote-endpoint = <&gamma0_in>;
+					};
+				};
+			};
 		};
 
 		gamma0: gamma@1c006000 {
@@ -3188,6 +3281,25 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
 			clocks = <&vdosys0 CLK_VDO0_DISP_GAMMA0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x6000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					gamma0_in: endpoint {
+						remote-endpoint = <&aal0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					gamma0_out: endpoint {
+						remote-endpoint = <&dither0_in>;
+					};
+				};
+			};
 		};
 
 		dither0: dither@1c007000 {
@@ -3197,6 +3309,23 @@
 			power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
 			clocks = <&vdosys0 CLK_VDO0_DISP_DITHER0>;
 			mediatek,gce-client-reg = <&gce0 SUBSYS_1c00XXXX 0x7000 0x1000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dither0_in: endpoint {
+						remote-endpoint = <&gamma0_out>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					dither0_out: endpoint { };
+				};
+			};
 		};
 
 		dsi0: dsi@1c008000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8365-evk.dts b/arch/arm64/boot/dts/mediatek/mt8365-evk.dts
index 44c61094c4d5..1f8584bd66c3 100644
--- a/arch/arm64/boot/dts/mediatek/mt8365-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8365-evk.dts
@@ -28,6 +28,21 @@
 		stdout-path = "serial0:921600n8";
 	};
 
+	connector {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+		type = "d";
+
+		port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			hdmi_connector_in: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&hdmi_connector_out>;
+			};
+		};
+	};
+
 	firmware {
 		optee {
 			compatible = "linaro,optee-tz";
@@ -105,6 +120,16 @@
 		pinctrl-5 = <&aud_mosi_on_pins>;
 		mediatek,platform = <&afe>;
 	};
+
+	vsys_lcm_reg: regulator-vsys-lcm {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&pio 129 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "vsys_lcm";
+	};
+
 };
 
 &afe {
@@ -132,13 +157,102 @@
 	sram-supply = <&mt6357_vsram_proc_reg>;
 };
 
+&dither0_out {
+	remote-endpoint = <&dsi0_in>;
+};
+
+&dpi0 {
+	pinctrl-0 = <&dpi_default_pins>;
+	pinctrl-1 = <&dpi_idle_pins>;
+	pinctrl-names = "default", "sleep";
+	/*
+	 * Ethernet and HDMI (DPI0) are sharing pins.
+	 * Only one can be enabled at a time and require the physical switch
+	 * SW2101 to be set on LAN position
+	 */
+	status = "disabled";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+			dpi0_in: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&rdma1_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+			dpi0_out: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&it66121_in>;
+			};
+		};
+	};
+};
+
+&dsi0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "startek,kd070fhfid015";
+		reg = <0>;
+		enable-gpios = <&pio 67 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&pio 20 GPIO_ACTIVE_HIGH>;
+		iovcc-supply = <&mt6357_vsim1_reg>;
+		power-supply = <&vsys_lcm_reg>;
+
+		port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			panel_in: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&dsi0_out>;
+			};
+		};
+	};
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+			dsi0_in: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&dither0_out>;
+			};
+		};
+
+		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+			dsi0_out: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
+};
+
 &ethernet {
 	pinctrl-0 = <&ethernet_pins>;
 	pinctrl-names = "default";
 	phy-handle = <&eth_phy>;
 	phy-mode = "rmii";
 	/*
-	 * Ethernet and HDMI (DSI0) are sharing pins.
+	 * Ethernet and HDMI (DPI0) are sharing pins.
 	 * Only one can be enabled at a time and require the physical switch
 	 * SW2101 to be set on LAN position
 	 * mt6357_vibr_reg and mt6357_vsim2_reg are needed to supply ethernet
@@ -162,6 +276,56 @@
 	status = "okay";
 };
 
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-div = <2>;
+	clock-frequency = <100000>;
+	pinctrl-0 = <&i2c1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	it66121_hdmi: hdmi@4c {
+		compatible = "ite,it66121";
+		reg = <0x4c>;
+		#sound-dai-cells = <0>;
+		interrupt-parent = <&pio>;
+		interrupts = <68 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-0 = <&ite_pins>;
+		pinctrl-names = "default";
+		reset-gpios = <&pio 69 GPIO_ACTIVE_LOW>;
+		vcn18-supply = <&mt6357_vsim2_reg>;
+		vcn33-supply = <&mt6357_vibr_reg>;
+		vrf12-supply = <&mt6357_vrf12_reg>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				it66121_in: endpoint@0 {
+					reg = <0>;
+					bus-width = <12>;
+					remote-endpoint = <&dpi0_out>;
+				};
+			};
+
+			port@1 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <1>;
+				hdmi_connector_out: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
+};
+
 &mmc0 {
 	assigned-clock-parents = <&topckgen CLK_TOP_MSDCPLL>;
 	assigned-clocks = <&topckgen CLK_TOP_MSDC50_0_SEL>;
@@ -206,6 +370,11 @@
 	mediatek,micbias1-microvolt = <1700000>;
 };
 
+&mt6357_vsim1_reg {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+};
+
 &pio {
 	aud_default_pins: audiodefault-pins {
 		clk-dat-pins {
@@ -268,6 +437,49 @@
 		};
 	};
 
+	dpi_default_pins: dpi-default-pins {
+		pins {
+			pinmux = <MT8365_PIN_0_GPIO0__FUNC_DPI_D0>,
+				 <MT8365_PIN_1_GPIO1__FUNC_DPI_D1>,
+				 <MT8365_PIN_2_GPIO2__FUNC_DPI_D2>,
+				 <MT8365_PIN_3_GPIO3__FUNC_DPI_D3>,
+				 <MT8365_PIN_4_GPIO4__FUNC_DPI_D4>,
+				 <MT8365_PIN_5_GPIO5__FUNC_DPI_D5>,
+				 <MT8365_PIN_6_GPIO6__FUNC_DPI_D6>,
+				 <MT8365_PIN_7_GPIO7__FUNC_DPI_D7>,
+				 <MT8365_PIN_8_GPIO8__FUNC_DPI_D8>,
+				 <MT8365_PIN_9_GPIO9__FUNC_DPI_D9>,
+				 <MT8365_PIN_10_GPIO10__FUNC_DPI_D10>,
+				 <MT8365_PIN_11_GPIO11__FUNC_DPI_D11>,
+				 <MT8365_PIN_12_GPIO12__FUNC_DPI_DE>,
+				 <MT8365_PIN_13_GPIO13__FUNC_DPI_VSYNC>,
+				 <MT8365_PIN_14_GPIO14__FUNC_DPI_CK>,
+				 <MT8365_PIN_15_GPIO15__FUNC_DPI_HSYNC>;
+			drive-strength = <4>;
+		};
+	};
+
+	dpi_idle_pins: dpi-idle-pins {
+		pins {
+			pinmux = <MT8365_PIN_0_GPIO0__FUNC_GPIO0>,
+				 <MT8365_PIN_1_GPIO1__FUNC_GPIO1>,
+				 <MT8365_PIN_2_GPIO2__FUNC_GPIO2>,
+				 <MT8365_PIN_3_GPIO3__FUNC_GPIO3>,
+				 <MT8365_PIN_4_GPIO4__FUNC_GPIO4>,
+				 <MT8365_PIN_5_GPIO5__FUNC_GPIO5>,
+				 <MT8365_PIN_6_GPIO6__FUNC_GPIO6>,
+				 <MT8365_PIN_7_GPIO7__FUNC_GPIO7>,
+				 <MT8365_PIN_8_GPIO8__FUNC_GPIO8>,
+				 <MT8365_PIN_9_GPIO9__FUNC_GPIO9>,
+				 <MT8365_PIN_10_GPIO10__FUNC_GPIO10>,
+				 <MT8365_PIN_11_GPIO11__FUNC_GPIO11>,
+				 <MT8365_PIN_12_GPIO12__FUNC_GPIO12>,
+				 <MT8365_PIN_13_GPIO13__FUNC_GPIO13>,
+				 <MT8365_PIN_14_GPIO14__FUNC_GPIO14>,
+				 <MT8365_PIN_15_GPIO15__FUNC_GPIO15>;
+		};
+	};
+
 	ethernet_pins: ethernet-pins {
 		phy_reset_pins {
 			pinmux = <MT8365_PIN_133_TDM_TX_DATA1__FUNC_GPIO133>;
@@ -309,6 +521,33 @@
 		};
 	};
 
+	i2c1_pins: i2c1-pins {
+		pins {
+			pinmux = <MT8365_PIN_59_SDA1__FUNC_SDA1_0>,
+				 <MT8365_PIN_60_SCL1__FUNC_SCL1_0>;
+			bias-pull-up;
+		};
+	};
+
+	ite_pins: ite-pins {
+		irq_ite_pins {
+			pinmux = <MT8365_PIN_68_CMDAT0__FUNC_GPIO68>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pwr_pins {
+			pinmux = <MT8365_PIN_70_CMDAT2__FUNC_GPIO70>,
+				 <MT8365_PIN_71_CMDAT3__FUNC_GPIO71>;
+			output-high;
+		};
+
+		rst_ite_pins {
+			pinmux = <MT8365_PIN_69_CMDAT1__FUNC_GPIO69>;
+			output-high;
+		};
+	};
+
 	mmc0_default_pins: mmc0-default-pins {
 		clk-pins {
 			pinmux = <MT8365_PIN_99_MSDC0_CLK__FUNC_MSDC0_CLK>;
@@ -464,6 +703,10 @@
 	status = "okay";
 };
 
+&rdma1_out {
+	remote-endpoint = <&dpi0_in>;
+};
+
 &ssusb {
 	dr_mode = "otg";
 	maximum-speed = "high-speed";
diff --git a/arch/arm64/boot/dts/mediatek/mt8365.dtsi b/arch/arm64/boot/dts/mediatek/mt8365.dtsi
index 2bf8c9d02b6e..e6d2b3221a3b 100644
--- a/arch/arm64/boot/dts/mediatek/mt8365.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8365.dtsi
@@ -10,6 +10,7 @@
 #include <dt-bindings/clock/mediatek,mt8365-clk.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/memory/mediatek,mt8365-larb-port.h>
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/power/mediatek,mt8365-power.h>
 
@@ -19,6 +20,19 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	aliases {
+		aal0 = &aal0;
+		ccorr0 = &ccorr0;
+		color0 = &color0;
+		dither0 = &dither0;
+		dpi0 = &dpi0;
+		dsi0 = &dsi0;
+		gamma0 = &gamma0;
+		ovl0 = &ovl0;
+		rdma0 = &rdma0;
+		rdma1 = &rdma1;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -609,6 +623,15 @@
 			status = "disabled";
 		};
 
+		disp_pwm: pwm@1100e000 {
+			compatible = "mediatek,mt8365-disp-pwm", "mediatek,mt8183-disp-pwm";
+			reg = <0 0x1100e000 0 0x1000>;
+			clock-names = "main", "mm";
+			clocks = <&topckgen CLK_TOP_DISP_PWM_SEL>, <&infracfg CLK_IFR_DISP_PWM>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			#pwm-cells = <2>;
+		};
+
 		i2c3: i2c@1100f000 {
 			compatible = "mediatek,mt8365-i2c", "mediatek,mt8168-i2c";
 			reg = <0 0x1100f000 0 0xa0>, <0 0x11000200 0 0x80>;
@@ -705,6 +728,15 @@
 			status = "disabled";
 		};
 
+		mipi_tx0: dsi-phy@11c00000 {
+			compatible = "mediatek,mt8365-mipi-tx", "mediatek,mt8183-mipi-tx";
+			reg = <0 0x11c00000 0 0x800>;
+			clock-output-names = "mipi_tx0_pll";
+			clocks = <&clk26m>;
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+		};
+
 		u3phy: t-phy@11cc0000 {
 			compatible = "mediatek,mt8365-tphy", "mediatek,generic-tphy-v2";
 			#address-cells = <1>;
@@ -732,6 +764,26 @@
 			compatible = "mediatek,mt8365-mmsys", "syscon";
 			reg = <0 0x14000000 0 0x1000>;
 			#clock-cells = <1>;
+			port {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				mmsys_main: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&ovl0_in>;
+				};
+				mmsys_ext: endpoint@1 {
+					reg = <1>;
+					remote-endpoint = <&rdma1_in>;
+				};
+			};
+		};
+
+		mutex: mutex@14001000 {
+			compatible =  "mediatek,mt8365-disp-mutex";
+			reg = <0 0x14001000 0 0x1000>;
+			interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
 		};
 
 		smi_common: smi@14002000 {
@@ -757,6 +809,290 @@
 			mediatek,larb-id = <0>;
 		};
 
+		ovl0: ovl@1400b000 {
+			compatible = "mediatek,mt8365-disp-ovl", "mediatek,mt8192-disp-ovl";
+			reg = <0 0x1400b000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_OVL0>;
+			interrupts = <GIC_SPI 161 IRQ_TYPE_LEVEL_LOW>;
+			iommus = <&iommu M4U_PORT_DISP_OVL0>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					ovl0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&mmsys_main>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					ovl0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&rdma0_in>;
+					};
+				};
+			};
+		};
+
+		rdma0: rdma@1400d000 {
+			compatible = "mediatek,mt8365-disp-rdma", "mediatek,mt8183-disp-rdma";
+			reg = <0 0x1400d000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_RDMA0>;
+			interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_LOW>;
+			iommus = <&iommu M4U_PORT_DISP_RDMA0>;
+			mediatek,rdma-fifo-size = <5120>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					rdma0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&ovl0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					rdma0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&color0_in>;
+					};
+				};
+			};
+		};
+
+		color0: color@1400f000 {
+			compatible = "mediatek,mt8365-disp-color", "mediatek,mt8173-disp-color";
+			reg = <0 0x1400f000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_COLOR0>;
+			interrupts = <GIC_SPI 164 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					color0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&rdma0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					color0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&ccorr0_in>;
+					};
+				};
+			};
+		};
+
+		ccorr0: ccorr@14010000 {
+			compatible = "mediatek,mt8365-disp-ccorr", "mediatek,mt8183-disp-ccorr";
+			reg = <0 0x14010000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_CCORR0>;
+			interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					ccorr0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&color0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					ccorr0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&aal0_in>;
+					};
+				};
+			};
+		};
+
+		aal0: aal@14011000 {
+			compatible = "mediatek,mt8365-disp-aal", "mediatek,mt8183-disp-aal";
+			reg = <0 0x14011000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_AAL0>;
+			interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					aal0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&ccorr0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					aal0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&gamma0_in>;
+					};
+				};
+			};
+		};
+
+		gamma0: gamma@14012000 {
+			compatible = "mediatek,mt8365-disp-gamma", "mediatek,mt8183-disp-gamma";
+			reg = <0 0x14012000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_GAMMA0>;
+			interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					gamma0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&aal0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					gamma0_out: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&dither0_in>;
+					};
+				};
+			};
+		};
+
+		dither0: dither@14013000 {
+			compatible = "mediatek,mt8365-disp-dither", "mediatek,mt8183-disp-dither";
+			reg = <0 0x14013000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_DITHER0>;
+			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					dither0_in: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&gamma0_out>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					dither0_out: endpoint@0 {
+						reg = <0>;
+					};
+				};
+			};
+		};
+
+		dsi0: dsi@14014000 {
+			compatible = "mediatek,mt8365-dsi", "mediatek,mt8183-dsi";
+			reg = <0 0x14014000 0 0x1000>;
+			clock-names = "engine", "digital", "hs";
+			clocks = <&mmsys CLK_MM_MM_DSI0>,
+				 <&mmsys CLK_MM_DSI0_DIG_DSI>,
+				 <&mipi_tx0>;
+			interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_LOW>;
+			phy-names = "dphy";
+			phys = <&mipi_tx0>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+		};
+
+		rdma1: rdma@14016000 {
+			compatible = "mediatek,mt8365-disp-rdma", "mediatek,mt8183-disp-rdma";
+			reg = <0 0x14016000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_MM_DISP_RDMA1>;
+			interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_LOW>;
+			iommus = <&iommu M4U_PORT_DISP_RDMA1>;
+			mediatek,rdma-fifo-size = <2048>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					rdma1_in: endpoint@1 {
+						reg = <1>;
+						remote-endpoint = <&mmsys_ext>;
+					};
+				};
+
+				port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+					rdma1_out: endpoint@1 {
+						reg = <1>;
+					};
+				};
+			};
+		};
+
+		dpi0: dpi@14018000 {
+			compatible = "mediatek,mt8365-dpi", "mediatek,mt8192-dpi";
+			reg = <0 0x14018000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_DPI0_DPI0>,
+				 <&mmsys CLK_MM_MM_DPI0>,
+				 <&apmixedsys CLK_APMIXED_LVDSPLL>;
+			clock-names = "pixel", "engine", "pll";
+			interrupts = <GIC_SPI 197 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&spm MT8365_POWER_DOMAIN_MM>;
+			status = "disabled";
+		};
+
 		camsys: syscon@15000000 {
 			compatible = "mediatek,mt8365-imgsys", "syscon";
 			reg = <0 0x15000000 0 0x1000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8370-genio-510-evk.dts b/arch/arm64/boot/dts/mediatek/mt8370-genio-510-evk.dts
new file mode 100644
index 000000000000..71a8cbed1df6
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8370-genio-510-evk.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2025 Collabora Ltd.
+ * Author: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
+ */
+/dts-v1/;
+
+#include "mt8370.dtsi"
+#include "mt8390-genio-common.dtsi"
+
+/ {
+	model = "MediaTek Genio-510 EVK";
+	compatible = "mediatek,mt8370-evk", "mediatek,mt8370", "mediatek,mt8188";
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0x1 0x00000000>;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8370.dtsi b/arch/arm64/boot/dts/mediatek/mt8370.dtsi
new file mode 100644
index 000000000000..cf1a3759451f
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8370.dtsi
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2025 Collabora Ltd.
+ * Author: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
+ */
+
+/dts-v1/;
+#include "mt8188.dtsi"
+
+/ {
+	compatible = "mediatek,mt8370";
+
+	cpus {
+		/delete-node/ cpu@400;
+		/delete-node/ cpu@500;
+
+		cpu-map {
+			cluster0 {
+				/delete-node/ core4;
+				/delete-node/ core5;
+			};
+		};
+	};
+};
+
+&cpu6 {
+	clock-frequency = <2200000000>;
+};
+
+&cpu7 {
+	clock-frequency = <2200000000>;
+};
+
+&cpu_little0_cooling_map0 {
+	cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+};
+
+&cpu_little1_cooling_map0 {
+	cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+};
+
+&cpu_little2_cooling_map0 {
+	cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+};
+
+&cpu_little3_cooling_map0 {
+	cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+};
+
+&ppi_cluster0 {
+	affinity = <&cpu0 &cpu1 &cpu2 &cpu3>;
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts b/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts
index 04e4a2f73799..612336713a64 100644
--- a/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8390-genio-700-evk.dts
@@ -8,1047 +8,16 @@
 /dts-v1/;
 
 #include "mt8188.dtsi"
-#include "mt6359.dtsi"
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h>
-#include <dt-bindings/regulator/mediatek,mt6360-regulator.h>
-#include <dt-bindings/spmi/spmi.h>
-#include <dt-bindings/usb/pd.h>
+#include "mt8390-genio-common.dtsi"
 
 / {
 	model = "MediaTek Genio-700 EVK";
 	compatible = "mediatek,mt8390-evk", "mediatek,mt8390",
 		     "mediatek,mt8188";
 
-	aliases {
-		ethernet0 = &eth;
-		i2c0 = &i2c0;
-		i2c1 = &i2c1;
-		i2c2 = &i2c2;
-		i2c3 = &i2c3;
-		i2c4 = &i2c4;
-		i2c5 = &i2c5;
-		i2c6 = &i2c6;
-		mmc0 = &mmc0;
-		mmc1 = &mmc1;
-		serial0 = &uart0;
-	};
-
-	chosen {
-		stdout-path = "serial0:921600n8";
-	};
-
-	firmware {
-		optee {
-			compatible = "linaro,optee-tz";
-			method = "smc";
-		};
-	};
-
 	memory@40000000 {
 		device_type = "memory";
 		reg = <0 0x40000000 0x2 0x00000000>;
 	};
-
-	reserved-memory {
-		#address-cells = <2>;
-		#size-cells = <2>;
-		ranges;
-
-		/*
-		 * 12 MiB reserved for OP-TEE (BL32)
-		 * +-----------------------+ 0x43e0_0000
-		 * |      SHMEM 2MiB       |
-		 * +-----------------------+ 0x43c0_0000
-		 * |        | TA_RAM  8MiB |
-		 * + TZDRAM +--------------+ 0x4340_0000
-		 * |        | TEE_RAM 2MiB |
-		 * +-----------------------+ 0x4320_0000
-		 */
-		optee_reserved: optee@43200000 {
-			no-map;
-			reg = <0 0x43200000 0 0x00c00000>;
-		};
-
-		scp_mem: memory@50000000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x50000000 0 0x2900000>;
-			no-map;
-		};
-
-		/* 2 MiB reserved for ARM Trusted Firmware (BL31) */
-		bl31_secmon_reserved: memory@54600000 {
-			no-map;
-			reg = <0 0x54600000 0x0 0x200000>;
-		};
-
-		apu_mem: memory@55000000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x55000000 0 0x1400000>; /* 20 MB */
-		};
-
-		vpu_mem: memory@57000000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x57000000 0 0x1400000>; /* 20 MB */
-		};
-
-		adsp_mem: memory@60000000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x60000000 0 0xf00000>;
-			no-map;
-		};
-
-		afe_dma_mem: memory@60f00000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x60f00000 0 0x100000>;
-			no-map;
-		};
-
-		adsp_dma_mem: memory@61000000 {
-			compatible = "shared-dma-pool";
-			reg = <0 0x61000000 0 0x100000>;
-			no-map;
-		};
-	};
-
-	common_fixed_5v: regulator-0 {
-		compatible = "regulator-fixed";
-		regulator-name = "vdd_5v";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		gpio = <&pio 10 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		regulator-always-on;
-		vin-supply = <&reg_vsys>;
-	};
-
-	edp_panel_fixed_3v3: regulator-1 {
-		compatible = "regulator-fixed";
-		regulator-name = "vedp_3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		enable-active-high;
-		gpio = <&pio 15 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&edp_panel_3v3_en_pins>;
-		vin-supply = <&reg_vsys>;
-	};
-
-	gpio_fixed_3v3: regulator-2 {
-		compatible = "regulator-fixed";
-		regulator-name = "ext_3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&pio 9 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		regulator-always-on;
-		vin-supply = <&reg_vsys>;
-	};
-
-	/* system wide 4.2V power rail from charger */
-	reg_vsys: regulator-vsys {
-		compatible = "regulator-fixed";
-		regulator-name = "vsys";
-		regulator-always-on;
-		regulator-boot-on;
-	};
-
-	/* used by mmc2 */
-	sdio_fixed_1v8: regulator-3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vio18_conn";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-		enable-active-high;
-		regulator-always-on;
-	};
-
-	/* used by mmc2 */
-	sdio_fixed_3v3: regulator-4 {
-		compatible = "regulator-fixed";
-		regulator-name = "wifi_3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&pio 74 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		regulator-always-on;
-		vin-supply = <&reg_vsys>;
-	};
-
-	touch0_fixed_3v3: regulator-5 {
-		compatible = "regulator-fixed";
-		regulator-name = "vio33_tp1";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&pio 119 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		vin-supply = <&reg_vsys>;
-	};
-
-	usb_hub_fixed_3v3: regulator-6 {
-		compatible = "regulator-fixed";
-		regulator-name = "vhub_3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&pio 112 GPIO_ACTIVE_HIGH>; /* HUB_3V3_EN */
-		startup-delay-us = <10000>;
-		enable-active-high;
-		vin-supply = <&reg_vsys>;
-	};
-
-	usb_p0_vbus: regulator-7 {
-		compatible = "regulator-fixed";
-		regulator-name = "vbus_p0";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		gpio = <&pio 84 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		vin-supply = <&reg_vsys>;
-	};
-
-	usb_p1_vbus: regulator-8 {
-		compatible = "regulator-fixed";
-		regulator-name = "vbus_p1";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		gpio = <&pio 87 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		vin-supply = <&reg_vsys>;
-	};
-
-	/* used by ssusb2 */
-	usb_p2_vbus: regulator-9 {
-		compatible = "regulator-fixed";
-		regulator-name = "wifi_3v3";
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		enable-active-high;
-	};
-};
-
-&adsp {
-	memory-region = <&adsp_dma_mem>, <&adsp_mem>;
-	status = "okay";
-};
-
-&afe {
-	memory-region = <&afe_dma_mem>;
-	status = "okay";
-};
-
-&gpu {
-	mali-supply = <&mt6359_vproc2_buck_reg>;
-	status = "okay";
-};
-
-&i2c0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c0_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-
-	touchscreen@5d {
-		compatible = "goodix,gt9271";
-		reg = <0x5d>;
-		interrupt-parent = <&pio>;
-		interrupts-extended = <&pio 6 IRQ_TYPE_EDGE_RISING>;
-		irq-gpios = <&pio 6 GPIO_ACTIVE_HIGH>;
-		reset-gpios = <&pio 5 GPIO_ACTIVE_HIGH>;
-		AVDD28-supply = <&touch0_fixed_3v3>;
-		VDDIO-supply = <&mt6359_vio18_ldo_reg>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&touch_pins>;
-	};
-};
-
-&i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-};
-
-&i2c2 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c2_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-};
-
-&i2c3 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c3_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-};
-
-&i2c4 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c4_pins>;
-	clock-frequency = <1000000>;
-	status = "okay";
-};
-
-&i2c5 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c5_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-};
-
-&i2c6 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c6_pins>;
-	clock-frequency = <400000>;
-	status = "okay";
-};
-
-&mfg0 {
-	domain-supply = <&mt6359_vproc2_buck_reg>;
-};
-
-&mfg1 {
-	domain-supply = <&mt6359_vsram_others_ldo_reg>;
-};
-
-&mmc0 {
-	status = "okay";
-	pinctrl-names = "default", "state_uhs";
-	pinctrl-0 = <&mmc0_default_pins>;
-	pinctrl-1 = <&mmc0_uhs_pins>;
-	bus-width = <8>;
-	max-frequency = <200000000>;
-	cap-mmc-highspeed;
-	mmc-hs200-1_8v;
-	mmc-hs400-1_8v;
-	supports-cqe;
-	cap-mmc-hw-reset;
-	no-sdio;
-	no-sd;
-	hs400-ds-delay = <0x1481b>;
-	vmmc-supply = <&mt6359_vemc_1_ldo_reg>;
-	vqmmc-supply = <&mt6359_vufs_ldo_reg>;
-	non-removable;
-};
-
-&mmc1 {
-	status = "okay";
-	pinctrl-names = "default", "state_uhs";
-	pinctrl-0 = <&mmc1_default_pins>;
-	pinctrl-1 = <&mmc1_uhs_pins>;
-	bus-width = <4>;
-	max-frequency = <200000000>;
-	cap-sd-highspeed;
-	sd-uhs-sdr50;
-	sd-uhs-sdr104;
-	no-mmc;
-	no-sdio;
-	cd-gpios = <&pio 2 GPIO_ACTIVE_LOW>;
-	vmmc-supply = <&mt6359_vpa_buck_reg>;
-	vqmmc-supply = <&mt6359_vsim1_ldo_reg>;
-};
-
-&mt6359_vbbck_ldo_reg {
-	regulator-always-on;
-};
-
-&mt6359_vcn18_ldo_reg {
-	regulator-name = "vcn18_pmu";
-	regulator-always-on;
-};
-
-&mt6359_vcn33_2_bt_ldo_reg {
-	regulator-name = "vcn33_2_pmu";
-	regulator-always-on;
-};
-
-&mt6359_vcore_buck_reg {
-	regulator-name = "dvdd_proc_l";
-	regulator-always-on;
-};
-
-&mt6359_vgpu11_buck_reg {
-	regulator-name = "dvdd_core";
-	regulator-always-on;
-};
-
-&mt6359_vpa_buck_reg {
-	regulator-name = "vpa_pmu";
-	regulator-max-microvolt = <3100000>;
-};
-
-&mt6359_vproc2_buck_reg {
-	/* The name "vgpu" is required by mtk-regulator-coupler */
-	regulator-name = "vgpu";
-	regulator-min-microvolt = <550000>;
-	regulator-max-microvolt = <800000>;
-	regulator-coupled-with = <&mt6359_vsram_others_ldo_reg>;
-	regulator-coupled-max-spread = <6250>;
-};
-
-&mt6359_vpu_buck_reg {
-	regulator-name = "dvdd_adsp";
-	regulator-always-on;
-};
-
-&mt6359_vrf12_ldo_reg {
-	regulator-name = "va12_abb2_pmu";
-	regulator-always-on;
-};
-
-&mt6359_vsim1_ldo_reg {
-	regulator-name = "vsim1_pmu";
-	regulator-enable-ramp-delay = <480>;
-};
-
-&mt6359_vsram_others_ldo_reg {
-	/* The name "vsram_gpu" is required by mtk-regulator-coupler */
-	regulator-name = "vsram_gpu";
-	regulator-min-microvolt = <750000>;
-	regulator-max-microvolt = <800000>;
-	regulator-coupled-with = <&mt6359_vproc2_buck_reg>;
-	regulator-coupled-max-spread = <6250>;
-};
-
-&mt6359_vufs_ldo_reg {
-	regulator-name = "vufs18_pmu";
-	regulator-always-on;
-};
-
-&mt6359codec {
-	mediatek,mic-type-0 = <1>; /* ACC */
-	mediatek,mic-type-1 = <3>; /* DCC */
-};
-
-&pcie {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pcie_pins_default>;
-	status = "okay";
-};
-
-&pciephy {
-	status = "okay";
-};
-
-&pio {
-	audio_default_pins: audio-default-pins {
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO101__FUNC_O_AUD_CLK_MOSI>,
-				 <PINMUX_GPIO102__FUNC_O_AUD_SYNC_MOSI>,
-				 <PINMUX_GPIO103__FUNC_O_AUD_DAT_MOSI0>,
-				 <PINMUX_GPIO104__FUNC_O_AUD_DAT_MOSI1>,
-				 <PINMUX_GPIO105__FUNC_I0_AUD_DAT_MISO0>,
-				 <PINMUX_GPIO106__FUNC_I0_AUD_DAT_MISO1>,
-				 <PINMUX_GPIO107__FUNC_B0_I2SIN_MCK>,
-				 <PINMUX_GPIO108__FUNC_B0_I2SIN_BCK>,
-				 <PINMUX_GPIO109__FUNC_B0_I2SIN_WS>,
-				 <PINMUX_GPIO110__FUNC_I0_I2SIN_D0>,
-				 <PINMUX_GPIO114__FUNC_O_I2SO2_MCK>,
-				 <PINMUX_GPIO115__FUNC_B0_I2SO2_BCK>,
-				 <PINMUX_GPIO116__FUNC_B0_I2SO2_WS>,
-				 <PINMUX_GPIO117__FUNC_O_I2SO2_D0>,
-				 <PINMUX_GPIO118__FUNC_O_I2SO2_D1>,
-				 <PINMUX_GPIO121__FUNC_B0_PCM_CLK>,
-				 <PINMUX_GPIO122__FUNC_B0_PCM_SYNC>,
-				 <PINMUX_GPIO124__FUNC_I0_PCM_DI>,
-				 <PINMUX_GPIO125__FUNC_O_DMIC1_CLK>,
-				 <PINMUX_GPIO126__FUNC_I0_DMIC1_DAT>,
-				 <PINMUX_GPIO128__FUNC_O_DMIC2_CLK>,
-				 <PINMUX_GPIO129__FUNC_I0_DMIC2_DAT>;
-		};
-	};
-
-	dptx_pins: dptx-pins {
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO46__FUNC_I0_DP_TX_HPD>;
-			bias-pull-up;
-		};
-	};
-
-	edp_panel_3v3_en_pins: edp-panel-3v3-en-pins {
-		pins1 {
-			pinmux = <PINMUX_GPIO15__FUNC_B_GPIO15>;
-			output-high;
-		};
-	};
-
-	eth_default_pins: eth-default-pins {
-		pins-cc {
-			pinmux = <PINMUX_GPIO139__FUNC_B0_GBE_TXC>,
-				 <PINMUX_GPIO140__FUNC_I0_GBE_RXC>,
-				 <PINMUX_GPIO141__FUNC_I0_GBE_RXDV>,
-				 <PINMUX_GPIO142__FUNC_O_GBE_TXEN>;
-			drive-strength = <8>;
-		};
-
-		pins-mdio {
-			pinmux = <PINMUX_GPIO143__FUNC_O_GBE_MDC>,
-				 <PINMUX_GPIO144__FUNC_B1_GBE_MDIO>;
-			drive-strength = <8>;
-			input-enable;
-		};
-
-		pins-power {
-			pinmux = <PINMUX_GPIO145__FUNC_B_GPIO145>,
-				 <PINMUX_GPIO146__FUNC_B_GPIO146>;
-			output-high;
-		};
-
-		pins-rxd {
-			pinmux = <PINMUX_GPIO135__FUNC_I0_GBE_RXD3>,
-				 <PINMUX_GPIO136__FUNC_I0_GBE_RXD2>,
-				 <PINMUX_GPIO137__FUNC_I0_GBE_RXD1>,
-				 <PINMUX_GPIO138__FUNC_I0_GBE_RXD0>;
-			drive-strength = <8>;
-		};
-
-		pins-txd {
-			pinmux = <PINMUX_GPIO131__FUNC_O_GBE_TXD3>,
-				 <PINMUX_GPIO132__FUNC_O_GBE_TXD2>,
-				 <PINMUX_GPIO133__FUNC_O_GBE_TXD1>,
-				 <PINMUX_GPIO134__FUNC_O_GBE_TXD0>;
-			drive-strength = <8>;
-		};
-	};
-
-	eth_sleep_pins: eth-sleep-pins {
-		pins-cc {
-			pinmux = <PINMUX_GPIO139__FUNC_B_GPIO139>,
-				 <PINMUX_GPIO140__FUNC_B_GPIO140>,
-				 <PINMUX_GPIO141__FUNC_B_GPIO141>,
-				 <PINMUX_GPIO142__FUNC_B_GPIO142>;
-		};
-
-		pins-mdio {
-			pinmux = <PINMUX_GPIO143__FUNC_B_GPIO143>,
-				 <PINMUX_GPIO144__FUNC_B_GPIO144>;
-			input-disable;
-			bias-disable;
-		};
-
-		pins-rxd {
-			pinmux = <PINMUX_GPIO135__FUNC_B_GPIO135>,
-				 <PINMUX_GPIO136__FUNC_B_GPIO136>,
-				 <PINMUX_GPIO137__FUNC_B_GPIO137>,
-				 <PINMUX_GPIO138__FUNC_B_GPIO138>;
-		};
-
-		pins-txd {
-			pinmux = <PINMUX_GPIO131__FUNC_B_GPIO131>,
-				 <PINMUX_GPIO132__FUNC_B_GPIO132>,
-				 <PINMUX_GPIO133__FUNC_B_GPIO133>,
-				 <PINMUX_GPIO134__FUNC_B_GPIO134>;
-		};
-	};
-
-	i2c0_pins: i2c0-pins {
-		pins {
-			pinmux = <PINMUX_GPIO56__FUNC_B1_SDA0>,
-				 <PINMUX_GPIO55__FUNC_B1_SCL0>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c1_pins: i2c1-pins {
-		pins {
-			pinmux = <PINMUX_GPIO58__FUNC_B1_SDA1>,
-				 <PINMUX_GPIO57__FUNC_B1_SCL1>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c2_pins: i2c2-pins {
-		pins {
-			pinmux = <PINMUX_GPIO60__FUNC_B1_SDA2>,
-				 <PINMUX_GPIO59__FUNC_B1_SCL2>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c3_pins: i2c3-pins {
-		pins {
-			pinmux = <PINMUX_GPIO62__FUNC_B1_SDA3>,
-				 <PINMUX_GPIO61__FUNC_B1_SCL3>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c4_pins: i2c4-pins {
-		pins {
-			pinmux = <PINMUX_GPIO64__FUNC_B1_SDA4>,
-				 <PINMUX_GPIO63__FUNC_B1_SCL4>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c5_pins: i2c5-pins {
-		pins {
-			pinmux = <PINMUX_GPIO66__FUNC_B1_SDA5>,
-				 <PINMUX_GPIO65__FUNC_B1_SCL5>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	i2c6_pins: i2c6-pins {
-		pins {
-			pinmux = <PINMUX_GPIO68__FUNC_B1_SDA6>,
-				 <PINMUX_GPIO67__FUNC_B1_SCL6>;
-			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
-			drive-strength-microamp = <1000>;
-		};
-	};
-
-	gpio_key_pins: gpio-key-pins {
-		pins {
-			pinmux = <PINMUX_GPIO42__FUNC_B1_KPCOL0>,
-				 <PINMUX_GPIO43__FUNC_B1_KPCOL1>,
-				 <PINMUX_GPIO44__FUNC_B1_KPROW0>;
-		};
-	};
-
-	mmc0_default_pins: mmc0-default-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>;
-			drive-strength = <6>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
-				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
-				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
-				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
-				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
-				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
-				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
-				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
-				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-
-		pins-rst {
-			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	mmc0_uhs_pins: mmc0-uhs-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>;
-			drive-strength = <8>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
-				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
-				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
-				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
-				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
-				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
-				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
-				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
-				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
-			input-enable;
-			drive-strength = <8>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-
-		pins-ds {
-			pinmux = <PINMUX_GPIO162__FUNC_B0_MSDC0_DSL>;
-			drive-strength = <8>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-rst {
-			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
-			drive-strength = <8>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	mmc1_default_pins: mmc1-default-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO164__FUNC_B1_MSDC1_CLK>;
-			drive-strength = <6>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO163__FUNC_B1_MSDC1_CMD>,
-				 <PINMUX_GPIO165__FUNC_B1_MSDC1_DAT0>,
-				 <PINMUX_GPIO166__FUNC_B1_MSDC1_DAT1>,
-				 <PINMUX_GPIO167__FUNC_B1_MSDC1_DAT2>,
-				 <PINMUX_GPIO168__FUNC_B1_MSDC1_DAT3>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-
-		pins-insert {
-			pinmux = <PINMUX_GPIO2__FUNC_B_GPIO2>;
-			bias-pull-up;
-		};
-	};
-
-	mmc1_uhs_pins: mmc1-uhs-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO164__FUNC_B1_MSDC1_CLK>;
-			drive-strength = <6>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO163__FUNC_B1_MSDC1_CMD>,
-				 <PINMUX_GPIO165__FUNC_B1_MSDC1_DAT0>,
-				 <PINMUX_GPIO166__FUNC_B1_MSDC1_DAT1>,
-				 <PINMUX_GPIO167__FUNC_B1_MSDC1_DAT2>,
-				 <PINMUX_GPIO168__FUNC_B1_MSDC1_DAT3>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	mmc2_default_pins: mmc2-default-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO170__FUNC_B1_MSDC2_CLK>;
-			drive-strength = <4>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO169__FUNC_B1_MSDC2_CMD>,
-				 <PINMUX_GPIO171__FUNC_B1_MSDC2_DAT0>,
-				 <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>,
-				 <PINMUX_GPIO173__FUNC_B1_MSDC2_DAT2>,
-				 <PINMUX_GPIO174__FUNC_B1_MSDC2_DAT3>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-
-		pins-pcm {
-			pinmux = <PINMUX_GPIO123__FUNC_O_PCM_DO>;
-		};
-	};
-
-	mmc2_uhs_pins: mmc2-uhs-pins {
-		pins-clk {
-			pinmux = <PINMUX_GPIO170__FUNC_B1_MSDC2_CLK>;
-			drive-strength = <4>;
-			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
-		};
-
-		pins-cmd-dat {
-			pinmux = <PINMUX_GPIO169__FUNC_B1_MSDC2_CMD>,
-				 <PINMUX_GPIO171__FUNC_B1_MSDC2_DAT0>,
-				 <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>,
-				 <PINMUX_GPIO173__FUNC_B1_MSDC2_DAT2>,
-				 <PINMUX_GPIO174__FUNC_B1_MSDC2_DAT3>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	mmc2_eint_pins: mmc2-eint-pins {
-		pins-dat1 {
-			pinmux = <PINMUX_GPIO172__FUNC_B_GPIO172>;
-			input-enable;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	mmc2_dat1_pins: mmc2-dat1-pins {
-		pins-dat1 {
-			pinmux = <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>;
-			input-enable;
-			drive-strength = <6>;
-			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
-		};
-	};
-
-	panel_default_pins: panel-default-pins {
-		pins-dcdc {
-			pinmux = <PINMUX_GPIO45__FUNC_B_GPIO45>;
-			output-low;
-		};
-
-		pins-en {
-			pinmux = <PINMUX_GPIO111__FUNC_B_GPIO111>;
-			output-low;
-		};
-
-		pins-rst {
-			pinmux = <PINMUX_GPIO25__FUNC_B_GPIO25>;
-			output-high;
-		};
-	};
-
-	pcie_pins_default: pcie-default {
-		mux {
-			pinmux = <PINMUX_GPIO47__FUNC_I1_WAKEN>,
-				 <PINMUX_GPIO48__FUNC_O_PERSTN>,
-				 <PINMUX_GPIO49__FUNC_B1_CLKREQN>;
-			bias-pull-up;
-		};
-	};
-
-	rt1715_int_pins: rt1715-int-pins {
-		pins_cmd0_dat {
-			pinmux = <PINMUX_GPIO12__FUNC_B_GPIO12>;
-			bias-pull-up;
-			input-enable;
-		};
-	};
-
-	spi0_pins: spi0-pins {
-		pins-spi {
-			pinmux = <PINMUX_GPIO69__FUNC_O_SPIM0_CSB>,
-				<PINMUX_GPIO70__FUNC_O_SPIM0_CLK>,
-				<PINMUX_GPIO71__FUNC_B0_SPIM0_MOSI>,
-				<PINMUX_GPIO72__FUNC_B0_SPIM0_MISO>;
-			bias-disable;
-		};
-	};
-
-	spi1_pins: spi1-pins {
-		pins-spi {
-			pinmux = <PINMUX_GPIO75__FUNC_O_SPIM1_CSB>,
-				<PINMUX_GPIO76__FUNC_O_SPIM1_CLK>,
-				<PINMUX_GPIO77__FUNC_B0_SPIM1_MOSI>,
-				<PINMUX_GPIO78__FUNC_B0_SPIM1_MISO>;
-			bias-disable;
-		};
-	};
-
-	spi2_pins: spi2-pins {
-		pins-spi {
-			pinmux = <PINMUX_GPIO79__FUNC_O_SPIM2_CSB>,
-				<PINMUX_GPIO80__FUNC_O_SPIM2_CLK>,
-				<PINMUX_GPIO81__FUNC_B0_SPIM2_MOSI>,
-				<PINMUX_GPIO82__FUNC_B0_SPIM2_MISO>;
-			bias-disable;
-		};
-	};
-
-	touch_pins: touch-pins {
-		pins-irq {
-			pinmux = <PINMUX_GPIO6__FUNC_B_GPIO6>;
-			input-enable;
-			bias-disable;
-		};
-
-		pins-reset {
-			pinmux = <PINMUX_GPIO5__FUNC_B_GPIO5>;
-			output-high;
-		};
-	};
-
-	uart0_pins: uart0-pins {
-		pins {
-			pinmux = <PINMUX_GPIO31__FUNC_O_UTXD0>,
-				 <PINMUX_GPIO32__FUNC_I1_URXD0>;
-			bias-pull-up;
-		};
-	};
-
-	uart1_pins: uart1-pins {
-		pins {
-			pinmux = <PINMUX_GPIO33__FUNC_O_UTXD1>,
-				 <PINMUX_GPIO34__FUNC_I1_URXD1>;
-			bias-pull-up;
-		};
-	};
-
-	uart2_pins: uart2-pins {
-		pins {
-			pinmux = <PINMUX_GPIO35__FUNC_O_UTXD2>,
-				 <PINMUX_GPIO36__FUNC_I1_URXD2>;
-			bias-pull-up;
-		};
-	};
-
-	usb_default_pins: usb-default-pins {
-		pins-iddig {
-			pinmux = <PINMUX_GPIO83__FUNC_B_GPIO83>;
-			input-enable;
-			bias-pull-up;
-		};
-
-		pins-valid {
-			pinmux = <PINMUX_GPIO85__FUNC_I0_VBUSVALID>;
-			input-enable;
-		};
-
-		pins-vbus {
-			pinmux = <PINMUX_GPIO84__FUNC_O_USB_DRVVBUS>;
-			output-high;
-		};
-
-	};
-
-	usb1_default_pins: usb1-default-pins {
-		pins-valid {
-			pinmux = <PINMUX_GPIO88__FUNC_I0_VBUSVALID_1P>;
-			input-enable;
-		};
-
-		pins-usb-hub-3v3-en {
-			pinmux = <PINMUX_GPIO112__FUNC_B_GPIO112>;
-			output-high;
-		};
-	};
-
-	wifi_pwrseq_pins: wifi-pwrseq-pins {
-		pins-wifi-enable {
-			pinmux = <PINMUX_GPIO127__FUNC_B_GPIO127>;
-			output-low;
-		};
-	};
-};
-
-&eth {
-	phy-mode ="rgmii-id";
-	phy-handle = <&ethernet_phy0>;
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&eth_default_pins>;
-	pinctrl-1 = <&eth_sleep_pins>;
-	mediatek,mac-wol;
-	snps,reset-gpio = <&pio 147 GPIO_ACTIVE_HIGH>;
-	snps,reset-delays-us = <0 10000 10000>;
-	status = "okay";
-};
-
-&eth_mdio {
-	ethernet_phy0: ethernet-phy@1 {
-		compatible = "ethernet-phy-id001c.c916";
-		reg = <0x1>;
-	};
-};
-
-&pmic {
-	interrupt-parent = <&pio>;
-	interrupts = <222 IRQ_TYPE_LEVEL_HIGH>;
-
-	mt6359keys: keys {
-		compatible = "mediatek,mt6359-keys";
-		mediatek,long-press-mode = <1>;
-		power-off-time-sec = <0>;
-
-		power-key {
-			linux,keycodes = <KEY_POWER>;
-			wakeup-source;
-		};
-	};
-};
-
-&scp {
-	memory-region = <&scp_mem>;
-	status = "okay";
-};
-
-&sound {
-	compatible = "mediatek,mt8390-mt6359-evk", "mediatek,mt8188-mt6359-evb";
-	model = "mt8390-evk";
-	pinctrl-names = "default";
-	pinctrl-0 = <&audio_default_pins>;
-	audio-routing =
-		"Headphone", "Headphone L",
-		"Headphone", "Headphone R";
-	mediatek,adsp = <&adsp>;
-	status = "okay";
-
-	dai-link-0 {
-		link-name = "DL_SRC_BE";
-
-		codec {
-			sound-dai = <&pmic 0>;
-		};
-	};
-};
-
-&spi2 {
-	pinctrl-0 = <&spi2_pins>;
-	pinctrl-names = "default";
-	mediatek,pad-select = <0>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-	status = "okay";
 };
 
-&uart0 {
-	pinctrl-0 = <&uart0_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&uart1 {
-	pinctrl-0 = <&uart1_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&uart2 {
-	pinctrl-0 = <&uart2_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&u3phy0 {
-	status = "okay";
-};
-
-&u3phy1 {
-	status = "okay";
-};
-
-&u3phy2 {
-	status = "okay";
-};
-
-&xhci0 {
-	status = "okay";
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
-};
-
-&xhci1 {
-	status = "okay";
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-
-	hub_2_0: hub@1 {
-		compatible = "usb451,8025";
-		reg = <1>;
-		peer-hub = <&hub_3_0>;
-		reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
-		vdd-supply = <&usb_hub_fixed_3v3>;
-	};
-
-	hub_3_0: hub@2 {
-		compatible = "usb451,8027";
-		reg = <2>;
-		peer-hub = <&hub_2_0>;
-		reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
-		vdd-supply = <&usb_hub_fixed_3v3>;
-	};
-};
-
-&xhci2 {
-	status = "okay";
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
-	vbus-supply = <&sdio_fixed_3v3>; /* wifi_3v3 */
-};
diff --git a/arch/arm64/boot/dts/mediatek/mt8390-genio-common.dtsi b/arch/arm64/boot/dts/mediatek/mt8390-genio-common.dtsi
new file mode 100644
index 000000000000..60139e6dffd8
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8390-genio-common.dtsi
@@ -0,0 +1,1223 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 MediaTek Inc.
+ * Author: Chris Chen <chris-qj.chen@mediatek.com>
+ *         Pablo Sun <pablo.sun@mediatek.com>
+ *         Macpaul Lin <macpaul.lin@mediatek.com>
+ *
+ * Copyright (C) 2025 Collabora Ltd.
+ *                    Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
+ *                    AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>   
+ */
+
+#include "mt6359.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h>
+#include <dt-bindings/regulator/mediatek,mt6360-regulator.h>
+#include <dt-bindings/spmi/spmi.h>
+#include <dt-bindings/usb/pd.h>
+
+/ {
+	aliases {
+		ethernet0 = &eth;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
+		mmc0 = &mmc0;
+		mmc1 = &mmc1;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:921600n8";
+	};
+
+	dmic_codec: dmic-codec {
+		#sound-dai-cells = <0>;
+		compatible = "dmic-codec";
+		num-channels = <2>;
+		wakeup-delay-ms = <30>;
+	};
+
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+	};
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/*
+		 * 12 MiB reserved for OP-TEE (BL32)
+		 * +-----------------------+ 0x43e0_0000
+		 * |      SHMEM 2MiB       |
+		 * +-----------------------+ 0x43c0_0000
+		 * |        | TA_RAM  8MiB |
+		 * + TZDRAM +--------------+ 0x4340_0000
+		 * |        | TEE_RAM 2MiB |
+		 * +-----------------------+ 0x4320_0000
+		 */
+		optee_reserved: optee@43200000 {
+			no-map;
+			reg = <0 0x43200000 0 0x00c00000>;
+		};
+
+		scp_mem: memory@50000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x50000000 0 0x2900000>;
+			no-map;
+		};
+
+		/* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+		bl31_secmon_reserved: memory@54600000 {
+			no-map;
+			reg = <0 0x54600000 0x0 0x200000>;
+		};
+
+		apu_mem: memory@55000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x55000000 0 0x1400000>; /* 20 MB */
+		};
+
+		vpu_mem: memory@57000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x57000000 0 0x1400000>; /* 20 MB */
+		};
+
+		adsp_mem: memory@60000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x60000000 0 0xf00000>;
+			no-map;
+		};
+
+		afe_dma_mem: memory@60f00000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x60f00000 0 0x100000>;
+			no-map;
+		};
+
+		adsp_dma_mem: memory@61000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x61000000 0 0x100000>;
+			no-map;
+		};
+	};
+
+	common_fixed_5v: regulator-0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&pio 10 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+		vin-supply = <&reg_vsys>;
+	};
+
+	edp_panel_fixed_3v3: regulator-1 {
+		compatible = "regulator-fixed";
+		regulator-name = "vedp_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		enable-active-high;
+		gpio = <&pio 15 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&edp_panel_3v3_en_pins>;
+		vin-supply = <&reg_vsys>;
+	};
+
+	gpio_fixed_3v3: regulator-2 {
+		compatible = "regulator-fixed";
+		regulator-name = "ext_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pio 9 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+		vin-supply = <&reg_vsys>;
+	};
+
+	/* system wide 4.2V power rail from charger */
+	reg_vsys: regulator-vsys {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	/* used by mmc2 */
+	sdio_fixed_1v8: regulator-3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vio18_conn";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	/* used by mmc2 */
+	sdio_fixed_3v3: regulator-4 {
+		compatible = "regulator-fixed";
+		regulator-name = "wifi_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pio 74 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+		vin-supply = <&reg_vsys>;
+	};
+
+	touch0_fixed_3v3: regulator-5 {
+		compatible = "regulator-fixed";
+		regulator-name = "vio33_tp1";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pio 119 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_vsys>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touch_vreg_pins>;
+	};
+
+	usb_hub_fixed_3v3: regulator-6 {
+		compatible = "regulator-fixed";
+		regulator-name = "vhub_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pio 112 GPIO_ACTIVE_HIGH>; /* HUB_3V3_EN */
+		startup-delay-us = <10000>;
+		enable-active-high;
+		vin-supply = <&reg_vsys>;
+	};
+
+	usb_p0_vbus: regulator-7 {
+		compatible = "regulator-fixed";
+		regulator-name = "vbus_p0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&pio 84 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_vsys>;
+	};
+
+	usb_p1_vbus: regulator-8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vbus_p1";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&pio 87 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_vsys>;
+	};
+
+	/* used by ssusb2 */
+	usb_p2_vbus: regulator-9 {
+		compatible = "regulator-fixed";
+		regulator-name = "vbus_p2";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		enable-active-high;
+	};
+};
+
+&adsp {
+	memory-region = <&adsp_dma_mem>, <&adsp_mem>;
+	status = "okay";
+};
+
+&afe {
+	memory-region = <&afe_dma_mem>;
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&mt6359_vproc2_buck_reg>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	touchscreen@5d {
+		compatible = "goodix,gt9271";
+		reg = <0x5d>;
+		interrupt-parent = <&pio>;
+		interrupts-extended = <&pio 6 IRQ_TYPE_EDGE_RISING>;
+		irq-gpios = <&pio 6 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&pio 5 GPIO_ACTIVE_HIGH>;
+		AVDD28-supply = <&touch0_fixed_3v3>;
+		VDDIO-supply = <&mt6359_vio18_ldo_reg>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touch_pins>;
+	};
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	typec-mux@48 {
+		compatible = "ite,it5205";
+		reg = <0x48>;
+
+		mode-switch;
+		orientation-switch;
+
+		vcc-supply = <&mt6359_vcn33_1_bt_ldo_reg>;
+
+		port {
+			it5205_sbu_mux: endpoint {
+				remote-endpoint = <&typec_sbu_out>;
+			};
+		};
+	};
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_pins>;
+	clock-frequency = <1000000>;
+	status = "okay";
+
+	rt1715@4e {
+		compatible = "richtek,rt1715";
+		reg = <0x4e>;
+		interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&tcpci_int_pins>;
+		vbus-supply = <&usb_p1_vbus>;
+
+		connector {
+			compatible = "usb-c-connector";
+			label = "USB-C";
+			data-role = "dual";
+			op-sink-microwatt = <10000000>;
+			power-role = "dual";
+			try-power-role  = "sink";
+			pd-revision = /bits/ 8 <0x03 0x00 0x01 0x08>;
+
+			sink-pdos = <PDO_FIXED(5000, 2000,
+					       PDO_FIXED_DUAL_ROLE |
+					       PDO_FIXED_DATA_SWAP)>;
+			source-pdos = <PDO_FIXED(5000, 2000,
+						 PDO_FIXED_DUAL_ROLE |
+						 PDO_FIXED_DATA_SWAP)>;
+
+			altmodes {
+				displayport {
+					svid = /bits/ 16 <0xff01>;
+					vdo = <0x001c1c47>;
+				};
+			};
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					typec_con_hs: endpoint {
+						remote-endpoint = <&mtu3_hs1_role_sw>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					typec_con_ss: endpoint {
+						remote-endpoint = <&xhci_ss_ep>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+					typec_sbu_out: endpoint {
+						remote-endpoint = <&it5205_sbu_mux>;
+					};
+
+				};
+			};
+		};
+	};
+};
+
+&i2c5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&i2c6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+};
+
+&mfg0 {
+	domain-supply = <&mt6359_vproc2_buck_reg>;
+};
+
+&mfg1 {
+	domain-supply = <&mt6359_vsram_others_ldo_reg>;
+};
+
+&mmc0 {
+	status = "okay";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_default_pins>;
+	pinctrl-1 = <&mmc0_uhs_pins>;
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	cap-mmc-highspeed;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	supports-cqe;
+	cap-mmc-hw-reset;
+	no-sdio;
+	no-sd;
+	hs400-ds-delay = <0x1481b>;
+	vmmc-supply = <&mt6359_vemc_1_ldo_reg>;
+	vqmmc-supply = <&mt6359_vufs_ldo_reg>;
+	non-removable;
+};
+
+&mmc1 {
+	status = "okay";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc1_default_pins>;
+	pinctrl-1 = <&mmc1_uhs_pins>;
+	bus-width = <4>;
+	max-frequency = <200000000>;
+	cap-sd-highspeed;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	no-mmc;
+	no-sdio;
+	cd-gpios = <&pio 2 GPIO_ACTIVE_LOW>;
+	vmmc-supply = <&mt6359_vpa_buck_reg>;
+	vqmmc-supply = <&mt6359_vsim1_ldo_reg>;
+};
+
+&mt6359_vbbck_ldo_reg {
+	regulator-always-on;
+};
+
+&mt6359_vcn18_ldo_reg {
+	regulator-name = "vcn18_pmu";
+	regulator-always-on;
+};
+
+&mt6359_vcn33_2_bt_ldo_reg {
+	regulator-name = "vcn33_2_pmu";
+	regulator-always-on;
+};
+
+&mt6359_vcore_buck_reg {
+	regulator-name = "dvdd_proc_l";
+	regulator-always-on;
+};
+
+&mt6359_vgpu11_buck_reg {
+	regulator-name = "dvdd_core";
+	regulator-always-on;
+};
+
+&mt6359_vpa_buck_reg {
+	regulator-name = "vpa_pmu";
+	regulator-max-microvolt = <3100000>;
+};
+
+&mt6359_vproc2_buck_reg {
+	/* The name "vgpu" is required by mtk-regulator-coupler */
+	regulator-name = "vgpu";
+	regulator-min-microvolt = <550000>;
+	regulator-max-microvolt = <800000>;
+	regulator-coupled-with = <&mt6359_vsram_others_ldo_reg>;
+	regulator-coupled-max-spread = <6250>;
+};
+
+&mt6359_vpu_buck_reg {
+	regulator-name = "dvdd_adsp";
+	regulator-always-on;
+};
+
+&mt6359_vrf12_ldo_reg {
+	regulator-name = "va12_abb2_pmu";
+	regulator-always-on;
+};
+
+&mt6359_vsim1_ldo_reg {
+	regulator-name = "vsim1_pmu";
+	regulator-enable-ramp-delay = <480>;
+};
+
+&mt6359_vsram_others_ldo_reg {
+	/* The name "vsram_gpu" is required by mtk-regulator-coupler */
+	regulator-name = "vsram_gpu";
+	regulator-min-microvolt = <750000>;
+	regulator-max-microvolt = <800000>;
+	regulator-coupled-with = <&mt6359_vproc2_buck_reg>;
+	regulator-coupled-max-spread = <6250>;
+};
+
+&mt6359_vufs_ldo_reg {
+	regulator-name = "vufs18_pmu";
+	regulator-always-on;
+};
+
+&mt6359codec {
+	mediatek,mic-type-0 = <1>; /* ACC */
+	mediatek,mic-type-1 = <3>; /* DCC */
+};
+
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie_pins_default>;
+	status = "okay";
+};
+
+&pciephy {
+	status = "okay";
+};
+
+&pio {
+	audio_default_pins: audio-default-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO101__FUNC_O_AUD_CLK_MOSI>,
+				 <PINMUX_GPIO102__FUNC_O_AUD_SYNC_MOSI>,
+				 <PINMUX_GPIO103__FUNC_O_AUD_DAT_MOSI0>,
+				 <PINMUX_GPIO104__FUNC_O_AUD_DAT_MOSI1>,
+				 <PINMUX_GPIO105__FUNC_I0_AUD_DAT_MISO0>,
+				 <PINMUX_GPIO106__FUNC_I0_AUD_DAT_MISO1>,
+				 <PINMUX_GPIO107__FUNC_B0_I2SIN_MCK>,
+				 <PINMUX_GPIO108__FUNC_B0_I2SIN_BCK>,
+				 <PINMUX_GPIO109__FUNC_B0_I2SIN_WS>,
+				 <PINMUX_GPIO110__FUNC_I0_I2SIN_D0>,
+				 <PINMUX_GPIO114__FUNC_O_I2SO2_MCK>,
+				 <PINMUX_GPIO115__FUNC_B0_I2SO2_BCK>,
+				 <PINMUX_GPIO116__FUNC_B0_I2SO2_WS>,
+				 <PINMUX_GPIO117__FUNC_O_I2SO2_D0>,
+				 <PINMUX_GPIO118__FUNC_O_I2SO2_D1>,
+				 <PINMUX_GPIO121__FUNC_B0_PCM_CLK>,
+				 <PINMUX_GPIO122__FUNC_B0_PCM_SYNC>,
+				 <PINMUX_GPIO124__FUNC_I0_PCM_DI>,
+				 <PINMUX_GPIO125__FUNC_O_DMIC1_CLK>,
+				 <PINMUX_GPIO126__FUNC_I0_DMIC1_DAT>,
+				 <PINMUX_GPIO128__FUNC_O_DMIC2_CLK>,
+				 <PINMUX_GPIO129__FUNC_I0_DMIC2_DAT>;
+		};
+	};
+
+	dptx_pins: dptx-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO46__FUNC_I0_DP_TX_HPD>;
+			bias-pull-up;
+		};
+	};
+
+	edp_panel_3v3_en_pins: edp-panel-3v3-en-pins {
+		pins1 {
+			pinmux = <PINMUX_GPIO15__FUNC_B_GPIO15>;
+			output-high;
+		};
+	};
+
+	eth_default_pins: eth-default-pins {
+		pins-cc {
+			pinmux = <PINMUX_GPIO139__FUNC_B0_GBE_TXC>,
+				 <PINMUX_GPIO140__FUNC_I0_GBE_RXC>,
+				 <PINMUX_GPIO141__FUNC_I0_GBE_RXDV>,
+				 <PINMUX_GPIO142__FUNC_O_GBE_TXEN>;
+			drive-strength = <8>;
+		};
+
+		pins-mdio {
+			pinmux = <PINMUX_GPIO143__FUNC_O_GBE_MDC>,
+				 <PINMUX_GPIO144__FUNC_B1_GBE_MDIO>;
+			drive-strength = <8>;
+			input-enable;
+		};
+
+		pins-power {
+			pinmux = <PINMUX_GPIO145__FUNC_B_GPIO145>,
+				 <PINMUX_GPIO146__FUNC_B_GPIO146>;
+			output-high;
+		};
+
+		pins-rxd {
+			pinmux = <PINMUX_GPIO135__FUNC_I0_GBE_RXD3>,
+				 <PINMUX_GPIO136__FUNC_I0_GBE_RXD2>,
+				 <PINMUX_GPIO137__FUNC_I0_GBE_RXD1>,
+				 <PINMUX_GPIO138__FUNC_I0_GBE_RXD0>;
+			drive-strength = <8>;
+		};
+
+		pins-txd {
+			pinmux = <PINMUX_GPIO131__FUNC_O_GBE_TXD3>,
+				 <PINMUX_GPIO132__FUNC_O_GBE_TXD2>,
+				 <PINMUX_GPIO133__FUNC_O_GBE_TXD1>,
+				 <PINMUX_GPIO134__FUNC_O_GBE_TXD0>;
+			drive-strength = <8>;
+		};
+	};
+
+	eth_sleep_pins: eth-sleep-pins {
+		pins-cc {
+			pinmux = <PINMUX_GPIO139__FUNC_B_GPIO139>,
+				 <PINMUX_GPIO140__FUNC_B_GPIO140>,
+				 <PINMUX_GPIO141__FUNC_B_GPIO141>,
+				 <PINMUX_GPIO142__FUNC_B_GPIO142>;
+		};
+
+		pins-mdio {
+			pinmux = <PINMUX_GPIO143__FUNC_B_GPIO143>,
+				 <PINMUX_GPIO144__FUNC_B_GPIO144>;
+			input-disable;
+			bias-disable;
+		};
+
+		pins-rxd {
+			pinmux = <PINMUX_GPIO135__FUNC_B_GPIO135>,
+				 <PINMUX_GPIO136__FUNC_B_GPIO136>,
+				 <PINMUX_GPIO137__FUNC_B_GPIO137>,
+				 <PINMUX_GPIO138__FUNC_B_GPIO138>;
+		};
+
+		pins-txd {
+			pinmux = <PINMUX_GPIO131__FUNC_B_GPIO131>,
+				 <PINMUX_GPIO132__FUNC_B_GPIO132>,
+				 <PINMUX_GPIO133__FUNC_B_GPIO133>,
+				 <PINMUX_GPIO134__FUNC_B_GPIO134>;
+		};
+	};
+
+	i2c0_pins: i2c0-pins {
+		pins {
+			pinmux = <PINMUX_GPIO56__FUNC_B1_SDA0>,
+				 <PINMUX_GPIO55__FUNC_B1_SCL0>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c1_pins: i2c1-pins {
+		pins {
+			pinmux = <PINMUX_GPIO58__FUNC_B1_SDA1>,
+				 <PINMUX_GPIO57__FUNC_B1_SCL1>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		pins {
+			pinmux = <PINMUX_GPIO60__FUNC_B1_SDA2>,
+				 <PINMUX_GPIO59__FUNC_B1_SCL2>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c3_pins: i2c3-pins {
+		pins {
+			pinmux = <PINMUX_GPIO62__FUNC_B1_SDA3>,
+				 <PINMUX_GPIO61__FUNC_B1_SCL3>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c4_pins: i2c4-pins {
+		pins {
+			pinmux = <PINMUX_GPIO64__FUNC_B1_SDA4>,
+				 <PINMUX_GPIO63__FUNC_B1_SCL4>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c5_pins: i2c5-pins {
+		pins {
+			pinmux = <PINMUX_GPIO66__FUNC_B1_SDA5>,
+				 <PINMUX_GPIO65__FUNC_B1_SCL5>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c6_pins: i2c6-pins {
+		pins {
+			pinmux = <PINMUX_GPIO68__FUNC_B1_SDA6>,
+				 <PINMUX_GPIO67__FUNC_B1_SCL6>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_011>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	gpio_key_pins: gpio-key-pins {
+		pins {
+			pinmux = <PINMUX_GPIO42__FUNC_B1_KPCOL0>,
+				 <PINMUX_GPIO43__FUNC_B1_KPCOL1>,
+				 <PINMUX_GPIO44__FUNC_B1_KPROW0>;
+		};
+	};
+
+	mmc0_default_pins: mmc0-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
+				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
+				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
+				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
+				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
+				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
+				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
+				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
+				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc0_uhs_pins: mmc0-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO157__FUNC_B1_MSDC0_CLK>;
+			drive-strength = <8>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0>,
+				 <PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1>,
+				 <PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2>,
+				 <PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3>,
+				 <PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4>,
+				 <PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5>,
+				 <PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6>,
+				 <PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7>,
+				 <PINMUX_GPIO156__FUNC_B1_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <8>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-ds {
+			pinmux = <PINMUX_GPIO162__FUNC_B0_MSDC0_DSL>;
+			drive-strength = <8>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO155__FUNC_O_MSDC0_RSTB>;
+			drive-strength = <8>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc1_default_pins: mmc1-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO164__FUNC_B1_MSDC1_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO163__FUNC_B1_MSDC1_CMD>,
+				 <PINMUX_GPIO165__FUNC_B1_MSDC1_DAT0>,
+				 <PINMUX_GPIO166__FUNC_B1_MSDC1_DAT1>,
+				 <PINMUX_GPIO167__FUNC_B1_MSDC1_DAT2>,
+				 <PINMUX_GPIO168__FUNC_B1_MSDC1_DAT3>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-insert {
+			pinmux = <PINMUX_GPIO2__FUNC_B_GPIO2>;
+			bias-pull-up;
+		};
+	};
+
+	mmc1_uhs_pins: mmc1-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO164__FUNC_B1_MSDC1_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO163__FUNC_B1_MSDC1_CMD>,
+				 <PINMUX_GPIO165__FUNC_B1_MSDC1_DAT0>,
+				 <PINMUX_GPIO166__FUNC_B1_MSDC1_DAT1>,
+				 <PINMUX_GPIO167__FUNC_B1_MSDC1_DAT2>,
+				 <PINMUX_GPIO168__FUNC_B1_MSDC1_DAT3>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc2_default_pins: mmc2-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO170__FUNC_B1_MSDC2_CLK>;
+			drive-strength = <4>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO169__FUNC_B1_MSDC2_CMD>,
+				 <PINMUX_GPIO171__FUNC_B1_MSDC2_DAT0>,
+				 <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>,
+				 <PINMUX_GPIO173__FUNC_B1_MSDC2_DAT2>,
+				 <PINMUX_GPIO174__FUNC_B1_MSDC2_DAT3>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-pcm {
+			pinmux = <PINMUX_GPIO123__FUNC_O_PCM_DO>;
+		};
+	};
+
+	mmc2_uhs_pins: mmc2-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO170__FUNC_B1_MSDC2_CLK>;
+			drive-strength = <4>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO169__FUNC_B1_MSDC2_CMD>,
+				 <PINMUX_GPIO171__FUNC_B1_MSDC2_DAT0>,
+				 <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>,
+				 <PINMUX_GPIO173__FUNC_B1_MSDC2_DAT2>,
+				 <PINMUX_GPIO174__FUNC_B1_MSDC2_DAT3>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc2_eint_pins: mmc2-eint-pins {
+		pins-dat1 {
+			pinmux = <PINMUX_GPIO172__FUNC_B_GPIO172>;
+			input-enable;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc2_dat1_pins: mmc2-dat1-pins {
+		pins-dat1 {
+			pinmux = <PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	panel_default_pins: panel-default-pins {
+		pins-dcdc {
+			pinmux = <PINMUX_GPIO45__FUNC_B_GPIO45>;
+			output-low;
+		};
+
+		pins-en {
+			pinmux = <PINMUX_GPIO111__FUNC_B_GPIO111>;
+			output-low;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO25__FUNC_B_GPIO25>;
+			output-high;
+		};
+	};
+
+	pcie_pins_default: pcie-default {
+		mux {
+			pinmux = <PINMUX_GPIO47__FUNC_I1_WAKEN>,
+				 <PINMUX_GPIO48__FUNC_O_PERSTN>,
+				 <PINMUX_GPIO49__FUNC_B1_CLKREQN>;
+			bias-pull-up;
+		};
+	};
+
+	rt1715_int_pins: rt1715-int-pins {
+		pins_cmd0_dat {
+			pinmux = <PINMUX_GPIO12__FUNC_B_GPIO12>;
+			bias-pull-up;
+			input-enable;
+		};
+	};
+
+	spi0_pins: spi0-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO69__FUNC_O_SPIM0_CSB>,
+				<PINMUX_GPIO70__FUNC_O_SPIM0_CLK>,
+				<PINMUX_GPIO71__FUNC_B0_SPIM0_MOSI>,
+				<PINMUX_GPIO72__FUNC_B0_SPIM0_MISO>;
+			bias-disable;
+		};
+	};
+
+	spi1_pins: spi1-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO75__FUNC_O_SPIM1_CSB>,
+				<PINMUX_GPIO76__FUNC_O_SPIM1_CLK>,
+				<PINMUX_GPIO77__FUNC_B0_SPIM1_MOSI>,
+				<PINMUX_GPIO78__FUNC_B0_SPIM1_MISO>;
+			bias-disable;
+		};
+	};
+
+	spi2_pins: spi2-pins {
+		pins-spi {
+			pinmux = <PINMUX_GPIO79__FUNC_O_SPIM2_CSB>,
+				<PINMUX_GPIO80__FUNC_O_SPIM2_CLK>,
+				<PINMUX_GPIO81__FUNC_B0_SPIM2_MOSI>,
+				<PINMUX_GPIO82__FUNC_B0_SPIM2_MISO>;
+			bias-disable;
+		};
+	};
+
+	touch_vreg_pins: touch-avdd-pins {
+		pins-power {
+			pinmux = <PINMUX_GPIO120__FUNC_B_GPIO120>;
+			output-high;
+		};
+	};
+
+	touch_pins: touch-pins {
+		pins-irq {
+			pinmux = <PINMUX_GPIO6__FUNC_B_GPIO6>;
+			input-enable;
+			bias-disable;
+		};
+
+		pins-reset {
+			pinmux = <PINMUX_GPIO5__FUNC_B_GPIO5>;
+			output-high;
+		};
+	};
+
+	tcpci_int_pins: tcpci-int-pins {
+		pins-int-n {
+			pinmux = <PINMUX_GPIO12__FUNC_B_GPIO12>;
+			bias-pull-up;
+			input-enable;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		pins {
+			pinmux = <PINMUX_GPIO31__FUNC_O_UTXD0>,
+				 <PINMUX_GPIO32__FUNC_I1_URXD0>;
+			bias-pull-up;
+		};
+	};
+
+	uart1_pins: uart1-pins {
+		pins {
+			pinmux = <PINMUX_GPIO33__FUNC_O_UTXD1>,
+				 <PINMUX_GPIO34__FUNC_I1_URXD1>;
+			bias-pull-up;
+		};
+	};
+
+	uart2_pins: uart2-pins {
+		pins {
+			pinmux = <PINMUX_GPIO35__FUNC_O_UTXD2>,
+				 <PINMUX_GPIO36__FUNC_I1_URXD2>;
+			bias-pull-up;
+		};
+	};
+
+	usb_default_pins: usb-default-pins {
+		pins-iddig {
+			pinmux = <PINMUX_GPIO83__FUNC_B_GPIO83>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pins-valid {
+			pinmux = <PINMUX_GPIO85__FUNC_I0_VBUSVALID>;
+			input-enable;
+		};
+
+		pins-vbus {
+			pinmux = <PINMUX_GPIO84__FUNC_O_USB_DRVVBUS>;
+			output-high;
+		};
+
+	};
+
+	usb1_default_pins: usb1-default-pins {
+		pins-valid {
+			pinmux = <PINMUX_GPIO88__FUNC_I0_VBUSVALID_1P>;
+			input-enable;
+		};
+
+		pins-usb-hub-3v3-en {
+			pinmux = <PINMUX_GPIO112__FUNC_B_GPIO112>;
+			output-high;
+		};
+	};
+
+	usb2_default_pins: usb2-default-pins {
+		pins-iddig {
+			pinmux = <PINMUX_GPIO89__FUNC_B_GPIO89>;
+			input-enable;
+			bias-pull-up;
+		};
+	};
+
+	wifi_pwrseq_pins: wifi-pwrseq-pins {
+		pins-wifi-enable {
+			pinmux = <PINMUX_GPIO127__FUNC_B_GPIO127>;
+			output-low;
+		};
+	};
+};
+
+&eth {
+	phy-mode ="rgmii-id";
+	phy-handle = <&ethernet_phy0>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&eth_default_pins>;
+	pinctrl-1 = <&eth_sleep_pins>;
+	mediatek,mac-wol;
+	snps,reset-gpio = <&pio 147 GPIO_ACTIVE_HIGH>;
+	snps,reset-delays-us = <0 10000 10000>;
+	status = "okay";
+};
+
+&eth_mdio {
+	ethernet_phy0: ethernet-phy@1 {
+		compatible = "ethernet-phy-id001c.c916";
+		reg = <0x1>;
+	};
+};
+
+&pmic {
+	interrupt-parent = <&pio>;
+	interrupts = <222 IRQ_TYPE_LEVEL_HIGH>;
+
+	mt6359keys: keys {
+		compatible = "mediatek,mt6359-keys";
+		mediatek,long-press-mode = <1>;
+		power-off-time-sec = <0>;
+
+		power-key {
+			linux,keycodes = <KEY_POWER>;
+			wakeup-source;
+		};
+	};
+};
+
+&scp {
+	memory-region = <&scp_mem>;
+	status = "okay";
+};
+
+&sound {
+	compatible = "mediatek,mt8390-mt6359-evk", "mediatek,mt8188-mt6359-evb";
+	model = "mt8390-evk";
+	pinctrl-names = "default";
+	pinctrl-0 = <&audio_default_pins>;
+	audio-routing =
+		"Headphone", "Headphone L",
+		"Headphone", "Headphone R",
+		"DMIC_INPUT", "AP DMIC",
+		"AP DMIC", "AUDGLB",
+		"AP DMIC", "MIC_BIAS_0",
+		"AP DMIC", "MIC_BIAS_2";
+	mediatek,adsp = <&adsp>;
+	status = "okay";
+
+	dai-link-0 {
+		link-name = "DL_SRC_BE";
+
+		codec {
+			sound-dai = <&pmic 0>;
+		};
+	};
+
+	dai-link-1 {
+		link-name = "DMIC_BE";
+
+		codec {
+			sound-dai = <&dmic_codec>;
+		};
+	};
+};
+
+&spi2 {
+	pinctrl-0 = <&spi2_pins>;
+	pinctrl-names = "default";
+	mediatek,pad-select = <0>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-0 = <&uart0_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-0 = <&uart1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&u3phy0 {
+	status = "okay";
+};
+
+&u3phy1 {
+	status = "okay";
+};
+
+&u3phy2 {
+	status = "okay";
+};
+
+&ssusb0 {
+	dr_mode = "otg";
+	maximum-speed = "high-speed";
+	usb-role-switch;
+	wakeup-source;
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	pinctrl-0 = <&usb_default_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		type = "micro";
+		id-gpios = <&pio 83 GPIO_ACTIVE_HIGH>;
+		vbus-supply = <&usb_p0_vbus>;
+	};
+};
+
+&xhci0 {
+	status = "okay";
+};
+
+&ssusb1 {
+	dr_mode = "otg";
+	usb-role-switch;
+	wakeup-source;
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	pinctrl-0 = <&usb1_default_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	port {
+		mtu3_hs1_role_sw: endpoint {
+			remote-endpoint = <&typec_con_hs>;
+		};
+	};
+};
+
+&xhci1 {
+	status = "okay";
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	hub_2_0: hub@1 {
+		compatible = "usb451,8025";
+		reg = <1>;
+		peer-hub = <&hub_3_0>;
+		reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
+		vdd-supply = <&usb_hub_fixed_3v3>;
+	};
+
+	hub_3_0: hub@2 {
+		compatible = "usb451,8027";
+		reg = <2>;
+		peer-hub = <&hub_2_0>;
+		reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
+		vdd-supply = <&usb_hub_fixed_3v3>;
+	};
+
+	port {
+		xhci_ss_ep: endpoint {
+			remote-endpoint = <&typec_con_ss>;
+		};
+	};
+};
+
+&ssusb2 {
+	dr_mode = "otg";
+	maximum-speed = "high-speed";
+	usb-role-switch;
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	wakeup-source;
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb2_default_pins>;
+	status = "okay";
+
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		type = "micro";
+		id-gpios = <&pio 89 GPIO_ACTIVE_HIGH>;
+		vbus-supply = <&usb_p2_vbus>;
+	};
+};
+
+&xhci2 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	vbus-supply = <&sdio_fixed_3v3>; /* wifi_3v3 */
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
index 5950194c9ccb..f02c32def593 100644
--- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
@@ -229,6 +229,21 @@
 	pinctrl-0 = <&i2c2_pins>;
 	pinctrl-names = "default";
 	status = "okay";
+
+	typec-mux@48 {
+		compatible = "ite,it5205";
+		reg = <0x48>;
+		vcc-supply = <&mt6359_vibr_ldo_reg>;
+		mode-switch;
+		orientation-switch;
+		status = "okay";
+
+		port {
+			it5205_sbu_ep: endpoint {
+				remote-endpoint = <&mt6360_ssusb_sbu_ep>;
+			};
+		};
+	};
 };
 
 &i2c6 {
@@ -335,6 +350,63 @@
 				regulator-always-on;
 			};
 		};
+
+		tcpc {
+			compatible = "mediatek,mt6360-tcpc";
+			interrupts-extended = <&pio 17 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-names = "PD_IRQB";
+
+			connector {
+				compatible = "usb-c-connector";
+				label = "USB-C";
+				data-role = "dual";
+				op-sink-microwatt = <10000000>;
+				power-role = "dual";
+				try-power-role = "sink";
+
+				source-pdos = <PDO_FIXED(5000, 1000,
+							 PDO_FIXED_DUAL_ROLE |
+							 PDO_FIXED_DATA_SWAP)>;
+				sink-pdos = <PDO_FIXED(5000, 2000,
+						       PDO_FIXED_DUAL_ROLE |
+						       PDO_FIXED_DATA_SWAP)>;
+
+				pd-revision = /bits/ 8 <0x03 0x01 0x01 0x06>;
+
+				altmodes {
+					displayport {
+						svid = /bits/ 16 <0xff01>;
+						vdo = <0x00001c46>;
+					};
+				};
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						typec_con_hs: endpoint {
+							remote-endpoint = <&mtu3_hs0_role_sw>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+						typec_con_ss: endpoint {
+							remote-endpoint = <&mtu3_ss0_role_sw>;
+						};
+					};
+
+					port@2 {
+						reg = <2>;
+						mt6360_ssusb_sbu_ep: endpoint {
+							remote-endpoint = <&it5205_sbu_ep>;
+						};
+					};
+				};
+			};
+		};
 	};
 };
 
@@ -770,6 +842,13 @@
 		};
 	};
 
+	u3_p0_vbus: u3-p0-vbus-default-pins {
+		pins-vbus {
+			pinmux = <PINMUX_GPIO63__FUNC_VBUSVALID>;
+			input-enable;
+		};
+	};
+
 	uart0_pins: uart0-pins {
 		pins {
 			pinmux = <PINMUX_GPIO98__FUNC_UTXD0>,
@@ -898,8 +977,31 @@
 };
 
 &ssusb0 {
+	dr_mode = "otg";
+	pinctrl-names = "default";
+	pinctrl-0 = <&u3_p0_vbus>;
+	usb-role-switch;
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			mtu3_hs0_role_sw: endpoint {
+				remote-endpoint = <&typec_con_hs>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			mtu3_ss0_role_sw: endpoint {
+				remote-endpoint = <&typec_con_ss>;
+			};
+		};
+	};
 };
 
 &ssusb2 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l-8-hd-panel.dtso b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l-8-hd-panel.dtso
new file mode 100644
index 000000000000..0389c9cb8581
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l-8-hd-panel.dtso
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Radxa Display 8 HD touchscreen module
+ * Copyright (C) 2025 Collabora Ltd.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+&backlight {
+	status = "okay";
+};
+
+&disp_pwm0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm0_default_pins>;
+	status = "okay";
+};
+
+&dsi0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "radxa,display-8hd-ad002", "jadard,jd9365da-h3";
+		reg = <0>;
+		backlight = <&backlight>;
+		vdd-supply = <&mt6359_vcn33_2_bt_ldo_reg>;
+		vccio-supply = <&mt6360_ldo2>;
+		reset-gpios = <&pio 108 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&panel_default_pins>;
+
+		port {
+			dsi_panel_in: endpoint {
+				remote-endpoint = <&dsi0_out>;
+			};
+		};
+	};
+};
+
+&dsi0_out {
+	remote-endpoint = <&dsi_panel_in>;
+};
+
+&i2c4 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	touchscreen@14 {
+		compatible = "goodix,gt911";
+		reg = <0x14>;
+		interrupts-extended = <&pio 132 IRQ_TYPE_EDGE_RISING>;
+		irq-gpios = <&pio 132 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&pio 133 GPIO_ACTIVE_HIGH>;
+		VDDIO-supply = <&mt6359_vcn33_2_bt_ldo_reg>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touch_pins>;
+	};
+};
+
+&mipi_tx0 {
+	status = "okay";
+};
+
+&ovl0_in {
+	remote-endpoint = <&vdosys0_ep_main>;
+};
+
+&vdosys0 {
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdosys0_ep_main: endpoint@0 {
+			reg = <0>;
+			remote-endpoint = <&ovl0_in>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
index 41dc34837b02..1c922e98441a 100644
--- a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
@@ -48,6 +48,18 @@
 		reg = <0 0x40000000 0x1 0x0>;
 	};
 
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		brightness-levels = <0 1023>;
+		default-brightness-level = <576>;
+		enable-gpios = <&pio 107 GPIO_ACTIVE_HIGH>;
+		num-interpolated-steps = <1023>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&dsi0_backlight_pins>;
+		pwms = <&disp_pwm0 0 500000>;
+		status = "disabled";
+	};
+
 	wifi_vreg: regulator-wifi-3v3-en {
 		compatible = "regulator-fixed";
 		regulator-name = "wifi_3v3_en";
@@ -172,6 +184,32 @@
 	cpu-supply = <&mt6315_6_vbuck1>;
 };
 
+&dither0_out {
+	remote-endpoint = <&dsi0_in>;
+};
+
+&dsi0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dsi0_in: endpoint {
+				remote-endpoint = <&dither0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dsi0_out: endpoint { };
+		};
+	};
+};
+
 &eth {
 	phy-mode = "rgmii-rxid";
 	phy-handle = <&rgmii_phy>;
@@ -476,6 +514,13 @@
 &pio {
 	mediatek,rsel-resistance-in-si-unit;
 
+	dsi0_backlight_pins: dsi0-backlight-pins {
+		pins-backlight-en {
+			pinmux = <PINMUX_GPIO107__FUNC_GPIO107>;
+			output-high;
+		};
+	};
+
 	eth_default_pins: eth-default-pins {
 		pins-cc {
 			pinmux = <PINMUX_GPIO85__FUNC_GBE_TXC>,
@@ -673,6 +718,13 @@
 		};
 	};
 
+	panel_default_pins: panel-pins {
+		pins-rst {
+			pinmux = <PINMUX_GPIO108__FUNC_GPIO108>;
+			bias-pull-up;
+		};
+	};
+
 	pcie0_default_pins: pcie0-default-pins {
 		pins-bus {
 			pinmux = <PINMUX_GPIO19__FUNC_WAKEN>,
@@ -691,6 +743,12 @@
 		};
 	};
 
+	pwm0_default_pins: pwm0-pins {
+		pins-disp-pwm {
+			pinmux = <PINMUX_GPIO97__FUNC_DISP_PWM0>;
+		};
+	};
+
 	spi1_pins: spi1-default-pins {
 		pins-bus {
 			pinmux = <PINMUX_GPIO136__FUNC_SPIM1_CSB>,
@@ -711,6 +769,19 @@
 		};
 	};
 
+	touch_pins: touch-pins {
+		pins-touch-int {
+			pinmux = <PINMUX_GPIO132__FUNC_GPIO132>;
+			input-enable;
+			bias-disable;
+		};
+
+		pins-touch-rst {
+			pinmux = <PINMUX_GPIO133__FUNC_GPIO133>;
+			output-high;
+		};
+	};
+
 	uart0_pins: uart0-pins {
 		pins-bus {
 			pinmux = <PINMUX_GPIO98__FUNC_UTXD0>,
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
index 1c53ccc5e3cb..9b9d1d15b0c7 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
@@ -49,6 +49,19 @@
 		};
 	};
 
+	i2c@7000c000 {
+		status = "okay";
+
+		tmp451: temperature-sensor@4c {
+			compatible = "ti,tmp451";
+			reg = <0x4c>;
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(X, 4) IRQ_TYPE_LEVEL_LOW>;
+			vcc-supply = <&vdd_1v8>;
+			#thermal-sensor-cells = <1>;
+		};
+	};
+
 	i2c@7000c400 {
 		status = "okay";
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
index 63b94a04308e..83ed6ac2a8d8 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
@@ -1375,6 +1375,15 @@
 
 			#gpio-cells = <2>;
 			gpio-controller;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(L, 1) IRQ_TYPE_EDGE_FALLING>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio_1v8>;
 		};
 
 		exp2: gpio@77 {
@@ -1383,6 +1392,15 @@
 
 			#gpio-cells = <2>;
 			gpio-controller;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(Z, 2) IRQ_TYPE_EDGE_FALLING>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&gpio_1v8>;
 		};
 	};
 
@@ -1686,7 +1704,7 @@
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 		regulator-always-on;
-		gpio = <&exp1 14 GPIO_ACTIVE_HIGH>;
+		gpio = <&exp1 9 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 		vin-supply = <&vdd_1v8>;
 	};
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts
index c56824d7f4d8..0ecdd7243b2e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts
@@ -266,7 +266,6 @@
 					regulator-max-microvolt = <1170000>;
 					regulator-enable-ramp-delay = <146>;
 					regulator-ramp-delay = <27500>;
-					regulator-ramp-delay-scale = <300>;
 					regulator-always-on;
 					regulator-boot-on;
 
@@ -281,7 +280,6 @@
 					regulator-max-microvolt = <1150000>;
 					regulator-enable-ramp-delay = <176>;
 					regulator-ramp-delay = <27500>;
-					regulator-ramp-delay-scale = <300>;
 					regulator-always-on;
 					regulator-boot-on;
 
@@ -296,7 +294,6 @@
 					regulator-max-microvolt = <1350000>;
 					regulator-enable-ramp-delay = <176>;
 					regulator-ramp-delay = <27500>;
-					regulator-ramp-delay-scale = <350>;
 					regulator-always-on;
 					regulator-boot-on;
 
@@ -311,7 +308,6 @@
 					regulator-max-microvolt = <1800000>;
 					regulator-enable-ramp-delay = <242>;
 					regulator-ramp-delay = <27500>;
-					regulator-ramp-delay-scale = <360>;
 					regulator-always-on;
 					regulator-boot-on;
 
@@ -326,7 +322,6 @@
 					regulator-max-microvolt = <1200000>;
 					regulator-enable-ramp-delay = <26>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 					regulator-always-on;
 					regulator-boot-on;
 
@@ -341,7 +336,6 @@
 					regulator-max-microvolt = <1050000>;
 					regulator-enable-ramp-delay = <22>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 
 					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
 					maxim,active-fps-power-up-slot = <0>;
@@ -354,7 +348,6 @@
 					regulator-max-microvolt = <3300000>;
 					regulator-enable-ramp-delay = <62>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 
 					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
 					maxim,active-fps-power-up-slot = <0>;
@@ -371,7 +364,6 @@
 					regulator-max-microvolt = <1100000>;
 					regulator-enable-ramp-delay = <22>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 					regulator-disable-active-discharge;
 					regulator-always-on;
 					regulator-boot-on;
@@ -395,7 +387,6 @@
 					regulator-max-microvolt = <1050000>;
 					regulator-enable-ramp-delay = <24>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 
 					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
 					maxim,active-fps-power-up-slot = <3>;
@@ -408,7 +399,6 @@
 					regulator-max-microvolt = <1050000>;
 					regulator-enable-ramp-delay = <22>;
 					regulator-ramp-delay = <100000>;
-					regulator-ramp-delay-scale = <200>;
 
 					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
 					maxim,active-fps-power-up-slot = <6>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 942e3a0f81ed..b6c84d195c0e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -874,6 +874,16 @@
 				pins = "sdmmc3";
 				power-source = <TEGRA_IO_PAD_VOLTAGE_3V3>;
 			};
+
+			gpio_1v8: gpio-1v8 {
+				pins = "gpio";
+				power-source = <TEGRA_IO_PAD_VOLTAGE_1V8>;
+			};
+
+			gpio_3v3: gpio-3v3 {
+				pins = "gpio";
+				power-source = <TEGRA_IO_PAD_VOLTAGE_3V3>;
+			};
 		};
 
 		powergates {
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002+p3701-0008.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002+p3701-0008.dts
index 36e888053746..9ce55b4d2de8 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002+p3701-0008.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002+p3701-0008.dts
@@ -302,6 +302,16 @@
 		};
 
 		pcie@141a0000 {
+			reg = <0x00 0x141a0000 0x0 0x00020000   /* appl registers (128K)      */
+			       0x00 0x3a000000 0x0 0x00040000   /* configuration space (256K) */
+			       0x00 0x3a040000 0x0 0x00040000   /* iATU_DMA reg space (256K)  */
+			       0x00 0x3a080000 0x0 0x00040000   /* DBI reg space (256K)       */
+			       0x2e 0x20000000 0x0 0x10000000>; /* ECAM (256MB)               */
+
+			ranges = <0x81000000 0x00 0x3a100000 0x00 0x3a100000 0x0 0x00100000      /* downstream I/O (1MB) */
+				  0x82000000 0x00 0x40000000 0x2e 0x30000000 0x0 0x08000000      /* non-prefetchable memory (128MB) */
+				  0xc3000000 0x28 0x00000000 0x28 0x00000000 0x6 0x20000000>;    /* prefetchable memory (25088MB) */
+
 			status = "okay";
 			vddio-pex-ctl-supply = <&vdd_1v8_ls>;
 			phys = <&p2u_nvhs_0>, <&p2u_nvhs_1>, <&p2u_nvhs_2>,
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi
index 19340d13f789..41821354bbda 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767.dtsi
@@ -227,13 +227,6 @@
 			wakeup-event-action = <EV_ACT_ASSERTED>;
 			wakeup-source;
 		};
-
-		key-suspend {
-			label = "Suspend";
-			gpios = <&gpio TEGRA234_MAIN_GPIO(G, 2) GPIO_ACTIVE_LOW>;
-			linux,input-type = <EV_KEY>;
-			linux,code = <KEY_SLEEP>;
-		};
 	};
 
 	fan: pwm-fan {
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts
index 09b95f89ee58..1667c7157057 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-huawei-gaokun3.dts
@@ -28,6 +28,7 @@
 
 	aliases {
 		i2c4 = &i2c4;
+		i2c15 = &i2c15;
 		serial1 = &uart2;
 	};
 
@@ -216,6 +217,40 @@
 		};
 	};
 
+	usb0-sbu-mux {
+		compatible = "pericom,pi3usb102", "gpio-sbu-mux";
+
+		select-gpios = <&tlmm 164 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&usb0_sbu_default>;
+		pinctrl-names = "default";
+
+		orientation-switch;
+
+		port {
+			usb0_sbu_mux: endpoint {
+				remote-endpoint = <&ucsi0_sbu>;
+			};
+		};
+	};
+
+	usb1-sbu-mux {
+		compatible = "pericom,pi3usb102", "gpio-sbu-mux";
+
+		select-gpios = <&tlmm 47 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&usb1_sbu_default>;
+		pinctrl-names = "default";
+
+		orientation-switch;
+
+		port {
+			usb1_sbu_mux: endpoint {
+				remote-endpoint = <&ucsi1_sbu>;
+			};
+		};
+	};
+
 	wcn6855-pmu {
 		compatible = "qcom,wcn6855-pmu";
 
@@ -584,6 +619,97 @@
 
 };
 
+&i2c15 {
+	clock-frequency = <400000>;
+
+	pinctrl-0 = <&i2c15_default>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	embedded-controller@38 {
+		compatible = "huawei,gaokun3-ec";
+		reg = <0x38>;
+
+		interrupts-extended = <&tlmm 107 IRQ_TYPE_LEVEL_LOW>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		connector@0 {
+			compatible = "usb-c-connector";
+			reg = <0>;
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					ucsi0_hs_in: endpoint {
+						remote-endpoint = <&usb_0_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					ucsi0_ss_in: endpoint {
+						remote-endpoint = <&usb_0_qmpphy_out>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					ucsi0_sbu: endpoint {
+						remote-endpoint = <&usb0_sbu_mux>;
+					};
+				};
+			};
+		};
+
+		connector@1 {
+			compatible = "usb-c-connector";
+			reg = <1>;
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					ucsi1_hs_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					ucsi1_ss_in: endpoint {
+						remote-endpoint = <&usb_1_qmpphy_out>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					ucsi1_sbu: endpoint {
+						remote-endpoint = <&usb1_sbu_mux>;
+					};
+				};
+			};
+		};
+	};
+};
+
 &mdss0 {
 	status = "okay";
 };
@@ -1004,6 +1130,10 @@
 	dr_mode = "host";
 };
 
+&usb_0_dwc3_hs {
+	remote-endpoint = <&ucsi0_hs_in>;
+};
+
 &usb_0_hsphy {
 	vdda-pll-supply = <&vreg_l9d>;
 	vdda18-supply = <&vreg_l1c>;
@@ -1025,6 +1155,10 @@
 	remote-endpoint = <&mdss0_dp0_out>;
 };
 
+&usb_0_qmpphy_out {
+	remote-endpoint = <&ucsi0_ss_in>;
+};
+
 &usb_1 {
 	status = "okay";
 };
@@ -1033,6 +1167,10 @@
 	dr_mode = "host";
 };
 
+&usb_1_dwc3_hs {
+	remote-endpoint = <&ucsi1_hs_in>;
+};
+
 &usb_1_hsphy {
 	vdda-pll-supply = <&vreg_l4b>;
 	vdda18-supply = <&vreg_l1c>;
@@ -1054,6 +1192,10 @@
 	remote-endpoint = <&mdss0_dp1_out>;
 };
 
+&usb_1_qmpphy_out {
+	remote-endpoint = <&ucsi1_ss_in>;
+};
+
 &usb_2 {
 	status = "okay";
 };
@@ -1177,6 +1319,13 @@
 		bias-disable;
 	};
 
+	i2c15_default: i2c15-default-state {
+		pins = "gpio36", "gpio37";
+		function = "qup15";
+		drive-strength = <2>;
+		bias-pull-up;
+	};
+
 	mode_pin_active: mode-pin-state {
 		pins = "gpio26";
 		function = "gpio";
@@ -1301,6 +1450,20 @@
 		};
 	};
 
+	usb0_sbu_default: usb0-sbu-state {
+		pins = "gpio164";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+	};
+
+	usb1_sbu_default: usb1-sbu-state {
+		pins = "gpio47";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+	};
+
 	wcd_default: wcd-default-state {
 		reset-pins {
 			pins = "gpio106";
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index e0ce804bb1a3..d0314cdf0b92 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -5163,7 +5163,6 @@
 				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>;
-			dma-coherent;
 		};
 
 		anoc_1_tbu: tbu@150c5000 {
diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile
index 928635f2e76b..d25e665ee4bf 100644
--- a/arch/arm64/boot/dts/renesas/Makefile
+++ b/arch/arm64/boot/dts/renesas/Makefile
@@ -132,6 +132,7 @@ dtb-$(CONFIG_ARCH_R9A07G044) += r9a07g044c2-smarc-cru-csi-ov5645.dtbo
 r9a07g044c2-smarc-cru-csi-ov5645-dtbs := r9a07g044c2-smarc.dtb r9a07g044c2-smarc-cru-csi-ov5645.dtbo
 dtb-$(CONFIG_ARCH_R9A07G044) += r9a07g044c2-smarc-cru-csi-ov5645.dtb
 
+dtb-$(CONFIG_ARCH_R9A07G044) += r9a07g044l2-remi-pi.dtb
 dtb-$(CONFIG_ARCH_R9A07G044) += r9a07g044l2-smarc.dtb
 dtb-$(CONFIG_ARCH_R9A07G044) += r9a07g044l2-smarc-cru-csi-ov5645.dtbo
 r9a07g044l2-smarc-cru-csi-ov5645-dtbs := r9a07g044l2-smarc.dtb r9a07g044l2-smarc-cru-csi-ov5645.dtbo
@@ -143,12 +144,16 @@ r9a07g054l2-smarc-cru-csi-ov5645-dtbs := r9a07g054l2-smarc.dtb r9a07g054l2-smarc
 dtb-$(CONFIG_ARCH_R9A07G054) += r9a07g054l2-smarc-cru-csi-ov5645.dtb
 
 dtb-$(CONFIG_ARCH_R9A08G045) += r9a08g045s33-smarc.dtb
+dtb-$(CONFIG_ARCH_R9A08G045) += r9a08g045s33-smarc-pmod1-type-3a.dtbo
+r9a08g045s33-smarc-pmod1-type-3a-dtbs := r9a08g045s33-smarc.dtb r9a08g045s33-smarc-pmod1-type-3a.dtbo
+dtb-$(CONFIG_ARCH_R9A08G045) += r9a08g045s33-smarc-pmod1-type-3a.dtb
 
 dtb-$(CONFIG_ARCH_R9A09G011) += r9a09g011-v2mevk2.dtb
 
 dtb-$(CONFIG_ARCH_R9A09G047) += r9a09g047e57-smarc.dtb
 
 dtb-$(CONFIG_ARCH_R9A09G057) += r9a09g057h44-rzv2h-evk.dtb
+dtb-$(CONFIG_ARCH_R9A09G057) += r9a09g057h48-kakip.dtb
 
 dtb-$(CONFIG_ARCH_RCAR_GEN3) += draak-ebisu-panel-aa104xd12.dtbo
 dtb-$(CONFIG_ARCH_RCAR_GEN3) += salvator-panel-aa104xd12.dtbo
diff --git a/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi b/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi
index 43f88c199b78..1489bc8d2f4e 100644
--- a/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi
@@ -282,6 +282,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/renesas/condor-common.dtsi b/arch/arm64/boot/dts/renesas/condor-common.dtsi
index 375a56b20f26..a10584150571 100644
--- a/arch/arm64/boot/dts/renesas/condor-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/condor-common.dtsi
@@ -544,6 +544,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>, <&scif_clk_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/draak.dtsi b/arch/arm64/boot/dts/renesas/draak.dtsi
index 05712cd96d28..380b857fd273 100644
--- a/arch/arm64/boot/dts/renesas/draak.dtsi
+++ b/arch/arm64/boot/dts/renesas/draak.dtsi
@@ -695,6 +695,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/ebisu.dtsi b/arch/arm64/boot/dts/renesas/ebisu.dtsi
index ab8283656660..4f38b01ae18d 100644
--- a/arch/arm64/boot/dts/renesas/ebisu.dtsi
+++ b/arch/arm64/boot/dts/renesas/ebisu.dtsi
@@ -786,6 +786,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/hihope-common.dtsi b/arch/arm64/boot/dts/renesas/hihope-common.dtsi
index 659ae1fed2fa..4e78139d52f6 100644
--- a/arch/arm64/boot/dts/renesas/hihope-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/hihope-common.dtsi
@@ -289,6 +289,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
index f065ee90649a..c8b87aed92a3 100644
--- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
@@ -215,6 +215,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -222,6 +223,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -262,6 +264,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -400,6 +404,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a774a1";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -480,11 +485,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a774a1-rst";
 			reg = <0 0xe6160000 0 0x018c>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2785,6 +2792,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774b1.dtsi b/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
index 117cb6950f91..f2fc2a2035a1 100644
--- a/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
@@ -108,6 +108,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -115,6 +116,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -146,6 +148,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -284,6 +288,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a774b1";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -364,11 +369,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a774b1-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2661,6 +2668,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0-cat874.dts b/arch/arm64/boot/dts/renesas/r8a774c0-cat874.dts
index b78dbd807d15..57a281fc4977 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0-cat874.dts
+++ b/arch/arm64/boot/dts/renesas/r8a774c0-cat874.dts
@@ -378,6 +378,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
index 7655d5e3a034..530ffd29cf13 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
@@ -47,16 +47,20 @@
 	cluster1_opp: opp-table-1 {
 		compatible = "operating-points-v2";
 		opp-shared;
+
 		opp-800000000 {
 			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 		};
 		opp-1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 		};
 		opp-1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
@@ -103,6 +107,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -134,6 +139,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -257,6 +264,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a774c0";
 			reg = <0 0xe6060000 0 0x508>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -337,11 +345,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a774c0-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1953,6 +1963,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
index f845ca604de0..e4dbda8c34d9 100644
--- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
@@ -277,6 +277,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -284,6 +285,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -326,6 +328,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -464,6 +468,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a774e1";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -544,11 +549,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a774e1-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2917,6 +2924,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77951.dtsi b/arch/arm64/boot/dts/renesas/r8a77951.dtsi
index 96f3b5fe7e92..6ee9cdeb5a3a 100644
--- a/arch/arm64/boot/dts/renesas/r8a77951.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77951.dtsi
@@ -292,6 +292,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -299,6 +300,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -347,6 +349,7 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -485,6 +488,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7795";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -565,11 +569,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7795-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -3398,6 +3404,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77960.dtsi b/arch/arm64/boot/dts/renesas/r8a77960.dtsi
index ee80f52dc7cf..a323ac47ca70 100644
--- a/arch/arm64/boot/dts/renesas/r8a77960.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77960.dtsi
@@ -264,6 +264,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -271,6 +272,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -311,6 +313,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -449,6 +453,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a7796";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -529,11 +534,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a7796-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2996,6 +3003,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77961.dtsi b/arch/arm64/boot/dts/renesas/r8a77961.dtsi
index 3b9066043a71..49f6d31c5903 100644
--- a/arch/arm64/boot/dts/renesas/r8a77961.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77961.dtsi
@@ -264,6 +264,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -271,6 +272,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -311,6 +313,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -449,6 +453,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77961";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -529,11 +534,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77961-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2817,6 +2824,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
index 557bdf8fab17..136a22ca50b7 100644
--- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
@@ -143,6 +143,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -150,6 +151,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -182,6 +184,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -320,6 +324,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77965";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -400,11 +405,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77965-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2828,6 +2835,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle-function-expansion.dtso b/arch/arm64/boot/dts/renesas/r8a77970-eagle-function-expansion.dtso
index 9450d8ac94cb..0c005660d8dd 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-eagle-function-expansion.dtso
+++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle-function-expansion.dtso
@@ -70,7 +70,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 
-		vin0_adv7612_en {
+		vin0-adv7612-en-hog {
 			gpio-hog;
 			gpios = <3 GPIO_ACTIVE_LOW>;
 			output-high;
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
index 32f07aa27316..8b594e9e9dc1 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
@@ -409,6 +409,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
index 118e77f4477e..445f5dd7c983 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
@@ -296,6 +296,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a77970.dtsi b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
index 38145fd6acf0..01744496805c 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
@@ -60,6 +60,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -67,6 +68,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pmu_a53 {
@@ -91,6 +93,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -200,6 +203,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77970";
 			reg = <0 0xe6060000 0 0x504>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -280,11 +284,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77970-rst";
 			reg = <0 0xe6160000 0 0x200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1196,6 +1202,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
index b409a8d1737e..c2692d6fd00d 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
@@ -282,6 +282,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>, <&scif_clk_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
index 55a6c622f873..f7e506ad7a21 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
@@ -80,6 +80,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -87,6 +88,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -120,6 +122,7 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
 
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -229,6 +232,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77980";
 			reg = <0 0xe6060000 0 0x50c>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -309,11 +313,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77980-rst";
 			reg = <0 0xe6160000 0 0x200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1579,6 +1585,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
index 233af3081e84..6b8742045836 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
@@ -47,16 +47,20 @@
 	cluster1_opp: opp-table-1 {
 		compatible = "operating-points-v2";
 		opp-shared;
+
 		opp-800000000 {
 			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 		};
 		opp-1000000000 {
 			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 		};
 		opp-1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <1030000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
@@ -118,6 +122,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	/* External PCIe clock - can be overridden by the board */
@@ -149,6 +154,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -272,6 +279,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77990";
 			reg = <0 0xe6060000 0 0x508>;
+			bootph-all;
 		};
 
 		i2c_dvfs: i2c@e60b0000 {
@@ -368,11 +376,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77990-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2117,6 +2127,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77995.dtsi b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
index 5f0828a4675b..b66cd7c90d53 100644
--- a/arch/arm64/boot/dts/renesas/r8a77995.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
@@ -65,6 +65,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pmu_a53 {
@@ -86,6 +87,8 @@
 	soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -209,6 +212,7 @@
 		pfc: pinctrl@e6060000 {
 			compatible = "renesas,pfc-r8a77995";
 			reg = <0 0xe6060000 0 0x508>;
+			bootph-all;
 		};
 
 		cmt0: timer@e60f0000 {
@@ -289,11 +293,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a77995-rst";
 			reg = <0 0xe6160000 0 0x0200>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -1448,6 +1454,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a779a0-falcon-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0-falcon-cpu.dtsi
index e8c8fca48b69..0916fd57d1f1 100644
--- a/arch/arm64/boot/dts/renesas/r8a779a0-falcon-cpu.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779a0-falcon-cpu.dtsi
@@ -348,6 +348,7 @@
 &scif0 {
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	uart-has-rtscts;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
index fe6d97859e4a..f1613bfd1632 100644
--- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
@@ -47,6 +47,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -54,6 +55,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pmu_a76 {
@@ -71,6 +73,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -93,6 +97,7 @@
 			      <0 0xe6060000 0 0x16c>, <0 0xe6060800 0 0x16c>,
 			      <0 0xe6068000 0 0x16c>, <0 0xe6068800 0 0x16c>,
 			      <0 0xe6069000 0 0x16c>, <0 0xe6069800 0 0x16c>;
+			bootph-all;
 		};
 
 		gpio0: gpio@e6058180 {
@@ -331,11 +336,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a779a0-rst";
 			reg = <0 0xe6160000 0 0x4000>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2338,6 +2345,42 @@
 			iommus = <&ipmmu_vi1 7>;
 		};
 
+		fcpvx0: fcp@fedb0000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedb0000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1100>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP01>;
+			resets = <&cpg 1100>;
+			iommus = <&ipmmu_vi1 24>;
+		};
+
+		fcpvx1: fcp@fedb8000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedb8000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1101>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP01>;
+			resets = <&cpg 1101>;
+			iommus = <&ipmmu_vi1 25>;
+		};
+
+		fcpvx2: fcp@fedc0000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedc0000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1102>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP23>;
+			resets = <&cpg 1102>;
+			iommus = <&ipmmu_vi1 26>;
+		};
+
+		fcpvx3: fcp@fedc8000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedc8000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1103>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP23>;
+			resets = <&cpg 1103>;
+			iommus = <&ipmmu_vi1 27>;
+		};
+
 		vspd0: vsp@fea20000 {
 			compatible = "renesas,vsp2";
 			reg = <0 0xfea20000 0 0x5000>;
@@ -2360,6 +2403,50 @@
 			renesas,fcp = <&fcpvd1>;
 		};
 
+		vspx0: vsp@fedd0000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfedd0000 0 0x8000>;
+			interrupts = <GIC_SPI 600 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1028>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP01>;
+			resets = <&cpg 1028>;
+
+			renesas,fcp = <&fcpvx0>;
+		};
+
+		vspx1: vsp@fedd8000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfedd8000 0 0x8000>;
+			interrupts = <GIC_SPI 601 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1029>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP01>;
+			resets = <&cpg 1029>;
+
+			renesas,fcp = <&fcpvx1>;
+		};
+
+		vspx2: vsp@fede0000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfede0000 0 0x8000>;
+			interrupts = <GIC_SPI 602 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1030>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP23>;
+			resets = <&cpg 1030>;
+
+			renesas,fcp = <&fcpvx2>;
+		};
+
+		vspx3: vsp@fede8000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfede8000 0 0x8000>;
+			interrupts = <GIC_SPI 603 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1031>;
+			power-domains = <&sysc R8A779A0_PD_A3ISP23>;
+			resets = <&cpg 1031>;
+
+			renesas,fcp = <&fcpvx3>;
+		};
+
 		csi40: csi2@feaa0000 {
 			compatible = "renesas,r8a779a0-csi2";
 			reg = <0 0xfeaa0000 0 0x10000>;
@@ -2893,6 +2980,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a779f0-spider-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0-spider-cpu.dtsi
index e03baefb6a98..1781bb79a619 100644
--- a/arch/arm64/boot/dts/renesas/r8a779f0-spider-cpu.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779f0-spider-cpu.dtsi
@@ -101,6 +101,7 @@
 &hscif0 {
 	pinctrl-0 = <&hscif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	uart-has-rtscts;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi
index 5d38669ed1ec..ad2b0398d354 100644
--- a/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi
@@ -5,6 +5,14 @@
  * Copyright (C) 2021 Renesas Electronics Corp.
  */
 
+/ {
+	aliases {
+		ethernet0 = &rswitch_port0;
+		ethernet1 = &rswitch_port1;
+		ethernet2 = &rswitch_port2;
+	};
+};
+
 &eth_serdes {
 	status = "okay";
 };
@@ -42,61 +50,61 @@
 	pinctrl-0 = <&tsn0_pins>, <&tsn1_pins>, <&tsn2_pins>;
 	pinctrl-names = "default";
 	status = "okay";
+};
+
+&rswitch_port0 {
+	reg = <0>;
+	phy-handle = <&u101>;
+	phy-mode = "sgmii";
+	phys = <&eth_serdes 0>;
+	status = "okay";
 
-	ethernet-ports {
+	mdio {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		port@0 {
-			reg = <0>;
-			phy-handle = <&u101>;
-			phy-mode = "sgmii";
-			phys = <&eth_serdes 0>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				u101: ethernet-phy@1 {
-					reg = <1>;
-					compatible = "ethernet-phy-ieee802.3-c45";
-					interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>;
-				};
-			};
-		};
-		port@1 {
+		u101: ethernet-phy@1 {
 			reg = <1>;
-			phy-handle = <&u201>;
-			phy-mode = "sgmii";
-			phys = <&eth_serdes 1>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				u201: ethernet-phy@2 {
-					reg = <2>;
-					compatible = "ethernet-phy-ieee802.3-c45";
-					interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>;
-				};
-			};
+			compatible = "ethernet-phy-ieee802.3-c45";
+			interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>;
 		};
-		port@2 {
+	};
+};
+
+&rswitch_port1 {
+	reg = <1>;
+	phy-handle = <&u201>;
+	phy-mode = "sgmii";
+	phys = <&eth_serdes 1>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		u201: ethernet-phy@2 {
 			reg = <2>;
-			phy-handle = <&u301>;
-			phy-mode = "sgmii";
-			phys = <&eth_serdes 2>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				u301: ethernet-phy@3 {
-					reg = <3>;
-					compatible = "ethernet-phy-ieee802.3-c45";
-					interrupts-extended = <&gpio3 9 IRQ_TYPE_LEVEL_LOW>;
-				};
-			};
+			compatible = "ethernet-phy-ieee802.3-c45";
+			interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>;
+		};
+	};
+};
+
+&rswitch_port2 {
+	reg = <2>;
+	phy-handle = <&u301>;
+	phy-mode = "sgmii";
+	phys = <&eth_serdes 2>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		u301: ethernet-phy@3 {
+			reg = <3>;
+			compatible = "ethernet-phy-ieee802.3-c45";
+			interrupts-extended = <&gpio3 9 IRQ_TYPE_LEVEL_LOW>;
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
index 054498e54730..b496495c59a6 100644
--- a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
@@ -253,6 +253,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -260,6 +261,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pcie0_clkref: pcie0-clkref {
@@ -296,6 +298,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -315,6 +319,7 @@
 			compatible = "renesas,pfc-r8a779f0";
 			reg = <0 0xe6050000 0 0x16c>, <0 0xe6050800 0 0x16c>,
 			      <0 0xe6051000 0 0x16c>, <0 0xe6051800 0 0x16c>;
+			bootph-all;
 		};
 
 		gpio0: gpio@e6050180 {
@@ -463,11 +468,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a779f0-rst";
 			reg = <0 0xe6160000 0 0x4000>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -974,17 +981,20 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				rswitch_port0: port@0 {
 					reg = <0>;
 					phys = <&eth_serdes 0>;
+					status = "disabled";
 				};
-				port@1 {
+				rswitch_port1: port@1 {
 					reg = <1>;
 					phys = <&eth_serdes 1>;
+					status = "disabled";
 				};
-				port@2 {
+				rswitch_port2: port@2 {
 					reg = <2>;
 					phys = <&eth_serdes 2>;
+					status = "disabled";
 				};
 			};
 		};
@@ -1280,6 +1290,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts b/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts
index 5d71d52f9c65..67b18f2bffbd 100644
--- a/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts
@@ -22,7 +22,8 @@
 		i2c5 = &i2c5;
 		serial0 = &hscif0;
 		serial1 = &hscif1;
-		ethernet0 = &rswitch;
+		ethernet0 = &rswitch_port0;
+		ethernet1 = &rswitch_port1;
 	};
 
 	chosen {
@@ -67,6 +68,7 @@
 &hscif0 {
 	pinctrl-0 = <&hscif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	uart-has-rtscts;
 	status = "okay";
@@ -179,49 +181,42 @@
 	pinctrl-0 = <&tsn0_pins>, <&tsn1_pins>;
 	pinctrl-names = "default";
 	status = "okay";
+};
+
+&rswitch_port0 {
+	reg = <0>;
+	phy-handle = <&ic99>;
+	phy-mode = "sgmii";
+	phys = <&eth_serdes 0>;
+	status = "okay";
 
-	ethernet-ports {
+	mdio {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		port@0 {
-			reg = <0>;
-			phy-handle = <&ic99>;
-			phy-mode = "sgmii";
-			phys = <&eth_serdes 0>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				ic99: ethernet-phy@1 {
-					reg = <1>;
-					compatible = "ethernet-phy-ieee802.3-c45";
-					interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>;
-				};
-			};
-		};
-
-		port@1 {
+		ic99: ethernet-phy@1 {
 			reg = <1>;
-			phy-handle = <&ic102>;
-			phy-mode = "sgmii";
-			phys = <&eth_serdes 1>;
-
-			mdio {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				ic102: ethernet-phy@2 {
-					reg = <2>;
-					compatible = "ethernet-phy-ieee802.3-c45";
-					interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>;
-				};
-			};
+			compatible = "ethernet-phy-ieee802.3-c45";
+			interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>;
 		};
+	};
+};
+
+&rswitch_port1 {
+	reg = <1>;
+	phy-handle = <&ic102>;
+	phy-mode = "sgmii";
+	phys = <&eth_serdes 1>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
-		port@2 {
-			status = "disabled";
+		ic102: ethernet-phy@2 {
+			reg = <2>;
+			compatible = "ethernet-phy-ieee802.3-c45";
+			interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>;
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
index 104f740d20d3..1760720b7128 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
@@ -166,6 +166,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr {
@@ -173,6 +174,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pcie0_clkref: pcie0-clkref {
@@ -215,6 +217,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -237,6 +241,7 @@
 			      <0 0xe6060000 0 0x16c>, <0 0xe6060800 0 0x16c>,
 			      <0 0xe6061000 0 0x16c>, <0 0xe6061800 0 0x16c>,
 			      <0 0xe6068000 0 0x16c>;
+			bootph-all;
 		};
 
 		gpio0: gpio@e6050180 {
@@ -452,11 +457,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a779g0-rst";
 			reg = <0 0xe6160000 0 0x4000>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -2171,6 +2178,24 @@
 			iommus = <&ipmmu_vi1 7>;
 		};
 
+		fcpvx0: fcp@fedb0000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedb0000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1100>;
+			power-domains = <&sysc R8A779G0_PD_A3ISP0>;
+			resets = <&cpg 1100>;
+			iommus = <&ipmmu_vi1 24>;
+		};
+
+		fcpvx1: fcp@fedb8000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedb8000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1101>;
+			power-domains = <&sysc R8A779G0_PD_A3ISP1>;
+			resets = <&cpg 1101>;
+			iommus = <&ipmmu_vi1 25>;
+		};
+
 		vspd0: vsp@fea20000 {
 			compatible = "renesas,vsp2";
 			reg = <0 0xfea20000 0 0x7000>;
@@ -2193,6 +2218,28 @@
 			renesas,fcp = <&fcpvd1>;
 		};
 
+		vspx0: vsp@fedd0000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfedd0000 0 0x8000>;
+			interrupts = <GIC_SPI 556 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1028>;
+			power-domains = <&sysc R8A779G0_PD_A3ISP0>;
+			resets = <&cpg 1028>;
+
+			renesas,fcp = <&fcpvx0>;
+		};
+
+		vspx1: vsp@fedd8000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfedd8000 0 0x8000>;
+			interrupts = <GIC_SPI 557 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1029>;
+			power-domains = <&sysc R8A779G0_PD_A3ISP1>;
+			resets = <&cpg 1029>;
+
+			renesas,fcp = <&fcpvx1>;
+		};
+
 		du: display@feb00000 {
 			compatible = "renesas,du-r8a779g0";
 			reg = <0 0xfeb00000 0 0x40000>;
@@ -2453,49 +2500,10 @@
 			};
 		};
 
-		fcpvx0: fcp@fedb0000 {
-			compatible = "renesas,fcpv";
-			reg = <0 0xfedb0000 0 0x200>;
-			clocks = <&cpg CPG_MOD 1100>;
-			power-domains = <&sysc R8A779G0_PD_A3ISP0>;
-			resets = <&cpg 1100>;
-			iommus = <&ipmmu_vi1 24>;
-		};
-
-		fcpvx1: fcp@fedb8000 {
-			compatible = "renesas,fcpv";
-			reg = <0 0xfedb8000 0 0x200>;
-			clocks = <&cpg CPG_MOD 1101>;
-			power-domains = <&sysc R8A779G0_PD_A3ISP1>;
-			resets = <&cpg 1101>;
-			iommus = <&ipmmu_vi1 25>;
-		};
-
-		vspx0: vsp@fedd0000 {
-			compatible = "renesas,vsp2";
-			reg = <0 0xfedd0000 0 0x8000>;
-			interrupts = <GIC_SPI 556 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&cpg CPG_MOD 1028>;
-			power-domains = <&sysc R8A779G0_PD_A3ISP0>;
-			resets = <&cpg 1028>;
-
-			renesas,fcp = <&fcpvx0>;
-		};
-
-		vspx1: vsp@fedd8000 {
-			compatible = "renesas,vsp2";
-			reg = <0 0xfedd8000 0 0x8000>;
-			interrupts = <GIC_SPI 557 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&cpg CPG_MOD 1029>;
-			power-domains = <&sysc R8A779G0_PD_A3ISP1>;
-			resets = <&cpg 1029>;
-
-			renesas,fcp = <&fcpvx1>;
-		};
-
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts
index 18fd52f55de5..4d890e0617af 100644
--- a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts
+++ b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts
@@ -46,6 +46,8 @@
 		serial0 = &hscif0;
 		serial1 = &hscif2;
 		ethernet0 = &avb0;
+		ethernet1 = &avb1;
+		ethernet2 = &avb2;
 	};
 
 	can_transceiver0: can-phy0 {
@@ -200,17 +202,64 @@
 &avb0 {
 	pinctrl-0 = <&avb0_pins>;
 	pinctrl-names = "default";
-	phy-handle = <&phy0>;
+	phy-handle = <&avb0_phy>;
 	tx-internal-delay-ps = <2000>;
 	status = "okay";
 
-	phy0: ethernet-phy@0 {
-		compatible = "ethernet-phy-id0022.1622",
-			     "ethernet-phy-ieee802.3-c22";
-		rxc-skew-ps = <1500>;
-		reg = <0>;
-		interrupts-extended = <&gpio7 5 IRQ_TYPE_LEVEL_LOW>;
-		reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		avb0_phy: ethernet-phy@0 {
+			compatible = "ethernet-phy-id0022.1622",
+				"ethernet-phy-ieee802.3-c22";
+				rxc-skew-ps = <1500>;
+				reg = <0>;
+				interrupts-extended = <&gpio7 5 IRQ_TYPE_LEVEL_LOW>;
+				reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&avb1 {
+	pinctrl-0 = <&avb1_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&avb1_phy>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reset-gpios = <&gpio6 1 GPIO_ACTIVE_LOW>;
+		reset-post-delay-us = <4000>;
+
+		avb1_phy: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c45";
+			reg = <0>;
+			interrupts-extended = <&gpio6 3 IRQ_TYPE_LEVEL_LOW>;
+		};
+	};
+};
+
+&avb2 {
+	pinctrl-0 = <&avb2_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&avb2_phy>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		reset-gpios = <&gpio5 5 GPIO_ACTIVE_LOW>;
+		reset-post-delay-us = <4000>;
+
+		avb2_phy: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c45";
+			reg = <0>;
+			interrupts-extended = <&gpio5 4 IRQ_TYPE_LEVEL_LOW>;
+		};
 	};
 };
 
@@ -233,25 +282,6 @@
 	};
 };
 
-&dsi0 {
-	status = "okay";
-
-	ports {
-		port@1 {
-			reg = <1>;
-
-			dsi0_out: endpoint {
-				remote-endpoint = <&sn65dsi86_in0>;
-				data-lanes = <1 2 3 4>;
-			};
-		};
-	};
-};
-
-&du {
-	status = "okay";
-};
-
 &csi40 {
 	status = "okay";
 
@@ -292,6 +322,25 @@
 	};
 };
 
+&dsi0 {
+	status = "okay";
+
+	ports {
+		port@1 {
+			reg = <1>;
+
+			dsi0_out: endpoint {
+				remote-endpoint = <&sn65dsi86_in0>;
+				data-lanes = <1 2 3 4>;
+			};
+		};
+	};
+};
+
+&du {
+	status = "okay";
+};
+
 &extal_clk {
 	clock-frequency = <16666666>;
 };
@@ -312,6 +361,7 @@
 &hscif0 {
 	pinctrl-0 = <&hscif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	uart-has-rtscts;
 	status = "okay";
@@ -558,6 +608,56 @@
 		};
 	};
 
+	avb1_pins: avb1 {
+		mux {
+			groups = "avb1_link", "avb1_mdio", "avb1_rgmii",
+				 "avb1_txcrefclk";
+			function = "avb1";
+		};
+
+		link {
+			groups = "avb1_link";
+			bias-disable;
+		};
+
+		mdio {
+			groups = "avb1_mdio";
+			drive-strength = <24>;
+			bias-disable;
+		};
+
+		rgmii {
+			groups = "avb1_rgmii";
+			drive-strength = <24>;
+			bias-disable;
+		};
+	};
+
+	avb2_pins: avb2 {
+		mux {
+			groups = "avb2_link", "avb2_mdio", "avb2_rgmii",
+				 "avb2_txcrefclk";
+			function = "avb2";
+		};
+
+		link {
+			groups = "avb2_link";
+			bias-disable;
+		};
+
+		mdio {
+			groups = "avb2_mdio";
+			drive-strength = <24>;
+			bias-disable;
+		};
+
+		rgmii {
+			groups = "avb2_rgmii";
+			drive-strength = <24>;
+			bias-disable;
+		};
+	};
+
 	can_clk_pins: can-clk {
 		groups = "can_clk";
 		function = "can_clk";
diff --git a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
index d0c01c0fdda2..8524a1e7205e 100644
--- a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
@@ -138,6 +138,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	extalr_clk: extalr-clk {
@@ -145,6 +146,7 @@
 		#clock-cells = <0>;
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
+		bootph-all;
 	};
 
 	pcie0_clkref: pcie0-clkref {
@@ -180,6 +182,8 @@
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
+		bootph-all;
+
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
@@ -201,6 +205,7 @@
 			      <0 0xe6058000 0 0x16c>, <0 0xe6058800 0 0x16c>,
 			      <0 0xe6060000 0 0x16c>, <0 0xe6060800 0 0x16c>,
 			      <0 0xe6061000 0 0x16c>, <0 0xe6061800 0 0x16c>;
+			bootph-all;
 		};
 
 		gpio0: gpio@e6050180 {
@@ -401,11 +406,13 @@
 			#clock-cells = <2>;
 			#power-domain-cells = <0>;
 			#reset-cells = <1>;
+			bootph-all;
 		};
 
 		rst: reset-controller@e6160000 {
 			compatible = "renesas,r8a779h0-rst";
 			reg = <0 0xe6160000 0 0x4000>;
+			bootph-all;
 		};
 
 		sysc: system-controller@e6180000 {
@@ -793,8 +800,6 @@
 			rx-internal-delay-ps = <0>;
 			tx-internal-delay-ps = <0>;
 			iommus = <&ipmmu_hc 0>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -842,8 +847,6 @@
 			rx-internal-delay-ps = <0>;
 			tx-internal-delay-ps = <0>;
 			iommus = <&ipmmu_hc 1>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -891,8 +894,6 @@
 			rx-internal-delay-ps = <0>;
 			tx-internal-delay-ps = <0>;
 			iommus = <&ipmmu_hc 2>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 		};
 
@@ -1908,6 +1909,15 @@
 			resets = <&cpg 508>;
 		};
 
+		fcpvx0: fcp@fedb0000 {
+			compatible = "renesas,fcpv";
+			reg = <0 0xfedb0000 0 0x200>;
+			clocks = <&cpg CPG_MOD 1100>;
+			power-domains = <&sysc R8A779H0_PD_A3ISP0>;
+			resets = <&cpg 1100>;
+			iommus = <&ipmmu_vi1 24>;
+		};
+
 		vspd0: vsp@fea20000 {
 			compatible = "renesas,vsp2";
 			reg = <0 0xfea20000 0 0x8000>;
@@ -1918,6 +1928,17 @@
 			renesas,fcp = <&fcpvd0>;
 		};
 
+		vspx0: vsp@fedd0000 {
+			compatible = "renesas,vsp2";
+			reg = <0 0xfedd0000 0 0x8000>;
+			interrupts = <GIC_SPI 556 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 1028>;
+			power-domains = <&sysc R8A779H0_PD_A3ISP0>;
+			resets = <&cpg 1028>;
+
+			renesas,fcp = <&fcpvx0>;
+		};
+
 		du: display@feb00000 {
 			compatible = "renesas,du-r8a779h0";
 			reg = <0 0xfeb00000 0 0x40000>;
@@ -2144,6 +2165,7 @@
 		prr: chipid@fff00044 {
 			compatible = "renesas,prr";
 			reg = <0 0xfff00044 0 4>;
+			bootph-all;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r9a07g044l2-remi-pi.dts b/arch/arm64/boot/dts/renesas/r9a07g044l2-remi-pi.dts
new file mode 100644
index 000000000000..3267e7b75b58
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r9a07g044l2-remi-pi.dts
@@ -0,0 +1,339 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the MYIR Remi Pi
+ *
+ * Copyright (C) 2022 MYIR Electronics Corp.
+ * Copyright (C) 2025 Collabora Ltd.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
+
+#include "r9a07g044l2.dtsi"
+
+/ {
+	model = "MYIR Tech Limited Remi Pi MYB-YG2LX-REMI";
+	compatible = "myir,remi-pi", "renesas,r9a07g044l2", "renesas,r9a07g044";
+
+	aliases {
+		ethernet0 = &eth0;
+		ethernet1 = &eth1;
+
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+
+		mmc0 = &sdhi0;
+
+		serial0 = &scif0;
+		serial4 = &scif4;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	hdmi-out {
+		compatible = "hdmi-connector";
+		type = "a";
+		ddc-i2c-bus = <&i2c1>;
+
+		port {
+			hdmi_con: endpoint {
+				remote-endpoint = <&lt8912_out>;
+			};
+		};
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x38000000>;
+	};
+
+	reg_1p8v: regulator-1p8v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		vin-supply = <&reg_5p0v>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		vin-supply = <&reg_5p0v>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_5p0v: regulator-5p0v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-5.0V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_1p1v: regulator-vdd-core {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.1V";
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		regulator-always-on;
+	};
+};
+
+&dsi {
+	status = "okay";
+
+	ports {
+		port@1 {
+			dsi_out: endpoint {
+				remote-endpoint = <&lt8912_in>;
+				data-lanes = <1 2 3 4>;
+			};
+		};
+	};
+};
+
+&du {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&eth0 {
+	pinctrl-0 = <&eth0_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy0>;
+	phy-mode = "rgmii-id";
+	status = "okay";
+
+	phy0: ethernet-phy@4 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <4>;
+		interrupts-extended = <&pinctrl RZG2L_GPIO(44, 2) IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&pinctrl RZG2L_GPIO(44, 3) GPIO_ACTIVE_LOW>;
+	};
+};
+
+&eth1 {
+	pinctrl-0 = <&eth1_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy1>;
+	phy-mode = "rgmii-id";
+	status = "okay";
+
+	phy1: ethernet-phy@6 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <6>;
+		interrupts-extended = <&pinctrl RZG2L_GPIO(43, 2) IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&pinctrl RZG2L_GPIO(43, 3) GPIO_ACTIVE_LOW>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <24000000>;
+};
+
+&gpu {
+	mali-supply = <&reg_1p1v>;
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0_pins>;
+	pinctrl-names = "default";
+
+	clock-frequency = <400000>;
+	status = "okay";
+
+	hdmi-bridge@48 {
+		compatible = "lontium,lt8912b";
+		reg = <0x48> ;
+		reset-gpios = <&pinctrl RZG2L_GPIO(42, 2) GPIO_ACTIVE_LOW>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lt8912_in: endpoint {
+					data-lanes = <1 2 3 4>;
+					remote-endpoint = <&dsi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lt8912_out: endpoint {
+					remote-endpoint = <&hdmi_con>;
+				};
+			};
+		};
+	};
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pins>;
+	pinctrl-names = "default";
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-0 = <&i2c2_pins>;
+	pinctrl-names = "default";
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&i2c3 {
+	pinctrl-0 = <&i2c3_pins>;
+	pinctrl-names = "default";
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&mtu3 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&ostm1 {
+	status = "okay";
+};
+
+&ostm2 {
+	status = "okay";
+};
+
+&phyrst {
+	status = "okay";
+};
+
+&pinctrl {
+	eth0_pins: eth0 {
+		pinmux = <RZG2L_PORT_PINMUX(27, 1, 1)>, /* ET0_MDC */
+			 <RZG2L_PORT_PINMUX(28, 0, 1)>, /* ET0_MDIO */
+			 <RZG2L_PORT_PINMUX(20, 0, 1)>, /* ET0_TXC */
+			 <RZG2L_PORT_PINMUX(20, 1, 1)>, /* ET0_TX_CTL */
+			 <RZG2L_PORT_PINMUX(20, 2, 1)>, /* ET0_TXD0 */
+			 <RZG2L_PORT_PINMUX(21, 0, 1)>, /* ET0_TXD1 */
+			 <RZG2L_PORT_PINMUX(21, 1, 1)>, /* ET0_TXD2 */
+			 <RZG2L_PORT_PINMUX(22, 0, 1)>, /* ET0_TXD3 */
+			 <RZG2L_PORT_PINMUX(24, 0, 1)>, /* ET0_RXC */
+			 <RZG2L_PORT_PINMUX(24, 1, 1)>, /* ET0_RX_CTL */
+			 <RZG2L_PORT_PINMUX(25, 0, 1)>, /* ET0_RXD0 */
+			 <RZG2L_PORT_PINMUX(25, 1, 1)>, /* ET0_RXD1 */
+			 <RZG2L_PORT_PINMUX(26, 0, 1)>, /* ET0_RXD2 */
+			 <RZG2L_PORT_PINMUX(26, 1, 1)>; /* ET0_RXD3 */
+	};
+
+	eth1_pins: eth1 {
+		pinmux = <RZG2L_PORT_PINMUX(37, 0, 1)>, /* ET1_MDC */
+			 <RZG2L_PORT_PINMUX(37, 1, 1)>, /* ET1_MDIO */
+			 <RZG2L_PORT_PINMUX(29, 0, 1)>, /* ET1_TXC */
+			 <RZG2L_PORT_PINMUX(29, 1, 1)>, /* ET1_TX_CTL */
+			 <RZG2L_PORT_PINMUX(30, 0, 1)>, /* ET1_TXD0 */
+			 <RZG2L_PORT_PINMUX(30, 1, 1)>, /* ET1_TXD1 */
+			 <RZG2L_PORT_PINMUX(31, 0, 1)>, /* ET1_TXD2 */
+			 <RZG2L_PORT_PINMUX(31, 1, 1)>, /* ET1_TXD3 */
+			 <RZG2L_PORT_PINMUX(33, 1, 1)>, /* ET1_RXC */
+			 <RZG2L_PORT_PINMUX(34, 0, 1)>, /* ET1_RX_CTL */
+			 <RZG2L_PORT_PINMUX(34, 1, 1)>, /* ET1_RXD0 */
+			 <RZG2L_PORT_PINMUX(35, 0, 1)>, /* ET1_RXD1 */
+			 <RZG2L_PORT_PINMUX(35, 1, 1)>, /* ET1_RXD2 */
+			 <RZG2L_PORT_PINMUX(36, 0, 1)>; /* ET1_RXD3 */
+	};
+
+	i2c0_pins: i2c0 {
+		pins = "RIIC0_SDA", "RIIC0_SCL";
+		input-enable;
+	};
+
+	i2c1_pins: i2c1 {
+		pins = "RIIC1_SDA", "RIIC1_SCL";
+		input-enable;
+	};
+
+	i2c2_pins: i2c2 {
+		pinmux = <RZG2L_PORT_PINMUX(3, 0, 2)>, /* SDA */
+			 <RZG2L_PORT_PINMUX(3, 1, 2)>; /* SCL */
+	};
+
+	i2c3_pins: i2c3 {
+		pinmux = <RZG2L_PORT_PINMUX(18, 0, 3)>, /* SDA */
+			 <RZG2L_PORT_PINMUX(18, 1, 3)>; /* SCL */
+	};
+
+	scif0_pins: scif0 {
+		pinmux = <RZG2L_PORT_PINMUX(38, 0, 1)>, /* TxD */
+			 <RZG2L_PORT_PINMUX(38, 1, 1)>; /* RxD */
+	};
+
+	scif4_pins: scif4 {
+		pinmux = <RZG2L_PORT_PINMUX(2, 0, 5)>, /* TxD */
+			 <RZG2L_PORT_PINMUX(2, 1, 5)>; /* RxD */
+	};
+
+	sdhi0_pins: sd0 {
+		sd0-ctrl {
+			pins = "SD0_CLK", "SD0_CMD";
+			power-source = <1800>;
+		};
+
+		sd0-data {
+			pins = "SD0_DATA0", "SD0_DATA1", "SD0_DATA2", "SD0_DATA3",
+			       "SD0_DATA4", "SD0_DATA5", "SD0_DATA6", "SD0_DATA7";
+			power-source = <1800>;
+		};
+
+		sd0-rst {
+			pins = "SD0_RST#";
+			power-source = <1800>;
+		};
+	};
+};
+
+&scif0 {
+	pinctrl-0 = <&scif0_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&scif4 {
+	pinctrl-0 = <&scif4_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&sdhi0 {
+	pinctrl-0 = <&sdhi0_pins>;
+	pinctrl-1 = <&sdhi0_pins>;
+	pinctrl-names = "default", "state_uhs";
+
+	vmmc-supply = <&reg_3p3v>;
+	vqmmc-supply = <&reg_1p8v>;
+	bus-width = <8>;
+	mmc-hs200-1_8v;
+	non-removable;
+	fixed-emmc-driver-type = <1>;
+	status = "okay";
+};
+
+&usb2_phy1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
index a9b98db9ef95..0364f89776e6 100644
--- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
@@ -28,6 +28,33 @@
 		clock-frequency = <0>;
 	};
 
+	cluster0_opp: opp-table-0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp-137500000 {
+			opp-hz = /bits/ 64 <137500000>;
+			opp-microvolt = <940000>;
+			clock-latency-ns = <300000>;
+		};
+		opp-275000000 {
+			opp-hz = /bits/ 64 <275000000>;
+			opp-microvolt = <940000>;
+			clock-latency-ns = <300000>;
+		};
+		opp-550000000 {
+			opp-hz = /bits/ 64 <550000000>;
+			opp-microvolt = <940000>;
+			clock-latency-ns = <300000>;
+		};
+		opp-1100000000 {
+			opp-hz = /bits/ 64 <1100000000>;
+			opp-microvolt = <940000>;
+			clock-latency-ns = <300000>;
+			opp-suspend;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -40,6 +67,7 @@
 			next-level-cache = <&L3_CA55>;
 			enable-method = "psci";
 			clocks = <&cpg CPG_CORE R9A08G045_CLK_I>;
+			operating-points-v2 = <&cluster0_opp>;
 		};
 
 		L3_CA55: cache-controller-0 {
@@ -443,7 +471,6 @@
 				     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "lpm_int", "ca55stbydone_int",
 					  "cm33stbyr_int", "ca55_deny";
-			status = "disabled";
 		};
 
 		pinctrl: pinctrl@11030000 {
diff --git a/arch/arm64/boot/dts/renesas/r9a08g045s33-smarc-pmod1-type-3a.dtso b/arch/arm64/boot/dts/renesas/r9a08g045s33-smarc-pmod1-type-3a.dtso
new file mode 100644
index 000000000000..4a81e3a3c8bd
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r9a08g045s33-smarc-pmod1-type-3a.dtso
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the RZ/G3S SMARC Carrier II EVK PMOD parts
+ *
+ * Copyright (C) 2024 Renesas Electronics Corp.
+ *
+ *
+ * [Connection]
+ *
+ * SMARC Carrier II EVK
+ * +--------------------------------------------+
+ * |PMOD1_3A (PMOD1 PIN HEADER)			|
+ * |	SCIF1_CTS# (pin1)  (pin7)  PMOD1_GPIO10	|
+ * |	SCIF1_TXD  (pin2)  (pin8)  PMOD1_GPIO11	|
+ * |	SCIF1_RXD  (pin3)  (pin9)  PMOD1_GPIO12	|
+ * |	SCIF1_RTS# (pin4)  (pin10) PMOD1_GPIO13	|
+ * |	GND	   (pin5)  (pin11) GND		|
+ * |	PWR_PMOD1  (pin6)  (pin12) GND		|
+ * +--------------------------------------------+
+ *
+ * The following switches should be set as follows for SCIF1:
+ * - SW_CONFIG2:  ON
+ * - SW_OPT_MUX4: ON
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
+#include "rzg3s-smarc-switches.h"
+
+&pinctrl {
+	scif1_pins: scif1-pins {
+		pinmux = <RZG2L_PORT_PINMUX(14, 0, 1)>, /* TXD */
+			 <RZG2L_PORT_PINMUX(14, 1, 1)>, /* RXD */
+			 <RZG2L_PORT_PINMUX(16, 0, 1)>, /* CTS# */
+			 <RZG2L_PORT_PINMUX(16, 1, 1)>; /* RTS# */
+	};
+};
+
+#if SW_CONFIG3 == SW_ON && SW_OPT_MUX4 == SW_ON
+&scif1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&scif1_pins>;
+	uart-has-rtscts;
+	status = "okay";
+};
+#endif
diff --git a/arch/arm64/boot/dts/renesas/r9a09g047.dtsi b/arch/arm64/boot/dts/renesas/r9a09g047.dtsi
index 200e9ea89193..c93aa16d0a6e 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g047.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g047.dtsi
@@ -154,6 +154,13 @@
 			#power-domain-cells = <0>;
 		};
 
+		sys: system-controller@10430000 {
+			compatible = "renesas,r9a09g047-sys";
+			reg = <0 0x10430000 0 0x10000>;
+			clocks = <&cpg CPG_CORE R9A09G047_SYS_0_PCLK>;
+			resets = <&cpg 0x30>;
+		};
+
 		scif0: serial@11c01400 {
 			compatible = "renesas,scif-r9a09g047", "renesas,scif-r9a09g057";
 			reg = <0 0x11c01400 0 0x400>;
@@ -175,6 +182,36 @@
 			status = "disabled";
 		};
 
+		wdt1: watchdog@14400000 {
+			compatible = "renesas,r9a09g047-wdt", "renesas,r9a09g057-wdt";
+			reg = <0 0x14400000 0 0x400>;
+			clocks = <&cpg CPG_MOD 0x4d>, <&cpg CPG_MOD 0x4e>;
+			clock-names = "pclk", "oscclk";
+			resets = <&cpg 0x76>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		wdt2: watchdog@13000000 {
+			compatible = "renesas,r9a09g047-wdt", "renesas,r9a09g057-wdt";
+			reg = <0 0x13000000 0 0x400>;
+			clocks = <&cpg CPG_MOD 0x4f>, <&cpg CPG_MOD 0x50>;
+			clock-names = "pclk", "oscclk";
+			resets = <&cpg 0x77>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		wdt3: watchdog@13000400 {
+			compatible = "renesas,r9a09g047-wdt", "renesas,r9a09g057-wdt";
+			reg = <0 0x13000400 0 0x400>;
+			clocks = <&cpg CPG_MOD 0x51>, <&cpg CPG_MOD 0x52>;
+			clock-names = "pclk", "oscclk";
+			resets = <&cpg 0x78>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
 		i2c0: i2c@14400400 {
 			compatible = "renesas,riic-r9a09g047", "renesas,riic-r9a09g057";
 			reg = <0 0x14400400 0 0x400>;
diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
index 1c550b22b164..0cd00bb05191 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
@@ -105,6 +105,35 @@
 		};
 	};
 
+	gpu_opp_table: opp-table-1 {
+		compatible = "operating-points-v2";
+
+		opp-630000000 {
+			opp-hz = /bits/ 64 <630000000>;
+			opp-microvolt = <800000>;
+		};
+
+		opp-315000000 {
+			opp-hz = /bits/ 64 <315000000>;
+			opp-microvolt = <800000>;
+		};
+
+		opp-157500000 {
+			opp-hz = /bits/ 64 <157500000>;
+			opp-microvolt = <800000>;
+		};
+
+		opp-78750000 {
+			opp-hz = /bits/ 64 <78750000>;
+			opp-microvolt = <800000>;
+		};
+
+		opp-19687500 {
+			opp-hz = /bits/ 64 <19687500>;
+			opp-microvolt = <800000>;
+		};
+	};
+
 	psci {
 		compatible = "arm,psci-1.0", "arm,psci-0.2";
 		method = "smc";
@@ -249,7 +278,6 @@
 			reg = <0 0x10430000 0 0x10000>;
 			clocks = <&cpg CPG_CORE R9A09G057_SYS_0_PCLK>;
 			resets = <&cpg 0x30>;
-			status = "disabled";
 		};
 
 		ostm0: timer@11800000 {
@@ -582,6 +610,28 @@
 			status = "disabled";
 		};
 
+		gpu: gpu@14850000 {
+			compatible = "renesas,r9a09g057-mali",
+				     "arm,mali-bifrost";
+			reg = <0x0 0x14850000 0x0 0x10000>;
+			interrupts = <GIC_SPI 884 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 885 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 883 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 886 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "job", "mmu", "gpu", "event";
+			clocks = <&cpg CPG_MOD 0xf0>,
+				 <&cpg CPG_MOD 0xf1>,
+				 <&cpg CPG_MOD 0xf2>;
+			clock-names = "gpu", "bus", "bus_ace";
+			power-domains = <&cpg>;
+			resets = <&cpg 0xdd>,
+				 <&cpg 0xde>,
+				 <&cpg 0xdf>;
+			reset-names = "rst", "axi_rst", "ace_rst";
+			operating-points-v2 = <&gpu_opp_table>;
+			status = "disabled";
+		};
+
 		gic: interrupt-controller@14900000 {
 			compatible = "arm,gic-v3";
 			reg = <0x0 0x14900000 0 0x20000>,
diff --git a/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts b/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts
index 0b705c987b6c..063eca0ba3e2 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts
+++ b/arch/arm64/boot/dts/renesas/r9a09g057h44-rzv2h-evk.dts
@@ -43,6 +43,16 @@
 		reg = <0x2 0x40000000 0x2 0x00000000>;
 	};
 
+	reg_0p8v: regulator0 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "fixed-0.8V";
+		regulator-min-microvolt = <800000>;
+		regulator-max-microvolt = <800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
 	reg_3p3v: regulator1 {
 		compatible = "regulator-fixed";
 
@@ -68,6 +78,11 @@
 	clock-frequency = <22579200>;
 };
 
+&gpu {
+	status = "okay";
+	mali-supply = <&reg_0p8v>;
+};
+
 &i2c0 {
 	pinctrl-0 = <&i2c0_pins>;
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/renesas/r9a09g057h48-kakip.dts b/arch/arm64/boot/dts/renesas/r9a09g057h48-kakip.dts
new file mode 100644
index 000000000000..d2586d278769
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r9a09g057h48-kakip.dts
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for Yuridenki-Shokai the Kakip board
+ *
+ * Copyright (C) 2024 Nobuhiro Iwamatsu <iwamatsu@nigauri.org>
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/pinctrl/renesas,r9a09g057-pinctrl.h>
+#include <dt-bindings/gpio/gpio.h>
+#include "r9a09g057.dtsi"
+
+/ {
+	model = "Yuridenki-Shokai Kakip Board based on r9a09g057h48";
+	compatible = "yuridenki,kakip", "renesas,r9a09g057h48", "renesas,r9a09g057";
+
+	aliases {
+		serial0 = &scif;
+		mmc0 = &sdhi0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x1 0xF8000000>;
+	};
+
+	reg_3p3v: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	vqmmc_sdhi0: regulator-vccq-sdhi0 {
+		compatible = "regulator-gpio";
+		regulator-name = "SDHI0 VccQ";
+		gpios = <&pinctrl RZV2H_GPIO(A, 0) GPIO_ACTIVE_HIGH>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		gpios-states = <0>;
+		states = <3300000 0>, <1800000 1>;
+	};
+};
+
+&ostm0 {
+	status = "okay";
+};
+
+&ostm1 {
+	status = "okay";
+};
+
+&ostm2 {
+	status = "okay";
+};
+
+&ostm3 {
+	status = "okay";
+};
+
+&ostm4 {
+	status = "okay";
+};
+
+&ostm5 {
+	status = "okay";
+};
+
+&ostm6 {
+	status = "okay";
+};
+
+&ostm7 {
+	status = "okay";
+};
+
+&pinctrl {
+	scif_pins: scif {
+		pins =  "SCIF_RXD", "SCIF_TXD";
+	};
+
+	sd0-pwr-en-hog {
+		gpio-hog;
+		gpios = <RZV2H_GPIO(A, 1) GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "sd0_pwr_en";
+	};
+
+	sdhi0_pins: sd0 {
+		sd0-clk {
+			pins = "SD0CLK";
+			renesas,output-impedance = <3>;
+			slew-rate = <0>;
+		};
+
+		sd0-data {
+			pins = "SD0DAT0", "SD0DAT1", "SD0DAT2", "SD0DAT3", "SD0CMD";
+			input-enable;
+			renesas,output-impedance = <3>;
+			slew-rate = <0>;
+		};
+
+		sd0-mux {
+			pinmux = <RZV2H_PORT_PINMUX(A, 5, 15)>; /* SD0_CD */
+		};
+	};
+};
+
+&qextal_clk {
+	clock-frequency = <24000000>;
+};
+
+&scif {
+	pinctrl-0 = <&scif_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&sdhi0 {
+	pinctrl-0 = <&sdhi0_pins>;
+	pinctrl-names = "default";
+	vmmc-supply = <&reg_3p3v>;
+	vqmmc-supply = <&vqmmc_sdhi0>;
+	bus-width = <4>;
+
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi
index 6b583ae2ac52..f4ba050beb0d 100644
--- a/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3e-smarc-som.dtsi
@@ -26,3 +26,7 @@
 &rtxin_clk {
 	clock-frequency = <32768>;
 };
+
+&wdt1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
index ef12c1c462a7..39845faec894 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
@@ -9,25 +9,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
 
-/*
- * On-board switches' states:
- * @SW_OFF: switch's state is OFF
- * @SW_ON:  switch's state is ON
- */
-#define SW_OFF		0
-#define SW_ON		1
-
-/*
- * SW_CONFIG[x] switches' states:
- * @SW_CONFIG2:
- *	SW_OFF - SD0 is connected to eMMC
- *	SW_ON  - SD0 is connected to uSD0 card
- * @SW_CONFIG3:
- *	SW_OFF - SD2 is connected to SoC
- *	SW_ON  - SCIF1, SSI0, IRQ0, IRQ1 connected to SoC
- */
-#define SW_CONFIG2	SW_OFF
-#define SW_CONFIG3	SW_ON
+#include "rzg3s-smarc-switches.h"
 
 / {
 	compatible = "renesas,rzg3s-smarcm", "renesas,r9a08g045s33", "renesas,r9a08g045";
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-switches.h b/arch/arm64/boot/dts/renesas/rzg3s-smarc-switches.h
new file mode 100644
index 000000000000..bbf908a5322c
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-switches.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * On-board switches for the Renesas RZ/G3S SMARC Module and RZ SMARC Carrier II
+ * boards.
+ *
+ * Copyright (C) 2024 Renesas Electronics Corp.
+ */
+
+#ifndef __RZG3S_SMARC_SWITCHES_H__
+#define __RZG3S_SMARC_SWITCHES_H__
+
+/*
+ * On-board switches' states:
+ * @SW_OFF: switch's state is OFF
+ * @SW_ON:  switch's state is ON
+ */
+#define SW_OFF		0
+#define SW_ON		1
+
+/*
+ * SW_CONFIG[x] switches' states:
+ * @SW_CONFIG2:
+ *	SW_OFF - SD0 is connected to eMMC
+ *	SW_ON  - SD0 is connected to uSD0 card
+ * @SW_CONFIG3:
+ *	SW_OFF - SD2 is connected to SoC
+ *	SW_ON  - SCIF1, SSI0, IRQ0, IRQ1 connected to SoC
+ */
+#define SW_CONFIG2	SW_OFF
+#define SW_CONFIG3	SW_ON
+
+/*
+ * SW_OPT_MUX[x] switches' states:
+ * @SW_OPT_MUX4:
+ *	SW_OFF - The SMARC SER0 signals are routed to M.2 Key E UART
+ *	SW_ON  - The SMARC SER0 signals are routed to PMOD1
+ */
+#define SW_OPT_MUX4	SW_ON
+
+#endif /* __RZG3S_SMARC_SWITCHES_H__ */
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
index 81b4ffd1417d..5e044a4d0234 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
@@ -12,6 +12,8 @@
 / {
 	aliases {
 		i2c0 = &i2c0;
+		serial0 = &scif1;
+		serial1 = &scif3;
 		serial3 = &scif0;
 		mmc1 = &sdhi1;
 	};
@@ -162,6 +164,11 @@
 			 <RZG2L_PORT_PINMUX(6, 4, 1)>; /* TXD */
 	};
 
+	scif3_pins: scif3 {
+		pinmux = <RZG2L_PORT_PINMUX(17, 2, 7)>, /* RXD */
+			 <RZG2L_PORT_PINMUX(17, 3, 7)>; /* TXD */
+	};
+
 	sdhi1_pins: sd1 {
 		data {
 			pins = "SD1_DATA0", "SD1_DATA1", "SD1_DATA2", "SD1_DATA3";
@@ -208,6 +215,12 @@
 	status = "okay";
 };
 
+&scif3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&scif3_pins>;
+	status = "okay";
+};
+
 &sdhi1 {
 	pinctrl-0 = <&sdhi1_pins>;
 	pinctrl-1 = <&sdhi1_pins_uhs>;
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index 06c7e9746304..68971c870d17 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -940,6 +940,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card-mix+split.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card-mix+split.dtsi
index 8ae6af1af094..4caa0281a687 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card-mix+split.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card-mix+split.dtsi
@@ -15,7 +15,9 @@
  *	(D) CPU3 (2ch)  --/			   (TDM-1 : 2,3ch)
  *	(E) CPU4 (2ch)  --/			   (TDM-2 : 4,5ch)
  *	(F) CPU5 (2ch)  --/			   (TDM-3 : 6,7ch)
- *	(G) CPU6 (6ch) <----  (6ch) (Z) PCM3168A-c
+ *	(G) CPU6 (2ch) <----  (6ch) (Z) PCM3168A-c (TDM-a: 0,1ch)
+ *	(H) CPU7 (2ch) <--/			   (TDM-b: 2,3ch)
+ *	(I) CPU8 (2ch) <--/			   (TDM-c: 4,5ch)
  *
  *	(A) aplay   -D plughw:0,0 xxx.wav (MIX-0)
  *	(B) aplay   -D plughw:0,1 xxx.wav (MIX-1)
@@ -25,7 +27,9 @@
  *	(F) aplay   -D plughw:1,3 xxx.wav (TDM-3)
  *
  *	(A) arecord -D plughw:0,0 xxx.wav
- *	(G) arecord -D plughw:1,4 xxx.wav
+ *	(G) arecord -D plughw:1,4 xxx.wav (TDM-a)
+ *	(H) arecord -D plughw:1,5 xxx.wav (TDM-b)
+ *	(I) arecord -D plughw:1,6 xxx.wav (TDM-c)
  */
 / {
 	sound_card_kf: expand-sound {
@@ -35,13 +39,18 @@
 		routing = "pcm3168a Playback", "DAI2 Playback",
 			  "pcm3168a Playback", "DAI3 Playback",
 			  "pcm3168a Playback", "DAI4 Playback",
-			  "pcm3168a Playback", "DAI5 Playback";
+			  "pcm3168a Playback", "DAI5 Playback",
+			  "DAI6 Capture", "pcm3168a Capture",
+			  "DAI7 Capture", "pcm3168a Capture",
+			  "DAI8 Capture", "pcm3168a Capture";
 
 		dais = <&snd_kf1 /* (C) CPU2 */
 			&snd_kf2 /* (D) CPU3 */
 			&snd_kf3 /* (E) CPU4 */
 			&snd_kf4 /* (F) CPU5 */
-			&snd_kf5 /* (G) GPU6 */
+			&snd_kf5 /* (G) CPU6 */
+			&snd_kf6 /* (H) CPU7 */
+			&snd_kf7 /* (I) CPU8 */
 		>;
 	};
 };
@@ -50,7 +59,9 @@
 	ports {
 		#address-cells = <1>;
 		#size-cells = <0>;
+
 		mclk-fs = <512>;
+		prefix = "pcm3168a";
 
 		/*
 		 * (Y) PCM3168A-p
@@ -59,7 +70,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0>;
-			prefix = "pcm3168a";
 			convert-channels = <8>; /* to 8ch TDM */
 
 			/* (C) CPU2 -> (Y) PCM3168A-p */
@@ -91,10 +101,28 @@
 		 * (Z) PCM3168A-c
 		 */
 		port@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
 			reg = <1>;
+
+			convert-channels = <6>; /* to 6ch TDM */
+
 			/* (G) CPU6 <- PCM3168A-c */
-			pcm3168a_endpoint_c: endpoint {
-				remote-endpoint = <&rsnd_for_pcm3168a_capture>;
+			pcm3168a_endpoint_c1: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&rsnd_for_pcm3168a_capture1>;
+				clocks = <&clksndsel>;
+			};
+			/* (H) CPU7 <- PCM3168A-c */
+			pcm3168a_endpoint_c2: endpoint@1 {
+				reg = <1>;
+				remote-endpoint = <&rsnd_for_pcm3168a_capture2>;
+				clocks = <&clksndsel>;
+			};
+			/* (I) CPU8 <- PCM3168A-c */
+			pcm3168a_endpoint_c3: endpoint@2 {
+				reg = <2>;
+				remote-endpoint = <&rsnd_for_pcm3168a_capture3>;
 				clocks = <&clksndsel>;
 			};
 		};
@@ -160,12 +188,35 @@
 		 */
 		snd_kf5: port@6 {
 			reg = <6>;
-			rsnd_for_pcm3168a_capture: endpoint {
-				remote-endpoint = <&pcm3168a_endpoint_c>;
+			rsnd_for_pcm3168a_capture1: endpoint {
+				remote-endpoint = <&pcm3168a_endpoint_c1>;
+				bitclock-master;
+				frame-master;
+				capture = <&ssiu40 &ssi4>;
+			};
+		};
+		/*
+		 * (H) CPU7
+		 */
+		snd_kf6: port@7 {
+			reg = <7>;
+			rsnd_for_pcm3168a_capture2: endpoint {
+				remote-endpoint = <&pcm3168a_endpoint_c2>;
+				bitclock-master;
+				frame-master;
+				capture = <&ssiu41 &ssi4>;
+			};
+		};
+		/*
+		 * (I) CPU8
+		 */
+		snd_kf7: port@8 {
+			reg = <8>;
+			rsnd_for_pcm3168a_capture3: endpoint {
+				remote-endpoint = <&pcm3168a_endpoint_c3>;
 				bitclock-master;
 				frame-master;
-				dai-tdm-slot-num = <6>;
-				capture  = <&ssi4>;
+				capture = <&ssiu42 &ssi4>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card2-mix+split.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card2-mix+split.dtsi
index 4cf632bc4621..67a0057a3383 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card2-mix+split.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf-audio-graph-card2-mix+split.dtsi
@@ -15,7 +15,9 @@
  *	(D) CPU2 (2ch)  --/			   (TDM-1 : 2,3ch)
  *	(E) CPU4 (2ch)  --/			   (TDM-2 : 4,5ch)
  *	(F) CPU5 (2ch)  --/			   (TDM-3 : 6,7ch)
- *	(G) CPU6 (6ch) <----  (6ch) (Z)	PCM3168A-c
+ *	(G) CPU6 (2ch) <----  (6ch) (Z) PCM3168A-c (TDM-a: 0,1ch)
+ *	(H) CPU7 (2ch) <--/			   (TDM-b: 2,3ch)
+ *	(I) CPU8 (2ch) <--/			   (TDM-c: 4,5ch)
  *
  *	(A) aplay   -D plughw:0,0 xxx.wav (MIX-0)
  *	(B) aplay   -D plughw:0,1 xxx.wav (MIX-1)
@@ -25,7 +27,9 @@
  *	(F) aplay   -D plughw:1,3 xxx.wav (TDM-3)
  *
  *	(A) arecord -D plughw:0,0 xxx.wav
- *	(G) arecord -D plughw:1,4 xxx.wav
+ *	(G) arecord -D plughw:1,4 xxx.wav (TDM-a)
+ *	(H) arecord -D plughw:1,5 xxx.wav (TDM-b)
+ *	(I) arecord -D plughw:1,6 xxx.wav (TDM-c)
  */
 / {
 	sound_card_kf: expand-sound {
@@ -36,19 +40,25 @@
 			  "pcm3168a Playback", "DAI3 Playback",
 			  "pcm3168a Playback", "DAI4 Playback",
 			  "pcm3168a Playback", "DAI5 Playback",
-			  "DAI6 Capture",      "pcm3168a Capture";
+			  "DAI6 Capture",      "pcm3168a Capture",
+			  "DAI7 Capture",      "pcm3168a Capture",
+			  "DAI8 Capture",      "pcm3168a Capture";
 
 		links = <&fe_c		/* (C) CPU2	  */
 			 &fe_d		/* (D) CPU3	  */
 			 &fe_e		/* (E) CPU4	  */
 			 &fe_f		/* (F) CPU5	  */
-			 &rsnd_g	/* (G) CPU6	  */
+			 &fe_g		/* (G) CPU6	  */
+			 &fe_h		/* (H) CPU7	  */
+			 &fe_i		/* (I) CPU8	  */
 			 &be_y		/* (Y) PCM3168A-p */
+			 &be_z		/* (Z) PCM3168A-c */
 		>;
 
-		dpcm {
+		dpcm: dpcm {
 			#address-cells = <1>;
 			#size-cells = <0>;
+			non-supplier;
 
 			ports@0 {
 				#address-cells = <1>;
@@ -62,21 +72,32 @@
 				 * (D) CPU3
 				 * (E) CPU4
 				 * (F) CPU5
+				 * (G) CPU6
+				 * (H) CPU7
+				 * (I) CPU8
 				 */
 			fe_c:	port@2 { reg = <2>; fe_c_ep: endpoint { remote-endpoint = <&rsnd_c_ep>; }; };
 			fe_d:	port@3 { reg = <3>; fe_d_ep: endpoint { remote-endpoint = <&rsnd_d_ep>; }; };
 			fe_e:	port@4 { reg = <4>; fe_e_ep: endpoint { remote-endpoint = <&rsnd_e_ep>; }; };
 			fe_f:	port@5 { reg = <5>; fe_f_ep: endpoint { remote-endpoint = <&rsnd_f_ep>; }; };
+
+			fe_g:	port@6 { reg = <6>; fe_g_ep: endpoint { remote-endpoint = <&rsnd_g_ep>; }; };
+			fe_h:	port@7 { reg = <7>; fe_h_ep: endpoint { remote-endpoint = <&rsnd_h_ep>; }; };
+			fe_i:	port@8 { reg = <8>; fe_i_ep: endpoint { remote-endpoint = <&rsnd_i_ep>; }; };
 			};
 
 			ports@1 {
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <1>;
 				/*
 				 * BE
 				 *
 				 * (Y) PCM3168A-p
+				 * (Z) PCM3168A-c
 				 */
-			be_y:	port { be_y_ep: endpoint { remote-endpoint = <&pcm3168a_y_ep>; }; };
+			be_y:	port@0 { reg = <0>; be_y_ep: endpoint { remote-endpoint = <&pcm3168a_y_ep>; }; };
+			be_z:	port@1 { reg = <1>; be_z_ep: endpoint { remote-endpoint = <&pcm3168a_z_ep>; }; };
 			};
 		};
 	};
@@ -106,8 +127,9 @@
 		 */
 		port@1 {
 			reg = <1>;
+			convert-channels = <6>; /* to 6ch TDM */
 			pcm3168a_z_ep: endpoint {
-				remote-endpoint = <&rsnd_g_ep>;
+				remote-endpoint = <&be_z_ep>;
 				clocks = <&clksndsel>;
 			};
 		};
@@ -171,13 +193,37 @@
 		/*
 		 * (G) CPU6
 		 */
-		rsnd_g: port@6 {
+		port@6 {
 			reg = <6>;
 			rsnd_g_ep: endpoint {
-				remote-endpoint = <&pcm3168a_z_ep>;
+				remote-endpoint = <&fe_g_ep>;
+				bitclock-master;
+				frame-master;
+				capture = <&ssiu40 &ssi4>;
+			};
+		};
+		/*
+		 * (H) CPU7
+		 */
+		port@7 {
+			reg = <7>;
+			rsnd_h_ep: endpoint {
+				remote-endpoint = <&fe_h_ep>;
+				bitclock-master;
+				frame-master;
+				capture = <&ssiu41 &ssi4>;
+			};
+		};
+		/*
+		 * (I) CPU8
+		 */
+		port@8 {
+			reg = <8>;
+			rsnd_i_ep: endpoint {
+				remote-endpoint = <&fe_i_ep>;
 				bitclock-master;
 				frame-master;
-				capture = <&ssi4>;
+				capture = <&ssiu42 &ssi4>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf-simple-audio-card-mix+split.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf-simple-audio-card-mix+split.dtsi
index f01d91aaadf3..fd75801c329e 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf-simple-audio-card-mix+split.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf-simple-audio-card-mix+split.dtsi
@@ -15,7 +15,9 @@
  *	(D) CPU2 (2ch)  --/			   (TDM-1 : 2,3ch)
  *	(E) CPU4 (2ch)  --/			   (TDM-2 : 4,5ch)
  *	(F) CPU5 (2ch)  --/			   (TDM-3 : 6,7ch)
- *	(G) CPU6 (6ch) <----  (6ch) (Z)	PCM3168A-c
+ *	(G) CPU6 (2ch) <----  (6ch) (Z) PCM3168A-c (TDM-a: 0,1ch)
+ *	(H) CPU7 (2ch) <--/			   (TDM-b: 2,3ch)
+ *	(I) CPU8 (2ch) <--/			   (TDM-c: 4,5ch)
  *
  *	(A) aplay   -D plughw:0,0 xxx.wav (MIX-0)
  *	(B) aplay   -D plughw:0,1 xxx.wav (MIX-1)
@@ -25,7 +27,9 @@
  *	(F) aplay   -D plughw:1,3 xxx.wav (TDM-3)
  *
  *	(A) arecord -D plughw:0,0 xxx.wav
- *	(G) arecord -D plughw:1,4 xxx.wav
+ *	(G) arecord -D plughw:1,4 xxx.wav (TDM-a)
+ *	(H) arecord -D plughw:1,5 xxx.wav (TDM-b)
+ *	(I) arecord -D plughw:1,6 xxx.wav (TDM-c)
  */
 
 / {
@@ -39,7 +43,10 @@
 		simple-audio-card,routing = "pcm3168a Playback", "DAI2 Playback",
 					    "pcm3168a Playback", "DAI3 Playback",
 					    "pcm3168a Playback", "DAI4 Playback",
-					    "pcm3168a Playback", "DAI5 Playback";
+					    "pcm3168a Playback", "DAI5 Playback",
+					    "DAI6 Capture",      "pcm3168a Capture",
+					    "DAI7 Capture",      "pcm3168a Capture",
+					    "DAI8 Capture",      "pcm3168a Capture";
 
 		simple-audio-card,dai-link@0 {
 			#address-cells = <1>;
@@ -88,16 +95,40 @@
 		};
 
 		simple-audio-card,dai-link@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
 			reg = <1>;
+			convert-channels = <6>; /* to 6ch TDM */
+
 			/*
 			 * (G) CPU6
 			 */
-			cpu {
+			cpu@0 {
+				reg = <0>;
 				bitclock-master;
 				frame-master;
 				sound-dai = <&rcar_sound 6>;
 			};
 			/*
+			 * (H) CPU7
+			 */
+			cpu@1 {
+				reg = <1>;
+				bitclock-master;
+				frame-master;
+				sound-dai = <&rcar_sound 7>;
+			};
+			/*
+			 * (I) CPU8
+			 */
+			cpu@2 {
+				reg = <2>;
+				bitclock-master;
+				frame-master;
+				sound-dai = <&rcar_sound 8>;
+			};
+
+			/*
 			 * (Z) PCM3168A-c
 			 */
 			codec {
@@ -151,7 +182,19 @@
 		 * (G) CPU6
 		 */
 		dai6 {
-			capture = <&ssi4>;
+			capture = <&ssiu40 &ssi4>;
+		};
+		/*
+		 * (H) CPU7
+		 */
+		dai7 {
+			capture = <&ssiu41 &ssi4>;
+		};
+		/*
+		 * (I) CPU8
+		 */
+		dai8 {
+			capture = <&ssiu42 &ssi4>;
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index 0c58d816c375..fcab957b54f7 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -448,6 +448,7 @@
 &scif2 {
 	pinctrl-0 = <&scif2_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi
index f24814d7c924..b4024e85ae5a 100644
--- a/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi
@@ -201,6 +201,7 @@
 &hscif0 {
 	pinctrl-0 = <&hscif0_pins>;
 	pinctrl-names = "default";
+	bootph-all;
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi
index 9017c4475a7c..a5d1c1008e7e 100644
--- a/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi
+++ b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi
@@ -21,7 +21,9 @@
 				bus-type = <MEDIA_BUS_TYPE_CSI2_CPHY>;
 				clock-lanes = <0>;
 				data-lanes = <1 2 3>;
-				line-orders = <0 3 0>;
+				line-orders = <MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ABC
+					       MEDIA_BUS_CSI2_CPHY_LINE_ORDER_BCA
+					       MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ABC>;
 				remote-endpoint = <&max96712_out0>;
 			};
 		};
@@ -42,7 +44,9 @@
 				bus-type = <MEDIA_BUS_TYPE_CSI2_CPHY>;
 				clock-lanes = <0>;
 				data-lanes = <1 2 3>;
-				line-orders = <0 3 0>;
+				line-orders = <MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ABC
+					       MEDIA_BUS_CSI2_CPHY_LINE_ORDER_BCA
+					       MEDIA_BUS_CSI2_CPHY_LINE_ORDER_ABC>;
 				remote-endpoint = <&max96712_out1>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile
index def1222c1907..3e8771ef69ba 100644
--- a/arch/arm64/boot/dts/rockchip/Makefile
+++ b/arch/arm64/boot/dts/rockchip/Makefile
@@ -5,6 +5,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-engicam-px30-core-ctouch2-of10.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-engicam-px30-core-edimm2.2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-firefly-jd4-core-mb.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-ringneck-haikou.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-ringneck-haikou-lvds-9904379.dtbo
+dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-ringneck-haikou-video-demo.dtbo
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3308-bpi-p2-pro.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3308-evb.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3308-roc-cc.dtb
@@ -61,6 +63,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-orangepi.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-pinebook-pro.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-pinephone-pro.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-puma-haikou.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-puma-haikou-video-demo.dtbo
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-roc-pc.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-roc-pc-mezzanine.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-roc-pc-plus.dtb
@@ -122,6 +125,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-mecsbc.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-nanopi-r5c.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-nanopi-r5s.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-odroid-m1.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-photonicat.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-qnap-ts433.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-radxa-e25.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-roc-pc.dtb
@@ -132,6 +136,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5-display-vz.dtbo
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5-io-expander.dtbo
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-armsom-sige5.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-evb1-v10.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-roc-pc.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3576-rock-4d.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3582-radxa-e52c.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-armsom-sige7.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-armsom-w3.dtb
@@ -145,11 +151,14 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-firefly-itx-3588j.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-friendlyelec-cm3588-nas.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-h96-max-v58.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar-pre-ict-tester.dtbo
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-mnt-reform2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6-lts.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-ok3588-c.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-max.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-plus.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-ultra.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-quartzpro64.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5-itx.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5b.dtb
@@ -170,3 +179,57 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-orangepi-5.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-orangepi-5b.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-rock-5a.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-rock-5c.dtb
+
+# Overlay application tests
+#
+# A .dtbo must have its own
+#
+#  dtb-$(CONFIG_ARCH_ROCKCHIP) += <overlay>.dtbo
+#
+# entry, and at least one overlay application test reflecting a possible
+# hardware combination in real life:
+#
+#  dtb-$(CONFIG_ARCH_ROCKCHIP) += <overlay-application-test>.dtb
+#  <overlay-application-test>-dtbs := <base>.dtb <overlay-1>.dtbo [<overlay-2>.dtbo ...]
+#
+# This will make the <base>.dtb have symbols (like when DTC_FLAGS has -@ passed)
+# and generate a new DTB (<overlay-application-test>.dtb) which is the
+# result of the application of <overlay-1>.dtbo and other listed overlays on top
+# of <base>.dtb.
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-ringneck-haikou-haikou-lvds-9904379.dtb
+px30-ringneck-haikou-haikou-lvds-9904379-dtbs := px30-ringneck-haikou.dtb \
+	px30-ringneck-haikou-lvds-9904379.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += px30-ringneck-haikou-haikou-video-demo.dtb
+px30-ringneck-haikou-haikou-video-demo-dtbs := px30-ringneck-haikou.dtb \
+	px30-ringneck-haikou-video-demo.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-puma-haikou-haikou-video-demo.dtb
+rk3399-puma-haikou-haikou-video-demo-dtbs := rk3399-puma-haikou.dtb \
+	rk3399-puma-haikou-video-demo.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-wolfvision-pf5-vz-2-uhd.dtb
+rk3568-wolfvision-pf5-vz-2-uhd-dtbs := rk3568-wolfvision-pf5.dtb \
+	rk3568-wolfvision-pf5-display-vz.dtbo \
+	rk3568-wolfvision-pf5-io-expander.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-wifi.dtb
+rk3588-edgeble-neu6a-wifi-dtbs := rk3588-edgeble-neu6a-io.dtb \
+	rk3588-edgeble-neu6a-wifi.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6b-wifi.dtb
+rk3588-edgeble-neu6b-wifi-dtbs := rk3588-edgeble-neu6b-io.dtb \
+	rk3588-edgeble-neu6a-wifi.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar-pre-ict-tester.dtb
+rk3588-jaguar-pre-ict-tester-dtbs := rk3588-jaguar.dtb \
+	rk3588-jaguar-pre-ict-tester.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5b-pcie-ep.dtb
+rk3588-rock-5b-pcie-ep-dtbs := rk3588-rock-5b.dtb \
+	rk3588-rock-5b-pcie-ep.dtbo
+
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5b-pcie-srns.dtb
+rk3588-rock-5b-pcie-srns-dtbs := rk3588-rock-5b.dtb \
+	rk3588-rock-5b-pcie-srns.dtbo
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
index 1edfd643b25a..a334ef0629d1 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi
@@ -31,7 +31,7 @@
 	};
 
 	vcc3v3_btreg: vcc3v3-btreg {
-		compatible = "regulator-gpio";
+		compatible = "regulator-fixed";
 		enable-active-high;
 		pinctrl-names = "default";
 		pinctrl-0 = <&bt_enable_h>;
@@ -39,7 +39,6 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
-		states = <3300000 0x0>;
 	};
 
 	vcc3v3_rf_aux_mod: regulator-vcc3v3-rf-aux-mod {
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
index 80db778c9684..b60e68faa83a 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi
@@ -26,5 +26,5 @@
 };
 
 &vcc3v3_btreg {
-	enable-gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
+	gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
index 165d09ccb942..5886b802c520 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts
@@ -39,5 +39,5 @@
 };
 
 &vcc3v3_btreg {
-	enable-gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
+	gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-lvds-9904379.dtso b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-lvds-9904379.dtso
new file mode 100644
index 000000000000..3fc088a5636a
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-lvds-9904379.dtso
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2025 Cherry Embedded Solutions GmbH
+ *
+ * HAIKOU-LVDS-9904379 adapter for PX30 Ringneck and Haikou carrierboard.
+ *
+ * This adapter needs to be plugged in the fake PCIe connector called Video
+ * Connector on Haikou carrierboard.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+&{/} {
+	backlight_lvds: backlight-lvds {
+		compatible = "pwm-backlight";
+		brightness-levels = <0 255>;
+		default-brightness-level = <255>;
+		num-interpolated-steps = <255>;
+		power-supply = <&vcc3v3_baseboard>;
+		pwms = <&pwm0 0 25000 0>;
+	};
+
+	panel {
+		compatible = "admatec,9904379", "panel-lvds";
+		backlight = <&backlight_lvds>;
+		data-mapping = "vesa-24";
+		height-mm = <126>;
+		power-supply = <&vcc3v3_baseboard>;
+		width-mm = <224>;
+
+		panel-timing {
+			clock-frequency = <49500000>;
+			hactive = <1024>;
+			hback-porch = <90>;
+			hfront-porch = <90>;
+			hsync-len = <90>;
+			vactive = <600>;
+			vback-porch = <10>;
+			vfront-porch = <10>;
+			vsync-len = <10>;
+		};
+
+		port {
+			panel_in_lvds: endpoint {
+				remote-endpoint = <&lvds_out_panel>;
+			};
+		};
+	};
+};
+
+&display_subsystem {
+	status = "okay";
+};
+
+&dsi_dphy {
+	status = "okay";
+};
+
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	/* EEPROM and GT928 are limited to 400KHz */
+	clock-frequency = <400000>;
+
+	touchscreen@14 {
+		compatible = "goodix,gt928";
+		reg = <0x14>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
+		irq-gpios = <&gpio0 RK_PA0 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&touch_int &touch_rst>;
+		pinctrl-names = "default";
+		touchscreen-inverted-x;
+		touchscreen-inverted-y;
+		AVDD28-supply = <&vcc3v3_baseboard>;
+		VDDIO-supply = <&vcc3v3_baseboard>;
+	};
+
+	eeprom@54 {
+		reg = <0x54>;
+		compatible = "st,24c04", "atmel,24c04";
+		pagesize = <16>;
+		size = <512>;
+		vcc-supply = <&vcc3v3_baseboard>;
+	};
+};
+
+&lvds {
+	status = "okay";
+};
+
+&lvds_out {
+	lvds_out_panel: endpoint {
+		remote-endpoint = <&panel_in_lvds>;
+	};
+};
+
+&pinctrl {
+	touch {
+		touch_int: touch-int {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		touch_rst: touch-rst {
+			rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&vopl {
+	status = "okay";
+};
+
+&vopl_mmu {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso
new file mode 100644
index 000000000000..7d9ea5aa5984
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2025 Cherry Embedded Solutions GmbH
+ *
+ * DEVKIT ADDON CAM-TS-A01
+ * https://embedded.cherry.de/product/development-kit/
+ *
+ * DT-overlay for the camera / DSI demo appliance for Haikou boards.
+ * In the flavour for use with a Ringneck system-on-module.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/clock/px30-cru.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+&{/} {
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&dc_12v>;
+		pwms = <&pwm0 0 25000 0>;
+	};
+
+	cam_afvdd_2v8: regulator-cam-afvdd-2v8 {
+		compatible  = "regulator-fixed";
+		gpio = <&pca9670 2 GPIO_ACTIVE_LOW>;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "cam-afvdd-2v8";
+		vin-supply = <&vcc2v8_video>;
+	};
+
+	cam_avdd_2v8: regulator-cam-avdd-2v8 {
+		compatible  = "regulator-fixed";
+		gpio = <&pca9670 4 GPIO_ACTIVE_LOW>;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "cam-avdd-2v8";
+		vin-supply = <&vcc2v8_video>;
+	};
+
+	cam_dovdd_1v8: regulator-cam-dovdd-1v8 {
+		compatible  = "regulator-fixed";
+	        gpio = <&pca9670 3 GPIO_ACTIVE_LOW>;
+	        regulator-max-microvolt = <1800000>;
+	        regulator-min-microvolt = <1800000>;
+	        regulator-name = "cam-dovdd-1v8";
+	        vin-supply = <&vcc1v8_video>;
+	};
+
+	cam_dvdd_1v2: regulator-cam-dvdd-1v2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&pca9670 5 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <1200000>;
+		regulator-min-microvolt = <1200000>;
+		regulator-name = "cam-dvdd-1v2";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	vcc1v8_video: regulator-vcc1v8-video {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-max-microvolt = <1800000>;
+		regulator-min-microvolt = <1800000>;
+		regulator-name = "vcc1v8-video";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	vcc2v8_video: regulator-vcc2v8-video {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "vcc2v8-video";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	video-adapter-leds {
+		compatible = "gpio-leds";
+
+		video-adapter-led {
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&pca9670 7 GPIO_ACTIVE_HIGH>;
+			label = "video-adapter-led";
+			linux,default-trigger = "none";
+		};
+	};
+};
+
+&display_subsystem {
+	status = "okay";
+};
+
+&dsi {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "leadtek,ltk050h3148w";
+		reg = <0>;
+		backlight = <&backlight>;
+		iovcc-supply = <&vcc1v8_video>;
+		reset-gpios = <&pca9670 0 GPIO_ACTIVE_LOW>;
+		vci-supply = <&vcc2v8_video>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&dsi_dphy {
+	status = "okay";
+};
+
+&dsi_out {
+	mipi_out_panel: endpoint {
+		remote-endpoint = <&mipi_in_panel>;
+	};
+};
+
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	/* OV5675, GT911, DW9714 are limited to 400KHz */
+	clock-frequency = <400000>;
+
+	touchscreen@14 {
+		compatible = "goodix,gt911";
+		reg = <0x14>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
+		irq-gpios = <&gpio0 RK_PA0 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&touch_int>;
+		pinctrl-names = "default";
+		reset-gpios = <&pca9670 1 GPIO_ACTIVE_HIGH>;
+		AVDD28-supply = <&vcc2v8_video>;
+		VDDIO-supply = <&vcc3v3_baseboard>;
+	};
+
+	pca9670: gpio@27 {
+		compatible = "nxp,pca9670";
+		reg = <0x27>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-0 = <&pca9670_resetn>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pinctrl {
+	pca9670 {
+		pca9670_resetn: pca9670-resetn {
+			rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	touch {
+		touch_int: touch-int {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&vopb {
+	status = "okay";
+};
+
+&vopb_mmu {
+	status = "okay";
+};
+
+&vopl {
+	status = "okay";
+};
+
+&vopl_mmu {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index eb9470a00e54..91cf4cd3fae2 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -154,6 +154,8 @@
 };
 
 &i2c3 {
+	status = "okay";
+
 	eeprom@50 {
 		reg = <0x50>;
 		compatible = "atmel,24c01";
@@ -194,6 +196,13 @@
 			  <3 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 	};
+
+	uart {
+		uart5_rts_pin: uart5-rts-pin {
+			rockchip,pins =
+			  <0 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
 };
 
 &pwm0 {
@@ -222,10 +231,15 @@
 };
 
 &uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_xfer>;
 	status = "okay";
 };
 
 &uart5 {
+	/* Add pinmux for rts-gpios (uart5_rts_pin) */
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart5_xfer &uart5_rts_pin>;
 	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index e80412abec08..142244d52706 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -325,10 +325,6 @@
 	};
 };
 
-&i2c3 {
-	status = "okay";
-};
-
 &i2s0_8ch {
 	rockchip,trcm-sync-tx-only;
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
index 629121de5a13..5e7181948992 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
@@ -147,7 +147,7 @@
 
 &pwm5 {
 	status = "okay";
-	pinctrl-names = "active";
+	pinctrl-names = "default";
 	pinctrl-0 = <&pwm5_pin_pull_down>;
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
index a94114fb7cc1..96c27fc5005d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3318-a95x-z2.dts
@@ -274,13 +274,13 @@
 
 &pwm0 {
 	pinctrl-0 = <&pwm0_pin_pull_up>;
-	pinctrl-names = "active";
+	pinctrl-names = "default";
 	status = "okay";
 };
 
 &pwm1 {
 	pinctrl-0 = <&pwm1_pin_pull_up>;
-	pinctrl-names = "active";
+	pinctrl-names = "default";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
index 6310b58de77f..a4bdd87d0729 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
@@ -428,10 +428,18 @@
 	status = "okay";
 };
 
+&u2phy_otg {
+	status = "okay";
+};
+
 &uart2 {
 	status = "okay";
 };
 
+&usb20_otg {
+	status = "okay";
+};
+
 &usbdrd3 {
 	dr_mode = "host";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
index b1c9bd0e63ef..8d94d9f91a5c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
@@ -115,7 +115,7 @@
 };
 
 &u2phy1_host {
-	status = "disabled";
+	phy-supply = <&vdd_5v>;
 };
 
 &uart0 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
index b169be06d4d1..c8eb5481f43d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi4.dtsi
@@ -603,7 +603,7 @@
 };
 
 &pwm2 {
-	pinctrl-names = "active";
+	pinctrl-names = "default";
 	pinctrl-0 = <&pwm2_pin_pull_down>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso
new file mode 100644
index 000000000000..0377ec860d35
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2025 Cherry Embedded Solutions GmbH
+ *
+ * DEVKIT ADDON CAM-TS-A01
+ * https://embedded.cherry.de/product/development-kit/
+ *
+ * DT-overlay for the camera / DSI demo appliance for Haikou boards.
+ * In the flavour for use with a Puma system-on-module.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/clock/rk3399-cru.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+&{/} {
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&dc_12v>;
+		pwms = <&pwm0 0 25000 0>;
+	};
+
+	cam_afvdd_2v8: regulator-cam-afvdd-2v8 {
+		compatible  = "regulator-fixed";
+		gpio = <&pca9670 2 GPIO_ACTIVE_LOW>;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "cam-afvdd-2v8";
+		vin-supply = <&vcc2v8_video>;
+	};
+
+	cam_avdd_2v8: regulator-cam-avdd-2v8 {
+		compatible  = "regulator-fixed";
+		gpio = <&pca9670 4 GPIO_ACTIVE_LOW>;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "cam-avdd-2v8";
+		vin-supply = <&vcc2v8_video>;
+	};
+
+	cam_dovdd_1v8: regulator-cam-dovdd-1v8 {
+		compatible  = "regulator-fixed";
+	        gpio = <&pca9670 3 GPIO_ACTIVE_LOW>;
+	        regulator-max-microvolt = <1800000>;
+	        regulator-min-microvolt = <1800000>;
+	        regulator-name = "cam-dovdd-1v8";
+	        vin-supply = <&vcc1v8_video>;
+	};
+
+	cam_dvdd_1v2: regulator-cam-dvdd-1v2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&pca9670 5 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <1200000>;
+		regulator-min-microvolt = <1200000>;
+		regulator-name = "cam-dvdd-1v2";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	vcc1v8_video: regulator-vcc1v8-video {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-max-microvolt = <1800000>;
+		regulator-min-microvolt = <1800000>;
+		regulator-name = "vcc1v8-video";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	vcc2v8_video: regulator-vcc2v8-video {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-max-microvolt = <2800000>;
+		regulator-min-microvolt = <2800000>;
+		regulator-name = "vcc2v8-video";
+		vin-supply = <&vcc3v3_baseboard>;
+	};
+
+	video-adapter-leds {
+		compatible = "gpio-leds";
+
+		video-adapter-led {
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&pca9670 7 GPIO_ACTIVE_HIGH>;
+			label = "video-adapter-led";
+			linux,default-trigger = "none";
+		};
+	};
+};
+
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	/* OV5675, GT911, DW9714 are limited to 400KHz */
+	clock-frequency = <400000>;
+
+	touchscreen@14 {
+		compatible = "goodix,gt911";
+		reg = <0x14>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <RK_PC7 IRQ_TYPE_LEVEL_LOW>;
+		irq-gpios = <&gpio1 RK_PC7 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&touch_int>;
+		pinctrl-names = "default";
+		reset-gpios = <&pca9670 1 GPIO_ACTIVE_HIGH>;
+		AVDD28-supply = <&vcc2v8_video>;
+		VDDIO-supply = <&vcc3v3_baseboard>;
+	};
+
+	pca9670: gpio@27 {
+		compatible = "nxp,pca9670";
+		reg = <0x27>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-0 = <&pca9670_resetn>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio4 RK_PD6 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&mipi_out {
+	mipi_out_panel: endpoint {
+		remote-endpoint = <&mipi_in_panel>;
+	};
+};
+
+&mipi_dsi {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "leadtek,ltk050h3148w";
+		reg = <0>;
+		backlight = <&backlight>;
+		iovcc-supply = <&vcc1v8_video>;
+		reset-gpios = <&pca9670 0 GPIO_ACTIVE_LOW>;
+		vci-supply = <&vcc2v8_video>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&pinctrl {
+	pca9670 {
+		pca9670_resetn: pca9670-resetn {
+			rockchip,pins = <4 RK_PD6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	touch {
+		touch_int: touch-int {
+			rockchip,pins = <1 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
index 947bbd62a6b0..f2234dabd664 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
@@ -149,8 +149,15 @@
 	};
 };
 
+&gmac {
+	status = "okay";
+};
+
 &hdmi {
-	ddc-i2c-bus = <&i2c3>;
+	status = "okay";
+};
+
+&hdmi_sound {
 	status = "okay";
 };
 
@@ -186,9 +193,22 @@
 	};
 };
 
-&i2c6 {
+&i2c7 {
+	eeprom@50 {
+		reg = <0x50>;
+		compatible = "atmel,24c01";
+		pagesize = <8>;
+		size = <128>;
+		vcc-supply = <&vcc3v3_baseboard>;
+	};
+};
+
+&i2s0 {
+	status = "okay";
+};
+
+&i2s2 {
 	status = "okay";
-	clock-frequency = <400000>;
 };
 
 &pcie_phy {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 995b30a7aae0..e00fbaa8acc1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -183,7 +183,6 @@
 	snps,reset-delays-us = <0 10000 50000>;
 	tx_delay = <0x10>;
 	rx_delay = <0x23>;
-	status = "okay";
 };
 
 &gpu {
@@ -389,6 +388,14 @@
 	};
 };
 
+&hdmi {
+	ddc-i2c-bus = <&i2c3>;
+};
+
+&i2c6 {
+	clock-frequency = <400000>;
+};
+
 &i2c7 {
 	status = "okay";
 	clock-frequency = <400000>;
@@ -439,7 +446,6 @@
 	pinctrl-1 = <&i2s0_2ch_bus_bclk_off>;
 	rockchip,playback-channels = <2>;
 	rockchip,capture-channels = <2>;
-	status = "okay";
 };
 
 /*
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
index e2e9279fa267..8e3858cf988c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
@@ -112,7 +112,7 @@
 
 &i2c1 {
 	es8388: es8388@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		clocks = <&cru SCLK_I2S_8CH_OUT>;
 		#sound-dai-cells = <0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index 541dca12bf1a..046dbe329017 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -43,7 +43,7 @@
 	sdio_pwrseq: sdio-pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		clocks = <&rk808 1>;
-		clock-names = "lpo";
+		clock-names = "ext_clock";
 		pinctrl-names = "default";
 		pinctrl-0 = <&wifi_enable_h>;
 		reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
index 69a9d6170649..51c6aa26d828 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
@@ -227,6 +227,16 @@
 		vin-supply = <&vcc12v_dcin>;
 	};
 
+	vcca_0v9: regulator-vcca-0v9 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcca_0v9";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <900000>;
+		regulator-max-microvolt = <900000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
 	vdd_log: regulator-vdd-log {
 		compatible = "pwm-regulator";
 		pwms = <&pwm2 0 25000 1>;
@@ -312,6 +322,8 @@
 };
 
 &hdmi {
+	avdd-0v9-supply = <&vcca_0v9>;
+	avdd-1v8-supply = <&vcc1v8_dvp>;
 	ddc-i2c-bus = <&i2c3>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_cec>;
@@ -661,6 +673,8 @@
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_perst>;
+	vpcie0v9-supply = <&vcca_0v9>;
+	vpcie1v8-supply = <&vcca_1v8>;
 	vpcie12v-supply = <&vcc12v_dcin>;
 	vpcie3v3-supply = <&vcc3v3_pcie>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3528-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3528-pinctrl.dtsi
new file mode 100644
index 000000000000..ea051362fb26
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3528-pinctrl.dtsi
@@ -0,0 +1,1397 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2022 Rockchip Electronics Co., Ltd.
+ */
+
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rockchip-pinconf.dtsi"
+
+/*
+ * This file is auto generated by pin2dts tool, please keep these code
+ * by adding changes at end of this file.
+ */
+&pinctrl {
+	arm {
+		/omit-if-no-ref/
+		arm_pins: arm-pins {
+			rockchip,pins =
+				/* arm_avs */
+				<4 RK_PC4 3 &pcfg_pull_none>;
+		};
+	};
+
+	clk {
+		/omit-if-no-ref/
+		clkm0_32k_out: clkm0-32k-out {
+			rockchip,pins =
+				/* clkm0_32k_out */
+				<3 RK_PC3 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		clkm1_32k_out: clkm1-32k-out {
+			rockchip,pins =
+				/* clkm1_32k_out */
+				<1 RK_PC3 1 &pcfg_pull_none>;
+		};
+	};
+
+	emmc {
+		/omit-if-no-ref/
+		emmc_rstnout: emmc-rstnout {
+			rockchip,pins =
+				/* emmc_rstn */
+				<1 RK_PD6 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		emmc_bus8: emmc-bus8 {
+			rockchip,pins =
+				/* emmc_d0 */
+				<1 RK_PC4 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d1 */
+				<1 RK_PC5 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d2 */
+				<1 RK_PC6 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d3 */
+				<1 RK_PC7 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d4 */
+				<1 RK_PD0 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d5 */
+				<1 RK_PD1 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d6 */
+				<1 RK_PD2 1 &pcfg_pull_up_drv_level_2>,
+				/* emmc_d7 */
+				<1 RK_PD3 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		emmc_clk: emmc-clk {
+			rockchip,pins =
+				/* emmc_clk */
+				<1 RK_PD5 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		emmc_cmd: emmc-cmd {
+			rockchip,pins =
+				/* emmc_cmd */
+				<1 RK_PD4 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		emmc_strb: emmc-strb {
+			rockchip,pins =
+				/* emmc_strb */
+				<1 RK_PD7 1 &pcfg_pull_none>;
+		};
+	};
+
+	eth {
+		/omit-if-no-ref/
+		eth_pins: eth-pins {
+			rockchip,pins =
+				/* eth_clk_25m_out */
+				<3 RK_PB5 2 &pcfg_pull_none_drv_level_2>;
+		};
+	};
+
+	fephy {
+		/omit-if-no-ref/
+		fephym0_led_dpx: fephym0-led_dpx {
+			rockchip,pins =
+				/* fephy_led_dpx_m0 */
+				<4 RK_PB5 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fephym0_led_link: fephym0-led_link {
+			rockchip,pins =
+				/* fephy_led_link_m0 */
+				<4 RK_PC0 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fephym0_led_spd: fephym0-led_spd {
+			rockchip,pins =
+				/* fephy_led_spd_m0 */
+				<4 RK_PB7 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fephym1_led_dpx: fephym1-led_dpx {
+			rockchip,pins =
+				/* fephy_led_dpx_m1 */
+				<2 RK_PA4 5 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fephym1_led_link: fephym1-led_link {
+			rockchip,pins =
+				/* fephy_led_link_m1 */
+				<2 RK_PA6 5 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fephym1_led_spd: fephym1-led_spd {
+			rockchip,pins =
+				/* fephy_led_spd_m1 */
+				<2 RK_PA5 5 &pcfg_pull_none>;
+		};
+	};
+
+	fspi {
+		/omit-if-no-ref/
+		fspi_pins: fspi-pins {
+			rockchip,pins =
+				/* fspi_clk */
+				<1 RK_PD5 2 &pcfg_pull_none>,
+				/* fspi_d0 */
+				<1 RK_PC4 2 &pcfg_pull_none>,
+				/* fspi_d1 */
+				<1 RK_PC5 2 &pcfg_pull_none>,
+				/* fspi_d2 */
+				<1 RK_PC6 2 &pcfg_pull_none>,
+				/* fspi_d3 */
+				<1 RK_PC7 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		fspi_csn0: fspi-csn0 {
+			rockchip,pins =
+				/* fspi_csn0 */
+				<1 RK_PD0 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		fspi_csn1: fspi-csn1 {
+			rockchip,pins =
+				/* fspi_csn1 */
+				<1 RK_PD1 2 &pcfg_pull_none>;
+		};
+	};
+
+	gpu {
+		/omit-if-no-ref/
+		gpu_pins: gpu-pins {
+			rockchip,pins =
+				/* gpu_avs */
+				<4 RK_PC3 3 &pcfg_pull_none>;
+		};
+	};
+
+	hdmi {
+		/omit-if-no-ref/
+		hdmi_pins: hdmi-pins {
+			rockchip,pins =
+				/* hdmi_tx_cec */
+				<0 RK_PA3 1 &pcfg_pull_none>,
+				/* hdmi_tx_hpd */
+				<0 RK_PA2 1 &pcfg_pull_none>,
+				/* hdmi_tx_scl */
+				<0 RK_PA4 1 &pcfg_pull_none>,
+				/* hdmi_tx_sda */
+				<0 RK_PA5 1 &pcfg_pull_none>;
+		};
+	};
+
+	hsm {
+		/omit-if-no-ref/
+		hsmm0_pins: hsmm0-pins {
+			rockchip,pins =
+				/* hsm_clk_out_m0 */
+				<2 RK_PA2 4 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		hsmm1_pins: hsmm1-pins {
+			rockchip,pins =
+				/* hsm_clk_out_m1 */
+				<1 RK_PA4 3 &pcfg_pull_none>;
+		};
+	};
+
+	i2c0 {
+		/omit-if-no-ref/
+		i2c0m0_xfer: i2c0m0-xfer {
+			rockchip,pins =
+				/* i2c0_scl_m0 */
+				<4 RK_PC4 2 &pcfg_pull_none_smt>,
+				/* i2c0_sda_m0 */
+				<4 RK_PC3 2 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c0m1_xfer: i2c0m1-xfer {
+			rockchip,pins =
+				/* i2c0_scl_m1 */
+				<4 RK_PA1 2 &pcfg_pull_none_smt>,
+				/* i2c0_sda_m1 */
+				<4 RK_PA0 2 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c1 {
+		/omit-if-no-ref/
+		i2c1m0_xfer: i2c1m0-xfer {
+			rockchip,pins =
+				/* i2c1_scl_m0 */
+				<4 RK_PA3 2 &pcfg_pull_none_smt>,
+				/* i2c1_sda_m0 */
+				<4 RK_PA2 2 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c1m1_xfer: i2c1m1-xfer {
+			rockchip,pins =
+				/* i2c1_scl_m1 */
+				<4 RK_PC5 4 &pcfg_pull_none_smt>,
+				/* i2c1_sda_m1 */
+				<4 RK_PC6 4 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c2 {
+		/omit-if-no-ref/
+		i2c2m0_xfer: i2c2m0-xfer {
+			rockchip,pins =
+				/* i2c2_scl_m0 */
+				<0 RK_PA4 2 &pcfg_pull_none_smt>,
+				/* i2c2_sda_m0 */
+				<0 RK_PA5 2 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c2m1_xfer: i2c2m1-xfer {
+			rockchip,pins =
+				/* i2c2_scl_m1 */
+				<1 RK_PA5 3 &pcfg_pull_none_smt>,
+				/* i2c2_sda_m1 */
+				<1 RK_PA6 3 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c3 {
+		/omit-if-no-ref/
+		i2c3m0_xfer: i2c3m0-xfer {
+			rockchip,pins =
+				/* i2c3_scl_m0 */
+				<1 RK_PA0 2 &pcfg_pull_none_smt>,
+				/* i2c3_sda_m0 */
+				<1 RK_PA1 2 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c3m1_xfer: i2c3m1-xfer {
+			rockchip,pins =
+				/* i2c3_scl_m1 */
+				<3 RK_PC1 5 &pcfg_pull_none_smt>,
+				/* i2c3_sda_m1 */
+				<3 RK_PC3 5 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c4 {
+		/omit-if-no-ref/
+		i2c4_xfer: i2c4-xfer {
+			rockchip,pins =
+				/* i2c4_scl */
+				<2 RK_PA0 4 &pcfg_pull_none_smt>,
+				/* i2c4_sda */
+				<2 RK_PA1 4 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c5 {
+		/omit-if-no-ref/
+		i2c5m0_xfer: i2c5m0-xfer {
+			rockchip,pins =
+				/* i2c5_scl_m0 */
+				<1 RK_PB2 3 &pcfg_pull_none_smt>,
+				/* i2c5_sda_m0 */
+				<1 RK_PB3 3 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c5m1_xfer: i2c5m1-xfer {
+			rockchip,pins =
+				/* i2c5_scl_m1 */
+				<1 RK_PD2 3 &pcfg_pull_none_smt>,
+				/* i2c5_sda_m1 */
+				<1 RK_PD3 3 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c6 {
+		/omit-if-no-ref/
+		i2c6m0_xfer: i2c6m0-xfer {
+			rockchip,pins =
+				/* i2c6_scl_m0 */
+				<3 RK_PB2 5 &pcfg_pull_none_smt>,
+				/* i2c6_sda_m0 */
+				<3 RK_PB3 5 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2c6m1_xfer: i2c6m1-xfer {
+			rockchip,pins =
+				/* i2c6_scl_m1 */
+				<1 RK_PD4 3 &pcfg_pull_none_smt>,
+				/* i2c6_sda_m1 */
+				<1 RK_PD7 3 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2c7 {
+		/omit-if-no-ref/
+		i2c7_xfer: i2c7-xfer {
+			rockchip,pins =
+				/* i2c7_scl */
+				<2 RK_PA5 4 &pcfg_pull_none_smt>,
+				/* i2c7_sda */
+				<2 RK_PA6 4 &pcfg_pull_none_smt>;
+		};
+	};
+
+	i2s0 {
+		/omit-if-no-ref/
+		i2s0m0_lrck: i2s0m0-lrck {
+			rockchip,pins =
+				/* i2s0_lrck_m0 */
+				<3 RK_PB6 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m0_mclk: i2s0m0-mclk {
+			rockchip,pins =
+				/* i2s0_mclk_m0 */
+				<3 RK_PB4 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m0_sclk: i2s0m0-sclk {
+			rockchip,pins =
+				/* i2s0_sclk_m0 */
+				<3 RK_PB5 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m0_sdi: i2s0m0-sdi {
+			rockchip,pins =
+				/* i2s0m0_sdi */
+				<3 RK_PB7 1 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		i2s0m0_sdo: i2s0m0-sdo {
+			rockchip,pins =
+				/* i2s0m0_sdo */
+				<3 RK_PC0 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m1_lrck: i2s0m1-lrck {
+			rockchip,pins =
+				/* i2s0_lrck_m1 */
+				<1 RK_PB6 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m1_mclk: i2s0m1-mclk {
+			rockchip,pins =
+				/* i2s0_mclk_m1 */
+				<1 RK_PB4 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m1_sclk: i2s0m1-sclk {
+			rockchip,pins =
+				/* i2s0_sclk_m1 */
+				<1 RK_PB5 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s0m1_sdi: i2s0m1-sdi {
+			rockchip,pins =
+				/* i2s0m1_sdi */
+				<1 RK_PB7 1 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		i2s0m1_sdo: i2s0m1-sdo {
+			rockchip,pins =
+				/* i2s0m1_sdo */
+				<1 RK_PC0 1 &pcfg_pull_none>;
+		};
+	};
+
+	i2s1 {
+		/omit-if-no-ref/
+		i2s1_lrck: i2s1-lrck {
+			rockchip,pins =
+				/* i2s1_lrck */
+				<4 RK_PA6 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_mclk: i2s1-mclk {
+			rockchip,pins =
+				/* i2s1_mclk */
+				<4 RK_PA4 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sclk: i2s1-sclk {
+			rockchip,pins =
+				/* i2s1_sclk */
+				<4 RK_PA5 1 &pcfg_pull_none_smt>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdi0: i2s1-sdi0 {
+			rockchip,pins =
+				/* i2s1_sdi0 */
+				<4 RK_PB4 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdi1: i2s1-sdi1 {
+			rockchip,pins =
+				/* i2s1_sdi1 */
+				<4 RK_PB3 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdi2: i2s1-sdi2 {
+			rockchip,pins =
+				/* i2s1_sdi2 */
+				<4 RK_PA3 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdi3: i2s1-sdi3 {
+			rockchip,pins =
+				/* i2s1_sdi3 */
+				<4 RK_PA2 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdo0: i2s1-sdo0 {
+			rockchip,pins =
+				/* i2s1_sdo0 */
+				<4 RK_PA7 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdo1: i2s1-sdo1 {
+			rockchip,pins =
+				/* i2s1_sdo1 */
+				<4 RK_PB0 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdo2: i2s1-sdo2 {
+			rockchip,pins =
+				/* i2s1_sdo2 */
+				<4 RK_PB1 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		i2s1_sdo3: i2s1-sdo3 {
+			rockchip,pins =
+				/* i2s1_sdo3 */
+				<4 RK_PB2 1 &pcfg_pull_none>;
+		};
+	};
+
+	jtag {
+		/omit-if-no-ref/
+		jtagm0_pins: jtagm0-pins {
+			rockchip,pins =
+				/* jtag_cpu_tck_m0 */
+				<2 RK_PA2 2 &pcfg_pull_none>,
+				/* jtag_cpu_tms_m0 */
+				<2 RK_PA3 2 &pcfg_pull_none>,
+				/* jtag_mcu_tck_m0 */
+				<2 RK_PA4 2 &pcfg_pull_none>,
+				/* jtag_mcu_tms_m0 */
+				<2 RK_PA5 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		jtagm1_pins: jtagm1-pins {
+			rockchip,pins =
+				/* jtag_cpu_tck_m1 */
+				<4 RK_PD0 2 &pcfg_pull_none>,
+				/* jtag_cpu_tms_m1 */
+				<4 RK_PC7 2 &pcfg_pull_none>,
+				/* jtag_mcu_tck_m1 */
+				<4 RK_PD0 3 &pcfg_pull_none>,
+				/* jtag_mcu_tms_m1 */
+				<4 RK_PC7 3 &pcfg_pull_none>;
+		};
+	};
+
+	pcie {
+		/omit-if-no-ref/
+		pciem0_pins: pciem0-pins {
+			rockchip,pins =
+				/* pcie_clkreqn_m0 */
+				<3 RK_PA6 5 &pcfg_pull_none>,
+				/* pcie_perstn_m0 */
+				<3 RK_PB0 5 &pcfg_pull_none>,
+				/* pcie_waken_m0 */
+				<3 RK_PA7 5 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pciem1_pins: pciem1-pins {
+			rockchip,pins =
+				/* pcie_clkreqn_m1 */
+				<1 RK_PA0 4 &pcfg_pull_none>,
+				/* pcie_perstn_m1 */
+				<1 RK_PA2 4 &pcfg_pull_none>,
+				/* pcie_waken_m1 */
+				<1 RK_PA1 4 &pcfg_pull_none>;
+		};
+	};
+
+	pdm {
+		/omit-if-no-ref/
+		pdm_clk0: pdm-clk0 {
+			rockchip,pins =
+				/* pdm_clk0 */
+				<4 RK_PB5 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pdm_clk1: pdm-clk1 {
+			rockchip,pins =
+				/* pdm_clk1 */
+				<4 RK_PA4 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pdm_sdi0: pdm-sdi0 {
+			rockchip,pins =
+				/* pdm_sdi0 */
+				<4 RK_PB2 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pdm_sdi1: pdm-sdi1 {
+			rockchip,pins =
+				/* pdm_sdi1 */
+				<4 RK_PB1 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pdm_sdi2: pdm-sdi2 {
+			rockchip,pins =
+				/* pdm_sdi2 */
+				<4 RK_PB3 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		pdm_sdi3: pdm-sdi3 {
+			rockchip,pins =
+				/* pdm_sdi3 */
+				<4 RK_PC1 3 &pcfg_pull_none>;
+		};
+	};
+
+	pmu {
+		/omit-if-no-ref/
+		pmu_pins: pmu-pins {
+			rockchip,pins =
+				/* pmu_debug */
+				<4 RK_PA0 4 &pcfg_pull_none>;
+		};
+	};
+
+	pwm0 {
+		/omit-if-no-ref/
+		pwm0m0_pins: pwm0m0-pins {
+			rockchip,pins =
+				/* pwm0_m0 */
+				<4 RK_PC3 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm0m1_pins: pwm0m1-pins {
+			rockchip,pins =
+				/* pwm0_m1 */
+				<1 RK_PA2 5 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm1 {
+		/omit-if-no-ref/
+		pwm1m0_pins: pwm1m0-pins {
+			rockchip,pins =
+				/* pwm1_m0 */
+				<4 RK_PC4 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm1m1_pins: pwm1m1-pins {
+			rockchip,pins =
+				/* pwm1_m1 */
+				<1 RK_PA3 4 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm2 {
+		/omit-if-no-ref/
+		pwm2m0_pins: pwm2m0-pins {
+			rockchip,pins =
+				/* pwm2_m0 */
+				<4 RK_PC5 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm2m1_pins: pwm2m1-pins {
+			rockchip,pins =
+				/* pwm2_m1 */
+				<1 RK_PA7 2 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm3 {
+		/omit-if-no-ref/
+		pwm3m0_pins: pwm3m0-pins {
+			rockchip,pins =
+				/* pwm3_m0 */
+				<4 RK_PC6 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm3m1_pins: pwm3m1-pins {
+			rockchip,pins =
+				/* pwm3_m1 */
+				<2 RK_PA4 3 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm4 {
+		/omit-if-no-ref/
+		pwm4m0_pins: pwm4m0-pins {
+			rockchip,pins =
+				/* pwm4_m0 */
+				<4 RK_PB7 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm4m1_pins: pwm4m1-pins {
+			rockchip,pins =
+				/* pwm4_m1 */
+				<1 RK_PA4 2 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm5 {
+		/omit-if-no-ref/
+		pwm5m0_pins: pwm5m0-pins {
+			rockchip,pins =
+				/* pwm5_m0 */
+				<4 RK_PC0 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm5m1_pins: pwm5m1-pins {
+			rockchip,pins =
+				/* pwm5_m1 */
+				<3 RK_PC3 1 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm6 {
+		/omit-if-no-ref/
+		pwm6m0_pins: pwm6m0-pins {
+			rockchip,pins =
+				/* pwm6_m0 */
+				<4 RK_PC1 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm6m1_pins: pwm6m1-pins {
+			rockchip,pins =
+				/* pwm6_m1 */
+				<1 RK_PC3 3 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm6m2_pins: pwm6m2-pins {
+			rockchip,pins =
+				/* pwm6_m2 */
+				<3 RK_PC1 1 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwm7 {
+		/omit-if-no-ref/
+		pwm7m0_pins: pwm7m0-pins {
+			rockchip,pins =
+				/* pwm7_m0 */
+				<4 RK_PC2 1 &pcfg_pull_none_drv_level_0>;
+		};
+
+		/omit-if-no-ref/
+		pwm7m1_pins: pwm7m1-pins {
+			rockchip,pins =
+				/* pwm7_m1 */
+				<1 RK_PC2 2 &pcfg_pull_none_drv_level_0>;
+		};
+	};
+
+	pwr {
+		/omit-if-no-ref/
+		pwr_pins: pwr-pins {
+			rockchip,pins =
+				/* pwr_ctrl0 */
+				<4 RK_PC2 2 &pcfg_pull_none>,
+				/* pwr_ctrl1 */
+				<4 RK_PB6 1 &pcfg_pull_none>;
+		};
+	};
+
+	ref {
+		/omit-if-no-ref/
+		refm0_pins: refm0-pins {
+			rockchip,pins =
+				/* ref_clk_out_m0 */
+				<0 RK_PA1 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		refm1_pins: refm1-pins {
+			rockchip,pins =
+				/* ref_clk_out_m1 */
+				<3 RK_PC3 6 &pcfg_pull_none>;
+		};
+	};
+
+	rgmii {
+		/omit-if-no-ref/
+		rgmii_miim: rgmii-miim {
+			rockchip,pins =
+				/* rgmii_mdc */
+				<3 RK_PB6 2 &pcfg_pull_none_drv_level_2>,
+				/* rgmii_mdio */
+				<3 RK_PB7 2 &pcfg_pull_none_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		rgmii_rx_bus2: rgmii-rx_bus2 {
+			rockchip,pins =
+				/* rgmii_rxd0 */
+				<3 RK_PA3 2 &pcfg_pull_none>,
+				/* rgmii_rxd1 */
+				<3 RK_PA2 2 &pcfg_pull_none>,
+				/* rgmii_rxdv_crs */
+				<3 RK_PC2 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		rgmii_tx_bus2: rgmii-tx_bus2 {
+			rockchip,pins =
+				/* rgmii_txd0 */
+				<3 RK_PA1 2 &pcfg_pull_none_drv_level_2>,
+				/* rgmii_txd1 */
+				<3 RK_PA0 2 &pcfg_pull_none_drv_level_2>,
+				/* rgmii_txen */
+				<3 RK_PC0 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		rgmii_rgmii_clk: rgmii-rgmii_clk {
+			rockchip,pins =
+				/* rgmii_rxclk */
+				<3 RK_PA5 2 &pcfg_pull_none>,
+				/* rgmii_txclk */
+				<3 RK_PA4 2 &pcfg_pull_none_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		rgmii_rgmii_bus: rgmii-rgmii_bus {
+			rockchip,pins =
+				/* rgmii_rxd2 */
+				<3 RK_PA7 2 &pcfg_pull_none>,
+				/* rgmii_rxd3 */
+				<3 RK_PA6 2 &pcfg_pull_none>,
+				/* rgmii_txd2 */
+				<3 RK_PB1 2 &pcfg_pull_none_drv_level_2>,
+				/* rgmii_txd3 */
+				<3 RK_PB0 2 &pcfg_pull_none_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		rgmii_clk: rgmii-clk {
+			rockchip,pins =
+				/* rgmii_clk */
+				<3 RK_PB4 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		rgmii_txer: rgmii-txer {
+			rockchip,pins =
+				/* rgmii_txer */
+				<3 RK_PC1 2 &pcfg_pull_none>;
+		};
+	};
+
+	scr {
+		/omit-if-no-ref/
+		scrm0_pins: scrm0-pins {
+			rockchip,pins =
+				/* scr_clk_m0 */
+				<1 RK_PA2 3 &pcfg_pull_none>,
+				/* scr_data_m0 */
+				<1 RK_PA1 3 &pcfg_pull_none>,
+				/* scr_detn_m0 */
+				<1 RK_PA0 3 &pcfg_pull_none>,
+				/* scr_rstn_m0 */
+				<1 RK_PA3 3 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		scrm1_pins: scrm1-pins {
+			rockchip,pins =
+				/* scr_clk_m1 */
+				<2 RK_PA5 3 &pcfg_pull_none>,
+				/* scr_data_m1 */
+				<2 RK_PA3 4 &pcfg_pull_none>,
+				/* scr_detn_m1 */
+				<2 RK_PA6 3 &pcfg_pull_none>,
+				/* scr_rstn_m1 */
+				<2 RK_PA4 4 &pcfg_pull_none>;
+		};
+	};
+
+	sdio0 {
+		/omit-if-no-ref/
+		sdio0_bus4: sdio0-bus4 {
+			rockchip,pins =
+				/* sdio0_d0 */
+				<1 RK_PA0 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio0_d1 */
+				<1 RK_PA1 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio0_d2 */
+				<1 RK_PA2 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio0_d3 */
+				<1 RK_PA3 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio0_clk: sdio0-clk {
+			rockchip,pins =
+				/* sdio0_clk */
+				<1 RK_PA5 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio0_cmd: sdio0-cmd {
+			rockchip,pins =
+				/* sdio0_cmd */
+				<1 RK_PA4 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio0_det: sdio0-det {
+			rockchip,pins =
+				/* sdio0_det */
+				<1 RK_PA6 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		sdio0_pwren: sdio0-pwren {
+			rockchip,pins =
+				/* sdio0_pwren */
+				<1 RK_PA7 1 &pcfg_pull_none>;
+		};
+	};
+
+	sdio1 {
+		/omit-if-no-ref/
+		sdio1_bus4: sdio1-bus4 {
+			rockchip,pins =
+				/* sdio1_d0 */
+				<3 RK_PA6 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio1_d1 */
+				<3 RK_PA7 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio1_d2 */
+				<3 RK_PB0 1 &pcfg_pull_up_drv_level_2>,
+				/* sdio1_d3 */
+				<3 RK_PB1 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio1_clk: sdio1-clk {
+			rockchip,pins =
+				/* sdio1_clk */
+				<3 RK_PA4 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio1_cmd: sdio1-cmd {
+			rockchip,pins =
+				/* sdio1_cmd */
+				<3 RK_PA5 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdio1_det: sdio1-det {
+			rockchip,pins =
+				/* sdio1_det */
+				<3 RK_PB3 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		sdio1_pwren: sdio1-pwren {
+			rockchip,pins =
+				/* sdio1_pwren */
+				<3 RK_PB2 1 &pcfg_pull_none>;
+		};
+	};
+
+	sdmmc {
+		/omit-if-no-ref/
+		sdmmc_bus4: sdmmc-bus4 {
+			rockchip,pins =
+				/* sdmmc_d0 */
+				<2 RK_PA0 1 &pcfg_pull_up_drv_level_2>,
+				/* sdmmc_d1 */
+				<2 RK_PA1 1 &pcfg_pull_up_drv_level_2>,
+				/* sdmmc_d2 */
+				<2 RK_PA2 1 &pcfg_pull_up_drv_level_2>,
+				/* sdmmc_d3 */
+				<2 RK_PA3 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdmmc_clk: sdmmc-clk {
+			rockchip,pins =
+				/* sdmmc_clk */
+				<2 RK_PA5 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdmmc_cmd: sdmmc-cmd {
+			rockchip,pins =
+				/* sdmmc_cmd */
+				<2 RK_PA4 1 &pcfg_pull_up_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		sdmmc_det: sdmmc-det {
+			rockchip,pins =
+				/* sdmmc_detn */
+				<2 RK_PA6 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		sdmmc_pwren: sdmmc-pwren {
+			rockchip,pins =
+				/* sdmmc_pwren */
+				<4 RK_PA1 1 &pcfg_pull_none>;
+		};
+	};
+
+	spdif {
+		/omit-if-no-ref/
+		spdifm0_pins: spdifm0-pins {
+			rockchip,pins =
+				/* spdif_tx_m0 */
+				<4 RK_PA0 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		spdifm1_pins: spdifm1-pins {
+			rockchip,pins =
+				/* spdif_tx_m1 */
+				<1 RK_PC3 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		spdifm2_pins: spdifm2-pins {
+			rockchip,pins =
+				/* spdif_tx_m2 */
+				<3 RK_PC3 2 &pcfg_pull_none>;
+		};
+	};
+
+	spi0 {
+		/omit-if-no-ref/
+		spi0_pins: spi0-pins {
+			rockchip,pins =
+				/* spi0_clk */
+				<4 RK_PB4 2 &pcfg_pull_none_drv_level_2>,
+				/* spi0_miso */
+				<4 RK_PB3 2 &pcfg_pull_none_drv_level_2>,
+				/* spi0_mosi */
+				<4 RK_PB2 2 &pcfg_pull_none_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		spi0_csn0: spi0-csn0 {
+			rockchip,pins =
+				/* spi0_csn0 */
+				<4 RK_PB6 2 &pcfg_pull_none_drv_level_2>;
+		};
+		/omit-if-no-ref/
+		spi0_csn1: spi0-csn1 {
+			rockchip,pins =
+				/* spi0_csn1 */
+				<4 RK_PC1 2 &pcfg_pull_none_drv_level_2>;
+		};
+	};
+
+	spi1 {
+		/omit-if-no-ref/
+		spi1_pins: spi1-pins {
+			rockchip,pins =
+				/* spi1_clk */
+				<1 RK_PB6 2 &pcfg_pull_none_drv_level_2>,
+				/* spi1_miso */
+				<1 RK_PC0 2 &pcfg_pull_none_drv_level_2>,
+				/* spi1_mosi */
+				<1 RK_PB7 2 &pcfg_pull_none_drv_level_2>;
+		};
+
+		/omit-if-no-ref/
+		spi1_csn0: spi1-csn0 {
+			rockchip,pins =
+				/* spi1_csn0 */
+				<1 RK_PC1 1 &pcfg_pull_none_drv_level_2>;
+		};
+		/omit-if-no-ref/
+		spi1_csn1: spi1-csn1 {
+			rockchip,pins =
+				/* spi1_csn1 */
+				<1 RK_PC2 1 &pcfg_pull_none_drv_level_2>;
+		};
+	};
+
+	tsi0 {
+		/omit-if-no-ref/
+		tsi0_pins: tsi0-pins {
+			rockchip,pins =
+				/* tsi0_clkin */
+				<3 RK_PB2 3 &pcfg_pull_none>,
+				/* tsi0_d0 */
+				<3 RK_PB1 3 &pcfg_pull_none>,
+				/* tsi0_d1 */
+				<3 RK_PB5 3 &pcfg_pull_none>,
+				/* tsi0_d2 */
+				<3 RK_PB6 3 &pcfg_pull_none>,
+				/* tsi0_d3 */
+				<3 RK_PB7 3 &pcfg_pull_none>,
+				/* tsi0_d4 */
+				<3 RK_PA3 3 &pcfg_pull_none>,
+				/* tsi0_d5 */
+				<3 RK_PA2 3 &pcfg_pull_none>,
+				/* tsi0_d6 */
+				<3 RK_PA1 3 &pcfg_pull_none>,
+				/* tsi0_d7 */
+				<3 RK_PA0 3 &pcfg_pull_none>,
+				/* tsi0_fail */
+				<3 RK_PC0 3 &pcfg_pull_none>,
+				/* tsi0_sync */
+				<3 RK_PB4 3 &pcfg_pull_none>,
+				/* tsi0_valid */
+				<3 RK_PB3 3 &pcfg_pull_none>;
+		};
+	};
+
+	tsi1 {
+		/omit-if-no-ref/
+		tsi1_pins: tsi1-pins {
+			rockchip,pins =
+				/* tsi1_clkin */
+				<3 RK_PA5 3 &pcfg_pull_none>,
+				/* tsi1_d0 */
+				<3 RK_PA4 3 &pcfg_pull_none>,
+				/* tsi1_sync */
+				<3 RK_PA7 3 &pcfg_pull_none>,
+				/* tsi1_valid */
+				<3 RK_PA6 3 &pcfg_pull_none>;
+		};
+	};
+
+	uart0 {
+		/omit-if-no-ref/
+		uart0m0_xfer: uart0m0-xfer {
+			rockchip,pins =
+				/* uart0_rx_m0 */
+				<4 RK_PC7 1 &pcfg_pull_up>,
+				/* uart0_tx_m0 */
+				<4 RK_PD0 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart0m1_xfer: uart0m1-xfer {
+			rockchip,pins =
+				/* uart0_rx_m1 */
+				<2 RK_PA0 2 &pcfg_pull_up>,
+				/* uart0_tx_m1 */
+				<2 RK_PA1 2 &pcfg_pull_up>;
+		};
+	};
+
+	uart1 {
+		/omit-if-no-ref/
+		uart1m0_xfer: uart1m0-xfer {
+			rockchip,pins =
+				/* uart1_rx_m0 */
+				<4 RK_PA7 2 &pcfg_pull_up>,
+				/* uart1_tx_m0 */
+				<4 RK_PA6 2 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart1m1_xfer: uart1m1-xfer {
+			rockchip,pins =
+				/* uart1_rx_m1 */
+				<4 RK_PC6 2 &pcfg_pull_up>,
+				/* uart1_tx_m1 */
+				<4 RK_PC5 2 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart1_ctsn: uart1-ctsn {
+			rockchip,pins =
+				/* uart1_ctsn */
+				<4 RK_PA4 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart1_rtsn: uart1-rtsn {
+			rockchip,pins =
+				/* uart1_rtsn */
+				<4 RK_PA5 2 &pcfg_pull_none>;
+		};
+	};
+
+	uart2 {
+		/omit-if-no-ref/
+		uart2m0_xfer: uart2m0-xfer {
+			rockchip,pins =
+				/* uart2_rx_m0 */
+				<3 RK_PA0 1 &pcfg_pull_up>,
+				/* uart2_tx_m0 */
+				<3 RK_PA1 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart2m0_ctsn: uart2m0-ctsn {
+			rockchip,pins =
+				/* uart2m0_ctsn */
+				<3 RK_PA3 1 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart2m0_rtsn: uart2m0-rtsn {
+			rockchip,pins =
+				/* uart2m0_rtsn */
+				<3 RK_PA2 1 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		uart2m1_xfer: uart2m1-xfer {
+			rockchip,pins =
+				/* uart2_rx_m1 */
+				<1 RK_PB0 1 &pcfg_pull_up>,
+				/* uart2_tx_m1 */
+				<1 RK_PB1 1 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart2m1_ctsn: uart2m1-ctsn {
+			rockchip,pins =
+				/* uart2m1_ctsn */
+				<1 RK_PB3 1 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart2m1_rtsn: uart2m1-rtsn {
+			rockchip,pins =
+				/* uart2m1_rtsn */
+				<1 RK_PB2 1 &pcfg_pull_none>;
+		};
+	};
+
+	uart3 {
+		/omit-if-no-ref/
+		uart3m0_xfer: uart3m0-xfer {
+			rockchip,pins =
+				/* uart3_rx_m0 */
+				<4 RK_PB0 2 &pcfg_pull_up>,
+				/* uart3_tx_m0 */
+				<4 RK_PB1 2 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart3m1_xfer: uart3m1-xfer {
+			rockchip,pins =
+				/* uart3_rx_m1 */
+				<4 RK_PB7 3 &pcfg_pull_up>,
+				/* uart3_tx_m1 */
+				<4 RK_PC0 3 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart3_ctsn: uart3-ctsn {
+			rockchip,pins =
+				/* uart3_ctsn */
+				<4 RK_PA3 3 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart3_rtsn: uart3-rtsn {
+			rockchip,pins =
+				/* uart3_rtsn */
+				<4 RK_PA2 3 &pcfg_pull_none>;
+		};
+	};
+
+	uart4 {
+		/omit-if-no-ref/
+		uart4_xfer: uart4-xfer {
+			rockchip,pins =
+				/* uart4_rx */
+				<2 RK_PA2 3 &pcfg_pull_up>,
+				/* uart4_tx */
+				<2 RK_PA3 3 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart4_ctsn: uart4-ctsn {
+			rockchip,pins =
+				/* uart4_ctsn */
+				<2 RK_PA1 3 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart4_rtsn: uart4-rtsn {
+			rockchip,pins =
+				/* uart4_rtsn */
+				<2 RK_PA0 3 &pcfg_pull_none>;
+		};
+	};
+
+	uart5 {
+		/omit-if-no-ref/
+		uart5m0_xfer: uart5m0-xfer {
+			rockchip,pins =
+				/* uart5_rx_m0 */
+				<1 RK_PA2 2 &pcfg_pull_up>,
+				/* uart5_tx_m0 */
+				<1 RK_PA3 2 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart5m0_ctsn: uart5m0-ctsn {
+			rockchip,pins =
+				/* uart5m0_ctsn */
+				<1 RK_PA6 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart5m0_rtsn: uart5m0-rtsn {
+			rockchip,pins =
+				/* uart5m0_rtsn */
+				<1 RK_PA5 2 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		uart5m1_xfer: uart5m1-xfer {
+			rockchip,pins =
+				/* uart5_rx_m1 */
+				<1 RK_PD4 2 &pcfg_pull_up>,
+				/* uart5_tx_m1 */
+				<1 RK_PD7 2 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart5m1_ctsn: uart5m1-ctsn {
+			rockchip,pins =
+				/* uart5m1_ctsn */
+				<1 RK_PD3 2 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart5m1_rtsn: uart5m1-rtsn {
+			rockchip,pins =
+				/* uart5m1_rtsn */
+				<1 RK_PD2 2 &pcfg_pull_none>;
+		};
+	};
+
+	uart6 {
+		/omit-if-no-ref/
+		uart6m0_xfer: uart6m0-xfer {
+			rockchip,pins =
+				/* uart6_rx_m0 */
+				<3 RK_PA7 4 &pcfg_pull_up>,
+				/* uart6_tx_m0 */
+				<3 RK_PA6 4 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart6m1_xfer: uart6m1-xfer {
+			rockchip,pins =
+				/* uart6_rx_m1 */
+				<3 RK_PC3 4 &pcfg_pull_up>,
+				/* uart6_tx_m1 */
+				<3 RK_PC1 4 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart6_ctsn: uart6-ctsn {
+			rockchip,pins =
+				/* uart6_ctsn */
+				<3 RK_PA4 4 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart6_rtsn: uart6-rtsn {
+			rockchip,pins =
+				/* uart6_rtsn */
+				<3 RK_PA5 4 &pcfg_pull_none>;
+		};
+	};
+
+	uart7 {
+		/omit-if-no-ref/
+		uart7m0_xfer: uart7m0-xfer {
+			rockchip,pins =
+				/* uart7_rx_m0 */
+				<3 RK_PB3 4 &pcfg_pull_up>,
+				/* uart7_tx_m0 */
+				<3 RK_PB2 4 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart7m0_ctsn: uart7m0-ctsn {
+			rockchip,pins =
+				/* uart7m0_ctsn */
+				<3 RK_PB0 4 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart7m0_rtsn: uart7m0-rtsn {
+			rockchip,pins =
+				/* uart7m0_rtsn */
+				<3 RK_PB1 4 &pcfg_pull_none>;
+		};
+
+		/omit-if-no-ref/
+		uart7m1_xfer: uart7m1-xfer {
+			rockchip,pins =
+				/* uart7_rx_m1 */
+				<1 RK_PB3 4 &pcfg_pull_up>,
+				/* uart7_tx_m1 */
+				<1 RK_PB2 4 &pcfg_pull_up>;
+		};
+
+		/omit-if-no-ref/
+		uart7m1_ctsn: uart7m1-ctsn {
+			rockchip,pins =
+				/* uart7m1_ctsn */
+				<1 RK_PB0 4 &pcfg_pull_none>;
+		};
+		/omit-if-no-ref/
+		uart7m1_rtsn: uart7m1-rtsn {
+			rockchip,pins =
+				/* uart7m1_rtsn */
+				<1 RK_PB1 4 &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3528-radxa-e20c.dts b/arch/arm64/boot/dts/rockchip/rk3528-radxa-e20c.dts
index d2cdb63d4a9d..57a446b5cbd6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3528-radxa-e20c.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3528-radxa-e20c.dts
@@ -6,17 +6,150 @@
  */
 
 /dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
 #include "rk3528.dtsi"
 
 / {
 	model = "Radxa E20C";
 	compatible = "radxa,e20c", "rockchip,rk3528";
 
+	aliases {
+		mmc0 = &sdhci;
+	};
+
 	chosen {
 		stdout-path = "serial0:1500000n8";
 	};
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		button-maskrom {
+			label = "MASKROM";
+			linux,code = <KEY_SETUP>;
+			press-threshold-microvolt = <0>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&user_key>;
+
+		button-user {
+			gpios = <&gpio0 RK_PA0 GPIO_ACTIVE_LOW>;
+			label = "USER";
+			linux,code = <BTN_1>;
+			wakeup-source;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&lan_led_g>, <&sys_led_g>, <&wan_led_g>;
+
+		led-lan {
+			color = <LED_COLOR_ID_GREEN>;
+			default-state = "off";
+			function = LED_FUNCTION_LAN;
+			gpios = <&gpio4 RK_PB5 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "netdev";
+		};
+
+		led-sys {
+			color = <LED_COLOR_ID_GREEN>;
+			default-state = "on";
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&gpio4 RK_PC1 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		led-wan {
+			color = <LED_COLOR_ID_GREEN>;
+			default-state = "off";
+			function = LED_FUNCTION_WAN;
+			gpios = <&gpio4 RK_PC0 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "netdev";
+		};
+	};
+
+	vcc_1v8: regulator-1v8-vcc {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc_3v3>;
+	};
+
+	vcc_3v3: regulator-3v3-vcc {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_sys: regulator-5v0-vcc-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+};
+
+&pinctrl {
+	gpio-keys {
+		user_key: user-key {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	leds {
+		lan_led_g: lan-led-g {
+			rockchip,pins = <4 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		sys_led_g: sys-led-g {
+			rockchip,pins = <4 RK_PC1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		wan_led_g: wan-led-g {
+			rockchip,pins = <4 RK_PC0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	no-sd;
+	no-sdio;
+	non-removable;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
 };
 
 &uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0m0_xfer>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3528.dtsi b/arch/arm64/boot/dts/rockchip/rk3528.dtsi
index e58faa985aa4..26c3559d6a6d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3528.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3528.dtsi
@@ -4,8 +4,12 @@
  * Copyright (c) 2024 Yao Zi <ziyao@disroot.org>
  */
 
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/clock/rockchip,rk3528-cru.h>
+#include <dt-bindings/reset/rockchip,rk3528-cru.h>
 
 / {
 	compatible = "rockchip,rk3528";
@@ -15,6 +19,11 @@
 	#size-cells = <2>;
 
 	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;
@@ -51,6 +60,7 @@
 			reg = <0x0>;
 			device_type = "cpu";
 			enable-method = "psci";
+			clocks = <&scmi_clk SCMI_CLK_CPU>;
 		};
 
 		cpu1: cpu@1 {
@@ -58,6 +68,7 @@
 			reg = <0x1>;
 			device_type = "cpu";
 			enable-method = "psci";
+			clocks = <&scmi_clk SCMI_CLK_CPU>;
 		};
 
 		cpu2: cpu@2 {
@@ -65,6 +76,7 @@
 			reg = <0x2>;
 			device_type = "cpu";
 			enable-method = "psci";
+			clocks = <&scmi_clk SCMI_CLK_CPU>;
 		};
 
 		cpu3: cpu@3 {
@@ -72,6 +84,22 @@
 			reg = <0x3>;
 			device_type = "cpu";
 			enable-method = "psci";
+			clocks = <&scmi_clk SCMI_CLK_CPU>;
+		};
+	};
+
+	firmware {
+		scmi: scmi {
+			compatible = "arm,scmi-smc";
+			arm,smc-id = <0x82000010>;
+			shmem = <&scmi_shmem>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			scmi_clk: protocol@14 {
+				reg = <0x14>;
+				#clock-cells = <1>;
+			};
 		};
 	};
 
@@ -80,6 +108,18 @@
 		method = "smc";
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		scmi_shmem: shmem@10f000 {
+			compatible = "arm,scmi-shmem";
+			reg = <0x0 0x0010f000 0x0 0x100>;
+			no-map;
+		};
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
@@ -95,6 +135,13 @@
 		#clock-cells = <0>;
 	};
 
+	gmac0_clk: clock-gmac50m {
+		compatible = "fixed-clock";
+		clock-frequency = <50000000>;
+		clock-output-names = "gmac0";
+		#clock-cells = <0>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		ranges = <0x0 0xfe000000 0x0 0xfe000000 0x0 0x2000000>;
@@ -114,10 +161,219 @@
 			#interrupt-cells = <3>;
 		};
 
+		qos_crypto_a: qos@ff200000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200000 0x0 0x20>;
+		};
+
+		qos_crypto_p: qos@ff200080 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200080 0x0 0x20>;
+		};
+
+		qos_dcf: qos@ff200100 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200100 0x0 0x20>;
+		};
+
+		qos_dft2apb: qos@ff200200 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200200 0x0 0x20>;
+		};
+
+		qos_dma2ddr: qos@ff200280 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200280 0x0 0x20>;
+		};
+
+		qos_dmac: qos@ff200300 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200300 0x0 0x20>;
+		};
+
+		qos_keyreader: qos@ff200380 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff200380 0x0 0x20>;
+		};
+
+		qos_cpu: qos@ff210000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff210000 0x0 0x20>;
+		};
+
+		qos_debug: qos@ff210080 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff210080 0x0 0x20>;
+		};
+
+		qos_gpu_m0: qos@ff220000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff220000 0x0 0x20>;
+		};
+
+		qos_gpu_m1: qos@ff220080 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff220080 0x0 0x20>;
+		};
+
+		qos_pmu_mcu: qos@ff240000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff240000 0x0 0x20>;
+		};
+
+		qos_rkvdec: qos@ff250000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff250000 0x0 0x20>;
+		};
+
+		qos_rkvenc: qos@ff260000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff260000 0x0 0x20>;
+		};
+
+		qos_gmac0: qos@ff270000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270000 0x0 0x20>;
+		};
+
+		qos_hdcp: qos@ff270080 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270080 0x0 0x20>;
+		};
+
+		qos_jpegdec: qos@ff270100 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270100 0x0 0x20>;
+		};
+
+		qos_rga2_m0ro: qos@ff270200 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270200 0x0 0x20>;
+		};
+
+		qos_rga2_m0wo: qos@ff270280 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270280 0x0 0x20>;
+		};
+
+		qos_sdmmc0: qos@ff270300 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270300 0x0 0x20>;
+		};
+
+		qos_usb2host: qos@ff270380 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270380 0x0 0x20>;
+		};
+
+		qos_vdpp: qos@ff270480 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270480 0x0 0x20>;
+		};
+
+		qos_vop: qos@ff270500 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff270500 0x0 0x20>;
+		};
+
+		qos_emmc: qos@ff280000 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280000 0x0 0x20>;
+		};
+
+		qos_fspi: qos@ff280080 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280080 0x0 0x20>;
+		};
+
+		qos_gmac1: qos@ff280100 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280100 0x0 0x20>;
+		};
+
+		qos_pcie: qos@ff280180 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280180 0x0 0x20>;
+		};
+
+		qos_sdio0: qos@ff280200 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280200 0x0 0x20>;
+		};
+
+		qos_sdio1: qos@ff280280 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280280 0x0 0x20>;
+		};
+
+		qos_tsp: qos@ff280300 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280300 0x0 0x20>;
+		};
+
+		qos_usb3otg: qos@ff280380 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280380 0x0 0x20>;
+		};
+
+		qos_vpu: qos@ff280400 {
+			compatible = "rockchip,rk3528-qos", "syscon";
+			reg = <0x0 0xff280400 0x0 0x20>;
+		};
+
+		cru: clock-controller@ff4a0000 {
+			compatible = "rockchip,rk3528-cru";
+			reg = <0x0 0xff4a0000 0x0 0x30000>;
+			assigned-clocks =
+				<&cru XIN_OSC0_DIV>, <&cru PLL_GPLL>,
+				<&cru PLL_PPLL>, <&cru PLL_CPLL>,
+				<&cru ARMCLK>, <&cru CLK_MATRIX_250M_SRC>,
+				<&cru CLK_MATRIX_500M_SRC>,
+				<&cru CLK_MATRIX_50M_SRC>,
+				<&cru CLK_MATRIX_100M_SRC>,
+				<&cru CLK_MATRIX_150M_SRC>,
+				<&cru CLK_MATRIX_200M_SRC>,
+				<&cru CLK_MATRIX_300M_SRC>,
+				<&cru CLK_MATRIX_339M_SRC>,
+				<&cru CLK_MATRIX_400M_SRC>,
+				<&cru CLK_MATRIX_600M_SRC>,
+				<&cru CLK_PPLL_50M_MATRIX>,
+				<&cru CLK_PPLL_100M_MATRIX>,
+				<&cru CLK_PPLL_125M_MATRIX>,
+				<&cru ACLK_BUS_VOPGL_ROOT>;
+			assigned-clock-rates =
+				<32768>, <1188000000>,
+				<1000000000>, <996000000>,
+				<408000000>, <250000000>,
+				<500000000>,
+				<50000000>,
+				<100000000>,
+				<150000000>,
+				<200000000>,
+				<300000000>,
+				<340000000>,
+				<400000000>,
+				<600000000>,
+				<50000000>,
+				<100000000>,
+				<125000000>,
+				<500000000>;
+			clocks = <&xin24m>, <&gmac0_clk>;
+			clock-names = "xin24m", "gmac0";
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		ioc_grf: syscon@ff540000 {
+			compatible = "rockchip,rk3528-ioc-grf", "syscon";
+			reg = <0x0 0xff540000 0x0 0x40000>;
+		};
+
 		uart0: serial@ff9f0000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xff9f0000 0x0 0x100>;
-			clock-frequency = <24000000>;
+			clocks = <&cru SCLK_UART0>, <&cru PCLK_UART0>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -127,6 +383,8 @@
 		uart1: serial@ff9f8000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xff9f8000 0x0 0x100>;
+			clocks = <&cru SCLK_UART1>, <&cru PCLK_UART1>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -136,6 +394,8 @@
 		uart2: serial@ffa00000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xffa00000 0x0 0x100>;
+			clocks = <&cru SCLK_UART2>, <&cru PCLK_UART2>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -144,6 +404,8 @@
 
 		uart3: serial@ffa08000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
+			clocks = <&cru SCLK_UART3>, <&cru PCLK_UART3>;
+			clock-names = "baudclk", "apb_pclk";
 			reg = <0x0 0xffa08000 0x0 0x100>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -153,6 +415,8 @@
 		uart4: serial@ffa10000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xffa10000 0x0 0x100>;
+			clocks = <&cru SCLK_UART4>, <&cru PCLK_UART4>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -162,6 +426,8 @@
 		uart5: serial@ffa18000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xffa18000 0x0 0x100>;
+			clocks = <&cru SCLK_UART5>, <&cru PCLK_UART5>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -171,6 +437,8 @@
 		uart6: serial@ffa20000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xffa20000 0x0 0x100>;
+			clocks = <&cru SCLK_UART6>, <&cru PCLK_UART6>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
@@ -180,10 +448,118 @@
 		uart7: serial@ffa28000 {
 			compatible = "rockchip,rk3528-uart", "snps,dw-apb-uart";
 			reg = <0x0 0xffa28000 0x0 0x100>;
+			clocks = <&cru SCLK_UART7>, <&cru PCLK_UART7>;
+			clock-names = "baudclk", "apb_pclk";
 			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
 			reg-io-width = <4>;
 			reg-shift = <2>;
 			status = "disabled";
 		};
+
+		saradc: adc@ffae0000 {
+			compatible = "rockchip,rk3528-saradc";
+			reg = <0x0 0xffae0000 0x0 0x10000>;
+			clocks = <&cru CLK_SARADC>, <&cru PCLK_SARADC>;
+			clock-names = "saradc", "apb_pclk";
+			interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
+			resets = <&cru SRST_P_SARADC>;
+			reset-names = "saradc-apb";
+			#io-channel-cells = <1>;
+			status = "disabled";
+		};
+
+		sdhci: mmc@ffbf0000 {
+			compatible = "rockchip,rk3528-dwcmshc",
+				     "rockchip,rk3588-dwcmshc";
+			reg = <0x0 0xffbf0000 0x0 0x10000>;
+			assigned-clocks = <&cru BCLK_EMMC>, <&cru TCLK_EMMC>,
+					  <&cru CCLK_SRC_EMMC>;
+			assigned-clock-rates = <200000000>, <24000000>,
+					       <200000000>;
+			clocks = <&cru CCLK_SRC_EMMC>, <&cru HCLK_EMMC>,
+				 <&cru ACLK_EMMC>, <&cru BCLK_EMMC>,
+				 <&cru TCLK_EMMC>;
+			clock-names = "core", "bus", "axi", "block", "timer";
+			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
+			max-frequency = <200000000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&emmc_bus8>, <&emmc_clk>, <&emmc_cmd>,
+				    <&emmc_strb>;
+			resets = <&cru SRST_C_EMMC>, <&cru SRST_H_EMMC>,
+				 <&cru SRST_A_EMMC>, <&cru SRST_B_EMMC>,
+				 <&cru SRST_T_EMMC>;
+			reset-names = "core", "bus", "axi", "block", "timer";
+			status = "disabled";
+		};
+
+		pinctrl: pinctrl {
+			compatible = "rockchip,rk3528-pinctrl";
+			rockchip,grf = <&ioc_grf>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			gpio0: gpio@ff610000 {
+				compatible = "rockchip,gpio-bank";
+				reg = <0x0 0xff610000 0x0 0x200>;
+				clocks = <&cru PCLK_GPIO0>, <&cru DBCLK_GPIO0>;
+				interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&pinctrl 0 0 32>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio1: gpio@ffaf0000 {
+				compatible = "rockchip,gpio-bank";
+				reg = <0x0 0xffaf0000 0x0 0x200>;
+				clocks = <&cru PCLK_GPIO1>, <&cru DBCLK_GPIO1>;
+				interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&pinctrl 0 32 32>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio2: gpio@ffb00000 {
+				compatible = "rockchip,gpio-bank";
+				reg = <0x0 0xffb00000 0x0 0x200>;
+				clocks = <&cru PCLK_GPIO2>, <&cru DBCLK_GPIO2>;
+				interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&pinctrl 0 64 32>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio3: gpio@ffb10000 {
+				compatible = "rockchip,gpio-bank";
+				reg = <0x0 0xffb10000 0x0 0x200>;
+				clocks = <&cru PCLK_GPIO3>, <&cru DBCLK_GPIO3>;
+				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&pinctrl 0 96 32>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio4: gpio@ffb20000 {
+				compatible = "rockchip,gpio-bank";
+				reg = <0x0 0xffb20000 0x0 0x200>;
+				clocks = <&cru PCLK_GPIO4>, <&cru DBCLK_GPIO4>;
+				interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				gpio-ranges = <&pinctrl 0 128 32>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+		};
 	};
 };
+
+#include "rk3528-pinctrl.dtsi"
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
index a48351471764..e7ba477e75f9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
@@ -775,7 +775,7 @@
 	rockchip,default-sample-phase = <90>;
 	status = "okay";
 
-	sdio-wifi@1 {
+	wifi@1 {
 		compatible = "brcm,bcm4329-fmac";
 		reg = <1>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
index 61dd71c259aa..ddf84c2a19cf 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
@@ -512,7 +512,6 @@
 
 &sdmmc0 {
 	max-frequency = <150000000>;
-	supports-sd;
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
index 2d3ae1544822..3613661417b2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
@@ -9,6 +9,8 @@
 #include "rk3566.dtsi"
 
 / {
+	chassis-type = "tablet";
+
 	aliases {
 		mmc0 = &sdhci;
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
index 98e75df8b158..3c127c5c2607 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
@@ -265,8 +265,12 @@
 };
 
 &gmac1 {
-	assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>;
-	assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>, <&gmac1_clkin>;
+	assigned-clocks = <&cru SCLK_GMAC1_RX_TX>,
+			  <&cru SCLK_GMAC1_RGMII_SPEED>,
+			  <&cru SCLK_GMAC1>;
+	assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>,
+				 <&cru SCLK_GMAC1>,
+				 <&gmac1_clkin>;
 	clock_in_out = "input";
 	phy-supply = <&vcc_3v3>;
 	phy-mode = "rgmii";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
index 24928a129446..5707321a1144 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
@@ -173,8 +173,12 @@
 };
 
 &gmac1 {
-	assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>;
-	assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru SCLK_GMAC1>, <&gmac1_clkin>;
+	assigned-clocks = <&cru SCLK_GMAC1_RX_TX>,
+			  <&cru SCLK_GMAC1_RGMII_SPEED>,
+			  <&cru SCLK_GMAC1>;
+	assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>,
+				 <&cru SCLK_GMAC1>,
+				 <&gmac1_clkin>;
 	clock_in_out = "input";
 	phy-mode = "rgmii";
 	phy-supply = <&vcc_3v3>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-photonicat.dts b/arch/arm64/boot/dts/rockchip/rk3568-photonicat.dts
new file mode 100644
index 000000000000..58c1052ba8ef
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3568-photonicat.dts
@@ -0,0 +1,588 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include "rk3568.dtsi"
+
+/ {
+	model = "Ariaboard Photonicat";
+	compatible = "ariaboard,photonicat", "rockchip,rk3568";
+
+	aliases {
+		ethernet0 = &gmac0;
+		ethernet1 = &gmac1;
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc0;
+		mmc2 = &sdmmc1;
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		device-chemistry = "lithium-ion";
+		charge-full-design-microamp-hours = <6800000>;
+		energy-full-design-microwatt-hours = <25000000>;
+		voltage-max-design-microvolt = <4200000>;
+		voltage-min-design-microvolt = <3400000>;
+
+		ocv-capacity-celsius = <25>;
+		ocv-capacity-table-0 =  <4100000 100>, <4040000 90>,
+					<3980000 80>, <3920000 70>,
+					<3870000 60>, <3820000 50>,
+					<3790000 40>, <3770000 30>,
+					<3740000 20>, <3680000 10>,
+					<3450000 0>;
+	};
+
+	chosen: chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	hdmi_con: hdmi-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	vcc_1v8: regulator-vcc-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vcc_3v3: regulator-vcc-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	/* actually fed by vcc_syson, dependent
+	 * on pi6c clock generator
+	 */
+	vcc3v3_pcie: regulator-vcc3v3-pcie {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_pcie";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc3v3_pi6c>;
+	};
+
+	/* pi6c pcie clock generator */
+	vcc3v3_pi6c: regulator-vcc3v3-pi6c {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie_pwren_h>;
+		regulator-name = "vcc3v3_pi6c";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_syson>;
+	};
+
+	vcc3v3_sd: regulator-vcc3v3-sd {
+		compatible = "regulator-fixed";
+		gpio = <&gpio0 RK_PB6 GPIO_ACTIVE_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&sdmmc0_pwren>;
+		regulator-boot-on;
+		regulator-name = "vcc3v3_sd";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_3v3>;
+	};
+
+	vcc3v3_sys: regulator-vcc3v3-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_syson>;
+	};
+
+	vcc3v4_rf: regulator-vcc3v4-rf {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&rf_pwr_en>;
+		regulator-name = "vcc3v4_rf";
+		regulator-min-microvolt = <3400000>;
+		regulator-max-microvolt = <3400000>;
+		vin-supply = <&vccin_5v>;
+	};
+
+	vcc5v0_usb30_otg0: regulator-vcc5v0-usb30-otg0 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_host_pwren_h>;
+		regulator-name = "vcc5v0_usb30_otg0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vccin_5v>;
+	};
+
+	vccin_5v: regulator-vccin-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "vccin_5v";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	vcc_sysin: regulator-vcc-sysin {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_sysin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vccin_5v>;
+	};
+
+	vcc_syson: regulator-vcc-syson {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_syson";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc_sysin>;
+	};
+
+	vcca_1v8: regulator-vcca-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcca_1v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vdda_0v9: regulator-vdda-0v9 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdda_0v9";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <900000>;
+		regulator-max-microvolt = <900000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vdd_gpu: regulator-vdd-gpu {
+		compatible = "pwm-regulator";
+		pwms = <&pwm2 0 5000 1>;
+		pwm-supply = <&vcc_syson>;
+		regulator-name = "vdd_gpu";
+		regulator-min-microvolt = <800000>;
+		regulator-max-microvolt = <1350000>;
+		regulator-ramp-delay = <6001>;
+		regulator-settling-time-up-us = <250>;
+	};
+
+	vdd_logic: regulator-vdd-logic {
+		compatible = "pwm-regulator";
+		pwms = <&pwm1 0 5000 1>;
+		pwm-supply = <&vcc_syson>;
+		regulator-name = "vdd_logic";
+		regulator-min-microvolt = <500000>;
+		regulator-max-microvolt = <1350000>;
+		regulator-ramp-delay = <6001>;
+		regulator-settling-time-up-us = <250>;
+	};
+
+	rfkill-modem {
+		compatible = "rfkill-gpio";
+		label = "M.2 USB Modem";
+		radio-type = "wwan";
+		shutdown-gpios = <&gpio4 RK_PC4 GPIO_ACTIVE_HIGH>;
+	};
+
+	wifi_pwrseq: wifi-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&pmucru CLK_RTC_32K>;
+		clock-names = "ext_clock";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_reg_on_h &clk32k_out1>;
+		post-power-on-delay-ms = <200>;
+		reset-gpios = <&gpio2 RK_PB1 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&combphy0 {
+	status = "okay";
+};
+
+&combphy1 {
+	status = "okay";
+};
+
+&combphy2 {
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+/* Motorcomm YT8521SC LAN port (require SGMII) */
+&gmac0 {
+	status = "disabled";
+};
+
+/* Motorcomm YT8521SC WAN port */
+&gmac1 {
+	assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1>;
+	assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>;
+	assigned-clock-rates = <0>, <125000000>;
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii-id";
+	phy-supply = <&vcc_3v3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac1m1_miim
+		     &gmac1m1_tx_bus2
+		     &gmac1m1_rx_bus2
+		     &gmac1m1_rgmii_clk
+		     &gmac1m1_rgmii_bus>;
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu>;
+	status = "okay";
+};
+
+&hdmi {
+	avdd-0v9-supply = <&vdda_0v9>;
+	avdd-1v8-supply = <&vcca_1v8>;
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdmi_sound {
+	status = "okay";
+};
+
+&i2c0 {
+	status = "okay";
+
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <800000>;
+		regulator-max-microvolt = <1150000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_syson>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2m1_xfer>;
+	status = "okay";
+};
+
+&i2s0_8ch {
+	status = "okay";
+};
+
+&mdio1 {
+	rgmii_phy: ethernet-phy@3 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x3>;
+		reset-assert-us = <20000>;
+		reset-deassert-us = <100000>;
+		reset-gpios = <&gpio4 RK_PC0 GPIO_ACTIVE_LOW>;
+		rx-internal-delay-ps = <1500>;
+		tx-internal-delay-ps = <1500>;
+	};
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+/* M.2 E-Key for PCIe WLAN */
+&pcie3x2 {
+	max-link-speed = <1>;
+	num-lanes = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie30x1m0_pins>;
+	reset-gpios = <&gpio0 RK_PC3 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_pcie>;
+	status = "okay";
+};
+
+&pinctrl {
+	bt {
+		bt_reg_on_h: bt-reg-on-h {
+			rockchip,pins = <2 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie {
+		pcie_pwren_h: pcie-pwren-h {
+			rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	sdmmc0 {
+		sdmmc0_pwren: sdmmc0-pwren {
+			rockchip,pins = <0 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		rf_pwr_en: rf-pwr-en {
+			rockchip,pins = <4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usb_host_pwren_h: usb-host-pwren-h {
+			rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	wifi {
+		wifi_reg_on_h: wifi-reg-on-h {
+			rockchip,pins = <2 RK_PB1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pmu_io_domains {
+	pmuio1-supply = <&vcc_3v3>;
+	pmuio2-supply = <&vcc_3v3>;
+	vccio1-supply = <&vcc_3v3>;
+	vccio2-supply = <&vcc_1v8>;
+	vccio3-supply = <&vcc_3v3>;
+	vccio4-supply = <&vcc_1v8>;
+	vccio5-supply = <&vcc_3v3>;
+	vccio6-supply = <&vcc_3v3>;
+	vccio7-supply = <&vcc_3v3>;
+	status = "okay";
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcca_1v8>;
+	status = "okay";
+};
+
+/* eMMC */
+&sdhci {
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	mmc-hs200-1_8v;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+/* Micro SD card slot */
+&sdmmc0 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	no-1-8-v;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd>;
+	vmmc-supply = <&vcc3v3_sd>;
+	vqmmc-supply = <&vcc_3v3>;
+	status = "okay";
+};
+
+/* Qualcomm Atheros QCA9377 WiFi */
+&sdmmc1 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc1_bus4 &sdmmc1_cmd &sdmmc1_clk>;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc3v3_sys>;
+	vqmmc-supply = <&vcc_1v8>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	wifi: wifi@1 {
+		reg = <1>;
+		interrupt-parent = <&gpio2>;
+		interrupts = <RK_PB2 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "host-wake";
+	};
+};
+
+&tsadc {
+	rockchip,hw-tshut-mode = <1>;
+	rockchip,hw-tshut-polarity = <0>;
+	status = "okay";
+};
+
+/* Qualcomm Atheros QCA9377 Bluetooth */
+&uart1 {
+	dma-names = "tx", "rx";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn &uart1m0_rtsn>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "qcom,qca9377-bt";
+		clocks = <&pmucru CLK_RTC_32K>;
+		enable-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_reg_on_h>;
+		vddio-supply = <&vcc_1v8>;
+	};
+};
+
+/* Debug UART */
+&uart2 {
+	status = "okay";
+};
+
+&uart3 {
+	dma-names = "tx", "rx";
+	status = "okay";
+};
+
+/* Onboard power management MCU */
+&uart4 {
+	dma-names = "tx", "rx";
+	status = "okay";
+};
+
+/* M.2 E-Key for USB Bluetooth */
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+/* USB Type-A Port */
+&usb_host0_xhci {
+	dr_mode = "host";
+	status = "okay";
+};
+
+/* M.2 B-Key for USB Modem WWAN */
+&usb_host1_xhci {
+	status = "okay";
+};
+
+&usb2phy0 {
+	status = "okay";
+};
+
+&usb2phy0_host {
+	phy-supply = <&vcc3v4_rf>;
+	status = "okay";
+};
+
+&usb2phy0_otg {
+	phy-supply = <&vcc5v0_usb30_otg0>;
+	status = "okay";
+};
+
+&usb2phy1 {
+	status = "okay";
+};
+
+&usb2phy1_otg {
+	phy-supply = <&vcc5v0_usb30_otg0>;
+	status = "okay";
+};
+
+&vop {
+	assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>;
+	assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>;
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
+
+&xin32k {
+	pinctrl-names = "default";
+	pinctrl-0 = <&clk32k_out1>;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
index 7bd32d230ad2..b80d628c426b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
@@ -619,6 +619,8 @@
 	bus-width = <8>;
 	max-frequency = <200000000>;
 	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd &emmc_datastrobe>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
index ac79140a9ecd..44cfdfeed668 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
@@ -778,20 +778,6 @@
 	pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn &uart1m0_rtsn>;
 	uart-has-rtscts;
 	status = "okay";
-
-	bluetooth {
-		compatible = "brcm,bcm43438-bt";
-		clocks = <&rk809 1>;
-		clock-names = "lpo";
-		device-wakeup-gpios = <&gpio4 RK_PB5 GPIO_ACTIVE_HIGH>;
-		host-wakeup-gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>;
-		shutdown-gpios = <&gpio4 RK_PB2 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&bt_host_wake &bt_wake &bt_enable>;
-		vbat-supply = <&vcc3v3_sys>;
-		vddio-supply = <&vcc_1v8>;
-		/* vddio comes from regulator on module, use IO bank voltage instead */
-	};
 };
 
 &uart2 {
diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
index e55390629114..fd2214b6fad4 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi
@@ -174,6 +174,18 @@
 		method = "smc";
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		scmi_shmem: shmem@10f000 {
+			compatible = "arm,scmi-shmem";
+			reg = <0x0 0x0010f000 0x0 0x100>;
+			no-map;
+		};
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>,
@@ -199,19 +211,6 @@
 		#clock-cells = <0>;
 	};
 
-	sram@10f000 {
-		compatible = "mmio-sram";
-		reg = <0x0 0x0010f000 0x0 0x100>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0x0 0x0010f000 0x100>;
-
-		scmi_shmem: sram@0 {
-			compatible = "arm,scmi-shmem";
-			reg = <0x0 0x100>;
-		};
-	};
-
 	sata1: sata@fc400000 {
 		compatible = "rockchip,rk3568-dwc-ahci", "snps,dwc-ahci";
 		reg = <0 0xfc400000 0 0x1000>;
@@ -284,6 +283,18 @@
 		mbi-alias = <0x0 0xfd410000>;
 		mbi-ranges = <296 24>;
 		msi-controller;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-noncoherent;
+
+		its: msi-controller@fd440000 {
+			compatible = "arm,gic-v3-its";
+			reg = <0x0 0xfd440000 0 0x20000>;
+			dma-noncoherent;
+			msi-controller;
+			#msi-cells = <1>;
+		};
 	};
 
 	usb_host0_ehci: usb@fd800000 {
@@ -957,7 +968,7 @@
 		num-ib-windows = <6>;
 		num-ob-windows = <2>;
 		max-link-speed = <2>;
-		msi-map = <0x0 &gic 0x0 0x1000>;
+		msi-map = <0x0 &its 0x0 0x1000>;
 		num-lanes = <1>;
 		phys = <&combphy2 PHY_TYPE_PCIE>;
 		phy-names = "pcie-phy";
@@ -1032,6 +1043,11 @@
 		status = "disabled";
 	};
 
+	/*
+	 * Testing showed that the HWRNG found in RK3566 produces unacceptably
+	 * low quality of random data, so the HWRNG isn't enabled for all RK356x
+	 * SoC variants despite its presence.
+	 */
 	rng: rng@fe388000 {
 		compatible = "rockchip,rk3568-rng";
 		reg = <0x0 0xfe388000 0x0 0x4000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
index 7c7331936a7f..314067ba6f3c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
@@ -10,6 +10,7 @@
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/rockchip.h>
 #include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
 #include <dt-bindings/usb/pd.h>
 #include "rk3576.dtsi"
 
@@ -26,6 +27,17 @@
 		stdout-path = "serial0:1500000n8";
 	};
 
+	hdmi-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
 	leds: leds {
 		compatible = "gpio-leds";
 
@@ -182,8 +194,7 @@
 		     &eth0m0_tx_bus2
 		     &eth0m0_rx_bus2
 		     &eth0m0_rgmii_clk
-		     &eth0m0_rgmii_bus
-		     &ethm0_clk0_25m_out>;
+		     &eth0m0_rgmii_bus>;
 
 	phy-handle = <&rgmii_phy0>;
 	status = "okay";
@@ -214,6 +225,26 @@
 	status = "okay";
 };
 
+&hdmi {
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdptxphy {
+	status = "okay";
+};
+
 &i2c1 {
 	status = "okay";
 
@@ -579,7 +610,7 @@
 		reg = <0x51>;
 		clock-output-names = "hym8563";
 		interrupt-parent = <&gpio0>;
-		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&hym8563_int>;
 		wakeup-source;
@@ -656,3 +687,18 @@
 	pinctrl-0 = <&uart0m0_xfer>;
 	status = "okay";
 };
+
+&vop {
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts
index 782ca000a644..e368691fd28e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3576-evb1-v10.dts
@@ -10,6 +10,7 @@
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
 #include "rk3576.dtsi"
 
 / {
@@ -57,6 +58,17 @@
 		};
 	};
 
+	hdmi-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
 	leds: leds {
 		compatible = "gpio-leds";
 
@@ -270,6 +282,26 @@
 	status = "okay";
 };
 
+&hdmi {
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdptxphy {
+	status = "okay";
+};
+
 &i2c1 {
 	status = "okay";
 
@@ -729,3 +761,18 @@
 	dr_mode = "host";
 	status = "okay";
 };
+
+&vop {
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3576-roc-pc.dts
new file mode 100644
index 000000000000..612b7bb0b749
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3576-roc-pc.dts
@@ -0,0 +1,736 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2024 Firefly Technology Co. Ltd
+ * Copyright (c) 2024 Heiko Stuebner <heiko@sntech.de>
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/usb/pd.h>
+#include "rk3576.dtsi"
+
+/ {
+	model = "Firefly ROC-RK3576-PC";
+	compatible = "firefly,roc-rk3576-pc", "rockchip,rk3576";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc;
+	};
+
+	chosen {
+		stdout-path = "serial0:1500000n8";
+	};
+
+	adc-keys-0 {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		button-maskrom {
+			label = "Maskrom";
+			linux,code = <KEY_SETUP>;
+			press-threshold-microvolt = <17000>;
+		};
+	};
+
+	adc-keys-1 {
+		compatible = "adc-keys";
+		io-channels = <&saradc 1>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		button-recovery {
+			label = "Recovery";
+			linux,code = <KEY_VENDOR>;
+			press-threshold-microvolt = <17000>;
+		};
+	};
+
+	vbus5v0_typec: regulator-vbus5v0-typec {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PD1 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_otg0_pwren_h>;
+		regulator-name = "vbus5v0_typec";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_device_s0>;
+	};
+
+	vcc12v_dcin: regulator-vcc12v-dcin {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc12v_dcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	vcc1v2_ufs_vccq_s0: regulator-vcc1v2-ufs-vccq-s0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc1v2_ufs_vccq_s0";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		vin-supply = <&vcc5v0_sys_s5>;
+	};
+
+	vcc1v8_ufs_vccq2_s0: regulator-vcc1v8-ufs-vccq2-s0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc1v8_ufs_vccq2_s0";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc_1v8_s3>;
+	};
+
+	vcc3v3_pcie: regulator-vcc3v3-pcie {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 RK_PB3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie_pwren_h>;
+		regulator-name = "vcc3v3_pcie";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <5000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc3v3_rtc_s5: regulator-vcc3v3-rtc-s5 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_rtc_s5";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc5v0_sys_s5>;
+	};
+
+	vcc5v0_device_s0: regulator-vcc5v0-device-s0 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5vd_en>;
+		regulator-name = "vcc5v0_device";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_sys_s5: regulator-vcc5v0-sys-s5 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usb20_host1: regulator-vcc5v0-usb20-host1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio0 RK_PC7 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb3_host_pwren_h>;
+		regulator-name = "vcc5v0_host1";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_device_s0>;
+	};
+
+	vcc_1v1_nldo_s3: regulator-vcc-1v1-nldo-s3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys_s5>;
+	};
+
+	vcc_1v8_s0: regulator-vcc-1v8-s0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v8_s0";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vcc_1v8_s3>;
+	};
+
+	vcc_2v0_pldo_s3: regulator-vcc-2v0-pldo-s3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_2v0_pldo_s3";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <2000000>;
+		regulator-max-microvolt = <2000000>;
+		vin-supply = <&vcc5v0_sys_s5>;
+	};
+
+	vcc_3v3_s0: regulator-vcc-3v3-s0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v3_s0";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc_ufs_s0: regulator-vcc-ufs-s0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_ufs_s0";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc5v0_sys_s5>;
+	};
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu_s0>;
+	status = "okay";
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	pinctrl-names = "default";
+	pinctrl-0 = <&eth0m0_miim
+		     &eth0m0_tx_bus2
+		     &eth0m0_rx_bus2
+		     &eth0m0_rgmii_clk
+		     &eth0m0_rgmii_bus
+		     &ethm0_clk0_25m_out>;
+	/* Use rgmii-rxid mode to disable rx delay inside Soc */
+	phy-mode = "rgmii-rxid";
+	phy-handle = <&rgmii_phy0>;
+	tx_delay = <0x21>;
+	status = "okay";
+};
+
+&mdio0 {
+	status = "okay";
+
+	rgmii_phy0: phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x1>;
+		clocks = <&cru REFCLKO25M_GMAC0_OUT>;
+		/* Reset time is 20ms, 100ms for rtl8211f */
+		reset-delay-us = <20000>;
+		reset-gpios = <&gpio2 RK_PB5 GPIO_ACTIVE_LOW>;
+		reset-post-delay-us = <100000>;
+	};
+};
+
+&i2c1 {
+	status = "okay";
+
+	pmic@23 {
+		compatible = "rockchip,rk806";
+		reg = <0x23>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		system-power-controller;
+
+		vcc1-supply = <&vcc5v0_sys_s5>;
+		vcc2-supply = <&vcc5v0_sys_s5>;
+		vcc3-supply = <&vcc5v0_sys_s5>;
+		vcc4-supply = <&vcc5v0_sys_s5>;
+		vcc5-supply = <&vcc5v0_sys_s5>;
+		vcc6-supply = <&vcc5v0_sys_s5>;
+		vcc7-supply = <&vcc5v0_sys_s5>;
+		vcc8-supply = <&vcc5v0_sys_s5>;
+		vcc9-supply = <&vcc5v0_sys_s5>;
+		vcc10-supply = <&vcc5v0_sys_s5>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys_s5>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys_s5>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs1_slp: dvs1-slp-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun1";
+		};
+
+		rk806_dvs1_pwrdn: dvs1-pwrdn-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs1_rst: dvs1-rst-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs2_slp: dvs2-slp-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun1";
+		};
+
+		rk806_dvs2_pwrdn: dvs2-pwrdn-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs2_rst: dvs2-rst-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs2_dvs: dvs2-dvs-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun4";
+		};
+
+		rk806_dvs2_gpio: dvs2-gpio-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun5";
+		};
+
+		rk806_dvs3_slp: dvs3-slp-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun1";
+		};
+
+		rk806_dvs3_pwrdn: dvs3-pwrdn-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs3_rst: dvs3-rst-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs3_dvs: dvs3-dvs-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun4";
+		};
+
+		rk806_dvs3_gpio: dvs3-gpio-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun5";
+		};
+
+		regulators {
+			vdd_cpu_big_s0: dcdc-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_cpu_big_s0";
+				regulator-enable-ramp-delay = <400>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_npu_s0: dcdc-reg2 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_npu_s0";
+				regulator-enable-ramp-delay = <400>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: dcdc-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vdd_gpu_s0: dcdc-reg5 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vddq_ddr_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_logic_s0: dcdc-reg7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <800000>;
+				regulator-name = "vdd_logic_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vdd2_ddr_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg10 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vdd_ddr_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_1v8_s0: pldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca_1v8_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca1v8_pldo2_s0: pldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pldo2_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_1v2_s0: pldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vdda_1v2_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_3v3_s0: pldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcca_3v3_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca1v8_pldo6_s3: pldo-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pldo6_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdda_ddr_pll_s0: nldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdda_ddr_pll_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda0v75_hdmi_s0: nldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <837500>;
+				regulator-max-microvolt = <837500>;
+				regulator-name = "vdda0v75_hdmi_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v85_s0: nldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdda_0v85_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v75_s0: nldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdda_0v75_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	/* pc9202 watchdog@3c with enable-gpio gpio0-c3 */
+
+	/* hnyetek,husb311 typec-portc@4e */
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtc_int_l>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
+		wakeup-source;
+	};
+};
+
+&saradc {
+	vref-supply = <&vcca_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	max-frequency = <200000000>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	full-pwr-cycle-in-suspend;
+	status = "okay";
+};
+
+&sdmmc {
+	max-frequency = <200000000>;
+	no-sdio;
+	no-mmc;
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&pinctrl {
+	hym8563 {
+		rtc_int_l: rtc-int-l {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	power {
+		vcc5vd_en: vcc5vd-en {
+			rockchip,pins = <2 RK_PC0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie_pwren_h: pcie-pwren-h {
+			rockchip,pins = <2 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		hub_reset_h: hub-reset-h {
+			rockchip,pins = <2 RK_PB1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usb3_host_pwren_h: usb3-host-pwren-h {
+			rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usb_otg0_pwren_h: usb-otg0-pwren-h {
+			rockchip,pins = <0 RK_PD1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usbc0_int_l: usbc0-int-l {
+			rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	watchdog {
+		wd_en: wd-en {
+			rockchip,pins = <0 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&uart0 {
+	pinctrl-0 = <&uart0m0_xfer>;
+	status = "okay";
+};
+
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart4m1_xfer &uart4m1_ctsn>;
+	status = "okay";
+};
+
+/* On the extension pin header */
+&uart6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart6m3_xfer>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3576-rock-4d.dts b/arch/arm64/boot/dts/rockchip/rk3576-rock-4d.dts
new file mode 100644
index 000000000000..6756403111e7
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3576-rock-4d.dts
@@ -0,0 +1,751 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2024 Radxa Computer (Shenzhen) Co., Ltd.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include <dt-bindings/usb/pd.h>
+#include "rk3576.dtsi"
+
+/ {
+	model = "Radxa ROCK 4D";
+	compatible = "radxa,rock-4d", "rockchip,rk3576";
+
+	aliases {
+		ethernet0 = &gmac0;
+		mmc0 = &sdmmc;
+	};
+
+	chosen {
+		stdout-path = "serial0:1500000n8";
+	};
+
+	hdmi-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	leds: leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_rgb_g &led_rgb_r>;
+
+		power-led {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			gpios = <&gpio0 RK_PB4 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "default-on";
+		};
+
+		user-led {
+			color = <LED_COLOR_ID_BLUE>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	vcc_12v0_dcin: regulator-vcc-12v0-dcin {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-name = "vcc_12v0_dcin";
+	};
+
+	vcc_1v1_nldo_s3: regulator-vcc-1v1-nldo-s3 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		regulator-name = "vcc_1v1_nldo_s3";
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_1v2_ufs_vccq_s0: regulator-vcc-1v2-ufs-vccq-s0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-name = "vcc_1v2_ufs_vccq_s0";
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_1v8_s0: regulator-vcc-1v8-s0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-name = "vcc_1v8_s0";
+		vin-supply = <&vcc_1v8_s3>;
+	};
+
+	vcc_1v8_ufs_vccq2_s0: regulator-vcc-1v8-ufs-vccq2-s0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-name = "vcc_1v8_ufs_vccq2_s0";
+		vin-supply = <&vcc_1v8_s3>;
+	};
+
+	vcc_2v0_pldo_s3: regulator-vcc-2v0-pldo-s3 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <2000000>;
+		regulator-max-microvolt = <2000000>;
+		regulator-name = "vcc_2v0_pldo_s3";
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_3v3_pcie: regulator-vcc-3v3-pcie {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio2 RK_PD3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie_pwren>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_3v3_pcie";
+		startup-delay-us = <5000>;
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_3v3_rtc_s5: regulator-vcc-3v3-rtc-s5 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_3v3_rtc_s5";
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_3v3_s0: regulator-vcc-3v3-s0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_3v3_s0";
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc_3v3_ufs_s0: regulator-vcc-ufs-s0 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_3v3_ufs_s0";
+		vin-supply = <&vcc_5v0_sys>;
+	};
+
+	vcc_5v0_device: regulator-vcc-5v0-device {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc_5v0_device";
+		vin-supply = <&vcc_12v0_dcin>;
+	};
+
+	vcc_5v0_host: regulator-vcc-5v0-host {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio0 RK_PD3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_host_pwren>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc5v0_host";
+		vin-supply = <&vcc_5v0_device>;
+	};
+
+	vcc_5v0_sys: regulator-vcc-5v0-sys {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc_5v0_sys";
+		vin-supply = <&vcc_12v0_dcin>;
+	};
+};
+
+&combphy1_psu {
+	status = "okay";
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy0>;
+	phy-mode = "rgmii-id";
+	pinctrl-names = "default";
+	pinctrl-0 = <&eth0m0_miim
+		     &eth0m0_tx_bus2
+		     &eth0m0_rx_bus2
+		     &eth0m0_rgmii_clk
+		     &eth0m0_rgmii_bus
+		     &ethm0_clk0_25m_out>;
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu_s0>;
+	status = "okay";
+};
+
+&hdmi {
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdptxphy {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+
+	pmic@23 {
+		compatible = "rockchip,rk806";
+		reg = <0x23>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		interrupt-parent = <&gpio0>;
+		interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins
+			     &rk806_dvs1_null
+			     &rk806_dvs2_null
+			     &rk806_dvs3_null>;
+		system-power-controller;
+		vcc1-supply = <&vcc_5v0_sys>;
+		vcc2-supply = <&vcc_5v0_sys>;
+		vcc3-supply = <&vcc_5v0_sys>;
+		vcc4-supply = <&vcc_5v0_sys>;
+		vcc5-supply = <&vcc_5v0_sys>;
+		vcc6-supply = <&vcc_5v0_sys>;
+		vcc7-supply = <&vcc_5v0_sys>;
+		vcc8-supply = <&vcc_5v0_sys>;
+		vcc9-supply = <&vcc_5v0_sys>;
+		vcc10-supply = <&vcc_5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc_5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc_5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs1_pwrdn: dvs1-pwrdn-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs1_rst: dvs1-rst-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs1_slp: dvs1-slp-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun1";
+		};
+
+		rk806_dvs2_dvs: dvs2-dvs-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun4";
+		};
+
+		rk806_dvs2_gpio: dvs2-gpio-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun5";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_pwrdn: dvs2-pwrdn-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs2_rst: dvs2-rst-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs2_slp: dvs2-slp-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun1";
+		};
+
+		rk806_dvs3_dvs: dvs3-dvs-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun4";
+		};
+
+		rk806_dvs3_gpio: dvs3-gpio-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun5";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_pwrdn: dvs3-pwrdn-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun2";
+		};
+
+		rk806_dvs3_rst: dvs3-rst-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun3";
+		};
+
+		rk806_dvs3_slp: dvs3-slp-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun1";
+		};
+
+		regulators {
+			vdd_cpu_big_s0: dcdc-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-enable-ramp-delay = <400>;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-name = "vdd_cpu_big_s0";
+				regulator-ramp-delay = <12500>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_npu_s0: dcdc-reg2 {
+				regulator-boot-on;
+				regulator-enable-ramp-delay = <400>;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-name = "vdd_npu_s0";
+				regulator-ramp-delay = <12500>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: dcdc-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-ramp-delay = <12500>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vdd_gpu_s0: dcdc-reg5 {
+				regulator-boot-on;
+				regulator-enable-ramp-delay = <400>;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-ramp-delay = <12500>;
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vddq_ddr_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_logic_s0: dcdc-reg7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <800000>;
+				regulator-name = "vdd_logic_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vdd2_ddr_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg10 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vdd_ddr_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_1v8_s0: pldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca_1v8_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca1v8_pldo2_s0: pldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pldo2_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_1v2_s0: pldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vdda_1v2_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_3v3_s0: pldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcca_3v3_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca1v8_pldo6_s3: pldo-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pldo6_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s3";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdda_ddr_pll_s0: nldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdda_ddr_pll_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda0v75_hdmi_s0: nldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <837500>;
+				regulator-max-microvolt = <837500>;
+				regulator-name = "vdda0v75_hdmi_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v85_s0: nldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdda_0v85_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v75_s0: nldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdda_0v75_s0";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hym8563_int>;
+		wakeup-source;
+	};
+};
+
+&mdio0 {
+	rgmii_phy0: ethernet-phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x1>;
+		clocks = <&cru REFCLKO25M_GMAC0_OUT>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtl8211f_rst>;
+		reset-assert-us = <20000>;
+		reset-deassert-us = <100000>;
+		reset-gpio = <&gpio2 RK_PB5 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pinctrl {
+	hym8563 {
+		hym8563_int: hym8563-int {
+			rockchip,pins = <0 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	leds {
+		led_rgb_g: led-green-en {
+			rockchip,pins = <0 RK_PB4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+		led_rgb_r: led-red-en {
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	rtl8211f {
+		rtl8211f_rst: rtl8211f-rst {
+			rockchip,pins = <2 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie {
+		pcie_pwren: pcie-pwren {
+			rockchip,pins = <2 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		usb_host_pwren: usb-host-pwren {
+			rockchip,pins = <0 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	max-frequency = <200000000>;
+	no-sdio;
+	no-mmc;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+
+&sfc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&fspi0_pins &fspi0_csn0>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <50000000>;
+		spi-rx-bus-width = <4>;
+		spi-tx-bus-width = <1>;
+		vcc-supply = <&vcc_1v8_s3>;
+	};
+};
+
+&u2phy0 {
+	status = "okay";
+};
+
+&u2phy1 {
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-0 = <&uart0m0_xfer>;
+	status = "okay";
+};
+
+&usb_drd1_dwc3 {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&vop {
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi
index 4dde954043ef..ebb5fc8bb8b1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi
@@ -111,7 +111,7 @@
 			reg = <0x0>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <485>;
-			clocks = <&scmi_clk ARMCLK_L>;
+			clocks = <&scmi_clk SCMI_ARMCLK_L>;
 			operating-points-v2 = <&cluster0_opp_table>;
 			#cooling-cells = <2>;
 			dynamic-power-coefficient = <120>;
@@ -124,7 +124,7 @@
 			reg = <0x1>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <485>;
-			clocks = <&scmi_clk ARMCLK_L>;
+			clocks = <&scmi_clk SCMI_ARMCLK_L>;
 			operating-points-v2 = <&cluster0_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -135,7 +135,7 @@
 			reg = <0x2>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <485>;
-			clocks = <&scmi_clk ARMCLK_L>;
+			clocks = <&scmi_clk SCMI_ARMCLK_L>;
 			operating-points-v2 = <&cluster0_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -146,7 +146,7 @@
 			reg = <0x3>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <485>;
-			clocks = <&scmi_clk ARMCLK_L>;
+			clocks = <&scmi_clk SCMI_ARMCLK_L>;
 			operating-points-v2 = <&cluster0_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -157,7 +157,7 @@
 			reg = <0x100>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <1024>;
-			clocks = <&scmi_clk ARMCLK_B>;
+			clocks = <&scmi_clk SCMI_ARMCLK_B>;
 			operating-points-v2 = <&cluster1_opp_table>;
 			#cooling-cells = <2>;
 			dynamic-power-coefficient = <320>;
@@ -170,7 +170,7 @@
 			reg = <0x101>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <1024>;
-			clocks = <&scmi_clk ARMCLK_B>;
+			clocks = <&scmi_clk SCMI_ARMCLK_B>;
 			operating-points-v2 = <&cluster1_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -181,7 +181,7 @@
 			reg = <0x102>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <1024>;
-			clocks = <&scmi_clk ARMCLK_B>;
+			clocks = <&scmi_clk SCMI_ARMCLK_B>;
 			operating-points-v2 = <&cluster1_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -192,7 +192,7 @@
 			reg = <0x103>;
 			enable-method = "psci";
 			capacity-dmips-mhz = <1024>;
-			clocks = <&scmi_clk ARMCLK_B>;
+			clocks = <&scmi_clk SCMI_ARMCLK_B>;
 			operating-points-v2 = <&cluster1_opp_table>;
 			cpu-idle-states = <&CPU_SLEEP>;
 		};
@@ -393,6 +393,11 @@
 		};
 	};
 
+	display_subsystem: display-subsystem {
+		compatible = "rockchip,display-subsystem";
+		ports = <&vop_out>;
+	};
+
 	firmware {
 		scmi: scmi {
 			compatible = "arm,scmi-smc";
@@ -620,6 +625,11 @@
 			};
 		};
 
+		hdptxphy_grf: syscon@26032000 {
+			compatible = "rockchip,rk3576-hdptxphy-grf", "syscon";
+			reg = <0x0 0x26032000 0x0 0x100>;
+		};
+
 		vo1_grf: syscon@26036000 {
 			compatible = "rockchip,rk3576-vo1-grf", "syscon";
 			reg = <0x0 0x26036000 0x0 0x100>;
@@ -922,7 +932,7 @@
 		gpu: gpu@27800000 {
 			compatible = "rockchip,rk3576-mali", "arm,mali-bifrost";
 			reg = <0x0 0x27800000 0x0 0x200000>;
-			assigned-clocks = <&scmi_clk CLK_GPU>;
+			assigned-clocks = <&scmi_clk SCMI_CLK_GPU>;
 			assigned-clock-rates = <198000000>;
 			clocks = <&cru CLK_GPU>;
 			clock-names = "core";
@@ -937,6 +947,109 @@
 			status = "disabled";
 		};
 
+		vop: vop@27d00000 {
+			compatible = "rockchip,rk3576-vop";
+			reg = <0x0 0x27d00000 0x0 0x3000>, <0x0 0x27d05000 0x0 0x1000>;
+			reg-names = "vop", "gamma-lut";
+			interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 380 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "sys",
+					  "vp0",
+					  "vp1",
+					  "vp2";
+			clocks = <&cru ACLK_VOP>,
+				 <&cru HCLK_VOP>,
+				 <&cru DCLK_VP0>,
+				 <&cru DCLK_VP1>,
+				 <&cru DCLK_VP2>;
+			clock-names = "aclk",
+				      "hclk",
+				      "dclk_vp0",
+				      "dclk_vp1",
+				      "dclk_vp2";
+			iommus = <&vop_mmu>;
+			power-domains = <&power RK3576_PD_VOP>;
+			rockchip,grf = <&sys_grf>;
+			rockchip,pmu = <&pmu>;
+			status = "disabled";
+
+			vop_out: ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				vp0: port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+				};
+
+				vp1: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+				};
+
+				vp2: port@2 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <2>;
+				};
+			};
+		};
+
+		vop_mmu: iommu@27d07e00 {
+			compatible = "rockchip,rk3576-iommu", "rockchip,rk3568-iommu";
+			reg = <0x0 0x27d07e00 0x0 0x100>, <0x0 0x27d07f00 0x0 0x100>;
+			interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cru ACLK_VOP>, <&cru HCLK_VOP>;
+			clock-names = "aclk", "iface";
+			#iommu-cells = <0>;
+			power-domains = <&power RK3576_PD_VOP>;
+			status = "disabled";
+		};
+
+		hdmi: hdmi@27da0000 {
+			compatible = "rockchip,rk3576-dw-hdmi-qp";
+			reg = <0x0 0x27da0000 0x0 0x20000>;
+			clocks = <&cru PCLK_HDMITX0>,
+				 <&cru CLK_HDMITX0_EARC>,
+				 <&cru CLK_HDMITX0_REF>,
+				 <&cru MCLK_SAI6_8CH>,
+				 <&cru CLK_HDMITXHDP>,
+				 <&cru HCLK_VO0_ROOT>;
+			clock-names = "pclk", "earc", "ref", "aud", "hdp", "hclk_vo1";
+			interrupts = <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "avp", "cec", "earc", "main", "hpd";
+			phys = <&hdptxphy>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&hdmi_txm0_pins &hdmi_tx_scl &hdmi_tx_sda>;
+			power-domains = <&power RK3576_PD_VO0>;
+			resets = <&cru SRST_HDMITX0_REF>, <&cru SRST_HDMITXHDP>;
+			reset-names = "ref", "hdp";
+			rockchip,grf = <&ioc_grf>;
+			rockchip,vo-grf = <&vo0_grf>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				hdmi_in: port@0 {
+					reg = <0>;
+				};
+
+				hdmi_out: port@1 {
+					reg = <1>;
+				};
+			};
+		};
+
 		qos_hdcp1: qos@27f02000 {
 			compatible = "rockchip,rk3576-qos", "syscon";
 			reg = <0x0 0x27f02000 0x0 0x20>;
@@ -1221,6 +1334,41 @@
 			};
 		};
 
+		ufshc: ufshc@2a2d0000 {
+			compatible = "rockchip,rk3576-ufshc";
+			reg = <0x0 0x2a2d0000 0x0 0x10000>,
+			      <0x0 0x2b040000 0x0 0x10000>,
+			      <0x0 0x2601f000 0x0 0x1000>,
+			      <0x0 0x2603c000 0x0 0x1000>,
+			      <0x0 0x2a2e0000 0x0 0x10000>;
+			reg-names = "hci", "mphy", "hci_grf", "mphy_grf", "hci_apb";
+			clocks = <&cru ACLK_UFS_SYS>, <&cru PCLK_USB_ROOT>, <&cru PCLK_MPHY>,
+				 <&cru CLK_REF_UFS_CLKOUT>;
+			clock-names = "core", "pclk", "pclk_mphy", "ref_out";
+			assigned-clocks = <&cru CLK_REF_OSC_MPHY>;
+			assigned-clock-parents = <&cru CLK_REF_MPHY_26M>;
+			interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&power RK3576_PD_USB>;
+			pinctrl-0 = <&ufs_refclk>;
+			pinctrl-names = "default";
+			resets = <&cru SRST_A_UFS_BIU>, <&cru SRST_A_UFS_SYS>,
+				 <&cru SRST_A_UFS>, <&cru SRST_P_UFS_GRF>;
+			reset-names = "biu", "sys", "ufs", "grf";
+			reset-gpios = <&gpio4 RK_PD0 GPIO_ACTIVE_LOW>;
+			status = "disabled";
+		};
+
+		sfc1: spi@2a300000 {
+			compatible = "rockchip,sfc";
+			reg = <0x0 0x2a300000 0x0 0x4000>;
+			interrupts = <GIC_SPI 255 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cru SCLK_FSPI1_X2>, <&cru HCLK_FSPI1>;
+			clock-names = "clk_sfc", "hclk_sfc";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		sdmmc: mmc@2a310000 {
 			compatible = "rockchip,rk3576-dw-mshc";
 			reg = <0x0 0x2a310000 0x0 0x4000>;
@@ -1260,6 +1408,56 @@
 			status = "disabled";
 		};
 
+		sfc0: spi@2a340000 {
+			compatible = "rockchip,sfc";
+			reg = <0x0 0x2a340000 0x0 0x4000>;
+			interrupts = <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cru SCLK_FSPI_X2>, <&cru HCLK_FSPI>;
+			clock-names = "clk_sfc", "hclk_sfc";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		otp: otp@2a580000 {
+			compatible = "rockchip,rk3576-otp";
+			reg = <0x0 0x2a580000 0x0 0x400>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&cru CLK_OTPC_NS>, <&cru PCLK_OTPC_NS>,
+				 <&cru CLK_OTP_PHY_G>;
+			clock-names = "otp", "apb_pclk", "phy";
+			resets = <&cru SRST_OTPC_NS>, <&cru SRST_P_OTPC_NS>;
+			reset-names = "otp", "apb";
+
+			/* Data cells */
+			cpu_code: cpu-code@2 {
+				reg = <0x02 0x2>;
+			};
+			otp_cpu_version: cpu-version@5 {
+				reg = <0x05 0x1>;
+				bits = <3 3>;
+			};
+			otp_id: id@a {
+				reg = <0x0a 0x10>;
+			};
+			cpub_leakage: cpub-leakage@1e {
+				reg = <0x1e 0x1>;
+			};
+			cpul_leakage: cpul-leakage@1f {
+				reg = <0x1f 0x1>;
+			};
+			npu_leakage: npu-leakage@20 {
+				reg = <0x20 0x1>;
+			};
+			gpu_leakage: gpu-leakage@21 {
+				reg = <0x21 0x1>;
+			};
+			log_leakage: log-leakage@22 {
+				reg = <0x22 0x1>;
+			};
+		};
+
 		gic: interrupt-controller@2a701000 {
 			compatible = "arm,gic-400";
 			reg = <0x0 0x2a701000 0 0x10000>,
@@ -1756,6 +1954,19 @@
 			status = "disabled";
 		};
 
+		hdptxphy: hdmiphy@2b000000 {
+			compatible = "rockchip,rk3576-hdptx-phy", "rockchip,rk3588-hdptx-phy";
+			reg = <0x0 0x2b000000 0x0 0x2000>;
+			clocks = <&cru CLK_PHY_REF_SRC>, <&cru PCLK_HDPTX_APB>;
+			clock-names = "ref", "apb";
+			resets = <&cru SRST_P_HDPTX_APB>, <&cru SRST_HDPTX_INIT>,
+				 <&cru SRST_HDPTX_CMN>, <&cru SRST_HDPTX_LANE>;
+			reset-names = "apb", "init", "cmn", "lane";
+			rockchip,grf = <&hdptxphy_grf>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
 		sram: sram@3ff88000 {
 			compatible = "mmio-sram";
 			reg = <0x0 0x3ff88000 0x0 0x78000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-armsom-lm7.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-armsom-lm7.dtsi
index a3138d2d384c..e44125e9a8fb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-armsom-lm7.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-armsom-lm7.dtsi
@@ -114,6 +114,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &saradc {
 	vref-supply = <&avcc_1v8_s0>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-armsom-sige7.dts b/arch/arm64/boot/dts/rockchip/rk3588-armsom-sige7.dts
index 08f09053a066..ae9274365bed 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-armsom-sige7.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-armsom-sige7.dts
@@ -4,6 +4,7 @@
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/leds/common.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
 #include "rk3588.dtsi"
 
 / {
@@ -33,6 +34,17 @@
 			  "Headphone", "Headphones";
 	};
 
+	hdmi0-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi0_con_in: endpoint {
+				remote-endpoint = <&hdmi0_out_con>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -164,6 +176,30 @@
 	status = "okay";
 };
 
+&hdmi0 {
+	status = "okay";
+};
+
+&hdmi0_in {
+	hdmi0_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi0>;
+	};
+};
+
+&hdmi0_out {
+	hdmi0_out_con: endpoint {
+		remote-endpoint = <&hdmi0_con_in>;
+	};
+};
+
+&hdmi0_sound {
+	status = "okay";
+};
+
+&hdptxphy0 {
+	status = "okay";
+};
+
 &i2c0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0m2_xfer>;
@@ -258,6 +294,10 @@
 	};
 };
 
+&i2s5_8ch {
+	status = "okay";
+};
+
 /* phy1 - right ethernet port */
 &pcie2x1l0 {
 	reset-gpios = <&gpio4 RK_PA5 GPIO_ACTIVE_HIGH>;
@@ -268,6 +308,22 @@
 &pcie2x1l1 {
 	reset-gpios = <&gpio3 RK_PD4 GPIO_ACTIVE_HIGH>;
 	status = "okay";
+
+	pcie@0,0 {
+		reg = <0x300000 0 0 0 0>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges;
+		device_type = "pci";
+		bus-range = <0x30 0x3f>;
+
+		wifi: wifi@0,0 {
+			compatible = "pci14e4,449d";
+			reg = <0x310000 0 0 0 0>;
+			clocks = <&hym8563>;
+			clock-names = "lpo";
+		};
+	};
 };
 
 /* phy0 - left ethernet port */
@@ -286,6 +342,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
@@ -723,3 +783,18 @@
 	dr_mode = "host";
 	status = "okay";
 };
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vop {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi0: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi0_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index c3abdfb04f8f..1e18ad93ba0e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -358,11 +358,6 @@
 	};
 
 	firmware {
-		optee: optee {
-			compatible = "linaro,optee-tz";
-			method = "smc";
-		};
-
 		scmi: scmi {
 			compatible = "arm,scmi-smc";
 			arm,smc-id = <0x82000010>;
@@ -382,6 +377,22 @@
 		};
 	};
 
+	hdmi0_sound: hdmi0-sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,mclk-fs = <128>;
+		simple-audio-card,name = "hdmi0";
+		status = "disabled";
+
+		simple-audio-card,codec {
+			sound-dai = <&hdmi0>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s5_8ch>;
+		};
+	};
+
 	pmu-a55 {
 		compatible = "arm,cortex-a55-pmu";
 		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_HIGH &ppi_partition0>;
@@ -864,7 +875,7 @@
 				};
 			};
 			/* These power domains are grouped by VD_GPU */
-			power-domain@RK3588_PD_GPU {
+			pd_gpu: power-domain@RK3588_PD_GPU {
 				reg = <RK3588_PD_GPU>;
 				clocks = <&cru CLK_GPU>,
 					 <&cru CLK_GPU_COREGROUP>,
@@ -1261,14 +1272,16 @@
 			 <&cru DCLK_VOP1>,
 			 <&cru DCLK_VOP2>,
 			 <&cru DCLK_VOP3>,
-			 <&cru PCLK_VOP_ROOT>;
+			 <&cru PCLK_VOP_ROOT>,
+			 <&hdptxphy0>;
 		clock-names = "aclk",
 			      "hclk",
 			      "dclk_vp0",
 			      "dclk_vp1",
 			      "dclk_vp2",
 			      "dclk_vp3",
-			      "pclk_vop";
+			      "pclk_vop",
+			      "pll_hdmiphy0";
 		iommus = <&vop_mmu>;
 		power-domains = <&power RK3588_PD_VOP>;
 		rockchip,grf = <&sys_grf>;
@@ -1318,6 +1331,21 @@
 		status = "disabled";
 	};
 
+	spdif_tx2: spdif-tx@fddb0000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfddb0000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF2_DP0_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF2>, <&cru HCLK_SPDIF2_DP0>;
+		dma-names = "tx";
+		dmas = <&dmac1 6>;
+		interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH 0>;
+		power-domains = <&power RK3588_PD_VO0>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
 	i2s4_8ch: i2s@fddc0000 {
 		compatible = "rockchip,rk3588-i2s-tdm";
 		reg = <0x0 0xfddc0000 0x0 0x1000>;
@@ -1335,6 +1363,21 @@
 		status = "disabled";
 	};
 
+	spdif_tx3: spdif-tx@fdde0000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfdde0000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF3_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF3>, <&cru HCLK_SPDIF3>;
+		dma-names = "tx";
+		dmas = <&dmac1 7>;
+		interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH 0>;
+		power-domains = <&power RK3588_PD_VO1>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
 	i2s5_8ch: i2s@fddf0000 {
 		compatible = "rockchip,rk3588-i2s-tdm";
 		reg = <0x0 0xfddf0000 0x0 0x1000>;
@@ -1385,7 +1428,7 @@
 			     <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH 0>,
 			     <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH 0>;
 		interrupt-names = "avp", "cec", "earc", "main", "hpd";
-		phys = <&hdptxphy_hdmi0>;
+		phys = <&hdptxphy0>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&hdmim0_tx0_cec &hdmim0_tx0_hpd
 			     &hdmim0_tx0_scl &hdmim0_tx0_sda>;
@@ -1394,6 +1437,7 @@
 		reset-names = "ref", "hdp";
 		rockchip,grf = <&sys_grf>;
 		rockchip,vo-grf = <&vo1_grf>;
+		#sound-dai-cells = <0>;
 		status = "disabled";
 
 		ports {
@@ -1921,6 +1965,14 @@
 		status = "disabled";
 	};
 
+	rng@fe378000 {
+		compatible = "rockchip,rk3588-rng";
+		reg = <0x0 0xfe378000 0x0 0x200>;
+		interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH 0>;
+		clocks = <&scmi_clk SCMI_HCLK_SECURE_NS>;
+		resets = <&scmi_reset 48>;
+	};
+
 	i2s0_8ch: i2s@fe470000 {
 		compatible = "rockchip,rk3588-i2s-tdm";
 		reg = <0x0 0xfe470000 0x0 0x1000>;
@@ -2016,12 +2068,47 @@
 		status = "disabled";
 	};
 
+	spdif_tx0: spdif-tx@fe4e0000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfe4e0000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF0_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF0>, <&cru HCLK_SPDIF0>;
+		dma-names = "tx";
+		dmas = <&dmac0 5>;
+		interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH 0>;
+		pinctrl-0 = <&spdif0m0_tx>;
+		pinctrl-names = "default";
+		power-domains = <&power RK3588_PD_AUDIO>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
+	spdif_tx1: spdif-tx@fe4f0000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfe4f0000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF1_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF1>, <&cru HCLK_SPDIF1>;
+		dma-names = "tx";
+		dmas = <&dmac1 5>;
+		interrupts = <GIC_SPI 194 IRQ_TYPE_LEVEL_HIGH 0>;
+		pinctrl-0 = <&spdif1m0_tx>;
+		pinctrl-names = "default";
+		power-domains = <&power RK3588_PD_AUDIO>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
 	gic: interrupt-controller@fe600000 {
 		compatible = "arm,gic-v3";
 		reg = <0x0 0xfe600000 0 0x10000>, /* GICD */
 		      <0x0 0xfe680000 0 0x100000>; /* GICR */
 		interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH 0>;
 		interrupt-controller;
+		dma-noncoherent;
 		mbi-alias = <0x0 0xfe610000>;
 		mbi-ranges = <424 56>;
 		msi-controller;
@@ -2033,6 +2120,7 @@
 		its0: msi-controller@fe640000 {
 			compatible = "arm,gic-v3-its";
 			reg = <0x0 0xfe640000 0x0 0x20000>;
+			dma-noncoherent;
 			msi-controller;
 			#msi-cells = <1>;
 		};
@@ -2040,6 +2128,7 @@
 		its1: msi-controller@fe660000 {
 			compatible = "arm,gic-v3-its";
 			reg = <0x0 0xfe660000 0x0 0x20000>;
+			dma-noncoherent;
 			msi-controller;
 			#msi-cells = <1>;
 		};
@@ -2807,11 +2896,12 @@
 		#dma-cells = <1>;
 	};
 
-	hdptxphy_hdmi0: phy@fed60000 {
+	hdptxphy0: phy@fed60000 {
 		compatible = "rockchip,rk3588-hdptx-phy";
 		reg = <0x0 0xfed60000 0x0 0x2000>;
 		clocks = <&cru CLK_USB2PHY_HDPTXRXPHY_REF>, <&cru PCLK_HDPTX0>;
 		clock-names = "ref", "apb";
+		#clock-cells = <0>;
 		#phy-cells = <0>;
 		resets = <&cru SRST_HDPTX0>, <&cru SRST_P_HDPTX0>,
 			 <&cru SRST_HDPTX0_INIT>, <&cru SRST_HDPTX0_CMN>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
index 9d525c8ff725..9eda69722665 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
@@ -129,7 +129,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
index bc6b43a77153..6dc10da5215f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
@@ -166,7 +166,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
index 71ed680621b8..cc37f082adea 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
@@ -277,6 +277,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi
index 5e72d0eff0e0..8a783dc64c0e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi
@@ -126,6 +126,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	leds {
 		led_user_en: led_user_en {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi
index 7125790bbed2..08920344a4b8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi
@@ -4,12 +4,24 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
 
 / {
 	chosen {
 		stdout-path = "serial2:1500000n8";
 	};
 
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+
 	/* Unnamed gated oscillator: 100MHz,3.3V,3225 */
 	pcie30_port0_refclk: pcie30_port1_refclk: pcie-oscillator {
 		compatible = "gated-fixed-clock";
@@ -81,6 +93,26 @@
 	status = "okay";
 };
 
+&hdmi1 {
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdptxphy1 {
+	status = "okay";
+};
+
 &i2c6 {
 	status = "okay";
 
@@ -275,3 +307,18 @@
 &usb_host2_xhci {
 	status = "okay";
 };
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vop {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
index ba49f0bbaac6..8e912da299a2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
@@ -132,6 +132,17 @@
 		};
 	};
 
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+
 	pcie20_avdd0v85: regulator-pcie20-avdd0v85 {
 		compatible = "regulator-fixed";
 		regulator-name = "pcie20_avdd0v85";
@@ -364,7 +375,27 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdmi1 {
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdptxphy0 {
+	status = "okay";
+};
+
+&hdptxphy1 {
 	status = "okay";
 };
 
@@ -441,7 +472,7 @@
 	status = "okay";
 
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		clocks = <&cru I2S0_8CH_MCLKOUT>;
 		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
@@ -519,6 +550,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	audio {
 		hp_detect: headphone-detect {
@@ -1371,11 +1406,11 @@
 	status = "okay";
 };
 
-&vop_mmu {
+&vop {
 	status = "okay";
 };
 
-&vop {
+&vop_mmu {
 	status = "okay";
 };
 
@@ -1385,3 +1420,10 @@
 		remote-endpoint = <&hdmi0_in_vp0>;
 	};
 };
+
+&vp1 {
+	vp1_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
index 840b638af1c2..099edb3fd0f6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
@@ -7,6 +7,46 @@
 #include "rk3588-extra-pinctrl.dtsi"
 
 / {
+	hdmi1_sound: hdmi1-sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,mclk-fs = <128>;
+		simple-audio-card,name = "hdmi1";
+		status = "disabled";
+
+		simple-audio-card,codec {
+			sound-dai = <&hdmi1>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s6_8ch>;
+		};
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/*
+		 * The 4k HDMI capture controller works only with 32bit
+		 * phys addresses and doesn't support IOMMU. HDMI RX CMA
+		 * must be reserved below 4GB.
+		 * The size of 160MB was determined as follows:
+		 * (3840 * 2160 pixels) * (4 bytes/pixel) * (2 frames/buffer) / 10^6 = 66MB
+		 * To ensure sufficient support for practical use-cases,
+		 * we doubled the 66MB value.
+		 */
+		hdmi_receiver_cma: hdmi-receiver-cma {
+			compatible = "shared-dma-pool";
+			alloc-ranges = <0x0 0x0 0x0 0xffffffff>;
+			size = <0x0 (160 * 0x100000)>; /* 160MiB */
+			alignment = <0x0 0x40000>; /* 64K */
+			no-map;
+			status = "disabled";
+		};
+	};
+
 	usb_host1_xhci: usb@fc400000 {
 		compatible = "rockchip,rk3588-dwc3", "snps,dwc3";
 		reg = <0x0 0xfc400000 0x0 0x400000>;
@@ -67,6 +107,26 @@
 		};
 	};
 
+	hdptxphy1_grf: syscon@fd5e4000 {
+		compatible = "rockchip,rk3588-hdptxphy-grf", "syscon";
+		reg = <0x0 0xfd5e4000 0x0 0x100>;
+	};
+
+	spdif_tx5: spdif-tx@fddb8000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfddb8000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF5_DP1_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF5>, <&cru HCLK_SPDIF5_DP1>;
+		dma-names = "tx";
+		dmas = <&dmac1 22>;
+		interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH 0>;
+		power-domains = <&power RK3588_PD_VO0>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
 	i2s8_8ch: i2s@fddc8000 {
 		compatible = "rockchip,rk3588-i2s-tdm";
 		reg = <0x0 0xfddc8000 0x0 0x1000>;
@@ -84,6 +144,21 @@
 		status = "disabled";
 	};
 
+	spdif_tx4: spdif-tx@fdde8000 {
+		compatible = "rockchip,rk3588-spdif", "rockchip,rk3568-spdif";
+		reg = <0x0 0xfdde8000 0x0 0x1000>;
+		assigned-clock-parents = <&cru PLL_AUPLL>;
+		assigned-clocks = <&cru CLK_SPDIF4_SRC>;
+		clock-names = "mclk", "hclk";
+		clocks = <&cru MCLK_SPDIF4>, <&cru HCLK_SPDIF4>;
+		dma-names = "tx";
+		dmas = <&dmac1 8>;
+		interrupts = <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH 0>;
+		power-domains = <&power RK3588_PD_VO1>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+	};
+
 	i2s6_8ch: i2s@fddf4000 {
 		compatible = "rockchip,rk3588-i2s-tdm";
 		reg = <0x0 0xfddf4000 0x0 0x1000>;
@@ -135,6 +210,79 @@
 		status = "disabled";
 	};
 
+	hdmi1: hdmi@fdea0000 {
+		compatible = "rockchip,rk3588-dw-hdmi-qp";
+		reg = <0x0 0xfdea0000 0x0 0x20000>;
+		clocks = <&cru PCLK_HDMITX1>,
+			 <&cru CLK_HDMITX1_EARC>,
+			 <&cru CLK_HDMITX1_REF>,
+			 <&cru MCLK_I2S6_8CH_TX>,
+			 <&cru CLK_HDMIHDP1>,
+			 <&cru HCLK_VO1>;
+		clock-names = "pclk", "earc", "ref", "aud", "hdp", "hclk_vo1";
+		interrupts = <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupt-names = "avp", "cec", "earc", "main", "hpd";
+		phys = <&hdptxphy1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hdmim2_tx1_cec &hdmim0_tx1_hpd
+			     &hdmim1_tx1_scl &hdmim1_tx1_sda>;
+		power-domains = <&power RK3588_PD_VO1>;
+		resets = <&cru SRST_HDMITX1_REF>, <&cru SRST_HDMIHDP1>;
+		reset-names = "ref", "hdp";
+		rockchip,grf = <&sys_grf>;
+		rockchip,vo-grf = <&vo1_grf>;
+		#sound-dai-cells = <0>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi1_in: port@0 {
+				reg = <0>;
+			};
+
+			hdmi1_out: port@1 {
+				reg = <1>;
+			};
+		};
+	};
+
+	hdmi_receiver: hdmi_receiver@fdee0000 {
+		compatible = "rockchip,rk3588-hdmirx-ctrler", "snps,dw-hdmi-rx";
+		reg = <0x0 0xfdee0000 0x0 0x6000>;
+		interrupts = <GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 178 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 179 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupt-names = "cec", "hdmi", "dma";
+		clocks = <&cru ACLK_HDMIRX>,
+			 <&cru CLK_HDMIRX_AUD>,
+			 <&cru CLK_CR_PARA>,
+			 <&cru PCLK_HDMIRX>,
+			 <&cru CLK_HDMIRX_REF>,
+			 <&cru PCLK_S_HDMIRX>,
+			 <&cru HCLK_VO1>;
+		clock-names = "aclk",
+			      "audio",
+			      "cr_para",
+			      "pclk",
+			      "ref",
+			      "hclk_s_hdmirx",
+			      "hclk_vo1";
+		memory-region = <&hdmi_receiver_cma>;
+		power-domains = <&power RK3588_PD_VO1>;
+		resets = <&cru SRST_A_HDMIRX>, <&cru SRST_P_HDMIRX>,
+			 <&cru SRST_HDMIRX_REF>, <&cru SRST_A_HDMIRX_BIU>;
+		reset-names = "axi", "apb", "ref", "biu";
+		rockchip,grf = <&sys_grf>;
+		rockchip,vo1-grf = <&vo1_grf>;
+		status = "disabled";
+	};
+
 	pcie3x4: pcie@fe150000 {
 		compatible = "rockchip,rk3588-pcie", "rockchip,rk3568-pcie";
 		#address-cells = <3>;
@@ -398,6 +546,23 @@
 		};
 	};
 
+	hdptxphy1: phy@fed70000 {
+		compatible = "rockchip,rk3588-hdptx-phy";
+		reg = <0x0 0xfed70000 0x0 0x2000>;
+		clocks = <&cru CLK_USB2PHY_HDPTXRXPHY_REF>, <&cru PCLK_HDPTX1>;
+		clock-names = "ref", "apb";
+		#clock-cells = <0>;
+		#phy-cells = <0>;
+		resets = <&cru SRST_HDPTX1>, <&cru SRST_P_HDPTX1>,
+			 <&cru SRST_HDPTX1_INIT>, <&cru SRST_HDPTX1_CMN>,
+			 <&cru SRST_HDPTX1_LANE>, <&cru SRST_HDPTX1_ROPLL>,
+			 <&cru SRST_HDPTX1_LCPLL>;
+		reset-names = "phy", "apb", "init", "cmn", "lane", "ropll",
+			      "lcpll";
+		rockchip,grf = <&hdptxphy1_grf>;
+		status = "disabled";
+	};
+
 	usbdp_phy1: phy@fed90000 {
 		compatible = "rockchip,rk3588-usbdp-phy";
 		reg = <0x0 0xfed90000 0x0 0x10000>;
@@ -449,3 +614,24 @@
 		status = "disabled";
 	};
 };
+
+&vop {
+	clocks = <&cru ACLK_VOP>,
+		 <&cru HCLK_VOP>,
+		 <&cru DCLK_VOP0>,
+		 <&cru DCLK_VOP1>,
+		 <&cru DCLK_VOP2>,
+		 <&cru DCLK_VOP3>,
+		 <&cru PCLK_VOP_ROOT>,
+		 <&hdptxphy0>,
+		 <&hdptxphy1>;
+	clock-names = "aclk",
+		      "hclk",
+		      "dclk_vp0",
+		      "dclk_vp1",
+		      "dclk_vp2",
+		      "dclk_vp3",
+		      "pclk_vop",
+		      "pll_hdmiphy0",
+		      "pll_hdmiphy1";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-fet3588-c.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-fet3588-c.dtsi
index 390051317389..4331cdc70f97 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-fet3588-c.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-fet3588-c.dtsi
@@ -205,6 +205,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	leds {
 		led_rgb_b: led-rgb-b {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi
index 42c523b553c9..80e16ea4154c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-firefly-core-3588j.dtsi
@@ -108,6 +108,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &sdhci {
 	bus-width = <8>;
 	no-sdio;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-firefly-icore-3588q.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-firefly-icore-3588q.dtsi
new file mode 100644
index 000000000000..6726eeb49255
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-firefly-icore-3588q.dtsi
@@ -0,0 +1,443 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+#include "rk3588.dtsi"
+
+/ {
+	compatible = "firefly,icore-3588q", "rockchip,rk3588";
+
+	aliases {
+		mmc0 = &sdhci;
+	};
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1m2_xfer>;
+	status = "okay";
+
+	vdd_npu_s0: vdd_npu_mem_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-name = "vdd_npu_s0";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&sdhci {
+	bus-width = <8>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	max-frequency = <150000000>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	status = "okay";
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		system-power-controller;
+
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_cpu_lit_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_log_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_vdenc_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vdd2_ddr_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-name = "vdd_2v0_pldo_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vddq_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "avcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "avdd_1v2_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_3v3_s0: pldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s0";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "pldo6_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_ddr_pll_s0: nldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdd_ddr_pll_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "avdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v85_s0: nldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "vdd_0v85_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts b/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts
index 2be5251d3e3b..e086114c7634 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-firefly-itx-3588j.dts
@@ -337,7 +337,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588-nas.dts b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588-nas.dts
index b3a04ca370bb..8171fbfd819a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588-nas.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588-nas.dts
@@ -335,7 +335,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
index e3a9598b99fc..af431fdcbea7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi
@@ -222,6 +222,10 @@
 		compatible = "realtek,rt5616";
 		reg = <0x1b>;
 		#sound-dai-cells = <0>;
+		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
+		assigned-clock-rates = <12288000>;
+		clocks = <&cru I2S0_8CH_MCLKOUT>;
+		clock-names = "mclk";
 	};
 };
 
@@ -256,6 +260,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	gpio-leds {
 		led_sys_pin: led-sys-pin {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts b/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts
index 4791b77f3571..73d8ce4fde2b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-h96-max-v58.dts
@@ -140,6 +140,24 @@
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 	};
+
+	spdif_dit: spdif-dit {
+		compatible = "linux,spdif-dit";
+		#sound-dai-cells = <0>;
+	};
+
+	spdif_sound: spdif-sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "SPDIF";
+
+		simple-audio-card,cpu {
+			sound-dai = <&spdif_tx0>;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&spdif_dit>;
+		};
+	};
 };
 
 &combphy0_ps {
@@ -207,7 +225,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -316,6 +334,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
@@ -400,6 +422,12 @@
 	status = "okay";
 };
 
+&spdif_tx0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spdif0m1_tx>;
+	status = "okay";
+};
+
 &spi2 {
 	assigned-clocks = <&cru CLK_SPI2>;
 	assigned-clock-rates = <200000000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar-pre-ict-tester.dtso b/arch/arm64/boot/dts/rockchip/rk3588-jaguar-pre-ict-tester.dtso
new file mode 100644
index 000000000000..9d44dfe2f30d
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar-pre-ict-tester.dtso
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
+/*
+ * Copyright (c) 2024 Cherry Embedded Solutions GmbH
+ *
+ * Device Tree Overlay for the Pre-ICT tester adapter for the Mezzanine
+ * connector on RK3588 Jaguar.
+ *
+ * This adapter has a PCIe Gen2 x1 M.2 M-Key connector and two proprietary
+ * camera connectors (each their own I2C bus, clock, reset and PWM lines as well
+ * as 2-lane CSI).
+ *
+ * This adapter routes some GPIOs to power rails and loops together some other
+ * GPIOs.
+ *
+ * This adapter is used during manufacturing for validating proper soldering of
+ * the mezzanine connector.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+&{/} {
+	pre_ict_tester_vcc_1v2: regulator-pre-ict-tester-vcc-1v2 {
+		compatible = "regulator-fixed";
+		regulator-name = "pre_ict_tester_vcc_1v2";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	pre_ict_tester_vcc_2v8: regulator-pre-ict-tester-vcc-2v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "pre_ict_tester_vcc_2v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <2800000>;
+		regulator-max-microvolt = <2800000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&gpio3 {
+	pinctrl-0 = <&pre_ict_pwr2gpio>;
+	pinctrl-names = "default";
+};
+
+&pcie2x1l2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie2x1l2_perstn_m0>;
+	reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>; /* PCIE20X1_2_PERSTN_M0 */
+	vpcie3v3-supply = <&vcc_3v3_s3>;
+	status = "okay";
+};
+
+&pinctrl {
+	pcie2x1l2 {
+		pcie2x1l2_perstn_m0: pcie2x1l2-perstn-m0 {
+			rockchip,pins = <3 RK_PD1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pre-ict-tester {
+		pre_ict_pwr2gpio: pre-ict-pwr2gpio-pins {
+			rockchip,pins =
+			/*
+			 * GPIO3_A3 requires two power rails to be properly
+			 * routed to the mezzanine connector to report a proper
+			 * value: VCC_1V8_S0_1 and VCC_IN_2. It may report an
+			 * incorrect value if VCC_1V8_S0_1 isn't properly routed,
+			 * but GPIO3_C6 would catch this HW soldering issue.
+			 * If VCC_IN_2 is properly routed, GPIO3_A3 should be
+			 * LOW. The signal shall not read HIGH in the event
+			 * GPIO3_A3 isn't properly routed due to soldering
+			 * issue. Therefore, let's enforce a pull-up (which is
+			 * the SoC default for this pin).
+			 */
+				<3 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>,
+			/*
+			 * GPIO3_A4 is directly routed to VCC_1V8_S0_2 power
+			 * rail. It should be HIGH if all is properly soldered.
+			 * To guarantee that, a pull-down is enforced (which is
+			 * the SoC default for this pin) so that LOW is read if
+			 * the loop doesn't exist on HW (soldering issue on
+			 * either signals).
+			 */
+				<3 RK_PA4 RK_FUNC_GPIO &pcfg_pull_down>,
+			/*
+			 * GPIO3_B2 requires two power rails to be properly
+			 * routed to the mezzanine connector to report a proper
+			 * value: VCC_1V8_S0_1 and VCC_IN_1. It may report an
+			 * incorrect value if VCC_1V8_S0_1 isn't properly routed,
+			 * but GPIO3_C6 would catch this HW soldering issue.
+			 * If VCC_IN_1 is properly routed, GPIO3_B2 should be
+			 * LOW. This is an issue if GPIO3_B2 isn't properly
+			 * routed due to soldering issue, because GPIO3_B2
+			 * default bias is pull-down therefore being LOW. So
+			 * the worst case scenario and the pass scenario expect
+			 * the same value. Make GPIO3_B2 a pull-up so that a
+			 * soldering issue on GPIO3_B2 reports HIGH but proper
+			 * soldering reports LOW.
+			 */
+				<3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>,
+			/*
+			 * GPIO3_C6 is directly routed to VCC_1V8_S0_1 power
+			 * rail. It should be HIGH if all is properly soldered.
+			 * This is an issue if GPIO3_C6 or VCC_1V8_S0_1 isn't
+			 * properly routed due to soldering issue, because
+			 * GPIO3_C6 default bias is pull-up therefore being HIGH
+			 * in all cases:
+			 *  - GPIO3_C6 is floating (so HIGH) if GPIO3_C6 is not
+			 *    routed properly,
+			 *  - GPIO3_C6 is floating (so HIGH) if VCC_1V8_S0_1 is
+			 *    not routed properly,
+			 *  - GPIO3_C6 is HIGH if everything is proper,
+			 * Make GPIO3_C6 a pull-down so that a soldering issue
+			 * on GPIO3_C6 or VCC_1V8_S0_1 reports LOW but proper
+			 * soldering reports HIGH.
+			 */
+				<3 RK_PC6 RK_FUNC_GPIO &pcfg_pull_down>,
+			/*
+			 * GPIO3_D2 is routed to VCC_5V0_1 power rail through a
+			 * voltage divider on the adapter.
+			 * It should be HIGH if all is properly soldered.
+			 * To guarantee that, a pull-down is enforced (which is
+			 * the SoC default for this pin) so that LOW is read if
+			 * the loop doesn't exist on HW (soldering issue on
+			 * either signals).
+			 */
+				<3 RK_PD2 RK_FUNC_GPIO &pcfg_pull_down>,
+			/*
+			 * GPIO3_D3 is routed to VCC_5V0_2 power rail through a
+			 * voltage divider on the adapter.
+			 * It should be HIGH if all is properly soldered.
+			 * To guarantee that, a pull-down is enforced (which is
+			 * the SoC default for this pin) so that LOW is read if
+			 * the loop doesn't exist on HW (soldering issue on
+			 * either signals).
+			 */
+				<3 RK_PD3 RK_FUNC_GPIO &pcfg_pull_down>,
+			/*
+			 * GPIO3_D4 is routed to VCC_3V3_S3_1 power rail through
+			 * a voltage divider on the adapter.
+			 * It should be HIGH if all is properly soldered.
+			 * To guarantee that, a pull-down is enforced (which is
+			 * the SoC default for this pin) so that LOW is read if
+			 * the loop doesn't exist on HW (soldering issue on
+			 * either signals).
+			 */
+				<3 RK_PD4 RK_FUNC_GPIO &pcfg_pull_down>,
+			/*
+			 * GPIO3_D5 is routed to VCC_3V3_S3_2 power rail through
+			 * a voltage divider on the adapter.
+			 * It should be HIGH if all is properly soldered.
+			 * To guarantee that, a pull-down is enforced (which is
+			 * the SoC default for this pin) so that LOW is read if
+			 * the loop doesn't exist on HW (soldering issue on
+			 * either signals).
+			 */
+				<3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
index 90f823b2c219..9fceea6c1398 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
@@ -303,7 +303,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -333,6 +333,56 @@
 		};
 	};
 
+	typec-portc@22 {
+		compatible = "fcs,fusb302";
+		reg = <0x22>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&cc_int1>;
+		vbus-supply = <&vcc_5v0_usb_c1>;
+
+		connector {
+			compatible = "usb-c-connector";
+			data-role = "dual";
+			label = "USBC-1 P11";
+			power-role = "source";
+			self-powered;
+			source-pdos =
+				<PDO_FIXED(5000, 1500, PDO_FIXED_DATA_SWAP | PDO_FIXED_USB_COMM)>;
+			vbus-supply = <&vcc_5v0_usb_c1>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usbc0_hs: endpoint {
+						remote-endpoint = <&usb_host0_xhci_drd_sw>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usbc0_ss: endpoint {
+						remote-endpoint = <&usbdp_phy0_typec_ss>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					usbc0_sbu: endpoint {
+						remote-endpoint = <&usbdp_phy0_typec_sbu>;
+					};
+				};
+			};
+		};
+	};
+
 	vdd_npu_s0: regulator@42 {
 		compatible = "rockchip,rk8602";
 		reg = <0x42>;
@@ -394,6 +444,56 @@
 	pinctrl-0 = <&i2c8m2_xfer>;
 	status = "okay";
 
+	typec-portc@22 {
+		compatible = "fcs,fusb302";
+		reg = <0x22>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <RK_PA4 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&cc_int2>;
+		vbus-supply = <&vcc_5v0_usb_c2>;
+
+		connector {
+			compatible = "usb-c-connector";
+			data-role = "dual";
+			label = "USBC-2 P12";
+			power-role = "source";
+			self-powered;
+			source-pdos =
+				<PDO_FIXED(5000, 1500, PDO_FIXED_DATA_SWAP | PDO_FIXED_USB_COMM)>;
+			vbus-supply = <&vcc_5v0_usb_c2>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usbc1_hs: endpoint {
+						remote-endpoint = <&usb_host1_xhci_drd_sw>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usbc1_ss: endpoint {
+						remote-endpoint = <&usbdp_phy1_typec_ss>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					usbc1_sbu: endpoint {
+						remote-endpoint = <&usbdp_phy1_typec_sbu>;
+					};
+				};
+			};
+		};
+	};
+
 	vdd_cpu_big0_s0: regulator@42 {
 		compatible = "rockchip,rk8602";
 		reg = <0x42>;
@@ -451,6 +551,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	emmc {
 		emmc_reset: emmc-reset {
@@ -483,6 +587,26 @@
 			rockchip,pins = <0 RK_PC7 12 &pcfg_pull_none>;
 		};
 	};
+
+	usb3 {
+		cc_int1: cc-int1 {
+			rockchip,pins = <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		cc_int2: cc-int2 {
+			rockchip,pins = <4 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		typec0_sbu_dc_pins: typec0-sbu-dc-pins {
+			rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_down>,
+					<1 RK_PC3 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		typec1_sbu_dc_pins: typec1-sbu-dc-pins {
+			rockchip,pins = <0 RK_PD4 RK_FUNC_GPIO &pcfg_pull_down>,
+					<1 RK_PB5 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
 };
 
 &saradc {
@@ -503,7 +627,6 @@
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
-	supports-cqe;
 	vmmc-supply = <&vcc_3v3_s3>;
 	vqmmc-supply = <&vcc_1v8_s3>;
 	status = "okay";
@@ -851,6 +974,24 @@
 	status = "okay";
 };
 
+/* USB-C P11 connector */
+&u2phy0 {
+	status = "okay";
+};
+
+&u2phy0_otg {
+	status = "okay";
+};
+
+/* USB-C P12 connector */
+&u2phy1 {
+	status = "okay";
+};
+
+&u2phy1_otg {
+	status = "okay";
+};
+
 &u2phy2 {
 	status = "okay";
 };
@@ -893,6 +1034,56 @@
 	status = "okay";
 };
 
+/* Type-C on P11 */
+&usbdp_phy0 {
+	orientation-switch;
+	pinctrl-names = "default";
+	pinctrl-0 = <&typec0_sbu_dc_pins>;
+	sbu1-dc-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; /* Q7_USB_C0_SBU1_DC */
+	sbu2-dc-gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>; /* Q7_USB_C0_SBU2_DC */
+	status = "okay";
+
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		usbdp_phy0_typec_ss: endpoint@0 {
+			reg = <0>;
+			remote-endpoint = <&usbc0_ss>;
+		};
+
+		usbdp_phy0_typec_sbu: endpoint@1 {
+			reg = <1>;
+			remote-endpoint = <&usbc0_sbu>;
+		};
+	};
+};
+
+/* Type-C on P12 */
+&usbdp_phy1 {
+	orientation-switch;
+	pinctrl-names = "default";
+	pinctrl-0 = <&typec1_sbu_dc_pins>;
+	sbu1-dc-gpios = <&gpio0 RK_PD4 GPIO_ACTIVE_HIGH>; /* Q7_USB_C1_SBU1_DC */
+	sbu2-dc-gpios = <&gpio1 RK_PB5 GPIO_ACTIVE_HIGH>; /* Q7_USB_C1_SBU2_DC */
+	status = "okay";
+
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		usbdp_phy1_typec_ss: endpoint@0 {
+			reg = <0>;
+			remote-endpoint = <&usbc1_ss>;
+		};
+
+		usbdp_phy1_typec_sbu: endpoint@1 {
+			reg = <1>;
+			remote-endpoint = <&usbc1_sbu>;
+		};
+	};
+};
+
 /* host0 on P10 USB-A */
 &usb_host0_ehci {
 	status = "okay";
@@ -903,6 +1094,36 @@
 	status = "okay";
 };
 
+/* host0 on P11 USB-C */
+&usb_host0_xhci {
+	usb-role-switch;
+	status = "okay";
+
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		usb_host0_xhci_drd_sw: endpoint {
+			remote-endpoint = <&usbc0_hs>;
+		};
+	};
+};
+
+/* host1 on P12 USB-C */
+&usb_host1_xhci {
+	usb-role-switch;
+	status = "okay";
+
+	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		usb_host1_xhci_drd_sw: endpoint {
+			remote-endpoint = <&usbc1_hs>;
+		};
+	};
+};
+
 /* host1 on M.2 E-key */
 &usb_host1_ehci {
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-mnt-reform2.dts b/arch/arm64/boot/dts/rockchip/rk3588-mnt-reform2.dts
new file mode 100644
index 000000000000..78a4e896f665
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-mnt-reform2.dts
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2021 Rockchip Electronics Co., Ltd.
+ * Copyright (c) 2024 MNT Research GmbH
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include <dt-bindings/usb/pd.h>
+
+#include "rk3588-firefly-icore-3588q.dtsi"
+
+/ {
+	model = "MNT Reform 2 with RCORE RK3588 Module";
+	compatible = "mntre,reform2-rcore", "firefly,icore-3588q", "rockchip,rk3588";
+	chassis-type = "laptop";
+
+	aliases {
+		ethernet0 = &gmac0;
+		mmc1 = &sdmmc;
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		brightness-levels = <0 8 16 32 64 128 160 200 255>;
+		default-brightness-level = <128>;
+		enable-gpios = <&gpio2 RK_PB5 GPIO_ACTIVE_HIGH>;
+		pwms = <&pwm8 0 10000 0>;
+	};
+
+	gmac0_clkin: external-gmac0-clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+		clock-output-names = "gmac0_clkin";
+	};
+
+	pcie30_avdd1v8: regulator-pcie30-avdd1v8 {
+		compatible = "regulator-fixed";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-name = "pcie30_avdd1v8";
+		vin-supply = <&avcc_1v8_s0>;
+	};
+
+	pcie30_avdd0v75: regulator-pcie30-avdd0v75 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <750000>;
+		regulator-max-microvolt = <750000>;
+		regulator-name = "pcie30_avdd0v75";
+		vin-supply = <&avdd_0v75_s0>;
+	};
+
+	vcc12v_dcin: regulator-vcc12v-dcin {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-name = "vcc12v_dcin";
+	};
+
+	vcc_1v1_nldo_s3: regulator-vcc-1v1-nldo-s3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc3v3_pcie30: regulator-vcc3v3-pcie30 {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc3v3_pcie30";
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_host: regulator-vcc5v0-host {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc5v0_host";
+	};
+
+	vcc5v0_sys: regulator-vcc5v0-sys {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc5v0_sys";
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usb: regulator-vcc5v0-usb {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "vcc5v0_usb";
+		vin-supply = <&vcc12v_dcin>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii-id";
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_tx_bus2
+		     &gmac0_rx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus
+		     &gmac0_clkinout
+		     &eth_phy_reset>;
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu_s0>;
+	sram-supply = <&vdd_gpu_mem_s0>;
+	status = "okay";
+};
+
+&hdmi0 {
+	status = "okay";
+};
+
+&hdmi0_in {
+	hdmi0_in_vp2: endpoint {
+		remote-endpoint = <&vp2_out_hdmi0>;
+	};
+};
+
+&hdptxphy0 {
+	status = "okay";
+};
+
+&i2c6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6m0_xfer>;
+	status = "okay";
+
+	rtc@68 {
+		compatible = "nxp,pcf8523";
+		reg = <0x68>;
+	};
+};
+
+&mdio0 {
+	rgmii_phy: ethernet-phy@0 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x0>;
+	};
+};
+
+&pcie2x1l2 {
+	pinctrl-0 = <&pcie2_0_rst>;
+	reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+&pcie3x4 {
+	num-lanes = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie3_reset>;
+	reset-gpios = <&gpio1 RK_PB4 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_pcie30>;
+	status = "okay";
+};
+
+&pinctrl {
+	dp {
+		dp1_hpd: dp1-hpd {
+			rockchip,pins = <1 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie2 {
+		pcie2_0_rst: pcie2-0-rst {
+			rockchip,pins = <3 RK_PD1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie3 {
+		pcie3_reset: pcie3-reset {
+			rockchip,pins = <1 RK_PB4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	eth_phy {
+		eth_phy_reset: eth-phy-reset {
+			rockchip,pins = <3 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pwm8 {
+	pinctrl-0 = <&pwm8m2_pins>;
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&avcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	max-frequency = <40000000>;
+	no-1-8-v;
+	no-mmc;
+	no-sdio;
+	vmmc-supply = <&vcc3v3_pcie30>;
+	vqmmc-supply = <&vcc3v3_pcie30>;
+	status = "okay";
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&u2phy0 {
+	status = "okay";
+};
+
+&u2phy0_otg {
+	status = "okay";
+};
+
+&u2phy1 {
+	status = "okay";
+};
+
+&u2phy1_otg {
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy3_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&usbdp_phy0 {
+	status = "okay";
+};
+
+&usbdp_phy1 {
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host0_xhci {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
+
+&usb_host1_xhci {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&vop {
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp2 {
+	vp2_out_hdmi0: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi0_in_vp2>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dtsi
index cb350727d116..bbe500cc924b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dtsi
@@ -360,7 +360,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -565,6 +565,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	gpio-leds {
 		sys_led_pin: sys-led-pin {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-ok3588-c.dts b/arch/arm64/boot/dts/rockchip/rk3588-ok3588-c.dts
index 1c0851b45eb8..fbe1d5c06d90 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-ok3588-c.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-ok3588-c.dts
@@ -312,6 +312,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	pcie2 {
 		pcie2_0_rst: pcie2-0-rst {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi
index 87090cb98020..f748c6f760d8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-compact.dtsi
@@ -7,9 +7,6 @@
 #include "rk3588-orangepi-5.dtsi"
 
 / {
-	model = "Xunlong Orange Pi 5 Max";
-	compatible = "xunlong,orangepi-5-max", "rockchip,rk3588";
-
 	vcc5v0_usb30_otg: vcc5v0-usb30-otg-regulator {
 		compatible = "regulator-fixed";
 		enable-active-high;
@@ -62,18 +59,12 @@
 
 &led_blue_pwm {
 	/* PWM_LED1 */
-	pwms = <&pwm4 0 25000 0>;
 	status = "okay";
 };
 
-&led_green_pwm {
-	/* PWM_LED2 */
-	pwms = <&pwm5 0 25000 0>;
-};
-
 /* phy2 */
 &pcie2x1l1 {
-	reset-gpios = <&gpio4 RK_PD4 GPIO_ACTIVE_HIGH>;
+	reset-gpios = <&gpio3 RK_PD4 GPIO_ACTIVE_HIGH>;
 	vpcie3v3-supply = <&vcc3v3_pcie_eth>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts
index ce44549babf4..8b1d35760c3b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-max.dts
@@ -21,6 +21,17 @@
 			};
 		};
 	};
+
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
 };
 
 &hdmi0 {
@@ -39,10 +50,57 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdmi0_sound {
+	status = "okay";
+};
+
+&hdmi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmim0_tx1_cec &hdmim0_tx1_hpd
+			     &hdmim1_tx1_scl &hdmim1_tx1_sda>;
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdmi1_sound {
 	status = "okay";
 };
 
+&hdptxphy0 {
+	status = "okay";
+};
+
+&hdptxphy1 {
+	status = "okay";
+};
+
+&i2s5_8ch {
+	status = "okay";
+};
+
+&i2s6_8ch {
+	status = "okay";
+};
+
+&led_blue_pwm {
+	pwms = <&pwm4 0 25000 0>;
+};
+
+&led_green_pwm {
+	pwms = <&pwm5 0 25000 0>;
+};
+
 &pinctrl {
 
 	usb {
@@ -58,3 +116,10 @@
 		remote-endpoint = <&hdmi0_in_vp0>;
 	};
 };
+
+&vp1 {
+	vp1_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index 255e33c5dbdc..121e4d1c3fa5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -26,6 +26,17 @@
 		};
 	};
 
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+
 	ir-receiver {
 		compatible = "gpio-ir-receiver";
 		gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>;
@@ -113,6 +124,10 @@
 	status = "okay";
 };
 
+&hdmi0_sound {
+	status = "okay";
+};
+
 &hdmi0_in {
 	hdmi0_in_vp0: endpoint {
 		remote-endpoint = <&vp0_out_hdmi0>;
@@ -125,7 +140,31 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdmi1 {
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdmi1_sound {
+	status = "okay";
+};
+
+&hdptxphy0 {
+	status = "okay";
+};
+
+&hdptxphy1 {
 	status = "okay";
 };
 
@@ -189,6 +228,14 @@
 	};
 };
 
+&i2s5_8ch {
+	status = "okay";
+};
+
+&i2s6_8ch {
+	status = "okay";
+};
+
 &led_blue_gpio {
 	gpios = <&gpio3 RK_PA6 GPIO_ACTIVE_HIGH>;
 	status = "okay";
@@ -342,3 +389,10 @@
 		remote-endpoint = <&hdmi0_in_vp0>;
 	};
 };
+
+&vp1 {
+	vp1_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-ultra.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-ultra.dts
new file mode 100644
index 000000000000..f8c6c080e418
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-ultra.dts
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include "rk3588-orangepi-5-compact.dtsi"
+
+/ {
+	model = "Xunlong Orange Pi 5 Ultra";
+	compatible = "xunlong,orangepi-5-ultra", "rockchip,rk3588";
+
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+};
+
+&hdmi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmim0_tx1_cec &hdmim0_tx1_hpd
+			     &hdmim1_tx1_scl &hdmim1_tx1_sda>;
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdmi1_sound {
+	status = "okay";
+};
+
+&hdptxphy1 {
+	status = "okay";
+};
+
+&i2s6_8ch {
+	status = "okay";
+};
+
+&led_blue_pwm {
+	pwms = <&pwm4 0 25000 PWM_POLARITY_INVERTED>;
+};
+
+&led_green_pwm {
+	pwms = <&pwm5 0 25000 PWM_POLARITY_INVERTED>;
+};
+
+&pinctrl {
+	usb {
+		usb_otg_pwren: usb-otg-pwren {
+			rockchip,pins = <4 RK_PB1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&vcc5v0_usb30_otg {
+	gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_HIGH>;
+};
+
+&vp0 {
+	vp0_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
index a98e804a0949..91d56c34a1e4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
@@ -276,7 +276,7 @@
 
 	/* PLDO2 vcca 1.8V, BUCK8 gated by PLDO2 being enabled */
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		clocks = <&cru I2S0_8CH_MCLKOUT>;
 		AVDD-supply = <&vcc_3v3_s0>;
@@ -348,6 +348,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &saradc {
 	vref-supply = <&vcc_1v8_s0>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
index 088cfade6f6f..78aaa6635b5d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
@@ -311,7 +311,7 @@
 	status = "okay";
 
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
 		assigned-clock-rates = <12288000>;
@@ -347,6 +347,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
index 6d68f70284e4..7de17117df7a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
@@ -11,6 +11,7 @@
 #include <dt-bindings/leds/common.h>
 #include <dt-bindings/pinctrl/rockchip.h>
 #include <dt-bindings/pwm/pwm.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
 #include "dt-bindings/usb/pd.h"
 #include "rk3588.dtsi"
 
@@ -72,6 +73,17 @@
 		};
 	};
 
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+
 	/* Unnamed gated oscillator: 100MHz,3.3V,3225 */
 	pcie30_port0_refclk: pcie30_port1_refclk: pcie-oscillator {
 		compatible = "gated-fixed-clock";
@@ -261,6 +273,28 @@
 	status = "okay";
 };
 
+&hdmi1 {
+	pinctrl-0 = <&hdmim0_tx1_cec &hdmim0_tx1_hpd
+		     &hdmim1_tx1_scl &hdmim1_tx1_sda>;
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdptxphy1 {
+	status = "okay";
+};
+
 &i2c0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0m2_xfer>;
@@ -564,6 +598,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		rtc_int: rtc-int {
@@ -690,10 +728,9 @@
 
 &sdhci {
 	bus-width = <8>;
-	max-frequency = <200000000>;
+	max-frequency = <150000000>;
 	mmc-hs400-1_8v;
 	mmc-hs400-enhanced-strobe;
-	mmc-hs200-1_8v;
 	no-sdio;
 	no-sd;
 	non-removable;
@@ -1209,3 +1246,18 @@
 	rockchip,dp-lane-mux = <2 3>;
 	status = "okay";
 };
+
+&vop {
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp1 {
+	vp1_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
index d597112f1d5b..d22068475c5d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
@@ -49,6 +49,17 @@
 		};
 	};
 
+	hdmi1-con {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi1_con_in: endpoint {
+				remote-endpoint = <&hdmi1_out_con>;
+			};
+		};
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
@@ -220,7 +231,48 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdmi0_sound {
+	status = "okay";
+};
+
+&hdmi1 {
+	pinctrl-0 = <&hdmim0_tx1_cec &hdmim0_tx1_hpd
+		     &hdmim1_tx1_scl &hdmim1_tx1_sda>;
+	status = "okay";
+};
+
+&hdmi1_in {
+	hdmi1_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_hdmi1>;
+	};
+};
+
+&hdmi1_out {
+	hdmi1_out_con: endpoint {
+		remote-endpoint = <&hdmi1_con_in>;
+	};
+};
+
+&hdmi1_sound {
+	status = "okay";
+};
+
+&hdmi_receiver_cma {
+	status = "okay";
+};
+
+&hdmi_receiver {
+	hpd-gpios = <&gpio1 RK_PC6 GPIO_ACTIVE_LOW>;
+	pinctrl-0 = <&hdmim1_rx_cec &hdmim1_rx_hpdin &hdmim1_rx_scl &hdmim1_rx_sda &hdmirx_hpd>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&hdptxphy0 {
+	status = "okay";
+};
+
+&hdptxphy1 {
 	status = "okay";
 };
 
@@ -318,6 +370,14 @@
 	};
 };
 
+&i2s5_8ch {
+	status = "okay";
+};
+
+&i2s6_8ch {
+	status = "okay";
+};
+
 &package_thermal {
 	polling-delay = <1000>;
 
@@ -376,7 +436,17 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
+	hdmirx {
+		hdmirx_hpd: hdmirx-5v-detection {
+			rockchip,pins = <1 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
 	hym8563 {
 		hym8563_int: hym8563-int {
 			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
@@ -891,11 +961,11 @@
 	status = "okay";
 };
 
-&vop_mmu {
+&vop {
 	status = "okay";
 };
 
-&vop {
+&vop_mmu {
 	status = "okay";
 };
 
@@ -905,3 +975,10 @@
 		remote-endpoint = <&hdmi0_in_vp0>;
 	};
 };
+
+&vp1 {
+	vp1_out_hdmi1: endpoint@ROCKCHIP_VOP2_EP_HDMI1 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI1>;
+		remote-endpoint = <&hdmi1_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts
index 3187b4918a30..a3d8ff647839 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts
@@ -189,7 +189,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -310,8 +310,10 @@
 	status = "okay";
 };
 
+/* DB9 RS232/RS485 when SW2 in "UART1" mode */
 &uart5 {
 	rts-gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_HIGH>;
+	status = "okay";
 };
 
 &usbdp_phy0 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
index 81a6a05ce13b..c4933a08dd1e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
@@ -173,7 +173,6 @@
 
 &i2c2 {
 	pinctrl-0 = <&i2c2m3_xfer>;
-	status = "okay";
 };
 
 &i2c2m3_xfer {
@@ -336,6 +335,10 @@
 	reset-gpios = <&gpio3 RK_PB6 GPIO_ACTIVE_HIGH>;
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	emmc {
 		emmc_reset: emmc-reset {
@@ -386,7 +389,6 @@
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
-	supports-cqe;
 	vmmc-supply = <&vcc_3v3_s3>;
 	vqmmc-supply = <&vcc_1v8_s3>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
index 3cbee5b97470..5a428e00ab93 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
@@ -289,6 +289,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	rtl8211f {
 		rtl8211f_rst: rtl8211f-rst {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index 6bc46734cc14..60ad272982ad 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -214,6 +214,8 @@
 };
 
 &package_thermal {
+	polling-delay = <1000>;
+
 	trips {
 		package_active1: trip-active1 {
 			temperature = <45000>;
@@ -287,6 +289,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	fan {
 		fan_int: fan-int {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
index bce72bac4503..3045cb3bd68c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
@@ -11,20 +11,15 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp-1416000000 {
-			opp-hz = /bits/ 64 <1416000000>;
+		opp-1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <750000 750000 950000>;
 			clock-latency-ns = <40000>;
 			opp-suspend;
 		};
-		opp-1608000000 {
-			opp-hz = /bits/ 64 <1608000000>;
-			opp-microvolt = <887500 887500 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-1704000000 {
-			opp-hz = /bits/ 64 <1704000000>;
-			opp-microvolt = <937500 937500 950000>;
+		opp-1296000000 {
+			opp-hz = /bits/ 64 <1296000000>;
+			opp-microvolt = <775000 775000 950000>;
 			clock-latency-ns = <40000>;
 		};
 	};
@@ -33,9 +28,14 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
+		opp-1200000000{
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <750000 750000 950000>;
+			clock-latency-ns = <40000>;
+		};
 		opp-1416000000 {
 			opp-hz = /bits/ 64 <1416000000>;
-			opp-microvolt = <750000 750000 950000>;
+			opp-microvolt = <762500 762500 950000>;
 			clock-latency-ns = <40000>;
 		};
 		opp-1608000000 {
@@ -43,25 +43,20 @@
 			opp-microvolt = <787500 787500 950000>;
 			clock-latency-ns = <40000>;
 		};
-		opp-1800000000 {
-			opp-hz = /bits/ 64 <1800000000>;
-			opp-microvolt = <875000 875000 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-2016000000 {
-			opp-hz = /bits/ 64 <2016000000>;
-			opp-microvolt = <950000 950000 950000>;
-			clock-latency-ns = <40000>;
-		};
 	};
 
 	cluster2_opp_table: opp-table-cluster2 {
 		compatible = "operating-points-v2";
 		opp-shared;
 
+		opp-1200000000{
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <750000 750000 950000>;
+			clock-latency-ns = <40000>;
+		};
 		opp-1416000000 {
 			opp-hz = /bits/ 64 <1416000000>;
-			opp-microvolt = <750000 750000 950000>;
+			opp-microvolt = <762500 762500 950000>;
 			clock-latency-ns = <40000>;
 		};
 		opp-1608000000 {
@@ -69,16 +64,6 @@
 			opp-microvolt = <787500 787500 950000>;
 			clock-latency-ns = <40000>;
 		};
-		opp-1800000000 {
-			opp-hz = /bits/ 64 <1800000000>;
-			opp-microvolt = <875000 875000 950000>;
-			clock-latency-ns = <40000>;
-		};
-		opp-2016000000 {
-			opp-hz = /bits/ 64 <2016000000>;
-			opp-microvolt = <950000 950000 950000>;
-			clock-latency-ns = <40000>;
-		};
 	};
 
 	gpu_opp_table: opp-table {
@@ -104,10 +89,6 @@
 			opp-hz = /bits/ 64 <700000000>;
 			opp-microvolt = <750000 750000 850000>;
 		};
-		opp-850000000 {
-			opp-hz = /bits/ 64 <800000000>;
-			opp-microvolt = <787500 787500 850000>;
-		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
index 9c394f733bbf..8b717c4017a4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
@@ -236,7 +236,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -361,6 +361,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
@@ -429,7 +433,7 @@
 };
 
 &pwm13 {
-	pinctrl-names = "active";
+	pinctrl-names = "default";
 	pinctrl-0 = <&pwm13m2_pins>;
 	status = "okay";
 };
@@ -803,6 +807,14 @@
 	status = "okay";
 };
 
+&u2phy0 {
+	status = "okay";
+};
+
+&u2phy0_otg {
+	status = "okay";
+};
+
 &u2phy2 {
 	status = "okay";
 };
@@ -832,6 +844,16 @@
 	pinctrl-0 = <&uart9m2_xfer &uart9m2_ctsn>;
 };
 
+&usbdp_phy0 {
+	/*
+	 * USBDP PHY0 is wired to a USB3 Type-A OTG connector. Additionally
+	 * the differential pairs 0+1 and the aux channel are wired to a
+	 * mini DP connector.
+	 */
+	rockchip,dp-lane-mux = <0 1>;
+	status = "okay";
+};
+
 &usb_host0_ehci {
 	status = "okay";
 };
@@ -840,6 +862,11 @@
 	status = "okay";
 };
 
+&usb_host0_xhci {
+	extcon = <&u2phy0>;
+	status = "okay";
+};
+
 &usb_host1_ehci {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588s-evb1-v10.dts
index bc4077575beb..9f4aca9c2e3f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-evb1-v10.dts
@@ -242,7 +242,7 @@
 	status = "okay";
 
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		clocks = <&cru I2S0_8CH_MCLKOUT>;
 		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
@@ -340,6 +340,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	audio {
 		hp_detect: headphone-detect {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts
index 812bba0aef1a..873a2bd6a6de 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-gameforce-ace.dts
@@ -611,7 +611,7 @@
 	status = "okay";
 
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		assigned-clock-rates = <12288000>;
 		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
@@ -675,6 +675,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	audio-amplifier {
 		headphone_amplifier_en: headphone-amplifier-en {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
index 4a3aa80f2226..4189a88ecf40 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
@@ -278,7 +278,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -412,7 +412,7 @@
 	status = "okay";
 
 	es8388: audio-codec@11 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x11>;
 		assigned-clock-rates = <12288000>;
 		assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
@@ -455,6 +455,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	bluetooth-pins {
 		bt_reset: bt-reset {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts b/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
index ac48e7fd3923..88a5e822ed17 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-khadas-edge2.dts
@@ -233,6 +233,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	vdd_sd {
 		vdd_sd_en: vdd-sd-en {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi
index d2eddea1840f..fbf062ec3bf1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi
@@ -251,7 +251,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -359,6 +359,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	gpio-key {
 		key1_pin: key1-pin {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-odroid-m2.dts b/arch/arm64/boot/dts/rockchip/rk3588s-odroid-m2.dts
index 8f034c6d494c..a72063c55140 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-odroid-m2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-odroid-m2.dts
@@ -264,7 +264,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -433,6 +433,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	lcd {
 		lcd_pwren: lcd-pwren {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dtsi
index d86aeacca238..4fedc50cce8c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dtsi
@@ -197,7 +197,11 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdmi0_sound {
+	status = "okay";
+};
+
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -268,7 +272,7 @@
 	status = "okay";
 
 	es8388: audio-codec@10 {
-		compatible = "everest,es8388";
+		compatible = "everest,es8388", "everest,es8328";
 		reg = <0x10>;
 		clocks = <&cru I2S1_8CH_MCLKOUT>;
 		AVDD-supply = <&vcc_3v3_s0>;
@@ -355,6 +359,10 @@
 	status = "okay";
 };
 
+&i2s5_8ch {
+	status = "okay";
+};
+
 &mdio1 {
 	rgmii_phy1: ethernet-phy@1 {
 		compatible = "ethernet-phy-ieee802.3-c22";
@@ -365,6 +373,10 @@
 	};
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	hym8563 {
 		hym8563_int: hym8563-int {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
index 70a43432bdc5..f894742b1ebe 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
@@ -334,7 +334,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -359,6 +359,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	leds {
 		io_led: io-led {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5c.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5c.dts
index 9b14d5383cdc..dd7317bab613 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5c.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5c.dts
@@ -68,10 +68,10 @@
 		};
 	};
 
-	fan {
+	fan: fan {
 		compatible = "pwm-fan";
 		#cooling-cells = <2>;
-		cooling-levels = <0 64 128 192 255>;
+		cooling-levels = <0 24 44 64 128 192 255>;
 		fan-supply = <&vcc_5v0>;
 		pwms = <&pwm3 0 10000 0>;
 	};
@@ -278,7 +278,7 @@
 	};
 };
 
-&hdptxphy_hdmi0 {
+&hdptxphy0 {
 	status = "okay";
 };
 
@@ -417,6 +417,36 @@
 	};
 };
 
+&package_thermal {
+	polling-delay = <1000>;
+
+	trips {
+		package_fan0: package-fan0 {
+			temperature = <55000>;
+			hysteresis = <2000>;
+			type = "active";
+		};
+
+		package_fan1: package-fan1 {
+			temperature = <65000>;
+			hysteresis = <2000>;
+			type = "active";
+		};
+	};
+
+	cooling-maps {
+		map0 {
+			trip = <&package_fan0>;
+			cooling-device = <&fan THERMAL_NO_LIMIT 1>;
+		};
+
+		map1 {
+			trip = <&package_fan1>;
+			cooling-device = <&fan 2 THERMAL_NO_LIMIT>;
+		};
+	};
+};
+
 &pcie2x1l2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie20x1_2_perstn_m0>;
@@ -425,6 +455,10 @@
 	status = "okay";
 };
 
+&pd_gpu {
+	domain-supply = <&vdd_gpu_s0>;
+};
+
 &pinctrl {
 	leds {
 		led_pins: led-pins {
@@ -843,6 +877,8 @@
 };
 
 &tsadc {
+	rockchip,hw-tshut-mode = <1>; /* tshut mode 0:CRU 1:GPIO */
+	rockchip,hw-tshut-polarity = <0>; /* tshut polarity 0:LOW 1:HIGH */
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/st/Makefile b/arch/arm64/boot/dts/st/Makefile
index 881fe1296c58..63908113ae36 100644
--- a/arch/arm64/boot/dts/st/Makefile
+++ b/arch/arm64/boot/dts/st/Makefile
@@ -1,2 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
-dtb-$(CONFIG_ARCH_STM32) += stm32mp257f-ev1.dtb
+dtb-$(CONFIG_ARCH_STM32) += \
+	stm32mp215f-dk.dtb \
+	stm32mp235f-dk.dtb \
+	stm32mp257f-dk.dtb \
+	stm32mp257f-ev1.dtb
diff --git a/arch/arm64/boot/dts/st/stm32mp211.dtsi b/arch/arm64/boot/dts/st/stm32mp211.dtsi
new file mode 100644
index 000000000000..bf888d60cd4f
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp211.dtsi
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a35";
+			reg = <0>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+	};
+
+	arm-pmu {
+		compatible = "arm,cortex-a35-pmu";
+		interrupts = <GIC_SPI 368 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>;
+		interrupt-parent = <&intc>;
+	};
+
+	arm_wdt: watchdog {
+		compatible = "arm,smc-wdt";
+		arm,smc-id = <0xbc000000>;
+		status = "disabled";
+	};
+
+	ck_flexgen_08: clock-64000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <64000000>;
+	};
+
+	ck_flexgen_51: clock-200000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+	};
+
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+
+		scmi: scmi {
+			compatible = "linaro,scmi-optee";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			linaro,optee-channel-id = <0>;
+
+			scmi_clk: protocol@14 {
+				reg = <0x14>;
+				#clock-cells = <1>;
+			};
+
+			scmi_reset: protocol@16 {
+				reg = <0x16>;
+				#reset-cells = <1>;
+			};
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&intc>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
+		arm,no-tick-in-suspend;
+	};
+
+	soc@0 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x0 0x0 0x0 0x80000000>;
+		dma-ranges = <0x0 0x0 0x80000000 0x1 0x0>;
+		interrupt-parent = <&intc>;
+		#address-cells = <1>;
+		#size-cells = <2>;
+
+		rifsc: bus@42080000 {
+			compatible = "simple-bus";
+			reg = <0x42080000 0x0 0x1000>;
+			ranges;
+			dma-ranges;
+			#address-cells = <1>;
+			#size-cells = <2>;
+
+			usart2: serial@400e0000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x400e0000 0x0 0x400>;
+				interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&ck_flexgen_08>;
+				status = "disabled";
+			};
+		};
+
+		syscfg: syscon@44230000 {
+			compatible = "st,stm32mp21-syscfg", "syscon";
+			reg = <0x44230000 0x0 0x10000>;
+		};
+
+		intc: interrupt-controller@4ac10000 {
+			compatible = "arm,gic-400";
+			reg = <0x4ac10000 0x0 0x1000>,
+			      <0x4ac20000 0x0 0x20000>,
+			      <0x4ac40000 0x0 0x20000>,
+			      <0x4ac60000 0x0 0x20000>;
+			      #interrupt-cells = <3>;
+			      interrupt-controller;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp213.dtsi b/arch/arm64/boot/dts/st/stm32mp213.dtsi
new file mode 100644
index 000000000000..fdd2dc432edd
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp213.dtsi
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include "stm32mp211.dtsi"
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp215.dtsi b/arch/arm64/boot/dts/st/stm32mp215.dtsi
new file mode 100644
index 000000000000..a7df77f928c5
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp215.dtsi
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include "stm32mp213.dtsi"
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp215f-dk.dts b/arch/arm64/boot/dts/st/stm32mp215f-dk.dts
new file mode 100644
index 000000000000..7bdaeaa5ab0f
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp215f-dk.dts
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Amelie Delaunay <amelie.delaunay@foss.st.com> for STMicroelectronics.
+ */
+
+/dts-v1/;
+
+#include "stm32mp215.dtsi"
+#include "stm32mp21xf.dtsi"
+
+/ {
+	model = "STMicroelectronics STM32MP215F-DK Discovery Board";
+	compatible = "st,stm32mp215f-dk", "st,stm32mp215";
+
+	aliases {
+		serial0 = &usart2;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x0 0x80000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		fw@80000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0x80000000 0x0 0x4000000>;
+			no-map;
+		};
+	};
+};
+
+&arm_wdt {
+	timeout-sec = <32>;
+	status = "okay";
+};
+
+&usart2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp21xc.dtsi b/arch/arm64/boot/dts/st/stm32mp21xc.dtsi
new file mode 100644
index 000000000000..e33b00b424e1
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp21xc.dtsi
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp21xf.dtsi b/arch/arm64/boot/dts/st/stm32mp21xf.dtsi
new file mode 100644
index 000000000000..e33b00b424e1
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp21xf.dtsi
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp231.dtsi b/arch/arm64/boot/dts/st/stm32mp231.dtsi
new file mode 100644
index 000000000000..75697acd1345
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp231.dtsi
@@ -0,0 +1,1213 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include <dt-bindings/clock/st,stm32mp25-rcc.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/regulator/st,stm32mp25-regulator.h>
+#include <dt-bindings/reset/st,stm32mp25-rcc.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a35";
+			reg = <0>;
+			device_type = "cpu";
+			enable-method = "psci";
+			power-domains = <&cpu0_pd>;
+			power-domain-names = "psci";
+		};
+	};
+
+	arm-pmu {
+		compatible = "arm,cortex-a35-pmu";
+		interrupts = <GIC_SPI 368 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>;
+		interrupt-parent = <&intc>;
+	};
+
+	arm_wdt: watchdog {
+		compatible = "arm,smc-wdt";
+		arm,smc-id = <0xb200005a>;
+		status = "disabled";
+	};
+
+	clk_dsi_txbyte: clock-0 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	clk_rcbsec: clk-64000000 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <64000000>;
+	};
+
+	firmware {
+		optee: optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+			interrupt-parent = <&intc>;
+			interrupts = <GIC_PPI 15 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
+		};
+
+		scmi {
+			compatible = "linaro,scmi-optee";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			linaro,optee-channel-id = <0>;
+
+			scmi_clk: protocol@14 {
+				reg = <0x14>;
+				#clock-cells = <1>;
+			};
+
+			scmi_reset: protocol@16 {
+				reg = <0x16>;
+				#reset-cells = <1>;
+			};
+
+			scmi_voltd: protocol@17 {
+				reg = <0x17>;
+
+				scmi_regu: regulators {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					scmi_vddio1: regulator@0 {
+						reg = <VOLTD_SCMI_VDDIO1>;
+						regulator-name = "vddio1";
+					};
+					scmi_vddio2: regulator@1 {
+						reg = <VOLTD_SCMI_VDDIO2>;
+						regulator-name = "vddio2";
+					};
+					scmi_vddio3: regulator@2 {
+						reg = <VOLTD_SCMI_VDDIO3>;
+						regulator-name = "vddio3";
+					};
+					scmi_vddio4: regulator@3 {
+						reg = <VOLTD_SCMI_VDDIO4>;
+						regulator-name = "vddio4";
+					};
+					scmi_vdd33ucpd: regulator@5 {
+						reg = <VOLTD_SCMI_UCPD>;
+						regulator-name = "vdd33ucpd";
+					};
+					scmi_vdda18adc: regulator@7 {
+						reg = <VOLTD_SCMI_ADC>;
+						regulator-name = "vdda18adc";
+					};
+				};
+			};
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+
+		cpu0_pd: power-domain-cpu0 {
+			#power-domain-cells = <0>;
+			power-domains = <&cluster_pd>;
+		};
+
+		cluster_pd: power-domain-cluster {
+			#power-domain-cells = <0>;
+			power-domains = <&ret_pd>;
+		};
+
+		ret_pd: power-domain-retention {
+			#power-domain-cells = <0>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&intc>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
+		always-on;
+	};
+
+	soc@0 {
+		compatible = "simple-bus";
+		ranges = <0x0 0x0 0x0 0x80000000>;
+		interrupt-parent = <&intc>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		hpdma: dma-controller@40400000 {
+			compatible = "st,stm32mp25-dma3";
+			reg = <0x40400000 0x1000>;
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&scmi_clk CK_SCMI_HPDMA1>;
+			#dma-cells = <3>;
+		};
+
+		hpdma2: dma-controller@40410000 {
+			compatible = "st,stm32mp25-dma3";
+			reg = <0x40410000 0x1000>;
+			interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&scmi_clk CK_SCMI_HPDMA2>;
+			#dma-cells = <3>;
+		};
+
+		hpdma3: dma-controller@40420000 {
+			compatible = "st,stm32mp25-dma3";
+			reg = <0x40420000 0x1000>;
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&scmi_clk CK_SCMI_HPDMA3>;
+			#dma-cells = <3>;
+		};
+
+		rifsc: bus@42080000 {
+			compatible = "st,stm32mp25-rifsc", "simple-bus";
+			reg = <0x42080000 0x1000>;
+			ranges;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			#access-controller-cells = <1>;
+
+			i2s2: audio-controller@400b0000 {
+				compatible = "st,stm32mp25-i2s";
+				reg = <0x400b0000 0x400>;
+				#sound-dai-cells = <0>;
+				interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_BUS_SPI2>, <&rcc CK_KER_SPI2>;
+				clock-names = "pclk", "i2sclk";
+				resets = <&rcc SPI2_R>;
+				dmas = <&hpdma 51 0x43 0x12>,
+				       <&hpdma 52 0x43 0x21>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 23>;
+				status = "disabled";
+			};
+
+			spi2: spi@400b0000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x400b0000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI2>;
+				resets = <&rcc SPI2_R>;
+				dmas = <&hpdma 51 0x20 0x3012>,
+				       <&hpdma 52 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 23>;
+				status = "disabled";
+			};
+
+			i2s3: audio-controller@400c0000 {
+				compatible = "st,stm32mp25-i2s";
+				reg = <0x400c0000 0x400>;
+				#sound-dai-cells = <0>;
+				interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_BUS_SPI3>, <&rcc CK_KER_SPI3>;
+				clock-names = "pclk", "i2sclk";
+				resets = <&rcc SPI3_R>;
+				dmas = <&hpdma 53 0x43 0x12>,
+				       <&hpdma 54 0x43 0x21>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 24>;
+				status = "disabled";
+			};
+
+			spi3: spi@400c0000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x400c0000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI3>;
+				resets = <&rcc SPI3_R>;
+				dmas = <&hpdma 53 0x20 0x3012>,
+				       <&hpdma 54 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 24>;
+				status = "disabled";
+			};
+
+			spdifrx: audio-controller@400d0000 {
+				compatible = "st,stm32h7-spdifrx";
+				reg = <0x400d0000 0x400>;
+				#sound-dai-cells = <0>;
+				clocks = <&rcc CK_KER_SPDIFRX>;
+				clock-names = "kclk";
+				interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+				dmas = <&hpdma 71 0x43 0x212>,
+				       <&hpdma 72 0x43 0x212>;
+				dma-names = "rx", "rx-ctrl";
+				access-controllers = <&rifsc 30>;
+				status = "disabled";
+			};
+
+			usart2: serial@400e0000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x400e0000 0x400>;
+				interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_USART2>;
+				dmas = <&hpdma 11 0x20 0x10012>,
+				       <&hpdma 12 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 32>;
+				status = "disabled";
+			};
+
+			usart3: serial@400f0000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x400f0000 0x400>;
+				interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_USART3>;
+				dmas = <&hpdma 13 0x20 0x10012>,
+				       <&hpdma 14 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 33>;
+				status = "disabled";
+			};
+
+			uart4: serial@40100000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x40100000 0x400>;
+				interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_UART4>;
+				dmas = <&hpdma 15 0x20 0x10012>,
+				       <&hpdma 16 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 34>;
+				status = "disabled";
+			};
+
+			uart5: serial@40110000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x40110000 0x400>;
+				interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_UART5>;
+				dmas = <&hpdma 17 0x20 0x10012>,
+				       <&hpdma 18 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 35>;
+				status = "disabled";
+			};
+
+			i2c1: i2c@40120000 {
+				compatible = "st,stm32mp25-i2c";
+				reg = <0x40120000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupt-names = "event";
+				interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_I2C1>;
+				resets = <&rcc I2C1_R>;
+				dmas = <&hpdma 27 0x20 0x3012>,
+				       <&hpdma 28 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 41>;
+				status = "disabled";
+			};
+
+			i2c2: i2c@40130000 {
+				compatible = "st,stm32mp25-i2c";
+				reg = <0x40130000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupt-names = "event";
+				interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_I2C2>;
+				resets = <&rcc I2C2_R>;
+				dmas = <&hpdma 30 0x20 0x3012>,
+				       <&hpdma 31 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 42>;
+				status = "disabled";
+			};
+
+			i2c7: i2c@40180000 {
+				compatible = "st,stm32mp25-i2c";
+				reg = <0x40180000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupt-names = "event";
+				interrupts = <GIC_SPI 210 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_I2C7>;
+				resets = <&rcc I2C7_R>;
+				dmas = <&hpdma 45 0x20 0x3012>,
+				       <&hpdma 46 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 47>;
+				status = "disabled";
+			};
+
+			usart6: serial@40220000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x40220000 0x400>;
+				interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_USART6>;
+				dmas = <&hpdma 19 0x20 0x10012>,
+				       <&hpdma 20 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 36>;
+				status = "disabled";
+			};
+
+			i2s1: audio-controller@40230000 {
+				compatible = "st,stm32mp25-i2s";
+				reg = <0x40230000 0x400>;
+				#sound-dai-cells = <0>;
+				interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_BUS_SPI1>, <&rcc CK_KER_SPI1>;
+				clock-names = "pclk", "i2sclk";
+				resets = <&rcc SPI1_R>;
+				dmas = <&hpdma 49 0x43 0x12>,
+				       <&hpdma 50 0x43 0x21>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 22>;
+				status = "disabled";
+			};
+
+			spi1: spi@40230000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x40230000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI1>;
+				resets = <&rcc SPI1_R>;
+				dmas = <&hpdma 49 0x20 0x3012>,
+				       <&hpdma 50 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 22>;
+				status = "disabled";
+			};
+
+			spi4: spi@40240000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x40240000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI4>;
+				resets = <&rcc SPI4_R>;
+				dmas = <&hpdma 55 0x20 0x3012>,
+				       <&hpdma 56 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 25>;
+				status = "disabled";
+			};
+
+			spi5: spi@40280000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x40280000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI5>;
+				resets = <&rcc SPI5_R>;
+				dmas = <&hpdma 57 0x20 0x3012>,
+				       <&hpdma 58 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 26>;
+				status = "disabled";
+			};
+
+			sai1: sai@40290000 {
+				compatible = "st,stm32mp25-sai";
+				reg = <0x40290000 0x4>, <0x4029a3f0 0x10>;
+				ranges = <0 0x40290000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				clocks = <&rcc CK_BUS_SAI1>;
+				clock-names = "pclk";
+				interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc SAI1_R>;
+				access-controllers = <&rifsc 49>;
+				status = "disabled";
+
+				sai1a: audio-controller@40290004 {
+					compatible = "st,stm32-sai-sub-a";
+					reg = <0x4 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI1>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 73 0x43 0x21>;
+					status = "disabled";
+				};
+
+				sai1b: audio-controller@40290024 {
+					compatible = "st,stm32-sai-sub-b";
+					reg = <0x24 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI1>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 74 0x43 0x12>;
+					status = "disabled";
+				};
+			};
+
+			sai2: sai@402a0000 {
+				compatible = "st,stm32mp25-sai";
+				reg = <0x402a0000 0x4>, <0x402aa3f0 0x10>;
+				ranges = <0 0x402a0000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				clocks = <&rcc CK_BUS_SAI2>;
+				clock-names = "pclk";
+				interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc SAI2_R>;
+				access-controllers = <&rifsc 50>;
+				status = "disabled";
+
+				sai2a: audio-controller@402a0004 {
+					compatible = "st,stm32-sai-sub-a";
+					reg = <0x4 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI2>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 75 0x43 0x21>;
+					status = "disabled";
+				};
+
+				sai2b: audio-controller@402a0024 {
+					compatible = "st,stm32-sai-sub-b";
+					reg = <0x24 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI2>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 76 0x43 0x12>;
+					status = "disabled";
+				};
+			};
+
+			sai3: sai@402b0000 {
+				compatible = "st,stm32mp25-sai";
+				reg = <0x402b0000 0x4>, <0x402ba3f0 0x10>;
+				ranges = <0 0x402b0000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				clocks = <&rcc CK_BUS_SAI3>;
+				clock-names = "pclk";
+				interrupts = <GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc SAI3_R>;
+				access-controllers = <&rifsc 51>;
+				status = "disabled";
+
+				sai3a: audio-controller@402b0004 {
+					compatible = "st,stm32-sai-sub-a";
+					reg = <0x4 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI3>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 77 0x43 0x21>;
+					status = "disabled";
+				};
+
+				sai3b: audio-controller@502b0024 {
+					compatible = "st,stm32-sai-sub-b";
+					reg = <0x24 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI3>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 78 0x43 0x12>;
+					status = "disabled";
+				};
+			};
+
+			usart1: serial@40330000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x40330000 0x400>;
+				interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_USART1>;
+				dmas = <&hpdma 9 0x20 0x10012>,
+				       <&hpdma 10 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 31>;
+				status = "disabled";
+			};
+
+			sai4: sai@40340000 {
+				compatible = "st,stm32mp25-sai";
+				reg = <0x40340000 0x4>, <0x4034a3f0 0x10>;
+				ranges = <0 0x40340000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				clocks = <&rcc CK_BUS_SAI4>;
+				clock-names = "pclk";
+				interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc SAI4_R>;
+				access-controllers = <&rifsc 52>;
+				status = "disabled";
+
+				sai4a: audio-controller@40340004 {
+					compatible = "st,stm32-sai-sub-a";
+					reg = <0x4 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI4>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 79 0x63 0x21>;
+					status = "disabled";
+				};
+
+				sai4b: audio-controller@40340024 {
+					compatible = "st,stm32-sai-sub-b";
+					reg = <0x24 0x20>;
+					#sound-dai-cells = <0>;
+					clocks = <&rcc CK_KER_SAI4>;
+					clock-names = "sai_ck";
+					dmas = <&hpdma 80 0x43 0x12>;
+					status = "disabled";
+				};
+			};
+
+			uart7: serial@40370000 {
+				compatible = "st,stm32h7-uart";
+				reg = <0x40370000 0x400>;
+				interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_UART7>;
+				dmas = <&hpdma 21 0x20 0x10012>,
+				       <&hpdma 22 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 37>;
+				status = "disabled";
+			};
+
+			rng: rng@42020000 {
+				compatible = "st,stm32mp25-rng";
+				reg = <0x42020000 0x400>;
+				clocks = <&clk_rcbsec>, <&rcc CK_BUS_RNG>;
+				clock-names = "core", "bus";
+				resets = <&rcc RNG_R>;
+				access-controllers = <&rifsc 92>;
+				status = "disabled";
+			};
+
+			spi8: spi@46020000 {
+				compatible = "st,stm32mp25-spi";
+				reg = <0x46020000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SPI8>;
+				resets = <&rcc SPI8_R>;
+				dmas = <&hpdma 171 0x20 0x3012>,
+				       <&hpdma 172 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 29>;
+				status = "disabled";
+			};
+
+			i2c8: i2c@46040000 {
+				compatible = "st,stm32mp25-i2c";
+				reg = <0x46040000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				interrupt-names = "event";
+				interrupts = <GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_I2C8>;
+				resets = <&rcc I2C8_R>;
+				dmas = <&hpdma 168 0x20 0x3012>,
+				       <&hpdma 169 0x20 0x3021>;
+				dma-names = "rx", "tx";
+				access-controllers = <&rifsc 48>;
+				status = "disabled";
+			};
+
+			csi: csi@48020000 {
+				compatible = "st,stm32mp25-csi";
+				reg = <0x48020000 0x2000>;
+				interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc CSI_R>;
+				clocks = <&rcc CK_KER_CSI>, <&rcc CK_KER_CSITXESC>,
+					 <&rcc CK_KER_CSIPHY>;
+				clock-names = "pclk", "txesc", "csi2phy";
+				access-controllers = <&rifsc 86>;
+				status = "disabled";
+			};
+
+			dcmipp: dcmipp@48030000 {
+				compatible = "st,stm32mp25-dcmipp";
+				reg = <0x48030000 0x1000>;
+				interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>;
+				resets = <&rcc DCMIPP_R>;
+				clocks = <&rcc CK_BUS_DCMIPP>, <&rcc CK_KER_CSI>;
+				clock-names = "kclk", "mclk";
+				access-controllers = <&rifsc 87>;
+				status = "disabled";
+			};
+
+			sdmmc1: mmc@48220000 {
+				compatible = "st,stm32mp25-sdmmc2", "arm,pl18x", "arm,primecell";
+				reg = <0x48220000 0x400>, <0x44230400 0x8>;
+				arm,primecell-periphid = <0x00353180>;
+				interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&rcc CK_KER_SDMMC1 >;
+				clock-names = "apb_pclk";
+				resets = <&rcc SDMMC1_R>;
+				cap-sd-highspeed;
+				cap-mmc-highspeed;
+				max-frequency = <120000000>;
+				access-controllers = <&rifsc 76>;
+				status = "disabled";
+			};
+
+			ethernet1: ethernet@482c0000 {
+				compatible = "st,stm32mp25-dwmac", "snps,dwmac-5.20";
+				reg = <0x482c0000 0x4000>;
+				reg-names = "stmmaceth";
+				interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq";
+				clock-names = "stmmaceth",
+					      "mac-clk-tx",
+					      "mac-clk-rx",
+					      "ptp_ref",
+					      "ethstp",
+					      "eth-ck";
+				clocks = <&rcc CK_ETH1_MAC>,
+					 <&rcc CK_ETH1_TX>,
+					 <&rcc CK_ETH1_RX>,
+					 <&rcc CK_KER_ETH1PTP>,
+					 <&rcc CK_ETH1_STP>,
+					 <&rcc CK_KER_ETH1>;
+				snps,axi-config = <&stmmac_axi_config_1>;
+				snps,mixed-burst;
+				snps,mtl-rx-config = <&mtl_rx_setup_1>;
+				snps,mtl-tx-config = <&mtl_tx_setup_1>;
+				snps,pbl = <2>;
+				snps,tso;
+				st,syscon = <&syscfg 0x3000>;
+				access-controllers = <&rifsc 60>;
+				status = "disabled";
+
+				mtl_rx_setup_1: rx-queues-config {
+					snps,rx-queues-to-use = <2>;
+					queue0 {};
+					queue1 {};
+				};
+
+				mtl_tx_setup_1: tx-queues-config {
+					snps,tx-queues-to-use = <4>;
+					queue0 {};
+					queue1 {};
+					queue2 {};
+					queue3 {};
+				};
+
+				stmmac_axi_config_1: stmmac-axi-config {
+					snps,blen = <0 0 0 0 16 8 4>;
+					snps,rd_osr_lmt = <0x7>;
+					snps,wr_osr_lmt = <0x7>;
+				};
+			};
+		};
+
+		bsec: efuse@44000000 {
+			compatible = "st,stm32mp25-bsec";
+			reg = <0x44000000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			part_number_otp@24 {
+				reg = <0x24 0x4>;
+			};
+
+			package_otp@1e8 {
+				reg = <0x1e8 0x1>;
+				bits = <0 3>;
+			};
+		};
+
+		rcc: clock-controller@44200000 {
+			compatible = "st,stm32mp25-rcc";
+			reg = <0x44200000 0x10000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			clocks = <&scmi_clk CK_SCMI_HSE>,
+				<&scmi_clk CK_SCMI_HSI>,
+				<&scmi_clk CK_SCMI_MSI>,
+				<&scmi_clk CK_SCMI_LSE>,
+				<&scmi_clk CK_SCMI_LSI>,
+				<&scmi_clk CK_SCMI_HSE_DIV2>,
+				<&scmi_clk CK_SCMI_ICN_HS_MCU>,
+				<&scmi_clk CK_SCMI_ICN_LS_MCU>,
+				<&scmi_clk CK_SCMI_ICN_SDMMC>,
+				<&scmi_clk CK_SCMI_ICN_DDR>,
+				<&scmi_clk CK_SCMI_ICN_DISPLAY>,
+				<&scmi_clk CK_SCMI_ICN_HSL>,
+				<&scmi_clk CK_SCMI_ICN_NIC>,
+				<&scmi_clk CK_SCMI_ICN_VID>,
+				<&scmi_clk CK_SCMI_FLEXGEN_07>,
+				<&scmi_clk CK_SCMI_FLEXGEN_08>,
+				<&scmi_clk CK_SCMI_FLEXGEN_09>,
+				<&scmi_clk CK_SCMI_FLEXGEN_10>,
+				<&scmi_clk CK_SCMI_FLEXGEN_11>,
+				<&scmi_clk CK_SCMI_FLEXGEN_12>,
+				<&scmi_clk CK_SCMI_FLEXGEN_13>,
+				<&scmi_clk CK_SCMI_FLEXGEN_14>,
+				<&scmi_clk CK_SCMI_FLEXGEN_15>,
+				<&scmi_clk CK_SCMI_FLEXGEN_16>,
+				<&scmi_clk CK_SCMI_FLEXGEN_17>,
+				<&scmi_clk CK_SCMI_FLEXGEN_18>,
+				<&scmi_clk CK_SCMI_FLEXGEN_19>,
+				<&scmi_clk CK_SCMI_FLEXGEN_20>,
+				<&scmi_clk CK_SCMI_FLEXGEN_21>,
+				<&scmi_clk CK_SCMI_FLEXGEN_22>,
+				<&scmi_clk CK_SCMI_FLEXGEN_23>,
+				<&scmi_clk CK_SCMI_FLEXGEN_24>,
+				<&scmi_clk CK_SCMI_FLEXGEN_25>,
+				<&scmi_clk CK_SCMI_FLEXGEN_26>,
+				<&scmi_clk CK_SCMI_FLEXGEN_27>,
+				<&scmi_clk CK_SCMI_FLEXGEN_28>,
+				<&scmi_clk CK_SCMI_FLEXGEN_29>,
+				<&scmi_clk CK_SCMI_FLEXGEN_30>,
+				<&scmi_clk CK_SCMI_FLEXGEN_31>,
+				<&scmi_clk CK_SCMI_FLEXGEN_32>,
+				<&scmi_clk CK_SCMI_FLEXGEN_33>,
+				<&scmi_clk CK_SCMI_FLEXGEN_34>,
+				<&scmi_clk CK_SCMI_FLEXGEN_35>,
+				<&scmi_clk CK_SCMI_FLEXGEN_36>,
+				<&scmi_clk CK_SCMI_FLEXGEN_37>,
+				<&scmi_clk CK_SCMI_FLEXGEN_38>,
+				<&scmi_clk CK_SCMI_FLEXGEN_39>,
+				<&scmi_clk CK_SCMI_FLEXGEN_40>,
+				<&scmi_clk CK_SCMI_FLEXGEN_41>,
+				<&scmi_clk CK_SCMI_FLEXGEN_42>,
+				<&scmi_clk CK_SCMI_FLEXGEN_43>,
+				<&scmi_clk CK_SCMI_FLEXGEN_44>,
+				<&scmi_clk CK_SCMI_FLEXGEN_45>,
+				<&scmi_clk CK_SCMI_FLEXGEN_46>,
+				<&scmi_clk CK_SCMI_FLEXGEN_47>,
+				<&scmi_clk CK_SCMI_FLEXGEN_48>,
+				<&scmi_clk CK_SCMI_FLEXGEN_49>,
+				<&scmi_clk CK_SCMI_FLEXGEN_50>,
+				<&scmi_clk CK_SCMI_FLEXGEN_51>,
+				<&scmi_clk CK_SCMI_FLEXGEN_52>,
+				<&scmi_clk CK_SCMI_FLEXGEN_53>,
+				<&scmi_clk CK_SCMI_FLEXGEN_54>,
+				<&scmi_clk CK_SCMI_FLEXGEN_55>,
+				<&scmi_clk CK_SCMI_FLEXGEN_56>,
+				<&scmi_clk CK_SCMI_FLEXGEN_57>,
+				<&scmi_clk CK_SCMI_FLEXGEN_58>,
+				<&scmi_clk CK_SCMI_FLEXGEN_59>,
+				<&scmi_clk CK_SCMI_FLEXGEN_60>,
+				<&scmi_clk CK_SCMI_FLEXGEN_61>,
+				<&scmi_clk CK_SCMI_FLEXGEN_62>,
+				<&scmi_clk CK_SCMI_FLEXGEN_63>,
+				<&scmi_clk CK_SCMI_ICN_APB1>,
+				<&scmi_clk CK_SCMI_ICN_APB2>,
+				<&scmi_clk CK_SCMI_ICN_APB3>,
+				<&scmi_clk CK_SCMI_ICN_APB4>,
+				<&scmi_clk CK_SCMI_ICN_APBDBG>,
+				<&scmi_clk CK_SCMI_TIMG1>,
+				<&scmi_clk CK_SCMI_TIMG2>,
+				<&scmi_clk CK_SCMI_PLL3>,
+				<&clk_dsi_txbyte>;
+				access-controllers = <&rifsc 156>;
+		};
+
+		exti1: interrupt-controller@44220000 {
+			compatible = "st,stm32mp1-exti", "syscon";
+			reg = <0x44220000 0x400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupts-extended =
+				<&intc GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_0 */
+				<&intc GIC_SPI 269 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 270 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 271 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 273 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 274 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 275 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 276 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 277 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_10 */
+				<&intc GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 283 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 1   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,						/* EXTI_20 */
+				<&intc GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_30 */
+				<&intc GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_40 */
+				<&intc GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 209 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 229 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 215 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 210 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_50 */
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,						/* EXTI_60 */
+				<&intc GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 10  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_70 */
+				<0>,
+				<&intc GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 253 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 255 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,						/* EXTI_80 */
+				<0>,
+				<0>,
+				<&intc GIC_SPI 257 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 258 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		syscfg: syscon@44230000 {
+			compatible = "st,stm32mp23-syscfg", "syscon";
+			reg = <0x44230000 0x10000>;
+		};
+
+		pinctrl: pinctrl@44240000 {
+			compatible = "st,stm32mp257-pinctrl";
+			ranges = <0 0x44240000 0xa0400>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			interrupt-parent = <&exti1>;
+			st,syscfg = <&exti1 0x60 0xff>;
+			pins-are-numbered;
+
+			gpioa: gpio@44240000 {
+				reg = <0x0 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOA>;
+				st,bank-name = "GPIOA";
+				status = "disabled";
+			};
+
+			gpiob: gpio@44250000 {
+				reg = <0x10000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOB>;
+				st,bank-name = "GPIOB";
+				status = "disabled";
+			};
+
+			gpioc: gpio@44260000 {
+				reg = <0x20000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOC>;
+				st,bank-name = "GPIOC";
+				status = "disabled";
+			};
+
+			gpiod: gpio@44270000 {
+				reg = <0x30000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOD>;
+				st,bank-name = "GPIOD";
+				status = "disabled";
+			};
+
+			gpioe: gpio@44280000 {
+				reg = <0x40000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOE>;
+				st,bank-name = "GPIOE";
+				status = "disabled";
+			};
+
+			gpiof: gpio@44290000 {
+				reg = <0x50000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOF>;
+				st,bank-name = "GPIOF";
+				status = "disabled";
+			};
+
+			gpiog: gpio@442a0000 {
+				reg = <0x60000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOG>;
+				st,bank-name = "GPIOG";
+				status = "disabled";
+			};
+
+			gpioh: gpio@442b0000 {
+				reg = <0x70000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOH>;
+				st,bank-name = "GPIOH";
+				status = "disabled";
+			};
+
+			gpioi: gpio@442c0000 {
+				reg = <0x80000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOI>;
+				st,bank-name = "GPIOI";
+				status = "disabled";
+			};
+
+			gpioj: gpio@442d0000 {
+				reg = <0x90000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOJ>;
+				st,bank-name = "GPIOJ";
+				status = "disabled";
+			};
+
+			gpiok: gpio@442e0000 {
+				reg = <0xa0000 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOK>;
+				st,bank-name = "GPIOK";
+				status = "disabled";
+			};
+		};
+
+		rtc: rtc@46000000 {
+			compatible = "st,stm32mp25-rtc";
+			reg = <0x46000000 0x400>;
+			clocks = <&scmi_clk CK_SCMI_RTC>,
+				 <&scmi_clk CK_SCMI_RTCCK>;
+			clock-names = "pclk", "rtc_ck";
+			interrupts-extended = <&exti2 17 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		pinctrl_z: pinctrl@46200000 {
+			compatible = "st,stm32mp257-z-pinctrl";
+			ranges = <0 0x46200000 0x400>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			interrupt-parent = <&exti1>;
+			st,syscfg = <&exti1 0x60 0xff>;
+			pins-are-numbered;
+
+			gpioz: gpio@46200000 {
+				reg = <0 0x400>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				clocks = <&scmi_clk CK_SCMI_GPIOZ>;
+				st,bank-name = "GPIOZ";
+				st,bank-ioport = <11>;
+				status = "disabled";
+			};
+
+		};
+
+		exti2: interrupt-controller@46230000 {
+			compatible = "st,stm32mp1-exti", "syscon";
+			reg = <0x46230000 0x400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupts-extended =
+				<&intc GIC_SPI 17  IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_0 */
+				<&intc GIC_SPI 18  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 19  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 20  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 21  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 22  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 23  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 24  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 25  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 26  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 27  IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_10 */
+				<&intc GIC_SPI 28  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 29  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 30  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 31  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 32  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 12  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 13  IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<0>,						/* EXTI_20 */
+				<&intc GIC_SPI 14  IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 15  IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_30 */
+				<&intc GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 177 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_40 */
+				<0>,
+				<0>,
+				<&intc GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 11  IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 5   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 4   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 6   IRQ_TYPE_LEVEL_HIGH>,	/* EXTI_50 */
+				<&intc GIC_SPI 7   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 2   IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 3   IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,
+				<0>,						/* EXTI_60 */
+				<&intc GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<&intc GIC_SPI 247 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 248 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 249 IRQ_TYPE_LEVEL_HIGH>,
+				<&intc GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
+				<0>,
+				<0>,
+				<&intc GIC_SPI 213 IRQ_TYPE_LEVEL_HIGH>;	/* EXTI_70 */
+		};
+
+		intc: interrupt-controller@4ac10000 {
+			compatible = "arm,gic-400";
+			reg = <0x4ac10000 0x1000>,
+			      <0x4ac20000 0x20000>,
+			      <0x4ac40000 0x20000>,
+			      <0x4ac60000 0x20000>;
+			#interrupt-cells = <3>;
+			interrupt-controller;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp233.dtsi b/arch/arm64/boot/dts/st/stm32mp233.dtsi
new file mode 100644
index 000000000000..78f4059fca5d
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp233.dtsi
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include "stm32mp231.dtsi"
+
+/ {
+	cpus {
+		cpu1: cpu@1 {
+			compatible = "arm,cortex-a35";
+			reg = <1>;
+			device_type = "cpu";
+			enable-method = "psci";
+			power-domains = <&cpu1_pd>;
+			power-domain-names = "psci";
+		};
+	};
+
+	arm-pmu {
+		interrupts = <GIC_SPI 368 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>;
+	};
+
+	psci {
+		cpu1_pd: power-domain-cpu1 {
+			#power-domain-cells = <0>;
+			power-domains = <&cluster_pd>;
+		};
+	};
+
+	timer {
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+};
+
+&optee {
+	interrupts = <GIC_PPI 15 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+};
+
+&rifsc {
+	ethernet2: ethernet@482d0000 {
+		compatible = "st,stm32mp25-dwmac", "snps,dwmac-5.20";
+		reg = <0x482d0000 0x4000>;
+		reg-names = "stmmaceth";
+		interrupts-extended = <&intc GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq";
+		clock-names = "stmmaceth",
+			      "mac-clk-tx",
+			      "mac-clk-rx",
+			      "ptp_ref",
+			      "ethstp",
+			      "eth-ck";
+		clocks = <&rcc CK_ETH2_MAC>,
+			 <&rcc CK_ETH2_TX>,
+			 <&rcc CK_ETH2_RX>,
+			 <&rcc CK_KER_ETH2PTP>,
+			 <&rcc CK_ETH2_STP>,
+			 <&rcc CK_KER_ETH2>;
+		snps,axi-config = <&stmmac_axi_config_2>;
+		snps,mixed-burst;
+		snps,mtl-rx-config = <&mtl_rx_setup_2>;
+		snps,mtl-tx-config = <&mtl_tx_setup_2>;
+		snps,pbl = <2>;
+		snps,tso;
+		st,syscon = <&syscfg 0x3400>;
+		access-controllers = <&rifsc 61>;
+		status = "disabled";
+
+		mtl_rx_setup_2: rx-queues-config {
+			snps,rx-queues-to-use = <2>;
+			queue0 {};
+			queue1 {};
+		};
+
+		mtl_tx_setup_2: tx-queues-config {
+			snps,tx-queues-to-use = <4>;
+			queue0 {};
+			queue1 {};
+			queue2 {};
+			queue3 {};
+		};
+
+		stmmac_axi_config_2: stmmac-axi-config {
+			snps,blen = <0 0 0 0 16 8 4>;
+			snps,rd_osr_lmt = <0x7>;
+			snps,wr_osr_lmt = <0x7>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp235.dtsi b/arch/arm64/boot/dts/st/stm32mp235.dtsi
new file mode 100644
index 000000000000..2719c088dd59
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp235.dtsi
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+#include "stm32mp233.dtsi"
+
+&rifsc {
+	vdec: vdec@480d0000 {
+		compatible = "st,stm32mp25-vdec";
+		reg = <0x480d0000 0x3c8>;
+		interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&rcc CK_BUS_VDEC>;
+		access-controllers = <&rifsc 89>;
+	};
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp235f-dk.dts b/arch/arm64/boot/dts/st/stm32mp235f-dk.dts
new file mode 100644
index 000000000000..04d1b434c433
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp235f-dk.dts
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Amelie Delaunay <amelie.delaunay@foss.st.com> for STMicroelectronics.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include "stm32mp235.dtsi"
+#include "stm32mp23xf.dtsi"
+#include "stm32mp25-pinctrl.dtsi"
+#include "stm32mp25xxak-pinctrl.dtsi"
+
+/ {
+	model = "STMicroelectronics STM32MP235F-DK Discovery Board";
+	compatible = "st,stm32mp235f-dk", "st,stm32mp235";
+
+	aliases {
+		serial0 = &usart2;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-user-1 {
+			label = "User-1";
+			linux,code = <BTN_1>;
+			gpios = <&gpioc 5 GPIO_ACTIVE_HIGH>;
+		};
+
+		button-user-2 {
+			label = "User-2";
+			linux,code = <BTN_2>;
+			gpios = <&gpioc 11 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led-blue {
+			function = LED_FUNCTION_HEARTBEAT;
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&gpioh 7 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+			default-state = "off";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x1 0x0>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		fw@80000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0x80000000 0x0 0x4000000>;
+			no-map;
+		};
+	};
+};
+
+&arm_wdt {
+	timeout-sec = <32>;
+	status = "okay";
+};
+
+&scmi_regu {
+	scmi_vddio1: regulator@0 {
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+	};
+	scmi_vdd_sdcard: regulator@23 {
+		reg = <VOLTD_SCMI_STPMIC2_LDO7>;
+		regulator-name = "vdd_sdcard";
+	};
+};
+
+&sdmmc1 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc1_b4_pins_a>;
+	pinctrl-1 = <&sdmmc1_b4_od_pins_a>;
+	pinctrl-2 = <&sdmmc1_b4_sleep_pins_a>;
+	cd-gpios = <&gpiod 3 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+	disable-wp;
+	st,neg-edge;
+	bus-width = <4>;
+	vmmc-supply = <&scmi_vdd_sdcard>;
+	vqmmc-supply = <&scmi_vddio1>;
+	status = "okay";
+};
+
+&usart2 {
+	pinctrl-names = "default", "idle", "sleep";
+	pinctrl-0 = <&usart2_pins_a>;
+	pinctrl-1 = <&usart2_idle_pins_a>;
+	pinctrl-2 = <&usart2_sleep_pins_a>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp23xc.dtsi b/arch/arm64/boot/dts/st/stm32mp23xc.dtsi
new file mode 100644
index 000000000000..e33b00b424e1
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp23xc.dtsi
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp23xf.dtsi b/arch/arm64/boot/dts/st/stm32mp23xf.dtsi
new file mode 100644
index 000000000000..e33b00b424e1
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp23xf.dtsi
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+
+/ {
+};
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index f3c6cdfd7008..87110f91e489 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -115,14 +115,13 @@
 	};
 
 	intc: interrupt-controller@4ac00000 {
-		compatible = "arm,cortex-a7-gic";
+		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
-		#address-cells = <1>;
 		interrupt-controller;
 		reg = <0x0 0x4ac10000 0x0 0x1000>,
-		      <0x0 0x4ac20000 0x0 0x2000>,
-		      <0x0 0x4ac40000 0x0 0x2000>,
-		      <0x0 0x4ac60000 0x0 0x2000>;
+		      <0x0 0x4ac20000 0x0 0x20000>,
+		      <0x0 0x4ac40000 0x0 0x20000>,
+		      <0x0 0x4ac60000 0x0 0x20000>;
 	};
 
 	psci {
diff --git a/arch/arm64/boot/dts/st/stm32mp257f-dk.dts b/arch/arm64/boot/dts/st/stm32mp257f-dk.dts
new file mode 100644
index 000000000000..a278a1e3ce03
--- /dev/null
+++ b/arch/arm64/boot/dts/st/stm32mp257f-dk.dts
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (C) STMicroelectronics 2025 - All Rights Reserved
+ * Author: Alexandre Torgue <alexandre.torgue@foss.st.com> for STMicroelectronics.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include "stm32mp257.dtsi"
+#include "stm32mp25xf.dtsi"
+#include "stm32mp25-pinctrl.dtsi"
+#include "stm32mp25xxak-pinctrl.dtsi"
+
+/ {
+	model = "STMicroelectronics STM32MP257F-DK Discovery Board";
+	compatible = "st,stm32mp257f-dk", "st,stm32mp257";
+
+	aliases {
+		serial0 = &usart2;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		button-user-1 {
+			label = "User-1";
+			linux,code = <BTN_1>;
+			gpios = <&gpioc 5 GPIO_ACTIVE_HIGH>;
+		};
+
+		button-user-2 {
+			label = "User-2";
+			linux,code = <BTN_2>;
+			gpios = <&gpioc 11 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led-blue {
+			function = LED_FUNCTION_HEARTBEAT;
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&gpioh 7 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+			default-state = "off";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x0 0x80000000 0x1 0x0>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		fw@80000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x0 0x80000000 0x0 0x4000000>;
+			no-map;
+		};
+	};
+};
+
+&arm_wdt {
+	timeout-sec = <32>;
+	status = "okay";
+};
+
+&scmi_regu {
+	scmi_vddio1: regulator@0 {
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+	};
+	scmi_vdd_sdcard: regulator@23 {
+		reg = <VOLTD_SCMI_STPMIC2_LDO7>;
+		regulator-name = "vdd_sdcard";
+	};
+};
+
+&sdmmc1 {
+	pinctrl-names = "default", "opendrain", "sleep";
+	pinctrl-0 = <&sdmmc1_b4_pins_a>;
+	pinctrl-1 = <&sdmmc1_b4_od_pins_a>;
+	pinctrl-2 = <&sdmmc1_b4_sleep_pins_a>;
+	cd-gpios = <&gpiod 3 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>;
+	disable-wp;
+	st,neg-edge;
+	bus-width = <4>;
+	vmmc-supply = <&scmi_vdd_sdcard>;
+	vqmmc-supply = <&scmi_vddio1>;
+	status = "okay";
+};
+
+&usart2 {
+	pinctrl-names = "default", "idle", "sleep";
+	pinctrl-0 = <&usart2_pins_a>;
+	pinctrl-1 = <&usart2_idle_pins_a>;
+	pinctrl-2 = <&usart2_sleep_pins_a>;
+	/delete-property/dmas;
+	/delete-property/dma-names;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/tesla/fsd.dtsi b/arch/arm64/boot/dts/tesla/fsd.dtsi
index 690b4ed9c29b..9951eef9507c 100644
--- a/arch/arm64/boot/dts/tesla/fsd.dtsi
+++ b/arch/arm64/boot/dts/tesla/fsd.dtsi
@@ -92,7 +92,7 @@
 				reg = <0x0 0x000>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -108,7 +108,7 @@
 				reg = <0x0 0x001>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -124,7 +124,7 @@
 				reg = <0x0 0x002>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -139,7 +139,7 @@
 				compatible = "arm,cortex-a72";
 				reg = <0x0 0x003>;
 				enable-method = "psci";
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -156,7 +156,7 @@
 				reg = <0x0 0x100>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -172,7 +172,7 @@
 				reg = <0x0 0x101>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -188,7 +188,7 @@
 				reg = <0x0 0x102>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -204,7 +204,7 @@
 				reg = <0x0 0x103>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -221,7 +221,7 @@
 				reg = <0x0 0x200>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -237,7 +237,7 @@
 				reg = <0x0 0x201>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -253,7 +253,7 @@
 				reg = <0x0 0x202>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -269,7 +269,7 @@
 				reg = <0x0 0x203>;
 				enable-method = "psci";
 				clock-frequency = <2400000000>;
-				cpu-idle-states = <&CPU_SLEEP>;
+				cpu-idle-states = <&cpu_sleep>;
 				i-cache-size = <0xc000>;
 				i-cache-line-size = <64>;
 				i-cache-sets = <256>;
@@ -291,7 +291,7 @@
 		idle-states {
 			entry-method = "psci";
 
-			CPU_SLEEP: cpu-sleep {
+			cpu_sleep: cpu-sleep {
 				idle-state-name = "c2";
 				compatible = "arm,idle-state";
 				local-timer-stop;
diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile
index 8a4bdf87e2d4..03d4cecfc001 100644
--- a/arch/arm64/boot/dts/ti/Makefile
+++ b/arch/arm64/boot/dts/ti/Makefile
@@ -54,6 +54,7 @@ dtb-$(CONFIG_ARCH_K3) += k3-am642-evm-nand.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-rdk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-gpio-fan.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-pcie-usb2.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am642-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-tqma64xxl-mbax4xxl.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
@@ -185,6 +186,8 @@ k3-am642-phyboard-electra-gpio-fan-dtbs := \
 	k3-am642-phyboard-electra-rdk.dtb k3-am642-phyboard-electra-gpio-fan.dtbo
 k3-am642-phyboard-electra-pcie-usb2-dtbs := \
 	k3-am642-phyboard-electra-rdk.dtb k3-am642-phyboard-electra-pcie-usb2.dtbo
+k3-am642-phyboard-electra-x27-gpio1-spi1-uart3-dtbs := \
+	k3-am642-phyboard-electra-rdk.dtb k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtbo
 k3-am642-tqma64xxl-mbax4xxl-sdcard-dtbs := \
 	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
 k3-am642-tqma64xxl-mbax4xxl-wlan-dtbs := \
diff --git a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
index 2ef4cbaec789..55ed418c023b 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
@@ -29,6 +29,7 @@
 	memory@80000000 {
 		device_type = "memory";
 		reg = <0x00000000 0x80000000 0x00000000 0x80000000>;
+		bootph-all;
 	};
 
 	reserved_memory: reserved-memory {
@@ -36,15 +37,21 @@
 		#size-cells = <2>;
 		ranges;
 
-		ramoops@9ca00000 {
+		ramoops@9c700000 {
 			compatible = "ramoops";
-			reg = <0x00 0x9ca00000 0x00 0x00100000>;
+			reg = <0x00 0x9c700000 0x00 0x00100000>;
 			record-size = <0x8000>;
 			console-size = <0x8000>;
 			ftrace-size = <0x00>;
 			pmsg-size = <0x8000>;
 		};
 
+		rtos_ipc_memory_region: ipc-memories@9c800000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0x9c800000 0x00 0x00300000>;
+			no-map;
+		};
+
 		mcu_m4fss_dma_memory_region: m4f-dma-memory@9cb00000 {
 			compatible = "shared-dma-pool";
 			reg = <0x00 0x9cb00000 0x00 0x100000>;
@@ -131,6 +138,7 @@
 			AM62X_IOPAD(0x1e0, PIN_INPUT_PULLUP, 0) /* (B16) I2C0_SCL */
 			AM62X_IOPAD(0x1e4, PIN_INPUT_PULLUP, 0) /* (A16) I2C0_SDA */
 		>;
+		bootph-all;
 	};
 
 	main_mdio1_pins_default: main-mdio1-default-pins {
@@ -138,6 +146,7 @@
 			AM62X_IOPAD(0x160, PIN_OUTPUT, 0) /* (AD24) MDIO0_MDC */
 			AM62X_IOPAD(0x15c, PIN_INPUT, 0) /* (AB22) MDIO0_MDIO */
 		>;
+		bootph-all;
 	};
 
 	main_mmc0_pins_default: main-mmc0-default-pins {
@@ -153,6 +162,7 @@
 			AM62X_IOPAD(0x1fc, PIN_INPUT_PULLUP, 0) /* (AD2) MMC0_DAT6 */
 			AM62X_IOPAD(0x1f8, PIN_INPUT_PULLUP, 0) /* (AC2) MMC0_DAT7 */
 		>;
+		bootph-all;
 	};
 
 	main_rgmii1_pins_default: main-rgmii1-default-pins {
@@ -170,6 +180,7 @@
 			AM62X_IOPAD(0x130, PIN_OUTPUT, 0) /* (AE19) RGMII1_TXC */
 			AM62X_IOPAD(0x12c, PIN_OUTPUT, 0) /* (AD19) RGMII1_TX_CTL */
 		>;
+		bootph-all;
 	};
 
 	ospi0_pins_default: ospi0-default-pins {
@@ -186,6 +197,7 @@
 			AM62X_IOPAD(0x028, PIN_INPUT, 0) /* (J22) OSPI0_D7 */
 			AM62X_IOPAD(0x008, PIN_INPUT, 0) /* (J24) OSPI0_DQS */
 		>;
+		bootph-all;
 	};
 
 	pmic_irq_pins_default: pmic-irq-default-pins {
@@ -210,6 +222,7 @@
 &cpsw_port1 {
 	phy-mode = "rgmii-rxid";
 	phy-handle = <&cpsw3g_phy1>;
+	bootph-all;
 };
 
 &cpsw3g_mdio {
@@ -220,6 +233,7 @@
 	cpsw3g_phy1: ethernet-phy@1 {
 		compatible = "ethernet-phy-id2000.a231", "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
+		bootph-all;
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
 		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 	};
@@ -232,10 +246,15 @@
 	};
 };
 
+&main_pktdma {
+	bootph-all;
+};
+
 &main_i2c0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_i2c0_pins_default>;
 	clock-frequency = <400000>;
+	bootph-all;
 	status = "okay";
 
 	pmic@30 {
@@ -355,6 +374,7 @@
 		cdns,tchsh-ns = <60>;
 		cdns,tslch-ns = <60>;
 		cdns,read-delay = <0>;
+		bootph-all;
 	};
 };
 
@@ -363,5 +383,6 @@
 	pinctrl-0 = <&main_mmc0_pins_default>;
 	disable-wp;
 	non-removable;
+	bootph-all;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
index 9202181fbd65..fcc4cb2e9389 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
@@ -28,10 +28,10 @@
 			"Headphone Jack", "HPOUTR",
 			"IN2L", "Line In Jack",
 			"IN2R", "Line In Jack",
-			"Headphone Jack", "MICBIAS",
-			"IN1L", "Headphone Jack";
+			"Microphone Jack", "MICBIAS",
+			"IN1L", "Microphone Jack";
 		simple-audio-card,widgets =
-			"Microphone", "Headphone Jack",
+			"Microphone", "Microphone Jack",
 			"Headphone", "Headphone Jack",
 			"Line", "Line In Jack";
 
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
index 75c80290b12a..a5469f2712f0 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
@@ -65,6 +65,14 @@
 			pmsg-size = <0x8000>;
 		};
 
+		/* global cma region */
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x00 0x8000000>;
+			linux,cma-default;
+		};
+
 		secure_tfa_ddr: tfa@9e780000 {
 			reg = <0x00 0x9e780000 0x00 0x80000>;
 			no-map;
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
index 0469c766b769..9ed9d703ff24 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
@@ -12,7 +12,6 @@
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
 		pinctrl-single,function-mask = <0xffffffff>;
-		status = "disabled";
 	};
 
 	mcu_esm: esm@4100000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-phycore-som.dtsi
index a5aceaa39670..147d56b87984 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-phycore-som.dtsi
@@ -42,6 +42,7 @@
 		device_type = "memory";
 		/* 2G RAM */
 		reg = <0x00000000 0x80000000 0x00000000 0x80000000>;
+		bootph-all;
 	};
 
 	reserved-memory {
@@ -99,6 +100,7 @@
 			AM62AX_IOPAD(0x1e0, PIN_INPUT_PULLUP, 0) /* (D17) I2C0_SCL */
 			AM62AX_IOPAD(0x1e4, PIN_INPUT_PULLUP, 0) /* (E16) I2C0_SDA */
 		>;
+		bootph-all;
 	};
 
 	main_mdio1_pins_default: main-mdio1-default-pins {
@@ -106,6 +108,7 @@
 			AM62AX_IOPAD(0x160, PIN_OUTPUT, 0) /* (V12) MDIO0_MDC */
 			AM62AX_IOPAD(0x15c, PIN_INPUT, 0) /* (V13) MDIO0_MDIO */
 		>;
+		bootph-all;
 	};
 
 	main_mmc0_pins_default: main-mmc0-default-pins {
@@ -121,6 +124,7 @@
 			AM62AX_IOPAD(0x1fc, PIN_INPUT_PULLUP, 0) /* (W9) MMC0_DAT6 */
 			AM62AX_IOPAD(0x1f8, PIN_INPUT_PULLUP, 0) /* (AB8) MMC0_DAT7 */
 		>;
+		bootph-all;
 	};
 
 	main_rgmii1_pins_default: main-rgmii1-default-pins {
@@ -138,6 +142,7 @@
 			AM62AX_IOPAD(0x130, PIN_OUTPUT, 0) /* (AB17) RGMII1_TXC */
 			AM62AX_IOPAD(0x12c, PIN_OUTPUT, 0) /* (W16) RGMII1_TX_CTL */
 		>;
+		bootph-all;
 	};
 
 	ospi0_pins_default: ospi0-default-pins {
@@ -155,6 +160,7 @@
 			AM62AX_IOPAD(0x028, PIN_INPUT, 0) /* (J22) OSPI0_D7 */
 			AM62AX_IOPAD(0x008, PIN_INPUT, 0) /* (L21) OSPI0_DQS */
 		>;
+		bootph-all;
 	};
 
 	pmic_irq_pins_default: pmic-irq-default-pins {
@@ -165,14 +171,15 @@
 };
 
 &cpsw3g {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_rgmii1_pins_default>;
+	status = "okay";
 };
 
 &cpsw_port1 {
 	phy-mode = "rgmii-rxid";
 	phy-handle = <&cpsw3g_phy1>;
+	bootph-all;
 };
 
 &cpsw3g_mdio {
@@ -182,6 +189,7 @@
 	cpsw3g_phy1: ethernet-phy@1 {
 		compatible = "ethernet-phy-id2000.a231", "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
+		bootph-all;
 		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
 		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
@@ -196,6 +204,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_i2c0_pins_default>;
 	clock-frequency = <400000>;
+	bootph-all;
 	status = "okay";
 
 	pmic@30 {
@@ -215,8 +224,8 @@
 		interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		ti,power-button;
 		system-power-controller;
+		ti,power-button;
 
 		regulators {
 			vdd_3v3: buck1 {
@@ -302,6 +311,10 @@
 	status = "okay";
 };
 
+&main_pktdma {
+	bootph-all;
+};
+
 &ospi0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ospi0_pins_default>;
@@ -318,6 +331,7 @@
 		cdns,tchsh-ns = <60>;
 		cdns,tslch-ns = <60>;
 		cdns,read-delay = <0>;
+		bootph-all;
 	};
 };
 
@@ -326,5 +340,6 @@
 	pinctrl-0 = <&main_mmc0_pins_default>;
 	disable-wp;
 	non-removable;
+	bootph-all;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
index a6f0d87a50d8..1c9d95696c83 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
@@ -18,10 +18,13 @@
 
 	aliases {
 		serial0 = &wkup_uart0;
+		serial1 = &mcu_uart0;
 		serial2 = &main_uart0;
 		serial3 = &main_uart1;
 		mmc0 = &sdhci0;
 		mmc1 = &sdhci1;
+		rtc0 = &wkup_rtc0;
+		rtc1 = &tps659312;
 	};
 
 	chosen {
@@ -655,6 +658,7 @@
 };
 
 &usb0 {
+	bootph-all;
 	usb-role-switch;
 
 	port {
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-mcu.dtsi
index b33aff0d65c9..bd6a00d13aea 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-mcu.dtsi
@@ -12,15 +12,7 @@
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
 		pinctrl-single,function-mask = <0xffffffff>;
-		pinctrl-single,gpio-range =
-			<&mcu_pmx_range 0 21 PIN_GPIO_RANGE_IOPAD>,
-			<&mcu_pmx_range 23 1 PIN_GPIO_RANGE_IOPAD>,
-			<&mcu_pmx_range 32 2 PIN_GPIO_RANGE_IOPAD>;
 		bootph-all;
-
-		mcu_pmx_range: gpio-range {
-			#pinctrl-single,gpio-range-cells = <3>;
-		};
 	};
 
 	mcu_esm: esm@4100000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-wakeup.dtsi
index 6f32135f00a5..6757b37a9de3 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-wakeup.dtsi
@@ -2,9 +2,11 @@
 /*
  * Device Tree file for the WAKEUP domain peripherals shared by AM62P and J722S
  *
- * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2025 Texas Instruments Incorporated - https://www.ti.com/
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
+
 &cbass_wakeup {
 	wkup_conf: bus@43000000 {
 		compatible = "simple-bus";
@@ -41,14 +43,34 @@
 		};
 	};
 
-	wkup_uart0: serial@2b300000 {
-		compatible = "ti,am64-uart", "ti,am654-uart";
-		reg = <0x00 0x2b300000 0x00 0x100>;
-		interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+	target-module@2b300050 {
+		compatible = "ti,sysc-omap2", "ti,sysc";
+		reg = <0 0x2b300050 0 0x4>,
+		      <0 0x2b300054 0 0x4>,
+		      <0 0x2b300058 0 0x4>;
+		reg-names = "rev", "sysc", "syss";
+		ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP |
+				 SYSC_OMAP2_SOFTRESET |
+				 SYSC_OMAP2_AUTOIDLE)>;
+		ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+				<SYSC_IDLE_NO>,
+				<SYSC_IDLE_SMART>,
+				<SYSC_IDLE_SMART_WKUP>;
+		ti,syss-mask = <1>;
+		ti,no-reset-on-init;
 		power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 114 0>;
-		clock-names = "fclk";
-		status = "disabled";
+		clock-names = "fck";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0 0x2b300000 0x100000>;
+
+		wkup_uart0: serial@0 {
+			compatible = "ti,am64-uart", "ti,am654-uart";
+			reg = <0 0x100>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
 	};
 
 	wkup_i2c0: i2c@2b200000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
index 420c77c8e9e5..6aea9d3f134e 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
@@ -42,17 +42,23 @@
 	ti,interrupt-ranges = <5 69 35>;
 };
 
-&main_pmx0 {
-	pinctrl-single,gpio-range =
-		<&main_pmx0_range 0 32 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 33 38 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 72 22 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 137 5 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 143 3 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 149 2 PIN_GPIO_RANGE_IOPAD>;
+&main_conf {
+	audio_refclk0: clock-controller@82e0 {
+		compatible = "ti,am62-audio-refclk";
+		reg = <0x82e0 0x4>;
+		clocks = <&k3_clks 157 0>;
+		assigned-clocks = <&k3_clks 157 0>;
+		assigned-clock-parents = <&k3_clks 157 16>;
+		#clock-cells = <0>;
+	};
 
-	main_pmx0_range: gpio-range {
-		#pinctrl-single,gpio-range-cells = <3>;
+	audio_refclk1: clock-controller@82e4 {
+		compatible = "ti,am62-audio-refclk";
+		reg = <0x82e4 0x4>;
+		clocks = <&k3_clks 157 18>;
+		assigned-clocks = <&k3_clks 157 18>;
+		assigned-clock-parents = <&k3_clks 157 34>;
+		#clock-cells = <0>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
index ad71d2f27f53..d29f524600af 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
@@ -19,6 +19,7 @@
 
 	aliases {
 		serial0 = &wkup_uart0;
+		serial1 = &mcu_uart0;
 		serial2 = &main_uart0;
 		serial3 = &main_uart1;
 		mmc0 = &sdhci0;
@@ -310,7 +311,7 @@
 
 	main_usb1_pins_default: main-usb1-default-pins {
 		pinctrl-single,pins = <
-			AM62PX_IOPAD(0x0258, PIN_INPUT, 0) /* (G21) USB1_DRVVBUS */
+			AM62PX_IOPAD(0x0258, PIN_INPUT | PIN_DS_PULLUD_ENABLE | PIN_DS_PULL_UP, 0) /* (G21) USB1_DRVVBUS */
 		>;
 	};
 
@@ -519,6 +520,7 @@
 };
 
 &usb0 {
+	bootph-all;
 	usb-role-switch;
 
 	port {
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi
index 922cad14c9f8..aab74d6019b0 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra.dtsi
@@ -138,6 +138,7 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 		regulator-boot-on;
+		bootph-all;
 	};
 
 	vcc_3v3_sw: regulator-vcc-3v3-sw {
@@ -233,6 +234,7 @@
 			AM62X_IOPAD(0x224, PIN_INPUT_PULLUP, 0) /* (D22) MMC1_DAT3 */
 			AM62X_IOPAD(0x240, PIN_INPUT_PULLUP, 0) /* (D17) MMC1_SDCD */
 		>;
+		bootph-all;
 	};
 
 	main_rgmii2_pins_default: main-rgmii2-default-pins {
@@ -257,6 +259,7 @@
 			AM62X_IOPAD(0x1c8, PIN_INPUT, 0) /* (D14) UART0_RXD */
 			AM62X_IOPAD(0x1cc, PIN_OUTPUT, 0) /* (E14) UART0_TXD */
 		>;
+		bootph-all;
 	};
 
 	main_uart1_pins_default: main-uart1-default-pins {
@@ -266,6 +269,7 @@
 			AM62X_IOPAD(0x1ac, PIN_INPUT, 2) /* (E19) MCASP0_AFSR.UART1_RXD */
 			AM62X_IOPAD(0x1b0, PIN_OUTPUT, 2) /* (A20) MCASP0_ACLKR.UART1_TXD */
 		>;
+		bootph-pre-ram;
 	};
 
 	main_usb1_pins_default: main-usb1-default-pins {
@@ -430,12 +434,14 @@
 &main_uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_uart0_pins_default>;
+	bootph-all;
 	status = "okay";
 };
 
 &main_uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_uart1_pins_default>;
+	bootph-pre-ram;
 	/* Main UART1 may be used by TIFS firmware */
 	status = "okay";
 };
@@ -467,11 +473,13 @@
 	pinctrl-0 = <&main_mmc1_pins_default>;
 	disable-wp;
 	no-1-8-v;
+	bootph-all;
 	status = "okay";
 };
 
 &usbss0 {
 	ti,vbus-divider;
+	bootph-all;
 	status = "okay";
 };
 
@@ -482,6 +490,7 @@
 
 &usb0 {
 	usb-role-switch;
+	bootph-all;
 
 	port {
 		typec_hs: endpoint {
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
index 2f129e8cd5b9..d52cb2a5a589 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
@@ -12,6 +12,8 @@
 
 / {
 	aliases {
+		serial0 = &wkup_uart0;
+		serial1 = &mcu_uart0;
 		serial2 = &main_uart0;
 		mmc0 = &sdhci0;
 		mmc1 = &sdhci1;
diff --git a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
index 99a6fdfaa7fb..d9d491b12c33 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
@@ -27,6 +27,7 @@
 	memory@80000000 {
 		device_type = "memory";
 		reg = <0x00000000 0x80000000 0x00000000 0x80000000>;
+		bootph-all;
 	};
 
 	reserved_memory: reserved-memory {
@@ -99,6 +100,12 @@
 			reg = <0x00 0xa4100000 0x00 0xf00000>;
 			no-map;
 		};
+
+		rtos_ipc_memory_region: ipc-memories@a5000000 {
+			reg = <0x00 0xa5000000 0x00 0x00800000>;
+			alignment = <0x1000>;
+			no-map;
+		};
 	};
 
 	leds {
@@ -132,6 +139,7 @@
 			AM64X_IOPAD(0x01fc, PIN_OUTPUT, 4)	/* (R2) PRG0_PRU1_GPO19.MDIO0_MDC */
 			AM64X_IOPAD(0x0100, PIN_OUTPUT, 7)	/* (V7) PRG1_PRU0_GPO18.GPIO0_63 */
 		>;
+		bootph-all;
 	};
 
 	cpsw_rgmii1_pins_default: cpsw-rgmii1-default-pins {
@@ -150,6 +158,7 @@
 			AM64X_IOPAD(0x014c, PIN_OUTPUT, 4)	/* (AA14) PRG1_PRU1_GPO17.RGMII1_TD3 */
 			AM64X_IOPAD(0x0154, PIN_INPUT, 7)	/* (V12) PRG1_PRU1_GPO19.GPIO0_84 */
 		>;
+		bootph-all;
 	};
 
 	eeprom_wp_pins_default: eeprom-wp-default-pins {
@@ -169,6 +178,7 @@
 			AM64X_IOPAD(0x0260, PIN_INPUT, 0)	/* (A18) I2C0_SCL */
 			AM64X_IOPAD(0x0264, PIN_INPUT, 0)	/* (B18) I2C0_SDA */
 		>;
+		bootph-all;
 	};
 
 	ospi0_pins_default: ospi0-default-pins {
@@ -185,6 +195,7 @@
 			AM64X_IOPAD(0x0028, PIN_INPUT, 0)	/* (M17) OSPI0_D7 */
 			AM64X_IOPAD(0x002c, PIN_OUTPUT, 0)	/* (L19) OSPI0_CSn0 */
 		>;
+		bootph-all;
 	};
 
 	rtc_pins_default: rtc-defaults-pins {
@@ -201,26 +212,29 @@
 };
 
 &cpsw3g_mdio {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&cpsw_mdio_pins_default>;
+	bootph-all;
+	status = "okay";
 
 	cpsw3g_phy1: ethernet-phy@1 {
 		compatible = "ethernet-phy-id2000.a231", "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
 		interrupt-parent = <&main_gpio0>;
 		interrupts = <84 IRQ_TYPE_EDGE_FALLING>;
-		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
-		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 		reset-gpios = <&main_gpio0 63 GPIO_ACTIVE_LOW>;
 		reset-assert-us = <1000>;
 		reset-deassert-us = <1000>;
+		bootph-all;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
+		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 	};
 };
 
 &cpsw_port1 {
 	phy-mode = "rgmii-rxid";
 	phy-handle = <&cpsw3g_phy1>;
+	bootph-all;
 	status = "okay";
 };
 
@@ -262,10 +276,11 @@
 };
 
 &main_i2c0 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_i2c0_pins_default>;
 	clock-frequency = <400000>;
+	bootph-all;
+	status = "okay";
 
 	eeprom@50 {
 		compatible = "atmel,24c32";
@@ -330,6 +345,10 @@
 	};
 };
 
+&main_pktdma {
+	bootph-all;
+};
+
 &main_r5fss0_core0 {
 	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
@@ -362,9 +381,9 @@
 };
 
 &ospi0 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&ospi0_pins_default>;
+	status = "okay";
 
 	serial_flash: flash@0 {
 		compatible = "jedec,spi-nor";
@@ -377,15 +396,17 @@
 		cdns,tchsh-ns = <60>;
 		cdns,tslch-ns = <60>;
 		cdns,read-delay = <0>;
+		bootph-all;
 	};
 };
 
 &sdhci0 {
-	status = "okay";
 	non-removable;
 	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	keep-power-in-suspend;
+	bootph-all;
+	status = "okay";
 };
 
 &tscadc0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
index bc8e1ce11047..f63c101b7d61 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
@@ -171,6 +171,7 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-boot-on;
 		regulator-always-on;
+		bootph-all;
 	};
 };
 
@@ -275,6 +276,7 @@
 			AM64X_IOPAD(0x0294, PIN_INPUT_PULLUP, 0)	/* (J19) MMC1_CMD */
 			AM64X_IOPAD(0x0298, PIN_INPUT_PULLUP, 0)	/* (D19) MMC1_SDCD */
 		>;
+		bootph-all;
 	};
 
 	main_spi0_pins_default: main-spi0-default-pins {
@@ -291,6 +293,7 @@
 			AM64X_IOPAD(0x0230, PIN_INPUT, 0)	/* (D15) UART0_RXD */
 			AM64X_IOPAD(0x0234, PIN_OUTPUT, 0)	/* (C16) UART0_TXD */
 		>;
+		bootph-all;
 	};
 
 	main_uart1_pins_default: main-uart1-default-pins {
@@ -349,10 +352,10 @@
 };
 
 &main_i2c1 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_i2c1_pins_default>;
 	clock-frequency = <400000>;
+	status = "okay";
 
 	eeprom@51 {
 		compatible = "atmel,24c02";
@@ -382,25 +385,25 @@
 };
 
 &main_mcan0 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mcan0_pins_default>;
 	phys = <&can_tc1>;
+	status = "okay";
 };
 
 &main_mcan1 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mcan1_pins_default>;
 	phys = <&can_tc2>;
+	status = "okay";
 };
 
 &main_spi0 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_spi0_pins_default>;
 	cs-gpios = <0>, <&main_gpio1 43 GPIO_ACTIVE_LOW>;
 	ti,pindir-d0-out-d1-in;
+	status = "okay";
 
 	tpm@1 {
 		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
@@ -410,25 +413,27 @@
 };
 
 &main_uart0 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_uart0_pins_default>;
+	bootph-all;
+	status = "okay";
 };
 
 &main_uart1 {
-	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_uart1_pins_default>;
 	uart-has-rtscts;
+	status = "okay";
 };
 
 &sdhci1 {
-	status = "okay";
 	vmmc-supply = <&vcc_3v3_mmc>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
 	disable-wp;
 	no-1-8-v;
+	bootph-all;
+	status = "okay";
 };
 
 &serdes0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso
new file mode 100644
index 000000000000..996c42ec4253
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2025 PHYTEC Messtechnik GmbH
+ * Authors:
+ *   Wadim Egorov <w.egorov@phytec.de>
+ *   Daniel Schultz <d.schultz@phytec.de>
+ *
+ * GPIO, SPI and UART examples for the X27 expansion connector.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include "k3-pinctrl.h"
+
+&{/} {
+	aliases {
+		serial5 = "/bus@f4000/serial@2830000";
+	};
+};
+
+&main_pmx0 {
+	main_gpio1_exp_header_gpio_pins_default: main-gpio1-exp-header-gpio-pins-default {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0220, PIN_INPUT, 7)	/* (D14) SPI1_CS1.GPIO1_48 */
+		>;
+	};
+
+	main_spi1_pins_default: main-spi1-pins-default {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0224, PIN_INPUT, 0)	/* (C14) SPI1_CLK */
+			AM64X_IOPAD(0x021C, PIN_OUTPUT, 0)	/* (B14) SPI1_CS0 */
+			AM64X_IOPAD(0x0228, PIN_OUTPUT, 0)	/* (B15) SPI1_D0 */
+			AM64X_IOPAD(0x022C, PIN_INPUT, 0)	/* (A15) SPI1_D1 */
+		>;
+	};
+
+	main_uart3_pins_default: main-uart3-pins-default {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0048, PIN_INPUT, 2)       /* (U20) GPMC0_AD3.UART3_RXD */
+			AM64X_IOPAD(0x004c, PIN_OUTPUT, 2)      /* (U18) GPMC0_AD4.UART3_TXD */
+		>;
+	};
+};
+
+&main_gpio1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_gpio1_exp_header_gpio_pins_default>;
+	status = "okay";
+};
+
+&main_spi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_spi1_pins_default>;
+	ti,pindir-d0-out-d1-in = <1>;
+	status = "okay";
+};
+
+&main_uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_uart3_pins_default>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
index 4c1e02a4e7a2..4421852161dd 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
@@ -540,6 +540,7 @@
 		#phy-cells = <0>;
 		cdns,phy-type = <PHY_TYPE_USB3>;
 		resets = <&serdes_wiz3 1>, <&serdes_wiz3 2>;
+		bootph-all;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
index 69b3d1ed8a21..440ef57be294 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
@@ -1040,6 +1040,7 @@
 		#phy-cells = <0>;
 		cdns,phy-type = <PHY_TYPE_USB3>;
 		resets = <&serdes_wiz3 1>, <&serdes_wiz3 2>;
+		bootph-all;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
index b3a0385ed3d8..54fc5c4f8c3f 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
@@ -448,6 +448,47 @@
 		cdns,tchsh-ns = <60>;
 		cdns,tslch-ns = <60>;
 		cdns,read-delay = <4>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "ospi.tiboot3";
+				reg = <0x0 0x80000>;
+			};
+
+			partition@80000 {
+				label = "ospi.tispl";
+				reg = <0x80000 0x200000>;
+			};
+
+			partition@280000 {
+				label = "ospi.u-boot";
+				reg = <0x280000 0x400000>;
+			};
+
+			partition@680000 {
+				label = "ospi.env";
+				reg = <0x680000 0x40000>;
+			};
+
+			partition@6c0000 {
+				label = "ospi.env.backup";
+				reg = <0x6c0000 0x40000>;
+			};
+
+			partition@800000 {
+				label = "ospi.rootfs";
+				reg = <0x800000 0x37c0000>;
+			};
+
+			partition@3fc0000 {
+				label = "ospi.phypattern";
+				reg = <0x3fc0000 0x40000>;
+			};
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
index d184e9c1a0a5..2127316f36a3 100644
--- a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
@@ -263,6 +263,13 @@
 		bootph-all;
 	};
 
+	main_i2c2_pins_default: main-i2c2-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x00b0, PIN_INPUT_PULLUP, 1) /* (P22) GPMC0_CSn2.I2C2_SCL */
+			J722S_IOPAD(0x00b4, PIN_INPUT_PULLUP, 1) /* (P23) GPMC0_CSn3.I2C2_SDA */
+		>;
+	};
+
 	main_uart0_pins_default: main-uart0-default-pins {
 		pinctrl-single,pins = <
 			J722S_IOPAD(0x01c8, PIN_INPUT, 0)	/* (A22) UART0_RXD */
@@ -590,7 +597,7 @@
 		p05-hog {
 			/* P05 - USB2.0_MUX_SEL */
 			gpio-hog;
-			gpios = <5 GPIO_ACTIVE_HIGH>;
+			gpios = <5 GPIO_ACTIVE_LOW>;
 			output-high;
 		};
 
@@ -631,6 +638,27 @@
 	};
 };
 
+&main_i2c2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c2_pins_default>;
+	clock-frequency = <400000>;
+
+	pca9543_0: i2c-mux@70 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x70>;
+	};
+
+	pca9543_1: i2c-mux@71 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x71>;
+	};
+};
+
 &ospi0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ospi0_pins_default>;
diff --git a/arch/arm64/boot/dts/ti/k3-j722s-main.dtsi b/arch/arm64/boot/dts/ti/k3-j722s-main.dtsi
index 3ac2d45a0558..6850f50530f1 100644
--- a/arch/arm64/boot/dts/ti/k3-j722s-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j722s-main.dtsi
@@ -154,6 +154,189 @@
 		};
 	};
 
+	ti_csi2rx1: ticsi2rx@30122000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x30122000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x5100 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 247 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx1: csi-bridge@30121000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30121000 0x00 0x1000>;
+			clocks = <&k3_clks 247 0>, <&k3_clks 247 3>, <&k3_clks 247 0>,
+				 <&k3_clks 247 0>, <&k3_clks 247 4>, <&k3_clks 247 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				      "pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy1>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi1_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi1_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi1_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi1_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi1_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx2: ticsi2rx@30142000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x30142000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		power-domains = <&k3_pds 248 TI_SCI_PD_EXCLUSIVE>;
+		dmas = <&main_bcdma_csi 0 0x5200 0>;
+		dma-names = "rx0";
+		status = "disabled";
+
+		cdns_csi2rx2: csi-bridge@30141000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30141000 0x00 0x1000>;
+			clocks = <&k3_clks 248 0>, <&k3_clks 248 3>, <&k3_clks 248 0>,
+				 <&k3_clks 248 0>, <&k3_clks 248 4>, <&k3_clks 248 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				      "pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy2>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi2_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi2_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi2_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi2_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi2_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx3: ticsi2rx@30162000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x30162000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x5300 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 249 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx3: csi-bridge@30161000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30161000 0x00 0x1000>;
+			clocks = <&k3_clks 249 0>, <&k3_clks 249 3>, <&k3_clks 249 0>,
+				 <&k3_clks 249 0>, <&k3_clks 249 4>, <&k3_clks 249 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				      "pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy3>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi3_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi3_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi3_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi3_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi3_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy1: phy@30130000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30130000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 251 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy2: phy@30150000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30150000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 252 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy3: phy@30170000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30170000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 253 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
 	main_r5fss0: r5fss@78400000 {
 		compatible = "ti,am62-r5fss";
 		#address-cells = <1>;
@@ -204,6 +387,16 @@
 	};
 };
 
+&main_bcdma_csi {
+	compatible = "ti,j722s-dmss-bcdma-csi";
+	reg = <0x00 0x4e230000 0x00 0x100>,
+	      <0x00 0x4e180000 0x00 0x20000>,
+	      <0x00 0x4e300000 0x00 0x10000>,
+	      <0x00 0x4e100000 0x00 0x80000>;
+	reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+	ti,sci-rm-range-tchan = <0x22>;
+};
+
 /* MCU domain overrides */
 
 &mcu_r5fss0_core0 {
@@ -251,21 +444,6 @@
 	ti,interrupt-ranges = <7 71 21>;
 };
 
-&main_pmx0 {
-	pinctrl-single,gpio-range =
-		<&main_pmx0_range 0 32 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 33 38 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 72 17 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 101 25 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 137 5 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 143 3 PIN_GPIO_RANGE_IOPAD>,
-		<&main_pmx0_range 149 2 PIN_GPIO_RANGE_IOPAD>;
-
-	main_pmx0_range: gpio-range {
-		#pinctrl-single,gpio-range-cells = <3>;
-	};
-};
-
 &main_gpio0 {
 	gpio-ranges = <&main_pmx0 0 0 32>, <&main_pmx0 32 33 38>,
 			<&main_pmx0 70 72 17>;
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-evm-quad-port-eth-exp1.dtso b/arch/arm64/boot/dts/ti/k3-j784s4-evm-quad-port-eth-exp1.dtso
index dcd2c7c39ec3..c1f9573557d0 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-evm-quad-port-eth-exp1.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-evm-quad-port-eth-exp1.dtso
@@ -102,13 +102,6 @@
 		gpios = <16 GPIO_ACTIVE_HIGH>;
 		output-low;
 	};
-
-	/* Toggle MUX2 for MDIO lines */
-	mux-sel-hog {
-		gpio-hog;
-		gpios = <13 GPIO_ACTIVE_HIGH>, <14 GPIO_ACTIVE_HIGH>, <15 GPIO_ACTIVE_HIGH>;
-		output-high;
-	};
 };
 
 &main_pmx0 {
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi
index 83bbf94b58d1..1944616ab357 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi
@@ -84,7 +84,9 @@
 					<0x10 0x3>, <0x14 0x3>, /* SERDES1 lane0/1 select */
 					<0x18 0x3>, <0x1c 0x3>, /* SERDES1 lane2/3 select */
 					<0x20 0x3>, <0x24 0x3>, /* SERDES2 lane0/1 select */
-					<0x28 0x3>, <0x2c 0x3>; /* SERDES2 lane2/3 select */
+					<0x28 0x3>, <0x2c 0x3>, /* SERDES2 lane2/3 select */
+					<0x40 0x3>, <0x44 0x3>, /* SERDES4 lane0/1 select */
+					<0x48 0x3>, <0x4c 0x3>; /* SERDES4 lane2/3 select */
 			idle-states = <J784S4_SERDES0_LANE0_PCIE1_LANE0>,
 				      <J784S4_SERDES0_LANE1_PCIE1_LANE1>,
 				      <J784S4_SERDES0_LANE2_IP3_UNUSED>,
@@ -193,7 +195,7 @@
 		ranges;
 		#interrupt-cells = <3>;
 		interrupt-controller;
-		reg = <0x00 0x01800000 0x00 0x200000>, /* GICD */
+		reg = <0x00 0x01800000 0x00 0x10000>, /* GICD */
 		      <0x00 0x01900000 0x00 0x100000>, /* GICR */
 		      <0x00 0x6f000000 0x00 0x2000>,   /* GICC */
 		      <0x00 0x6f010000 0x00 0x1000>,   /* GICH */
diff --git a/arch/arm64/boot/dts/xilinx/Makefile b/arch/arm64/boot/dts/xilinx/Makefile
index 1068b0fa8e98..7f5a8801cad1 100644
--- a/arch/arm64/boot/dts/xilinx/Makefile
+++ b/arch/arm64/boot/dts/xilinx/Makefile
@@ -29,3 +29,5 @@ zynqmp-smk-k26-revA-sck-kv-g-revA-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-
 dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revA.dtb
 zynqmp-smk-k26-revA-sck-kv-g-revB-dtbs := zynqmp-smk-k26-revA.dtb zynqmp-sck-kv-g-revB.dtbo
 dtb-$(CONFIG_ARCH_ZYNQMP) += zynqmp-smk-k26-revA-sck-kv-g-revB.dtb
+
+dtb-$(CONFIG_ARCH_ZYNQMP) += versal-net-vn-x-b2197-01-revA.dtb
diff --git a/arch/arm64/boot/dts/xilinx/versal-net-clk.dtsi b/arch/arm64/boot/dts/xilinx/versal-net-clk.dtsi
new file mode 100644
index 000000000000..b7a8a1a512cb
--- /dev/null
+++ b/arch/arm64/boot/dts/xilinx/versal-net-clk.dtsi
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dts file for Xilinx Versal NET fixed clock
+ *
+ * (C) Copyright 2022, Xilinx, Inc.
+ * (C) Copyright 2022 - 2025, Advanced Micro Devices, Inc.
+ *
+ * Michal Simek <michal.simek@amd.com>
+ */
+
+/ {
+	clk60: clk60 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <60000000>;
+	};
+
+	clk100: clk100 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+	};
+
+	clk125: clk125 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <125000000>;
+	};
+
+	clk150: clk150 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <150000000>;
+	};
+
+	clk160: clk160 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <160000000>;
+	};
+
+	clk200: clk200 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+	};
+
+	clk250: clk250 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <250000000>;
+	};
+
+	clk300: clk300 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <300000000>;
+	};
+
+	clk450: clk450 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <450000000>;
+	};
+
+	clk1200: clk1200 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <1200000000>;
+	};
+
+	firmware {
+		versal_net_firmware: versal-net-firmware {
+			compatible = "xlnx,versal-net-firmware", "xlnx,versal-firmware";
+			bootph-all;
+			method = "smc";
+		};
+	};
+};
+
+&adma0 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma1 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma2 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma3 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma4 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma5 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma6 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&adma7 {
+	clocks = <&clk450>, <&clk450>;
+};
+
+&can0 {
+	clocks = <&clk160>, <&clk160>;
+};
+
+&can1 {
+	clocks = <&clk160>, <&clk160>;
+};
+
+&gem0 {
+	clocks = <&clk125>, <&clk125>, <&clk125>, <&clk125>, <&clk250>;
+};
+
+&gem1 {
+	clocks = <&clk125>, <&clk125>, <&clk125>, <&clk125>, <&clk250>;
+};
+
+&gpio0 {
+	clocks = <&clk100>;
+};
+
+&gpio1 {
+	clocks = <&clk100>;
+};
+
+&i2c0 {
+	clocks = <&clk100>;
+};
+
+&i2c1 {
+	clocks = <&clk100>;
+};
+
+&i3c0 {
+	clocks = <&clk100>;
+};
+
+&i3c1 {
+	clocks = <&clk100>;
+};
+
+&ospi {
+	clocks = <&clk200>;
+};
+
+&qspi {
+	clocks = <&clk300>, <&clk300>;
+};
+
+&rtc {
+	/* Nothing */
+};
+
+&sdhci0 {
+	clocks = <&clk200>, <&clk200>, <&clk1200>;
+};
+
+&sdhci1 {
+	clocks = <&clk200>, <&clk200>, <&clk1200>;
+};
+
+&serial0 {
+	clocks = <&clk100>, <&clk100>;
+};
+
+&serial1 {
+	clocks = <&clk100>, <&clk100>;
+};
+
+&spi0 {
+	clocks = <&clk200>, <&clk200>;
+};
+
+&spi1 {
+	clocks = <&clk200>, <&clk200>;
+};
+
+&ttc0 {
+	clocks = <&clk150>;
+};
+
+&usb0 {
+	clocks = <&clk60>, <&clk60>;
+};
+
+&dwc3_0 {
+	clocks = <&clk60>;
+};
+
+&usb1 {
+	clocks = <&clk60>, <&clk60>;
+};
+
+&dwc3_1 {
+	clocks = <&clk60>;
+};
+
+&wwdt0 {
+	clocks = <&clk150>;
+};
+
+&wwdt1 {
+	clocks = <&clk150>;
+};
+
+&wwdt2 {
+	clocks = <&clk150>;
+};
+
+&wwdt3 {
+	clocks = <&clk150>;
+};
+
+&lpd_wwdt0 {
+	clocks = <&clk150>;
+};
+
+&lpd_wwdt1 {
+	clocks = <&clk150>;
+};
diff --git a/arch/arm64/boot/dts/xilinx/versal-net-vn-x-b2197-01-revA.dts b/arch/arm64/boot/dts/xilinx/versal-net-vn-x-b2197-01-revA.dts
new file mode 100644
index 000000000000..06b2301f48a0
--- /dev/null
+++ b/arch/arm64/boot/dts/xilinx/versal-net-vn-x-b2197-01-revA.dts
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dts file for Xilinx Versal Net VNX board revA
+ *
+ * (C) Copyright 2022, Xilinx, Inc.
+ * (C) Copyright 2022 - 2025, Advanced Micro Devices, Inc.
+ *
+ * Michal Simek <michal.simek@amd.com>
+ */
+
+/dts-v1/;
+
+#include "versal-net.dtsi"
+#include "versal-net-clk.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	compatible = "xlnx,versal-net-vnx-revA", "xlnx,versal-net-vnx", "xlnx,versal-net";
+	model = "Xilinx Versal NET VNX revA";
+	dma-coherent;
+
+	memory: memory@0 {
+		reg = <0 0 0 0x80000000>;
+		device_type = "memory";
+	};
+
+	memory_hi: memory@800000000 {
+		reg = <8 0 3 0x80000000>;
+		device_type = "memory";
+	};
+
+	memory_hi2: memory@50000000000 {
+		reg = <0x500 0 4 0>;
+		device_type = "memory";
+	};
+
+	chosen {
+		bootargs = "console=ttyAMA1,115200n8";
+		stdout-path = "serial1:115200n8";
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		rsc_tbl_carveout: rproc@bbf14000 {
+			reg = <0 0xbbf14000 0 0x1000>;
+			no-map;
+		};
+		rpu0vdev0vring0: rpu0vdev0vring0@bbf15000 {
+			reg = <0 0xbbf15000 0 0x1000>;
+			no-map;
+		};
+		rpu0vdev0vring1: rpu0vdev0vring1@bbf16000 {
+			reg = <0 0xbbf16000 0 0x1000>;
+			no-map;
+		};
+		rpu0vdev0buffer: rpu0vdev0buffer@bbf17000 {
+			reg = <0 0xbbf17000 0 0xD000>;
+			no-map;
+		};
+		reserve_others: reserveothers@0 {
+			reg = <0 0x0 0 0x1c200000>;
+			no-map;
+		};
+		pdi_update: pdiupdate@1c200000 {
+			reg = <0 0x1c200000 0 0x6000000>;
+			no-map;
+		};
+		reserve_optee_atf: reserveopteeatf@22200000 {
+			reg = <0 0x22200000 0 0x4100000>;
+			no-map;
+		};
+	};
+};
+
+&gem1 {
+	status = "okay";
+	iommus = <&smmu 0x235>;
+	phy-handle = <&phy>;
+	phy-mode = "rmii";
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy: ethernet-phy@4 {
+			reg = <4>;
+		};
+	};
+};
+
+&ospi {
+	num-cs = <2>;
+	iommus = <&smmu 0x245>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+};
+
+&sdhci1 {
+	status = "okay";
+	iommus = <&smmu 0x243>;
+	non-removable;
+	disable-wp;
+	no-sd;
+	no-sdio;
+	cap-mmc-hw-reset;
+	bus-width = <8>;
+	no-1-8-v;
+};
+
+&serial1 {
+	status = "okay";
+};
+
+&smmu {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/xilinx/versal-net.dtsi b/arch/arm64/boot/dts/xilinx/versal-net.dtsi
new file mode 100644
index 000000000000..fc9f49e57385
--- /dev/null
+++ b/arch/arm64/boot/dts/xilinx/versal-net.dtsi
@@ -0,0 +1,752 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dts file for Xilinx Versal NET
+ *
+ * (C) Copyright 2022, Xilinx, Inc.
+ * (C) Copyright 2022 - 2025, Advanced Micro Devices, Inc.
+ *
+ * Michal Simek <michal.simek@amd.com>
+ */
+
+/dts-v1/;
+
+/ {
+	compatible = "xlnx,versal-net";
+	model = "Xilinx Versal NET";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&gic>;
+
+	options {
+		u-boot {
+			compatible = "u-boot,config";
+			bootscr-address = /bits/ 64 <0x20000000>;
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&cpu0>;
+				};
+				core1 {
+					cpu = <&cpu100>;
+				};
+				core2 {
+					cpu = <&cpu200>;
+				};
+				core3 {
+					cpu = <&cpu300>;
+				};
+			};
+
+			cluster1 {
+				core0 {
+					cpu = <&cpu10000>;
+				};
+
+				core1 {
+					cpu = <&cpu10100>;
+				};
+
+				core2 {
+					cpu = <&cpu10200>;
+				};
+
+				core3 {
+					cpu = <&cpu10300>;
+				};
+			};
+			cluster2 {
+				core0 {
+					cpu = <&cpu20000>;
+				};
+
+				core1 {
+					cpu = <&cpu20100>;
+				};
+
+				core2 {
+					cpu = <&cpu20200>;
+				};
+
+				core3 {
+					cpu = <&cpu20300>;
+				};
+			};
+			cluster3 {
+				core0 {
+					cpu = <&cpu30000>;
+				};
+
+				core1 {
+					cpu = <&cpu30100>;
+				};
+
+				core2 {
+					cpu = <&cpu30200>;
+				};
+
+				core3 {
+					cpu = <&cpu30300>;
+				};
+			};
+
+		};
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu100: cpu@100 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x100>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu200: cpu@200 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x200>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu300: cpu@300 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x300>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu10000: cpu@10000 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x10000>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu10100: cpu@10100 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x10100>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu10200: cpu@10200 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x10200>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu10300: cpu@10300 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x10300>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu20000: cpu@20000 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x20000>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu20100: cpu@20100 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x20100>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu20200: cpu@20200 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x20200>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu20300: cpu@20300 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x20300>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu30000: cpu@30000 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x30000>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu30100: cpu@30100 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x30100>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu30200: cpu@30200 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x30200>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		cpu30300: cpu@30300 {
+			compatible = "arm,cortex-a78";
+			device_type = "cpu";
+			enable-method = "psci";
+			reg = <0x30300>;
+			operating-points-v2 = <&cpu_opp_table>;
+			cpu-idle-states = <&CPU_SLEEP_0>;
+		};
+		idle-states {
+			entry-method = "psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x40000000>;
+				local-timer-stop;
+				entry-latency-us = <300>;
+				exit-latency-us = <600>;
+				min-residency-us = <10000>;
+			};
+		};
+	};
+
+	cpu_opp_table: opp-table {
+		compatible = "operating-points-v2";
+		opp-1066000000 {
+			opp-hz = /bits/ 64 <1066000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-1866000000 {
+			opp-hz = /bits/ 64 <1866000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-1900000000 {
+			opp-hz = /bits/ 64 <1900000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-1999000000 {
+			opp-hz = /bits/ 64 <1999000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-2050000000 {
+			opp-hz = /bits/ 64 <2050000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-2100000000 {
+			opp-hz = /bits/ 64 <2100000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-2200000000 {
+			opp-hz = /bits/ 64 <2200000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-2400000000 {
+			opp-hz = /bits/ 64 <2400000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <500000>;
+		};
+	};
+
+	aliases {
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &dcc;
+		mmc0 = &sdhci0;
+		mmc1 = &sdhci1;
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		rtc = &rtc;
+		usb0 = &usb0;
+		usb1 = &usb1;
+		spi0 = &ospi;
+		spi1 = &qspi;
+	};
+
+	dcc: dcc {
+		compatible = "arm,dcc";
+		status = "disabled";
+		bootph-all;
+	};
+
+	firmware {
+		psci {
+			compatible = "arm,psci-1.0";
+			method = "smc";
+		};
+	};
+
+	fpga: fpga-region {
+		compatible = "fpga-region";
+		fpga-mgr = <&versal_fpga>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+	};
+
+	timer: timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 13 4>, <1 14 4>, <1 11 4>, <1 10 4>;
+	};
+
+	versal_fpga: versal-fpga {
+		compatible = "xlnx,versal-fpga";
+	};
+
+	amba: axi {
+		compatible = "simple-bus";
+		bootph-all;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		adma0: dma-controller@ebd00000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd00000 0 0x1000>;
+			interrupts = <0 72 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma1: dma-controller@ebd10000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd10000 0 0x1000>;
+			interrupts = <0 73 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma2: dma-controller@ebd20000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd20000 0 0x1000>;
+			interrupts = <0 74 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma3: dma-controller@ebd30000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd30000 0 0x1000>;
+			interrupts = <0 75 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma4: dma-controller@ebd40000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd40000 0 0x1000>;
+			interrupts = <0 76 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma5: dma-controller@ebd50000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd50000 0 0x1000>;
+			interrupts = <0 77 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma6: dma-controller@ebd60000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd60000 0 0x1000>;
+			interrupts = <0 78 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		adma7: dma-controller@ebd70000 {
+			compatible = "xlnx,zynqmp-dma-1.0";
+			status = "disabled";
+			reg = <0 0xebd70000 0 0x1000>;
+			interrupts = <0 79 4>;
+			clock-names = "clk_main", "clk_apb";
+			#dma-cells = <1>;
+			xlnx,bus-width = <64>;
+		};
+
+		can0: can@f1980000 {
+			compatible = "xlnx,canfd-2.0";
+			status = "disabled";
+			reg = <0 0xf1980000 0 0x6000>;
+			interrupts = <0 27 4>;
+			clock-names = "can_clk", "s_axi_aclk";
+			rx-fifo-depth = <64>;
+			tx-mailbox-count = <32>;
+		};
+
+		can1: can@f1990000 {
+			compatible = "xlnx,canfd-2.0";
+			status = "disabled";
+			reg = <0 0xf1990000 0 0x6000>;
+			interrupts = <0 28 4>;
+			clock-names = "can_clk", "s_axi_aclk";
+			rx-fifo-depth = <64>;
+			tx-mailbox-count = <32>;
+		};
+
+		gem0: ethernet@f19e0000 {
+			compatible = "xlnx,versal-gem", "cdns,gem";
+			status = "disabled";
+			reg = <0 0xf19e0000 0 0x1000>;
+			interrupts = <0 39 4>, <0 39 4>;
+			clock-names = "pclk", "hclk", "tx_clk", "rx_clk",
+				      "tsu_clk";
+		};
+
+		gem1: ethernet@f19f0000 {
+			compatible = "xlnx,versal-gem", "cdns,gem";
+			status = "disabled";
+			reg = <0 0xf19f0000 0 0x1000>;
+			interrupts = <0 41 4>, <0 41 4>;
+			clock-names = "pclk", "hclk", "tx_clk", "rx_clk",
+				      "tsu_clk";
+		};
+
+		gic: interrupt-controller@e2000000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <3>;
+			reg = <0 0xe2000000 0 0x10000>,
+			      <0 0xe2060000 0 0x200000>;
+			interrupt-controller;
+			interrupts = <1 9 4>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			its: msi-controller@e2040000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				#msi-cells = <1>;
+				reg = <0 0xe2040000 0 0x20000>;
+			};
+		};
+
+		gpio0: gpio@f19d0000 {
+			compatible = "xlnx,versal-gpio-1.0";
+			status = "disabled";
+			reg = <0 0xf19d0000 0 0x1000>;
+			interrupts = <0 20 4>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+		};
+
+		gpio1: gpio@f1020000 {
+			compatible = "xlnx,pmc-gpio-1.0";
+			status = "disabled";
+			reg = <0 0xf1020000 0 0x1000>;
+			interrupts = <0 180 4>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+		};
+
+		i2c0: i2c@f1940000 {
+			compatible = "cdns,i2c-r1p14";
+			status = "disabled";
+			reg = <0 0xf1940000 0 0x1000>;
+			interrupts = <0 21 4>;
+			clock-frequency = <400000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i2c1: i2c@f1950000 {
+			compatible = "cdns,i2c-r1p14";
+			status = "disabled";
+			reg = <0 0xf1950000 0 0x1000>;
+			interrupts = <0 22 4>;
+			clock-frequency = <400000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		i3c0: i3c@f1948000 {
+			compatible = "snps,dw-i3c-master-1.00a";
+			status = "disabled";
+			reg = <0 0xf1948000 0 0x1000>;
+			#address-cells = <3>;
+			#size-cells = <0>;
+			interrupts = <0 21 4>;
+		};
+
+		i3c1: i3c@f1958000 {
+			compatible = "snps,dw-i3c-master-1.00a";
+			status = "disabled";
+			reg = <0 0xf1958000 0 0x1000>;
+			#address-cells = <3>;
+			#size-cells = <0>;
+			interrupts = <0 22 4>;
+		};
+
+		ospi: spi@f1010000 {
+			compatible = "xlnx,versal-ospi-1.0", "cdns,qspi-nor";
+			status = "disabled";
+			reg = <0 0xf1010000 0 0x10000>,
+			      <0 0xc0000000 0 0x20000000>;
+			interrupts = <0 182 4>;
+			cdns,fifo-depth = <256>;
+			cdns,fifo-width = <4>;
+			cdns,is-dma = <1>; /* u-boot specific */
+			cdns,trigger-address = <0xc0000000>;
+		};
+
+		qspi: spi@f1030000 {
+			compatible = "xlnx,versal-qspi-1.0";
+			status = "disabled";
+			reg = <0 0xf1030000 0 0x1000>;
+			interrupts = <0 183 4>;
+			clock-names = "ref_clk", "pclk";
+		};
+
+		rtc: rtc@f12a0000 {
+			compatible = "xlnx,zynqmp-rtc";
+			status = "disabled";
+			reg = <0 0xf12a0000 0 0x100>;
+			interrupts = <0 200 4>, <0 201 4>;
+			interrupt-names = "alarm", "sec";
+			calibration = <0x8000>;
+		};
+
+		sdhci0: mmc@f1040000 {
+			compatible = "xlnx,versal-8.9a", "arasan,sdhci-8.9a";
+			status = "disabled";
+			reg = <0 0xf1040000 0 0x10000>;
+			interrupts = <0 184 4>;
+			clock-names = "clk_xin", "clk_ahb", "gate";
+			#clock-cells = <1>;
+			clock-output-names = "clk_out_sd0", "clk_in_sd0";
+		};
+
+		sdhci1: mmc@f1050000 {
+			compatible = "xlnx,versal-net-emmc";
+			status = "disabled";
+			reg = <0 0xf1050000 0 0x10000>;
+			interrupts = <0 186 4>;
+			clock-names = "clk_xin", "clk_ahb", "gate";
+			#clock-cells = <1>;
+			clock-output-names = "clk_out_sd1", "clk_in_sd1";
+		};
+
+		serial0: serial@f1920000 {
+			bootph-all;
+			compatible = "arm,pl011", "arm,primecell";
+			status = "disabled";
+			reg = <0 0xf1920000 0 0x1000>;
+			interrupts = <0 25 4>;
+			reg-io-width = <4>;
+			clock-names = "uartclk", "apb_pclk";
+		};
+
+		serial1: serial@f1930000 {
+			bootph-all;
+			compatible = "arm,pl011", "arm,primecell";
+			status = "disabled";
+			reg = <0 0xf1930000 0 0x1000>;
+			interrupts = <0 26 4>;
+			reg-io-width = <4>;
+			clock-names = "uartclk", "apb_pclk";
+		};
+
+		smmu: iommu@ec000000 {
+			compatible = "arm,smmu-v3";
+			status = "disabled";
+			reg = <0 0xec000000 0 0x40000>;
+			#iommu-cells = <1>;
+			interrupt-names = "combined";
+			interrupts = <0 169 4>;
+			dma-coherent;
+		};
+
+		spi0: spi@f1960000 {
+			compatible = "cdns,spi-r1p6";
+			status = "disabled";
+			interrupts = <0 23 4>;
+			reg = <0 0xf1960000 0 0x1000>;
+			clock-names = "ref_clk", "pclk";
+		};
+
+		spi1: spi@f1970000 {
+			compatible = "cdns,spi-r1p6";
+			status = "disabled";
+			interrupts = <0 24 4>;
+			reg = <0 0xf1970000 0 0x1000>;
+			clock-names = "ref_clk", "pclk";
+		};
+
+		ttc0: timer@f1dc0000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupts = <0 43 4>, <0 44 4>, <0 45 4>;
+			timer-width = <32>;
+			reg = <0x0 0xf1dc0000 0x0 0x1000>;
+		};
+
+		ttc1: timer@f1dd0000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupts = <0 46 4>, <0 47 4>, <0 48 4>;
+			timer-width = <32>;
+			reg = <0x0 0xf1dd0000 0x0 0x1000>;
+		};
+
+		ttc2: timer@f1de0000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupts = <0 49 4>, <0 50 4>, <0 51 4>;
+			timer-width = <32>;
+			reg = <0x0 0xf1de0000 0x0 0x1000>;
+		};
+
+		ttc3: timer@f1df0000 {
+			compatible = "cdns,ttc";
+			status = "disabled";
+			interrupts = <0 52 4>, <0 53 4>, <0 54 4>;
+			timer-width = <32>;
+			reg = <0x0 0xf1df0000 0x0 0x1000>;
+		};
+
+		usb0: usb@f1e00000 {
+			compatible = "xlnx,versal-dwc3";
+			status = "disabled";
+			reg = <0 0xf1e00000 0 0x100>;
+			clock-names = "bus_clk", "ref_clk";
+			ranges;
+			#address-cells = <2>;
+			#size-cells = <2>;
+
+			dwc3_0: usb@f1b00000  {
+				compatible = "snps,dwc3";
+				status = "disabled";
+				reg = <0 0xf1b00000 0 0x10000>;
+				interrupt-names = "host", "peripheral", "otg", "wakeup";
+				interrupts = <0 29 4>, <0 29 4>, <0 33 4>, <0 98 4>;
+				snps,dis_u2_susphy_quirk;
+				snps,dis_u3_susphy_quirk;
+				snps,quirk-frame-length-adjustment = <0x20>;
+				dr_mode = "peripheral";
+				maximum-speed = "high-speed";
+				snps,usb3_lpm_capable;
+				clock-names = "ref";
+			};
+		};
+
+		usb1: usb@f1e10000 {
+			compatible = "xlnx,versal-dwc3";
+			status = "disabled";
+			reg = <0x0 0xf1e10000 0x0 0x100>;
+			clock-names = "bus_clk", "ref_clk";
+			ranges;
+			#address-cells = <2>;
+			#size-cells = <2>;
+
+			dwc3_1: usb@f1c00000  {
+				compatible = "snps,dwc3";
+				status = "disabled";
+				reg = <0x0 0xf1c00000 0x0 0x10000>;
+				interrupt-names = "host", "peripheral", "otg", "wakeup";
+				interrupts = <0 34 4>, <0 34 4>, <0 38 4>, <0 99 4>;
+				snps,dis_u2_susphy_quirk;
+				snps,dis_u3_susphy_quirk;
+				snps,quirk-frame-length-adjustment = <0x20>;
+				dr_mode = "host";
+				maximum-speed = "high-speed";
+				snps,usb3_lpm_capable;
+				clock-names = "ref";
+			};
+		};
+
+		wwdt0: watchdog@ecc10000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xecc10000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+
+		wwdt1: watchdog@ecd10000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xecd10000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+
+		wwdt2: watchdog@ece10000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xece10000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+
+		wwdt3: watchdog@ecf10000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xecf10000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+
+		lpd_wwdt0: watchdog@ea420000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xea420000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+
+		lpd_wwdt1: watchdog@ea430000 {
+			compatible = "xlnx,versal-wwdt";
+			status = "disabled";
+			reg = <0 0xea430000 0 0x10000>;
+			timeout-sec = <30>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/xilinx/xlnx-zynqmp-clk.h b/arch/arm64/boot/dts/xilinx/xlnx-zynqmp-clk.h
new file mode 100644
index 000000000000..0aa17f2a2818
--- /dev/null
+++ b/arch/arm64/boot/dts/xilinx/xlnx-zynqmp-clk.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Xilinx Zynq MPSoC Firmware layer
+ *
+ *  Copyright (C) 2014-2018 Xilinx, Inc.
+ *
+ */
+
+#ifndef _XLNX_ZYNQMP_CLK_H
+#define _XLNX_ZYNQMP_CLK_H
+
+#define IOPLL			0
+#define RPLL			1
+#define APLL			2
+#define DPLL			3
+#define VPLL			4
+#define IOPLL_TO_FPD		5
+#define RPLL_TO_FPD		6
+#define APLL_TO_LPD		7
+#define DPLL_TO_LPD		8
+#define VPLL_TO_LPD		9
+#define ACPU			10
+#define ACPU_HALF		11
+#define DBF_FPD			12
+#define DBF_LPD			13
+#define DBG_TRACE		14
+#define DBG_TSTMP		15
+#define DP_VIDEO_REF		16
+#define DP_AUDIO_REF		17
+#define DP_STC_REF		18
+#define GDMA_REF		19
+#define DPDMA_REF		20
+#define DDR_REF			21
+#define SATA_REF		22
+#define PCIE_REF		23
+#define GPU_REF			24
+#define GPU_PP0_REF		25
+#define GPU_PP1_REF		26
+#define TOPSW_MAIN		27
+#define TOPSW_LSBUS		28
+#define GTGREF0_REF		29
+#define LPD_SWITCH		30
+#define LPD_LSBUS		31
+#define USB0_BUS_REF		32
+#define USB1_BUS_REF		33
+#define USB3_DUAL_REF		34
+#define USB0			35
+#define USB1			36
+#define CPU_R5			37
+#define CPU_R5_CORE		38
+#define CSU_SPB			39
+#define CSU_PLL			40
+#define PCAP			41
+#define IOU_SWITCH		42
+#define GEM_TSU_REF		43
+#define GEM_TSU			44
+#define GEM0_TX			45
+#define GEM1_TX			46
+#define GEM2_TX			47
+#define GEM3_TX			48
+#define GEM0_RX			49
+#define GEM1_RX			50
+#define GEM2_RX			51
+#define GEM3_RX			52
+#define QSPI_REF		53
+#define SDIO0_REF		54
+#define SDIO1_REF		55
+#define UART0_REF		56
+#define UART1_REF		57
+#define SPI0_REF		58
+#define SPI1_REF		59
+#define NAND_REF		60
+#define I2C0_REF		61
+#define I2C1_REF		62
+#define CAN0_REF		63
+#define CAN1_REF		64
+#define CAN0			65
+#define CAN1			66
+#define DLL_REF			67
+#define ADMA_REF		68
+#define TIMESTAMP_REF		69
+#define AMS_REF			70
+#define PL0_REF			71
+#define PL1_REF			72
+#define PL2_REF			73
+#define PL3_REF			74
+#define WDT			75
+#define IOPLL_INT		76
+#define IOPLL_PRE_SRC		77
+#define IOPLL_HALF		78
+#define IOPLL_INT_MUX		79
+#define IOPLL_POST_SRC		80
+#define RPLL_INT		81
+#define RPLL_PRE_SRC		82
+#define RPLL_HALF		83
+#define RPLL_INT_MUX		84
+#define RPLL_POST_SRC		85
+#define APLL_INT		86
+#define APLL_PRE_SRC		87
+#define APLL_HALF		88
+#define APLL_INT_MUX		89
+#define APLL_POST_SRC		90
+#define DPLL_INT		91
+#define DPLL_PRE_SRC		92
+#define DPLL_HALF		93
+#define DPLL_INT_MUX		94
+#define DPLL_POST_SRC		95
+#define VPLL_INT		96
+#define VPLL_PRE_SRC		97
+#define VPLL_HALF		98
+#define VPLL_INT_MUX		99
+#define VPLL_POST_SRC		100
+#define CAN0_MIO		101
+#define CAN1_MIO		102
+#define ACPU_FULL		103
+#define GEM0_REF		104
+#define GEM1_REF		105
+#define GEM2_REF		106
+#define GEM3_REF		107
+#define GEM0_REF_UNG		108
+#define GEM1_REF_UNG		109
+#define GEM2_REF_UNG		110
+#define GEM3_REF_UNG		111
+#define LPD_WDT			112
+
+#endif /* _XLNX_ZYNQMP_CLK_H */
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
index 60d1b1acf9a0..52e122fc7c9e 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
@@ -8,41 +8,46 @@
  * Michal Simek <michal.simek@amd.com>
  */
 
-#include <dt-bindings/clock/xlnx-zynqmp-clk.h>
+#include "xlnx-zynqmp-clk.h"
 / {
-	pss_ref_clk: pss_ref_clk {
+	pss_ref_clk: pss-ref-clk {
 		bootph-all;
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <33333333>;
+		clock-output-names = "pss_ref_clk";
 	};
 
-	video_clk: video_clk {
+	video_clk: video-clk {
 		bootph-all;
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <27000000>;
+		clock-output-names = "video_clk";
 	};
 
-	pss_alt_ref_clk: pss_alt_ref_clk {
+	pss_alt_ref_clk: pss-alt-ref-clk {
 		bootph-all;
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <0>;
+		clock-output-names = "pss_alt_ref_clk";
 	};
 
-	gt_crx_ref_clk: gt_crx_ref_clk {
+	gt_crx_ref_clk: gt-crx-ref-clk {
 		bootph-all;
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <108000000>;
+		clock-output-names = "gt_crx_ref_clk";
 	};
 
-	aux_ref_clk: aux_ref_clk {
+	aux_ref_clk: aux-ref-clk {
 		bootph-all;
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <27000000>;
+		clock-output-names = "aux_ref_clk";
 	};
 };
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 1f25423de383..a61154545c89 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -177,6 +177,7 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_GACT=m
 CONFIG_NET_ACT_MIRRED=m
+CONFIG_HSR=m
 CONFIG_NET_ACT_GATE=m
 CONFIG_QRTR_SMD=m
 CONFIG_QRTR_TUN=m
@@ -284,6 +285,7 @@ CONFIG_MTD_NAND_BRCMNAND=m
 CONFIG_MTD_NAND_FSL_IFC=y
 CONFIG_MTD_NAND_QCOM=y
 CONFIG_MTD_SPI_NOR=y
+CONFIG_MTD_SPI_NAND=m
 CONFIG_MTD_UBI=m
 CONFIG_MTD_HYPERBUS=m
 CONFIG_HBMC_AM654=m
@@ -845,6 +847,7 @@ CONFIG_VIDEO_IMX8_ISI=m
 CONFIG_VIDEO_IMX8_ISI_M2M=y
 CONFIG_VIDEO_IMX8_JPEG=m
 CONFIG_VIDEO_QCOM_CAMSS=m
+CONFIG_VIDEO_QCOM_IRIS=m
 CONFIG_VIDEO_QCOM_VENUS=m
 CONFIG_VIDEO_RCAR_ISP=m
 CONFIG_VIDEO_RCAR_CSI2=m
@@ -859,6 +862,8 @@ CONFIG_VIDEO_SAMSUNG_EXYNOS_GSC=m
 CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
 CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
 CONFIG_VIDEO_SUN6I_CSI=m
+CONFIG_VIDEO_SYNOPSYS_HDMIRX=m
+CONFIG_VIDEO_SYNOPSYS_HDMIRX_LOAD_DEFAULT_EDID=y
 CONFIG_VIDEO_TI_J721E_CSI2RX=m
 CONFIG_VIDEO_HANTRO=m
 CONFIG_VIDEO_IMX219=m
@@ -911,6 +916,7 @@ CONFIG_DRM_PANEL_SAMSUNG_ATNA33XC20=m
 CONFIG_DRM_PANEL_SITRONIX_ST7703=m
 CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m
 CONFIG_DRM_PANEL_VISIONOX_VTDR6130=m
+CONFIG_DRM_DISPLAY_CONNECTOR=m
 CONFIG_DRM_FSL_LDB=m
 CONFIG_DRM_ITE_IT6263=m
 CONFIG_DRM_LONTIUM_LT8912B=m
@@ -1004,6 +1010,7 @@ CONFIG_SND_SOC_ROCKCHIP_RT5645=m
 CONFIG_SND_SOC_RK3399_GRU_SOUND=m
 CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_RCAR=m
+CONFIG_SND_SOC_MSIOF=m
 CONFIG_SND_SOC_RZ=m
 CONFIG_SND_SOC_SOF_TOPLEVEL=y
 CONFIG_SND_SOC_SOF_OF=y
@@ -1147,6 +1154,7 @@ CONFIG_TYPEC_HD3SS3220=m
 CONFIG_TYPEC_MUX_FSA4480=m
 CONFIG_TYPEC_MUX_GPIO_SBU=m
 CONFIG_TYPEC_MUX_NB7VPQ904M=m
+CONFIG_TYPEC_MUX_PS883X=m
 CONFIG_TYPEC_MUX_WCD939X_USBSS=m
 CONFIG_TYPEC_DP_ALTMODE=m
 CONFIG_MMC=y
@@ -1188,6 +1196,7 @@ CONFIG_SCSI_UFS_HISI=y
 CONFIG_SCSI_UFS_RENESAS=m
 CONFIG_SCSI_UFS_TI_J721E=m
 CONFIG_SCSI_UFS_EXYNOS=y
+CONFIG_SCSI_UFS_ROCKCHIP=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_CLASS_MULTICOLOR=m
@@ -1270,6 +1279,8 @@ CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_XEN_GNTDEV=y
 CONFIG_XEN_GRANT_DEV_ALLOC=y
+CONFIG_GREYBUS=m
+CONFIG_GREYBUS_BEAGLEPLAY=m
 CONFIG_STAGING=y
 CONFIG_STAGING_MEDIA=y
 CONFIG_VIDEO_MAX96712=m
@@ -1320,6 +1331,7 @@ CONFIG_CLK_X1E80100_DISPCC=m
 CONFIG_CLK_X1E80100_GCC=y
 CONFIG_CLK_X1E80100_GPUCC=m
 CONFIG_CLK_X1E80100_TCSRCC=y
+CONFIG_CLK_QCM2290_GPUCC=m
 CONFIG_QCOM_A53PLL=y
 CONFIG_QCOM_CLK_APCS_MSM8916=y
 CONFIG_QCOM_CLK_APCC_MSM8996=y
@@ -1333,6 +1345,7 @@ CONFIG_IPQ_GCC_5332=y
 CONFIG_IPQ_GCC_6018=y
 CONFIG_IPQ_GCC_8074=y
 CONFIG_IPQ_GCC_9574=y
+CONFIG_IPQ_NSSCC_9574=m
 CONFIG_MSM_GCC_8916=y
 CONFIG_MSM_MMCC_8994=m
 CONFIG_MSM_GCC_8994=y
@@ -1394,6 +1407,7 @@ CONFIG_SM_TCSRCC_8650=y
 CONFIG_SM_TCSRCC_8750=m
 CONFIG_SA_VIDEOCC_8775P=m
 CONFIG_SM_VIDEOCC_8250=y
+CONFIG_SM_VIDEOCC_8550=m
 CONFIG_QCOM_HFPLL=y
 CONFIG_CLK_GFM_LPASS_SM8250=m
 CONFIG_CLK_RCAR_USB2_CLOCK_SEL=y
@@ -1461,29 +1475,6 @@ CONFIG_QCOM_WCNSS_CTRL=m
 CONFIG_QCOM_APR=m
 CONFIG_QCOM_ICC_BWMON=m
 CONFIG_QCOM_PBS=m
-CONFIG_ARCH_R8A77995=y
-CONFIG_ARCH_R8A77990=y
-CONFIG_ARCH_R8A77951=y
-CONFIG_ARCH_R8A77965=y
-CONFIG_ARCH_R8A77960=y
-CONFIG_ARCH_R8A77961=y
-CONFIG_ARCH_R8A779F0=y
-CONFIG_ARCH_R8A77980=y
-CONFIG_ARCH_R8A77970=y
-CONFIG_ARCH_R8A779A0=y
-CONFIG_ARCH_R8A779G0=y
-CONFIG_ARCH_R8A779H0=y
-CONFIG_ARCH_R8A774C0=y
-CONFIG_ARCH_R8A774E1=y
-CONFIG_ARCH_R8A774A1=y
-CONFIG_ARCH_R8A774B1=y
-CONFIG_ARCH_R9A07G043=y
-CONFIG_ARCH_R9A07G044=y
-CONFIG_ARCH_R9A07G054=y
-CONFIG_ARCH_R9A08G045=y
-CONFIG_ARCH_R9A09G011=y
-CONFIG_ARCH_R9A09G047=y
-CONFIG_ARCH_R9A09G057=y
 CONFIG_ROCKCHIP_IODOMAIN=y
 CONFIG_ARCH_TEGRA_132_SOC=y
 CONFIG_ARCH_TEGRA_210_SOC=y
@@ -1537,10 +1528,11 @@ CONFIG_PWM_IMX27=m
 CONFIG_PWM_MESON=m
 CONFIG_PWM_MTK_DISP=m
 CONFIG_PWM_MEDIATEK=m
-CONFIG_PWM_RCAR=m
+CONFIG_PWM_RENESAS_RCAR=m
+CONFIG_PWM_RENESAS_RZG2L_GPT=m
+CONFIG_PWM_RENESAS_RZ_MTU3=m
 CONFIG_PWM_RENESAS_TPU=m
 CONFIG_PWM_ROCKCHIP=y
-CONFIG_PWM_RZ_MTU3=m
 CONFIG_PWM_SAMSUNG=y
 CONFIG_PWM_SL28CPLD=m
 CONFIG_PWM_SUN4I=m
@@ -1561,6 +1553,7 @@ CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_RESET_TI_SCI=y
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_CAN_TRANSCEIVER=m
+CONFIG_PHY_NXP_PTN3222=m
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_CADENCE_TORRENT=m
 CONFIG_PHY_CADENCE_DPHY_RX=m
@@ -1715,15 +1708,14 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_SECURITY=y
 CONFIG_CRYPTO_USER=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_CHACHA20=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_ECHAINIV=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_CHACHA20_NEON=m
 CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y
-CONFIG_CRYPTO_SHA2_ARM64_CE=y
 CONFIG_CRYPTO_SHA512_ARM64_CE=m
 CONFIG_CRYPTO_SHA3_ARM64=m
 CONFIG_CRYPTO_SM3_ARM64_CE=m
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 5636ab83f22a..c44b0f202a1f 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -25,17 +25,6 @@ config CRYPTO_NHPOLY1305_NEON
 	  Architecture: arm64 using:
 	  - NEON (Advanced SIMD) extensions
 
-config CRYPTO_POLY1305_NEON
-	tristate "Hash functions: Poly1305 (NEON)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_HASH
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
-	help
-	  Poly1305 authenticator algorithm (RFC7539)
-
-	  Architecture: arm64 using:
-	  - NEON (Advanced SIMD) extensions
-
 config CRYPTO_SHA1_ARM64_CE
 	tristate "Hash functions: SHA-1 (ARMv8 Crypto Extensions)"
 	depends on KERNEL_MODE_NEON
@@ -47,25 +36,6 @@ config CRYPTO_SHA1_ARM64_CE
 	  Architecture: arm64 using:
 	  - ARMv8 Crypto Extensions
 
-config CRYPTO_SHA256_ARM64
-	tristate "Hash functions: SHA-224 and SHA-256"
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: arm64
-
-config CRYPTO_SHA2_ARM64_CE
-	tristate "Hash functions: SHA-224 and SHA-256 (ARMv8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_HASH
-	select CRYPTO_SHA256_ARM64
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: arm64 using:
-	  - ARMv8 Crypto Extensions
-
 config CRYPTO_SHA512_ARM64
 	tristate "Hash functions: SHA-384 and SHA-512"
 	select CRYPTO_HASH
@@ -100,7 +70,7 @@ config CRYPTO_SM3_NEON
 	tristate "Hash functions: SM3 (NEON)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_HASH
-	select CRYPTO_SM3
+	select CRYPTO_LIB_SM3
 	help
 	  SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
 
@@ -111,7 +81,7 @@ config CRYPTO_SM3_ARM64_CE
 	tristate "Hash functions: SM3 (ARMv8.2 Crypto Extensions)"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_HASH
-	select CRYPTO_SM3
+	select CRYPTO_LIB_SM3
 	help
 	  SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
 
@@ -142,7 +112,7 @@ config CRYPTO_AES_ARM64
 
 config CRYPTO_AES_ARM64_CE
 	tristate "Ciphers: AES (ARMv8 Crypto Extensions)"
-	depends on ARM64 && KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
 	select CRYPTO_LIB_AES
 	help
@@ -185,19 +155,6 @@ config CRYPTO_AES_ARM64_NEON_BLK
 	  Architecture: arm64 using:
 	  - NEON (Advanced SIMD) extensions
 
-config CRYPTO_CHACHA20_NEON
-	tristate "Ciphers: ChaCha (NEON)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_CHACHA_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
-	  stream cipher algorithms
-
-	  Architecture: arm64 using:
-	  - NEON (Advanced SIMD) extensions
-
 config CRYPTO_AES_ARM64_BS
 	tristate "Ciphers: AES, modes: ECB/CBC/CTR/XCTR/XTS modes (bit-sliced NEON)"
 	depends on KERNEL_MODE_NEON
@@ -265,7 +222,7 @@ config CRYPTO_SM4_ARM64_NEON_BLK
 
 config CRYPTO_AES_ARM64_CE_CCM
 	tristate "AEAD cipher: AES in CCM mode (ARMv8 Crypto Extensions)"
-	depends on ARM64 && KERNEL_MODE_NEON
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
 	select CRYPTO_AES_ARM64_CE
 	select CRYPTO_AES_ARM64_CE_BLK
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index e7139c4768ce..c231c980c514 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -8,9 +8,6 @@
 obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
 sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
 
-obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
-sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
-
 obj-$(CONFIG_CRYPTO_SHA512_ARM64_CE) += sha512-ce.o
 sha512-ce-y := sha512-ce-glue.o sha512-ce-core.o
 
@@ -56,19 +53,9 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
 obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
 aes-neon-blk-y := aes-glue-neon.o aes-neon.o
 
-obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
-sha256-arm64-y := sha256-glue.o sha256-core.o
-
 obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o
 sha512-arm64-y := sha512-glue.o sha512-core.o
 
-obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
-chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
-
-obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
-poly1305-neon-y := poly1305-core.o poly1305-glue.o
-AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64
-
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
 
@@ -81,10 +68,7 @@ aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
 quiet_cmd_perlasm = PERLASM $@
       cmd_perlasm = $(PERL) $(<) void $(@)
 
-$(obj)/%-core.S: $(src)/%-armv8.pl
-	$(call cmd,perlasm)
-
-$(obj)/sha256-core.S: $(src)/sha512-armv8.pl
+$(obj)/sha512-core.S: $(src)/../lib/crypto/sha2-armv8.pl
 	$(call cmd,perlasm)
 
-clean-files += poly1305-core.S sha256-core.S sha512-core.S
+clean-files += sha512-core.S
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index a2b5d6f20f4d..2d791d51891b 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -156,23 +156,13 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 	scatterwalk_start(&walk, req->src);
 
 	do {
-		u32 n = scatterwalk_clamp(&walk, len);
-		u8 *p;
-
-		if (!n) {
-			scatterwalk_start(&walk, sg_next(walk.sg));
-			n = scatterwalk_clamp(&walk, len);
-		}
-		p = scatterwalk_map(&walk);
-
-		macp = ce_aes_ccm_auth_data(mac, p, n, macp, ctx->key_enc,
-					    num_rounds(ctx));
+		unsigned int n;
 
+		n = scatterwalk_next(&walk, len);
+		macp = ce_aes_ccm_auth_data(mac, walk.addr, n, macp,
+					    ctx->key_enc, num_rounds(ctx));
+		scatterwalk_done_src(&walk, n);
 		len -= n;
-
-		scatterwalk_unmap(p);
-		scatterwalk_advance(&walk, n);
-		scatterwalk_done(&walk, 0, len);
 	} while (len);
 }
 
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index b0150999743f..81560f722b9d 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -5,19 +5,20 @@
  * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
-#include <asm/neon.h>
 #include <asm/hwcap.h>
-#include <asm/simd.h>
+#include <asm/neon.h>
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
-#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
+#include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include <crypto/xts.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
 #include "aes-ce-setkey.h"
 
@@ -130,7 +131,6 @@ struct mac_tfm_ctx {
 };
 
 struct mac_desc_ctx {
-	unsigned int len;
 	u8 dg[AES_BLOCK_SIZE];
 };
 
@@ -869,109 +869,64 @@ static int mac_init(struct shash_desc *desc)
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
 	memset(ctx->dg, 0, AES_BLOCK_SIZE);
-	ctx->len = 0;
-
 	return 0;
 }
 
 static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
-			  u8 dg[], int enc_before, int enc_after)
+			  u8 dg[], int enc_before)
 {
 	int rounds = 6 + ctx->key_length / 4;
+	int rem;
 
-	if (crypto_simd_usable()) {
-		int rem;
-
-		do {
-			kernel_neon_begin();
-			rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
-					     dg, enc_before, enc_after);
-			kernel_neon_end();
-			in += (blocks - rem) * AES_BLOCK_SIZE;
-			blocks = rem;
-			enc_before = 0;
-		} while (blocks);
-	} else {
-		if (enc_before)
-			aes_encrypt(ctx, dg, dg);
-
-		while (blocks--) {
-			crypto_xor(dg, in, AES_BLOCK_SIZE);
-			in += AES_BLOCK_SIZE;
-
-			if (blocks || enc_after)
-				aes_encrypt(ctx, dg, dg);
-		}
-	}
+	do {
+		kernel_neon_begin();
+		rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
+				     dg, enc_before, !enc_before);
+		kernel_neon_end();
+		in += (blocks - rem) * AES_BLOCK_SIZE;
+		blocks = rem;
+	} while (blocks);
 }
 
 static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
 {
 	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+	int blocks = len / AES_BLOCK_SIZE;
 
-	while (len > 0) {
-		unsigned int l;
-
-		if ((ctx->len % AES_BLOCK_SIZE) == 0 &&
-		    (ctx->len + len) > AES_BLOCK_SIZE) {
-
-			int blocks = len / AES_BLOCK_SIZE;
-
-			len %= AES_BLOCK_SIZE;
-
-			mac_do_update(&tctx->key, p, blocks, ctx->dg,
-				      (ctx->len != 0), (len != 0));
-
-			p += blocks * AES_BLOCK_SIZE;
-
-			if (!len) {
-				ctx->len = AES_BLOCK_SIZE;
-				break;
-			}
-			ctx->len = 0;
-		}
-
-		l = min(len, AES_BLOCK_SIZE - ctx->len);
-
-		if (l <= AES_BLOCK_SIZE) {
-			crypto_xor(ctx->dg + ctx->len, p, l);
-			ctx->len += l;
-			len -= l;
-			p += l;
-		}
-	}
-
-	return 0;
+	len %= AES_BLOCK_SIZE;
+	mac_do_update(&tctx->key, p, blocks, ctx->dg, 0);
+	return len;
 }
 
-static int cbcmac_final(struct shash_desc *desc, u8 *out)
+static int cbcmac_finup(struct shash_desc *desc, const u8 *src,
+			unsigned int len, u8 *out)
 {
 	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0);
-
+	if (len) {
+		crypto_xor(ctx->dg, src, len);
+		mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1);
+	}
 	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
-
 	return 0;
 }
 
-static int cmac_final(struct shash_desc *desc, u8 *out)
+static int cmac_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+		      u8 *out)
 {
 	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
 	u8 *consts = tctx->consts;
 
-	if (ctx->len != AES_BLOCK_SIZE) {
-		ctx->dg[ctx->len] ^= 0x80;
+	crypto_xor(ctx->dg, src, len);
+	if (len != AES_BLOCK_SIZE) {
+		ctx->dg[len] ^= 0x80;
 		consts += AES_BLOCK_SIZE;
 	}
-
-	mac_do_update(&tctx->key, consts, 1, ctx->dg, 0, 1);
-
+	mac_do_update(&tctx->key, consts, 1, ctx->dg, 0);
 	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
-
 	return 0;
 }
 
@@ -979,6 +934,8 @@ static struct shash_alg mac_algs[] = { {
 	.base.cra_name		= "cmac(aes)",
 	.base.cra_driver_name	= "cmac-aes-" MODE,
 	.base.cra_priority	= PRIO,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINAL_NONZERO,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
 				  2 * AES_BLOCK_SIZE,
@@ -987,13 +944,15 @@ static struct shash_alg mac_algs[] = { {
 	.digestsize		= AES_BLOCK_SIZE,
 	.init			= mac_init,
 	.update			= mac_update,
-	.final			= cmac_final,
+	.finup			= cmac_finup,
 	.setkey			= cmac_setkey,
 	.descsize		= sizeof(struct mac_desc_ctx),
 }, {
 	.base.cra_name		= "xcbc(aes)",
 	.base.cra_driver_name	= "xcbc-aes-" MODE,
 	.base.cra_priority	= PRIO,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINAL_NONZERO,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
 				  2 * AES_BLOCK_SIZE,
@@ -1002,21 +961,22 @@ static struct shash_alg mac_algs[] = { {
 	.digestsize		= AES_BLOCK_SIZE,
 	.init			= mac_init,
 	.update			= mac_update,
-	.final			= cmac_final,
+	.finup			= cmac_finup,
 	.setkey			= xcbc_setkey,
 	.descsize		= sizeof(struct mac_desc_ctx),
 }, {
 	.base.cra_name		= "cbcmac(aes)",
 	.base.cra_driver_name	= "cbcmac-aes-" MODE,
 	.base.cra_priority	= PRIO,
-	.base.cra_blocksize	= 1,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx),
 	.base.cra_module	= THIS_MODULE,
 
 	.digestsize		= AES_BLOCK_SIZE,
 	.init			= mac_init,
 	.update			= mac_update,
-	.final			= cbcmac_final,
+	.finup			= cbcmac_finup,
 	.setkey			= cbcmac_setkey,
 	.descsize		= sizeof(struct mac_desc_ctx),
 } };
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index 46425e7b9755..c4a623e86593 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -287,7 +287,8 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt,
 	struct skcipher_walk walk;
 	int nbytes, err;
 	int first = 1;
-	u8 *out, *in;
+	const u8 *in;
+	u8 *out;
 
 	if (req->cryptlen < AES_BLOCK_SIZE)
 		return -EINVAL;
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
deleted file mode 100644
index af2bbca38e70..000000000000
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on:
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_neon(u32 *state, u8 *dst, const u8 *src,
-				      int nrounds);
-asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src,
-				       int nrounds, int bytes);
-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
-			  int bytes, int nrounds)
-{
-	while (bytes > 0) {
-		int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
-
-		if (l <= CHACHA_BLOCK_SIZE) {
-			u8 buf[CHACHA_BLOCK_SIZE];
-
-			memcpy(buf, src, l);
-			chacha_block_xor_neon(state, buf, buf, nrounds);
-			memcpy(dst, buf, l);
-			state[12] += 1;
-			break;
-		}
-		chacha_4block_xor_neon(state, dst, src, nrounds, l);
-		bytes -= l;
-		src += l;
-		dst += l;
-		state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
-	}
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
-	if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
-		hchacha_block_generic(state, stream, nrounds);
-	} else {
-		kernel_neon_begin();
-		hchacha_block_neon(state, stream, nrounds);
-		kernel_neon_end();
-	}
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
-		       int nrounds)
-{
-	if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
-	    !crypto_simd_usable())
-		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
-	do {
-		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
-		kernel_neon_begin();
-		chacha_doneon(state, dst, src, todo, nrounds);
-		kernel_neon_end();
-
-		bytes -= todo;
-		src += todo;
-		dst += todo;
-	} while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_neon_stream_xor(struct skcipher_request *req,
-				  const struct chacha_ctx *ctx, const u8 *iv)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	chacha_init_generic(state, ctx->key, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = rounddown(nbytes, walk.stride);
-
-		if (!static_branch_likely(&have_neon) ||
-		    !crypto_simd_usable()) {
-			chacha_crypt_generic(state, walk.dst.virt.addr,
-					     walk.src.virt.addr, nbytes,
-					     ctx->nrounds);
-		} else {
-			kernel_neon_begin();
-			chacha_doneon(state, walk.dst.virt.addr,
-				      walk.src.virt.addr, nbytes, ctx->nrounds);
-			kernel_neon_end();
-		}
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha_neon(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return chacha_neon_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_neon(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 state[16];
-	u8 real_iv[16];
-
-	chacha_init_generic(state, ctx->key, req->iv);
-	hchacha_block_arch(state, subctx.key, ctx->nrounds);
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_neon_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_neon,
-		.decrypt		= chacha_neon,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-neon",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.walksize		= 5 * CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_neon,
-		.decrypt		= xchacha_neon,
-	}
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	if (!cpu_have_named_feature(ASIMD))
-		return 0;
-
-	static_branch_enable(&have_neon);
-
-	return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
-		crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && cpu_have_named_feature(ASIMD))
-		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index da7b7ec1a664..4995b6e22335 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -6,30 +6,27 @@
  */
 
 #include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/aes.h>
-#include <crypto/gcm.h>
-#include <crypto/algapi.h>
 #include <crypto/b128ops.h>
+#include <crypto/gcm.h>
+#include <crypto/ghash.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
 MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("ghash");
 
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
-
 #define RFC4106_NONCE_SIZE	4
 
 struct ghash_key {
@@ -37,10 +34,8 @@ struct ghash_key {
 	u64			h[][2];
 };
 
-struct ghash_desc_ctx {
+struct arm_ghash_desc_ctx {
 	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
-	u8 buf[GHASH_BLOCK_SIZE];
-	u32 count;
 };
 
 struct gcm_aes_ctx {
@@ -65,36 +60,12 @@ asmlinkage int pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
 
 static int ghash_init(struct shash_desc *desc)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	*ctx = (struct ghash_desc_ctx){};
+	*ctx = (struct arm_ghash_desc_ctx){};
 	return 0;
 }
 
-static void ghash_do_update(int blocks, u64 dg[], const char *src,
-			    struct ghash_key *key, const char *head)
-{
-	be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
-
-	do {
-		const u8 *in = src;
-
-		if (head) {
-			in = head;
-			blocks++;
-			head = NULL;
-		} else {
-			src += GHASH_BLOCK_SIZE;
-		}
-
-		crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
-		gf128mul_lle(&dst, &key->k);
-	} while (--blocks);
-
-	dg[0] = be64_to_cpu(dst.b);
-	dg[1] = be64_to_cpu(dst.a);
-}
-
 static __always_inline
 void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
 			  struct ghash_key *key, const char *head,
@@ -103,13 +74,9 @@ void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
 					      u64 const h[][2],
 					      const char *head))
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_neon_begin();
-		simd_update(blocks, dg, src, key->h, head);
-		kernel_neon_end();
-	} else {
-		ghash_do_update(blocks, dg, src, key, head);
-	}
+	kernel_neon_begin();
+	simd_update(blocks, dg, src, key->h, head);
+	kernel_neon_end();
 }
 
 /* avoid hogging the CPU for too long */
@@ -118,61 +85,59 @@ void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
 static int ghash_update(struct shash_desc *desc, const u8 *src,
 			unsigned int len)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+	int blocks;
 
-	ctx->count += len;
+	blocks = len / GHASH_BLOCK_SIZE;
+	len -= blocks * GHASH_BLOCK_SIZE;
 
-	if ((partial + len) >= GHASH_BLOCK_SIZE) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
-		int blocks;
-
-		if (partial) {
-			int p = GHASH_BLOCK_SIZE - partial;
+	do {
+		int chunk = min(blocks, MAX_BLOCKS);
 
-			memcpy(ctx->buf + partial, src, p);
-			src += p;
-			len -= p;
-		}
+		ghash_do_simd_update(chunk, ctx->digest, src, key, NULL,
+				     pmull_ghash_update_p8);
+		blocks -= chunk;
+		src += chunk * GHASH_BLOCK_SIZE;
+	} while (unlikely(blocks > 0));
+	return len;
+}
 
-		blocks = len / GHASH_BLOCK_SIZE;
-		len %= GHASH_BLOCK_SIZE;
+static int ghash_export(struct shash_desc *desc, void *out)
+{
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	u8 *dst = out;
 
-		do {
-			int chunk = min(blocks, MAX_BLOCKS);
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+	return 0;
+}
 
-			ghash_do_simd_update(chunk, ctx->digest, src, key,
-					     partial ? ctx->buf : NULL,
-					     pmull_ghash_update_p8);
+static int ghash_import(struct shash_desc *desc, const void *in)
+{
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	const u8 *src = in;
 
-			blocks -= chunk;
-			src += chunk * GHASH_BLOCK_SIZE;
-			partial = 0;
-		} while (unlikely(blocks > 0));
-	}
-	if (len)
-		memcpy(ctx->buf + partial, src, len);
+	ctx->digest[1] = get_unaligned_be64(src);
+	ctx->digest[0] = get_unaligned_be64(src + 8);
 	return 0;
 }
 
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *dst)
 {
-	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
-
-	if (partial) {
-		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+	struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	struct ghash_key *key = crypto_shash_ctx(desc->tfm);
 
-		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
 
-		ghash_do_simd_update(1, ctx->digest, ctx->buf, key, NULL,
+		memcpy(buf, src, len);
+		ghash_do_simd_update(1, ctx->digest, src, key, NULL,
 				     pmull_ghash_update_p8);
+		memzero_explicit(buf, sizeof(buf));
 	}
-	put_unaligned_be64(ctx->digest[1], dst);
-	put_unaligned_be64(ctx->digest[0], dst + 8);
-
-	memzero_explicit(ctx, sizeof(*ctx));
-	return 0;
+	return ghash_export(desc, dst);
 }
 
 static void ghash_reflect(u64 h[], const be128 *k)
@@ -205,6 +170,7 @@ static struct shash_alg ghash_alg = {
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
 	.base.cra_priority	= 150,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
@@ -212,9 +178,12 @@ static struct shash_alg ghash_alg = {
 	.digestsize		= GHASH_DIGEST_SIZE,
 	.init			= ghash_init,
 	.update			= ghash_update,
-	.final			= ghash_final,
+	.finup			= ghash_finup,
 	.setkey			= ghash_setkey,
-	.descsize		= sizeof(struct ghash_desc_ctx),
+	.export			= ghash_export,
+	.import			= ghash_import,
+	.descsize		= sizeof(struct arm_ghash_desc_ctx),
+	.statesize		= sizeof(struct ghash_desc_ctx),
 };
 
 static int num_rounds(struct crypto_aes_ctx *ctx)
@@ -308,21 +277,12 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[], u32 len)
 	scatterwalk_start(&walk, req->src);
 
 	do {
-		u32 n = scatterwalk_clamp(&walk, len);
-		u8 *p;
-
-		if (!n) {
-			scatterwalk_start(&walk, sg_next(walk.sg));
-			n = scatterwalk_clamp(&walk, len);
-		}
-		p = scatterwalk_map(&walk);
+		unsigned int n;
 
-		gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
+		n = scatterwalk_next(&walk, len);
+		gcm_update_mac(dg, walk.addr, n, buf, &buf_count, ctx);
+		scatterwalk_done_src(&walk, n);
 		len -= n;
-
-		scatterwalk_unmap(p);
-		scatterwalk_advance(&walk, n);
-		scatterwalk_done(&walk, 0, len);
 	} while (len);
 
 	if (buf_count) {
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
deleted file mode 100644
index 18883ea438f3..000000000000
--- a/arch/arm64/crypto/poly1305-glue.c
+++ /dev/null
@@ -1,232 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/jump_label.h>
-#include <linux/module.h>
-
-asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
-asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	poly1305_init_arm64(&dctx->h, key);
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static int neon_poly1305_init(struct shash_desc *desc)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	dctx->buflen = 0;
-	dctx->rset = 0;
-	dctx->sset = false;
-
-	return 0;
-}
-
-static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
-				 u32 len, u32 hibit, bool do_neon)
-{
-	if (unlikely(!dctx->sset)) {
-		if (!dctx->rset) {
-			poly1305_init_arm64(&dctx->h, src);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (len >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(src +  0);
-			dctx->s[1] = get_unaligned_le32(src +  4);
-			dctx->s[2] = get_unaligned_le32(src +  8);
-			dctx->s[3] = get_unaligned_le32(src + 12);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-		if (len < POLY1305_BLOCK_SIZE)
-			return;
-	}
-
-	len &= ~(POLY1305_BLOCK_SIZE - 1);
-
-	if (static_branch_likely(&have_neon) && likely(do_neon))
-		poly1305_blocks_neon(&dctx->h, src, len, hibit);
-	else
-		poly1305_blocks(&dctx->h, src, len, hibit);
-}
-
-static void neon_poly1305_do_update(struct poly1305_desc_ctx *dctx,
-				    const u8 *src, u32 len, bool do_neon)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		len -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			neon_poly1305_blocks(dctx, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1, false);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(len >= POLY1305_BLOCK_SIZE)) {
-		neon_poly1305_blocks(dctx, src, len, 1, do_neon);
-		src += round_down(len, POLY1305_BLOCK_SIZE);
-		len %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(len)) {
-		dctx->buflen = len;
-		memcpy(dctx->buf, src, len);
-	}
-}
-
-static int neon_poly1305_update(struct shash_desc *desc,
-				const u8 *src, unsigned int srclen)
-{
-	bool do_neon = crypto_simd_usable() && srclen > 128;
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (static_branch_likely(&have_neon) && do_neon)
-		kernel_neon_begin();
-	neon_poly1305_do_update(dctx, src, srclen, do_neon);
-	if (static_branch_likely(&have_neon) && do_neon)
-		kernel_neon_end();
-	return 0;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
-
-		if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
-			do {
-				unsigned int todo = min_t(unsigned int, len, SZ_4K);
-
-				kernel_neon_begin();
-				poly1305_blocks_neon(&dctx->h, src, todo, 1);
-				kernel_neon_end();
-
-				len -= todo;
-				src += todo;
-			} while (len);
-		} else {
-			poly1305_blocks(&dctx->h, src, len, 1);
-			src += len;
-		}
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit(&dctx->h, dst, dctx->s);
-	memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int neon_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(!dctx->sset))
-		return -ENOKEY;
-
-	poly1305_final_arch(dctx, dst);
-	return 0;
-}
-
-static struct shash_alg neon_poly1305_alg = {
-	.init			= neon_poly1305_init,
-	.update			= neon_poly1305_update,
-	.final			= neon_poly1305_final,
-	.digestsize		= POLY1305_DIGEST_SIZE,
-	.descsize		= sizeof(struct poly1305_desc_ctx),
-
-	.base.cra_name		= "poly1305",
-	.base.cra_driver_name	= "poly1305-neon",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-};
-
-static int __init neon_poly1305_mod_init(void)
-{
-	if (!cpu_have_named_feature(ASIMD))
-		return 0;
-
-	static_branch_enable(&have_neon);
-
-	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
-		crypto_register_shash(&neon_poly1305_alg) : 0;
-}
-
-static void __exit neon_poly1305_mod_exit(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && cpu_have_named_feature(ASIMD))
-		crypto_unregister_shash(&neon_poly1305_alg);
-}
-
-module_init(neon_poly1305_mod_init);
-module_exit(neon_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Poly1305 transform using NEON instructions");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm64/crypto/polyval-ce-glue.c b/arch/arm64/crypto/polyval-ce-glue.c
index 0a3b5718df85..c4e653688ea0 100644
--- a/arch/arm64/crypto/polyval-ce-glue.c
+++ b/arch/arm64/crypto/polyval-ce-glue.c
@@ -15,17 +15,15 @@
  * ARMv8 Crypto Extensions instructions to implement the finite field operations.
  */
 
-#include <crypto/algapi.h>
+#include <asm/neon.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/polyval.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
+#include <crypto/utils.h>
+#include <linux/cpufeature.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/cpufeature.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
+#include <linux/string.h>
 
 #define NUM_KEY_POWERS	8
 
@@ -38,7 +36,6 @@ struct polyval_tfm_ctx {
 
 struct polyval_desc_ctx {
 	u8 buffer[POLYVAL_BLOCK_SIZE];
-	u32 bytes;
 };
 
 asmlinkage void pmull_polyval_update(const struct polyval_tfm_ctx *keys,
@@ -48,25 +45,16 @@ asmlinkage void pmull_polyval_mul(u8 *op1, const u8 *op2);
 static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator)
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_neon_begin();
-		pmull_polyval_update(keys, in, nblocks, accumulator);
-		kernel_neon_end();
-	} else {
-		polyval_update_non4k(keys->key_powers[NUM_KEY_POWERS-1], in,
-			nblocks, accumulator);
-	}
+	kernel_neon_begin();
+	pmull_polyval_update(keys, in, nblocks, accumulator);
+	kernel_neon_end();
 }
 
 static void internal_polyval_mul(u8 *op1, const u8 *op2)
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_neon_begin();
-		pmull_polyval_mul(op1, op2);
-		kernel_neon_end();
-	} else {
-		polyval_mul_non4k(op1, op2);
-	}
+	kernel_neon_begin();
+	pmull_polyval_mul(op1, op2);
+	kernel_neon_end();
 }
 
 static int polyval_arm64_setkey(struct crypto_shash *tfm,
@@ -103,49 +91,27 @@ static int polyval_arm64_update(struct shash_desc *desc,
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
 	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
-	u8 *pos;
 	unsigned int nblocks;
-	unsigned int n;
-
-	if (dctx->bytes) {
-		n = min(srclen, dctx->bytes);
-		pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes;
-
-		dctx->bytes -= n;
-		srclen -= n;
 
-		while (n--)
-			*pos++ ^= *src++;
-
-		if (!dctx->bytes)
-			internal_polyval_mul(dctx->buffer,
-					    tctx->key_powers[NUM_KEY_POWERS-1]);
-	}
-
-	while (srclen >= POLYVAL_BLOCK_SIZE) {
+	do {
 		/* allow rescheduling every 4K bytes */
 		nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
 		internal_polyval_update(tctx, src, nblocks, dctx->buffer);
 		srclen -= nblocks * POLYVAL_BLOCK_SIZE;
 		src += nblocks * POLYVAL_BLOCK_SIZE;
-	}
+	} while (srclen >= POLYVAL_BLOCK_SIZE);
 
-	if (srclen) {
-		dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
-		pos = dctx->buffer;
-		while (srclen--)
-			*pos++ ^= *src++;
-	}
-
-	return 0;
+	return srclen;
 }
 
-static int polyval_arm64_final(struct shash_desc *desc, u8 *dst)
+static int polyval_arm64_finup(struct shash_desc *desc, const u8 *src,
+			       unsigned int len, u8 *dst)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
 	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 
-	if (dctx->bytes) {
+	if (len) {
+		crypto_xor(dctx->buffer, src, len);
 		internal_polyval_mul(dctx->buffer,
 				     tctx->key_powers[NUM_KEY_POWERS-1]);
 	}
@@ -159,13 +125,14 @@ static struct shash_alg polyval_alg = {
 	.digestsize	= POLYVAL_DIGEST_SIZE,
 	.init		= polyval_arm64_init,
 	.update		= polyval_arm64_update,
-	.final		= polyval_arm64_final,
+	.finup		= polyval_arm64_finup,
 	.setkey		= polyval_arm64_setkey,
 	.descsize	= sizeof(struct polyval_desc_ctx),
 	.base		= {
 		.cra_name		= "polyval",
 		.cra_driver_name	= "polyval-ce",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct polyval_tfm_ctx),
 		.cra_module		= THIS_MODULE,
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index cbd14f208f83..65b6980817e5 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -7,14 +7,14 @@
 
 #include <asm/neon.h>
 #include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
 
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
@@ -56,79 +56,49 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 
-	if (!crypto_simd_usable())
-		return crypto_sha1_update(desc, data, len);
-
 	sctx->finalize = 0;
-	sha1_base_do_update(desc, data, len, sha1_ce_transform);
-
-	return 0;
+	return sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
 }
 
 static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len;
-
-	if (!crypto_simd_usable())
-		return crypto_sha1_finup(desc, data, len, out);
+	bool finalized = false;
 
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
 	 */
-	sctx->finalize = finalize;
-
-	sha1_base_do_update(desc, data, len, sha1_ce_transform);
-	if (!finalize)
-		sha1_base_do_finalize(desc, sha1_ce_transform);
-	return sha1_base_finish(desc, out);
-}
-
-static int sha1_ce_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable())
-		return crypto_sha1_finup(desc, NULL, 0, out);
-
-	sctx->finalize = 0;
-	sha1_base_do_finalize(desc, sha1_ce_transform);
+	if (len >= SHA1_BLOCK_SIZE) {
+		unsigned int remain = len - round_down(len, SHA1_BLOCK_SIZE);
+
+		finalized = !remain;
+		sctx->finalize = finalized;
+		sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
+		data += len - remain;
+		len = remain;
+	}
+	if (!finalized) {
+		sctx->finalize = 0;
+		sha1_base_do_finup(desc, data, len, sha1_ce_transform);
+	}
 	return sha1_base_finish(desc, out);
 }
 
-static int sha1_ce_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, &sctx->sst, sizeof(struct sha1_state));
-	return 0;
-}
-
-static int sha1_ce_import(struct shash_desc *desc, const void *in)
-{
-	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(&sctx->sst, in, sizeof(struct sha1_state));
-	sctx->finalize = 0;
-	return 0;
-}
-
 static struct shash_alg alg = {
 	.init			= sha1_base_init,
 	.update			= sha1_ce_update,
-	.final			= sha1_ce_final,
 	.finup			= sha1_ce_finup,
-	.import			= sha1_ce_import,
-	.export			= sha1_ce_export,
 	.descsize		= sizeof(struct sha1_ce_state),
-	.statesize		= sizeof(struct sha1_state),
+	.statesize		= SHA1_STATE_SIZE,
 	.digestsize		= SHA1_DIGEST_SIZE,
 	.base			= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-ce",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					  CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
deleted file mode 100644
index 6b4866a88ded..000000000000
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ /dev/null
@@ -1,192 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/module.h>
-
-MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha256");
-
-struct sha256_ce_state {
-	struct sha256_state	sst;
-	u32			finalize;
-};
-
-extern const u32 sha256_ce_offsetof_count;
-extern const u32 sha256_ce_offsetof_finalize;
-
-asmlinkage int __sha256_ce_transform(struct sha256_ce_state *sst, u8 const *src,
-				     int blocks);
-
-static void sha256_ce_transform(struct sha256_state *sst, u8 const *src,
-				int blocks)
-{
-	while (blocks) {
-		int rem;
-
-		kernel_neon_begin();
-		rem = __sha256_ce_transform(container_of(sst,
-							 struct sha256_ce_state,
-							 sst), src, blocks);
-		kernel_neon_end();
-		src += (blocks - rem) * SHA256_BLOCK_SIZE;
-		blocks = rem;
-	}
-}
-
-const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
-					      sst.count);
-const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
-						 finalize);
-
-asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks);
-
-static void sha256_arm64_transform(struct sha256_state *sst, u8 const *src,
-				   int blocks)
-{
-	sha256_block_data_order(sst->state, src, blocks);
-}
-
-static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
-			    unsigned int len)
-{
-	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable())
-		return sha256_base_do_update(desc, data, len,
-					     sha256_arm64_transform);
-
-	sctx->finalize = 0;
-	sha256_base_do_update(desc, data, len, sha256_ce_transform);
-
-	return 0;
-}
-
-static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
-			   unsigned int len, u8 *out)
-{
-	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len;
-
-	if (!crypto_simd_usable()) {
-		if (len)
-			sha256_base_do_update(desc, data, len,
-					      sha256_arm64_transform);
-		sha256_base_do_finalize(desc, sha256_arm64_transform);
-		return sha256_base_finish(desc, out);
-	}
-
-	/*
-	 * Allow the asm code to perform the finalization if there is no
-	 * partial data and the input is a round multiple of the block size.
-	 */
-	sctx->finalize = finalize;
-
-	sha256_base_do_update(desc, data, len, sha256_ce_transform);
-	if (!finalize)
-		sha256_base_do_finalize(desc, sha256_ce_transform);
-	return sha256_base_finish(desc, out);
-}
-
-static int sha256_ce_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable()) {
-		sha256_base_do_finalize(desc, sha256_arm64_transform);
-		return sha256_base_finish(desc, out);
-	}
-
-	sctx->finalize = 0;
-	sha256_base_do_finalize(desc, sha256_ce_transform);
-	return sha256_base_finish(desc, out);
-}
-
-static int sha256_ce_digest(struct shash_desc *desc, const u8 *data,
-			    unsigned int len, u8 *out)
-{
-	sha256_base_init(desc);
-	return sha256_ce_finup(desc, data, len, out);
-}
-
-static int sha256_ce_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, &sctx->sst, sizeof(struct sha256_state));
-	return 0;
-}
-
-static int sha256_ce_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(&sctx->sst, in, sizeof(struct sha256_state));
-	sctx->finalize = 0;
-	return 0;
-}
-
-static struct shash_alg algs[] = { {
-	.init			= sha224_base_init,
-	.update			= sha256_ce_update,
-	.final			= sha256_ce_final,
-	.finup			= sha256_ce_finup,
-	.export			= sha256_ce_export,
-	.import			= sha256_ce_import,
-	.descsize		= sizeof(struct sha256_ce_state),
-	.statesize		= sizeof(struct sha256_state),
-	.digestsize		= SHA224_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha224",
-		.cra_driver_name	= "sha224-ce",
-		.cra_priority		= 200,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-}, {
-	.init			= sha256_base_init,
-	.update			= sha256_ce_update,
-	.final			= sha256_ce_final,
-	.finup			= sha256_ce_finup,
-	.digest			= sha256_ce_digest,
-	.export			= sha256_ce_export,
-	.import			= sha256_ce_import,
-	.descsize		= sizeof(struct sha256_ce_state),
-	.statesize		= sizeof(struct sha256_state),
-	.digestsize		= SHA256_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha256",
-		.cra_driver_name	= "sha256-ce",
-		.cra_priority		= 200,
-		.cra_blocksize		= SHA256_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-} };
-
-static int __init sha2_ce_mod_init(void)
-{
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha2_ce_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_cpu_feature_match(SHA2, sha2_ce_mod_init);
-module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
deleted file mode 100644
index 35356987cc1e..000000000000
--- a/arch/arm64/crypto/sha256-glue.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Linux/arm64 port of the OpenSSL SHA256 implementation for AArch64
- *
- * Copyright (c) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash for arm64");
-MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha256");
-
-asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
-					unsigned int num_blks);
-EXPORT_SYMBOL(sha256_block_data_order);
-
-static void sha256_arm64_transform(struct sha256_state *sst, u8 const *src,
-				   int blocks)
-{
-	sha256_block_data_order(sst->state, src, blocks);
-}
-
-asmlinkage void sha256_block_neon(u32 *digest, const void *data,
-				  unsigned int num_blks);
-
-static void sha256_neon_transform(struct sha256_state *sst, u8 const *src,
-				  int blocks)
-{
-	sha256_block_neon(sst->state, src, blocks);
-}
-
-static int crypto_sha256_arm64_update(struct shash_desc *desc, const u8 *data,
-				      unsigned int len)
-{
-	return sha256_base_do_update(desc, data, len, sha256_arm64_transform);
-}
-
-static int crypto_sha256_arm64_finup(struct shash_desc *desc, const u8 *data,
-				     unsigned int len, u8 *out)
-{
-	if (len)
-		sha256_base_do_update(desc, data, len, sha256_arm64_transform);
-	sha256_base_do_finalize(desc, sha256_arm64_transform);
-
-	return sha256_base_finish(desc, out);
-}
-
-static int crypto_sha256_arm64_final(struct shash_desc *desc, u8 *out)
-{
-	return crypto_sha256_arm64_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg algs[] = { {
-	.digestsize		= SHA256_DIGEST_SIZE,
-	.init			= sha256_base_init,
-	.update			= crypto_sha256_arm64_update,
-	.final			= crypto_sha256_arm64_final,
-	.finup			= crypto_sha256_arm64_finup,
-	.descsize		= sizeof(struct sha256_state),
-	.base.cra_name		= "sha256",
-	.base.cra_driver_name	= "sha256-arm64",
-	.base.cra_priority	= 125,
-	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-}, {
-	.digestsize		= SHA224_DIGEST_SIZE,
-	.init			= sha224_base_init,
-	.update			= crypto_sha256_arm64_update,
-	.final			= crypto_sha256_arm64_final,
-	.finup			= crypto_sha256_arm64_finup,
-	.descsize		= sizeof(struct sha256_state),
-	.base.cra_name		= "sha224",
-	.base.cra_driver_name	= "sha224-arm64",
-	.base.cra_priority	= 125,
-	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-} };
-
-static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
-			      unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable())
-		return sha256_base_do_update(desc, data, len,
-				sha256_arm64_transform);
-
-	while (len > 0) {
-		unsigned int chunk = len;
-
-		/*
-		 * Don't hog the CPU for the entire time it takes to process all
-		 * input when running on a preemptible kernel, but process the
-		 * data block by block instead.
-		 */
-		if (IS_ENABLED(CONFIG_PREEMPTION) &&
-		    chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
-			chunk = SHA256_BLOCK_SIZE -
-				sctx->count % SHA256_BLOCK_SIZE;
-
-		kernel_neon_begin();
-		sha256_base_do_update(desc, data, chunk, sha256_neon_transform);
-		kernel_neon_end();
-		data += chunk;
-		len -= chunk;
-	}
-	return 0;
-}
-
-static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *out)
-{
-	if (!crypto_simd_usable()) {
-		if (len)
-			sha256_base_do_update(desc, data, len,
-				sha256_arm64_transform);
-		sha256_base_do_finalize(desc, sha256_arm64_transform);
-	} else {
-		if (len)
-			sha256_update_neon(desc, data, len);
-		kernel_neon_begin();
-		sha256_base_do_finalize(desc, sha256_neon_transform);
-		kernel_neon_end();
-	}
-	return sha256_base_finish(desc, out);
-}
-
-static int sha256_final_neon(struct shash_desc *desc, u8 *out)
-{
-	return sha256_finup_neon(desc, NULL, 0, out);
-}
-
-static struct shash_alg neon_algs[] = { {
-	.digestsize		= SHA256_DIGEST_SIZE,
-	.init			= sha256_base_init,
-	.update			= sha256_update_neon,
-	.final			= sha256_final_neon,
-	.finup			= sha256_finup_neon,
-	.descsize		= sizeof(struct sha256_state),
-	.base.cra_name		= "sha256",
-	.base.cra_driver_name	= "sha256-arm64-neon",
-	.base.cra_priority	= 150,
-	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-}, {
-	.digestsize		= SHA224_DIGEST_SIZE,
-	.init			= sha224_base_init,
-	.update			= sha256_update_neon,
-	.final			= sha256_final_neon,
-	.finup			= sha256_finup_neon,
-	.descsize		= sizeof(struct sha256_state),
-	.base.cra_name		= "sha224",
-	.base.cra_driver_name	= "sha224-arm64-neon",
-	.base.cra_priority	= 150,
-	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-} };
-
-static int __init sha256_mod_init(void)
-{
-	int ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
-	if (ret)
-		return ret;
-
-	if (cpu_have_named_feature(ASIMD)) {
-		ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
-		if (ret)
-			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-	}
-	return ret;
-}
-
-static void __exit sha256_mod_fini(void)
-{
-	if (cpu_have_named_feature(ASIMD))
-		crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha256_mod_init);
-module_exit(sha256_mod_fini);
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index 5662c3ac49e9..b4f1001046c9 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -12,13 +12,13 @@
 #include <asm/hwcap.h>
 #include <asm/neon.h>
 #include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sha3.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
 MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
@@ -35,74 +35,55 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
 		       unsigned int len)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
-	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
-
-	if (!crypto_simd_usable())
-		return crypto_sha3_update(desc, data, len);
-
-	if ((sctx->partial + len) >= sctx->rsiz) {
-		int blocks;
-
-		if (sctx->partial) {
-			int p = sctx->rsiz - sctx->partial;
-
-			memcpy(sctx->buf + sctx->partial, data, p);
-			kernel_neon_begin();
-			sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
-			kernel_neon_end();
-
-			data += p;
-			len -= p;
-			sctx->partial = 0;
-		}
-
-		blocks = len / sctx->rsiz;
-		len %= sctx->rsiz;
-
-		while (blocks) {
-			int rem;
-
-			kernel_neon_begin();
-			rem = sha3_ce_transform(sctx->st, data, blocks,
-						digest_size);
-			kernel_neon_end();
-			data += (blocks - rem) * sctx->rsiz;
-			blocks = rem;
-		}
-	}
-
-	if (len) {
-		memcpy(sctx->buf + sctx->partial, data, len);
-		sctx->partial += len;
-	}
-	return 0;
+	struct crypto_shash *tfm = desc->tfm;
+	unsigned int bs, ds;
+	int blocks;
+
+	ds = crypto_shash_digestsize(tfm);
+	bs = crypto_shash_blocksize(tfm);
+	blocks = len / bs;
+	len -= blocks * bs;
+	do {
+		int rem;
+
+		kernel_neon_begin();
+		rem = sha3_ce_transform(sctx->st, data, blocks, ds);
+		kernel_neon_end();
+		data += (blocks - rem) * bs;
+		blocks = rem;
+	} while (blocks);
+	return len;
 }
 
-static int sha3_final(struct shash_desc *desc, u8 *out)
+static int sha3_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+		      u8 *out)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
-	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+	struct crypto_shash *tfm = desc->tfm;
 	__le64 *digest = (__le64 *)out;
+	u8 block[SHA3_224_BLOCK_SIZE];
+	unsigned int bs, ds;
 	int i;
 
-	if (!crypto_simd_usable())
-		return crypto_sha3_final(desc, out);
+	ds = crypto_shash_digestsize(tfm);
+	bs = crypto_shash_blocksize(tfm);
+	memcpy(block, src, len);
 
-	sctx->buf[sctx->partial++] = 0x06;
-	memset(sctx->buf + sctx->partial, 0, sctx->rsiz - sctx->partial);
-	sctx->buf[sctx->rsiz - 1] |= 0x80;
+	block[len++] = 0x06;
+	memset(block + len, 0, bs - len);
+	block[bs - 1] |= 0x80;
 
 	kernel_neon_begin();
-	sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+	sha3_ce_transform(sctx->st, block, 1, ds);
 	kernel_neon_end();
+	memzero_explicit(block , sizeof(block));
 
-	for (i = 0; i < digest_size / 8; i++)
+	for (i = 0; i < ds / 8; i++)
 		put_unaligned_le64(sctx->st[i], digest++);
 
-	if (digest_size & 4)
+	if (ds & 4)
 		put_unaligned_le32(sctx->st[i], (__le32 *)digest);
 
-	memzero_explicit(sctx, sizeof(*sctx));
 	return 0;
 }
 
@@ -110,10 +91,11 @@ static struct shash_alg algs[] = { {
 	.digestsize		= SHA3_224_DIGEST_SIZE,
 	.init			= crypto_sha3_init,
 	.update			= sha3_update,
-	.final			= sha3_final,
-	.descsize		= sizeof(struct sha3_state),
+	.finup			= sha3_finup,
+	.descsize		= SHA3_STATE_SIZE,
 	.base.cra_name		= "sha3-224",
 	.base.cra_driver_name	= "sha3-224-ce",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -121,10 +103,11 @@ static struct shash_alg algs[] = { {
 	.digestsize		= SHA3_256_DIGEST_SIZE,
 	.init			= crypto_sha3_init,
 	.update			= sha3_update,
-	.final			= sha3_final,
-	.descsize		= sizeof(struct sha3_state),
+	.finup			= sha3_finup,
+	.descsize		= SHA3_STATE_SIZE,
 	.base.cra_name		= "sha3-256",
 	.base.cra_driver_name	= "sha3-256-ce",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -132,10 +115,11 @@ static struct shash_alg algs[] = { {
 	.digestsize		= SHA3_384_DIGEST_SIZE,
 	.init			= crypto_sha3_init,
 	.update			= sha3_update,
-	.final			= sha3_final,
-	.descsize		= sizeof(struct sha3_state),
+	.finup			= sha3_finup,
+	.descsize		= SHA3_STATE_SIZE,
 	.base.cra_name		= "sha3-384",
 	.base.cra_driver_name	= "sha3-384-ce",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -143,10 +127,11 @@ static struct shash_alg algs[] = { {
 	.digestsize		= SHA3_512_DIGEST_SIZE,
 	.init			= crypto_sha3_init,
 	.update			= sha3_update,
-	.final			= sha3_final,
-	.descsize		= sizeof(struct sha3_state),
+	.finup			= sha3_finup,
+	.descsize		= SHA3_STATE_SIZE,
 	.base.cra_name		= "sha3-512",
 	.base.cra_driver_name	= "sha3-512-ce",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index 071f64293227..6fb3001fa2c9 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -10,14 +10,11 @@
  */
 
 #include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
 MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions");
@@ -29,12 +26,10 @@ MODULE_ALIAS_CRYPTO("sha512");
 asmlinkage int __sha512_ce_transform(struct sha512_state *sst, u8 const *src,
 				     int blocks);
 
-asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
-
 static void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
 				int blocks)
 {
-	while (blocks) {
+	do {
 		int rem;
 
 		kernel_neon_begin();
@@ -42,67 +37,47 @@ static void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
 		kernel_neon_end();
 		src += (blocks - rem) * SHA512_BLOCK_SIZE;
 		blocks = rem;
-	}
-}
-
-static void sha512_arm64_transform(struct sha512_state *sst, u8 const *src,
-				   int blocks)
-{
-	sha512_block_data_order(sst->state, src, blocks);
+	} while (blocks);
 }
 
 static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
-	sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
-						   : sha512_arm64_transform;
-
-	sha512_base_do_update(desc, data, len, fn);
-	return 0;
+	return sha512_base_do_update_blocks(desc, data, len,
+					    sha512_ce_transform);
 }
 
 static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
-						   : sha512_arm64_transform;
-
-	sha512_base_do_update(desc, data, len, fn);
-	sha512_base_do_finalize(desc, fn);
-	return sha512_base_finish(desc, out);
-}
-
-static int sha512_ce_final(struct shash_desc *desc, u8 *out)
-{
-	sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
-						   : sha512_arm64_transform;
-
-	sha512_base_do_finalize(desc, fn);
+	sha512_base_do_finup(desc, data, len, sha512_ce_transform);
 	return sha512_base_finish(desc, out);
 }
 
 static struct shash_alg algs[] = { {
 	.init			= sha384_base_init,
 	.update			= sha512_ce_update,
-	.final			= sha512_ce_final,
 	.finup			= sha512_ce_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA384_DIGEST_SIZE,
 	.base.cra_name		= "sha384",
 	.base.cra_driver_name	= "sha384-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
 	.init			= sha512_base_init,
 	.update			= sha512_ce_update,
-	.final			= sha512_ce_final,
 	.finup			= sha512_ce_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.digestsize		= SHA512_DIGEST_SIZE,
 	.base.cra_name		= "sha512",
 	.base.cra_driver_name	= "sha512-ce",
 	.base.cra_priority	= 200,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index 62f129dea83d..15aa9d8b7b2c 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -6,11 +6,10 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <linux/types.h>
-#include <linux/string.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <asm/neon.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash for arm64");
 MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
@@ -19,59 +18,53 @@ MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("sha384");
 MODULE_ALIAS_CRYPTO("sha512");
 
-asmlinkage void sha512_block_data_order(u64 *digest, const void *data,
-					unsigned int num_blks);
-EXPORT_SYMBOL(sha512_block_data_order);
+asmlinkage void sha512_blocks_arch(u64 *digest, const void *data,
+				   unsigned int num_blks);
 
 static void sha512_arm64_transform(struct sha512_state *sst, u8 const *src,
 				   int blocks)
 {
-	sha512_block_data_order(sst->state, src, blocks);
+	sha512_blocks_arch(sst->state, src, blocks);
 }
 
 static int sha512_update(struct shash_desc *desc, const u8 *data,
 			 unsigned int len)
 {
-	return sha512_base_do_update(desc, data, len, sha512_arm64_transform);
+	return sha512_base_do_update_blocks(desc, data, len,
+					    sha512_arm64_transform);
 }
 
 static int sha512_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out)
 {
-	if (len)
-		sha512_base_do_update(desc, data, len, sha512_arm64_transform);
-	sha512_base_do_finalize(desc, sha512_arm64_transform);
-
+	sha512_base_do_finup(desc, data, len, sha512_arm64_transform);
 	return sha512_base_finish(desc, out);
 }
 
-static int sha512_final(struct shash_desc *desc, u8 *out)
-{
-	return sha512_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg algs[] = { {
 	.digestsize		= SHA512_DIGEST_SIZE,
 	.init			= sha512_base_init,
 	.update			= sha512_update,
-	.final			= sha512_final,
 	.finup			= sha512_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.base.cra_name		= "sha512",
 	.base.cra_driver_name	= "sha512-arm64",
 	.base.cra_priority	= 150,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
 	.digestsize		= SHA384_DIGEST_SIZE,
 	.init			= sha384_base_init,
 	.update			= sha512_update,
-	.final			= sha512_final,
 	.finup			= sha512_finup,
-	.descsize		= sizeof(struct sha512_state),
+	.descsize		= SHA512_STATE_SIZE,
 	.base.cra_name		= "sha384",
 	.base.cra_driver_name	= "sha384-arm64",
 	.base.cra_priority	= 150,
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SHA384_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
index 1a71788c4cda..eac6f5fa0abe 100644
--- a/arch/arm64/crypto/sm3-ce-glue.c
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -6,14 +6,11 @@
  */
 
 #include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sm3.h>
 #include <crypto/sm3_base.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
 MODULE_DESCRIPTION("SM3 secure hash using ARMv8 Crypto Extensions");
@@ -26,50 +23,20 @@ asmlinkage void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
 static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
 			 unsigned int len)
 {
-	if (!crypto_simd_usable()) {
-		sm3_update(shash_desc_ctx(desc), data, len);
-		return 0;
-	}
+	int remain;
 
 	kernel_neon_begin();
-	sm3_base_do_update(desc, data, len, sm3_ce_transform);
+	remain = sm3_base_do_update_blocks(desc, data, len, sm3_ce_transform);
 	kernel_neon_end();
-
-	return 0;
-}
-
-static int sm3_ce_final(struct shash_desc *desc, u8 *out)
-{
-	if (!crypto_simd_usable()) {
-		sm3_final(shash_desc_ctx(desc), out);
-		return 0;
-	}
-
-	kernel_neon_begin();
-	sm3_base_do_finalize(desc, sm3_ce_transform);
-	kernel_neon_end();
-
-	return sm3_base_finish(desc, out);
+	return remain;
 }
 
 static int sm3_ce_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable()) {
-		struct sm3_state *sctx = shash_desc_ctx(desc);
-
-		if (len)
-			sm3_update(sctx, data, len);
-		sm3_final(sctx, out);
-		return 0;
-	}
-
 	kernel_neon_begin();
-	if (len)
-		sm3_base_do_update(desc, data, len, sm3_ce_transform);
-	sm3_base_do_finalize(desc, sm3_ce_transform);
+	sm3_base_do_finup(desc, data, len, sm3_ce_transform);
 	kernel_neon_end();
-
 	return sm3_base_finish(desc, out);
 }
 
@@ -77,11 +44,12 @@ static struct shash_alg sm3_alg = {
 	.digestsize		= SM3_DIGEST_SIZE,
 	.init			= sm3_base_init,
 	.update			= sm3_ce_update,
-	.final			= sm3_ce_final,
 	.finup			= sm3_ce_finup,
-	.descsize		= sizeof(struct sm3_state),
+	.descsize		= SM3_STATE_SIZE,
 	.base.cra_name		= "sm3",
 	.base.cra_driver_name	= "sm3-ce",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SM3_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 400,
diff --git a/arch/arm64/crypto/sm3-neon-glue.c b/arch/arm64/crypto/sm3-neon-glue.c
index 8dd71ce79b69..6c4611a503a3 100644
--- a/arch/arm64/crypto/sm3-neon-glue.c
+++ b/arch/arm64/crypto/sm3-neon-glue.c
@@ -6,14 +6,11 @@
  */
 
 #include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/sm3.h>
 #include <crypto/sm3_base.h>
 #include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
 
@@ -23,50 +20,20 @@ asmlinkage void sm3_neon_transform(struct sm3_state *sst, u8 const *src,
 static int sm3_neon_update(struct shash_desc *desc, const u8 *data,
 			   unsigned int len)
 {
-	if (!crypto_simd_usable()) {
-		sm3_update(shash_desc_ctx(desc), data, len);
-		return 0;
-	}
+	int remain;
 
 	kernel_neon_begin();
-	sm3_base_do_update(desc, data, len, sm3_neon_transform);
+	remain = sm3_base_do_update_blocks(desc, data, len, sm3_neon_transform);
 	kernel_neon_end();
-
-	return 0;
-}
-
-static int sm3_neon_final(struct shash_desc *desc, u8 *out)
-{
-	if (!crypto_simd_usable()) {
-		sm3_final(shash_desc_ctx(desc), out);
-		return 0;
-	}
-
-	kernel_neon_begin();
-	sm3_base_do_finalize(desc, sm3_neon_transform);
-	kernel_neon_end();
-
-	return sm3_base_finish(desc, out);
+	return remain;
 }
 
 static int sm3_neon_finup(struct shash_desc *desc, const u8 *data,
 			  unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable()) {
-		struct sm3_state *sctx = shash_desc_ctx(desc);
-
-		if (len)
-			sm3_update(sctx, data, len);
-		sm3_final(sctx, out);
-		return 0;
-	}
-
 	kernel_neon_begin();
-	if (len)
-		sm3_base_do_update(desc, data, len, sm3_neon_transform);
-	sm3_base_do_finalize(desc, sm3_neon_transform);
+	sm3_base_do_finup(desc, data, len, sm3_neon_transform);
 	kernel_neon_end();
-
 	return sm3_base_finish(desc, out);
 }
 
@@ -74,11 +41,12 @@ static struct shash_alg sm3_alg = {
 	.digestsize		= SM3_DIGEST_SIZE,
 	.init			= sm3_base_init,
 	.update			= sm3_neon_update,
-	.final			= sm3_neon_final,
 	.finup			= sm3_neon_finup,
-	.descsize		= sizeof(struct sm3_state),
+	.descsize		= SM3_STATE_SIZE,
 	.base.cra_name		= "sm3",
 	.base.cra_driver_name	= "sm3-neon",
+	.base.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				  CRYPTO_AHASH_ALG_FINUP_MAX,
 	.base.cra_blocksize	= SM3_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
diff --git a/arch/arm64/crypto/sm4-ce-ccm-glue.c b/arch/arm64/crypto/sm4-ce-ccm-glue.c
index 5e7e17bbec81..e9cc1c1364ec 100644
--- a/arch/arm64/crypto/sm4-ce-ccm-glue.c
+++ b/arch/arm64/crypto/sm4-ce-ccm-glue.c
@@ -112,17 +112,12 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 	scatterwalk_start(&walk, req->src);
 
 	do {
-		u32 n = scatterwalk_clamp(&walk, assoclen);
-		u8 *p, *ptr;
+		unsigned int n, orig_n;
+		const u8 *p;
 
-		if (!n) {
-			scatterwalk_start(&walk, sg_next(walk.sg));
-			n = scatterwalk_clamp(&walk, assoclen);
-		}
-
-		p = ptr = scatterwalk_map(&walk);
-		assoclen -= n;
-		scatterwalk_advance(&walk, n);
+		orig_n = scatterwalk_next(&walk, assoclen);
+		p = walk.addr;
+		n = orig_n;
 
 		while (n > 0) {
 			unsigned int l, nblocks;
@@ -136,9 +131,9 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 				} else {
 					nblocks = n / SM4_BLOCK_SIZE;
 					sm4_ce_cbcmac_update(ctx->rkey_enc,
-							     mac, ptr, nblocks);
+							     mac, p, nblocks);
 
-					ptr += nblocks * SM4_BLOCK_SIZE;
+					p += nblocks * SM4_BLOCK_SIZE;
 					n %= SM4_BLOCK_SIZE;
 
 					continue;
@@ -147,15 +142,15 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 
 			l = min(n, SM4_BLOCK_SIZE - len);
 			if (l) {
-				crypto_xor(mac + len, ptr, l);
+				crypto_xor(mac + len, p, l);
 				len += l;
-				ptr += l;
+				p += l;
 				n -= l;
 			}
 		}
 
-		scatterwalk_unmap(p);
-		scatterwalk_done(&walk, 0, assoclen);
+		scatterwalk_done_src(&walk, orig_n);
+		assoclen -= orig_n;
 	} while (assoclen);
 }
 
diff --git a/arch/arm64/crypto/sm4-ce-gcm-glue.c b/arch/arm64/crypto/sm4-ce-gcm-glue.c
index 73bfb6972d3a..c2ea3d5f690b 100644
--- a/arch/arm64/crypto/sm4-ce-gcm-glue.c
+++ b/arch/arm64/crypto/sm4-ce-gcm-glue.c
@@ -82,20 +82,15 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u8 ghash[])
 	scatterwalk_start(&walk, req->src);
 
 	do {
-		u32 n = scatterwalk_clamp(&walk, assoclen);
-		u8 *p, *ptr;
+		unsigned int n, orig_n;
+		const u8 *p;
 
-		if (!n) {
-			scatterwalk_start(&walk, sg_next(walk.sg));
-			n = scatterwalk_clamp(&walk, assoclen);
-		}
-
-		p = ptr = scatterwalk_map(&walk);
-		assoclen -= n;
-		scatterwalk_advance(&walk, n);
+		orig_n = scatterwalk_next(&walk, assoclen);
+		p = walk.addr;
+		n = orig_n;
 
 		if (n + buflen < GHASH_BLOCK_SIZE) {
-			memcpy(&buffer[buflen], ptr, n);
+			memcpy(&buffer[buflen], p, n);
 			buflen += n;
 		} else {
 			unsigned int nblocks;
@@ -103,8 +98,8 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u8 ghash[])
 			if (buflen) {
 				unsigned int l = GHASH_BLOCK_SIZE - buflen;
 
-				memcpy(&buffer[buflen], ptr, l);
-				ptr += l;
+				memcpy(&buffer[buflen], p, l);
+				p += l;
 				n -= l;
 
 				pmull_ghash_update(ctx->ghash_table, ghash,
@@ -114,17 +109,17 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u8 ghash[])
 			nblocks = n / GHASH_BLOCK_SIZE;
 			if (nblocks) {
 				pmull_ghash_update(ctx->ghash_table, ghash,
-						   ptr, nblocks);
-				ptr += nblocks * GHASH_BLOCK_SIZE;
+						   p, nblocks);
+				p += nblocks * GHASH_BLOCK_SIZE;
 			}
 
 			buflen = n % GHASH_BLOCK_SIZE;
 			if (buflen)
-				memcpy(&buffer[0], ptr, buflen);
+				memcpy(&buffer[0], p, buflen);
 		}
 
-		scatterwalk_unmap(p);
-		scatterwalk_done(&walk, 0, assoclen);
+		scatterwalk_done_src(&walk, orig_n);
+		assoclen -= orig_n;
 	} while (assoclen);
 
 	/* padding with '0' */
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index 43741bed874e..7a60e7b559dc 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -8,19 +8,18 @@
  * Copyright (C) 2022 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
  */
 
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
 #include <asm/neon.h>
-#include <asm/simd.h>
 #include <crypto/b128ops.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/xts.h>
 #include <crypto/sm4.h>
+#include <crypto/utils.h>
+#include <crypto/xts.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
 #define BYTES2BLKS(nbytes)	((nbytes) >> 4)
 
@@ -64,7 +63,6 @@ struct sm4_mac_tfm_ctx {
 };
 
 struct sm4_mac_desc_ctx {
-	unsigned int len;
 	u8 digest[SM4_BLOCK_SIZE];
 };
 
@@ -591,8 +589,6 @@ static int sm4_mac_init(struct shash_desc *desc)
 	struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
 	memset(ctx->digest, 0, SM4_BLOCK_SIZE);
-	ctx->len = 0;
-
 	return 0;
 }
 
@@ -601,87 +597,50 @@ static int sm4_mac_update(struct shash_desc *desc, const u8 *p,
 {
 	struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int l, nblocks;
-
-	if (len == 0)
-		return 0;
-
-	if (ctx->len || ctx->len + len < SM4_BLOCK_SIZE) {
-		l = min(len, SM4_BLOCK_SIZE - ctx->len);
-
-		crypto_xor(ctx->digest + ctx->len, p, l);
-		ctx->len += l;
-		len -= l;
-		p += l;
-	}
-
-	if (len && (ctx->len % SM4_BLOCK_SIZE) == 0) {
-		kernel_neon_begin();
-
-		if (len < SM4_BLOCK_SIZE && ctx->len == SM4_BLOCK_SIZE) {
-			sm4_ce_crypt_block(tctx->key.rkey_enc,
-					   ctx->digest, ctx->digest);
-			ctx->len = 0;
-		} else {
-			nblocks = len / SM4_BLOCK_SIZE;
-			len %= SM4_BLOCK_SIZE;
+	unsigned int nblocks = len / SM4_BLOCK_SIZE;
 
-			sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, p,
-					  nblocks, (ctx->len == SM4_BLOCK_SIZE),
-					  (len != 0));
-
-			p += nblocks * SM4_BLOCK_SIZE;
-
-			if (len == 0)
-				ctx->len = SM4_BLOCK_SIZE;
-		}
-
-		kernel_neon_end();
-
-		if (len) {
-			crypto_xor(ctx->digest, p, len);
-			ctx->len = len;
-		}
-	}
-
-	return 0;
+	len %= SM4_BLOCK_SIZE;
+	kernel_neon_begin();
+	sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, p,
+			  nblocks, false, true);
+	kernel_neon_end();
+	return len;
 }
 
-static int sm4_cmac_final(struct shash_desc *desc, u8 *out)
+static int sm4_cmac_finup(struct shash_desc *desc, const u8 *src,
+			  unsigned int len, u8 *out)
 {
 	struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
 	const u8 *consts = tctx->consts;
 
-	if (ctx->len != SM4_BLOCK_SIZE) {
-		ctx->digest[ctx->len] ^= 0x80;
+	crypto_xor(ctx->digest, src, len);
+	if (len != SM4_BLOCK_SIZE) {
+		ctx->digest[len] ^= 0x80;
 		consts += SM4_BLOCK_SIZE;
 	}
-
 	kernel_neon_begin();
 	sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, consts, 1,
 			  false, true);
 	kernel_neon_end();
-
 	memcpy(out, ctx->digest, SM4_BLOCK_SIZE);
-
 	return 0;
 }
 
-static int sm4_cbcmac_final(struct shash_desc *desc, u8 *out)
+static int sm4_cbcmac_finup(struct shash_desc *desc, const u8 *src,
+			    unsigned int len, u8 *out)
 {
 	struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	if (ctx->len) {
+	if (len) {
+		crypto_xor(ctx->digest, src, len);
 		kernel_neon_begin();
 		sm4_ce_crypt_block(tctx->key.rkey_enc, ctx->digest,
 				   ctx->digest);
 		kernel_neon_end();
 	}
-
 	memcpy(out, ctx->digest, SM4_BLOCK_SIZE);
-
 	return 0;
 }
 
@@ -691,6 +650,8 @@ static struct shash_alg sm4_mac_algs[] = {
 			.cra_name		= "cmac(sm4)",
 			.cra_driver_name	= "cmac-sm4-ce",
 			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+						  CRYPTO_AHASH_ALG_FINAL_NONZERO,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_mac_tfm_ctx)
 							+ SM4_BLOCK_SIZE * 2,
@@ -699,7 +660,7 @@ static struct shash_alg sm4_mac_algs[] = {
 		.digestsize	= SM4_BLOCK_SIZE,
 		.init		= sm4_mac_init,
 		.update		= sm4_mac_update,
-		.final		= sm4_cmac_final,
+		.finup		= sm4_cmac_finup,
 		.setkey		= sm4_cmac_setkey,
 		.descsize	= sizeof(struct sm4_mac_desc_ctx),
 	}, {
@@ -707,6 +668,8 @@ static struct shash_alg sm4_mac_algs[] = {
 			.cra_name		= "xcbc(sm4)",
 			.cra_driver_name	= "xcbc-sm4-ce",
 			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
+						  CRYPTO_AHASH_ALG_FINAL_NONZERO,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_mac_tfm_ctx)
 							+ SM4_BLOCK_SIZE * 2,
@@ -715,7 +678,7 @@ static struct shash_alg sm4_mac_algs[] = {
 		.digestsize	= SM4_BLOCK_SIZE,
 		.init		= sm4_mac_init,
 		.update		= sm4_mac_update,
-		.final		= sm4_cmac_final,
+		.finup		= sm4_cmac_finup,
 		.setkey		= sm4_xcbc_setkey,
 		.descsize	= sizeof(struct sm4_mac_desc_ctx),
 	}, {
@@ -723,14 +686,15 @@ static struct shash_alg sm4_mac_algs[] = {
 			.cra_name		= "cbcmac(sm4)",
 			.cra_driver_name	= "cbcmac-sm4-ce",
 			.cra_priority		= 400,
-			.cra_blocksize		= 1,
+			.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
+			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_mac_tfm_ctx),
 			.cra_module		= THIS_MODULE,
 		},
 		.digestsize	= SM4_BLOCK_SIZE,
 		.init		= sm4_mac_init,
 		.update		= sm4_mac_update,
-		.final		= sm4_cbcmac_final,
+		.finup		= sm4_cbcmac_finup,
 		.setkey		= sm4_cbcmac_setkey,
 		.descsize	= sizeof(struct sm4_mac_desc_ctx),
 	}
diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c
index 69004f619c57..e33a9e3c366a 100644
--- a/arch/arm64/hyperv/hv_core.c
+++ b/arch/arm64/hyperv/hv_core.c
@@ -54,6 +54,23 @@ u64 hv_do_fast_hypercall8(u16 code, u64 input)
 EXPORT_SYMBOL_GPL(hv_do_fast_hypercall8);
 
 /*
+ * hv_do_fast_hypercall16 -- Invoke the specified hypercall
+ * with arguments in registers instead of physical memory.
+ * Avoids the overhead of virt_to_phys for simple hypercalls.
+ */
+u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	struct arm_smccc_res	res;
+	u64			control;
+
+	control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+	arm_smccc_1_1_hvc(HV_FUNC_ID, control, input1, input2, &res);
+	return res.a0;
+}
+EXPORT_SYMBOL_GPL(hv_do_fast_hypercall16);
+
+/*
  * Set a single VP register to a 64-bit value.
  */
 void hv_set_vpreg(u32 msr, u64 value)
diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index fc49949b7df6..4e27cc29c79e 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -26,6 +26,7 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
 
 static int __init hyperv_init(void)
 {
@@ -61,6 +62,8 @@ static int __init hyperv_init(void)
 		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
 		ms_hyperv.misc_features);
 
+	hv_identify_partition_type();
+
 	ret = hv_common_init();
 	if (ret)
 		return ret;
@@ -72,6 +75,9 @@ static int __init hyperv_init(void)
 		return ret;
 	}
 
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
+		hv_get_partition_id();
+
 	ms_hyperv_late_init();
 
 	hyperv_initialized = true;
diff --git a/arch/arm64/include/asm/apple_m1_pmu.h b/arch/arm64/include/asm/apple_m1_pmu.h
index 99483b19b99f..02e05d05851f 100644
--- a/arch/arm64/include/asm/apple_m1_pmu.h
+++ b/arch/arm64/include/asm/apple_m1_pmu.h
@@ -37,6 +37,7 @@
 #define PMCR0_PMI_ENABLE_8_9	GENMASK(45, 44)
 
 #define SYS_IMP_APL_PMCR1_EL1	sys_reg(3, 1, 15, 1, 0)
+#define SYS_IMP_APL_PMCR1_EL12	sys_reg(3, 1, 15, 7, 2)
 #define PMCR1_COUNT_A64_EL0_0_7	GENMASK(15, 8)
 #define PMCR1_COUNT_A64_EL1_0_7	GENMASK(23, 16)
 #define PMCR1_COUNT_A64_EL0_8_9	GENMASK(41, 40)
diff --git a/arch/arm64/include/asm/asm-extable.h b/arch/arm64/include/asm/asm-extable.h
index b8a5861dc7b7..292f2687a12e 100644
--- a/arch/arm64/include/asm/asm-extable.h
+++ b/arch/arm64/include/asm/asm-extable.h
@@ -9,7 +9,8 @@
 #define EX_TYPE_BPF			1
 #define EX_TYPE_UACCESS_ERR_ZERO	2
 #define EX_TYPE_KACCESS_ERR_ZERO	3
-#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
+#define EX_TYPE_UACCESS_CPY		4
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	5
 
 /* Data fields for EX_TYPE_UACCESS_ERR_ZERO */
 #define EX_DATA_REG_ERR_SHIFT	0
@@ -23,6 +24,9 @@
 #define EX_DATA_REG_ADDR_SHIFT	5
 #define EX_DATA_REG_ADDR	GENMASK(9, 5)
 
+/* Data fields for EX_TYPE_UACCESS_CPY */
+#define EX_DATA_UACCESS_WRITE	BIT(0)
+
 #ifdef __ASSEMBLY__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
@@ -69,6 +73,10 @@
 	.endif
 	.endm
 
+	.macro		_asm_extable_uaccess_cpy, insn, fixup, uaccess_is_write
+	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_UACCESS_CPY, \uaccess_is_write)
+	.endm
+
 #else /* __ASSEMBLY__ */
 
 #include <linux/stringify.h>
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index 5b6efe8abeeb..9148f5a31968 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -61,6 +61,10 @@ alternative_else_nop_endif
 9999:	x;					\
 	_asm_extable_uaccess	9999b, l
 
+#define USER_CPY(l, uaccess_is_write, x...)	\
+9999:	x;					\
+	_asm_extable_uaccess_cpy 9999b, l, uaccess_is_write
+
 /*
  * Generate the assembly for LDTR/STTR with exception table entries.
  * This is complicated as there is no post-increment or pair versions of the
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 06a4670bdb0b..99cd6546e72e 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -35,7 +35,7 @@
 #define ARCH_DMA_MINALIGN	(128)
 #define ARCH_KMALLOC_MINALIGN	(8)
 
-#ifndef __ASSEMBLY__
+#if !defined(__ASSEMBLY__) && !defined(BUILD_VDSO)
 
 #include <linux/bitops.h>
 #include <linux/kasan-enabled.h>
@@ -118,6 +118,6 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
 	return ctr;
 }
 
-#endif	/* __ASSEMBLY__ */
+#endif /* !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) */
 
 #endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 0b5ca6e0eb09..9d769291a306 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -71,6 +71,8 @@ cpucap_is_possible(const unsigned int cap)
 		 * KVM MPAM support doesn't rely on the host kernel supporting MPAM.
 		*/
 		return true;
+	case ARM64_HAS_PMUV3:
+		return IS_ENABLED(CONFIG_HW_PERF_EVENTS);
 	}
 
 	return true;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e0e4478f5fb5..c4326f1cb917 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -525,29 +525,6 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
 	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
 }
 
-/*
- * Fields that identify the version of the Performance Monitors Extension do
- * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825,
- * "Alternative ID scheme used for the Performance Monitors Extension version".
- */
-static inline u64 __attribute_const__
-cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap)
-{
-	u64 val = cpuid_feature_extract_unsigned_field(features, field);
-	u64 mask = GENMASK_ULL(field + 3, field);
-
-	/* Treat IMPLEMENTATION DEFINED functionality as unimplemented */
-	if (val == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
-		val = 0;
-
-	if (val > cap) {
-		features &= ~mask;
-		features |= (cap << field) & mask;
-	}
-
-	return features;
-}
-
 static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -866,6 +843,11 @@ static __always_inline bool system_supports_mpam_hcr(void)
 	return alternative_has_cap_unlikely(ARM64_MPAM_HCR);
 }
 
+static inline bool system_supports_pmuv3(void)
+{
+	return cpus_have_final_cap(ARM64_HAS_PMUV3);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 6f3f4142e214..dffff6763812 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,11 +75,13 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_CORTEX_A76AE	0xD0E
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_X1C		0xD4C
 #define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
@@ -119,6 +121,7 @@
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
 #define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
+#define QCOM_CPU_PART_KRYO_3XX_GOLD	0x802
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
@@ -130,6 +133,7 @@
 #define FUJITSU_CPU_PART_A64FX		0x001
 
 #define HISI_CPU_PART_TSV110		0xD01
+#define HISI_CPU_PART_HIP09			0xD02
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
@@ -159,11 +163,13 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_CORTEX_A76AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76AE)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
 #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
@@ -196,14 +202,26 @@
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
 #define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
+#define MIDR_QCOM_KRYO_3XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_GOLD)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
 #define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1)
+
+/*
+ * NOTES:
+ * - Qualcomm Kryo 5XX Prime / Gold ID themselves as MIDR_CORTEX_A77
+ * - Qualcomm Kryo 5XX Silver IDs itself as MIDR_QCOM_KRYO_4XX_SILVER
+ * - Qualcomm Kryo 6XX Prime IDs itself as MIDR_CORTEX_X1
+ * - Qualcomm Kryo 6XX Gold IDs itself as ARM_CPU_PART_CORTEX_A78
+ * - Qualcomm Kryo 6XX Silver IDs itself as MIDR_CORTEX_A55
+ */
+
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
@@ -232,6 +250,16 @@
 #define read_cpuid(reg)			read_sysreg_s(SYS_ ## reg)
 
 /*
+ * The CPU ID never changes at run time, so we might as well tell the
+ * compiler that it's constant.  Use this function to read the CPU ID
+ * rather than directly reading processor_id or read_cpuid() directly.
+ */
+static inline u32 __attribute_const__ read_cpuid_id(void)
+{
+	return read_cpuid(MIDR_EL1);
+}
+
+/*
  * Represent a range of MIDR values for a given CPU model and a
  * range of variant/revision values.
  *
@@ -266,30 +294,14 @@ static inline bool midr_is_cpu_model_range(u32 midr, u32 model, u32 rv_min,
 	return _model == model && rv >= rv_min && rv <= rv_max;
 }
 
-static inline bool is_midr_in_range(u32 midr, struct midr_range const *range)
-{
-	return midr_is_cpu_model_range(midr, range->model,
-				       range->rv_min, range->rv_max);
-}
-
-static inline bool
-is_midr_in_range_list(u32 midr, struct midr_range const *ranges)
-{
-	while (ranges->model)
-		if (is_midr_in_range(midr, ranges++))
-			return true;
-	return false;
-}
+struct target_impl_cpu {
+	u64 midr;
+	u64 revidr;
+	u64 aidr;
+};
 
-/*
- * The CPU ID never changes at run time, so we might as well tell the
- * compiler that it's constant.  Use this function to read the CPU ID
- * rather than directly reading processor_id or read_cpuid() directly.
- */
-static inline u32 __attribute_const__ read_cpuid_id(void)
-{
-	return read_cpuid(MIDR_EL1);
-}
+bool cpu_errata_set_target_impl(u64 num, void *impl_cpus);
+bool is_midr_in_range_list(struct midr_range const *ranges);
 
 static inline u64 __attribute_const__ read_cpuid_mpidr(void)
 {
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 25e162651750..d40e427ddad9 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -16,6 +16,32 @@
 #include <asm/sysreg.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+.macro init_el2_hcr	val
+	mov_q	x0, \val
+
+	/*
+	 * Compliant CPUs advertise their VHE-onlyness with
+	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
+	 * can reset into an UNKNOWN state and might not read as 1 until it has
+	 * been initialized explicitly.
+	 *
+	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+	 * don't advertise it (they predate this relaxation).
+	 *
+	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * indicating whether the CPU is running in E2H mode.
+	 */
+	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
+	sbfx	x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+	cmp	x1, #0
+	b.ge	.LnVHE_\@
+
+	orr	x0, x0, #HCR_E2H
+.LnVHE_\@:
+	msr	hcr_el2, x0
+	isb
+.endm
+
 .macro __init_el2_sctlr
 	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
 	msr	sctlr_el2, x0
@@ -26,7 +52,7 @@
 	mrs	x0, id_aa64mmfr1_el1
 	ubfx	x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
 	cbz	x0, .Lskip_hcrx_\@
-	mov_q	x0, HCRX_HOST_FLAGS
+	mov_q	x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
 
         /* Enable GCS if supported */
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
@@ -233,6 +259,30 @@
 .Lskip_fgt_\@:
 .endm
 
+.macro __init_el2_fgt2
+	mrs	x1, id_aa64mmfr0_el1
+	ubfx	x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
+	cmp	x1, #ID_AA64MMFR0_EL1_FGT_FGT2
+	b.lt	.Lskip_fgt2_\@
+
+	mov	x0, xzr
+	mrs	x1, id_aa64dfr0_el1
+	ubfx	x1, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x1, #ID_AA64DFR0_EL1_PMUVer_V3P9
+	b.lt	.Lskip_pmuv3p9_\@
+
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICNTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICFILTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMUACR_EL1
+.Lskip_pmuv3p9_\@:
+	msr_s   SYS_HDFGRTR2_EL2, x0
+	msr_s   SYS_HDFGWTR2_EL2, x0
+	msr_s   SYS_HFGRTR2_EL2, xzr
+	msr_s   SYS_HFGWTR2_EL2, xzr
+	msr_s   SYS_HFGITR2_EL2, xzr
+.Lskip_fgt2_\@:
+.endm
+
 .macro __init_el2_gcs
 	mrs_s	x1, SYS_ID_AA64PFR1_EL1
 	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
@@ -244,11 +294,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_nvhe_prepare_eret
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
-.endm
-
 .macro __init_el2_mpam
 	/* Memory Partitioning And Monitoring: disable EL2 traps */
 	mrs	x1, id_aa64pfr0_el1
@@ -283,6 +328,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_cptr
 	__init_el2_fgt
+	__init_el2_fgt2
         __init_el2_gcs
 .endm
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d1b1a33f9a8b..e4f77757937e 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -121,6 +121,15 @@
 #define ESR_ELx_FSC_SEA_TTW(n)	(0x14 + (n))
 #define ESR_ELx_FSC_SECC	(0x18)
 #define ESR_ELx_FSC_SECC_TTW(n)	(0x1c + (n))
+#define ESR_ELx_FSC_ADDRSZ	(0x00)
+
+/*
+ * Annoyingly, the negative levels for Address size faults aren't laid out
+ * contiguously (or in the desired order)
+ */
+#define ESR_ELx_FSC_ADDRSZ_nL(n)	((n) == -1 ? 0x25 : 0x2C)
+#define ESR_ELx_FSC_ADDRSZ_L(n)		((n) < 0 ? ESR_ELx_FSC_ADDRSZ_nL(n) : \
+						   (ESR_ELx_FSC_ADDRSZ + (n)))
 
 /* Status codes for individual page table levels */
 #define ESR_ELx_FSC_ACCESS_L(n)	(ESR_ELx_FSC_ACCESS + (n))
@@ -161,8 +170,6 @@
 #define ESR_ELx_Xs_MASK		(GENMASK_ULL(4, 0))
 
 /* ISS field definitions for exceptions taken in to Hyp */
-#define ESR_ELx_FSC_ADDRSZ	(0x00)
-#define ESR_ELx_FSC_ADDRSZ_L(n)	(ESR_ELx_FSC_ADDRSZ + (n))
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -464,6 +471,39 @@ static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
 	       (esr == ESR_ELx_FSC_ACCESS_L(0));
 }
 
+static inline bool esr_fsc_is_addr_sz_fault(unsigned long esr)
+{
+	esr &= ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_ADDRSZ_L(3))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(2))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(1)) ||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(0))	||
+	       (esr == ESR_ELx_FSC_ADDRSZ_L(-1));
+}
+
+static inline bool esr_fsc_is_sea_ttw(unsigned long esr)
+{
+	esr = esr & ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_SEA_TTW(3)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(2)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(1)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(0)) ||
+	       (esr == ESR_ELx_FSC_SEA_TTW(-1));
+}
+
+static inline bool esr_fsc_is_secc_ttw(unsigned long esr)
+{
+	esr = esr & ESR_ELx_FSC;
+
+	return (esr == ESR_ELx_FSC_SECC_TTW(3)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(2)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(1)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(0)) ||
+	       (esr == ESR_ELx_FSC_SECC_TTW(-1));
+}
+
 /* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */
 static inline bool esr_iss_is_eretax(unsigned long esr)
 {
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 72b0e71cc3de..9dc39612bdf5 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -33,6 +33,8 @@ do {							\
 	(b)->data = (tmp).data;				\
 } while (0)
 
+bool insn_may_access_user(unsigned long addr, unsigned long esr);
+
 #ifdef CONFIG_BPF_JIT
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs);
@@ -45,5 +47,5 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 }
 #endif /* !CONFIG_BPF_JIT */
 
-bool fixup_exception(struct pt_regs *regs);
+bool fixup_exception(struct pt_regs *regs, unsigned long esr);
 #endif
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index f2a84efc3618..564bc09b3e06 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -80,7 +80,6 @@ extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
-extern void fpsimd_kvm_prepare(void);
 
 struct cpu_fp_state {
 	struct user_fpsimd_state *st;
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6dff3e69539..07fbf5bf85a7 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
@@ -76,12 +76,22 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	if (stride == PMD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 2);
-	else if (stride == PUD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 1);
-	else
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	switch (stride) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		break;
+#endif
+	case CONT_PMD_SIZE:
+	case PMD_SIZE:
+		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		break;
+	case CONT_PTE_SIZE:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		break;
+	default:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	}
 }
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hypervisor.h b/arch/arm64/include/asm/hypervisor.h
index 409e239834d1..a12fd897c877 100644
--- a/arch/arm64/include/asm/hypervisor.h
+++ b/arch/arm64/include/asm/hypervisor.h
@@ -6,6 +6,7 @@
 
 void kvm_init_hyp_services(void);
 bool kvm_arm_hyp_service_available(u32 func_id);
+void kvm_arm_target_impl_cpu_init(void);
 
 #ifdef CONFIG_ARM_PKVM_GUEST
 void pkvm_init_hyp_services(void);
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index e390c432f546..18c7811774d3 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -188,8 +188,10 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
 	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
 	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_ACQ,
 	AARCH64_INSN_LDST_LOAD_EX,
 	AARCH64_INSN_LDST_LOAD_ACQ_EX,
+	AARCH64_INSN_LDST_STORE_REL,
 	AARCH64_INSN_LDST_STORE_EX,
 	AARCH64_INSN_LDST_STORE_REL_EX,
 	AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET,
@@ -351,8 +353,10 @@ __AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
 __AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
-__AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
-__AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_acq,  0x3FDFFC00, 0x08DFFC00)
+__AARCH64_INSN_FUNCS(store_rel, 0x3FDFFC00, 0x089FFC00)
+__AARCH64_INSN_FUNCS(load_ex,	0x3FC00000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex,	0x3FC00000, 0x08000000)
 __AARCH64_INSN_FUNCS(mops,	0x3B200C00, 0x19000400)
 __AARCH64_INSN_FUNCS(stp,	0x7FC00000, 0x29000000)
 __AARCH64_INSN_FUNCS(ldp,	0x7FC00000, 0x29400000)
@@ -602,6 +606,10 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 				     int offset,
 				     enum aarch64_insn_variant variant,
 				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type);
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,
@@ -698,6 +706,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
 }
 #endif
 u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type);
 u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
 			 enum aarch64_insn_system_register sysreg);
 
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 76ebbdc6ffdd..9b96840fb979 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -270,9 +270,9 @@ int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
 #define _PAGE_IOREMAP PROT_DEVICE_nGnRE
 
 #define ioremap_wc(addr, size)	\
-	ioremap_prot((addr), (size), PROT_NORMAL_NC)
+	ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\
-	ioremap_prot((addr), (size), PROT_DEVICE_nGnRnE)
+	ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
 
 /*
  * io{read,write}{16,32,64}be() macros
@@ -293,7 +293,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
 	if (pfn_is_map_memory(__phys_to_pfn(addr)))
 		return (void __iomem *)__phys_to_virt(addr);
 
-	return ioremap_prot(addr, size, PROT_NORMAL);
+	return ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
 }
 
 /*
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index fd5a08450b12..9e93733523f6 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -45,11 +45,11 @@
 #define SPAN_NR_ENTRIES(vstart, vend, shift) \
 	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1)
 
-#define EARLY_ENTRIES(vstart, vend, shift, add) \
-	(SPAN_NR_ENTRIES(vstart, vend, shift) + (add))
+#define EARLY_ENTRIES(lvl, vstart, vend) \
+	SPAN_NR_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * PTDESC_TABLE_SHIFT)
 
-#define EARLY_LEVEL(lvl, lvls, vstart, vend, add)	\
-	(lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0)
+#define EARLY_LEVEL(lvl, lvls, vstart, vend, add) \
+	((lvls) > (lvl) ? EARLY_ENTRIES(lvl, vstart, vend) + (add) : 0)
 
 #define EARLY_PAGES(lvls, vstart, vend, add) (1 	/* PGDIR page */				\
 	+ EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */	\
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8d94a6c0ed5c..e9c8a581e16f 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -92,17 +92,16 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
  * TID3:	Trap EL1 reads of group 3 ID registers
- * TID2:	Trap CTR_EL0, CCSIDR2_EL1, CLIDR_EL1, and CSSELR_EL1
+ * TID1:	Trap REVIDR_EL1, AIDR_EL1, and SMIDR_EL1
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_BSU_IS | HCR_FB | HCR_TACR | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
-			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3)
+			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
-#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO)
 
-#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
 #define MPAMHCR_HOST_FLAGS	0
 
 /* TCR_EL2 Registers bits */
@@ -119,7 +118,7 @@
 #define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
 #define TCR_EL2_T0SZ_MASK	0x3f
 #define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
-			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_DS		TCR_EL2_DS
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 78ec1ef2cfe8..bd020fc28aa9 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -275,6 +275,19 @@ static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault.esr_el2;
 }
 
+static inline bool guest_hyp_wfx_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE);
+	u64 hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+	if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu))
+		return false;
+
+	return ((is_wfe && (hcr_el2 & HCR_TWE)) ||
+		(!is_wfe && (hcr_el2 & HCR_TWI)));
+}
+
 static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
 {
 	u64 esr = kvm_vcpu_get_esr(vcpu);
@@ -292,7 +305,12 @@ static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vc
 
 static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
 {
-	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
+	u64 hpfar = vcpu->arch.fault.hpfar_el2;
+
+	if (unlikely(!(hpfar & HPFAR_EL2_NS)))
+		return INVALID_GPA;
+
+	return FIELD_GET(HPFAR_EL2_FIPA, hpfar) << 12;
 }
 
 static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
@@ -649,4 +667,28 @@ static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
 {
 	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
 }
+
+static inline void vcpu_set_hcrx(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
+		/*
+		 * In general, all HCRX_EL2 bits are gated by a feature.
+		 * The only reason we can set SMPME without checking any
+		 * feature is that its effects are not directly observable
+		 * from the guest.
+		 */
+		vcpu->arch.hcrx_el2 = HCRX_EL2_SMPME;
+
+		if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
+			vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
+
+		if (kvm_has_tcr2(kvm))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;
+
+		if (kvm_has_fpmr(kvm))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnFPM;
+	}
+}
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3a7ec98ef123..08ba91e6fb03 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -44,14 +44,15 @@
 
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
-#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
-#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
-#define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
-#define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
-#define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
-#define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
-#define KVM_REQ_NESTED_S2_UNMAP	KVM_ARCH_REQ(8)
+#define KVM_REQ_IRQ_PENDING		KVM_ARCH_REQ(1)
+#define KVM_REQ_VCPU_RESET		KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL		KVM_ARCH_REQ(3)
+#define KVM_REQ_RELOAD_GICv4		KVM_ARCH_REQ(4)
+#define KVM_REQ_RELOAD_PMU		KVM_ARCH_REQ(5)
+#define KVM_REQ_SUSPEND			KVM_ARCH_REQ(6)
+#define KVM_REQ_RESYNC_PMU_EL0		KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP		KVM_ARCH_REQ(8)
+#define KVM_REQ_GUEST_HYP_IRQ_PENDING	KVM_ARCH_REQ(9)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -86,6 +87,9 @@ struct kvm_hyp_memcache {
 	phys_addr_t head;
 	unsigned long nr_pages;
 	struct pkvm_mapping *mapping; /* only used from EL1 */
+
+#define	HYP_MEMCACHE_ACCOUNT_STAGE2	BIT(1)
+	unsigned long flags;
 };
 
 static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
@@ -237,7 +241,8 @@ struct kvm_arch_memory_slot {
 struct kvm_smccc_features {
 	unsigned long std_bmap;
 	unsigned long std_hyp_bmap;
-	unsigned long vendor_hyp_bmap;
+	unsigned long vendor_hyp_bmap; /* Function numbers 0-63 */
+	unsigned long vendor_hyp_bmap_2; /* Function numbers 64-127 */
 };
 
 typedef unsigned int pkvm_handle_t;
@@ -245,6 +250,7 @@ typedef unsigned int pkvm_handle_t;
 struct kvm_protected_vm {
 	pkvm_handle_t handle;
 	struct kvm_hyp_memcache teardown_mc;
+	struct kvm_hyp_memcache stage2_teardown_mc;
 	bool enabled;
 };
 
@@ -334,6 +340,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_FGU_INITIALIZED			8
 	/* SVE exposed to guest */
 #define KVM_ARCH_FLAG_GUEST_HAS_SVE			9
+	/* MIDR_EL1, REVIDR_EL1, and AIDR_EL1 are writable from userspace */
+#define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS		10
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */
@@ -373,6 +381,9 @@ struct kvm_arch {
 #define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
 	u64 id_regs[KVM_ARM_ID_REG_NUM];
 
+	u64 midr_el1;
+	u64 revidr_el1;
+	u64 aidr_el1;
 	u64 ctr_el0;
 
 	/* Masks for VNCR-backed and general EL2 sysregs */
@@ -557,7 +568,33 @@ enum vcpu_sysreg {
 	VNCR(CNTP_CVAL_EL0),
 	VNCR(CNTP_CTL_EL0),
 
+	VNCR(ICH_LR0_EL2),
+	VNCR(ICH_LR1_EL2),
+	VNCR(ICH_LR2_EL2),
+	VNCR(ICH_LR3_EL2),
+	VNCR(ICH_LR4_EL2),
+	VNCR(ICH_LR5_EL2),
+	VNCR(ICH_LR6_EL2),
+	VNCR(ICH_LR7_EL2),
+	VNCR(ICH_LR8_EL2),
+	VNCR(ICH_LR9_EL2),
+	VNCR(ICH_LR10_EL2),
+	VNCR(ICH_LR11_EL2),
+	VNCR(ICH_LR12_EL2),
+	VNCR(ICH_LR13_EL2),
+	VNCR(ICH_LR14_EL2),
+	VNCR(ICH_LR15_EL2),
+
+	VNCR(ICH_AP0R0_EL2),
+	VNCR(ICH_AP0R1_EL2),
+	VNCR(ICH_AP0R2_EL2),
+	VNCR(ICH_AP0R3_EL2),
+	VNCR(ICH_AP1R0_EL2),
+	VNCR(ICH_AP1R1_EL2),
+	VNCR(ICH_AP1R2_EL2),
+	VNCR(ICH_AP1R3_EL2),
 	VNCR(ICH_HCR_EL2),
+	VNCR(ICH_VMCR_EL2),
 
 	NR_SYS_REGS	/* Nothing after this line! */
 };
@@ -869,6 +906,8 @@ struct kvm_vcpu_arch {
 #define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(0))
 /* SVE config completed */
 #define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
+/* pKVM VCPU setup completed */
+#define VCPU_PKVM_FINALIZED	__vcpu_single_flag(cflags, BIT(2))
 
 /* Exception pending */
 #define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
@@ -919,6 +958,8 @@ struct kvm_vcpu_arch {
 #define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(5))
 /* WFI instruction trapped */
 #define IN_WFI			__vcpu_single_flag(sflags, BIT(6))
+/* KVM is currently emulating a nested ERET */
+#define IN_NESTED_ERET		__vcpu_single_flag(sflags, BIT(7))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -1259,7 +1300,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
@@ -1334,8 +1375,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 	return cpus_have_final_cap(ARM64_SPECTRE_V3A);
 }
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-
 void kvm_init_host_debug_data(void);
 void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu);
@@ -1459,6 +1498,12 @@ static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg)
 		return &ka->id_regs[IDREG_IDX(reg)];
 	case SYS_CTR_EL0:
 		return &ka->ctr_el0;
+	case SYS_MIDR_EL1:
+		return &ka->midr_el1;
+	case SYS_REVIDR_EL1:
+		return &ka->revidr_el1;
+	case SYS_AIDR_EL1:
+		return &ka->aidr_el1;
 	default:
 		WARN_ON_ONCE(1);
 		return NULL;
@@ -1543,4 +1588,9 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 #define kvm_has_s1poe(k)				\
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return true;
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c838309e4ec4..e6be1f5d0967 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -76,6 +76,8 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
+u64 __gic_v3_get_lr(unsigned int lr);
+
 void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
 void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 56c4bcd35e2e..692f403c1896 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -188,6 +188,7 @@ static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr)
 }
 
 int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu);
+u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val);
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr);
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index eb65f12e81d9..abd693ce5b93 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -19,6 +19,7 @@
 int pkvm_init_host_vm(struct kvm *kvm);
 int pkvm_create_hyp_vm(struct kvm *kvm);
 void pkvm_destroy_hyp_vm(struct kvm *kvm);
+int pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu);
 
 /*
  * This functions as an allow-list of protected VM capabilities.
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
index 87e10d9a635b..9398ade632aa 100644
--- a/arch/arm64/include/asm/kvm_ras.h
+++ b/arch/arm64/include/asm/kvm_ras.h
@@ -14,7 +14,7 @@
  * Was this synchronous external abort a RAS notification?
  * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
  */
-static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
+static inline int kvm_handle_guest_sea(void)
 {
 	/* apei_claim_sea(NULL) expects to mask interrupts itself */
 	lockdep_assert_irqs_enabled();
diff --git a/arch/arm64/include/asm/mem_encrypt.h b/arch/arm64/include/asm/mem_encrypt.h
index f8f78f622dd2..a2a1eeb36d4b 100644
--- a/arch/arm64/include/asm/mem_encrypt.h
+++ b/arch/arm64/include/asm/mem_encrypt.h
@@ -21,4 +21,15 @@ static inline bool force_dma_unencrypted(struct device *dev)
 	return is_realm_world();
 }
 
+/*
+ * For Arm CCA guests, canonical addresses are "encrypted", so no changes
+ * required for dma_addr_encrypted().
+ * The unencrypted DMA buffers must be accessed via the unprotected IPA,
+ * "top IPA bit" set.
+ */
+#define dma_addr_unencrypted(x)		((x) | PROT_NS_SHARED)
+
+/* Clear the "top" IPA bit while converting back */
+#define dma_addr_canonical(x)		((x) & ~PROT_NS_SHARED)
+
 #endif	/* __ASM_MEM_ENCRYPT_H */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 662471cfc536..6e8aa8e72601 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -94,18 +94,6 @@ static inline bool kaslr_requires_kpti(void)
 			return false;
 	}
 
-	/*
-	 * Systems affected by Cavium erratum 24756 are incompatible
-	 * with KPTI.
-	 */
-	if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
-		extern const struct midr_range cavium_erratum_27456_cpus[];
-
-		if (is_midr_in_range_list(read_cpuid_id(),
-					  cavium_erratum_27456_cpus))
-			return false;
-	}
-
 	return true;
 }
 
diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h
index 2e2f83bafcfb..b721d3134ab6 100644
--- a/arch/arm64/include/asm/mshyperv.h
+++ b/arch/arm64/include/asm/mshyperv.h
@@ -40,6 +40,19 @@ static inline u64 hv_get_msr(unsigned int reg)
 	return hv_get_vpreg(reg);
 }
 
+/*
+ * Nested is not supported on arm64
+ */
+static inline void hv_set_non_nested_msr(unsigned int reg, u64 value)
+{
+	hv_set_msr(reg, value);
+}
+
+static inline u64 hv_get_non_nested_msr(unsigned int reg)
+{
+	return hv_get_msr(reg);
+}
+
 /* SMCCC hypercall parameters */
 #define HV_SMCCC_FUNC_NUMBER	1
 #define HV_FUNC_ID	ARM_SMCCC_CALL_VAL(			\
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index a9136cc551cc..f3b77deedfa2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -7,40 +7,46 @@
 
 #include <asm/memory.h>
 
+#define PTDESC_ORDER 3
+
+/* Number of VA bits resolved by a single translation table level */
+#define PTDESC_TABLE_SHIFT	(PAGE_SHIFT - PTDESC_ORDER)
+
 /*
  * Number of page-table levels required to address 'va_bits' wide
  * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
- * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
+ * bits with PTDESC_TABLE_SHIFT bits at each page table level. Hence:
  *
- *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
+ *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), PTDESC_TABLE_SHIFT)
  *
  * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
  *
  * We cannot include linux/kernel.h which defines DIV_ROUND_UP here
  * due to build issues. So we open code DIV_ROUND_UP here:
  *
- *	((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
+ *	((((va_bits) - PAGE_SHIFT) + PTDESC_TABLE_SHIFT - 1) / PTDESC_TABLE_SHIFT)
  *
  * which gets simplified as :
  */
-#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
+#define ARM64_HW_PGTABLE_LEVELS(va_bits) \
+	(((va_bits) - PTDESC_ORDER - 1) / PTDESC_TABLE_SHIFT)
 
 /*
  * Size mapped by an entry at level n ( -1 <= n <= 3)
- * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
+ * We map PTDESC_TABLE_SHIFT at all translation levels and PAGE_SHIFT bits
  * in the final page. The maximum number of translation levels supported by
  * the architecture is 5. Hence, starting at level n, we have further
  * ((4 - n) - 1) levels of translation excluding the offset within the page.
  * So, the total number of bits mapped by an entry at level n is :
  *
- *  ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
+ *  ((4 - n) - 1) * PTDESC_TABLE_SHIFT + PAGE_SHIFT
  *
  * Rearranging it a bit we get :
- *   (4 - n) * (PAGE_SHIFT - 3) + 3
+ *   (4 - n) * PTDESC_TABLE_SHIFT + PTDESC_ORDER
  */
-#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	((PAGE_SHIFT - 3) * (4 - (n)) + 3)
+#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	(PTDESC_TABLE_SHIFT * (4 - (n)) + PTDESC_ORDER)
 
-#define PTRS_PER_PTE		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PTE		(1 << PTDESC_TABLE_SHIFT)
 
 /*
  * PMD_SHIFT determines the size a level 2 page table entry can map.
@@ -49,7 +55,7 @@
 #define PMD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
 #define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
-#define PTRS_PER_PMD		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PMD		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 /*
@@ -59,14 +65,14 @@
 #define PUD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
 #define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE-1))
-#define PTRS_PER_PUD		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_PUD		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 #if CONFIG_PGTABLE_LEVELS > 4
 #define P4D_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(0)
 #define P4D_SIZE		(_AC(1, UL) << P4D_SHIFT)
 #define P4D_MASK		(~(P4D_SIZE-1))
-#define PTRS_PER_P4D		(1 << (PAGE_SHIFT - 3))
+#define PTRS_PER_P4D		(1 << PTDESC_TABLE_SHIFT)
 #endif
 
 /*
@@ -97,7 +103,6 @@
  * Level -1 descriptor (PGD).
  */
 #define PGD_TYPE_TABLE		(_AT(pgdval_t, 3) << 0)
-#define PGD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
 #define PGD_TYPE_MASK		(_AT(pgdval_t, 3) << 0)
 #define PGD_TABLE_AF		(_AT(pgdval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 #define PGD_TABLE_PXN		(_AT(pgdval_t, 1) << 59)
@@ -107,7 +112,6 @@
  * Level 0 descriptor (P4D).
  */
 #define P4D_TYPE_TABLE		(_AT(p4dval_t, 3) << 0)
-#define P4D_TABLE_BIT		(_AT(p4dval_t, 1) << 1)
 #define P4D_TYPE_MASK		(_AT(p4dval_t, 3) << 0)
 #define P4D_TYPE_SECT		(_AT(p4dval_t, 1) << 0)
 #define P4D_SECT_RDONLY		(_AT(p4dval_t, 1) << 7)		/* AP[2] */
@@ -119,7 +123,6 @@
  * Level 1 descriptor (PUD).
  */
 #define PUD_TYPE_TABLE		(_AT(pudval_t, 3) << 0)
-#define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
 #define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
 #define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
@@ -133,7 +136,6 @@
 #define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
-#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 #define PMD_TABLE_AF		(_AT(pmdval_t, 1) << 10)	/* Ignored if no FEAT_HAFT */
 
 /*
@@ -162,7 +164,6 @@
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
-#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
 #define PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index a95f1f77bb39..7830d031742e 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -169,25 +169,25 @@ static inline bool __pure lpa2_is_enabled(void)
 #define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
 
 #define PIE_E0	( \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_X_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O)  | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R_O)   | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW_O))
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_EXECONLY),      PIE_X_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O)  | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY),      PIE_R_O)   | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED),        PIE_RW_O))
 
 #define PIE_E1	( \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS),           PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO),        PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_NONE_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RW)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_ROX),    PIE_RX)     | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_EXEC),   PIE_RWX)    | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_RO),     PIE_R)      | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL),        PIE_RW))
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_EXECONLY),      PIE_NONE_O) | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RW)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_READONLY),      PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_SHARED),        PIE_RW)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_ROX),    PIE_RX)     | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_EXEC),   PIE_RWX)    | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL_RO),     PIE_R)      | \
+	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_KERNEL),        PIE_RW))
 
 #endif /* __ASM_PGTABLE_PROT_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0b2a2ad1b9e8..d3b538be1500 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -68,10 +68,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_ERROR(e)	\
 	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
 
-/*
- * Macros to convert between a physical address and its placement in a
- * page table entry, taking care of 52-bit addresses.
- */
 #ifdef CONFIG_ARM64_PA_BITS_52
 static inline phys_addr_t __pte_to_phys(pte_t pte)
 {
@@ -84,8 +80,15 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 	return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK;
 }
 #else
-#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_LOW)
-#define __phys_to_pte_val(phys)	(phys)
+static inline phys_addr_t __pte_to_phys(pte_t pte)
+{
+	return pte_val(pte) & PTE_ADDR_LOW;
+}
+
+static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
+{
+	return phys;
+}
 #endif
 
 #define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
@@ -483,12 +486,12 @@ static inline pmd_t pte_pmd(pte_t pte)
 
 static inline pgprot_t mk_pud_sect_prot(pgprot_t prot)
 {
-	return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT);
+	return __pgprot((pgprot_val(prot) & ~PUD_TYPE_MASK) | PUD_TYPE_SECT);
 }
 
 static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
 {
-	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
+	return __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT);
 }
 
 static inline pte_t pte_swp_mkexclusive(pte_t pte)
@@ -548,18 +551,6 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif
 
 #define pmd_present(pmd)	pte_present(pmd_pte(pmd))
-
-/*
- * THP definitions.
- */
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pmd_trans_huge(pmd_t pmd)
-{
-	return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
@@ -585,7 +576,18 @@ static inline int pmd_trans_huge(pmd_t pmd)
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
-#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+	/*
+	 * It's possible that the pmd is present-invalid on entry
+	 * and in that case it needs to remain present-invalid on
+	 * exit. So ensure the VALID bit does not get modified.
+	 */
+	pmdval_t mask = PMD_TYPE_MASK & ~PTE_VALID;
+	pmdval_t val = PMD_TYPE_SECT & ~PTE_VALID;
+
+	return __pmd((pmd_val(pmd) & ~mask) | val);
+}
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
@@ -613,18 +615,24 @@ static inline pmd_t pmd_mkspecial(pmd_t pmd)
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
-#define pud_mkhuge(pud)		(__pud(pud_val(pud) & ~PUD_TABLE_BIT))
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+	/*
+	 * It's possible that the pud is present-invalid on entry
+	 * and in that case it needs to remain present-invalid on
+	 * exit. So ensure the VALID bit does not get modified.
+	 */
+	pudval_t mask = PUD_TYPE_MASK & ~PTE_VALID;
+	pudval_t val = PUD_TYPE_SECT & ~PTE_VALID;
+
+	return __pud((pud_val(pud) & ~mask) | val);
+}
 
 #define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
 #define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
-#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
-#define pud_special(pte)	pte_special(pud_pte(pud))
-#define pud_mkspecial(pte)	pte_pud(pte_mkspecial(pud_pte(pud)))
-#endif
-
 #define pmd_pgprot pmd_pgprot
 static inline pgprot_t pmd_pgprot(pmd_t pmd)
 {
@@ -724,6 +732,18 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
 #define pte_leaf_size(pte)	(pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	/*
+	 * If pmd is present-invalid, pmd_table() won't detect it
+	 * as a table, so force the valid bit for the comparison.
+	 */
+	return pmd_val(pmd) && pmd_present(pmd) &&
+	       !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
 static inline bool pud_sect(pud_t pud) { return false; }
 static inline bool pud_table(pud_t pud) { return true; }
@@ -805,7 +825,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
 #define pud_none(pud)		(!pud_val(pud))
-#define pud_bad(pud)		(!pud_table(pud))
+#define pud_bad(pud)		((pud_val(pud) & PUD_TYPE_MASK) != \
+				 PUD_TYPE_TABLE)
 #define pud_present(pud)	pte_present(pud_pte(pud))
 #ifndef __PAGETABLE_PMD_FOLDED
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
@@ -896,7 +917,9 @@ static inline bool mm_pud_folded(const struct mm_struct *mm)
 	pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e))
 
 #define p4d_none(p4d)		(pgtable_l4_enabled() && !p4d_val(p4d))
-#define p4d_bad(p4d)		(pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT))
+#define p4d_bad(p4d)		(pgtable_l4_enabled() && \
+				((p4d_val(p4d) & P4D_TYPE_MASK) != \
+				 P4D_TYPE_TABLE))
 #define p4d_present(p4d)	(!p4d_none(p4d))
 
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
@@ -1023,7 +1046,9 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm)
 	pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e))
 
 #define pgd_none(pgd)		(pgtable_l5_enabled() && !pgd_val(pgd))
-#define pgd_bad(pgd)		(pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT))
+#define pgd_bad(pgd)		(pgtable_l5_enabled() && \
+				((pgd_val(pgd) & PGD_TYPE_MASK) != \
+				 PGD_TYPE_TABLE))
 #define pgd_present(pgd)	(!pgd_none(pgd))
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
diff --git a/arch/arm64/include/asm/por.h b/arch/arm64/include/asm/por.h
index e06e9f473675..d913d5b529e4 100644
--- a/arch/arm64/include/asm/por.h
+++ b/arch/arm64/include/asm/por.h
@@ -6,26 +6,27 @@
 #ifndef _ASM_ARM64_POR_H
 #define _ASM_ARM64_POR_H
 
-#define POR_BITS_PER_PKEY		4
-#define POR_ELx_IDX(por_elx, idx)	(((por_elx) >> ((idx) * POR_BITS_PER_PKEY)) & 0xf)
+#include <asm/sysreg.h>
+
+#define POR_EL0_INIT	POR_ELx_PERM_PREP(0, POE_RWX)
 
 static inline bool por_elx_allows_read(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_R;
 }
 
 static inline bool por_elx_allows_write(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_W;
 }
 
 static inline bool por_elx_allows_exec(u64 por, u8 pkey)
 {
-	u8 perm = POR_ELx_IDX(por, pkey);
+	u8 perm = POR_ELx_PERM_GET(pkey, por);
 
 	return perm & POE_X;
 }
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
index 6cf4aae05219..b2931d1ae0fb 100644
--- a/arch/arm64/include/asm/ptdump.h
+++ b/arch/arm64/include/asm/ptdump.h
@@ -7,7 +7,7 @@
 
 #include <linux/ptdump.h>
 
-#ifdef CONFIG_PTDUMP_CORE
+#ifdef CONFIG_PTDUMP
 
 #include <linux/mm_types.h>
 #include <linux/seq_file.h>
@@ -70,6 +70,6 @@ static inline void ptdump_debugfs_register(struct ptdump_info *info,
 #else
 static inline void note_page(struct ptdump_state *pt_st, unsigned long addr,
 			     int level, u64 val) { }
-#endif /* CONFIG_PTDUMP_CORE */
+#endif /* CONFIG_PTDUMP */
 
 #endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm64/include/asm/rqspinlock.h b/arch/arm64/include/asm/rqspinlock.h
new file mode 100644
index 000000000000..9ea0a74e5892
--- /dev/null
+++ b/arch/arm64/include/asm/rqspinlock.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RQSPINLOCK_H
+#define _ASM_RQSPINLOCK_H
+
+#include <asm/barrier.h>
+
+/*
+ * Hardcode res_smp_cond_load_acquire implementations for arm64 to a custom
+ * version based on [0]. In rqspinlock code, our conditional expression involves
+ * checking the value _and_ additionally a timeout. However, on arm64, the
+ * WFE-based implementation may never spin again if no stores occur to the
+ * locked byte in the lock word. As such, we may be stuck forever if
+ * event-stream based unblocking is not available on the platform for WFE spin
+ * loops (arch_timer_evtstrm_available).
+ *
+ * Once support for smp_cond_load_acquire_timewait [0] lands, we can drop this
+ * copy-paste.
+ *
+ * While we rely on the implementation to amortize the cost of sampling
+ * cond_expr for us, it will not happen when event stream support is
+ * unavailable, time_expr check is amortized. This is not the common case, and
+ * it would be difficult to fit our logic in the time_expr_ns >= time_limit_ns
+ * comparison, hence just let it be. In case of event-stream, the loop is woken
+ * up at microsecond granularity.
+ *
+ * [0]: https://lore.kernel.org/lkml/20250203214911.898276-1-ankur.a.arora@oracle.com
+ */
+
+#ifndef smp_cond_load_acquire_timewait
+
+#define smp_cond_time_check_count	200
+
+#define __smp_cond_load_relaxed_spinwait(ptr, cond_expr, time_expr_ns,	\
+					 time_limit_ns) ({		\
+	typeof(ptr) __PTR = (ptr);					\
+	__unqual_scalar_typeof(*ptr) VAL;				\
+	unsigned int __count = 0;					\
+	for (;;) {							\
+		VAL = READ_ONCE(*__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		cpu_relax();						\
+		if (__count++ < smp_cond_time_check_count)		\
+			continue;					\
+		if ((time_expr_ns) >= (time_limit_ns))			\
+			break;						\
+		__count = 0;						\
+	}								\
+	(typeof(*ptr))VAL;						\
+})
+
+#define __smp_cond_load_acquire_timewait(ptr, cond_expr,		\
+					 time_expr_ns, time_limit_ns)	\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	__unqual_scalar_typeof(*ptr) VAL;				\
+	for (;;) {							\
+		VAL = smp_load_acquire(__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+		if ((time_expr_ns) >= (time_limit_ns))			\
+			break;						\
+	}								\
+	(typeof(*ptr))VAL;						\
+})
+
+#define smp_cond_load_acquire_timewait(ptr, cond_expr,			\
+				      time_expr_ns, time_limit_ns)	\
+({									\
+	__unqual_scalar_typeof(*ptr) _val;				\
+	int __wfe = arch_timer_evtstrm_available();			\
+									\
+	if (likely(__wfe)) {						\
+		_val = __smp_cond_load_acquire_timewait(ptr, cond_expr,	\
+							time_expr_ns,	\
+							time_limit_ns);	\
+	} else {							\
+		_val = __smp_cond_load_relaxed_spinwait(ptr, cond_expr,	\
+							time_expr_ns,	\
+							time_limit_ns);	\
+		smp_acquire__after_ctrl_dep();				\
+	}								\
+	(typeof(*ptr))_val;						\
+})
+
+#endif
+
+#define res_smp_cond_load_acquire(v, c) smp_cond_load_acquire_timewait(v, c, 0, 1)
+
+#include <asm-generic/rqspinlock.h>
+
+#endif /* _ASM_RQSPINLOCK_H */
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 0c4d9045c31f..8fef12626090 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -97,7 +97,9 @@ enum mitigation_state arm64_get_meltdown_state(void);
 
 enum mitigation_state arm64_get_spectre_bhb_state(void);
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
-u8 spectre_bhb_loop_affected(int scope);
+extern bool __nospectre_bhb;
+u8 get_spectre_bhb_loop_value(void);
+bool is_spectre_bhb_fw_mitigated(void);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 05ea5223d2d5..2639d3633073 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -562,9 +562,6 @@
 
 #define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
 #define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
-#define SYS_ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
-#define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
-#define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
 #define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
 #define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
 #define SYS_ICH_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
@@ -985,10 +982,6 @@
 #define SYS_MPIDR_SAFE_VAL	(BIT(31))
 
 /* GIC Hypervisor interface registers */
-/* ICH_MISR_EL2 bit definitions */
-#define ICH_MISR_EOI		(1 << 0)
-#define ICH_MISR_U		(1 << 1)
-
 /* ICH_LR*_EL2 bit definitions */
 #define ICH_LR_VIRTUAL_ID_MASK	((1ULL << 32) - 1)
 
@@ -1003,17 +996,6 @@
 #define ICH_LR_PRIORITY_SHIFT	48
 #define ICH_LR_PRIORITY_MASK	(0xffULL << ICH_LR_PRIORITY_SHIFT)
 
-/* ICH_HCR_EL2 bit definitions */
-#define ICH_HCR_EN		(1 << 0)
-#define ICH_HCR_UIE		(1 << 1)
-#define ICH_HCR_NPIE		(1 << 3)
-#define ICH_HCR_TC		(1 << 10)
-#define ICH_HCR_TALL0		(1 << 11)
-#define ICH_HCR_TALL1		(1 << 12)
-#define ICH_HCR_TDIR		(1 << 14)
-#define ICH_HCR_EOIcount_SHIFT	27
-#define ICH_HCR_EOIcount_MASK	(0x1f << ICH_HCR_EOIcount_SHIFT)
-
 /* ICH_VMCR_EL2 bit definitions */
 #define ICH_VMCR_ACK_CTL_SHIFT	2
 #define ICH_VMCR_ACK_CTL_MASK	(1 << ICH_VMCR_ACK_CTL_SHIFT)
@@ -1034,18 +1016,6 @@
 #define ICH_VMCR_ENG1_SHIFT	1
 #define ICH_VMCR_ENG1_MASK	(1 << ICH_VMCR_ENG1_SHIFT)
 
-/* ICH_VTR_EL2 bit definitions */
-#define ICH_VTR_PRI_BITS_SHIFT	29
-#define ICH_VTR_PRI_BITS_MASK	(7 << ICH_VTR_PRI_BITS_SHIFT)
-#define ICH_VTR_ID_BITS_SHIFT	23
-#define ICH_VTR_ID_BITS_MASK	(7 << ICH_VTR_ID_BITS_SHIFT)
-#define ICH_VTR_SEIS_SHIFT	22
-#define ICH_VTR_SEIS_MASK	(1 << ICH_VTR_SEIS_SHIFT)
-#define ICH_VTR_A3V_SHIFT	21
-#define ICH_VTR_A3V_MASK	(1 << ICH_VTR_A3V_SHIFT)
-#define ICH_VTR_TDS_SHIFT	19
-#define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
-
 /*
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
@@ -1062,8 +1032,11 @@
 #define PIE_RX		UL(0xa)
 #define PIE_RW		UL(0xc)
 #define PIE_RWX		UL(0xe)
+#define PIE_MASK	UL(0xf)
 
-#define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
+#define PIRx_ELx_BITS_PER_IDX		4
+#define PIRx_ELx_PERM_SHIFT(idx)	((idx) * PIRx_ELx_BITS_PER_IDX)
+#define PIRx_ELx_PERM_PREP(idx, perm)	(((perm) & PIE_MASK) << PIRx_ELx_PERM_SHIFT(idx))
 
 /*
  * Permission Overlay Extension (POE) permission encodings.
@@ -1074,12 +1047,14 @@
 #define POE_RX		UL(0x3)
 #define POE_W		UL(0x4)
 #define POE_RW		UL(0x5)
-#define POE_XW		UL(0x6)
-#define POE_RXW		UL(0x7)
+#define POE_WX		UL(0x6)
+#define POE_RWX		UL(0x7)
 #define POE_MASK	UL(0xf)
 
-/* Initial value for Permission Overlay Extension for EL0 */
-#define POR_EL0_INIT	POE_RXW
+#define POR_ELx_BITS_PER_IDX		4
+#define POR_ELx_PERM_SHIFT(idx)		((idx) * POR_ELx_BITS_PER_IDX)
+#define POR_ELx_PERM_GET(idx, reg)	(((reg) >> POR_ELx_PERM_SHIFT(idx)) & POE_MASK)
+#define POR_ELx_PERM_PREP(idx, perm)	(((perm) & POE_MASK) << POR_ELx_PERM_SHIFT(idx))
 
 /*
  * Definitions for Guarded Control Stack
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bc94e036a26b..eba1a98657f1 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -322,13 +322,6 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 	return true;
 }
 
-static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					     struct mm_struct *mm,
-					     unsigned long uaddr)
-{
-	__flush_tlb_page_nosync(mm, uaddr);
-}
-
 /*
  * If mprotect/munmap/etc occurs during TLB batched flushing, we need to
  * synchronise all the TLBI issued with a DSB to avoid the race mentioned in
@@ -396,33 +389,35 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 #define __flush_tlb_range_op(op, start, pages, stride,			\
 				asid, tlb_level, tlbi_user, lpa2)	\
 do {									\
+	typeof(start) __flush_start = start;				\
+	typeof(pages) __flush_pages = pages;				\
 	int num = 0;							\
 	int scale = 3;							\
 	int shift = lpa2 ? 16 : PAGE_SHIFT;				\
 	unsigned long addr;						\
 									\
-	while (pages > 0) {						\
+	while (__flush_pages > 0) {					\
 		if (!system_supports_tlb_range() ||			\
-		    pages == 1 ||					\
-		    (lpa2 && start != ALIGN(start, SZ_64K))) {		\
-			addr = __TLBI_VADDR(start, asid);		\
+		    __flush_pages == 1 ||				\
+		    (lpa2 && __flush_start != ALIGN(__flush_start, SZ_64K))) {	\
+			addr = __TLBI_VADDR(__flush_start, asid);	\
 			__tlbi_level(op, addr, tlb_level);		\
 			if (tlbi_user)					\
 				__tlbi_user_level(op, addr, tlb_level);	\
-			start += stride;				\
-			pages -= stride >> PAGE_SHIFT;			\
+			__flush_start += stride;			\
+			__flush_pages -= stride >> PAGE_SHIFT;		\
 			continue;					\
 		}							\
 									\
-		num = __TLBI_RANGE_NUM(pages, scale);			\
+		num = __TLBI_RANGE_NUM(__flush_pages, scale);		\
 		if (num >= 0) {						\
-			addr = __TLBI_VADDR_RANGE(start >> shift, asid, \
+			addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
 						scale, num, tlb_level);	\
 			__tlbi(r##op, addr);				\
 			if (tlbi_user)					\
 				__tlbi_user(r##op, addr);		\
-			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
-			pages -= __TLBI_RANGE_PAGES(num, scale);	\
+			__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
+			__flush_pages -= __TLBI_RANGE_PAGES(num, scale);\
 		}							\
 		scale--;						\
 	}								\
@@ -448,7 +443,7 @@ static inline bool __flush_tlb_range_limit_excess(unsigned long start,
 	return false;
 }
 
-static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
+static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
 				     unsigned long start, unsigned long end,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
@@ -460,12 +455,12 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
 	pages = (end - start) >> PAGE_SHIFT;
 
 	if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
-		flush_tlb_mm(vma->vm_mm);
+		flush_tlb_mm(mm);
 		return;
 	}
 
 	dsb(ishst);
-	asid = ASID(vma->vm_mm);
+	asid = ASID(mm);
 
 	if (last_level)
 		__flush_tlb_range_op(vale1is, start, pages, stride, asid,
@@ -474,7 +469,7 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
 		__flush_tlb_range_op(vae1is, start, pages, stride, asid,
 				     tlb_level, true, lpa2_is_enabled());
 
-	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
@@ -482,7 +477,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
 {
-	__flush_tlb_range_nosync(vma, start, end, stride,
+	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
 				 last_level, tlb_level);
 	dsb(ish);
 }
@@ -533,6 +528,12 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 	dsb(ish);
 	isb();
 }
+
+static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+		struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
+}
 #endif
 
 #endif
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index d780d1bd2eac..82cf1f879c61 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -109,10 +109,9 @@ static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned lon
 	int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr);
 	int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr);
 	int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr);
-	unsigned long dst, src, size;
+	unsigned long dst, size;
 
 	dst = regs->regs[dstreg];
-	src = regs->regs[srcreg];
 	size = regs->regs[sizereg];
 
 	/*
@@ -129,6 +128,7 @@ static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned lon
 		}
 	} else {
 		/* CPY* instruction */
+		unsigned long src = regs->regs[srcreg];
 		if (!(option_a ^ wrong_option)) {
 			/* Format is from Option B */
 			if (regs->pstate & PSR_N_BIT) {
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index 3e3c3fdb1842..61679070f595 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_H
 #define __ASM_VDSO_H
 
-#define __VVAR_PAGES    2
+#define __VDSO_PAGES    4
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index 778c1202bbbf..d60ea7a72a9c 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -104,7 +104,7 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	u64 res;
 
@@ -131,45 +131,33 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	const struct vdso_data *ret;
+	const struct vdso_time_data *ret;
 
 	/*
-	 * This simply puts &_vdso_data into ret. The reason why we don't use
-	 * `ret = _vdso_data` is that the compiler tends to optimise this in a
-	 * very suboptimal way: instead of keeping &_vdso_data in a register,
-	 * it goes through a relocation almost every time _vdso_data must be
+	 * This simply puts &_vdso_time_data into ret. The reason why we don't use
+	 * `ret = _vdso_time_data` is that the compiler tends to optimise this in a
+	 * very suboptimal way: instead of keeping &_vdso_time_data in a register,
+	 * it goes through a relocation almost every time _vdso_time_data must be
 	 * accessed (even in subfunctions). This is both time and space
 	 * consuming: each relocation uses a word in the code section, and it
 	 * has to be loaded at runtime.
 	 *
 	 * This trick hides the assignment from the compiler. Since it cannot
 	 * track where the pointer comes from, it will only use one relocation
-	 * where __arch_get_vdso_data() is called, and then keep the result in
-	 * a register.
+	 * where __aarch64_get_vdso_u_time_data() is called, and then keep the
+	 * result in a register.
 	 */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data));
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(&vdso_u_time_data));
 
 	return ret;
 }
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	const struct vdso_data *ret;
-
-	/* See __arch_get_vdso_data(). */
-	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
-
-	return ret;
-}
-#endif
-
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
-	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+	return vc->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
 }
 #define vdso_clocksource_ok	vdso_clocksource_ok
 
diff --git a/arch/arm64/include/asm/vdso/getrandom.h b/arch/arm64/include/asm/vdso/getrandom.h
index 342f807e2044..a2197da1951b 100644
--- a/arch/arm64/include/asm/vdso/getrandom.h
+++ b/arch/arm64/include/asm/vdso/getrandom.h
@@ -33,18 +33,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	/*
-	 * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace
-	 * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_
-	 * PAGE_OFFSET points to the real VVAR page.
-	 */
-	if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * (1UL << CONFIG_PAGE_SHIFT);
-	return &_vdso_rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 764d13e2916c..3322c7047d84 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -67,7 +67,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	u64 res;
 
@@ -99,19 +99,18 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
-static __always_inline
-const struct vdso_data *__arch_get_vdso_data(void)
+#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return _vdso_data;
-}
+	const struct vdso_time_data *ret = &vdso_u_time_data;
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
+	/* Work around invalid absolute relocations */
+	OPTIMIZER_HIDE_VAR(ret);
+
+	return ret;
 }
-#endif
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
+#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index eea51946d45a..de58951b8df6 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -2,44 +2,21 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET  480
-
 #ifndef __ASSEMBLY__
 
 #include <vdso/datapage.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 #define VDSO_PRECISION_MASK	~(0xFF00ULL<<48)
 
-extern struct vdso_data *vdso_data;
 
 /*
  * Update the vDSO data page to keep in sync with kernel timekeeping.
  */
 static __always_inline
-struct vdso_data *__arm64_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __arm64_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__arm64_get_k_vdso_rnd_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __arm64_get_k_vdso_rnd_data
-
-static __always_inline
-void __arm64_update_vsyscall(struct vdso_data *vdata)
+void __arm64_update_vsyscall(struct vdso_time_data *vdata)
 {
-	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
-	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
+	vdata->clock_data[CS_RAW].mask		= VDSO_PRECISION_MASK;
 }
 #define __arch_update_vsyscall __arm64_update_vsyscall
 
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 568bf858f319..af9d9acaf997 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -105,6 +105,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
 #define KVM_ARM_VCPU_HAS_EL2		7 /* Support nested virtualization */
+#define KVM_ARM_VCPU_HAS_EL2_E2H0	8 /* Limit NV support to E2H RES0 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -371,6 +372,7 @@ enum {
 #endif
 };
 
+/* Vendor hyper call function numbers 0-63 */
 #define KVM_REG_ARM_VENDOR_HYP_BMAP		KVM_REG_ARM_FW_FEAT_BMAP_REG(2)
 
 enum {
@@ -381,6 +383,17 @@ enum {
 #endif
 };
 
+/* Vendor hyper call function numbers 64-127 */
+#define KVM_REG_ARM_VENDOR_HYP_BMAP_2		KVM_REG_ARM_FW_FEAT_BMAP_REG(3)
+
+enum {
+	KVM_REG_ARM_VENDOR_HYP_BIT_DISCOVER_IMPL_VER	= 0,
+	KVM_REG_ARM_VENDOR_HYP_BIT_DISCOVER_IMPL_CPUS	= 1,
+#ifdef __KERNEL__
+	KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT,
+#endif
+};
+
 /* Device Control API on vm fd */
 #define KVM_ARM_VM_SMCCC_CTRL		0
 #define   KVM_ARM_VM_SMCCC_FILTER	0
@@ -403,6 +416,7 @@ enum {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
 #define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
 #define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ  9
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
 #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
 			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index e6f66491fbe9..b9a66fc146c9 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -379,7 +379,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
-	return ioremap_prot(phys, size, pgprot_val(prot));
+	return ioremap_prot(phys, size, prot);
 }
 
 /*
diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c
index deff21bfa680..b68e1d328d4c 100644
--- a/arch/arm64/kernel/compat_alignment.c
+++ b/arch/arm64/kernel/compat_alignment.c
@@ -368,6 +368,8 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs)
 		return 1;
 	}
 
+	if (!handler)
+		return 1;
 	type = handler(addr, instr, regs);
 
 	if (type == TYPE_ERROR || type == TYPE_FAULT)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 7ce555862895..6b0ad5070d3e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -14,31 +14,85 @@
 #include <asm/kvm_asm.h>
 #include <asm/smp_plat.h>
 
+static u64 target_impl_cpu_num;
+static struct target_impl_cpu *target_impl_cpus;
+
+bool cpu_errata_set_target_impl(u64 num, void *impl_cpus)
+{
+	if (target_impl_cpu_num || !num || !impl_cpus)
+		return false;
+
+	target_impl_cpu_num = num;
+	target_impl_cpus = impl_cpus;
+	return true;
+}
+
+static inline bool is_midr_in_range(struct midr_range const *range)
+{
+	int i;
+
+	if (!target_impl_cpu_num)
+		return midr_is_cpu_model_range(read_cpuid_id(), range->model,
+					       range->rv_min, range->rv_max);
+
+	for (i = 0; i < target_impl_cpu_num; i++) {
+		if (midr_is_cpu_model_range(target_impl_cpus[i].midr,
+					    range->model,
+					    range->rv_min, range->rv_max))
+			return true;
+	}
+	return false;
+}
+
+bool is_midr_in_range_list(struct midr_range const *ranges)
+{
+	while (ranges->model)
+		if (is_midr_in_range(ranges++))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(is_midr_in_range_list);
+
 static bool __maybe_unused
-is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
+__is_affected_midr_range(const struct arm64_cpu_capabilities *entry,
+			 u32 midr, u32 revidr)
 {
 	const struct arm64_midr_revidr *fix;
-	u32 midr = read_cpuid_id(), revidr;
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	if (!is_midr_in_range(midr, &entry->midr_range))
+	if (!is_midr_in_range(&entry->midr_range))
 		return false;
 
 	midr &= MIDR_REVISION_MASK | MIDR_VARIANT_MASK;
-	revidr = read_cpuid(REVIDR_EL1);
 	for (fix = entry->fixed_revs; fix && fix->revidr_mask; fix++)
 		if (midr == fix->midr_rv && (revidr & fix->revidr_mask))
 			return false;
-
 	return true;
 }
 
 static bool __maybe_unused
+is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int i;
+
+	if (!target_impl_cpu_num) {
+		WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+		return __is_affected_midr_range(entry, read_cpuid_id(),
+						read_cpuid(REVIDR_EL1));
+	}
+
+	for (i = 0; i < target_impl_cpu_num; i++) {
+		if (__is_affected_midr_range(entry, target_impl_cpus[i].midr,
+					     target_impl_cpus[i].midr))
+			return true;
+	}
+	return false;
+}
+
+static bool __maybe_unused
 is_affected_midr_range_list(const struct arm64_cpu_capabilities *entry,
 			    int scope)
 {
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list);
+	return is_midr_in_range_list(entry->midr_range_list);
 }
 
 static bool __maybe_unused
@@ -186,12 +240,48 @@ static bool __maybe_unused
 has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 				int scope)
 {
-	u32 midr = read_cpuid_id();
 	bool has_dic = read_cpuid_cachetype() & BIT(CTR_EL0_DIC_SHIFT);
 	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range(midr, &range) && has_dic;
+	return is_midr_in_range(&range) && has_dic;
+}
+
+static const struct midr_range impdef_pmuv3_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
+	{},
+};
+
+static bool has_impdef_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	unsigned int pmuver;
+
+	if (!is_kernel_in_hyp_mode())
+		return false;
+
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
+						      ID_AA64DFR0_EL1_PMUVer_SHIFT);
+	if (pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return false;
+
+	return is_midr_in_range_list(impdef_pmuv3_cpus);
+}
+
+static void cpu_enable_impdef_pmuv3_traps(const struct arm64_cpu_capabilities *__unused)
+{
+	sysreg_clear_set_s(SYS_HACR_EL2, 0, BIT(56));
 }
 
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
@@ -245,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
 	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
 	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
 	/* Cavium ThunderX, T81 pass 1.0 */
@@ -795,5 +885,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 				})),
 	},
 	{
+		.desc = "Apple IMPDEF PMUv3 Traps",
+		.capability = ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_impdef_pmuv3,
+		.cpu_enable = cpu_enable_impdef_pmuv3_traps,
+	},
+	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d561cf3b8ac7..4c46d80aa64b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -86,6 +86,7 @@
 #include <asm/kvm_host.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
+#include <asm/hypervisor.h>
 #include <asm/processor.h>
 #include <asm/smp.h>
 #include <asm/sysreg.h>
@@ -113,7 +114,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC
 
 DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS);
 
-bool arm64_use_ng_mappings = false;
+/*
+ * arm64_use_ng_mappings must be placed in the .data section, otherwise it
+ * ends up in the .bss section where it is initialized in early_map_kernel()
+ * after the MMU (with the idmap) was enabled. create_init_idmap() - which
+ * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG -
+ * may end up generating an incorrect idmap page table attributes.
+ */
+bool arm64_use_ng_mappings __read_mostly = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
 DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
@@ -497,6 +505,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr4[] = {
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_E2H0_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_NV_frac_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1792,7 +1801,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 	char const *str = "kpti command line option";
 	bool meltdown_safe;
 
-	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+	meltdown_safe = is_midr_in_range_list(kpti_safe_list);
 
 	/* Defer to CPU feature registers */
 	if (has_cpuid_feature(entry, scope))
@@ -1862,7 +1871,7 @@ static bool has_nv1(const struct arm64_cpu_capabilities *entry, int scope)
 
 	return (__system_matches_cap(ARM64_HAS_NESTED_VIRT) &&
 		!(has_cpuid_feature(entry, scope) ||
-		  is_midr_in_range_list(read_cpuid_id(), nv1_ni_list)));
+		  is_midr_in_range_list(nv1_ni_list)));
 }
 
 #if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2)
@@ -1898,6 +1907,28 @@ static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope)
 }
 #endif
 
+#ifdef CONFIG_HW_PERF_EVENTS
+static bool has_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	unsigned int pmuver;
+
+	/*
+	 * PMUVer follows the standard ID scheme for an unsigned field with the
+	 * exception of 0xF (IMP_DEF) which is treated specially and implies
+	 * FEAT_PMUv3 is not implemented.
+	 *
+	 * See DDI0487L.a D24.1.3.2 for more details.
+	 */
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
+						      ID_AA64DFR0_EL1_PMUVer_SHIFT);
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return false;
+
+	return pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP;
+}
+#endif
+
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 #define KPTI_NG_TEMP_VA		(-(1UL << PMD_SHIFT))
 
@@ -2045,7 +2076,7 @@ static bool cpu_has_broken_dbm(void)
 		{},
 	};
 
-	return is_midr_in_range_list(read_cpuid_id(), cpus);
+	return is_midr_in_range_list(cpus);
 }
 
 static bool cpu_can_use_dbm(const struct arm64_cpu_capabilities *cap)
@@ -2162,7 +2193,7 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap,
 	if (kvm_get_mode() != KVM_MODE_NV)
 		return false;
 
-	if (!has_cpuid_feature(cap, scope)) {
+	if (!cpucap_multi_entry_cap_matches(cap, scope)) {
 		pr_warn("unavailable: %s\n", cap->desc);
 		return false;
 	}
@@ -2519,7 +2550,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_NESTED_VIRT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
 		.matches = has_nested_virt_support,
-		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
+		.match_list = (const struct arm64_cpu_capabilities []){
+			{
+				.matches = has_cpuid_feature,
+				ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2)
+			},
+			{
+				.matches = has_cpuid_feature,
+				ARM64_CPUID_FIELDS(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)
+			},
+			{ /* Sentinel */ }
+		},
 	},
 	{
 		.capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE,
@@ -2999,6 +3040,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, GCS, IMP)
 	},
 #endif
+#ifdef CONFIG_HW_PERF_EVENTS
+	{
+		.desc = "PMUv3",
+		.capability = ARM64_HAS_PMUV3,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_pmuv3,
+	},
+#endif
 	{},
 };
 
@@ -3680,6 +3729,7 @@ unsigned long cpu_get_elf_hwcap3(void)
 
 static void __init setup_boot_cpu_capabilities(void)
 {
+	kvm_arm_target_impl_cpu_init();
 	/*
 	 * The boot CPU's feature register values have been recorded. Detect
 	 * boot cpucaps and local cpucaps for the boot CPU, then enable and
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 2e94d20c4ac7..b735f4c2fe5e 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -27,9 +27,10 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 	int ret = 1;
 	unsigned long addr;
 	void *tags = NULL;
+	int locked = 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
-		struct page *page = get_dump_page(addr);
+		struct page *page = get_dump_page(addr, &locked);
 
 		/*
 		 * get_dump_page() returns NULL when encountering an empty
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index d7c0d023dfe5..5a890714ee2e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -320,14 +320,13 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	 * dealing with an out-of-range condition, we can assume it
 	 * is due to a module being loaded far away from the kernel.
 	 *
-	 * NOTE: __module_text_address() must be called with preemption
-	 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+	 * NOTE: __module_text_address() must be called within a RCU read
+	 * section, but we can rely on ftrace_lock to ensure that 'mod'
 	 * retains its validity throughout the remainder of this code.
 	 */
 	if (!mod) {
-		preempt_disable();
+		guard(rcu)();
 		mod = __module_text_address(pc);
-		preempt_enable();
 	}
 
 	if (WARN_ON(!mod))
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 5ab1970ee543..2ce73525de2c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -298,25 +298,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el2, x0
 	isb
 0:
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-
-	/*
-	 * Compliant CPUs advertise their VHE-onlyness with
-	 * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
-	 * RES1 in that case. Publish the E2H bit early so that
-	 * it can be picked up by the init_el2_state macro.
-	 *
-	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
-	 * don't advertise it (they predate this relaxation).
-	 */
-	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
-	tbz	x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
-	orr	x0, x0, #HCR_E2H
-1:
-	msr	hcr_el2, x0
-	isb
 
+	init_el2_hcr	HCR_HOST_NVHE_FLAGS
 	init_el2_state
 
 	/* Hypervisor stub */
@@ -339,7 +322,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 3:
-	__init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
 
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index ef3a69cc398e..2004b4f41ade 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,9 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override	= id_aa64smfr0_override);
 PROVIDE(__pi_id_aa64zfr0_override	= id_aa64zfr0_override);
 PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
 PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus	= cavium_erratum_27456_cpus);
-#endif
 PROVIDE(__pi__ctype			= _ctype);
 PROVIDE(__pi_memstart_offset_seed	= memstart_offset_seed);
 
@@ -112,11 +109,6 @@ KVM_NVHE_ALIAS(broken_cntvoff_key);
 KVM_NVHE_ALIAS(__start___kvm_ex_table);
 KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 
-/* PMU available static key */
-#ifdef CONFIG_HW_PERF_EVENTS
-KVM_NVHE_ALIAS(kvm_arm_pmu_available);
-#endif
-
 /* Position-independent library routines */
 KVM_NVHE_ALIAS_HYP(clear_page, __pi_clear_page);
 KVM_NVHE_ALIAS_HYP(copy_page, __pi_copy_page);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043f324b..c6650cfe706c 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
 	dsb(ishst);
 }
 
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+	static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+		/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+		/* Cavium ThunderX, T81 pass 1.0 */
+		MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+		{},
+	};
+
+	for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+		if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+					    r->rv_min, r->rv_max))
+			return false;
+	}
+
+	return true;
+}
+
 asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 {
 	static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 		u64 kaslr_seed = kaslr_early_init(fdt, chosen);
 
 		if (kaslr_seed && kaslr_requires_kpti())
-			arm64_use_ng_mappings = true;
+			arm64_use_ng_mappings = ng_mappings_allowed();
 
 		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
 	}
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
index 2b69e3beeef8..81345f68f9fc 100644
--- a/arch/arm64/kernel/pi/map_range.c
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -31,7 +31,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 {
 	u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
 	pteval_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
-	int lshift = (3 - level) * (PAGE_SHIFT - 3);
+	int lshift = (3 - level) * PTDESC_TABLE_SHIFT;
 	u64 lmask = (PAGE_SIZE << lshift) - 1;
 
 	start	&= PAGE_MASK;
@@ -45,12 +45,12 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 	 * clearing the mapping
 	 */
 	if (protval)
-		protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
+		protval |= (level == 2) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
 
 	while (start < end) {
 		u64 next = min((start | lmask) + 1, PAGE_ALIGN(end));
 
-		if (level < 3 && (start | next | pa) & lmask) {
+		if (level < 2 || (level == 2 && (start | next | pa) & lmask)) {
 			/*
 			 * This chunk needs a finer grained mapping. Create a
 			 * table mapping if necessary and recurse.
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index da53722f95d4..edf1783ffc81 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -172,7 +172,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void)
 		return SPECTRE_UNAFFECTED;
 
 	/* Alternatively, we have a list of unaffected CPUs */
-	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+	if (is_midr_in_range_list(spectre_v2_safe_list))
 		return SPECTRE_UNAFFECTED;
 
 	return SPECTRE_VULNERABLE;
@@ -331,7 +331,7 @@ bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope)
 	};
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range_list(read_cpuid_id(), spectre_v3a_unsafe_list);
+	return is_midr_in_range_list(spectre_v3a_unsafe_list);
 }
 
 void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
@@ -475,7 +475,7 @@ static enum mitigation_state spectre_v4_get_cpu_hw_mitigation_state(void)
 		{ /* sentinel */ },
 	};
 
-	if (is_midr_in_range_list(read_cpuid_id(), spectre_v4_safe_list))
+	if (is_midr_in_range_list(spectre_v4_safe_list))
 		return SPECTRE_UNAFFECTED;
 
 	/* CPU features are detected first */
@@ -845,52 +845,90 @@ static unsigned long system_bhb_mitigations;
  * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any
  * SCOPE_SYSTEM call will give the right answer.
  */
-u8 spectre_bhb_loop_affected(int scope)
+static bool is_spectre_bhb_safe(int scope)
+{
+	static const struct midr_range spectre_bhb_safe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A510),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A520),
+		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
+		{},
+	};
+	static bool all_safe = true;
+
+	if (scope != SCOPE_LOCAL_CPU)
+		return all_safe;
+
+	if (is_midr_in_range_list(spectre_bhb_safe_list))
+		return true;
+
+	all_safe = false;
+
+	return false;
+}
+
+static u8 spectre_bhb_loop_affected(void)
 {
 	u8 k = 0;
-	static u8 max_bhb_k;
-
-	if (scope == SCOPE_LOCAL_CPU) {
-		static const struct midr_range spectre_bhb_k32_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k24_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
-			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k11_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_AMPERE1),
-			{},
-		};
-		static const struct midr_range spectre_bhb_k8_list[] = {
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-			MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-			{},
-		};
-
-		if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list))
-			k = 32;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list))
-			k = 24;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list))
-			k = 11;
-		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list))
-			k =  8;
-
-		max_bhb_k = max(max_bhb_k, k);
-	} else {
-		k = max_bhb_k;
-	}
+
+	static const struct midr_range spectre_bhb_k132_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k38_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k32_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k24_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A76AE),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
+		MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD),
+		MIDR_ALL_VERSIONS(MIDR_HISI_HIP09),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k11_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_AMPERE1),
+		{},
+	};
+	static const struct midr_range spectre_bhb_k8_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		{},
+	};
+
+	if (is_midr_in_range_list(spectre_bhb_k132_list))
+		k = 132;
+	else if (is_midr_in_range_list(spectre_bhb_k38_list))
+		k = 38;
+	else if (is_midr_in_range_list(spectre_bhb_k32_list))
+		k = 32;
+	else if (is_midr_in_range_list(spectre_bhb_k24_list))
+		k = 24;
+	else if (is_midr_in_range_list(spectre_bhb_k11_list))
+		k = 11;
+	else if (is_midr_in_range_list(spectre_bhb_k8_list))
+		k =  8;
 
 	return k;
 }
@@ -916,29 +954,13 @@ static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void)
 	}
 }
 
-static bool is_spectre_bhb_fw_affected(int scope)
+static bool has_spectre_bhb_fw_mitigation(void)
 {
-	static bool system_affected;
 	enum mitigation_state fw_state;
 	bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE;
-	static const struct midr_range spectre_bhb_firmware_mitigated_list[] = {
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-		{},
-	};
-	bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(),
-					 spectre_bhb_firmware_mitigated_list);
-
-	if (scope != SCOPE_LOCAL_CPU)
-		return system_affected;
 
 	fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-	if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) {
-		system_affected = true;
-		return true;
-	}
-
-	return false;
+	return has_smccc && fw_state == SPECTRE_MITIGATED;
 }
 
 static bool supports_ecbhb(int scope)
@@ -954,6 +976,8 @@ static bool supports_ecbhb(int scope)
 						    ID_AA64MMFR1_EL1_ECBHB_SHIFT);
 }
 
+static u8 max_bhb_k;
+
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 			     int scope)
 {
@@ -962,16 +986,23 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
 	if (supports_csv2p3(scope))
 		return false;
 
-	if (supports_clearbhb(scope))
-		return true;
+	if (is_spectre_bhb_safe(scope))
+		return false;
 
-	if (spectre_bhb_loop_affected(scope))
-		return true;
+	/*
+	 * At this point the core isn't known to be "safe" so we're going to
+	 * assume it's vulnerable. We still need to update `max_bhb_k` though,
+	 * but only if we aren't mitigating with clearbhb though.
+	 */
+	if (scope == SCOPE_LOCAL_CPU && !supports_clearbhb(SCOPE_LOCAL_CPU))
+		max_bhb_k = max(max_bhb_k, spectre_bhb_loop_affected());
 
-	if (is_spectre_bhb_fw_affected(scope))
-		return true;
+	return true;
+}
 
-	return false;
+u8 get_spectre_bhb_loop_value(void)
+{
+	return max_bhb_k;
 }
 
 static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
@@ -991,7 +1022,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
 	isb();
 }
 
-static bool __read_mostly __nospectre_bhb;
+bool __read_mostly __nospectre_bhb;
 static int __init parse_spectre_bhb_param(char *str)
 {
 	__nospectre_bhb = true;
@@ -1002,7 +1033,7 @@ early_param("nospectre_bhb", parse_spectre_bhb_param);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 {
 	bp_hardening_cb_t cpu_cb;
-	enum mitigation_state fw_state, state = SPECTRE_VULNERABLE;
+	enum mitigation_state state = SPECTRE_VULNERABLE;
 	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
 
 	if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU))
@@ -1028,7 +1059,7 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_INSN, &system_bhb_mitigations);
-	} else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) {
+	} else if (spectre_bhb_loop_affected()) {
 		/*
 		 * Ensure KVM uses the indirect vector which will have the
 		 * branchy-loop added. A57/A72-r0 will already have selected
@@ -1041,37 +1072,39 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_LOOP, &system_bhb_mitigations);
-	} else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) {
-		fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
-		if (fw_state == SPECTRE_MITIGATED) {
-			/*
-			 * Ensure KVM uses one of the spectre bp_hardening
-			 * vectors. The indirect vector doesn't include the EL3
-			 * call, so needs upgrading to
-			 * HYP_VECTOR_SPECTRE_INDIRECT.
-			 */
-			if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
-				data->slot += 1;
-
-			this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
-
-			/*
-			 * The WA3 call in the vectors supersedes the WA1 call
-			 * made during context-switch. Uninstall any firmware
-			 * bp_hardening callback.
-			 */
-			cpu_cb = spectre_v2_get_sw_mitigation_cb();
-			if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
-				__this_cpu_write(bp_hardening_data.fn, NULL);
-
-			state = SPECTRE_MITIGATED;
-			set_bit(BHB_FW, &system_bhb_mitigations);
-		}
+	} else if (has_spectre_bhb_fw_mitigation()) {
+		/*
+		 * Ensure KVM uses one of the spectre bp_hardening
+		 * vectors. The indirect vector doesn't include the EL3
+		 * call, so needs upgrading to
+		 * HYP_VECTOR_SPECTRE_INDIRECT.
+		 */
+		if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
+			data->slot += 1;
+
+		this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
+
+		/*
+		 * The WA3 call in the vectors supersedes the WA1 call
+		 * made during context-switch. Uninstall any firmware
+		 * bp_hardening callback.
+		 */
+		cpu_cb = spectre_v2_get_sw_mitigation_cb();
+		if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
+			__this_cpu_write(bp_hardening_data.fn, NULL);
+
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_FW, &system_bhb_mitigations);
 	}
 
 	update_mitigation_state(&spectre_bhb_state, state);
 }
 
+bool is_spectre_bhb_fw_mitigated(void)
+{
+	return test_bit(BHB_FW, &system_bhb_mitigations);
+}
+
 /* Patched to NOP when enabled */
 void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
 						     __le32 *origptr,
@@ -1100,7 +1133,6 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 {
 	u8 rd;
 	u32 insn;
-	u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM);
 
 	BUG_ON(nr_inst != 1); /* MOV -> MOV */
 
@@ -1109,7 +1141,7 @@ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
 
 	insn = le32_to_cpu(*origptr);
 	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
-	insn = aarch64_insn_gen_movewide(rd, loop_count, 0,
+	insn = aarch64_insn_gen_movewide(rd, max_bhb_k, 0,
 					 AARCH64_INSN_VARIANT_64BIT,
 					 AARCH64_INSN_MOVEWIDE_ZERO);
 	*updptr++ = cpu_to_le32(insn);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 99ea26d400ff..a7c37afb4ebe 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -91,7 +91,7 @@ static void save_reset_user_access_state(struct user_access_state *ua_state)
 		u64 por_enable_all = 0;
 
 		for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
-			por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+			por_enable_all |= POR_ELx_PERM_PREP(pkey, POE_RWX);
 
 		ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
 		write_sysreg_s(por_enable_all, SYS_POR_EL0);
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index cb180684d10d..5d07ee85bdae 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -15,8 +15,11 @@
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_smt.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
+#include <linux/sched/isolation.h>
+#include <linux/xarray.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
@@ -37,17 +40,28 @@ static bool __init acpi_cpu_is_threaded(int cpu)
 	return !!is_threaded;
 }
 
+struct cpu_smt_info {
+	unsigned int thread_num;
+	int core_id;
+};
+
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
 int __init parse_acpi_topology(void)
 {
+	unsigned int max_smt_thread_num = 1;
+	struct cpu_smt_info *entry;
+	struct xarray hetero_cpu;
+	unsigned long hetero_id;
 	int cpu, topology_id;
 
 	if (acpi_disabled)
 		return 0;
 
+	xa_init(&hetero_cpu);
+
 	for_each_possible_cpu(cpu) {
 		topology_id = find_acpi_cpu_topology(cpu, 0);
 		if (topology_id < 0)
@@ -57,6 +71,34 @@ int __init parse_acpi_topology(void)
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
+
+			/*
+			 * In the PPTT, CPUs below a node with the 'identical
+			 * implementation' flag have the same number of threads.
+			 * Count the number of threads for only one CPU (i.e.
+			 * one core_id) among those with the same hetero_id.
+			 * See the comment of find_acpi_cpu_topology_hetero_id()
+			 * for more details.
+			 *
+			 * One entry is created for each node having:
+			 * - the 'identical implementation' flag
+			 * - its parent not having the flag
+			 */
+			hetero_id = find_acpi_cpu_topology_hetero_id(cpu);
+			entry = xa_load(&hetero_cpu, hetero_id);
+			if (!entry) {
+				entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+				WARN_ON_ONCE(!entry);
+
+				if (entry) {
+					entry->core_id = topology_id;
+					entry->thread_num = 1;
+					xa_store(&hetero_cpu, hetero_id,
+						 entry, GFP_KERNEL);
+				}
+			} else if (entry->core_id == topology_id) {
+				entry->thread_num++;
+			}
 		} else {
 			cpu_topology[cpu].thread_id  = -1;
 			cpu_topology[cpu].core_id    = topology_id;
@@ -67,6 +109,19 @@ int __init parse_acpi_topology(void)
 		cpu_topology[cpu].package_id = topology_id;
 	}
 
+	/*
+	 * This is a short loop since the number of XArray elements is the
+	 * number of heterogeneous CPU clusters. On a homogeneous system
+	 * there's only one entry in the XArray.
+	 */
+	xa_for_each(&hetero_cpu, hetero_id, entry) {
+		max_smt_thread_num = max(max_smt_thread_num, entry->thread_num);
+		xa_erase(&hetero_cpu, hetero_id);
+		kfree(entry);
+	}
+
+	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+	xa_destroy(&hetero_cpu);
 	return 0;
 }
 #endif
@@ -88,18 +143,28 @@ int __init parse_acpi_topology(void)
  * initialized.
  */
 static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
-static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
-static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
 
+struct amu_cntr_sample {
+	u64		arch_const_cycles_prev;
+	u64		arch_core_cycles_prev;
+	unsigned long	last_scale_update;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct amu_cntr_sample, cpu_amu_samples);
+
 void update_freq_counters_refs(void)
 {
-	this_cpu_write(arch_core_cycles_prev, read_corecnt());
-	this_cpu_write(arch_const_cycles_prev, read_constcnt());
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
+
+	amu_sample->arch_core_cycles_prev = read_corecnt();
+	amu_sample->arch_const_cycles_prev = read_constcnt();
 }
 
 static inline bool freq_counters_valid(int cpu)
 {
+	struct amu_cntr_sample *amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
 	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
 		return false;
 
@@ -108,8 +173,8 @@ static inline bool freq_counters_valid(int cpu)
 		return false;
 	}
 
-	if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
-		     !per_cpu(arch_core_cycles_prev, cpu))) {
+	if (unlikely(!amu_sample->arch_const_cycles_prev ||
+		     !amu_sample->arch_core_cycles_prev)) {
 		pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
 		return false;
 	}
@@ -152,17 +217,22 @@ void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 
 static void amu_scale_freq_tick(void)
 {
+	struct amu_cntr_sample *amu_sample = this_cpu_ptr(&cpu_amu_samples);
 	u64 prev_core_cnt, prev_const_cnt;
 	u64 core_cnt, const_cnt, scale;
 
-	prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
-	prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+	prev_const_cnt = amu_sample->arch_const_cycles_prev;
+	prev_core_cnt = amu_sample->arch_core_cycles_prev;
 
 	update_freq_counters_refs();
 
-	const_cnt = this_cpu_read(arch_const_cycles_prev);
-	core_cnt = this_cpu_read(arch_core_cycles_prev);
+	const_cnt = amu_sample->arch_const_cycles_prev;
+	core_cnt = amu_sample->arch_core_cycles_prev;
 
+	/*
+	 * This should not happen unless the AMUs have been reset and the
+	 * counter values have not been restored - unlikely
+	 */
 	if (unlikely(core_cnt <= prev_core_cnt ||
 		     const_cnt <= prev_const_cnt))
 		return;
@@ -182,6 +252,8 @@ static void amu_scale_freq_tick(void)
 
 	scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
 	this_cpu_write(arch_freq_scale, (unsigned long)scale);
+
+	amu_sample->last_scale_update = jiffies;
 }
 
 static struct scale_freq_data amu_sfd = {
@@ -189,6 +261,96 @@ static struct scale_freq_data amu_sfd = {
 	.set_freq_scale = amu_scale_freq_tick,
 };
 
+static __always_inline bool amu_fie_cpu_supported(unsigned int cpu)
+{
+	return cpumask_available(amu_fie_cpus) &&
+		cpumask_test_cpu(cpu, amu_fie_cpus);
+}
+
+void arch_cpu_idle_enter(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (!amu_fie_cpu_supported(cpu))
+		return;
+
+	/* Kick in AMU update but only if one has not happened already */
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK) &&
+	    time_is_before_jiffies(per_cpu(cpu_amu_samples.last_scale_update, cpu)))
+		amu_scale_freq_tick();
+}
+
+#define AMU_SAMPLE_EXP_MS	20
+
+int arch_freq_get_on_cpu(int cpu)
+{
+	struct amu_cntr_sample *amu_sample;
+	unsigned int start_cpu = cpu;
+	unsigned long last_update;
+	unsigned int freq = 0;
+	u64 scale;
+
+	if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
+		return -EOPNOTSUPP;
+
+	while (1) {
+
+		amu_sample = per_cpu_ptr(&cpu_amu_samples, cpu);
+
+		last_update = amu_sample->last_scale_update;
+
+		/*
+		 * For those CPUs that are in full dynticks mode, or those that have
+		 * not seen tick for a while, try an alternative source for the counters
+		 * (and thus freq scale), if available, for given policy: this boils
+		 * down to identifying an active cpu within the same freq domain, if any.
+		 */
+		if (!housekeeping_cpu(cpu, HK_TYPE_TICK) ||
+		    time_is_before_jiffies(last_update + msecs_to_jiffies(AMU_SAMPLE_EXP_MS))) {
+			struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+			int ref_cpu;
+
+			if (!policy)
+				return -EINVAL;
+
+			if (!cpumask_intersects(policy->related_cpus,
+						housekeeping_cpumask(HK_TYPE_TICK))) {
+				cpufreq_cpu_put(policy);
+				return -EOPNOTSUPP;
+			}
+
+			for_each_cpu_wrap(ref_cpu, policy->cpus, cpu + 1) {
+				if (ref_cpu == start_cpu) {
+					/* Prevent verifying same CPU twice */
+					ref_cpu = nr_cpu_ids;
+					break;
+				}
+				if (!idle_cpu(ref_cpu))
+					break;
+			}
+
+			cpufreq_cpu_put(policy);
+
+			if (ref_cpu >= nr_cpu_ids)
+				/* No alternative to pull info from */
+				return -EAGAIN;
+
+			cpu = ref_cpu;
+		} else {
+			break;
+		}
+	}
+	/*
+	 * Reversed computation to the one used to determine
+	 * the arch_freq_scale value
+	 * (see amu_scale_freq_tick for details)
+	 */
+	scale = arch_scale_freq_capacity(cpu);
+	freq = scale * arch_scale_freq_ref(cpu);
+	freq >>= SCHED_CAPACITY_SHIFT;
+	return freq;
+}
+
 static void amu_fie_setup(const struct cpumask *cpus)
 {
 	int cpu;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 4e26bd356a48..529cff825531 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -172,14 +172,6 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 	printk("%sCode: %s\n", lvl, str);
 }
 
-#ifdef CONFIG_PREEMPT
-#define S_PREEMPT " PREEMPT"
-#elif defined(CONFIG_PREEMPT_RT)
-#define S_PREEMPT " PREEMPT_RT"
-#else
-#define S_PREEMPT ""
-#endif
-
 #define S_SMP " SMP"
 
 static int __die(const char *str, long err, struct pt_regs *regs)
@@ -187,7 +179,7 @@ static int __die(const char *str, long err, struct pt_regs *regs)
 	static int die_counter;
 	int ret;
 
-	pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n",
+	pr_emerg("Internal error: %s: %016lx [#%d] " S_SMP "\n",
 		 str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index e8ed8e5b713b..78ddf6bdecad 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,7 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
@@ -57,12 +57,6 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = {
 #endif /* CONFIG_COMPAT_VDSO */
 };
 
-/*
- * The vDSO data page.
- */
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
@@ -104,78 +98,6 @@ static int __init __vdso_init(enum vdso_abi abi)
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-static const struct vm_special_mapping vvar_map;
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_map))
-			zap_vma_pages(vma);
-	}
-
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_special_mapping vvar_map = {
-	.name   = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
@@ -185,11 +107,11 @@ static int __setup_additional_pages(enum vdso_abi abi,
 	unsigned long gp_flags = 0;
 	void *ret;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 
 	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_mapping_len = vdso_text_len + VDSO_NR_PAGES * PAGE_SIZE;
 
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
@@ -197,20 +119,19 @@ static int __setup_additional_pages(enum vdso_abi abi,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_PFNMAP,
-				       &vvar_map);
+	ret = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(ret))
 		goto up_fail;
 
 	if (system_supports_bti_kernel())
 		gp_flags = VM_ARM64_BTI;
 
-	vdso_base += VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_base += VDSO_NR_PAGES * PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
 				       VM_READ|VM_EXEC|gp_flags|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
 		goto up_fail;
@@ -336,7 +257,8 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	 */
 	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
 				       VM_READ | VM_EXEC |
-				       VM_MAYREAD | VM_MAYEXEC,
+				       VM_MAYREAD | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_VECTORS]);
 
 	return PTR_ERR_OR_ZERO(ret);
@@ -359,7 +281,8 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	 */
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
-				       VM_MAYWRITE | VM_MAYEXEC,
+				       VM_MAYWRITE | VM_MAYEXEC |
+				       VM_SEALED_SYSMAP,
 				       &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
 	if (IS_ERR(ret))
 		goto out;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 35685c036044..5e27e46aa496 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -7,7 +7,7 @@
 #
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso := vgettimeofday.o note.o sigreturn.o vgetrandom.o vgetrandom-chacha.o
 
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 47ad6944f9f0..52314be29191 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -20,11 +20,8 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-	PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 25a2cb6317f3..f2dfdc7dc818 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -3,7 +3,7 @@
 # Makefile for vdso32
 #
 
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Same as cc-*option, but using CC_COMPAT instead of CC
 ifeq ($(CONFIG_CC_IS_CLANG), y)
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index 732702a187e9..e02b27487ce8 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -12,16 +12,15 @@
 #include <asm/page.h>
 #include <asm/vdso.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
 OUTPUT_ARCH(arm)
 
 SECTIONS
 {
-	PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index ead632ad01b4..096e45acadb2 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -71,8 +71,8 @@ config PTDUMP_STAGE2_DEBUGFS
 	depends on KVM
 	depends on DEBUG_KERNEL
 	depends on DEBUG_FS
-	depends on GENERIC_PTDUMP
-	select PTDUMP_CORE
+	depends on ARCH_HAS_PTDUMP
+	select PTDUMP
 	default n
 	help
 	  Say Y here if you want to show the stage-2 kernel pagetables
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 3cf7adb2b503..209bc76263f1 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -23,7 +23,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
 	 vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
-	 vgic/vgic-its.o vgic/vgic-debug.o
+	 vgic/vgic-its.o vgic/vgic-debug.o vgic/vgic-v3-nested.o
 
 kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o pmu.o
 kvm-$(CONFIG_ARM64_PTR_AUTH)  += pauth.o
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 70802e4c91cf..5133dcbfe9f7 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1070,8 +1070,7 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid)
 	else
 		ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset;
 
-	hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	ctxt->hrtimer.function = kvm_hrtimer_expire;
+	hrtimer_setup(&ctxt->hrtimer, kvm_hrtimer_expire, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
 
 	switch (timerid) {
 	case TIMER_PTIMER:
@@ -1098,8 +1097,8 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 		timer_set_offset(vcpu_ptimer(vcpu), 0);
 	}
 
-	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	timer->bg_timer.function = kvm_bg_timer_expire;
+	hrtimer_setup(&timer->bg_timer, kvm_bg_timer_expire, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 }
 
 void kvm_timer_init_vm(struct kvm *kvm)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b8e55a441282..19ca57def629 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -125,6 +125,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		}
 		mutex_unlock(&kvm->slots_lock);
 		break;
+	case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS:
+		mutex_lock(&kvm->lock);
+		if (!kvm->created_vcpus) {
+			r = 0;
+			set_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags);
+		}
+		mutex_unlock(&kvm->lock);
+		break;
 	default:
 		break;
 	}
@@ -313,6 +321,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_SYSTEM_SUSPEND:
 	case KVM_CAP_IRQFD_RESAMPLE:
 	case KVM_CAP_COUNTER_OFFSET:
+	case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
@@ -366,7 +375,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = get_num_wrps();
 		break;
 	case KVM_CAP_ARM_PMU_V3:
-		r = kvm_arm_support_pmu_v3();
+		r = kvm_supports_guest_pmuv3();
 		break;
 	case KVM_CAP_ARM_INJECT_SERROR_ESR:
 		r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN);
@@ -466,7 +475,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	return kvm_share_hyp(vcpu, vcpu + 1);
+	err = kvm_share_hyp(vcpu, vcpu + 1);
+	if (err)
+		kvm_vgic_vcpu_destroy(vcpu);
+
+	return err;
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
@@ -560,6 +573,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
+	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
 	 * previously run on the same physical CPU, call into the
@@ -576,8 +599,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 nommu:
 	vcpu->cpu = cpu;
 
-	kvm_vgic_load(vcpu);
+	/*
+	 * The timer must be loaded before the vgic to correctly set up physical
+	 * interrupt deactivation in nested state (e.g. timer interrupt).
+	 */
 	kvm_timer_vcpu_load(vcpu);
+	kvm_vgic_load(vcpu);
 	kvm_vcpu_load_debug(vcpu);
 	if (has_vhe())
 		kvm_vcpu_load_vhe(vcpu);
@@ -815,6 +842,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_vgic_vcpu_nv_init(vcpu);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * This needs to happen after any restriction has been applied
 	 * to the feature set.
@@ -825,14 +858,20 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
-	ret = kvm_arm_pmu_v3_enable(vcpu);
-	if (ret)
-		return ret;
+	if (kvm_vcpu_has_pmu(vcpu)) {
+		ret = kvm_arm_pmu_v3_enable(vcpu);
+		if (ret)
+			return ret;
+	}
 
 	if (is_protected_kvm_enabled()) {
 		ret = pkvm_create_hyp_vm(kvm);
 		if (ret)
 			return ret;
+
+		ret = pkvm_create_hyp_vcpu(vcpu);
+		if (ret)
+			return ret;
 	}
 
 	mutex_lock(&kvm->arch.config_lock);
@@ -1138,19 +1177,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
-		kvm_pmu_flush_hwstate(vcpu);
+		if (kvm_vcpu_has_pmu(vcpu))
+			kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
 
@@ -1169,7 +1197,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
-			kvm_pmu_sync_hwstate(vcpu);
+			if (kvm_vcpu_has_pmu(vcpu))
+				kvm_pmu_sync_hwstate(vcpu);
 			if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
@@ -1199,7 +1228,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * that the vgic can properly sample the updated state of the
 		 * interrupt line.
 		 */
-		kvm_pmu_sync_hwstate(vcpu);
+		if (kvm_vcpu_has_pmu(vcpu))
+			kvm_pmu_sync_hwstate(vcpu);
 
 		/*
 		 * Sync the vgic state before syncing the timer state because
@@ -1388,7 +1418,7 @@ static unsigned long system_supported_vcpu_features(void)
 	if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1))
 		clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features);
 
-	if (!kvm_arm_support_pmu_v3())
+	if (!kvm_supports_guest_pmuv3())
 		clear_bit(KVM_ARM_VCPU_PMU_V3, &features);
 
 	if (!system_supports_sve())
@@ -1980,7 +2010,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	unsigned long tcr, ips;
+	unsigned long tcr;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -1994,19 +2024,18 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
-	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
 		tcr |= TCR_EPD1_MASK;
 	} else {
+		unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
 		tcr &= TCR_EL2_MASK;
-		tcr |= TCR_EL2_RES1;
+		tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+		if (lpa2_is_enabled())
+			tcr |= TCR_EL2_DS;
 	}
-	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
-	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
-	if (lpa2_is_enabled())
-		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
@@ -2310,6 +2339,13 @@ static int __init init_subsystems(void)
 		goto out;
 	}
 
+	if (kvm_mode == KVM_MODE_NV &&
+	   !(vgic_present && kvm_vgic_global_state.type == VGIC_V3)) {
+		kvm_err("NV support requires GICv3, giving up\n");
+		err = -EINVAL;
+		goto out;
+	}
+
 	/*
 	 * Init HYP architected timer support
 	 */
@@ -2707,16 +2743,19 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
 	return irqchip_in_kernel(kvm);
 }
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return true;
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm_kernel_irq_routing_entry *irq_entry = &irqfd->irq_entry;
+
+	/*
+	 * The only thing we have a chance of directly-injecting is LPIs. Maybe
+	 * one day...
+	 */
+	if (irq_entry->type != KVM_IRQ_ROUTING_MSI)
+		return 0;
 
 	return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq,
 					  &irqfd->irq_entry);
@@ -2726,6 +2765,10 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm_kernel_irq_routing_entry *irq_entry = &irqfd->irq_entry;
+
+	if (irq_entry->type != KVM_IRQ_ROUTING_MSI)
+		return;
 
 	kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq,
 				     &irqfd->irq_entry);
@@ -2806,11 +2849,12 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_hyp;
 
-	kvm_info("%s%sVHE mode initialized successfully\n",
+	kvm_info("%s%sVHE%s mode initialized successfully\n",
 		 in_hyp_mode ? "" : (is_protected_kvm_enabled() ?
 				     "Protected " : "Hyp "),
 		 in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ?
-				     "h" : "n"));
+				     "h" : "n"),
+		 cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) ? "+NV2": "");
 
 	/*
 	 * FIXME: Do something reasonable if kvm_init() fails after pKVM
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 3a96c96816e9..f74a66ce3064 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1090,22 +1090,22 @@ static void compute_s1_overlay_permissions(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	if (pov_perms & ~POE_RXW)
+	if (pov_perms & ~POE_RWX)
 		pov_perms = POE_NONE;
 
 	if (wi->poe && wr->pov) {
 		wr->pr &= pov_perms & POE_R;
-		wr->px &= pov_perms & POE_X;
 		wr->pw &= pov_perms & POE_W;
+		wr->px &= pov_perms & POE_X;
 	}
 
-	if (uov_perms & ~POE_RXW)
+	if (uov_perms & ~POE_RWX)
 		uov_perms = POE_NONE;
 
 	if (wi->e0poe && wr->uov) {
 		wr->ur &= uov_perms & POE_R;
-		wr->ux &= uov_perms & POE_X;
 		wr->uw &= uov_perms & POE_W;
+		wr->ux &= uov_perms & POE_X;
 	}
 }
 
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 607d37bab70b..0fcfcc0478f9 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -412,26 +412,26 @@ static const struct trap_bits coarse_trap_bits[] = {
 	},
 	[CGT_ICH_HCR_TC] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TC,
-		.mask		= ICH_HCR_TC,
+		.value		= ICH_HCR_EL2_TC,
+		.mask		= ICH_HCR_EL2_TC,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TALL0] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TALL0,
-		.mask		= ICH_HCR_TALL0,
+		.value		= ICH_HCR_EL2_TALL0,
+		.mask		= ICH_HCR_EL2_TALL0,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TALL1] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TALL1,
-		.mask		= ICH_HCR_TALL1,
+		.value		= ICH_HCR_EL2_TALL1,
+		.mask		= ICH_HCR_EL2_TALL1,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 	[CGT_ICH_HCR_TDIR] = {
 		.index		= ICH_HCR_EL2,
-		.value		= ICH_HCR_TDIR,
-		.mask		= ICH_HCR_TDIR,
+		.value		= ICH_HCR_EL2_TDIR,
+		.mask		= ICH_HCR_EL2_TDIR,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
 };
@@ -2503,6 +2503,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	}
 
 	preempt_disable();
+	vcpu_set_flag(vcpu, IN_NESTED_ERET);
 	kvm_arch_vcpu_put(vcpu);
 
 	if (!esr_iss_is_eretax(esr))
@@ -2514,9 +2515,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	*vcpu_cpsr(vcpu) = spsr;
 
 	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	vcpu_clear_flag(vcpu, IN_NESTED_ERET);
 	preempt_enable();
 
-	kvm_pmu_nested_transition(vcpu);
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_pmu_nested_transition(vcpu);
 }
 
 static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2,
@@ -2599,7 +2602,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
 	kvm_arch_vcpu_load(vcpu, smp_processor_id());
 	preempt_enable();
 
-	kvm_pmu_nested_transition(vcpu);
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_pmu_nested_transition(vcpu);
 
 	return 1;
 }
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 512d152233ff..b73dc26bc44b 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -129,8 +129,12 @@ static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
 static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
 	u64 esr = kvm_vcpu_get_esr(vcpu);
+	bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE);
 
-	if (esr & ESR_ELx_WFx_ISS_WFE) {
+	if (guest_hyp_wfx_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	if (is_wfe) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
 	} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 17df94570f03..fc573fc767b0 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -12,6 +12,16 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
+static inline bool __fault_safe_to_translate(u64 esr)
+{
+	u64 fsc = esr & ESR_ELx_FSC;
+
+	if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr))
+		return false;
+
+	return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV));
+}
+
 static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	int ret;
@@ -44,34 +54,50 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
 	return true;
 }
 
-static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+/*
+ * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR.
+ */
+static inline bool __hpfar_valid(u64 esr)
 {
-	u64 hpfar, far;
-
-	far = read_sysreg_el2(SYS_FAR);
-
 	/*
-	 * The HPFAR can be invalid if the stage 2 fault did not
-	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
-	 * bit is clear) and one of the two following cases are true:
-	 *   1. The fault was due to a permission fault
-	 *   2. The processor carries errata 834220
+	 * CPUs affected by ARM erratum #834220 may incorrectly report a
+	 * stage-2 translation fault when a stage-1 permission fault occurs.
 	 *
-	 * Therefore, for all non S1PTW faults where we either have a
-	 * permission fault or the errata workaround is enabled, we
-	 * resolve the IPA using the AT instruction.
+	 * Re-walk the page tables to determine if a stage-1 fault actually
+	 * occurred.
 	 */
-	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     esr_fsc_is_permission_fault(esr))) {
-		if (!__translate_far_to_hpfar(far, &hpfar))
-			return false;
-	} else {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_834220) &&
+	    esr_fsc_is_translation_fault(esr))
+		return false;
+
+	if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr))
+		return true;
+
+	if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr))
+		return true;
+
+	return esr_fsc_is_addr_sz_fault(esr);
+}
+
+static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+{
+	u64 hpfar;
+
+	fault->far_el2		= read_sysreg_el2(SYS_FAR);
+	fault->hpfar_el2	= 0;
+
+	if (__hpfar_valid(esr))
 		hpfar = read_sysreg(hpfar_el2);
-	}
+	else if (unlikely(!__fault_safe_to_translate(esr)))
+		return true;
+	else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar))
+		return false;
 
-	fault->far_el2 = far;
-	fault->hpfar_el2 = hpfar;
+	/*
+	 * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid
+	 * HPFAR value.
+	 */
+	fault->hpfar_el2 = hpfar | HPFAR_EL2_NS;
 	return true;
 }
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 23bbe28eaaf9..96f625dc7256 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void)
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
 	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
 
@@ -244,12 +246,9 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
 	 * EL1 instead of being trapped to EL2.
 	 */
-	if (kvm_arm_support_pmu_v3()) {
-		struct kvm_cpu_context *hctxt;
-
+	if (system_supports_pmuv3()) {
 		write_sysreg(0, pmselr_el0);
 
-		hctxt = host_data_ptr(host_ctxt);
 		ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
 		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 		vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
@@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 			hcrx &= ~clr;
 		}
 
+		ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2);
 		write_sysreg_s(hcrx, SYS_HCRX_EL2);
 	}
 
@@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 {
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
+
 	write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
 
 	write_sysreg(0, hstr_el2);
-	if (kvm_arm_support_pmu_v3()) {
-		struct kvm_cpu_context *hctxt;
-
-		hctxt = host_data_ptr(host_ctxt);
+	if (system_supports_pmuv3()) {
 		write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
 	if (cpus_have_final_cap(ARM64_HAS_HCX))
-		write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2);
+		write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2);
 
 	__deactivate_traps_hfgxtr(vcpu);
 	__deactivate_traps_mpam();
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 76ff095c6b6e..b9cff893bbe0 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -43,6 +43,17 @@ static inline u64 *ctxt_mdscr_el1(struct kvm_cpu_context *ctxt)
 	return &ctxt_sys_reg(ctxt, MDSCR_EL1);
 }
 
+static inline u64 ctxt_midr_el1(struct kvm_cpu_context *ctxt)
+{
+	struct kvm *kvm = kern_hyp_va(ctxt_to_vcpu(ctxt)->kvm);
+
+	if (!(ctxt_is_guest(ctxt) &&
+	      test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags)))
+		return read_cpuid_id();
+
+	return kvm_read_vm_id_reg(kvm, SYS_MIDR_EL1);
+}
+
 static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	*ctxt_mdscr_el1(ctxt)	= read_sysreg(mdscr_el1);
@@ -168,8 +179,9 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 }
 
 static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
-					      u64 mpidr)
+					      u64 midr, u64 mpidr)
 {
+	write_sysreg(midr,				vpidr_el2);
 	write_sysreg(mpidr,				vmpidr_el2);
 
 	if (has_vhe() ||
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 978f38c386ee..ea0a704da9b8 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -56,7 +56,7 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt);
 
 int hyp_pin_shared_mem(void *from, void *to);
 void hyp_unpin_shared_mem(void *from, void *to);
-void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc);
+void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc);
 int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages,
 		    struct kvm_hyp_memcache *host_mc);
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index e42bf68c8848..ce31d3b73603 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -43,12 +43,6 @@ struct pkvm_hyp_vm {
 	struct hyp_pool pool;
 	hyp_spinlock_t lock;
 
-	/*
-	 * The number of vcpus initialized and ready to run.
-	 * Modifying this is protected by 'vm_table_lock'.
-	 */
-	unsigned int nr_vcpus;
-
 	/* Array of the hyp vCPU structures for this VM. */
 	struct pkvm_hyp_vcpu *vcpus[];
 };
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index e433dfab882a..3369dd0c4009 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -730,10 +730,10 @@ static void do_ffa_version(struct arm_smccc_res *res,
 		hyp_ffa_version = ffa_req_version;
 	}
 
-	if (hyp_ffa_post_init())
+	if (hyp_ffa_post_init()) {
 		res->a0 = FFA_RET_NOT_SUPPORTED;
-	else {
-		has_version_negotiated = true;
+	} else {
+		smp_store_release(&has_version_negotiated, true);
 		res->a0 = hyp_ffa_version;
 	}
 unlock:
@@ -809,7 +809,8 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	if (!is_ffa_call(func_id))
 		return false;
 
-	if (!has_version_negotiated && func_id != FFA_VERSION) {
+	if (func_id != FFA_VERSION &&
+	    !smp_load_acquire(&has_version_negotiated)) {
 		ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS);
 		goto out_handled;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index fc1866226067..f8af11189572 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -73,8 +73,12 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+/*
+ * Initialize EL2 CPU state to sane values.
+ *
+ * HCR_EL2.E2H must have been initialized already.
+ */
 SYM_CODE_START_LOCAL(__kvm_init_el2_state)
-	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
 	ret
@@ -206,9 +210,9 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
-	bl	__kvm_init_el2_state
+	init_el2_hcr	0
 
-	__init_el2_nvhe_prepare_eret
+	bl	__kvm_init_el2_state
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 19c3c631708c..e80f3ebd3e2a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -266,7 +266,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
 	return 0;
 }
 
-void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
+void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
 {
 	struct hyp_page *page;
 	void *addr;
@@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
 	int ret;
 
-	if (!addr_is_memory(addr))
+	if (!range_is_memory(addr, addr + size))
 		return -EPERM;
 
 	ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
@@ -578,7 +578,14 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 		return;
 	}
 
-	addr = (fault.hpfar_el2 & HPFAR_MASK) << 8;
+
+	/*
+	 * Yikes, we couldn't resolve the fault IPA. This should reinject an
+	 * abort into the host when we figure out how to do that.
+	 */
+	BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
+	addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;
+
 	ret = host_stage2_idmap(addr);
 	BUG_ON(ret && ret != -EAGAIN);
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 3927fe52a3dd..5a335a51deca 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -46,7 +46,8 @@ static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 |= HCR_FWB;
 
 	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
-	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) &&
+	    kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0) == read_cpuid(CTR_EL0))
 		vcpu->arch.hcr_el2 |= HCR_TID4;
 	else
 		vcpu->arch.hcr_el2 |= HCR_TID2;
@@ -166,8 +167,13 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	pkvm_vcpu_reset_hcr(vcpu);
 
-	if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu)))
+	if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) {
+		struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+		/* Trust the host for non-protected vcpu features. */
+		vcpu->arch.hcrx_el2 = host_vcpu->arch.hcrx_el2;
 		return 0;
+	}
 
 	ret = pkvm_check_pvm_cpu_features(vcpu);
 	if (ret)
@@ -175,6 +181,7 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	pvm_init_traps_hcr(vcpu);
 	pvm_init_traps_mdcr(vcpu);
+	vcpu_set_hcrx(vcpu);
 
 	return 0;
 }
@@ -239,10 +246,12 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 
 	hyp_spin_lock(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
-	if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx)
+	if (!hyp_vm || hyp_vm->kvm.created_vcpus <= vcpu_idx)
 		goto unlock;
 
 	hyp_vcpu = hyp_vm->vcpus[vcpu_idx];
+	if (!hyp_vcpu)
+		goto unlock;
 
 	/* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
 	if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
@@ -315,6 +324,9 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags);
 	DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES);
 
+	/* CTR_EL0 is always under host control, even for protected VMs. */
+	hyp_vm->kvm.arch.ctr_el0 = host_kvm->arch.ctr_el0;
+
 	if (test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &host_kvm->arch.flags))
 		set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags);
 
@@ -325,6 +337,10 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
 			    KVM_VCPU_MAX_FEATURES);
+
+		if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags))
+			hyp_vm->kvm.arch.midr_el1 = host_kvm->arch.midr_el1;
+
 		return;
 	}
 
@@ -361,8 +377,14 @@ static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],
 {
 	int i;
 
-	for (i = 0; i < nr_vcpus; i++)
-		unpin_host_vcpu(hyp_vcpus[i]->host_vcpu);
+	for (i = 0; i < nr_vcpus; i++) {
+		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vcpus[i];
+
+		if (!hyp_vcpu)
+			continue;
+
+		unpin_host_vcpu(hyp_vcpu->host_vcpu);
+	}
 }
 
 static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
@@ -386,24 +408,18 @@ static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *
 
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 			      struct pkvm_hyp_vm *hyp_vm,
-			      struct kvm_vcpu *host_vcpu,
-			      unsigned int vcpu_idx)
+			      struct kvm_vcpu *host_vcpu)
 {
 	int ret = 0;
 
 	if (hyp_pin_shared_mem(host_vcpu, host_vcpu + 1))
 		return -EBUSY;
 
-	if (host_vcpu->vcpu_idx != vcpu_idx) {
-		ret = -EINVAL;
-		goto done;
-	}
-
 	hyp_vcpu->host_vcpu = host_vcpu;
 
 	hyp_vcpu->vcpu.kvm = &hyp_vm->kvm;
 	hyp_vcpu->vcpu.vcpu_id = READ_ONCE(host_vcpu->vcpu_id);
-	hyp_vcpu->vcpu.vcpu_idx = vcpu_idx;
+	hyp_vcpu->vcpu.vcpu_idx = READ_ONCE(host_vcpu->vcpu_idx);
 
 	hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu;
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
@@ -641,27 +657,28 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
 		goto unlock;
 	}
 
-	idx = hyp_vm->nr_vcpus;
+	ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu);
+	if (ret)
+		goto unlock;
+
+	idx = hyp_vcpu->vcpu.vcpu_idx;
 	if (idx >= hyp_vm->kvm.created_vcpus) {
 		ret = -EINVAL;
 		goto unlock;
 	}
 
-	ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu, idx);
-	if (ret)
+	if (hyp_vm->vcpus[idx]) {
+		ret = -EINVAL;
 		goto unlock;
+	}
 
 	hyp_vm->vcpus[idx] = hyp_vcpu;
-	hyp_vm->nr_vcpus++;
 unlock:
 	hyp_spin_unlock(&vm_table_lock);
 
-	if (ret) {
+	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static void
@@ -678,7 +695,7 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size)
 
 int __pkvm_teardown_vm(pkvm_handle_t handle)
 {
-	struct kvm_hyp_memcache *mc;
+	struct kvm_hyp_memcache *mc, *stage2_mc;
 	struct pkvm_hyp_vm *hyp_vm;
 	struct kvm *host_kvm;
 	unsigned int idx;
@@ -706,18 +723,24 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
 
 	/* Reclaim guest pages (including page-table pages) */
 	mc = &host_kvm->arch.pkvm.teardown_mc;
-	reclaim_guest_pages(hyp_vm, mc);
-	unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->nr_vcpus);
+	stage2_mc = &host_kvm->arch.pkvm.stage2_teardown_mc;
+	reclaim_pgtable_pages(hyp_vm, stage2_mc);
+	unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->kvm.created_vcpus);
 
 	/* Push the metadata pages to the teardown memcache */
-	for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) {
+	for (idx = 0; idx < hyp_vm->kvm.created_vcpus; ++idx) {
 		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx];
-		struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
+		struct kvm_hyp_memcache *vcpu_mc;
+
+		if (!hyp_vcpu)
+			continue;
+
+		vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
 
 		while (vcpu_mc->nr_pages) {
 			void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt);
 
-			push_hyp_memcache(mc, addr, hyp_virt_to_phys);
+			push_hyp_memcache(stage2_mc, addr, hyp_virt_to_phys);
 			unmap_donated_memory_noclear(addr, PAGE_SIZE);
 		}
 
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 9c2ce1e0e99a..c3e196fb8b18 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -218,6 +218,9 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	if (is_cpu_on)
 		release_boot_args(boot_args);
 
+	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
+	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
+
 	__host_enter(host_ctxt);
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index dba101565de3..3cc613cce5f5 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -28,7 +28,9 @@ void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_restore_el1_state(ctxt, ctxt_sys_reg(ctxt, MPIDR_EL1));
+	u64 midr = ctxt_midr_el1(ctxt);
+
+	__sysreg_restore_el1_state(ctxt, midr, ctxt_sys_reg(ctxt, MPIDR_EL1));
 	__sysreg_restore_common_state(ctxt);
 	__sysreg_restore_user_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 3f9741e51d41..50aa8dbcae75 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -18,7 +18,7 @@
 #define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 #define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))
 
-static u64 __gic_v3_get_lr(unsigned int lr)
+u64 __gic_v3_get_lr(unsigned int lr)
 {
 	switch (lr & 0xf) {
 	case 0:
@@ -218,7 +218,7 @@ void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
 
 		elrsr = read_gicreg(ICH_ELRSR_EL2);
 
-		write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2);
+		write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EL2_En, ICH_HCR_EL2);
 
 		for (i = 0; i < used_lrs; i++) {
 			if (elrsr & (1 << i))
@@ -274,7 +274,7 @@ void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 	 * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1
 	 * so that the trap bits can take effect. Yes, we *loves* the GIC.
 	 */
-	if (!(cpu_if->vgic_hcr & ICH_HCR_EN)) {
+	if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) {
 		write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1);
 		isb();
 	} else if (!cpu_if->vgic_sre) {
@@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void)
 	/*
 	 * To check whether we have a MMIO-based (GICv2 compatible)
 	 * CPU interface, we need to disable the system register
-	 * view. To do that safely, we have to prevent any interrupt
-	 * from firing (which would be deadly).
+	 * view.
 	 *
-	 * Note that this only makes sense on VHE, as interrupts are
-	 * already masked for nVHE as part of the exception entry to
-	 * EL2.
-	 */
-	if (has_vhe())
-		flags = local_daif_save();
-
-	/*
 	 * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
 	 * that to be able to set ICC_SRE_EL1.SRE to 0, all the
 	 * interrupt overrides must be set. You've got to love this.
+	 *
+	 * As we always run VHE with HCR_xMO set, no extra xMO
+	 * manipulation is required in that case.
+	 *
+	 * To safely disable SRE, we have to prevent any interrupt
+	 * from firing (which would be deadly). This only makes sense
+	 * on VHE, as interrupts are already masked for nVHE as part
+	 * of the exception entry to EL2.
 	 */
-	sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
-	isb();
+	if (has_vhe()) {
+		flags = local_daif_save();
+	} else {
+		sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+		isb();
+	}
+
 	write_gicreg(0, ICC_SRE_EL1);
 	isb();
 
@@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void)
 
 	write_gicreg(sre, ICC_SRE_EL1);
 	isb();
-	sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
-	isb();
 
-	if (has_vhe())
+	if (has_vhe()) {
 		local_daif_restore(flags);
+	} else {
+		sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+		isb();
+	}
 
 	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
 	val |= read_gicreg(ICH_VTR_EL2);
@@ -752,7 +758,7 @@ static void __vgic_v3_bump_eoicount(void)
 	u32 hcr;
 
 	hcr = read_gicreg(ICH_HCR_EL2);
-	hcr += 1 << ICH_HCR_EOIcount_SHIFT;
+	hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT;
 	write_gicreg(hcr, ICH_HCR_EL2);
 }
 
@@ -1069,7 +1075,7 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_EOIR0_EL1:
 	case SYS_ICC_HPPIR0_EL1:
 	case SYS_ICC_IAR0_EL1:
-		return ich_hcr & ICH_HCR_TALL0;
+		return ich_hcr & ICH_HCR_EL2_TALL0;
 
 	case SYS_ICC_IGRPEN1_EL1:
 		if (is_read &&
@@ -1090,10 +1096,10 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_EOIR1_EL1:
 	case SYS_ICC_HPPIR1_EL1:
 	case SYS_ICC_IAR1_EL1:
-		return ich_hcr & ICH_HCR_TALL1;
+		return ich_hcr & ICH_HCR_EL2_TALL1;
 
 	case SYS_ICC_DIR_EL1:
-		if (ich_hcr & ICH_HCR_TDIR)
+		if (ich_hcr & ICH_HCR_EL2_TDIR)
 			return true;
 
 		fallthrough;
@@ -1101,7 +1107,7 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	case SYS_ICC_RPR_EL1:
 	case SYS_ICC_CTLR_EL1:
 	case SYS_ICC_PMR_EL1:
-		return ich_hcr & ICH_HCR_TC;
+		return ich_hcr & ICH_HCR_EL2_TC;
 
 	default:
 		return false;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 647737d6e8d0..731a0378ed13 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -527,6 +527,25 @@ static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return kvm_hyp_handle_sysreg(vcpu, exit_code);
 }
 
+static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 iss;
+
+	if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return false;
+
+	/*
+	 * Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2
+	 * is populated with a correct ISS for a sysreg trap. These fruity
+	 * parts are 64bit only, so unconditionally set IL.
+	 */
+	iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2));
+	vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) |
+				   FIELD_PREP(ESR_ELx_ISS_MASK, iss) |
+				   ESR_ELx_IL;
+	return false;
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
@@ -538,6 +557,9 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_ERET]		= kvm_hyp_handle_eret,
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
+
+	/* Apple shenanigans */
+	[0x3F]				= kvm_hyp_handle_impdef,
 };
 
 static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 90b018e06f2c..3814b0b2c937 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -87,11 +87,12 @@ static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
 	write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1),	par_el1);
 	write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1),	tpidr_el1);
 
-	write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1),		vmpidr_el2);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2),	SYS_MAIR);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2),	SYS_VBAR);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2),	SYS_CONTEXTIDR);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2),	SYS_AMAIR);
+	write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt),			vpidr_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1),			vmpidr_el2);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2),		SYS_MAIR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2),		SYS_VBAR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2),		SYS_CONTEXTIDR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2),		SYS_AMAIR);
 
 	if (vcpu_el2_e2h_is_set(vcpu)) {
 		/*
@@ -191,7 +192,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
-	u64 mpidr;
+	u64 midr, mpidr;
 
 	host_ctxt = host_data_ptr(host_ctxt);
 	__sysreg_save_user_state(host_ctxt);
@@ -221,22 +222,17 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	} else {
 		if (vcpu_has_nv(vcpu)) {
 			/*
-			 * Use the guest hypervisor's VPIDR_EL2 when in a
-			 * nested state. The hardware value of MIDR_EL1 gets
-			 * restored on put.
-			 */
-			write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2);
-
-			/*
 			 * As we're restoring a nested guest, set the value
 			 * provided by the guest hypervisor.
 			 */
+			midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2);
 			mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
 		} else {
+			midr = ctxt_midr_el1(guest_ctxt);
 			mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
 		}
 
-		__sysreg_restore_el1_state(guest_ctxt, mpidr);
+		__sysreg_restore_el1_state(guest_ctxt, midr, mpidr);
 	}
 
 	vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
@@ -271,9 +267,5 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 	/* Restore host user state */
 	__sysreg_restore_user_state(host_ctxt);
 
-	/* If leaving a nesting guest, restore MIDR_EL1 default view */
-	if (vcpu_has_nv(vcpu))
-		write_sysreg(read_cpuid_id(),	vpidr_el2);
-
 	vcpu_clear_flag(vcpu, SYSREGS_ON_CPU);
 }
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 27ce4cb44904..569941eeb3fe 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -15,6 +15,8 @@
 	GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0)
 #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES			\
 	GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0)
+#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2			\
+	GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT - 1, 0)
 
 static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val)
 {
@@ -360,6 +362,8 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 		break;
 	case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
 		val[0] = smccc_feat->vendor_hyp_bmap;
+		/* Function numbers 2-63 are reserved for pKVM for now */
+		val[2] = smccc_feat->vendor_hyp_bmap_2;
 		break;
 	case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID:
 		kvm_ptp_get_time(vcpu, val);
@@ -387,6 +391,7 @@ static const u64 kvm_arm_fw_reg_ids[] = {
 	KVM_REG_ARM_STD_BMAP,
 	KVM_REG_ARM_STD_HYP_BMAP,
 	KVM_REG_ARM_VENDOR_HYP_BMAP,
+	KVM_REG_ARM_VENDOR_HYP_BMAP_2,
 };
 
 void kvm_arm_init_hypercalls(struct kvm *kvm)
@@ -497,6 +502,9 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_VENDOR_HYP_BMAP:
 		val = READ_ONCE(smccc_feat->vendor_hyp_bmap);
 		break;
+	case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
+		val = READ_ONCE(smccc_feat->vendor_hyp_bmap_2);
+		break;
 	default:
 		return -ENOENT;
 	}
@@ -527,6 +535,10 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val)
 		fw_reg_bmap = &smccc_feat->vendor_hyp_bmap;
 		fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES;
 		break;
+	case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
+		fw_reg_bmap = &smccc_feat->vendor_hyp_bmap_2;
+		fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2;
+		break;
 	default:
 		return -ENOENT;
 	}
@@ -633,6 +645,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_STD_BMAP:
 	case KVM_REG_ARM_STD_HYP_BMAP:
 	case KVM_REG_ARM_VENDOR_HYP_BMAP:
+	case KVM_REG_ARM_VENDOR_HYP_BMAP_2:
 		return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val);
 	default:
 		return -ENOENT;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1f55b0c7b11d..eeda92330ade 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1086,14 +1086,26 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	}
 }
 
-static void hyp_mc_free_fn(void *addr, void *unused)
+static void hyp_mc_free_fn(void *addr, void *mc)
 {
+	struct kvm_hyp_memcache *memcache = mc;
+
+	if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
+		kvm_account_pgtable_pages(addr, -1);
+
 	free_page((unsigned long)addr);
 }
 
-static void *hyp_mc_alloc_fn(void *unused)
+static void *hyp_mc_alloc_fn(void *mc)
 {
-	return (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
+	struct kvm_hyp_memcache *memcache = mc;
+	void *addr;
+
+	addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
+	if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
+		kvm_account_pgtable_pages(addr, 1);
+
+	return addr;
 }
 
 void free_hyp_memcache(struct kvm_hyp_memcache *mc)
@@ -1102,7 +1114,7 @@ void free_hyp_memcache(struct kvm_hyp_memcache *mc)
 		return;
 
 	kfree(mc->mapping);
-	__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL);
+	__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc);
 }
 
 int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
@@ -1117,7 +1129,7 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
 	}
 
 	return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
-				    kvm_host_pa, NULL);
+				    kvm_host_pa, mc);
 }
 
 /**
@@ -1489,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
+	if (!is_protected_kvm_enabled())
+		memcache = &vcpu->arch.mmu_page_cache;
+	else
+		memcache = &vcpu->arch.pkvm_memcache;
+
 	/*
 	 * Permission faults just need to update the existing leaf entry,
 	 * and so normally don't require allocations from the memcache. The
@@ -1498,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!fault_is_perm || (logging_active && write_fault)) {
 		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
 
-		if (!is_protected_kvm_enabled()) {
-			memcache = &vcpu->arch.mmu_page_cache;
+		if (!is_protected_kvm_enabled())
 			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
-		} else {
-			memcache = &vcpu->arch.pkvm_memcache;
+		else
 			ret = topup_hyp_memcache(memcache, min_pages);
-		}
+
 		if (ret)
 			return ret;
 	}
@@ -1782,9 +1797,28 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
+	/* Synchronous External Abort? */
+	if (kvm_vcpu_abt_issea(vcpu)) {
+		/*
+		 * For RAS the host kernel may handle this abort.
+		 * There is no need to pass the error into the guest.
+		 */
+		if (kvm_handle_guest_sea())
+			kvm_inject_vabt(vcpu);
+
+		return 1;
+	}
+
 	esr = kvm_vcpu_get_esr(vcpu);
 
+	/*
+	 * The fault IPA should be reliable at this point as we're not dealing
+	 * with an SEA.
+	 */
 	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm))
+		return -EFAULT;
+
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	if (esr_fsc_is_translation_fault(esr)) {
@@ -1806,18 +1840,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
-			kvm_inject_vabt(vcpu);
-
-		return 1;
-	}
-
 	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 0c9387d2f507..4a3fc11f7ecf 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -16,9 +16,6 @@
 
 #include "sys_regs.h"
 
-/* Protection against the sysreg repainting madness... */
-#define NV_FTR(r, f)		ID_AA64##r##_EL1_##f
-
 /*
  * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
  * memory usage and potential number of different sets of S2 PTs in
@@ -54,6 +51,10 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	struct kvm_s2_mmu *tmp;
 	int num_mmus, ret = 0;
 
+	if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features) &&
+	    !cpus_have_final_cap(ARM64_HAS_HCR_NV1))
+		return -EINVAL;
+
 	/*
 	 * Let's treat memory allocation failures as benign: If we fail to
 	 * allocate anything, return an error and keep the allocated array
@@ -807,134 +808,151 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
  * This list should get updated as new features get added to the NV
  * support, and new extension to the architecture.
  */
-static void limit_nv_id_regs(struct kvm *kvm)
+u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 {
-	u64 val, tmp;
-
-	/* Support everything but TME */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1);
-	val &= ~NV_FTR(ISAR0, TME);
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1, val);
-
-	/* Support everything but Spec Invalidation and LS64 */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1);
-	val &= ~(NV_FTR(ISAR1, LS64)	|
-		 NV_FTR(ISAR1, SPECRES));
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1, val);
-
-	/* No AMU, MPAM, S-EL2, or RAS */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1);
-	val &= ~(GENMASK_ULL(55, 52)	|
-		 NV_FTR(PFR0, AMU)	|
-		 NV_FTR(PFR0, MPAM)	|
-		 NV_FTR(PFR0, SEL2)	|
-		 NV_FTR(PFR0, RAS)	|
-		 NV_FTR(PFR0, EL3)	|
-		 NV_FTR(PFR0, EL2)	|
-		 NV_FTR(PFR0, EL1)	|
-		 NV_FTR(PFR0, EL0));
-	/* 64bit only at any EL */
-	val |= FIELD_PREP(NV_FTR(PFR0, EL0), 0b0001);
-	val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001);
-	val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001);
-	val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001);
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val);
-
-	/* Only support BTI, SSBS, CSV2_frac */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1);
-	val &= (NV_FTR(PFR1, BT)	|
-		NV_FTR(PFR1, SSBS)	|
-		NV_FTR(PFR1, CSV2_frac));
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1, val);
-
-	/* Hide ECV, ExS, Secure Memory */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1);
-	val &= ~(NV_FTR(MMFR0, ECV)		|
-		 NV_FTR(MMFR0, EXS)		|
-		 NV_FTR(MMFR0, TGRAN4_2)	|
-		 NV_FTR(MMFR0, TGRAN16_2)	|
-		 NV_FTR(MMFR0, TGRAN64_2)	|
-		 NV_FTR(MMFR0, SNSMEM));
-
-	/* Disallow unsupported S2 page sizes */
-	switch (PAGE_SIZE) {
-	case SZ_64K:
-		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001);
-		fallthrough;
-	case SZ_16K:
-		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001);
-		fallthrough;
-	case SZ_4K:
-		/* Support everything */
+	switch (reg) {
+	case SYS_ID_AA64ISAR0_EL1:
+		/* Support everything but TME */
+		val &= ~ID_AA64ISAR0_EL1_TME;
 		break;
-	}
-	/*
-	 * Since we can't support a guest S2 page size smaller than
-	 * the host's own page size (due to KVM only populating its
-	 * own S2 using the kernel's page size), advertise the
-	 * limitation using FEAT_GTG.
-	 */
-	switch (PAGE_SIZE) {
-	case SZ_4K:
-		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010);
-		fallthrough;
-	case SZ_16K:
-		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010);
-		fallthrough;
-	case SZ_64K:
-		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010);
+
+	case SYS_ID_AA64ISAR1_EL1:
+		/* Support everything but LS64 and Spec Invalidation */
+		val &= ~(ID_AA64ISAR1_EL1_LS64	|
+			 ID_AA64ISAR1_EL1_SPECRES);
+		break;
+
+	case SYS_ID_AA64PFR0_EL1:
+		/* No RME, AMU, MPAM, S-EL2, or RAS */
+		val &= ~(ID_AA64PFR0_EL1_RME	|
+			 ID_AA64PFR0_EL1_AMU	|
+			 ID_AA64PFR0_EL1_MPAM	|
+			 ID_AA64PFR0_EL1_SEL2	|
+			 ID_AA64PFR0_EL1_RAS	|
+			 ID_AA64PFR0_EL1_EL3	|
+			 ID_AA64PFR0_EL1_EL2	|
+			 ID_AA64PFR0_EL1_EL1	|
+			 ID_AA64PFR0_EL1_EL0);
+		/* 64bit only at any EL */
+		val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP);
+		val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP);
+		val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP);
+		val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP);
+		break;
+
+	case SYS_ID_AA64PFR1_EL1:
+		/* Only support BTI, SSBS, CSV2_frac */
+		val &= (ID_AA64PFR1_EL1_BT	|
+			ID_AA64PFR1_EL1_SSBS	|
+			ID_AA64PFR1_EL1_CSV2_frac);
+		break;
+
+	case SYS_ID_AA64MMFR0_EL1:
+		/* Hide ExS, Secure Memory */
+		val &= ~(ID_AA64MMFR0_EL1_EXS		|
+			 ID_AA64MMFR0_EL1_TGRAN4_2	|
+			 ID_AA64MMFR0_EL1_TGRAN16_2	|
+			 ID_AA64MMFR0_EL1_TGRAN64_2	|
+			 ID_AA64MMFR0_EL1_SNSMEM);
+
+		/* Hide CNTPOFF if present */
+		val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, ECV, IMP);
+
+		/* Disallow unsupported S2 page sizes */
+		switch (PAGE_SIZE) {
+		case SZ_64K:
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, NI);
+			fallthrough;
+		case SZ_16K:
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, NI);
+			fallthrough;
+		case SZ_4K:
+			/* Support everything */
+			break;
+		}
+
+		/*
+		 * Since we can't support a guest S2 page size smaller
+		 * than the host's own page size (due to KVM only
+		 * populating its own S2 using the kernel's page
+		 * size), advertise the limitation using FEAT_GTG.
+		 */
+		switch (PAGE_SIZE) {
+		case SZ_4K:
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
+			fallthrough;
+		case SZ_16K:
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
+			fallthrough;
+		case SZ_64K:
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
+			break;
+		}
+
+		/* Cap PARange to 48bits */
+		val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, PARANGE, 48);
+		break;
+
+	case SYS_ID_AA64MMFR1_EL1:
+		val &= (ID_AA64MMFR1_EL1_HCX	|
+			ID_AA64MMFR1_EL1_PAN	|
+			ID_AA64MMFR1_EL1_LO	|
+			ID_AA64MMFR1_EL1_HPDS	|
+			ID_AA64MMFR1_EL1_VH	|
+			ID_AA64MMFR1_EL1_VMIDBits);
+		/* FEAT_E2H0 implies no VHE */
+		if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features))
+			val &= ~ID_AA64MMFR1_EL1_VH;
+		break;
+
+	case SYS_ID_AA64MMFR2_EL1:
+		val &= ~(ID_AA64MMFR2_EL1_BBM	|
+			 ID_AA64MMFR2_EL1_TTL	|
+			 GENMASK_ULL(47, 44)	|
+			 ID_AA64MMFR2_EL1_ST	|
+			 ID_AA64MMFR2_EL1_CCIDX	|
+			 ID_AA64MMFR2_EL1_VARange);
+
+		/* Force TTL support */
+		val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR2_EL1, TTL, IMP);
+		break;
+
+	case SYS_ID_AA64MMFR4_EL1:
+		/*
+		 * You get EITHER
+		 *
+		 * - FEAT_VHE without FEAT_E2H0
+		 * - FEAT_NV limited to FEAT_NV2
+		 * - HCR_EL2.NV1 being RES0
+		 *
+		 * OR
+		 *
+		 * - FEAT_E2H0 without FEAT_VHE nor FEAT_NV
+		 *
+		 * Life is too short for anything else.
+		 */
+		if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) {
+			val = 0;
+		} else {
+			val = SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY);
+			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI_NV1);
+		}
+		break;
+
+	case SYS_ID_AA64DFR0_EL1:
+		/* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */
+		val &= (ID_AA64DFR0_EL1_PMUVer	|
+			ID_AA64DFR0_EL1_WRPs	|
+			ID_AA64DFR0_EL1_BRPs	|
+			ID_AA64DFR0_EL1_DebugVer|
+			ID_AA64DFR0_EL1_HPMN0);
+
+		/* Cap Debug to ARMv8.1 */
+		val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, VHE);
 		break;
 	}
-	/* Cap PARange to 48bits */
-	tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val);
-	if (tmp > 0b0101) {
-		val &= ~NV_FTR(MMFR0, PARANGE);
-		val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101);
-	}
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1, val);
-
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1);
-	val &= (NV_FTR(MMFR1, HCX)	|
-		NV_FTR(MMFR1, PAN)	|
-		NV_FTR(MMFR1, LO)	|
-		NV_FTR(MMFR1, HPDS)	|
-		NV_FTR(MMFR1, VH)	|
-		NV_FTR(MMFR1, VMIDBits));
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1, val);
-
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1);
-	val &= ~(NV_FTR(MMFR2, BBM)	|
-		 NV_FTR(MMFR2, TTL)	|
-		 GENMASK_ULL(47, 44)	|
-		 NV_FTR(MMFR2, ST)	|
-		 NV_FTR(MMFR2, CCIDX)	|
-		 NV_FTR(MMFR2, VARange));
-
-	/* Force TTL support */
-	val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001);
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1, val);
-
-	val = 0;
-	if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
-		val |= FIELD_PREP(NV_FTR(MMFR4, E2H0),
-				  ID_AA64MMFR4_EL1_E2H0_NI_NV1);
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR4_EL1, val);
-
-	/* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */
-	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
-	val &= (NV_FTR(DFR0, PMUVer)	|
-		NV_FTR(DFR0, WRPs)	|
-		NV_FTR(DFR0, BRPs)	|
-		NV_FTR(DFR0, DebugVer)	|
-		NV_FTR(DFR0, HPMN0));
-
-	/* Cap Debug to ARMv8.1 */
-	tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val);
-	if (tmp > 0b0111) {
-		val &= ~NV_FTR(DFR0, DebugVer);
-		val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111);
-	}
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val);
+
+	return val;
 }
 
 u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu,
@@ -981,8 +999,6 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 	if (!kvm->arch.sysreg_masks)
 		return -ENOMEM;
 
-	limit_nv_id_regs(kvm);
-
 	/* VTTBR_EL2 */
 	res0 = res1 = 0;
 	if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16))
@@ -1021,10 +1037,11 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 		res0 |= HCR_FIEN;
 	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP))
 		res0 |= HCR_FWB;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2))
-		res0 |= HCR_NV2;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP))
-		res0 |= (HCR_AT | HCR_NV1 | HCR_NV);
+	/* Implementation choice: NV2 is the only supported config */
+	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
+		res0 |= (HCR_NV2 | HCR_NV | HCR_AT);
+	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, NI))
+		res0 |= HCR_NV1;
 	if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
 	      kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
 		res0 |= (HCR_API | HCR_APK);
@@ -1034,6 +1051,8 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 		res0 |= (HCR_TEA | HCR_TERR);
 	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
 		res0 |= HCR_TLOR;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
+		res0 |= HCR_E2H;
 	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP))
 		res1 |= HCR_E2H;
 	set_sysreg_masks(kvm, HCR_EL2, res0, res1);
@@ -1290,6 +1309,15 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 		res0 |= GENMASK(11, 8);
 	set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1);
 
+	/* ICH_HCR_EL2 */
+	res0 = ICH_HCR_EL2_RES0;
+	res1 = ICH_HCR_EL2_RES1;
+	if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS))
+		res0 |= ICH_HCR_EL2_TDIR;
+	/* No GICv4 is presented to the guest */
+	res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount;
+	set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1);
+
 out:
 	for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
 		(void)__vcpu_sys_reg(vcpu, sr);
@@ -1309,4 +1337,8 @@ void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 		write_unlock(&vcpu->kvm->mmu_lock);
 	}
+
+	/* Must be last, as may switch context! */
+	if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu))
+		kvm_inject_nested_irq(vcpu);
 }
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 930b677eb9b0..0f89157d31fd 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -111,6 +111,29 @@ static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 
 	host_kvm->arch.pkvm.handle = 0;
 	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+	free_hyp_memcache(&host_kvm->arch.pkvm.stage2_teardown_mc);
+}
+
+static int __pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu)
+{
+	size_t hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE);
+	pkvm_handle_t handle = vcpu->kvm->arch.pkvm.handle;
+	void *hyp_vcpu;
+	int ret;
+
+	vcpu->arch.pkvm_memcache.flags |= HYP_MEMCACHE_ACCOUNT_STAGE2;
+
+	hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT);
+	if (!hyp_vcpu)
+		return -ENOMEM;
+
+	ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, vcpu, hyp_vcpu);
+	if (!ret)
+		vcpu_set_flag(vcpu, VCPU_PKVM_FINALIZED);
+	else
+		free_pages_exact(hyp_vcpu, hyp_vcpu_sz);
+
+	return ret;
 }
 
 /*
@@ -125,11 +148,8 @@ static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
  */
 static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
 {
-	size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz;
-	struct kvm_vcpu *host_vcpu;
-	pkvm_handle_t handle;
+	size_t pgd_sz, hyp_vm_sz;
 	void *pgd, *hyp_vm;
-	unsigned long idx;
 	int ret;
 
 	if (host_kvm->created_vcpus < 1)
@@ -161,40 +181,11 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
 	if (ret < 0)
 		goto free_vm;
 
-	handle = ret;
-
-	host_kvm->arch.pkvm.handle = handle;
-
-	/* Donate memory for the vcpus at hyp and initialize it. */
-	hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE);
-	kvm_for_each_vcpu(idx, host_vcpu, host_kvm) {
-		void *hyp_vcpu;
-
-		/* Indexing of the vcpus to be sequential starting at 0. */
-		if (WARN_ON(host_vcpu->vcpu_idx != idx)) {
-			ret = -EINVAL;
-			goto destroy_vm;
-		}
-
-		hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT);
-		if (!hyp_vcpu) {
-			ret = -ENOMEM;
-			goto destroy_vm;
-		}
-
-		ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu,
-					hyp_vcpu);
-		if (ret) {
-			free_pages_exact(hyp_vcpu, hyp_vcpu_sz);
-			goto destroy_vm;
-		}
-	}
+	host_kvm->arch.pkvm.handle = ret;
+	host_kvm->arch.pkvm.stage2_teardown_mc.flags |= HYP_MEMCACHE_ACCOUNT_STAGE2;
+	kvm_account_pgtable_pages(pgd, pgd_sz / PAGE_SIZE);
 
 	return 0;
-
-destroy_vm:
-	__pkvm_destroy_hyp_vm(host_kvm);
-	return ret;
 free_vm:
 	free_pages_exact(hyp_vm, hyp_vm_sz);
 free_pgd:
@@ -214,6 +205,18 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm)
 	return ret;
 }
 
+int pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu)
+{
+	int ret = 0;
+
+	mutex_lock(&vcpu->kvm->arch.config_lock);
+	if (!vcpu_get_flag(vcpu, VCPU_PKVM_FINALIZED))
+		ret = __pkvm_create_hyp_vcpu(vcpu);
+	mutex_unlock(&vcpu->kvm->arch.config_lock);
+
+	return ret;
+}
+
 void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 {
 	mutex_lock(&host_kvm->arch.config_lock);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 6c5950b9ceac..a1bc10d7116a 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -17,8 +17,6 @@
 
 #define PERF_ATTR_CFG1_COUNTER_64BIT	BIT(0)
 
-DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
-
 static LIST_HEAD(arm_pmus);
 static DEFINE_MUTEX(arm_pmus_lock);
 
@@ -26,6 +24,12 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc);
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc);
 static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc);
 
+bool kvm_supports_guest_pmuv3(void)
+{
+	guard(mutex)(&arm_pmus_lock);
+	return !list_empty(&arm_pmus);
+}
+
 static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc)
 {
 	return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]);
@@ -150,9 +154,6 @@ static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
  */
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
 }
 
@@ -191,13 +192,23 @@ static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
  */
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false);
 }
 
 /**
+ * kvm_pmu_set_counter_value_user - set PMU counter value from user
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ * @val: The counter value
+ */
+void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
+{
+	kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
+	__vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
+}
+
+/**
  * kvm_pmu_release_perf_event - remove the perf event
  * @pmc: The PMU counter pointer
  */
@@ -248,20 +259,6 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
 }
 
 /**
- * kvm_pmu_vcpu_reset - reset pmu state for cpu
- * @vcpu: The vcpu pointer
- *
- */
-void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
-{
-	unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu);
-	int i;
-
-	for_each_set_bit(i, &mask, 32)
-		kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i));
-}
-
-/**
  * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
  * @vcpu: The vcpu pointer
  *
@@ -350,7 +347,7 @@ void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu) || !val)
+	if (!val)
 		return;
 
 	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
@@ -401,9 +398,6 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	bool overflow;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	overflow = kvm_pmu_overflow_status(vcpu);
 	if (pmu->irq_level == overflow)
 		return;
@@ -599,9 +593,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	/* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */
 	if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
 		val &= ~ARMV8_PMU_PMCR_LP;
@@ -673,6 +664,20 @@ static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc)
 	return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2;
 }
 
+static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel)
+{
+	struct arm_pmu *pmu = kvm->arch.arm_pmu;
+
+	/*
+	 * The CPU PMU likely isn't PMUv3; let the driver provide a mapping
+	 * for the guest's PMUv3 event ID.
+	 */
+	if (unlikely(pmu->map_pmuv3_event))
+		return pmu->map_pmuv3_event(eventsel);
+
+	return eventsel;
+}
+
 /**
  * kvm_pmu_create_perf_event - create a perf event for a counter
  * @pmc: Counter context
@@ -683,7 +688,8 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
 	struct perf_event *event;
 	struct perf_event_attr attr;
-	u64 eventsel, evtreg;
+	int eventsel;
+	u64 evtreg;
 
 	evtreg = kvm_pmc_read_evtreg(pmc);
 
@@ -709,6 +715,14 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	    !test_bit(eventsel, vcpu->kvm->arch.pmu_filter))
 		return;
 
+	/*
+	 * Don't create an event if we're running on hardware that requires
+	 * PMUv3 event translation and we couldn't find a valid mapping.
+	 */
+	eventsel = kvm_map_pmu_event(vcpu->kvm, eventsel);
+	if (eventsel < 0)
+		return;
+
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.type = arm_pmu->pmu.type;
 	attr.size = sizeof(attr);
@@ -766,9 +780,6 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx);
 	u64 reg;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	reg = counter_index_to_evtreg(pmc->idx);
 	__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
 
@@ -786,29 +797,23 @@ void kvm_host_pmu_init(struct arm_pmu *pmu)
 	if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit()))
 		return;
 
-	mutex_lock(&arm_pmus_lock);
+	guard(mutex)(&arm_pmus_lock);
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		goto out_unlock;
+		return;
 
 	entry->arm_pmu = pmu;
 	list_add_tail(&entry->entry, &arm_pmus);
-
-	if (list_is_singular(&arm_pmus))
-		static_branch_enable(&kvm_arm_pmu_available);
-
-out_unlock:
-	mutex_unlock(&arm_pmus_lock);
 }
 
 static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 {
-	struct arm_pmu *tmp, *pmu = NULL;
 	struct arm_pmu_entry *entry;
+	struct arm_pmu *pmu;
 	int cpu;
 
-	mutex_lock(&arm_pmus_lock);
+	guard(mutex)(&arm_pmus_lock);
 
 	/*
 	 * It is safe to use a stale cpu to iterate the list of PMUs so long as
@@ -829,42 +834,62 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 	 */
 	cpu = raw_smp_processor_id();
 	list_for_each_entry(entry, &arm_pmus, entry) {
-		tmp = entry->arm_pmu;
+		pmu = entry->arm_pmu;
 
-		if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) {
-			pmu = tmp;
-			break;
-		}
+		if (cpumask_test_cpu(cpu, &pmu->supported_cpus))
+			return pmu;
 	}
 
-	mutex_unlock(&arm_pmus_lock);
+	return NULL;
+}
+
+static u64 __compute_pmceid(struct arm_pmu *pmu, bool pmceid1)
+{
+	u32 hi[2], lo[2];
+
+	bitmap_to_arr32(lo, pmu->pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+	bitmap_to_arr32(hi, pmu->pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 
-	return pmu;
+	return ((u64)hi[pmceid1] << 32) | lo[pmceid1];
+}
+
+static u64 compute_pmceid0(struct arm_pmu *pmu)
+{
+	u64 val = __compute_pmceid(pmu, 0);
+
+	/* always support SW_INCR */
+	val |= BIT(ARMV8_PMUV3_PERFCTR_SW_INCR);
+	/* always support CHAIN */
+	val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
+	return val;
+}
+
+static u64 compute_pmceid1(struct arm_pmu *pmu)
+{
+	u64 val = __compute_pmceid(pmu, 1);
+
+	/*
+	 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
+	 * as RAZ
+	 */
+	val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
+		 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
+		 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
+	return val;
 }
 
 u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 {
+	struct arm_pmu *cpu_pmu = vcpu->kvm->arch.arm_pmu;
 	unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
 	u64 val, mask = 0;
 	int base, i, nr_events;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	if (!pmceid1) {
-		val = read_sysreg(pmceid0_el0);
-		/* always support CHAIN */
-		val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
+		val = compute_pmceid0(cpu_pmu);
 		base = 0;
 	} else {
-		val = read_sysreg(pmceid1_el0);
-		/*
-		 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
-		 * as RAZ
-		 */
-		val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
-			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
-			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
+		val = compute_pmceid1(cpu_pmu);
 		base = 32;
 	}
 
@@ -900,9 +925,6 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
 
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	if (!vcpu->arch.pmu.created)
 		return -EINVAL;
 
@@ -925,9 +947,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 		   return -EINVAL;
 	}
 
-	/* One-off reload of the PMU on first run */
-	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
-
 	return 0;
 }
 
@@ -995,6 +1014,13 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
 	struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
 
 	/*
+	 * PMUv3 requires that all event counters are capable of counting any
+	 * event, though the same may not be true of non-PMUv3 hardware.
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return 1;
+
+	/*
 	 * The arm_pmu->cntr_mask considers the fixed counter(s) as well.
 	 * Ignore those and return only the general-purpose counters.
 	 */
@@ -1205,13 +1231,26 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
-	u64 tmp;
+	unsigned int pmuver;
+
+	pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer,
+			       read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1));
+
+	/*
+	 * Spoof a barebones PMUv3 implementation if the system supports IMPDEF
+	 * traps of the PMUv3 sysregs
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return ID_AA64DFR0_EL1_PMUVer_IMP;
+
+	/*
+	 * Otherwise, treat IMPLEMENTATION DEFINED functionality as
+	 * unimplemented
+	 */
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return 0;
 
-	tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
-	tmp = cpuid_feature_cap_perfmon_field(tmp,
-					      ID_AA64DFR0_EL1_PMUVer_SHIFT,
-					      ID_AA64DFR0_EL1_PMUVer_V3P5);
-	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
+	return min(pmuver, ID_AA64DFR0_EL1_PMUVer_V3P5);
 }
 
 /**
@@ -1231,9 +1270,6 @@ void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu)
 	unsigned long mask;
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
 	for_each_set_bit(i, &mask, 32) {
 		struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 0b3adf3e17b4..6b48a3d16d0d 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -41,7 +41,7 @@ void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr)
 {
 	struct kvm_pmu_events *pmu = kvm_get_pmu_events();
 
-	if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr))
+	if (!system_supports_pmuv3() || !kvm_pmu_switch_needed(attr))
 		return;
 
 	if (!attr->exclude_host)
@@ -57,7 +57,7 @@ void kvm_clr_pmu_events(u64 clr)
 {
 	struct kvm_pmu_events *pmu = kvm_get_pmu_events();
 
-	if (!kvm_arm_support_pmu_v3())
+	if (!system_supports_pmuv3())
 		return;
 
 	pmu->events_host &= ~clr;
@@ -133,7 +133,7 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 	struct kvm_pmu_events *pmu;
 	u64 events_guest, events_host;
 
-	if (!kvm_arm_support_pmu_v3() || !has_vhe())
+	if (!system_supports_pmuv3() || !has_vhe())
 		return;
 
 	preempt_disable();
@@ -154,7 +154,7 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
 	struct kvm_pmu_events *pmu;
 	u64 events_guest, events_host;
 
-	if (!kvm_arm_support_pmu_v3() || !has_vhe())
+	if (!system_supports_pmuv3() || !has_vhe())
 		return;
 
 	pmu = kvm_get_pmu_events();
@@ -180,7 +180,7 @@ bool kvm_set_pmuserenr(u64 val)
 	struct kvm_cpu_context *hctxt;
 	struct kvm_vcpu *vcpu;
 
-	if (!kvm_arm_support_pmu_v3() || !has_vhe())
+	if (!system_supports_pmuv3() || !has_vhe())
 		return false;
 
 	vcpu = kvm_get_running_vcpu();
diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c
index e4a342e903e2..098416d7e5c2 100644
--- a/arch/arm64/kvm/ptdump.c
+++ b/arch/arm64/kvm/ptdump.c
@@ -52,8 +52,8 @@ static const struct ptdump_prot_bits stage2_pte_bits[] = {
 		.set	= "AF",
 		.clear	= "  ",
 	}, {
-		.mask	= PTE_TABLE_BIT | PTE_VALID,
-		.val	= PTE_VALID,
+		.mask	= PMD_TYPE_MASK,
+		.val	= PMD_TYPE_SECT,
 		.set	= "BLK",
 		.clear	= "   ",
 	},
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 803e11b0dc8f..f82fcc614e13 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -196,9 +196,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.reset_state.reset = false;
 	spin_unlock(&vcpu->arch.mp_state_lock);
 
-	/* Reset PMU outside of the non-preemptible section */
-	kvm_pmu_vcpu_reset(vcpu);
-
 	preempt_disable();
 	loaded = (vcpu->cpu != -1);
 	if (loaded)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 82430c1e1dd0..5dde9285afc8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/printk.h>
 #include <linux/uaccess.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/arm_pmuv3.h>
 #include <asm/cacheflush.h>
@@ -531,7 +532,13 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	if (p->Op1 == 4) {	/* ICC_SRE_EL2 */
+		p->regval = (ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE |
+			     ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB);
+	} else {		/* ICC_SRE_EL1 */
+		p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	}
+
 	return true;
 }
 
@@ -960,6 +967,22 @@ static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	return 0;
 }
 
+static int set_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+			  u64 val)
+{
+	u64 idx;
+
+	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0)
+		/* PMCCNTR_EL0 */
+		idx = ARMV8_PMU_CYCLE_IDX;
+	else
+		/* PMEVCNTRn_EL0 */
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+
+	kvm_pmu_set_counter_value_user(vcpu, idx, val);
+	return 0;
+}
+
 static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			      struct sys_reg_params *p,
 			      const struct sys_reg_desc *r)
@@ -1051,25 +1074,10 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val)
 {
-	bool set;
-
-	val &= kvm_pmu_accessible_counter_mask(vcpu);
-
-	switch (r->reg) {
-	case PMOVSSET_EL0:
-		/* CRm[1] being set indicates a SET register, and CLR otherwise */
-		set = r->CRm & 2;
-		break;
-	default:
-		/* Op2[0] being set indicates a SET register, and CLR otherwise */
-		set = r->Op2 & 1;
-		break;
-	}
+	u64 mask = kvm_pmu_accessible_counter_mask(vcpu);
 
-	if (set)
-		__vcpu_sys_reg(vcpu, r->reg) |= val;
-	else
-		__vcpu_sys_reg(vcpu, r->reg) &= ~val;
+	__vcpu_sys_reg(vcpu, r->reg) = val & mask;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
 }
@@ -1229,6 +1237,8 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		val |= ARMV8_PMU_PMCR_LC;
 
 	__vcpu_sys_reg(vcpu, r->reg) = val;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
+
 	return 0;
 }
 
@@ -1255,6 +1265,7 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 #define PMU_PMEVCNTR_EL0(n)						\
 	{ PMU_SYS_REG(PMEVCNTRn_EL0(n)),				\
 	  .reset = reset_pmevcntr, .get_user = get_pmu_evcntr,		\
+	  .set_user = set_pmu_evcntr,					\
 	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
@@ -1627,6 +1638,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		break;
 	case SYS_ID_AA64MMFR2_EL1:
 		val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
+		val &= ~ID_AA64MMFR2_EL1_NV;
 		break;
 	case SYS_ID_AA64MMFR3_EL1:
 		val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE |
@@ -1637,6 +1649,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		break;
 	}
 
+	if (vcpu_has_nv(vcpu))
+		val = limit_nv_id_reg(vcpu->kvm, id, val);
+
 	return val;
 }
 
@@ -1663,15 +1678,24 @@ static bool is_feature_id_reg(u32 encoding)
  * Return true if the register's (Op0, Op1, CRn, CRm, Op2) is
  * (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8, which is the range of ID
  * registers KVM maintains on a per-VM basis.
+ *
+ * Additionally, the implementation ID registers and CTR_EL0 are handled as
+ * per-VM registers.
  */
 static inline bool is_vm_ftr_id_reg(u32 id)
 {
-	if (id == SYS_CTR_EL0)
+	switch (id) {
+	case SYS_CTR_EL0:
+	case SYS_MIDR_EL1:
+	case SYS_REVIDR_EL1:
+	case SYS_AIDR_EL1:
 		return true;
+	default:
+		return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
+			sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
+			sys_reg_CRm(id) < 8);
 
-	return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
-		sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
-		sys_reg_CRm(id) < 8);
+	}
 }
 
 static inline bool is_vcpu_ftr_id_reg(u32 id)
@@ -1802,16 +1826,6 @@ static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 	return val;
 }
 
-#define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit)			       \
-({									       \
-	u64 __f_val = FIELD_GET(reg##_##field##_MASK, val);		       \
-	(val) &= ~reg##_##field##_MASK;					       \
-	(val) |= FIELD_PREP(reg##_##field##_MASK,			       \
-			    min(__f_val,				       \
-				(u64)SYS_FIELD_VALUE(reg, field, limit)));     \
-	(val);								       \
-})
-
 static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 {
 	val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8);
@@ -1870,12 +1884,14 @@ static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu,
 static u64 read_sanitised_id_dfr0_el1(struct kvm_vcpu *vcpu,
 				      const struct sys_reg_desc *rd)
 {
-	u8 perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
+	u8 perfmon;
 	u64 val = read_sanitised_ftr_reg(SYS_ID_DFR0_EL1);
 
 	val &= ~ID_DFR0_EL1_PerfMon_MASK;
-	if (kvm_vcpu_has_pmu(vcpu))
+	if (kvm_vcpu_has_pmu(vcpu)) {
+		perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
 		val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon);
+	}
 
 	val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8);
 
@@ -1929,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 	if ((hw_val & mpam_mask) == (user_val & mpam_mask))
 		user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
 
+	/* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */
+	if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) ||
+	    !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) ||
+	    (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val)))
+		return -EINVAL;
+
 	return set_id_reg(vcpu, rd, user_val);
 }
 
@@ -1945,6 +1967,37 @@ static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu,
 	return set_id_reg(vcpu, rd, user_val);
 }
 
+static int set_id_aa64mmfr0_el1(struct kvm_vcpu *vcpu,
+				const struct sys_reg_desc *rd, u64 user_val)
+{
+	u64 sanitized_val = kvm_read_sanitised_id_reg(vcpu, rd);
+	u64 tgran2_mask = ID_AA64MMFR0_EL1_TGRAN4_2_MASK |
+			  ID_AA64MMFR0_EL1_TGRAN16_2_MASK |
+			  ID_AA64MMFR0_EL1_TGRAN64_2_MASK;
+
+	if (vcpu_has_nv(vcpu) &&
+	    ((sanitized_val & tgran2_mask) != (user_val & tgran2_mask)))
+		return -EINVAL;
+
+	return set_id_reg(vcpu, rd, user_val);
+}
+
+static int set_id_aa64mmfr2_el1(struct kvm_vcpu *vcpu,
+				const struct sys_reg_desc *rd, u64 user_val)
+{
+	u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1);
+	u64 nv_mask = ID_AA64MMFR2_EL1_NV_MASK;
+
+	/*
+	 * We made the mistake to expose the now deprecated NV field,
+	 * so allow userspace to write it, but silently ignore it.
+	 */
+	if ((hw_val & nv_mask) == (user_val & nv_mask))
+		user_val &= ~nv_mask;
+
+	return set_id_reg(vcpu, rd, user_val);
+}
+
 static int set_ctr_el0(struct kvm_vcpu *vcpu,
 		       const struct sys_reg_desc *rd, u64 user_val)
 {
@@ -2266,35 +2319,33 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
  * from userspace.
  */
 
+#define ID_DESC_DEFAULT_CALLBACKS		\
+	.access	= access_id_reg,		\
+	.get_user = get_id_reg,			\
+	.set_user = set_id_reg,			\
+	.visibility = id_visibility,		\
+	.reset = kvm_read_sanitised_id_reg
+
 #define ID_DESC(name)				\
 	SYS_DESC(SYS_##name),			\
-	.access	= access_id_reg,		\
-	.get_user = get_id_reg			\
+	ID_DESC_DEFAULT_CALLBACKS
 
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	ID_DESC(name),				\
-	.set_user = set_id_reg,			\
-	.visibility = id_visibility,		\
-	.reset = kvm_read_sanitised_id_reg,	\
 	.val = 0,				\
 }
 
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define AA32_ID_SANITISED(name) {		\
 	ID_DESC(name),				\
-	.set_user = set_id_reg,			\
 	.visibility = aa32_id_visibility,	\
-	.reset = kvm_read_sanitised_id_reg,	\
 	.val = 0,				\
 }
 
 /* sys_reg_desc initialiser for writable ID registers */
 #define ID_WRITABLE(name, mask) {		\
 	ID_DESC(name),				\
-	.set_user = set_id_reg,			\
-	.visibility = id_visibility,		\
-	.reset = kvm_read_sanitised_id_reg,	\
 	.val = mask,				\
 }
 
@@ -2302,8 +2353,6 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
 #define ID_FILTERED(sysreg, name, mask) {	\
 	ID_DESC(sysreg),				\
 	.set_user = set_##name,				\
-	.visibility = id_visibility,			\
-	.reset = kvm_read_sanitised_id_reg,		\
 	.val = (mask),					\
 }
 
@@ -2313,12 +2362,10 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
  * (1 <= crm < 8, 0 <= Op2 < 8).
  */
 #define ID_UNALLOCATED(crm, op2) {			\
+	.name = "S3_0_0_" #crm "_" #op2,		\
 	Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2),	\
-	.access = access_id_reg,			\
-	.get_user = get_id_reg,				\
-	.set_user = set_id_reg,				\
+	ID_DESC_DEFAULT_CALLBACKS,			\
 	.visibility = raz_visibility,			\
-	.reset = kvm_read_sanitised_id_reg,		\
 	.val = 0,					\
 }
 
@@ -2329,9 +2376,7 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
  */
 #define ID_HIDDEN(name) {			\
 	ID_DESC(name),				\
-	.set_user = set_id_reg,			\
 	.visibility = raz_visibility,		\
-	.reset = kvm_read_sanitised_id_reg,	\
 	.val = 0,				\
 }
 
@@ -2426,6 +2471,59 @@ static bool access_zcr_el2(struct kvm_vcpu *vcpu,
 	vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1;
 	vq = min(vq, vcpu_sve_max_vq(vcpu));
 	vcpu_write_sys_reg(vcpu, vq - 1, ZCR_EL2);
+
+	return true;
+}
+
+static bool access_gic_vtr(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = kvm_vgic_global_state.ich_vtr_el2;
+	p->regval &= ~(ICH_VTR_EL2_DVIM 	|
+		       ICH_VTR_EL2_A3V		|
+		       ICH_VTR_EL2_IDbits);
+	p->regval |= ICH_VTR_EL2_nV4;
+
+	return true;
+}
+
+static bool access_gic_misr(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_misr(vcpu);
+
+	return true;
+}
+
+static bool access_gic_eisr(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_eisr(vcpu);
+
+	return true;
+}
+
+static bool access_gic_elrsr(struct kvm_vcpu *vcpu,
+			     struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = vgic_v3_get_elrsr(vcpu);
+
 	return true;
 }
 
@@ -2493,6 +2591,120 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+/*
+ * For historical (ahem ABI) reasons, KVM treated MIDR_EL1, REVIDR_EL1, and
+ * AIDR_EL1 as "invariant" registers, meaning userspace cannot change them.
+ * The values made visible to userspace were the register values of the boot
+ * CPU.
+ *
+ * At the same time, reads from these registers at EL1 previously were not
+ * trapped, allowing the guest to read the actual hardware value. On big-little
+ * machines, this means the VM can see different values depending on where a
+ * given vCPU got scheduled.
+ *
+ * These registers are now trapped as collateral damage from SME, and what
+ * follows attempts to give a user / guest view consistent with the existing
+ * ABI.
+ */
+static bool access_imp_id_reg(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	/*
+	 * Return the VM-scoped implementation ID register values if userspace
+	 * has made them writable.
+	 */
+	if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &vcpu->kvm->arch.flags))
+		return access_id_reg(vcpu, p, r);
+
+	/*
+	 * Otherwise, fall back to the old behavior of returning the value of
+	 * the current CPU.
+	 */
+	switch (reg_to_encoding(r)) {
+	case SYS_REVIDR_EL1:
+		p->regval = read_sysreg(revidr_el1);
+		break;
+	case SYS_AIDR_EL1:
+		p->regval = read_sysreg(aidr_el1);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+
+	return true;
+}
+
+static u64 __ro_after_init boot_cpu_midr_val;
+static u64 __ro_after_init boot_cpu_revidr_val;
+static u64 __ro_after_init boot_cpu_aidr_val;
+
+static void init_imp_id_regs(void)
+{
+	boot_cpu_midr_val = read_sysreg(midr_el1);
+	boot_cpu_revidr_val = read_sysreg(revidr_el1);
+	boot_cpu_aidr_val = read_sysreg(aidr_el1);
+}
+
+static u64 reset_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	switch (reg_to_encoding(r)) {
+	case SYS_MIDR_EL1:
+		return boot_cpu_midr_val;
+	case SYS_REVIDR_EL1:
+		return boot_cpu_revidr_val;
+	case SYS_AIDR_EL1:
+		return boot_cpu_aidr_val;
+	default:
+		KVM_BUG_ON(1, vcpu->kvm);
+		return 0;
+	}
+}
+
+static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+			  u64 val)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 expected;
+
+	guard(mutex)(&kvm->arch.config_lock);
+
+	expected = read_id_reg(vcpu, r);
+	if (expected == val)
+		return 0;
+
+	if (!test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags))
+		return -EINVAL;
+
+	/*
+	 * Once the VM has started the ID registers are immutable. Reject the
+	 * write if userspace tries to change it.
+	 */
+	if (kvm_vm_has_ran_once(kvm))
+		return -EBUSY;
+
+	/*
+	 * Any value is allowed for the implementation ID registers so long as
+	 * it is within the writable mask.
+	 */
+	if ((val & r->val) != val)
+		return -EINVAL;
+
+	kvm_set_vm_id_reg(kvm, reg_to_encoding(r), val);
+	return 0;
+}
+
+#define IMPLEMENTATION_ID(reg, mask) {			\
+	SYS_DESC(SYS_##reg),				\
+	.access = access_imp_id_reg,			\
+	.get_user = get_id_reg,				\
+	.set_user = set_imp_id_reg,			\
+	.reset = reset_imp_id_reg,			\
+	.val = mask,					\
+}
 
 /*
  * Architected system registers.
@@ -2542,7 +2754,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_DBGVCR32_EL2), undef_access, reset_val, DBGVCR32_EL2, 0 },
 
+	IMPLEMENTATION_ID(MIDR_EL1, GENMASK_ULL(31, 0)),
 	{ SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 },
+	IMPLEMENTATION_ID(REVIDR_EL1, GENMASK_ULL(63, 0)),
 
 	/*
 	 * ID regs: all ID_SANITISED() entries here must have corresponding
@@ -2660,10 +2874,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(6,7),
 
 	/* CRm=7 */
-	ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 |
-					ID_AA64MMFR0_EL1_TGRAN4_2 |
-					ID_AA64MMFR0_EL1_TGRAN64_2 |
-					ID_AA64MMFR0_EL1_TGRAN16_2 |
+	ID_FILTERED(ID_AA64MMFR0_EL1, id_aa64mmfr0_el1,
+				      ~(ID_AA64MMFR0_EL1_RES0 |
 					ID_AA64MMFR0_EL1_ASIDBITS)),
 	ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
 					ID_AA64MMFR1_EL1_HCX |
@@ -2671,7 +2883,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 					ID_AA64MMFR1_EL1_XNX |
 					ID_AA64MMFR1_EL1_VH |
 					ID_AA64MMFR1_EL1_VMIDBits)),
-	ID_WRITABLE(ID_AA64MMFR2_EL1, ~(ID_AA64MMFR2_EL1_RES0 |
+	ID_FILTERED(ID_AA64MMFR2_EL1,
+		    id_aa64mmfr2_el1, ~(ID_AA64MMFR2_EL1_RES0 |
 					ID_AA64MMFR2_EL1_EVT |
 					ID_AA64MMFR2_EL1_FWB |
 					ID_AA64MMFR2_EL1_IDS |
@@ -2680,7 +2893,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX	|
 				       ID_AA64MMFR3_EL1_S1PIE   |
 				       ID_AA64MMFR3_EL1_S1POE)),
-	ID_SANITISED(ID_AA64MMFR4_EL1),
+	ID_WRITABLE(ID_AA64MMFR4_EL1, ID_AA64MMFR4_EL1_NV_frac),
 	ID_UNALLOCATED(7,5),
 	ID_UNALLOCATED(7,6),
 	ID_UNALLOCATED(7,7),
@@ -2814,6 +3027,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  .set_user = set_clidr, .val = ~CLIDR_EL1_RES0 },
 	{ SYS_DESC(SYS_CCSIDR2_EL1), undef_access },
 	{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
+	IMPLEMENTATION_ID(AIDR_EL1, GENMASK_ULL(63, 0)),
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
 	ID_FILTERED(CTR_EL0, ctr_el0,
 		    CTR_EL0_DIC_MASK |
@@ -2850,7 +3064,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  .access = access_pmceid, .reset = NULL },
 	{ PMU_SYS_REG(PMCCNTR_EL0),
 	  .access = access_pmu_evcntr, .reset = reset_unknown,
-	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr},
+	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr,
+	  .set_user = set_pmu_evcntr },
 	{ PMU_SYS_REG(PMXEVTYPER_EL0),
 	  .access = access_pmu_evtyper, .reset = NULL },
 	{ PMU_SYS_REG(PMXEVCNTR_EL0),
@@ -3102,7 +3317,40 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(RVBAR_EL2, access_rw, reset_val, 0),
 	{ SYS_DESC(SYS_RMR_EL2), undef_access },
 
+	EL2_REG_VNCR(ICH_AP0R0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP0R3_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_AP1R3_EL2, reset_val, 0),
+
+	{ SYS_DESC(SYS_ICC_SRE_EL2), access_gic_sre },
+
 	EL2_REG_VNCR(ICH_HCR_EL2, reset_val, 0),
+	{ SYS_DESC(SYS_ICH_VTR_EL2), access_gic_vtr },
+	{ SYS_DESC(SYS_ICH_MISR_EL2), access_gic_misr },
+	{ SYS_DESC(SYS_ICH_EISR_EL2), access_gic_eisr },
+	{ SYS_DESC(SYS_ICH_ELRSR_EL2), access_gic_elrsr },
+	EL2_REG_VNCR(ICH_VMCR_EL2, reset_val, 0),
+
+	EL2_REG_VNCR(ICH_LR0_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR1_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR2_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR3_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR4_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR5_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR6_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR7_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR8_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR9_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR10_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR11_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR12_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR13_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR14_EL2, reset_val, 0),
+	EL2_REG_VNCR(ICH_LR15_EL2, reset_val, 0),
 
 	EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
 	EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
@@ -4272,9 +4520,13 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu)
 	 * Certain AArch32 ID registers are handled by rerouting to the AArch64
 	 * system register table. Registers in the ID range where CRm=0 are
 	 * excluded from this scheme as they do not trivially map into AArch64
-	 * system register encodings.
+	 * system register encodings, except for AIDR/REVIDR.
 	 */
-	if (params.Op1 == 0 && params.CRn == 0 && params.CRm)
+	if (params.Op1 == 0 && params.CRn == 0 &&
+	    (params.CRm || params.Op2 == 6 /* REVIDR */))
+		return kvm_emulate_cp15_id_reg(vcpu, &params);
+	if (params.Op1 == 1 && params.CRn == 0 &&
+	    params.CRm == 0 && params.Op2 == 7 /* AIDR */)
 		return kvm_emulate_cp15_id_reg(vcpu, &params);
 
 	return kvm_handle_cp_32(vcpu, &params, cp15_regs, ARRAY_SIZE(cp15_regs));
@@ -4473,6 +4725,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 	}
 
 	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
+
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 }
 
 /**
@@ -4578,65 +4833,6 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-/*
- * These are the invariant sys_reg registers: we let the guest see the
- * host versions of these, so they're part of the guest state.
- *
- * A future CPU may provide a mechanism to present different values to
- * the guest, or a future kvm may trap them.
- */
-
-#define FUNCTION_INVARIANT(reg)						\
-	static u64 reset_##reg(struct kvm_vcpu *v,			\
-			       const struct sys_reg_desc *r)		\
-	{								\
-		((struct sys_reg_desc *)r)->val = read_sysreg(reg);	\
-		return ((struct sys_reg_desc *)r)->val;			\
-	}
-
-FUNCTION_INVARIANT(midr_el1)
-FUNCTION_INVARIANT(revidr_el1)
-FUNCTION_INVARIANT(aidr_el1)
-
-/* ->val is filled in by kvm_sys_reg_table_init() */
-static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = {
-	{ SYS_DESC(SYS_MIDR_EL1), NULL, reset_midr_el1 },
-	{ SYS_DESC(SYS_REVIDR_EL1), NULL, reset_revidr_el1 },
-	{ SYS_DESC(SYS_AIDR_EL1), NULL, reset_aidr_el1 },
-};
-
-static int get_invariant_sys_reg(u64 id, u64 __user *uaddr)
-{
-	const struct sys_reg_desc *r;
-
-	r = get_reg_by_id(id, invariant_sys_regs,
-			  ARRAY_SIZE(invariant_sys_regs));
-	if (!r)
-		return -ENOENT;
-
-	return put_user(r->val, uaddr);
-}
-
-static int set_invariant_sys_reg(u64 id, u64 __user *uaddr)
-{
-	const struct sys_reg_desc *r;
-	u64 val;
-
-	r = get_reg_by_id(id, invariant_sys_regs,
-			  ARRAY_SIZE(invariant_sys_regs));
-	if (!r)
-		return -ENOENT;
-
-	if (get_user(val, uaddr))
-		return -EFAULT;
-
-	/* This is what we mean by invariant: you can't change it. */
-	if (r->val != val)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
 {
 	u32 val;
@@ -4718,15 +4914,10 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	void __user *uaddr = (void __user *)(unsigned long)reg->addr;
-	int err;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_get(vcpu, reg->id, uaddr);
 
-	err = get_invariant_sys_reg(reg->id, uaddr);
-	if (err != -ENOENT)
-		return err;
-
 	return kvm_sys_reg_get_user(vcpu, reg,
 				    sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 }
@@ -4762,15 +4953,10 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	void __user *uaddr = (void __user *)(unsigned long)reg->addr;
-	int err;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_set(vcpu, reg->id, uaddr);
 
-	err = set_invariant_sys_reg(reg->id, uaddr);
-	if (err != -ENOENT)
-		return err;
-
 	return kvm_sys_reg_set_user(vcpu, reg,
 				    sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 }
@@ -4859,23 +5045,14 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
 
 unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu)
 {
-	return ARRAY_SIZE(invariant_sys_regs)
-		+ num_demux_regs()
+	return num_demux_regs()
 		+ walk_sys_regs(vcpu, (u64 __user *)NULL);
 }
 
 int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
-	unsigned int i;
 	int err;
 
-	/* Then give them all the invariant registers' indices. */
-	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) {
-		if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices))
-			return -EFAULT;
-		uindices++;
-	}
-
 	err = walk_sys_regs(vcpu, uindices);
 	if (err < 0)
 		return err;
@@ -4971,25 +5148,7 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 	mutex_lock(&kvm->arch.config_lock);
 	vcpu_set_hcr(vcpu);
 	vcpu_set_ich_hcr(vcpu);
-
-	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
-		/*
-		 * In general, all HCRX_EL2 bits are gated by a feature.
-		 * The only reason we can set SMPME without checking any
-		 * feature is that its effects are not directly observable
-		 * from the guest.
-		 */
-		vcpu->arch.hcrx_el2 = HCRX_EL2_SMPME;
-
-		if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
-			vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
-
-		if (kvm_has_tcr2(kvm))
-			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;
-
-		if (kvm_has_fpmr(kvm))
-			vcpu->arch.hcrx_el2 |= HCRX_EL2_EnFPM;
-	}
+	vcpu_set_hcrx(vcpu);
 
 	if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
 		goto out;
@@ -5101,15 +5260,12 @@ int __init kvm_sys_reg_table_init(void)
 	valid &= check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true);
 	valid &= check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true);
 	valid &= check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true);
-	valid &= check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false);
 	valid &= check_sysreg_table(sys_insn_descs, ARRAY_SIZE(sys_insn_descs), false);
 
 	if (!valid)
 		return -EINVAL;
 
-	/* We abuse the reset function to overwrite the table itself. */
-	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
-		invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);
+	init_imp_id_regs();
 
 	ret = populate_nv_trap_config();
 
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 1d94ed6efad2..cc6338d38766 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -247,4 +247,14 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu);
 	CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)),	\
 	Op2(sys_reg_Op2(reg))
 
+#define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit)			       \
+({									       \
+	u64 __f_val = FIELD_GET(reg##_##field##_MASK, val);		       \
+	(val) &= ~reg##_##field##_MASK;					       \
+	(val) |= FIELD_PREP(reg##_##field##_MASK,			       \
+			    min(__f_val,				       \
+				(u64)SYS_FIELD_VALUE(reg, field, limit)));     \
+	(val);								       \
+})
+
 #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 9e7c486b48c2..5eacb4b3250a 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -35,12 +35,12 @@ static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 
 	vgic_v3_cpu->num_id_bits = host_id_bits;
 
-	host_seis = FIELD_GET(ICH_VTR_SEIS_MASK, kvm_vgic_global_state.ich_vtr_el2);
+	host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2);
 	seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val);
 	if (host_seis != seis)
 		return -EINVAL;
 
-	host_a3v = FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2);
+	host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2);
 	a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val);
 	if (host_a3v != a3v)
 		return -EINVAL;
@@ -68,10 +68,10 @@ static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	val |= FIELD_PREP(ICC_CTLR_EL1_PRI_BITS_MASK, vgic_v3_cpu->num_pri_bits - 1);
 	val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits);
 	val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK,
-			  FIELD_GET(ICH_VTR_SEIS_MASK,
+			  FIELD_GET(ICH_VTR_EL2_SEIS,
 				    kvm_vgic_global_state.ich_vtr_el2));
 	val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK,
-			  FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2));
+			  FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2));
 	/*
 	 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 	 * Extract it directly using ICC_CTLR_EL1 reg definitions.
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 775461cf2d2d..1f33e71c2a73 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -198,6 +198,27 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	return 0;
 }
 
+/* Default GICv3 Maintenance Interrupt INTID, as per SBSA */
+#define DEFAULT_MI_INTID	25
+
+int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	guard(mutex)(&vcpu->kvm->arch.config_lock);
+
+	/*
+	 * Matching the tradition established with the timers, provide
+	 * a default PPI for the maintenance interrupt. It makes
+	 * things easier to reason about.
+	 */
+	if (vcpu->kvm->arch.vgic.mi_intid == 0)
+		vcpu->kvm->arch.vgic.mi_intid = DEFAULT_MI_INTID;
+	ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.mi_intid, vcpu);
+
+	return ret;
+}
+
 static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
@@ -588,12 +609,20 @@ void kvm_vgic_cpu_down(void)
 
 static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 {
+	struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data;
+
 	/*
 	 * We cannot rely on the vgic maintenance interrupt to be
 	 * delivered synchronously. This means we can only use it to
 	 * exit the VM, and we perform the handling of EOIed
 	 * interrupts on the exit path (see vgic_fold_lr_state).
+	 *
+	 * Of course, NV throws a wrench in this plan, and needs
+	 * something special.
 	 */
+	if (vcpu && vgic_state_is_nested(vcpu))
+		vgic_v3_handle_nested_maint_irq(vcpu);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 5f4f57aaa23e..359094f68c23 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -303,6 +303,12 @@ static int vgic_get_common_attr(struct kvm_device *dev,
 			     VGIC_NR_PRIVATE_IRQS, uaddr);
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+
+		r = put_user(dev->kvm->arch.vgic.mi_intid, uaddr);
+		break;
+	}
 	}
 
 	return r;
@@ -517,7 +523,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 	struct vgic_reg_attr reg_attr;
 	gpa_t addr;
 	struct kvm_vcpu *vcpu;
-	bool uaccess;
+	bool uaccess, post_init = true;
 	u32 val;
 	int ret;
 
@@ -533,6 +539,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 		/* Sysregs uaccess is performed by the sysreg handling code */
 		uaccess = false;
 		break;
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
+		post_init = false;
+		fallthrough;
 	default:
 		uaccess = true;
 	}
@@ -552,7 +561,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->arch.config_lock);
 
-	if (unlikely(!vgic_initialized(dev->kvm))) {
+	if (post_init != vgic_initialized(dev->kvm)) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -582,6 +591,19 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 		}
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
+		if (!is_write) {
+			val = dev->kvm->arch.vgic.mi_intid;
+			ret = 0;
+			break;
+		}
+
+		ret = -EINVAL;
+		if ((val < VGIC_NR_PRIVATE_IRQS) && (val >= VGIC_NR_SGIS)) {
+			dev->kvm->arch.vgic.mi_intid = val;
+			ret = 0;
+		}
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -608,6 +630,7 @@ static int vgic_v3_set_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return vgic_v3_attr_regs_access(dev, attr, true);
 	default:
 		return vgic_set_common_attr(dev, attr);
@@ -622,6 +645,7 @@ static int vgic_v3_get_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return vgic_v3_attr_regs_access(dev, attr, false);
 	default:
 		return vgic_get_common_attr(dev, attr);
@@ -645,6 +669,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
 	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS:
 		return vgic_v3_has_attr_regs(dev, attr);
 	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+	case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ:
 		return 0;
 	case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: {
 		if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >>
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
new file mode 100644
index 000000000000..bfa5bde1f106
--- /dev/null
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+
+#include <kvm/arm_vgic.h>
+
+#include <asm/kvm_arm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_nested.h>
+
+#include "vgic.h"
+
+#define ICH_LRN(n)	(ICH_LR0_EL2 + (n))
+#define ICH_AP0RN(n)	(ICH_AP0R0_EL2 + (n))
+#define ICH_AP1RN(n)	(ICH_AP1R0_EL2 + (n))
+
+struct mi_state {
+	u16	eisr;
+	u16	elrsr;
+	bool	pend;
+};
+
+/*
+ * The shadow registers loaded to the hardware when running a L2 guest
+ * with the virtual IMO/FMO bits set.
+ */
+struct shadow_if {
+	struct vgic_v3_cpu_if	cpuif;
+	unsigned long		lr_map;
+};
+
+static DEFINE_PER_CPU(struct shadow_if, shadow_if);
+
+/*
+ * Nesting GICv3 support
+ *
+ * On a non-nesting VM (only running at EL0/EL1), the host hypervisor
+ * completely controls the interrupts injected via the list registers.
+ * Consequently, most of the state that is modified by the guest (by ACK-ing
+ * and EOI-ing interrupts) is synced by KVM on each entry/exit, so that we
+ * keep a semi-consistent view of the interrupts.
+ *
+ * This still applies for a NV guest, but only while "InHost" (either
+ * running at EL2, or at EL0 with HCR_EL2.{E2H.TGE}=={1,1}.
+ *
+ * When running a L2 guest ("not InHost"), things are radically different,
+ * as the L1 guest is in charge of provisioning the interrupts via its own
+ * view of the ICH_LR*_EL2 registers, which conveniently live in the VNCR
+ * page.  This means that the flow described above does work (there is no
+ * state to rebuild in the L0 hypervisor), and that most things happed on L2
+ * load/put:
+ *
+ * - on L2 load: move the in-memory L1 vGIC configuration into a shadow,
+ *   per-CPU data structure that is used to populate the actual LRs. This is
+ *   an extra copy that we could avoid, but life is short. In the process,
+ *   we remap any interrupt that has the HW bit set to the mapped interrupt
+ *   on the host, should the host consider it a HW one. This allows the HW
+ *   deactivation to take its course, such as for the timer.
+ *
+ * - on L2 put: perform the inverse transformation, so that the result of L2
+ *   running becomes visible to L1 in the VNCR-accessible registers.
+ *
+ * - there is nothing to do on L2 entry, as everything will have happened
+ *   on load. However, this is the point where we detect that an interrupt
+ *   targeting L1 and prepare the grand switcheroo.
+ *
+ * - on L2 exit: emulate the HW bit, and deactivate corresponding the L1
+ *   interrupt. The L0 active state will be cleared by the HW if the L1
+ *   interrupt was itself backed by a HW interrupt.
+ *
+ * Maintenance Interrupt (MI) management:
+ *
+ * Since the L2 guest runs the vgic in its full glory, MIs get delivered and
+ * used as a handover point between L2 and L1.
+ *
+ * - on delivery of a MI to L0 while L2 is running: make the L1 MI pending,
+ *   and let it rip. This will initiate a vcpu_put() on L2, and allow L1 to
+ *   run and process the MI.
+ *
+ * - L1 MI is a fully virtual interrupt, not linked to the host's MI. Its
+ *   state must be computed at each entry/exit of the guest, much like we do
+ *   it for the PMU interrupt.
+ *
+ * - because most of the ICH_*_EL2 registers live in the VNCR page, the
+ *   quality of emulation is poor: L1 can setup the vgic so that an MI would
+ *   immediately fire, and not observe anything until the next exit. Trying
+ *   to read ICH_MISR_EL2 would do the trick, for example.
+ *
+ * System register emulation:
+ *
+ * We get two classes of registers:
+ *
+ * - those backed by memory (LRs, APRs, HCR, VMCR): L1 can freely access
+ *   them, and L0 doesn't see a thing.
+ *
+ * - those that always trap (ELRSR, EISR, MISR): these are status registers
+ *   that are built on the fly based on the in-memory state.
+ *
+ * Only L1 can access the ICH_*_EL2 registers. A non-NV L2 obviously cannot,
+ * and a NV L2 would either access the VNCR page provided by L1 (memory
+ * based registers), or see the access redirected to L1 (registers that
+ * trap) thanks to NV being set by L1.
+ */
+
+bool vgic_state_is_nested(struct kvm_vcpu *vcpu)
+{
+	u64 xmo;
+
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+		xmo = __vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_IMO | HCR_FMO);
+		WARN_ONCE(xmo && xmo != (HCR_IMO | HCR_FMO),
+			  "Separate virtual IRQ/FIQ settings not supported\n");
+
+		return !!xmo;
+	}
+
+	return false;
+}
+
+static struct shadow_if *get_shadow_if(void)
+{
+	return this_cpu_ptr(&shadow_if);
+}
+
+static bool lr_triggers_eoi(u64 lr)
+{
+	return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI);
+}
+
+static void vgic_compute_mi_state(struct kvm_vcpu *vcpu, struct mi_state *mi_state)
+{
+	u16 eisr = 0, elrsr = 0;
+	bool pend = false;
+
+	for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+
+		if (lr_triggers_eoi(lr))
+			eisr |= BIT(i);
+		if (!(lr & ICH_LR_STATE))
+			elrsr |= BIT(i);
+		pend |= (lr & ICH_LR_PENDING_BIT);
+	}
+
+	mi_state->eisr	= eisr;
+	mi_state->elrsr	= elrsr;
+	mi_state->pend	= pend;
+}
+
+u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+	return mi_state.eisr;
+}
+
+u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+	return mi_state.elrsr;
+}
+
+u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
+{
+	struct mi_state mi_state;
+	u64 reg = 0, hcr, vmcr;
+
+	hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
+
+	vgic_compute_mi_state(vcpu, &mi_state);
+
+	if (mi_state.eisr)
+		reg |= ICH_MISR_EL2_EOI;
+
+	if (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_UIE) {
+		int used_lrs = kvm_vgic_global_state.nr_lr;
+
+		used_lrs -= hweight16(mi_state.elrsr);
+		reg |= (used_lrs <= 1) ? ICH_MISR_EL2_U : 0;
+	}
+
+	if ((hcr & ICH_HCR_EL2_LRENPIE) && FIELD_GET(ICH_HCR_EL2_EOIcount_MASK, hcr))
+		reg |= ICH_MISR_EL2_LRENP;
+
+	if ((hcr & ICH_HCR_EL2_NPIE) && !mi_state.pend)
+		reg |= ICH_MISR_EL2_NP;
+
+	if ((hcr & ICH_HCR_EL2_VGrp0EIE) && (vmcr & ICH_VMCR_ENG0_MASK))
+		reg |= ICH_MISR_EL2_VGrp0E;
+
+	if ((hcr & ICH_HCR_EL2_VGrp0DIE) && !(vmcr & ICH_VMCR_ENG0_MASK))
+		reg |= ICH_MISR_EL2_VGrp0D;
+
+	if ((hcr & ICH_HCR_EL2_VGrp1EIE) && (vmcr & ICH_VMCR_ENG1_MASK))
+		reg |= ICH_MISR_EL2_VGrp1E;
+
+	if ((hcr & ICH_HCR_EL2_VGrp1DIE) && !(vmcr & ICH_VMCR_ENG1_MASK))
+		reg |= ICH_MISR_EL2_VGrp1D;
+
+	return reg;
+}
+
+/*
+ * For LRs which have HW bit set such as timer interrupts, we modify them to
+ * have the host hardware interrupt number instead of the virtual one programmed
+ * by the guest hypervisor.
+ */
+static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
+				     struct vgic_v3_cpu_if *s_cpu_if)
+{
+	unsigned long lr_map = 0;
+	int index = 0;
+
+	for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+		struct vgic_irq *irq;
+
+		if (!(lr & ICH_LR_STATE))
+			lr = 0;
+
+		if (!(lr & ICH_LR_HW))
+			goto next;
+
+		/* We have the HW bit set, check for validity of pINTID */
+		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+		if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) {
+			/* There was no real mapping, so nuke the HW bit */
+			lr &= ~ICH_LR_HW;
+			if (irq)
+				vgic_put_irq(vcpu->kvm, irq);
+			goto next;
+		}
+
+		/* It is illegal to have the EOI bit set with HW */
+		lr &= ~ICH_LR_EOI;
+
+		/* Translate the virtual mapping to the real one */
+		lr &= ~ICH_LR_PHYS_ID_MASK;
+		lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
+
+		vgic_put_irq(vcpu->kvm, irq);
+
+next:
+		s_cpu_if->vgic_lr[index] = lr;
+		if (lr) {
+			lr_map |= BIT(i);
+			index++;
+		}
+	}
+
+	container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map;
+	s_cpu_if->used_lrs = index;
+}
+
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	int i, index = 0;
+
+	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
+		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+		struct vgic_irq *irq;
+
+		if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
+			goto next;
+
+		/*
+		 * If we had a HW lr programmed by the guest hypervisor, we
+		 * need to emulate the HW effect between the guest hypervisor
+		 * and the nested guest.
+		 */
+		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+		if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */
+			goto next;
+
+		lr = __gic_v3_get_lr(index);
+		if (!(lr & ICH_LR_STATE))
+			irq->active = false;
+
+		vgic_put_irq(vcpu->kvm, irq);
+	next:
+		index++;
+	}
+}
+
+static void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu,
+					struct vgic_v3_cpu_if *s_cpu_if)
+{
+	struct vgic_v3_cpu_if *host_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u64 val = 0;
+	int i;
+
+	/*
+	 * If we're on a system with a broken vgic that requires
+	 * trapping, propagate the trapping requirements.
+	 *
+	 * Ah, the smell of rotten fruits...
+	 */
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap))
+		val = host_if->vgic_hcr & (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
+					   ICH_HCR_EL2_TC | ICH_HCR_EL2_TDIR);
+	s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) | val;
+	s_cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2);
+	s_cpu_if->vgic_sre = host_if->vgic_sre;
+
+	for (i = 0; i < 4; i++) {
+		s_cpu_if->vgic_ap0r[i] = __vcpu_sys_reg(vcpu, ICH_AP0RN(i));
+		s_cpu_if->vgic_ap1r[i] = __vcpu_sys_reg(vcpu, ICH_AP1RN(i));
+	}
+
+	vgic_v3_create_shadow_lr(vcpu, s_cpu_if);
+}
+
+void vgic_v3_load_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	struct vgic_v3_cpu_if *cpu_if = &shadow_if->cpuif;
+
+	BUG_ON(!vgic_state_is_nested(vcpu));
+
+	vgic_v3_create_shadow_state(vcpu, cpu_if);
+
+	__vgic_v3_restore_vmcr_aprs(cpu_if);
+	__vgic_v3_activate_traps(cpu_if);
+
+	__vgic_v3_restore_state(cpu_if);
+
+	/*
+	 * Propagate the number of used LRs for the benefit of the HYP
+	 * GICv3 emulation code. Yes, this is a pretty sorry hack.
+	 */
+	vcpu->arch.vgic_cpu.vgic_v3.used_lrs = cpu_if->used_lrs;
+}
+
+void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
+{
+	struct shadow_if *shadow_if = get_shadow_if();
+	struct vgic_v3_cpu_if *s_cpu_if = &shadow_if->cpuif;
+	u64 val;
+	int i;
+
+	__vgic_v3_save_vmcr_aprs(s_cpu_if);
+	__vgic_v3_deactivate_traps(s_cpu_if);
+	__vgic_v3_save_state(s_cpu_if);
+
+	/*
+	 * Translate the shadow state HW fields back to the virtual ones
+	 * before copying the shadow struct back to the nested one.
+	 */
+	val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+	val &= ~ICH_HCR_EL2_EOIcount_MASK;
+	val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
+	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
+	__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
+
+	for (i = 0; i < 4; i++) {
+		__vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
+		__vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
+	}
+
+	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
+		val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
+
+		val &= ~ICH_LR_STATE;
+		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
+
+		__vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
+		s_cpu_if->vgic_lr[i] = 0;
+	}
+
+	shadow_if->lr_map = 0;
+	vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0;
+}
+
+/*
+ * If we exit a L2 VM with a pending maintenance interrupt from the GIC,
+ * then we need to forward this to L1 so that it can re-sync the appropriate
+ * LRs and sample level triggered interrupts again.
+ */
+void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu)
+{
+	bool state = read_sysreg_s(SYS_ICH_MISR_EL2);
+
+	/* This will force a switch back to L1 if the level is high */
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    vcpu->kvm->arch.vgic.mi_intid, state, vcpu);
+
+	sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0);
+}
+
+void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
+{
+	bool level;
+
+	level  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
+	if (level)
+		level &= vgic_v3_get_misr(vcpu);
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
+}
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index d7233ab982d0..b9ad7c42c5b0 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -24,7 +24,7 @@ void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	cpuif->vgic_hcr |= ICH_HCR_UIE;
+	cpuif->vgic_hcr |= ICH_HCR_EL2_UIE;
 }
 
 static bool lr_signals_eoi_mi(u64 lr_val)
@@ -42,7 +42,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	cpuif->vgic_hcr &= ~ICH_HCR_EL2_UIE;
 
 	for (lr = 0; lr < cpuif->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];
@@ -284,15 +284,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 		vgic_v3->vgic_sre = 0;
 	}
 
-	vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 &
-					   ICH_VTR_ID_BITS_MASK) >>
-					   ICH_VTR_ID_BITS_SHIFT;
-	vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 &
-					    ICH_VTR_PRI_BITS_MASK) >>
-					    ICH_VTR_PRI_BITS_SHIFT) + 1;
+	vcpu->arch.vgic_cpu.num_id_bits = FIELD_GET(ICH_VTR_EL2_IDbits,
+						    kvm_vgic_global_state.ich_vtr_el2);
+	vcpu->arch.vgic_cpu.num_pri_bits = FIELD_GET(ICH_VTR_EL2_PRIbits,
+						     kvm_vgic_global_state.ich_vtr_el2) + 1;
 
 	/* Get the show on the road... */
-	vgic_v3->vgic_hcr = ICH_HCR_EN;
+	vgic_v3->vgic_hcr = ICH_HCR_EL2_En;
 }
 
 void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
@@ -301,18 +299,19 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
 
 	/* Hide GICv3 sysreg if necessary */
 	if (!kvm_has_gicv3(vcpu->kvm)) {
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL0 | ICH_HCR_TALL1 | ICH_HCR_TC;
+		vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 |
+				      ICH_HCR_EL2_TC);
 		return;
 	}
 
 	if (group0_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL0;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL0;
 	if (group1_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TALL1;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL1;
 	if (common_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TC;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TC;
 	if (dir_trap)
-		vgic_v3->vgic_hcr |= ICH_HCR_TDIR;
+		vgic_v3->vgic_hcr |= ICH_HCR_EL2_TDIR;
 }
 
 int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
@@ -632,8 +631,8 @@ static const struct midr_range broken_seis[] = {
 
 static bool vgic_v3_broken_seis(void)
 {
-	return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) &&
-		is_midr_in_range_list(read_cpuid_id(), broken_seis));
+	return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_SEIS) &&
+		is_midr_in_range_list(broken_seis));
 }
 
 /**
@@ -706,10 +705,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (vgic_v3_broken_seis()) {
 		kvm_info("GICv3 with broken locally generated SEI\n");
 
-		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK;
+		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_EL2_SEIS;
 		group0_trap = true;
 		group1_trap = true;
-		if (ich_vtr_el2 & ICH_VTR_TDS_MASK)
+		if (ich_vtr_el2 & ICH_VTR_EL2_TDS)
 			dir_trap = true;
 		else
 			common_trap = true;
@@ -735,6 +734,12 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	/* If the vgic is nested, perform the full state loading */
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_load_nested(vcpu);
+		return;
+	}
+
 	if (likely(!is_protected_kvm_enabled()))
 		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
 
@@ -748,6 +753,11 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_put_nested(vcpu);
+		return;
+	}
+
 	if (likely(!is_protected_kvm_enabled()))
 		kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
 	WARN_ON(vgic_v4_put(vcpu));
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index eedecbbbcf31..c7de6154627c 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -336,6 +336,22 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
+static inline bool vgic_v4_want_doorbell(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_get_flag(vcpu, IN_WFI))
+		return true;
+
+	if (likely(!vcpu_has_nv(vcpu)))
+		return false;
+
+	/*
+	 * GICv4 hardware is only ever used for the L1. Mark the vPE (i.e. the
+	 * L1 context) nonresident and request a doorbell to kick us out of the
+	 * L2 when an IRQ becomes pending.
+	 */
+	return vcpu_get_flag(vcpu, IN_NESTED_ERET);
+}
+
 int vgic_v4_put(struct kvm_vcpu *vcpu)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
@@ -343,7 +359,7 @@ int vgic_v4_put(struct kvm_vcpu *vcpu)
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI));
+	return its_make_vpe_non_resident(vpe, vgic_v4_want_doorbell(vcpu));
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -415,7 +431,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 	struct vgic_irq *irq;
 	struct its_vlpi_map map;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	if (!vgic_supports_direct_msis(kvm))
 		return 0;
@@ -430,10 +446,15 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 
 	mutex_lock(&its->its_lock);
 
-	/* Perform the actual DevID/EventID -> LPI translation. */
-	ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
-				   irq_entry->msi.data, &irq);
-	if (ret)
+	/*
+	 * Perform the actual DevID/EventID -> LPI translation.
+	 *
+	 * Silently exit if translation fails as the guest (or userspace!) has
+	 * managed to do something stupid. Emulated LPI injection will still
+	 * work if the guest figures itself out at a later time.
+	 */
+	if (vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
+				 irq_entry->msi.data, &irq))
 		goto out;
 
 	/* Silently exit if the vLPI is already mapped */
@@ -512,7 +533,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 	if (ret)
 		goto out;
 
-	WARN_ON(!(irq->hw && irq->host_irq == virq));
+	WARN_ON(irq->hw && irq->host_irq != virq);
 	if (irq->hw) {
 		atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
 		irq->hw = false;
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index cc8c6b9b5dd8..8f8096d48925 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -872,6 +872,15 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	int used_lrs;
 
+	/* If nesting, emulate the HW effect from L0 to L1 */
+	if (vgic_state_is_nested(vcpu)) {
+		vgic_v3_sync_nested(vcpu);
+		return;
+	}
+
+	if (vcpu_has_nv(vcpu))
+		vgic_v3_nested_update_mi(vcpu);
+
 	/* An empty ap_list_head implies used_lrs == 0 */
 	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
 		return;
@@ -901,6 +910,35 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu)
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 {
 	/*
+	 * If in a nested state, we must return early. Two possibilities:
+	 *
+	 * - If we have any pending IRQ for the guest and the guest
+	 *   expects IRQs to be handled in its virtual EL2 mode (the
+	 *   virtual IMO bit is set) and it is not already running in
+	 *   virtual EL2 mode, then we have to emulate an IRQ
+	 *   exception to virtual EL2.
+	 *
+	 *   We do that by placing a request to ourselves which will
+	 *   abort the entry procedure and inject the exception at the
+	 *   beginning of the run loop.
+	 *
+	 * - Otherwise, do exactly *NOTHING*. The guest state is
+	 *   already loaded, and we can carry on with running it.
+	 *
+	 * If we have NV, but are not in a nested state, compute the
+	 * maintenance interrupt state, as it may fire.
+	 */
+	if (vgic_state_is_nested(vcpu)) {
+		if (kvm_vgic_vcpu_pending_irq(vcpu))
+			kvm_make_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu);
+
+		return;
+	}
+
+	if (vcpu_has_nv(vcpu))
+		vgic_v3_nested_update_mi(vcpu);
+
+	/*
 	 * If there are no virtual interrupts active or pending for this
 	 * VCPU, then there is no work to do and we can bail out without
 	 * taking any lock.  There is a potential race with someone injecting
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 122d95b4e284..0c5a63712702 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -353,4 +353,10 @@ static inline bool kvm_has_gicv3(struct kvm *kvm)
 	return kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP);
 }
 
+void vgic_v3_sync_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_load_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_put_nested(struct kvm_vcpu *vcpu);
+void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu);
+void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 806223b7022a..7fe8ba1a2851 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 4d49dff721a8..027bfa9689c6 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,4 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+
+obj-y += crypto/
+
 lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_page.o				\
 		   clear_page.o csum.o insn.o memchr.o memcpy.o		\
@@ -14,10 +17,10 @@ endif
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-arm64.o
-crc32-arm64-y := crc32.o crc32-glue.o
+crc32-arm64-y := crc32.o crc32-core.o
 
 obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm64.o
-crc-t10dif-arm64-y := crc-t10dif-glue.o crc-t10dif-core.o
+crc-t10dif-arm64-y := crc-t10dif.o crc-t10dif-core.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index a5a5f5b97b17..de9a303b6ad0 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,14 +17,27 @@
  * Alignment fixed up by hardware.
  */
 
-	.p2align 4
-	// Alignment is for the loop, but since the prologue (including BTI)
-	// is also 16 bytes we can keep any padding outside the function
 SYM_FUNC_START(__arch_clear_user)
 	add	x2, x0, x1
+
+#ifdef CONFIG_AS_HAS_MOPS
+	.arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+
+USER(9f, setpt	[x0]!, x1!, xzr)
+USER(6f, setmt	[x0]!, x1!, xzr)
+USER(6f, setet	[x0]!, x1!, xzr)
+	mov	x0, #0
+	ret
+.Lno_mops:
+#endif
+
 	subs	x1, x1, #8
 	b.mi	2f
-1:
+
+1:	.p2align 4
 USER(9f, sttr	xzr, [x0])
 	add	x0, x0, #8
 	subs	x1, x1, #8
@@ -47,6 +60,10 @@ USER(7f, sttrb	wzr, [x2, #-1])
 	ret
 
 	// Exception fixups
+6:	b.cs	9f
+	// Registers are in Option A format
+	add	x0, x0, x1
+	b	9f
 7:	sub	x0, x2, #5	// Adjust for faulting on the final byte...
 8:	add	x0, x0, #4	// ...or the second word of the 4-7 byte case
 9:	sub	x0, x2, x0
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 34e317907524..400057d607ec 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -52,6 +52,13 @@
 	stp \reg1, \reg2, [\ptr], \val
 	.endm
 
+	.macro cpy1 dst, src, count
+	.arch_extension mops
+	USER_CPY(9997f, 0, cpyfprt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 0, cpyfmrt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 0, cpyfert [\dst]!, [\src]!, \count!)
+	.endm
+
 end	.req	x5
 srcin	.req	x15
 SYM_FUNC_START(__arch_copy_from_user)
@@ -62,6 +69,9 @@ SYM_FUNC_START(__arch_copy_from_user)
 	ret
 
 	// Exception fixups
+9996:	b.cs	9997f
+	// Registers are in Option A format
+	add	dst, dst, count
 9997:	cmp	dst, dstin
 	b.ne	9998f
 	// Before being absolutely sure we couldn't copy anything, try harder
diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
index 488df234c49a..7f2f5a0e2fb9 100644
--- a/arch/arm64/lib/copy_template.S
+++ b/arch/arm64/lib/copy_template.S
@@ -40,6 +40,16 @@ D_l	.req	x13
 D_h	.req	x14
 
 	mov	dst, dstin
+
+#ifdef CONFIG_AS_HAS_MOPS
+alternative_if_not ARM64_HAS_MOPS
+	b	.Lno_mops
+alternative_else_nop_endif
+	cpy1	dst, src, count
+	b	.Lexitfunc
+.Lno_mops:
+#endif
+
 	cmp	count, #16
 	/*When memory length is less than 16, the accessed are not aligned.*/
 	b.lo	.Ltiny15
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 802231772608..819f2e3fc7a9 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -51,6 +51,13 @@
 	user_stp 9997f, \reg1, \reg2, \ptr, \val
 	.endm
 
+	.macro cpy1 dst, src, count
+	.arch_extension mops
+	USER_CPY(9997f, 1, cpyfpwt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 1, cpyfmwt [\dst]!, [\src]!, \count!)
+	USER_CPY(9996f, 1, cpyfewt [\dst]!, [\src]!, \count!)
+	.endm
+
 end	.req	x5
 srcin	.req	x15
 SYM_FUNC_START(__arch_copy_to_user)
@@ -61,6 +68,9 @@ SYM_FUNC_START(__arch_copy_to_user)
 	ret
 
 	// Exception fixups
+9996:	b.cs	9997f
+	// Registers are in Option A format
+	add	dst, dst, count
 9997:	cmp	dst, dstin
 	b.ne	9998f
 	// Before being absolutely sure we couldn't copy anything, try harder
diff --git a/arch/arm64/lib/crc-t10dif-glue.c b/arch/arm64/lib/crc-t10dif.c
index dab7e3796232..c2ffe4fdb59d 100644
--- a/arch/arm64/lib/crc-t10dif-glue.c
+++ b/arch/arm64/lib/crc-t10dif.c
@@ -17,8 +17,8 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 
-static DEFINE_STATIC_KEY_FALSE(have_asimd);
-static DEFINE_STATIC_KEY_FALSE(have_pmull);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_asimd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
 
 #define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
 
@@ -45,9 +45,7 @@ u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
 			crc_t10dif_pmull_p8(crc, data, length, buf);
 			kernel_neon_end();
 
-			crc = 0;
-			data = buf;
-			length = sizeof(buf);
+			return crc_t10dif_generic(0, buf, sizeof(buf));
 		}
 	}
 	return crc_t10dif_generic(crc, data, length);
@@ -63,19 +61,13 @@ static int __init crc_t10dif_arm64_init(void)
 	}
 	return 0;
 }
-arch_initcall(crc_t10dif_arm64_init);
+subsys_initcall(crc_t10dif_arm64_init);
 
 static void __exit crc_t10dif_arm64_exit(void)
 {
 }
 module_exit(crc_t10dif_arm64_exit);
 
-bool crc_t10dif_is_optimized(void)
-{
-	return static_key_enabled(&have_asimd);
-}
-EXPORT_SYMBOL(crc_t10dif_is_optimized);
-
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_DESCRIPTION("CRC-T10DIF using arm64 NEON and Crypto Extensions");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32-core.S
index 68825317460f..68825317460f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32-core.S
diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32.c
index 15c4c9db573e..ed3acd71178f 100644
--- a/arch/arm64/lib/crc32-glue.c
+++ b/arch/arm64/lib/crc32.c
@@ -22,7 +22,7 @@ asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
 asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
 asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len);
 
-u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
 		return crc32_le_base(crc, p, len);
@@ -43,10 +43,10 @@ u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
-u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
-		return crc32c_le_base(crc, p, len);
+		return crc32c_base(crc, p, len);
 
 	if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
 		kernel_neon_begin();
@@ -62,9 +62,9 @@ u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 
 	return crc32c_le_arm64(crc, p, len);
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
-u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
 		return crc32_be_base(crc, p, len);
diff --git a/arch/arm64/lib/crypto/.gitignore b/arch/arm64/lib/crypto/.gitignore
new file mode 100644
index 000000000000..12d74d8b03d0
--- /dev/null
+++ b/arch/arm64/lib/crypto/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+poly1305-core.S
+sha256-core.S
diff --git a/arch/arm64/lib/crypto/Kconfig b/arch/arm64/lib/crypto/Kconfig
new file mode 100644
index 000000000000..129a7685cb4c
--- /dev/null
+++ b/arch/arm64/lib/crypto/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA20_NEON
+	tristate
+	depends on KERNEL_MODE_NEON
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_NEON
+	tristate
+	depends on KERNEL_MODE_NEON
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+config CRYPTO_SHA256_ARM64
+	tristate
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD
diff --git a/arch/arm64/lib/crypto/Makefile b/arch/arm64/lib/crypto/Makefile
new file mode 100644
index 000000000000..946c09903711
--- /dev/null
+++ b/arch/arm64/lib/crypto/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
+poly1305-neon-y := poly1305-core.o poly1305-glue.o
+AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_block_init_arch
+AFLAGS_poly1305-core.o += -Dpoly1305_emit=poly1305_emit_arch
+
+obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
+sha256-arm64-y := sha256.o sha256-core.o
+sha256-arm64-$(CONFIG_KERNEL_MODE_NEON) += sha256-ce.o
+
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $(<) void $(@)
+
+$(obj)/%-core.S: $(src)/%-armv8.pl
+	$(call cmd,perlasm)
+
+$(obj)/sha256-core.S: $(src)/sha2-armv8.pl
+	$(call cmd,perlasm)
+
+clean-files += poly1305-core.S sha256-core.S
diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/lib/crypto/chacha-neon-core.S
index b70ac76f2610..80079586ecc7 100644
--- a/arch/arm64/crypto/chacha-neon-core.S
+++ b/arch/arm64/lib/crypto/chacha-neon-core.S
@@ -1,5 +1,5 @@
 /*
- * ChaCha/XChaCha NEON helper functions
+ * ChaCha/HChaCha NEON helper functions
  *
  * Copyright (C) 2016-2018 Linaro, Ltd. <ard.biesheuvel@linaro.org>
  *
diff --git a/arch/arm64/lib/crypto/chacha-neon-glue.c b/arch/arm64/lib/crypto/chacha-neon-glue.c
new file mode 100644
index 000000000000..d0188f974ca5
--- /dev/null
+++ b/arch/arm64/lib/crypto/chacha-neon-glue.c
@@ -0,0 +1,119 @@
+/*
+ * ChaCha and HChaCha functions (ARM64 optimized)
+ *
+ * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
+				      u8 *dst, const u8 *src, int nrounds);
+asmlinkage void chacha_4block_xor_neon(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       int nrounds, int bytes);
+asmlinkage void hchacha_block_neon(const struct chacha_state *state,
+				   u32 out[HCHACHA_OUT_WORDS], int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+static void chacha_doneon(struct chacha_state *state, u8 *dst, const u8 *src,
+			  int bytes, int nrounds)
+{
+	while (bytes > 0) {
+		int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
+
+		if (l <= CHACHA_BLOCK_SIZE) {
+			u8 buf[CHACHA_BLOCK_SIZE];
+
+			memcpy(buf, src, l);
+			chacha_block_xor_neon(state, buf, buf, nrounds);
+			memcpy(dst, buf, l);
+			state->x[12] += 1;
+			break;
+		}
+		chacha_4block_xor_neon(state, dst, src, nrounds, l);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
+	}
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, out, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, out, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_neon);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_simd_mod_init(void)
+{
+	if (cpu_have_named_feature(ASIMD))
+		static_branch_enable(&have_neon);
+	return 0;
+}
+subsys_initcall(chacha_simd_mod_init);
+
+static void __exit chacha_simd_mod_exit(void)
+{
+}
+module_exit(chacha_simd_mod_exit);
+
+MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM64 optimized)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/lib/crypto/poly1305-armv8.pl
index 22c9069c0650..22c9069c0650 100644
--- a/arch/arm64/crypto/poly1305-armv8.pl
+++ b/arch/arm64/lib/crypto/poly1305-armv8.pl
diff --git a/arch/arm64/lib/crypto/poly1305-glue.c b/arch/arm64/lib/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..6a661cf04821
--- /dev/null
+++ b/arch/arm64/lib/crypto/poly1305-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_block_init_arch(
+	struct poly1305_block_state *state,
+	const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks(struct poly1305_block_state *state,
+				const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
+				     const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
+				   u8 digest[POLY1305_DIGEST_SIZE],
+				   const u32 nonce[4]);
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
+			  unsigned int len, u32 padbit)
+{
+	len = round_down(len, POLY1305_BLOCK_SIZE);
+	if (static_branch_likely(&have_neon)) {
+		do {
+			unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+			kernel_neon_begin();
+			poly1305_blocks_neon(state, src, todo, 1);
+			kernel_neon_end();
+
+			len -= todo;
+			src += todo;
+		} while (len);
+	} else
+		poly1305_blocks(state, src, len, 1);
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	/* We always can use at least the ARM64 scalar implementation. */
+	return true;
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init neon_poly1305_mod_init(void)
+{
+	if (cpu_have_named_feature(ASIMD))
+		static_branch_enable(&have_neon);
+	return 0;
+}
+subsys_initcall(neon_poly1305_mod_init);
+
+static void __exit neon_poly1305_mod_exit(void)
+{
+}
+module_exit(neon_poly1305_mod_exit);
+
+MODULE_DESCRIPTION("Poly1305 authenticator (ARM64 optimized)");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/lib/crypto/sha2-armv8.pl
index 35ec9ae99fe1..4aebd20c498b 100644
--- a/arch/arm64/crypto/sha512-armv8.pl
+++ b/arch/arm64/lib/crypto/sha2-armv8.pl
@@ -95,7 +95,7 @@ if ($output =~ /512/) {
 	$reg_t="w";
 }
 
-$func="sha${BITS}_block_data_order";
+$func="sha${BITS}_blocks_arch";
 
 ($ctx,$inp,$num,$Ktbl)=map("x$_",(0..2,30));
 
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/lib/crypto/sha256-ce.S
index fce84d88ddb2..f3e21c6d87d2 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/lib/crypto/sha256-ce.S
@@ -71,8 +71,8 @@
 	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
 
 	/*
-	 * int __sha256_ce_transform(struct sha256_ce_state *sst, u8 const *src,
-	 *			     int blocks)
+	 * size_t __sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+	 *				const u8 *data, size_t nblocks);
 	 */
 	.text
 SYM_FUNC_START(__sha256_ce_transform)
@@ -86,20 +86,16 @@ SYM_FUNC_START(__sha256_ce_transform)
 	/* load state */
 	ld1		{dgav.4s, dgbv.4s}, [x0]
 
-	/* load sha256_ce_state::finalize */
-	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
-
 	/* load input */
 0:	ld1		{v16.4s-v19.4s}, [x1], #64
-	sub		w2, w2, #1
+	sub		x2, x2, #1
 
 CPU_LE(	rev32		v16.16b, v16.16b	)
 CPU_LE(	rev32		v17.16b, v17.16b	)
 CPU_LE(	rev32		v18.16b, v18.16b	)
 CPU_LE(	rev32		v19.16b, v19.16b	)
 
-1:	add		t0.4s, v16.4s, v0.4s
+	add		t0.4s, v16.4s, v0.4s
 	mov		dg0v.16b, dgav.16b
 	mov		dg1v.16b, dgbv.16b
 
@@ -127,31 +123,14 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	add		dgav.4s, dgav.4s, dg0v.4s
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
-	/* handled all input blocks? */
-	cbz		w2, 2f
-	cond_yield	3f, x5, x6
-	b		0b
+	/* return early if voluntary preemption is needed */
+	cond_yield	1f, x5, x6
 
-	/*
-	 * Final block: add padding and total bit count.
-	 * Skip if the input size was not a round multiple of the block size,
-	 * the padding is handled by the C code in that case.
-	 */
-2:	cbz		x4, 3f
-	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
-	movi		v17.2d, #0
-	mov		x8, #0x80000000
-	movi		v18.2d, #0
-	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
-	fmov		d16, x8
-	mov		x4, #0
-	mov		v19.d[0], xzr
-	mov		v19.d[1], x7
-	b		1b
+	/* handled all input blocks? */
+	cbnz		x2, 0b
 
 	/* store new state */
-3:	st1		{dgav.4s, dgbv.4s}, [x0]
-	mov		w0, w2
+1:	st1		{dgav.4s, dgbv.4s}, [x0]
+	mov		x0, x2
 	ret
 SYM_FUNC_END(__sha256_ce_transform)
diff --git a/arch/arm64/lib/crypto/sha256.c b/arch/arm64/lib/crypto/sha256.c
new file mode 100644
index 000000000000..bcf7a3adc0c4
--- /dev/null
+++ b/arch/arm64/lib/crypto/sha256.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized for ARM64
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/neon.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+				   const u8 *data, size_t nblocks);
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+asmlinkage void sha256_block_neon(u32 state[SHA256_STATE_WORDS],
+				  const u8 *data, size_t nblocks);
+asmlinkage size_t __sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+					const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon)) {
+		if (static_branch_likely(&have_ce)) {
+			do {
+				size_t rem;
+
+				kernel_neon_begin();
+				rem = __sha256_ce_transform(state,
+							    data, nblocks);
+				kernel_neon_end();
+				data += (nblocks - rem) * SHA256_BLOCK_SIZE;
+				nblocks = rem;
+			} while (nblocks);
+		} else {
+			kernel_neon_begin();
+			sha256_block_neon(state, data, nblocks);
+			kernel_neon_end();
+		}
+	} else {
+		sha256_blocks_arch(state, data, nblocks);
+	}
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+bool sha256_is_arch_optimized(void)
+{
+	/* We always can use at least the ARM64 scalar implementation. */
+	return true;
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_arm64_mod_init(void)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    cpu_have_named_feature(ASIMD)) {
+		static_branch_enable(&have_neon);
+		if (cpu_have_named_feature(SHA2))
+			static_branch_enable(&have_ce);
+	}
+	return 0;
+}
+subsys_initcall(sha256_arm64_mod_init);
+
+static void __exit sha256_arm64_mod_exit(void)
+{
+}
+module_exit(sha256_arm64_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 optimized for ARM64");
diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c
index b008a9b46a7f..4e298baddc2e 100644
--- a/arch/arm64/lib/insn.c
+++ b/arch/arm64/lib/insn.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
  */
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
 #include <linux/printk.h>
@@ -540,6 +541,35 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 					     offset >> shift);
 }
 
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_ACQ:
+		insn = aarch64_insn_get_load_acq_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REL:
+		insn = aarch64_insn_get_store_rel_value();
+		break;
+	default:
+		pr_err("%s: unknown load-acquire/store-release encoding %d\n",
+		       __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+}
+
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,
@@ -1471,43 +1501,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
 	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm);
 }
 
-u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
+static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type)
 {
-	u32 opt;
-	u32 insn;
-
 	switch (type) {
 	case AARCH64_INSN_MB_SY:
-		opt = 0xf;
-		break;
+		return 0xf;
 	case AARCH64_INSN_MB_ST:
-		opt = 0xe;
-		break;
+		return 0xe;
 	case AARCH64_INSN_MB_LD:
-		opt = 0xd;
-		break;
+		return 0xd;
 	case AARCH64_INSN_MB_ISH:
-		opt = 0xb;
-		break;
+		return 0xb;
 	case AARCH64_INSN_MB_ISHST:
-		opt = 0xa;
-		break;
+		return 0xa;
 	case AARCH64_INSN_MB_ISHLD:
-		opt = 0x9;
-		break;
+		return 0x9;
 	case AARCH64_INSN_MB_NSH:
-		opt = 0x7;
-		break;
+		return 0x7;
 	case AARCH64_INSN_MB_NSHST:
-		opt = 0x6;
-		break;
+		return 0x6;
 	case AARCH64_INSN_MB_NSHLD:
-		opt = 0x5;
-		break;
+		return 0x5;
 	default:
-		pr_err("%s: unknown dmb type %d\n", __func__, type);
+		pr_err("%s: unknown barrier type %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
+}
+
+u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
+{
+	u32 opt;
+	u32 insn;
+
+	opt = __get_barrier_crm_val(type);
+	if (opt == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
 
 	insn = aarch64_insn_get_dmb_value();
 	insn &= ~GENMASK(11, 8);
@@ -1516,6 +1544,21 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
 	return insn;
 }
 
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type)
+{
+	u32 opt, insn;
+
+	opt = __get_barrier_crm_val(type);
+	if (opt == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
+	insn = aarch64_insn_get_dsb_base_value();
+	insn &= ~GENMASK(11, 8);
+	insn |= (opt << 8);
+
+	return insn;
+}
+
 u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
 			 enum aarch64_insn_system_register sysreg)
 {
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index fc92170a8f37..c26489cf96cd 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -5,7 +5,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o fixmap.o
 obj-$(CONFIG_ARM64_CONTPTE)	+= contpte.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_PTDUMP_CORE)	+= ptdump.o
+obj-$(CONFIG_PTDUMP)		+= ptdump.o
 obj-$(CONFIG_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd.o
 obj-$(CONFIG_TRANS_TABLE)	+= trans_pgd-asm.o
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 55107d27d3f8..bcac4f55f9c1 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -335,7 +335,7 @@ int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
 		 * eliding the trailing DSB applies here.
 		 */
 		addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
-		__flush_tlb_range_nosync(vma, addr, addr + CONT_PTE_SIZE,
+		__flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
 					 PAGE_SIZE, true, 3);
 	}
 
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 228d681a8715..6e0528831cd3 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -8,8 +8,33 @@
 #include <linux/uaccess.h>
 
 #include <asm/asm-extable.h>
+#include <asm/esr.h>
 #include <asm/ptrace.h>
 
+static bool cpy_faulted_on_uaccess(const struct exception_table_entry *ex,
+				   unsigned long esr)
+{
+	bool uaccess_is_write = FIELD_GET(EX_DATA_UACCESS_WRITE, ex->data);
+	bool fault_on_write = esr & ESR_ELx_WNR;
+
+	return uaccess_is_write == fault_on_write;
+}
+
+bool insn_may_access_user(unsigned long addr, unsigned long esr)
+{
+	const struct exception_table_entry *ex = search_exception_tables(addr);
+
+	if (!ex)
+		return false;
+
+	switch (ex->type) {
+	case EX_TYPE_UACCESS_CPY:
+		return cpy_faulted_on_uaccess(ex, esr);
+	default:
+		return true;
+	}
+}
+
 static inline unsigned long
 get_ex_fixup(const struct exception_table_entry *ex)
 {
@@ -29,6 +54,17 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
 	return true;
 }
 
+static bool ex_handler_uaccess_cpy(const struct exception_table_entry *ex,
+				   struct pt_regs *regs, unsigned long esr)
+{
+	/* Do not fix up faults on kernel memory accesses */
+	if (!cpy_faulted_on_uaccess(ex, esr))
+		return false;
+
+	regs->pc = get_ex_fixup(ex);
+	return true;
+}
+
 static bool
 ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
 				  struct pt_regs *regs)
@@ -56,7 +92,7 @@ ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
 	return true;
 }
 
-bool fixup_exception(struct pt_regs *regs)
+bool fixup_exception(struct pt_regs *regs, unsigned long esr)
 {
 	const struct exception_table_entry *ex;
 
@@ -70,6 +106,8 @@ bool fixup_exception(struct pt_regs *regs)
 	case EX_TYPE_UACCESS_ERR_ZERO:
 	case EX_TYPE_KACCESS_ERR_ZERO:
 		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_UACCESS_CPY:
+		return ex_handler_uaccess_cpy(ex, regs, esr);
 	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
 		return ex_handler_load_unaligned_zeropad(ex, regs);
 	}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index ef63651099a9..ec0a337891dd 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -375,7 +375,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 	 * Are we prepared to handle this kernel fault?
 	 * We are almost certainly not prepared to handle instruction faults.
 	 */
-	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
+	if (!is_el1_instruction_abort(esr) && fixup_exception(regs, esr))
 		return;
 
 	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
@@ -606,7 +606,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 			die_kernel_fault("execution of user memory",
 					 addr, esr, regs);
 
-		if (!search_exception_tables(regs->pc))
+		if (!insn_may_access_user(regs->pc, esr))
 			die_kernel_fault("access to user memory outside uaccess routines",
 					 addr, esr, regs);
 	}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e25..cfe8cb8ba1cc 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -342,7 +334,9 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 	switch (hp_size) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		return PGDIR_SIZE - PUD_SIZE;
+		if (pud_sect_supported())
+			return PGDIR_SIZE - PUD_SIZE;
+		break;
 #endif
 	case CONT_PMD_SIZE:
 		return PUD_SIZE - CONT_PMD_SIZE;
@@ -364,23 +358,21 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	switch (pagesize) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		entry = pud_pte(pud_mkhuge(pte_pud(entry)));
+		if (pud_sect_supported())
+			return pud_pte(pud_mkhuge(pte_pud(entry)));
 		break;
 #endif
 	case CONT_PMD_SIZE:
-		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
-		fallthrough;
+		return pmd_pte(pmd_mkhuge(pmd_mkcont(pte_pmd(entry))));
 	case PMD_SIZE:
-		entry = pmd_pte(pmd_mkhuge(pte_pmd(entry)));
-		break;
+		return pmd_pte(pmd_mkhuge(pte_pmd(entry)));
 	case CONT_PTE_SIZE:
-		entry = pte_mkcont(entry);
-		break;
+		return pte_mkcont(entry);
 	default:
-		pr_warn("%s: unrecognized huge page size 0x%lx\n",
-			__func__, pagesize);
 		break;
 	}
+	pr_warn("%s: unrecognized huge page size 0x%lx\n",
+		__func__, pagesize);
 	return entry;
 }
 
@@ -396,18 +388,13 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 
@@ -549,6 +536,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +547,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc..b99bf3980fc6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -98,21 +98,19 @@ static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
@@ -279,12 +277,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
@@ -314,8 +307,6 @@ void __init arm64_memblock_init(void)
 	}
 
 	early_init_fdt_scan_reserved_mem();
-
-	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
 void __init bootmem_init(void)
@@ -364,12 +355,7 @@ void __init bootmem_init(void)
 	memblock_dump_all();
 }
 
-/*
- * mem_init() marks the free areas in the mem_map and tells us how much memory
- * is free.  This is done after various parts of the system have claimed their
- * memory after the kernel image.
- */
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	unsigned int flags = SWIOTLB_VERBOSE;
 	bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
@@ -393,9 +379,6 @@ void __init mem_init(void)
 	swiotlb_init(swiotlb, flags);
 	swiotlb_update_mem_attributes();
 
-	/* this will put all unused low memory onto the freelists */
-	memblock_free_all();
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can be
 	 * detected at build time already.
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 6cc0b7e7eb03..10e246f11271 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -15,10 +15,9 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook)
 }
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot)
+			   pgprot_t pgprot)
 {
 	unsigned long last_addr = phys_addr + size - 1;
-	pgprot_t pgprot = __pgprot(prot);
 
 	/* Don't allow outside PHYS_MASK */
 	if (last_addr & ~PHYS_MASK)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index b65a29440a0c..d541ce45daeb 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -190,7 +190,7 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
  */
 static bool __init root_level_aligned(u64 addr)
 {
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * PTDESC_TABLE_SHIFT;
 
 	return (addr % (PAGE_SIZE << shift)) == 0;
 }
@@ -245,7 +245,7 @@ static int __init root_level_idx(u64 addr)
 	 */
 	u64 vabits = IS_ENABLED(CONFIG_ARM64_64K_PAGES) ? VA_BITS
 							: vabits_actual;
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * PTDESC_TABLE_SHIFT;
 
 	return (addr & ~_PAGE_OFFSET(vabits)) >> (shift + PAGE_SHIFT);
 }
@@ -269,7 +269,7 @@ static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud)
  */
 static int __init next_level_idx(u64 addr)
 {
-	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * (PAGE_SHIFT - 3);
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * PTDESC_TABLE_SHIFT;
 
 	return (addr >> (shift + PAGE_SHIFT)) % PTRS_PER_PTE;
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b4df5bc5b1b8..ea6695d53fb9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1177,8 +1177,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+	/* [start, end] should be within one section */
+	WARN_ON_ONCE(end - start > PAGES_PER_SECTION * sizeof(struct page));
 
-	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) ||
+	    (end - start < PAGES_PER_SECTION * sizeof(struct page)))
 		return vmemmap_populate_basepages(start, end, node, altmap);
 	else
 		return vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1358,7 +1361,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		__remove_pgd_mapping(swapper_pg_dir,
 				     __phys_to_virt(start), size);
 	else {
-		max_pfn = PFN_UP(start + size);
+		/* Address of hotplugged memory can be smaller */
+		max_pfn = max(max_pfn, PFN_UP(start + size));
 		max_low_pfn = max_pfn;
 	}
 
@@ -1555,9 +1559,8 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp)
 #ifdef CONFIG_ARCH_HAS_PKEYS
 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
 {
-	u64 new_por = POE_RXW;
+	u64 new_por;
 	u64 old_por;
-	u64 pkey_shift;
 
 	if (!system_supports_poe())
 		return -ENOSPC;
@@ -1571,7 +1574,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i
 		return -EINVAL;
 
 	/* Set the bits we need in POR:  */
-	new_por = POE_RXW;
+	new_por = POE_RWX;
 	if (init_val & PKEY_DISABLE_WRITE)
 		new_por &= ~POE_W;
 	if (init_val & PKEY_DISABLE_ACCESS)
@@ -1582,12 +1585,11 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long i
 		new_por &= ~POE_X;
 
 	/* Shift the bits in to the correct place in POR for pkey: */
-	pkey_shift = pkey * POR_BITS_PER_PKEY;
-	new_por <<= pkey_shift;
+	new_por = POR_ELx_PERM_PREP(pkey, new_por);
 
 	/* Get old POR and mask off any old bits in place: */
 	old_por = read_sysreg_s(SYS_POR_EL0);
-	old_por &= ~(POE_MASK << pkey_shift);
+	old_por &= ~(POE_MASK << POR_ELx_PERM_SHIFT(pkey));
 
 	/* Write old part along with new part: */
 	write_sysreg_s(old_por | new_por, SYS_POR_EL0);
diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c
index cde44c13dda1..7d94e09b01b3 100644
--- a/arch/arm64/mm/physaddr.c
+++ b/arch/arm64/mm/physaddr.c
@@ -10,7 +10,7 @@
 phys_addr_t __virt_to_phys(unsigned long x)
 {
 	WARN(!__is_lm_address(__tag_reset(x)),
-	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     "virt_to_phys used for non-linear address: %p (%pS)\n",
 	      (void *)x,
 	      (void *)x);
 
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 688fbe0271ca..8cec0da4cff2 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -80,8 +80,8 @@ static const struct ptdump_prot_bits pte_bits[] = {
 		.set	= "CON",
 		.clear	= "   ",
 	}, {
-		.mask	= PTE_TABLE_BIT | PTE_VALID,
-		.val	= PTE_VALID,
+		.mask	= PMD_TYPE_MASK,
+		.val	= PMD_TYPE_SECT,
 		.set	= "BLK",
 		.clear	= "   ",
 	}, {
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index b22ab2f97a30..a3b0e693a125 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -119,6 +119,26 @@
 	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
 				       AARCH64_INSN_LDST_STORE_REL_EX)
 
+/* Load-acquire & store-release */
+#define A64_LDAR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_LOAD_ACQ)
+#define A64_STLR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_STORE_REL)
+
+/* Rt = [Rn] (load acquire) */
+#define A64_LDARB(Wt, Xn)	A64_LDAR(Wt, Xn, 8)
+#define A64_LDARH(Wt, Xn)	A64_LDAR(Wt, Xn, 16)
+#define A64_LDAR32(Wt, Xn)	A64_LDAR(Wt, Xn, 32)
+#define A64_LDAR64(Xt, Xn)	A64_LDAR(Xt, Xn, 64)
+
+/* [Rn] = Rt (store release) */
+#define A64_STLRB(Wt, Xn)	A64_STLR(Wt, Xn, 8)
+#define A64_STLRH(Wt, Xn)	A64_STLR(Wt, Xn, 16)
+#define A64_STLR32(Wt, Xn)	A64_STLR(Wt, Xn, 32)
+#define A64_STLR64(Xt, Xn)	A64_STLR(Xt, Xn, 64)
+
 /*
  * LSE atomics
  *
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 8446848edddb..634d78422adb 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -7,6 +7,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/arm-smccc.h>
 #include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
@@ -17,6 +18,7 @@
 #include <asm/asm-extable.h>
 #include <asm/byteorder.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
 #include <asm/text-patching.h>
@@ -272,7 +274,7 @@ static inline void emit_a64_add_i(const bool is64, const int dst, const int src,
 {
 	if (is_addsub_imm(imm)) {
 		emit(A64_ADD_I(is64, dst, src, imm), ctx);
-	} else if (is_addsub_imm(-imm)) {
+	} else if (is_addsub_imm(-(u32)imm)) {
 		emit(A64_SUB_I(is64, dst, src, -imm), ctx);
 	} else {
 		emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -647,6 +649,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	return 0;
 }
 
+static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const s32 imm = insn->imm;
+	const s16 off = insn->off;
+	const u8 code = insn->code;
+	const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
+	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+	const u8 dst = bpf2a64[insn->dst_reg];
+	const u8 src = bpf2a64[insn->src_reg];
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	u8 reg;
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		reg = src;
+		break;
+	case BPF_STORE_REL:
+		reg = dst;
+		break;
+	default:
+		pr_err_once("unknown atomic load/store op code %02x\n", imm);
+		return -EINVAL;
+	}
+
+	if (off) {
+		emit_a64_add_i(1, tmp, reg, tmp, off, ctx);
+		reg = tmp;
+	}
+	if (arena) {
+		emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+		reg = tmp;
+	}
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_LDARB(dst, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_LDARH(dst, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_LDAR32(dst, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_LDAR64(dst, reg), ctx);
+			break;
+		}
+		break;
+	case BPF_STORE_REL:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_STLRB(src, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STLRH(src, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_STLR32(src, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STLR64(src, reg), ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("unexpected atomic load/store op code %02x\n",
+			    imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_ARM64_LSE_ATOMICS
 static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
@@ -864,7 +941,51 @@ static void build_plt(struct jit_ctx *ctx)
 		plt->target = (u64)&dummy_tramp;
 }
 
-static void build_epilogue(struct jit_ctx *ctx)
+/* Clobbers BPF registers 1-4, aka x0-x3 */
+static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx)
+{
+	const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */
+	u8 k = get_spectre_bhb_loop_value();
+
+	if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) ||
+	    cpu_mitigations_off() || __nospectre_bhb ||
+	    arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE)
+		return;
+
+	if (capable(CAP_SYS_ADMIN))
+		return;
+
+	if (supports_clearbhb(SCOPE_SYSTEM)) {
+		emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx);
+		return;
+	}
+
+	if (k) {
+		emit_a64_mov_i64(r1, k, ctx);
+		emit(A64_B(1), ctx);
+		emit(A64_SUBS_I(true, r1, r1, 1), ctx);
+		emit(A64_B_(A64_COND_NE, -2), ctx);
+		emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx);
+		emit(aarch64_insn_get_isb_value(), ctx);
+	}
+
+	if (is_spectre_bhb_fw_mitigated()) {
+		emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR,
+			       ARM_SMCCC_ARCH_WORKAROUND_3), ctx);
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
+			emit(aarch64_insn_get_hvc_value(), ctx);
+			break;
+		case SMCCC_CONDUIT_SMC:
+			emit(aarch64_insn_get_smc_value(), ctx);
+			break;
+		default:
+			pr_err_once("Firmware mitigation enabled with unknown conduit\n");
+		}
+	}
+}
+
+static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
 {
 	const u8 r0 = bpf2a64[BPF_REG_0];
 	const u8 ptr = bpf2a64[TCCNT_PTR];
@@ -877,10 +998,13 @@ static void build_epilogue(struct jit_ctx *ctx)
 
 	emit(A64_POP(A64_ZR, ptr, A64_SP), ctx);
 
+	if (was_classic)
+		build_bhb_mitigation(ctx);
+
 	/* Restore FP/LR registers */
 	emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
-	/* Set return value */
+	/* Move the return value from bpf:r0 (aka x7) to x0 */
 	emit(A64_MOV(1, A64_R(0), r0), ctx);
 
 	/* Authenticate lr */
@@ -1159,7 +1283,7 @@ emit_bswap_uxt:
 	case BPF_ALU64 | BPF_SUB | BPF_K:
 		if (is_addsub_imm(imm)) {
 			emit(A64_SUB_I(is64, dst, dst, imm), ctx);
-		} else if (is_addsub_imm(-imm)) {
+		} else if (is_addsub_imm(-(u32)imm)) {
 			emit(A64_ADD_I(is64, dst, dst, -imm), ctx);
 		} else {
 			emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -1330,7 +1454,7 @@ emit_cond_jmp:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
 		if (is_addsub_imm(imm)) {
 			emit(A64_CMP_I(is64, dst, imm), ctx);
-		} else if (is_addsub_imm(-imm)) {
+		} else if (is_addsub_imm(-(u32)imm)) {
 			emit(A64_CMN_I(is64, dst, -imm), ctx);
 		} else {
 			emit_a64_mov_i(is64, tmp, imm, ctx);
@@ -1641,11 +1765,17 @@ emit_cond_jmp:
 			return ret;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
-		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(insn, ctx);
+		else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			ret = emit_lse_atomic(insn, ctx);
 		else
 			ret = emit_ll_sc_atomic(insn, ctx);
@@ -1817,7 +1947,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.epilogue_offset = ctx.idx;
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, was_classic);
 	build_plt(&ctx);
 
 	extable_align = __alignof__(struct exception_table_entry);
@@ -1880,7 +2010,7 @@ skip_init_ctx:
 		goto out_free_hdr;
 	}
 
-	build_epilogue(&ctx);
+	build_epilogue(&ctx, was_classic);
 	build_plt(&ctx);
 
 	/* Extra pass to validate JITed code. */
@@ -2669,7 +2799,8 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 	switch (insn->code) {
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (!bpf_atomic_is_load_store(insn) &&
+		    !cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			return false;
 	}
 	return true;
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 1e65f2fb45bd..772c1b008e43 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -45,6 +45,7 @@ HAS_LSE_ATOMICS
 HAS_MOPS
 HAS_NESTED_VIRT
 HAS_PAN
+HAS_PMUV3
 HAS_S1PIE
 HAS_S1POE
 HAS_RAS_EXTN
@@ -104,6 +105,7 @@ WORKAROUND_CAVIUM_TX2_219_TVM
 WORKAROUND_CLEAN_CACHE
 WORKAROUND_DEVICE_LOAD_ACQUIRE
 WORKAROUND_NVIDIA_CARMEL_CNP
+WORKAROUND_PMUV3_IMPDEF_TRAPS
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_QCOM_ORYON_CNTVOFF
 WORKAROUND_REPEAT_TLBI
diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk
index 1a2afc9fdd42..f2a1732cb1f6 100755
--- a/arch/arm64/tools/gen-sysreg.awk
+++ b/arch/arm64/tools/gen-sysreg.awk
@@ -111,7 +111,7 @@ END {
 /^$/ { next }
 /^[\t ]*#/ { next }
 
-/^SysregFields/ && block_current() == "Root" {
+$1 == "SysregFields" && block_current() == "Root" {
 	block_push("SysregFields")
 
 	expect_fields(2)
@@ -127,7 +127,8 @@ END {
 	next
 }
 
-/^EndSysregFields/ && block_current() == "SysregFields" {
+$1 == "EndSysregFields" && block_current() == "SysregFields" {
+	expect_fields(1)
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
@@ -145,7 +146,7 @@ END {
 	next
 }
 
-/^Sysreg/ && block_current() == "Root" {
+$1 == "Sysreg" && block_current() == "Root" {
 	block_push("Sysreg")
 
 	expect_fields(7)
@@ -177,7 +178,8 @@ END {
 	next
 }
 
-/^EndSysreg/ && block_current() == "Sysreg" {
+$1 == "EndSysreg" && block_current() == "Sysreg" {
+	expect_fields(1)
 	if (next_bit > 0)
 		fatal("Unspecified bits in " reg)
 
@@ -206,7 +208,7 @@ END {
 
 # Currently this is effectivey a comment, in future we may want to emit
 # defines for the fields.
-(/^Fields/ || /^Mapping/) && block_current() == "Sysreg" {
+($1 == "Fields" || $1 == "Mapping") && block_current() == "Sysreg" {
 	expect_fields(2)
 
 	if (next_bit != 63)
@@ -224,7 +226,7 @@ END {
 }
 
 
-/^Res0/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Res0" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES0", $2)
 	field = "RES0_" msb "_" lsb
@@ -234,7 +236,7 @@ END {
 	next
 }
 
-/^Res1/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Res1" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "RES1", $2)
 	field = "RES1_" msb "_" lsb
@@ -244,7 +246,7 @@ END {
 	next
 }
 
-/^Unkn/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Unkn" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, "UNKN", $2)
 	field = "UNKN_" msb "_" lsb
@@ -254,7 +256,7 @@ END {
 	next
 }
 
-/^Field/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Field" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(3)
 	field = $3
 	parse_bitdef(reg, field, $2)
@@ -265,14 +267,14 @@ END {
 	next
 }
 
-/^Raz/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Raz" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	expect_fields(2)
 	parse_bitdef(reg, field, $2)
 
 	next
 }
 
-/^SignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "SignedEnum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -285,7 +287,7 @@ END {
 	next
 }
 
-/^UnsignedEnum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "UnsignedEnum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -298,7 +300,7 @@ END {
 	next
 }
 
-/^Enum/ && (block_current() == "Sysreg" || block_current() == "SysregFields") {
+$1 == "Enum" && (block_current() == "Sysreg" || block_current() == "SysregFields") {
 	block_push("Enum")
 
 	expect_fields(3)
@@ -310,7 +312,8 @@ END {
 	next
 }
 
-/^EndEnum/ && block_current() == "Enum" {
+$1 == "EndEnum" && block_current() == "Enum" {
+	expect_fields(1)
 
 	field = null
 	msb = null
diff --git a/arch/arm64/tools/syscall_32.tbl b/arch/arm64/tools/syscall_32.tbl
index 69a829912a05..0765b3a8d6d6 100644
--- a/arch/arm64/tools/syscall_32.tbl
+++ b/arch/arm64/tools/syscall_32.tbl
@@ -478,3 +478,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 762ee084b37c..bdf044c5d11b 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1664,6 +1664,7 @@ EndEnum
 UnsignedEnum	59:56	FGT
 	0b0000	NI
 	0b0001	IMP
+	0b0010	FGT2
 EndEnum
 Res0	55:48
 UnsignedEnum	47:44	EXS
@@ -1725,6 +1726,7 @@ Enum	3:0	PARANGE
 	0b0100	44
 	0b0101	48
 	0b0110	52
+	0b0111	56
 EndEnum
 EndSysreg
 
@@ -2074,7 +2076,7 @@ EndEnum
 Res0	4:2
 Field	1	ExTRE
 Field	0	E0TRE
-EndSysregFields
+EndSysreg
 
 Sysreg	SMPRI_EL1	3	0	1	2	4
 Res0	63:4
@@ -2641,6 +2643,101 @@ Field	0	E0HTRE
 EndSysreg
 
 
+Sysreg HDFGRTR2_EL2	3	4	3	1	0
+Res0	63:25
+Field	24	nPMBMAR_EL1
+Field	23	nMDSTEPOP_EL1
+Field	22	nTRBMPAM_EL1
+Res0	21
+Field	20	nTRCITECR_EL1
+Field	19	nPMSDSFR_EL1
+Field	18	nSPMDEVAFF_EL1
+Field	17	nSPMID
+Field	16	nSPMSCR_EL1
+Field	15	nSPMACCESSR_EL1
+Field	14	nSPMCR_EL0
+Field	13	nSPMOVS
+Field	12	nSPMINTEN
+Field	11	nSPMCNTEN
+Field	10	nSPMSELR_EL0
+Field	9	nSPMEVTYPERn_EL0
+Field	8	nSPMEVCNTRn_EL0
+Field	7	nPMSSCR_EL1
+Field	6	nPMSSDATA
+Field	5	nMDSELR_EL1
+Field	4	nPMUACR_EL1
+Field	3	nPMICFILTR_EL0
+Field	2	nPMICNTR_EL0
+Field	1	nPMIAR_EL1
+Field	0	nPMECR_EL1
+EndSysreg
+
+Sysreg HDFGWTR2_EL2	3	4	3	1	1
+Res0	63:25
+Field	24	nPMBMAR_EL1
+Field	23	nMDSTEPOP_EL1
+Field	22	nTRBMPAM_EL1
+Field	21	nPMZR_EL0
+Field	20	nTRCITECR_EL1
+Field	19	nPMSDSFR_EL1
+Res0	18:17
+Field	16	nSPMSCR_EL1
+Field	15	nSPMACCESSR_EL1
+Field	14	nSPMCR_EL0
+Field	13	nSPMOVS
+Field	12	nSPMINTEN
+Field	11	nSPMCNTEN
+Field	10	nSPMSELR_EL0
+Field	9	nSPMEVTYPERn_EL0
+Field	8	nSPMEVCNTRn_EL0
+Field	7	nPMSSCR_EL1
+Res0	6
+Field	5	nMDSELR_EL1
+Field	4	nPMUACR_EL1
+Field	3	nPMICFILTR_EL0
+Field	2	nPMICNTR_EL0
+Field	1	nPMIAR_EL1
+Field	0	nPMECR_EL1
+EndSysreg
+
+Sysreg	HFGRTR2_EL2	3	4	3	1	2
+Res0	63:15
+Field	14	nACTLRALIAS_EL1
+Field	13	nACTLRMASK_EL1
+Field	12	nTCR2ALIAS_EL1
+Field	11	nTCRALIAS_EL1
+Field	10	nSCTLRALIAS2_EL1
+Field	9	nSCTLRALIAS_EL1
+Field	8	nCPACRALIAS_EL1
+Field	7	nTCR2MASK_EL1
+Field	6	nTCRMASK_EL1
+Field	5	nSCTLR2MASK_EL1
+Field	4	nSCTLRMASK_EL1
+Field	3	nCPACRMASK_EL1
+Field	2	nRCWSMASK_EL1
+Field	1	nERXGSR_EL1
+Field	0	nPFAR_EL1
+EndSysreg
+
+Sysreg	HFGWTR2_EL2	3	4	3	1	3
+Res0	63:15
+Field	14	nACTLRALIAS_EL1
+Field	13	nACTLRMASK_EL1
+Field	12	nTCR2ALIAS_EL1
+Field	11	nTCRALIAS_EL1
+Field	10	nSCTLRALIAS2_EL1
+Field	9	nSCTLRALIAS_EL1
+Field	8	nCPACRALIAS_EL1
+Field	7	nTCR2MASK_EL1
+Field	6	nTCRMASK_EL1
+Field	5	nSCTLR2MASK_EL1
+Field	4	nSCTLRMASK_EL1
+Field	3	nCPACRMASK_EL1
+Field	2	nRCWSMASK_EL1
+Res0	1
+Field	0	nPFAR_EL1
+EndSysreg
+
 Sysreg HDFGRTR_EL2	3	4	3	1	4
 Field	63	PMBIDR_EL1
 Field	62	nPMSNEVFR_EL1
@@ -2813,6 +2910,12 @@ Field	1	AMEVCNTR00_EL0
 Field	0	AMCNTEN0
 EndSysreg
 
+Sysreg	HFGITR2_EL2	3	4	3	1	7
+Res0	63:2
+Field	1	nDCCIVAPS
+Field	0	TSBCSYNC
+EndSysreg
+
 Sysreg	ZCR_EL2	3	4	1	2	0
 Fields	ZCR_ELx
 EndSysreg
@@ -3035,6 +3138,54 @@ Field	31:16	PhyPARTID29
 Field	15:0	PhyPARTID28
 EndSysreg
 
+Sysreg	ICH_HCR_EL2	3	4	12	11	0
+Res0	63:32
+Field	31:27	EOIcount
+Res0	26:16
+Field	15	DVIM
+Field	14	TDIR
+Field	13	TSEI
+Field	12	TALL1
+Field	11	TALL0
+Field	10	TC
+Res0	9
+Field	8	vSGIEOICount
+Field	7	VGrp1DIE
+Field	6	VGrp1EIE
+Field	5	VGrp0DIE
+Field	4	VGrp0EIE
+Field	3	NPIE
+Field	2	LRENPIE
+Field	1	UIE
+Field	0	En
+EndSysreg
+
+Sysreg	ICH_VTR_EL2	3	4	12	11	1
+Res0	63:32
+Field	31:29	PRIbits
+Field	28:26	PREbits
+Field	25:23	IDbits
+Field	22	SEIS
+Field	21	A3V
+Field	20	nV4
+Field	19	TDS
+Field	18	DVIM
+Res0	17:5
+Field	4:0	ListRegs
+EndSysreg
+
+Sysreg	ICH_MISR_EL2	3	4	12	11	2
+Res0	63:8
+Field	7	VGrp1D
+Field	6	VGrp1E
+Field	5	VGrp0D
+Field	4	VGrp0E
+Field	3	NP
+Field	2	LRENP
+Field	1	U
+Field	0	EOI
+EndSysreg
+
 Sysreg	CONTEXTIDR_EL2	3	4	13	0	1
 Fields	CONTEXTIDR_ELx
 EndSysreg
@@ -3385,3 +3536,10 @@ Field	5	F
 Field	4	P
 Field	3:0	Align
 EndSysreg
+
+Sysreg	HPFAR_EL2	3	4	6	0	4
+Field	63	NS
+Res0	62:48
+Field	47:4	FIPA
+Res0	3:0
+EndSysreg
diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c
index e5b8b4b2109a..aee904833dec 100644
--- a/arch/csky/abiv1/alignment.c
+++ b/arch/csky/abiv1/alignment.c
@@ -300,7 +300,7 @@ bad_area:
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 }
 
-static struct ctl_table alignment_tbl[5] = {
+static const struct ctl_table alignment_tbl[] = {
 	{
 		.procname = "kernel_enable",
 		.data = &align_kern_enable,
diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h
index ed53f0b47388..536d3bf32ff1 100644
--- a/arch/csky/include/asm/io.h
+++ b/arch/csky/include/asm/io.h
@@ -36,7 +36,7 @@
  */
 #define ioremap_wc(addr, size) \
 	ioremap_prot((addr), (size), \
-		(_PAGE_IOREMAP & ~_CACHE_MASK) | _CACHE_UNCACHED)
+		__pgprot((_PAGE_IOREMAP & ~_CACHE_MASK) | _CACHE_UNCACHED))
 
 #include <asm-generic/io.h>
 
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index bf8400c28b5a..11055c574968 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -61,11 +61,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 	return ret;
 }
 
-#define __pte_free_tlb(tlb, pte, address)		\
-do {							\
-	pagetable_dtor(page_ptdesc(pte));		\
-	tlb_remove_page_ptdesc(tlb, page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 extern void pagetable_init(void);
 extern void mmu_init(unsigned long min_pfn, unsigned long max_pfn);
diff --git a/arch/csky/kernel/perf_event.c b/arch/csky/kernel/perf_event.c
index e5f18420ce64..e0a36acd265b 100644
--- a/arch/csky/kernel/perf_event.c
+++ b/arch/csky/kernel/perf_event.c
@@ -1139,8 +1139,7 @@ static irqreturn_t csky_pmu_handle_irq(int irq_num, void *dev)
 		perf_sample_data_init(&data, 0, hwc->last_period);
 		csky_pmu_event_set_period(event);
 
-		if (perf_event_overflow(event, &data, regs))
-			csky_pmu_stop_event(event);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	csky_pmu_enable(&csky_pmu.pmu);
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index fe715b707fd0..e0d6ca86ea8c 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -12,6 +12,45 @@
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 
+#ifdef CONFIG_BLK_DEV_INITRD
+static void __init setup_initrd(void)
+{
+	unsigned long size;
+
+	if (initrd_start >= initrd_end) {
+		pr_err("initrd not found or empty");
+		goto disable;
+	}
+
+	if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
+		pr_err("initrd extends beyond end of memory");
+		goto disable;
+	}
+
+	size = initrd_end - initrd_start;
+
+	if (memblock_is_region_reserved(__pa(initrd_start), size)) {
+		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region",
+		       __pa(initrd_start), size);
+		goto disable;
+	}
+
+	memblock_reserve(__pa(initrd_start), size);
+
+	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
+		(void *)(initrd_start), size);
+
+	initrd_below_start_ok = 1;
+
+	return;
+
+disable:
+	initrd_start = initrd_end = 0;
+
+	pr_err(" - disabling initrd\n");
+}
+#endif
+
 static void __init csky_memblock_init(void)
 {
 	unsigned long lowmem_size = PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
@@ -40,6 +79,10 @@ static void __init csky_memblock_init(void)
 		max_low_pfn = min_low_pfn + sseg_size;
 	}
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	setup_initrd();
+#endif
+
 	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
 
 	mmu_init(min_low_pfn, max_low_pfn);
diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile
index 069ef0b17fe5..a3042287a070 100644
--- a/arch/csky/kernel/vdso/Makefile
+++ b/arch/csky/kernel/vdso/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Symbols present in the vdso
 vdso-syms  += rt_sigreturn
diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c
index bde7cabd23df..573da66b2543 100644
--- a/arch/csky/mm/init.c
+++ b/arch/csky/mm/init.c
@@ -42,73 +42,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 						__page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
 
-#ifdef CONFIG_BLK_DEV_INITRD
-static void __init setup_initrd(void)
-{
-	unsigned long size;
-
-	if (initrd_start >= initrd_end) {
-		pr_err("initrd not found or empty");
-		goto disable;
-	}
-
-	if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
-		pr_err("initrd extends beyond end of memory");
-		goto disable;
-	}
-
-	size = initrd_end - initrd_start;
-
-	if (memblock_is_region_reserved(__pa(initrd_start), size)) {
-		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region",
-		       __pa(initrd_start), size);
-		goto disable;
-	}
-
-	memblock_reserve(__pa(initrd_start), size);
-
-	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
-		(void *)(initrd_start), size);
-
-	initrd_below_start_ok = 1;
-
-	return;
-
-disable:
-	initrd_start = initrd_end = 0;
-
-	pr_err(" - disabling initrd\n");
-}
-#endif
-
-void __init mem_init(void)
-{
-#ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
-	set_max_mapnr(highend_pfn - ARCH_PFN_OFFSET);
-#else
-	set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
-#endif
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	setup_initrd();
-#endif
-
-	memblock_free_all();
-
-#ifdef CONFIG_HIGHMEM
-	for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
-		struct page *page = pfn_to_page(tmp);
-
-		/* FIXME not sure about */
-		if (!memblock_is_reserved(tmp << PAGE_SHIFT))
-			free_highmem_page(page);
-	}
-#endif
-}
-
 void free_initmem(void)
 {
 	free_initmem_default(-1);
diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig
index 6cb764947596..c6108f000288 100644
--- a/arch/hexagon/configs/comet_defconfig
+++ b/arch/hexagon/configs/comet_defconfig
@@ -72,10 +72,6 @@ CONFIG_INET=y
 CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=y
 CONFIG_FRAME_WARN=0
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 1ee5f5f157ca..937a11ef4c33 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -87,10 +87,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 		max_kernel_seg = pmdindex;
 }
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor((page_ptdesc(pte)));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif
diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c
index 3458f39ca2ac..34eb9d424b96 100644
--- a/arch/hexagon/mm/init.c
+++ b/arch/hexagon/mm/init.c
@@ -43,32 +43,6 @@ DEFINE_SPINLOCK(kmap_gen_lock);
 /*  checkpatch says don't init this to 0.  */
 unsigned long long kmap_generation;
 
-/*
- * mem_init - initializes memory
- *
- * Frees up bootmem
- * Fixes up more stuff for HIGHMEM
- * Calculates and displays memory available/used
- */
-void __init mem_init(void)
-{
-	/*  No idea where this is actually declared.  Seems to evade LXR.  */
-	memblock_free_all();
-
-	/*
-	 *  To-Do:  someone somewhere should wipe out the bootmem map
-	 *  after we're done?
-	 */
-
-	/*
-	 * This can be moved to some more virtual-memory-specific
-	 * initialization hook at some point.  Set the init_mm
-	 * descriptors "context" value to point to the initial
-	 * kernel segment table's physical address.
-	 */
-	init_mm.context.ptbase = __pa(init_mm.pgd);
-}
-
 void sync_icache_dcache(pte_t pte)
 {
 	unsigned long addr;
@@ -104,10 +78,10 @@ static void __init paging_init(void)
 	free_area_init(max_zone_pfn);  /*  sets up the zonelists and mem_map  */
 
 	/*
-	 * Start of high memory area.  Will probably need something more
-	 * fancy if we...  get more fancy.
+	 * Set the init_mm descriptors "context" value to point to the
+	 * initial kernel segment table's physical address.
 	 */
-	high_memory = (void *)((bootmem_lastpg + 1) << PAGE_SHIFT);
+	init_mm.context.ptbase = __pa(init_mm.pgd);
 }
 
 #ifndef DMA_RESERVE
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 2b8bd27a852f..1a2cf012b8f2 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -30,6 +30,8 @@ config LOONGARCH
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN
+	select ARCH_HAS_VDSO_ARCH_DATA
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION
@@ -71,6 +73,7 @@ config LOONGARCH
 	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_BPF_JIT
@@ -106,6 +109,7 @@ config LOONGARCH
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GPIOLIB
 	select HAS_IOPORT
@@ -175,7 +179,7 @@ config LOONGARCH
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
-	select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
+	select HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_FORCED_THREADING
 	select IRQ_LOONGARCH_CPU
 	select LOCK_MM_AND_FIND_VMA
@@ -291,6 +295,9 @@ config AS_HAS_LBT_EXTENSION
 config AS_HAS_LVZ_EXTENSION
 	def_bool $(as-instr,hvcl 0)
 
+config CC_HAS_ANNOTATE_TABLEJUMP
+	def_bool $(cc-option,-mannotate-tablejump)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -382,8 +389,8 @@ config CMDLINE_BOOTLOADER
 config CMDLINE_EXTEND
 	bool "Use built-in to extend bootloader kernel arguments"
 	help
-	  The command-line arguments provided during boot will be
-	  appended to the built-in command line. This is useful in
+	  The built-in command line will be appended to the command-
+	  line arguments provided during boot. This is useful in
 	  cases where the provided arguments are insufficient and
 	  you don't want to or cannot modify them.
 
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 567bd122a9ee..0304eabbe606 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -101,7 +101,11 @@ KBUILD_AFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)
 KBUILD_CFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
 
 ifdef CONFIG_OBJTOOL
-KBUILD_CFLAGS			+= -fno-jump-tables
+ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP
+KBUILD_CFLAGS			+= -mannotate-tablejump
+else
+KBUILD_CFLAGS			+= -fno-jump-tables # keep compatibility with older compilers
+endif
 endif
 
 KBUILD_RUSTFLAGS		+= --target=loongarch64-unknown-none-softfloat -Ccode-model=small
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
index 23cf26cc3e5f..3514ea78f525 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -90,11 +90,6 @@
 
 	#address-cells = <1>;
 	#size-cells = <0>;
-	spidev@0 {
-		compatible = "rohm,dh2228fv";
-		spi-max-frequency = <100000000>;
-		reg = <0>;
-	};
 };
 
 &ehci0 {
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 73c77500ac46..0d59af6007b7 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -24,9 +24,9 @@ CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_RDMA=y
+CONFIG_CGROUP_DMEM=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
 CONFIG_CPUSETS=y
@@ -109,8 +109,7 @@ CONFIG_BINFMT_MISC=m
 CONFIG_ZPOOL=y
 CONFIG_ZSWAP=y
 CONFIG_ZSWAP_COMPRESSOR_DEFAULT_ZSTD=y
-CONFIG_ZBUD=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
 # CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set
@@ -666,6 +665,10 @@ CONFIG_RTW88_8723DE=m
 CONFIG_RTW88_8723DU=m
 CONFIG_RTW88_8821CE=m
 CONFIG_RTW88_8821CU=m
+CONFIG_RTW88_8821AU=m
+CONFIG_RTW88_8812AU=m
+CONFIG_RTW88_8814AE=m
+CONFIG_RTW88_8814AU=m
 CONFIG_RTW89=m
 CONFIG_RTW89_8851BE=m
 CONFIG_RTW89_8852AE=m
@@ -749,6 +752,7 @@ CONFIG_MEDIA_PCI_SUPPORT=y
 CONFIG_VIDEO_BT848=m
 CONFIG_DVB_BT8XX=m
 CONFIG_DRM=y
+CONFIG_DRM_LOAD_EDID_FIRMWARE=y
 CONFIG_DRM_RADEON=m
 CONFIG_DRM_RADEON_USERPTR=y
 CONFIG_DRM_AMDGPU=m
@@ -762,6 +766,7 @@ CONFIG_DRM_LOONGSON=y
 CONFIG_FB=y
 CONFIG_FB_EFI=y
 CONFIG_FB_RADEON=y
+CONFIG_FIRMWARE_EDID=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=m
 # CONFIG_VGA_CONSOLE is not set
@@ -844,6 +849,9 @@ CONFIG_TYPEC_TCPCI=m
 CONFIG_TYPEC_UCSI=m
 CONFIG_UCSI_ACPI=m
 CONFIG_INFINIBAND=m
+CONFIG_EDAC=y
+# CONFIG_EDAC_LEGACY_SYSFS is not set
+CONFIG_EDAC_LOONGSON=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
 CONFIG_RTC_DRV_LOONGSON=y
@@ -981,7 +989,6 @@ CONFIG_MINIX_FS=m
 CONFIG_ROMFS_FS=m
 CONFIG_PSTORE=m
 CONFIG_PSTORE_COMPRESS=y
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_EROFS_FS_ZIP_LZMA=y
@@ -1019,7 +1026,7 @@ CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_YAMA=y
 CONFIG_DEFAULT_SECURITY_DAC=y
 CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_SELFTESTS=y
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_ANUBIS=m
diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h
index 51f224bcfc65..704066b4f736 100644
--- a/arch/loongarch/include/asm/asm-prototypes.h
+++ b/arch/loongarch/include/asm/asm-prototypes.h
@@ -12,3 +12,11 @@ __int128_t __ashlti3(__int128_t a, int b);
 __int128_t __ashrti3(__int128_t a, int b);
 __int128_t __lshrti3(__int128_t a, int b);
 #endif
+
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *regs);
+
+asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev,
+								    struct pt_regs *regs,
+								    int (*fn)(void *),
+								    void *fn_arg);
diff --git a/arch/loongarch/include/asm/cache.h b/arch/loongarch/include/asm/cache.h
index 1b6d09617199..aa622c754414 100644
--- a/arch/loongarch/include/asm/cache.h
+++ b/arch/loongarch/include/asm/cache.h
@@ -8,6 +8,8 @@
 #define L1_CACHE_SHIFT		CONFIG_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+#define ARCH_DMA_MINALIGN	(16)
+
 #define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_CACHE_H */
diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h
index 3177674228f8..45514f314664 100644
--- a/arch/loongarch/include/asm/fpu.h
+++ b/arch/loongarch/include/asm/fpu.h
@@ -22,22 +22,29 @@
 struct sigcontext;
 
 #define kernel_fpu_available() cpu_has_fpu
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
-
-extern void _init_fpu(unsigned int);
-extern void _save_fp(struct loongarch_fpu *);
-extern void _restore_fp(struct loongarch_fpu *);
-
-extern void _save_lsx(struct loongarch_fpu *fpu);
-extern void _restore_lsx(struct loongarch_fpu *fpu);
-extern void _init_lsx_upper(void);
-extern void _restore_lsx_upper(struct loongarch_fpu *fpu);
-
-extern void _save_lasx(struct loongarch_fpu *fpu);
-extern void _restore_lasx(struct loongarch_fpu *fpu);
-extern void _init_lasx_upper(void);
-extern void _restore_lasx_upper(struct loongarch_fpu *fpu);
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+asmlinkage void _init_fpu(unsigned int);
+asmlinkage void _save_fp(struct loongarch_fpu *);
+asmlinkage void _restore_fp(struct loongarch_fpu *);
+asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+
+asmlinkage void _save_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lsx_upper(void);
+asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+
+asmlinkage void _save_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lasx_upper(void);
+asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
 static inline void enable_lsx(void);
 static inline void disable_lsx(void);
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index c8e4057734d0..4dc4b3e04225 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index e77a56eaf906..eaff72b38dc8 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -23,9 +23,9 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size);
 #ifdef CONFIG_ARCH_IOREMAP
 
 static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
-					 unsigned long prot_val)
+					 pgprot_t prot)
 {
-	switch (prot_val & _CACHE_MASK) {
+	switch (pgprot_val(prot) & _CACHE_MASK) {
 	case _CACHE_CC:
 		return (void __iomem *)(unsigned long)(CACHE_BASE + offset);
 	case _CACHE_SUC:
@@ -38,7 +38,7 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 }
 
 #define ioremap(offset, size)		\
-	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC))
+	ioremap_prot((offset), (size), PAGE_KERNEL_SUC)
 
 #define iounmap(addr) 			((void)(addr))
 
@@ -55,10 +55,10 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
  */
 #define ioremap_wc(offset, size)	\
 	ioremap_prot((offset), (size),	\
-		pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC))
+		     wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)
 
 #define ioremap_cache(offset, size)	\
-	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))
+	ioremap_prot((offset), (size), PAGE_KERNEL)
 
 #define mmiowb() wmb()
 
diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h
index a0ca84da8541..12bd15578c33 100644
--- a/arch/loongarch/include/asm/irq.h
+++ b/arch/loongarch/include/asm/irq.h
@@ -53,7 +53,7 @@ void spurious_interrupt(void);
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
 void arch_trigger_cpumask_backtrace(const struct cpumask *mask, int exclude_cpu);
 
-#define MAX_IO_PICS 2
+#define MAX_IO_PICS 8
 #define NR_IRQS	(64 + NR_VECTORS * (NR_CPUS + MAX_IO_PICS))
 
 struct acpi_vector_group {
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 590982cd986e..f457c2662e2f 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -12,6 +12,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
 #include <linux/mutex.h>
+#include <linux/perf_event.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
 #include <linux/types.h>
@@ -176,6 +177,9 @@ struct kvm_vcpu_arch {
 	/* Pointers stored here for easy accessing from assembly code */
 	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 
+	/* GPA (=HVA) of PGD for secondary mmu */
+	unsigned long kvm_pgd;
+
 	/* Host registers preserved across guest mode execution */
 	unsigned long host_sp;
 	unsigned long host_tp;
@@ -289,6 +293,8 @@ static inline int kvm_get_pmu_num(struct kvm_vcpu_arch *arch)
 	return (arch->cpucfg[6] & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT;
 }
 
+bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu);
+
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
@@ -320,7 +326,6 @@ static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch)
 
 /* Misc */
 static inline void kvm_arch_hardware_unsetup(void) {}
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
index e671978bf552..38566574e562 100644
--- a/arch/loongarch/include/asm/lbt.h
+++ b/arch/loongarch/include/asm/lbt.h
@@ -12,9 +12,13 @@
 #include <asm/loongarch.h>
 #include <asm/processor.h>
 
-extern void _init_lbt(void);
-extern void _save_lbt(struct loongarch_lbt *);
-extern void _restore_lbt(struct loongarch_lbt *);
+asmlinkage void _init_lbt(void);
+asmlinkage void _save_lbt(struct loongarch_lbt *);
+asmlinkage void _restore_lbt(struct loongarch_lbt *);
+asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _save_ftop_context(void __user *ftop);
+asmlinkage int _restore_ftop_context(void __user *ftop);
 
 static inline int is_lbt_enabled(void)
 {
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index 7211dff8c969..b58f587f0f0a 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -55,11 +55,8 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	return pte;
 }
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index f3ddaed9ef7f..e5d21e836d99 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/arch/loongarch/include/asm/ptrace.h
@@ -33,9 +33,9 @@ struct pt_regs {
 	unsigned long __last[];
 } __aligned(8);
 
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 {
-	return arch_irqs_disabled_flags(regs->csr_prmd);
+	return !(regs->csr_prmd & CSR_PRMD_PIE);
 }
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
@@ -55,7 +55,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long))
 
 /**
  * regs_get_register() - get register value from its offset
diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h
index f23adb15f418..fc8b64773794 100644
--- a/arch/loongarch/include/asm/stacktrace.h
+++ b/arch/loongarch/include/asm/stacktrace.h
@@ -8,6 +8,7 @@
 #include <asm/asm.h>
 #include <asm/ptrace.h>
 #include <asm/loongarch.h>
+#include <asm/unwind_hints.h>
 #include <linux/stringify.h>
 
 enum stack_type {
@@ -43,6 +44,7 @@ int get_stack_info(unsigned long stack, struct task_struct *task, struct stack_i
 static __always_inline void prepare_frametrace(struct pt_regs *regs)
 {
 	__asm__ __volatile__(
+		UNWIND_HINT_SAVE
 		/* Save $ra */
 		STORE_ONE_REG(1)
 		/* Use $ra to save PC */
@@ -80,6 +82,7 @@ static __always_inline void prepare_frametrace(struct pt_regs *regs)
 		STORE_ONE_REG(29)
 		STORE_ONE_REG(30)
 		STORE_ONE_REG(31)
+		UNWIND_HINT_RESTORE
 		: "=m" (regs->csr_era)
 		: "r" (regs->regs)
 		: "memory");
diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h
index a01086ad9dde..2c68bc72736c 100644
--- a/arch/loongarch/include/asm/unwind_hints.h
+++ b/arch/loongarch/include/asm/unwind_hints.h
@@ -23,6 +23,14 @@
 	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
 .endm
 
-#endif /* __ASSEMBLY__ */
+#else /* !__ASSEMBLY__ */
+
+#define UNWIND_HINT_SAVE \
+	UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
+
+#define UNWIND_HINT_RESTORE \
+	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
+
+#endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */
diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h
index 99a0d198927f..025fc3f0a102 100644
--- a/arch/loongarch/include/asm/uprobes.h
+++ b/arch/loongarch/include/asm/uprobes.h
@@ -15,7 +15,6 @@ typedef u32 uprobe_opcode_t;
 #define UPROBE_XOLBP_INSN	__emit_break(BRK_UPROBE_XOLBP)
 
 struct arch_uprobe {
-	unsigned long	resume_era;
 	u32	insn[2];
 	u32	ixol[2];
 	bool	simulate;
diff --git a/arch/loongarch/include/asm/vdso.h b/arch/loongarch/include/asm/vdso.h
index d3ba35eb23e7..f72ec79e2dde 100644
--- a/arch/loongarch/include/asm/vdso.h
+++ b/arch/loongarch/include/asm/vdso.h
@@ -31,7 +31,6 @@ struct loongarch_vdso_info {
 	unsigned long size;
 	unsigned long offset_sigreturn;
 	struct vm_special_mapping code_mapping;
-	struct vm_special_mapping data_mapping;
 };
 
 extern struct loongarch_vdso_info vdso_info;
diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h
new file mode 100644
index 000000000000..322d0a5f1c84
--- /dev/null
+++ b/arch/loongarch/include/asm/vdso/arch_data.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Author: Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _VDSO_ARCH_DATA_H
+#define _VDSO_ARCH_DATA_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/vdso.h>
+
+struct vdso_pcpu_data {
+	u32 node;
+} ____cacheline_aligned_in_smp;
+
+struct vdso_arch_data {
+	struct vdso_pcpu_data pdata[NR_CPUS];
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h
index e80f3c4ac748..48c43f55b039 100644
--- a/arch/loongarch/include/asm/vdso/getrandom.h
+++ b/arch/loongarch/include/asm/vdso/getrandom.h
@@ -28,11 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	return &_loongarch_data.rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h
index 7eb3f041af76..88cfcf133116 100644
--- a/arch/loongarch/include/asm/vdso/gettimeofday.h
+++ b/arch/loongarch/include/asm/vdso/gettimeofday.h
@@ -72,7 +72,7 @@ static __always_inline int clock_getres_fallback(
 }
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	uint64_t count;
 
@@ -89,18 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable loongarch_vdso_hres_capable
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h
index 1c183a9b2115..50c65fb29daf 100644
--- a/arch/loongarch/include/asm/vdso/vdso.h
+++ b/arch/loongarch/include/asm/vdso/vdso.h
@@ -12,43 +12,9 @@
 #include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
-struct vdso_pcpu_data {
-	u32 node;
-} ____cacheline_aligned_in_smp;
-
-struct loongarch_vdso_data {
-	struct vdso_pcpu_data pdata[NR_CPUS];
-	struct vdso_rng_data rng_data;
-};
-
-/*
- * The layout of vvar:
- *
- *                      high
- * +---------------------+--------------------------+
- * | loongarch vdso data | LOONGARCH_VDSO_DATA_SIZE |
- * +---------------------+--------------------------+
- * |  time-ns vdso data  |        PAGE_SIZE         |
- * +---------------------+--------------------------+
- * |  generic vdso data  |        PAGE_SIZE         |
- * +---------------------+--------------------------+
- *                      low
- */
-#define LOONGARCH_VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data))
-#define LOONGARCH_VDSO_DATA_PAGES (LOONGARCH_VDSO_DATA_SIZE >> PAGE_SHIFT)
-
-enum vvar_pages {
-	VVAR_GENERIC_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_LOONGARCH_PAGES_START,
-	VVAR_LOONGARCH_PAGES_END = VVAR_LOONGARCH_PAGES_START + LOONGARCH_VDSO_DATA_PAGES - 1,
-	VVAR_NR_PAGES,
-};
-
-#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT)
-
-extern struct loongarch_vdso_data _loongarch_data __attribute__((visibility("hidden")));
+#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h
index 8987e951d0a9..1140b54b4bc8 100644
--- a/arch/loongarch/include/asm/vdso/vsyscall.h
+++ b/arch/loongarch/include/asm/vdso/vsyscall.h
@@ -6,23 +6,6 @@
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-extern struct vdso_rng_data *vdso_rng_data;
-
-static __always_inline
-struct vdso_data *__loongarch_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __loongarch_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__loongarch_get_k_vdso_rng_data(void)
-{
-	return vdso_rng_data;
-}
-#define __arch_get_k_vdso_rng_data __loongarch_get_k_vdso_rng_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4853e8b04c6f..f9dcaa60033d 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -21,10 +21,10 @@ obj-$(CONFIG_CPU_HAS_LBT)	+= lbt.o
 
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
-CFLAGS_module.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_traps.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_perf_event.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_module.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_syscall.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_traps.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_perf_event.o	+= $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_FUNCTION_TRACER
   ifndef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c..1120ac2824f6 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 8be1c38ad8eb..db1e4bb26b6a 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -296,6 +296,7 @@ static void __used output_kvm_defines(void)
 	OFFSET(KVM_ARCH_HSP, kvm_vcpu_arch, host_sp);
 	OFFSET(KVM_ARCH_HTP, kvm_vcpu_arch, host_tp);
 	OFFSET(KVM_ARCH_HPGD, kvm_vcpu_arch, host_pgd);
+	OFFSET(KVM_ARCH_KVMPGD, kvm_vcpu_arch, kvm_pgd);
 	OFFSET(KVM_ARCH_HANDLE_EXIT, kvm_vcpu_arch, handle_exit);
 	OFFSET(KVM_ARCH_HEENTRY, kvm_vcpu_arch, host_eentry);
 	OFFSET(KVM_ARCH_GEENTRY, kvm_vcpu_arch, guest_eentry);
@@ -315,6 +316,6 @@ static void __used output_vdso_defines(void)
 {
 	COMMENT("LoongArch vDSO offsets.");
 
-	DEFINE(__VVAR_PAGES, VVAR_NR_PAGES);
+	DEFINE(__VDSO_PAGES, VDSO_NR_PAGES);
 	BLANK();
 }
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 48e7e34e355e..2abc29e57381 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -77,24 +77,22 @@ SYM_CODE_START(handle_syscall)
 SYM_CODE_END(handle_syscall)
 _ASM_NOKPROBE(handle_syscall)
 
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, sp
-	bl 		syscall_exit_to_user_mode
+	move		a1, sp
+	bl 		ret_from_fork
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 
-SYM_CODE_START(ret_from_kernel_thread)
+SYM_CODE_START(ret_from_kernel_thread_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, s1
-	jirl		ra, s0, 0
-	move		a0, sp
-	bl		syscall_exit_to_user_mode
+	move		a1, sp
+	move		a2, s0
+	move		a3, s1
+	bl		ret_from_kernel_thread
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_kernel_thread)
+SYM_CODE_END(ret_from_kernel_thread_asm)
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 2f1f5b08638f..27144de5c5fe 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -68,6 +68,8 @@ static int __init fdt_cpu_clk_init(void)
 		return -ENODEV;
 
 	clk = of_clk_get(np, 0);
+	of_node_put(np);
+
 	if (IS_ERR(clk))
 		return -ENODEV;
 
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 6ab640101457..28caf416ae36 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -458,6 +458,7 @@ SYM_FUNC_START(_save_fp_context)
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_save_fp_context)
+EXPORT_SYMBOL_GPL(_save_fp_context)
 
 /*
  * a0: fpregs
@@ -471,6 +472,7 @@ SYM_FUNC_START(_restore_fp_context)
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_restore_fp_context)
+EXPORT_SYMBOL_GPL(_restore_fp_context)
 
 /*
  * a0: fpregs
@@ -484,6 +486,7 @@ SYM_FUNC_START(_save_lsx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lsx_context)
+EXPORT_SYMBOL_GPL(_save_lsx_context)
 
 /*
  * a0: fpregs
@@ -497,6 +500,7 @@ SYM_FUNC_START(_restore_lsx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lsx_context)
+EXPORT_SYMBOL_GPL(_restore_lsx_context)
 
 /*
  * a0: fpregs
@@ -510,6 +514,7 @@ SYM_FUNC_START(_save_lasx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lasx_context)
+EXPORT_SYMBOL_GPL(_save_lasx_context)
 
 /*
  * a0: fpregs
@@ -523,6 +528,7 @@ SYM_FUNC_START(_restore_lasx_context)
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lasx_context)
+EXPORT_SYMBOL_GPL(_restore_lasx_context)
 
 .L_fpu_fault:
 	li.w	a0, -EFAULT				# failure
diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
index 25c9a4cfd5fa..d5d81d74034c 100644
--- a/arch/loongarch/kernel/ftrace_dyn.c
+++ b/arch/loongarch/kernel/ftrace_dyn.c
@@ -85,14 +85,13 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod
 	 * dealing with an out-of-range condition, we can assume it
 	 * is due to a module being loaded far away from the kernel.
 	 *
-	 * NOTE: __module_text_address() must be called with preemption
-	 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+	 * NOTE: __module_text_address() must be called within a RCU read
+	 * section, but we can rely on ftrace_lock to ensure that 'mod'
 	 * retains its validity throughout the remainder of this code.
 	 */
 	if (!mod) {
-		preempt_disable();
-		mod = __module_text_address(pc);
-		preempt_enable();
+		scoped_guard(rcu)
+			mod = __module_text_address(pc);
 	}
 
 	if (WARN_ON(!mod))
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 4f0912141781..733a7665e434 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -16,6 +16,7 @@
 #include <asm/stackframe.h>
 #include <asm/thread_info.h>
 
+	.section .cpuidle.text, "ax"
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
 	/* start of idle interrupt region */
@@ -31,14 +32,16 @@ SYM_FUNC_START(__arch_cpu_idle)
 	 */
 	idle	0
 	/* end of idle interrupt region */
-1:	jr	ra
+idle_exit:
+	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
+	.previous
 
 SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, 1b
+	la_abs	t1, idle_exit
 	LONG_L	t0, sp, PT_ERA
 	/* 3 instructions idle interrupt region */
 	ori	t0, t0, 0b1100
diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index ec5b28e570c9..4c476904227f 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN;
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
 static DEFINE_PER_CPU(unsigned int, euen_current);
 
+static inline void fpregs_lock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
+	else
+		local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	else
+		local_bh_enable();
+}
+
 void kernel_fpu_begin(void)
 {
 	unsigned int *euen_curr;
 
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON(this_cpu_read(in_kernel_fpu));
 
@@ -73,7 +90,8 @@ void kernel_fpu_end(void)
 
 	this_cpu_write(in_kernel_fpu, false);
 
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
diff --git a/arch/loongarch/kernel/kgdb.c b/arch/loongarch/kernel/kgdb.c
index 445c452d72a7..7be5b4c0c900 100644
--- a/arch/loongarch/kernel/kgdb.c
+++ b/arch/loongarch/kernel/kgdb.c
@@ -8,6 +8,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
+#include <linux/objtool.h>
 #include <linux/processor.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -224,13 +225,13 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
 	regs->csr_era = pc;
 }
 
-void arch_kgdb_breakpoint(void)
+noinline void arch_kgdb_breakpoint(void)
 {
 	__asm__ __volatile__ (			\
 		".globl kgdb_breakinst\n\t"	\
-		"nop\n"				\
 		"kgdb_breakinst:\tbreak 2\n\t"); /* BRK_KDB = 2 */
 }
+STACK_FRAME_NON_STANDARD(arch_kgdb_breakpoint);
 
 /*
  * Calls linux_debug_hook before the kernel dies. If KGDB is enabled,
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
index 001f061d226a..71678912d24c 100644
--- a/arch/loongarch/kernel/lbt.S
+++ b/arch/loongarch/kernel/lbt.S
@@ -90,6 +90,7 @@ SYM_FUNC_START(_save_lbt_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_lbt_context)
+EXPORT_SYMBOL_GPL(_save_lbt_context)
 
 /*
  * a0: scr
@@ -110,6 +111,7 @@ SYM_FUNC_START(_restore_lbt_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_lbt_context)
+EXPORT_SYMBOL_GPL(_restore_lbt_context)
 
 /*
  * a0: ftop
@@ -120,6 +122,7 @@ SYM_FUNC_START(_save_ftop_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_ftop_context)
+EXPORT_SYMBOL_GPL(_save_ftop_context)
 
 /*
  * a0: ftop
@@ -150,6 +153,7 @@ SYM_FUNC_START(_restore_ftop_context)
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_ftop_context)
+EXPORT_SYMBOL_GPL(_restore_ftop_context)
 
 .L_lbt_fault:
 	li.w		a0, -EFAULT		# failure
diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 8ae641dc53bb..f9381800e291 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 84fe7f854820..30a72fd528c0 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -387,12 +387,6 @@ void __init paging_init(void)
 	free_area_init(zones_size);
 }
 
-void __init mem_init(void)
-{
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-	memblock_free_all();
-}
-
 int pcibus_to_node(struct pci_bus *bus)
 {
 	return dev_to_node(&bus->dev);
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
index f86a4b838dd7..8ad098703488 100644
--- a/arch/loongarch/kernel/perf_event.c
+++ b/arch/loongarch/kernel/perf_event.c
@@ -479,8 +479,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc, int idx,
 	if (!loongarch_pmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, data, regs))
-		loongarch_pmu_disable_event(idx);
+	perf_event_overflow(event, data, regs);
 }
 
 static irqreturn_t pmu_handle_irq(int irq, void *dev)
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 6e58f65455c7..3582f591bab2 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/entry-common.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -34,6 +35,7 @@
 #include <linux/nmi.h>
 
 #include <asm/asm.h>
+#include <asm/asm-prototypes.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/elf.h>
@@ -47,6 +49,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 #include <asm/unwind.h>
 #include <asm/vdso.h>
 
@@ -63,8 +66,9 @@ EXPORT_SYMBOL(__stack_chk_guard);
 unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(boot_option_idle_override);
 
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
+asmlinkage void restore_and_ret(void);
+asmlinkage void ret_from_fork_asm(void);
+asmlinkage void ret_from_kernel_thread_asm(void);
 
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 {
@@ -138,6 +142,23 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *regs)
+{
+	schedule_tail(prev);
+	syscall_exit_to_user_mode(regs);
+}
+
+asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev,
+								    struct pt_regs *regs,
+								    int (*fn)(void *),
+								    void *fn_arg)
+{
+	schedule_tail(prev);
+	fn(fn_arg);
+	syscall_exit_to_user_mode(regs);
+}
+
 /*
  * Copy architecture-specific thread state
  */
@@ -165,8 +186,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.reg03 = childksp;
 		p->thread.reg23 = (unsigned long)args->fn;
 		p->thread.reg24 = (unsigned long)args->fn_arg;
-		p->thread.reg01 = (unsigned long)ret_from_kernel_thread;
-		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread;
+		p->thread.reg01 = (unsigned long)ret_from_kernel_thread_asm;
+		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread_asm;
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->csr_euen = p->thread.csr_euen;
 		childregs->csr_crmd = p->thread.csr_crmd;
@@ -182,8 +203,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->regs[3] = usp;
 
 	p->thread.reg03 = (unsigned long) childregs;
-	p->thread.reg01 = (unsigned long) ret_from_fork;
-	p->thread.sched_ra = (unsigned long) ret_from_fork;
+	p->thread.reg01 = (unsigned long) ret_from_fork_asm;
+	p->thread.sched_ra = (unsigned long) ret_from_fork_asm;
 
 	/*
 	 * New tasks lose permission to use the fpu. This accelerates context
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edcfdfcad7d2..b99fbb388fe0 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -259,18 +259,17 @@ static void __init arch_reserve_crashkernel(void)
 	int ret;
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base, &low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static void __init fdt_setup(void)
@@ -387,6 +386,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 7a555b600171..4740cb5b2388 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -51,27 +51,6 @@
 #define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
-/* Assembly functions to move context to/from the FPU */
-extern asmlinkage int
-_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-
-#ifdef CONFIG_CPU_HAS_LBT
-extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _save_ftop_context(void __user *ftop);
-extern asmlinkage int _restore_ftop_context(void __user *ftop);
-#endif
-
 struct rt_sigframe {
 	struct siginfo rs_info;
 	struct ucontext rs_uctx;
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fbf747447f13..4b24589c0b56 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index e2d3bfeb6366..bc75a3a69fc8 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -111,7 +111,7 @@ static unsigned long __init get_loops_per_jiffy(void)
 	return lpj;
 }
 
-static long init_offset __nosavedata;
+static long init_offset;
 
 void save_counter(void)
 {
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 2ec3106c0da3..47fc2de6d150 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -553,9 +553,10 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 #else
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int *pc;
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
@@ -582,7 +583,7 @@ sigbus:
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 #endif
 	irqentry_exit(regs, state);
@@ -621,12 +622,13 @@ static void bug_handler(struct pt_regs *regs)
 asmlinkage void noinstr do_bce(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned long era = exception_era(regs);
 	u64 badv = 0, lower = 0, upper = ULONG_MAX;
 	union loongarch_instruction insn;
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	current->thread.trap_nr = read_csr_excode();
@@ -692,7 +694,7 @@ asmlinkage void noinstr do_bce(struct pt_regs *regs)
 	force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper);
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
@@ -710,11 +712,12 @@ bad_era:
 asmlinkage void noinstr do_bp(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int opcode, bcode;
 	unsigned long era = exception_era(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (__get_inst(&opcode, (u32 *)era, user))
@@ -780,7 +783,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
 	}
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
@@ -1015,6 +1018,7 @@ static void init_restore_lbt(void)
 
 asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 {
+	bool pie = regs_irqs_disabled(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
 	/*
@@ -1024,7 +1028,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 	 * (including the user using 'MOVGR2GCSR' to turn on TM, which
 	 * will not trigger the BTE), we need to check PRMD first.
 	 */
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (!cpu_has_lbt) {
@@ -1038,7 +1042,7 @@ asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 	preempt_enable();
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
index b25722876331..d623935a7547 100644
--- a/arch/loongarch/kernel/unwind_orc.c
+++ b/arch/loongarch/kernel/unwind_orc.c
@@ -399,7 +399,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	/* Don't let modules unload while we're reading their ORC data. */
-	preempt_disable();
+	guard(rcu)();
 
 	if (is_entry_func(state->pc))
 		goto end;
@@ -514,14 +514,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (!__kernel_text_address(state->pc))
 		goto err;
 
-	preempt_enable();
 	return true;
 
 err:
 	state->error = true;
 
 end:
-	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c
index 87abc7137b73..6022eb0f71db 100644
--- a/arch/loongarch/kernel/uprobes.c
+++ b/arch/loongarch/kernel/uprobes.c
@@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	utask->autask.saved_trap_nr = current->thread.trap_nr;
 	current->thread.trap_nr = UPROBE_TRAP_NR;
 	instruction_pointer_set(regs, utask->xol_vaddr);
-	user_enable_single_step(current);
 
 	return 0;
 }
@@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
-
-	if (auprobe->simulate)
-		instruction_pointer_set(regs, auprobe->resume_era);
-	else
-		instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
-
-	user_disable_single_step(current);
+	instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
 
 	return 0;
 }
@@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
 	instruction_pointer_set(regs, utask->vaddr);
-	user_disable_single_step(current);
 }
 
 bool arch_uprobe_xol_was_trapped(struct task_struct *t)
@@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	insn.word = auprobe->insn[0];
 	arch_simulate_insn(insn, regs);
-	auprobe->resume_era = regs->csr_era;
 
 	return true;
 }
diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c
index 05e5fbac102a..10cf1608c7b3 100644
--- a/arch/loongarch/kernel/vdso.c
+++ b/arch/loongarch/kernel/vdso.c
@@ -14,7 +14,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/page.h>
 #include <asm/vdso.h>
@@ -25,18 +25,6 @@
 
 extern char vdso_start[], vdso_end[];
 
-/* Kernel-provided data used by the VDSO. */
-static union vdso_data_store generic_vdso_data __page_aligned_data;
-
-static union {
-	u8 page[LOONGARCH_VDSO_DATA_SIZE];
-	struct loongarch_vdso_data vdata;
-} loongarch_vdso_data __page_aligned_data;
-
-struct vdso_data *vdso_data = generic_vdso_data.data;
-struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
-struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
 {
 	current->mm->context.vdso = (void *)(new_vma->vm_start);
@@ -44,53 +32,12 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc
 	return 0;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	unsigned long pfn;
-	struct page *timens_page = find_timens_vvar_page(vma);
-
-	switch (vmf->pgoff) {
-	case VVAR_GENERIC_PAGE_OFFSET:
-		if (!timens_page)
-			pfn = sym_to_pfn(vdso_data);
-		else
-			pfn = page_to_pfn(timens_page);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace specific
-		 * VVAR is mapped with the VVAR_GENERIC_PAGE_OFFSET and the real
-		 * VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END:
-		pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START;
-		break;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 struct loongarch_vdso_info vdso_info = {
 	.vdso = vdso_start,
 	.code_mapping = {
 		.name = "[vdso]",
 		.mremap = vdso_mremap,
 	},
-	.data_mapping = {
-		.name = "[vvar]",
-		.fault = vvar_fault,
-	},
 	.offset_sigreturn = vdso_offset_sigreturn,
 };
 
@@ -101,7 +48,7 @@ static int __init init_vdso(void)
 	BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
 
 	for_each_possible_cpu(cpu)
-		vdso_pdata[cpu].node = cpu_to_node(cpu);
+		vdso_k_arch_data->pdata[cpu].node = cpu_to_node(cpu);
 
 	vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
 	vdso_info.code_mapping.pages =
@@ -115,37 +62,6 @@ static int __init init_vdso(void)
 }
 subsys_initcall(init_vdso);
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a
- * task changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vdso_info.data_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
 static unsigned long vdso_base(void)
 {
 	unsigned long base = STACK_TOP;
@@ -181,9 +97,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto out;
 	}
 
-	vma = _install_special_mapping(mm, data_addr, VVAR_SIZE,
-				       VM_READ | VM_MAYREAD | VM_PFNMAP,
-				       &info->data_mapping);
+	vma = vdso_install_vvar_mapping(mm, data_addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index 97a811077ac3..40eea6da7c25 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -33,6 +33,7 @@ config KVM
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
 	select SCHED_INFO
+	select GUEST_PERF_EVENTS if PERF_EVENTS
 	help
 	  Support hosting virtualized guest machines using
 	  hardware virtualization extensions. You will need
diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile
index 3a01292f71cc..cb41d9265662 100644
--- a/arch/loongarch/kvm/Makefile
+++ b/arch/loongarch/kvm/Makefile
@@ -3,8 +3,6 @@
 # Makefile for LoongArch KVM support
 #
 
-ccflags-y += -I $(src)
-
 include $(srctree)/virt/kvm/Makefile.kvm
 
 obj-$(CONFIG_KVM) += kvm.o
@@ -23,4 +21,4 @@ kvm-y += intc/eiointc.o
 kvm-y += intc/pch_pic.o
 kvm-y += irqfd.o
 
-CFLAGS_exit.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_exit.o	+= $(call cc-disable-warning, override-init)
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index c1e8ec5b941b..ea321403644a 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index 93f4acd44523..fe734dc062ed 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -111,7 +111,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
-			kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
+			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
 			return ret;
 		}
 		/* Construct the mask by scanning the bit 27-30 */
@@ -127,7 +127,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
-		kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
+		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
 
 	return ret;
 }
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index f6d3242b9234..80ea63d465b8 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -296,10 +296,10 @@ int kvm_arch_enable_virtualization_cpu(void)
 	/*
 	 * Enable virtualization features granting guest direct control of
 	 * certain features:
-	 * GCI=2:       Trap on init or unimplement cache instruction.
+	 * GCI=2:       Trap on init or unimplemented cache instruction.
 	 * TORU=0:      Trap on Root Unimplement.
 	 * CACTRL=1:    Root control cache.
-	 * TOP=0:       Trap on Previlege.
+	 * TOP=0:       Trap on Privilege.
 	 * TOE=0:       Trap on Exception.
 	 * TIT=0:       Trap on Timer.
 	 */
@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 
@@ -387,6 +394,7 @@ static int kvm_loongarch_env_init(void)
 	}
 
 	kvm_init_gcsr_flag();
+	kvm_register_perf_callbacks(NULL);
 
 	/* Register LoongArch IPI interrupt controller interface. */
 	ret = kvm_loongarch_register_ipi_device();
@@ -418,6 +426,8 @@ static void kvm_loongarch_env_exit(void)
 		}
 		kfree(kvm_loongarch_ops);
 	}
+
+	kvm_unregister_perf_callbacks();
 }
 
 static int kvm_loongarch_init(void)
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 1be185e94807..f1768b7a6194 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -60,16 +60,8 @@
 	ld.d	t0, a2, KVM_ARCH_GPC
 	csrwr	t0, LOONGARCH_CSR_ERA
 
-	/* Save host PGDL */
-	csrrd	t0, LOONGARCH_CSR_PGDL
-	st.d	t0, a2, KVM_ARCH_HPGD
-
-	/* Switch to kvm */
-	ld.d	t1, a2, KVM_VCPU_KVM - KVM_VCPU_ARCH
-
-	/* Load guest PGDL */
-	li.w    t0, KVM_GPGD
-	ldx.d   t0, t1, t0
+	/* Load PGD for KVM hypervisor */
+	ld.d	t0, a2, KVM_ARCH_KVMPGD
 	csrwr	t0, LOONGARCH_CSR_PGDL
 
 	/* Mix GID and RID */
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 20f941af3e9e..5af32ec62cb1 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -294,6 +294,7 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
 
 		if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) {
+			kvm_lose_pmu(vcpu);
 			/* make sure the vcpu mode has been written */
 			smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE);
 			local_irq_enable();
@@ -311,7 +312,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -361,6 +362,34 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
+	unsigned long val;
+
+	preempt_disable();
+	val = gcsr_read(LOONGARCH_CSR_CRMD);
+	preempt_enable();
+
+	return (val & CSR_PRMD_PPLV) == PLV_KERN;
+}
+
+#ifdef CONFIG_GUEST_PERF_EVENTS
+unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pc;
+}
+
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context.  For LoongArch64, if PMU is not passthrough to VM,
+ * any event that arrives while a vCPU is loaded is considered to be "in guest".
+ */
+bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+	return (vcpu && !(vcpu->arch.aux_inuse & KVM_LARCH_PMU));
+}
+#endif
+
+bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu)
+{
 	return false;
 }
 
@@ -874,6 +903,13 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 			vcpu->arch.st.guest_addr = 0;
 			memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
 			memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+
+			/*
+			 * When vCPU reset, clear the ESTAT and GINTC registers
+			 * Other CSR registers are cleared with function _kvm_setcsr().
+			 */
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_GINTC, 0);
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_ESTAT, 0);
 			break;
 		default:
 			ret = -EINVAL;
@@ -1459,8 +1495,17 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.vpid = 0;
 	vcpu->arch.flush_gpa = INVALID_GPA;
 
-	hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-	vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
+	hrtimer_setup(&vcpu->arch.swtimer, kvm_swtimer_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_HARD);
+
+	/* Get GPA (=HVA) of PGD for kvm hypervisor */
+	vcpu->arch.kvm_pgd = __pa(vcpu->kvm->arch.pgd);
+
+	/*
+	 * Get PGD for primary mmu, virtual address is used since there is
+	 * memory access after loading from CSR_PGD in tlb exception fast path.
+	 */
+	vcpu->arch.host_pgd = (unsigned long)vcpu->kvm->mm->pgd;
 
 	vcpu->arch.handle_exit = kvm_handle_exit;
 	vcpu->arch.guest_eentry = (unsigned long)kvm_loongarch_ops->exc_entry;
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index b8b3e1972d6e..edccfc8c9cd8 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -48,7 +48,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (kvm_pvtime_supported())
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
 
-	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
+	/*
+	 * cpu_vabits means user address space only (a half of total).
+	 * GPA size of VM is the same with the size of user address space.
+	 */
+	kvm->arch.gpa_size = BIT(cpu_vabits);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
 	kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table;
diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c
index 8af8113ecd9d..b37cd8537b45 100644
--- a/arch/loongarch/lib/crc32-loongarch.c
+++ b/arch/loongarch/lib/crc32-loongarch.c
@@ -26,7 +26,7 @@ do {							\
 #define CRC32(crc, value, size)		_CRC32(crc, value, size, crc)
 #define CRC32C(crc, value, size)	_CRC32(crc, value, size, crcc)
 
-static DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
 
 u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -65,10 +65,10 @@ u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
-u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (!static_branch_likely(&have_crc32))
-		return crc32c_le_base(crc, p, len);
+		return crc32c_base(crc, p, len);
 
 	while (len >= sizeof(u64)) {
 		u64 value = get_unaligned_le64(p);
@@ -100,7 +100,7 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -114,7 +114,7 @@ static int __init crc32_loongarch_init(void)
 		static_branch_enable(&have_crc32);
 	return 0;
 }
-arch_initcall(crc32_loongarch_init);
+subsys_initcall(crc32_loongarch_init);
 
 static void __exit crc32_loongarch_exit(void)
 {
diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
index e4068906143b..cea84d7f2b91 100644
--- a/arch/loongarch/mm/hugetlbpage.c
+++ b/arch/loongarch/mm/hugetlbpage.c
@@ -47,7 +47,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 				pmd = pmd_offset(pud, addr);
 		}
 	}
-	return (pte_t *) pmd;
+	return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd;
 }
 
 uint64_t pmd_to_entrylo(unsigned long pmd_val)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index ca5aa5f46a9f..06f11d9e4ec1 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -65,9 +65,6 @@ void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
-#ifdef CONFIG_ZONE_DMA
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
 #ifdef CONFIG_ZONE_DMA32
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 #endif
@@ -75,14 +72,6 @@ void __init paging_init(void)
 
 	free_area_init(max_zone_pfns);
 }
-
-void __init mem_init(void)
-{
-	max_mapnr = max_low_pfn;
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-
-	memblock_free_all();
-}
 #endif /* !CONFIG_NUMA */
 
 void __ref free_initmem(void)
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index 914e82ff3f65..1df9e99582cc 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/kfence.h>
 #include <linux/memblock.h>
@@ -63,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
+	else
+		info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 
 	if (dir == DOWN) {
 		info.flags = VM_UNMAPPED_AREA_TOPDOWN;
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index ea357a3edc09..fa1500d4aa3e 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -142,6 +142,8 @@ static void build_prologue(struct jit_ctx *ctx)
 	 */
 	if (seen_tail_call(ctx) && seen_call(ctx))
 		move_reg(ctx, TCC_SAVED, REG_TCC);
+	else
+		emit_insn(ctx, nop);
 
 	ctx->stack_size = stack_adjust;
 }
@@ -905,7 +907,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 		move_addr(ctx, t1, func_addr);
 		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0);
-		move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0);
+
+		if (insn->src_reg != BPF_PSEUDO_CALL)
+			move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0);
+
 		break;
 
 	/* tail call */
@@ -930,7 +935,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	{
 		const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
 
-		move_imm(ctx, dst, imm64, is32);
+		if (bpf_pseudo_func(insn))
+			move_addr(ctx, dst, imm64);
+		else
+			move_imm(ctx, dst, imm64, is32);
 		return 1;
 	}
 
diff --git a/arch/loongarch/net/bpf_jit.h b/arch/loongarch/net/bpf_jit.h
index 68586338ecf8..f9c569f53949 100644
--- a/arch/loongarch/net/bpf_jit.h
+++ b/arch/loongarch/net/bpf_jit.h
@@ -27,6 +27,11 @@ struct jit_data {
 	struct jit_ctx ctx;
 };
 
+static inline void emit_nop(union loongarch_instruction *insn)
+{
+	insn->word = INSN_NOP;
+}
+
 #define emit_insn(ctx, func, ...)						\
 do {										\
 	if (ctx->image != NULL) {						\
diff --git a/arch/loongarch/power/hibernate.c b/arch/loongarch/power/hibernate.c
index 1e0590542f98..e7b7346592cb 100644
--- a/arch/loongarch/power/hibernate.c
+++ b/arch/loongarch/power/hibernate.c
@@ -2,6 +2,7 @@
 #include <asm/fpu.h>
 #include <asm/loongson.h>
 #include <asm/sections.h>
+#include <asm/time.h>
 #include <asm/tlbflush.h>
 #include <linux/suspend.h>
 
@@ -14,6 +15,7 @@ struct pt_regs saved_regs;
 
 void save_processor_state(void)
 {
+	save_counter();
 	saved_crmd = csr_read32(LOONGARCH_CSR_CRMD);
 	saved_prmd = csr_read32(LOONGARCH_CSR_PRMD);
 	saved_euen = csr_read32(LOONGARCH_CSR_EUEN);
@@ -26,6 +28,7 @@ void save_processor_state(void)
 
 void restore_processor_state(void)
 {
+	sync_counter();
 	csr_write32(saved_crmd, LOONGARCH_CSR_CRMD);
 	csr_write32(saved_prmd, LOONGARCH_CSR_PRMD);
 	csr_write32(saved_euen, LOONGARCH_CSR_EUEN);
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index fdde1bcd4e26..ccd2c5e135c6 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,7 +2,7 @@
 # Objects to go into the VDSO.
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso-y := elf.o vgetcpu.o vgettimeofday.o vgetrandom.o \
               vgetrandom-chacha.o sigreturn.o
@@ -36,8 +36,7 @@ endif
 
 # VDSO linker flags.
 ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
-	$(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \
-	--hash-style=sysv --build-id -T
+	$(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared --build-id -T
 
 #
 # Shared build commands.
diff --git a/arch/loongarch/vdso/vdso.lds.S b/arch/loongarch/vdso/vdso.lds.S
index 160cfaef2de4..8ff986499947 100644
--- a/arch/loongarch/vdso/vdso.lds.S
+++ b/arch/loongarch/vdso/vdso.lds.S
@@ -5,6 +5,7 @@
  */
 #include <asm/page.h>
 #include <generated/asm-offsets.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf64-loongarch", "elf64-loongarch", "elf64-loongarch")
 
@@ -12,11 +13,8 @@ OUTPUT_ARCH(loongarch)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
-	PROVIDE(_loongarch_data = _vdso_data + 2 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c
index 0db51258b2a7..5301cd9d0f83 100644
--- a/arch/loongarch/vdso/vgetcpu.c
+++ b/arch/loongarch/vdso/vgetcpu.c
@@ -19,27 +19,19 @@ static __always_inline int read_cpu_id(void)
 	return cpu_id;
 }
 
-static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void)
-{
-	return _loongarch_data.pdata;
-}
-
 extern
 int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
 int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
 {
 	int cpu_id;
-	const struct vdso_pcpu_data *data;
 
 	cpu_id = read_cpu_id();
 
 	if (cpu)
 		*cpu = cpu_id;
 
-	if (node) {
-		data = get_pcpu_data();
-		*node = data[cpu_id].node;
-	}
+	if (node)
+		*node = vdso_u_arch_data.pdata[cpu_id].node;
 
 	return 0;
 }
diff --git a/arch/loongarch/vdso/vgetrandom-chacha.S b/arch/loongarch/vdso/vgetrandom-chacha.S
index c2733e6c3a8d..c4dd2bab8825 100644
--- a/arch/loongarch/vdso/vgetrandom-chacha.S
+++ b/arch/loongarch/vdso/vgetrandom-chacha.S
@@ -58,9 +58,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 #define copy0		t5
 #define copy1		t6
 #define copy2		t7
-
-/* Reuse i as copy3 */
-#define copy3		i
+#define copy3		t8
 
 /* Packs to be used with OP_4REG */
 #define line0		state0, state1, state2, state3
@@ -99,6 +97,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	li.w		copy0, 0x61707865
 	li.w		copy1, 0x3320646e
 	li.w		copy2, 0x79622d32
+	li.w		copy3, 0x6b206574
 
 	ld.w		cnt_lo, counter, 0
 	ld.w		cnt_hi, counter, 4
@@ -108,7 +107,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	move		state0, copy0
 	move		state1, copy1
 	move		state2, copy2
-	li.w		state3, 0x6b206574
+	move		state3, copy3
 
 	/* state[4,5,..,11] = key */
 	ld.w		state4, key, 0
@@ -167,12 +166,6 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack)
 	addi.w		i, i, -1
 	bnez		i, .Lpermute
 
-	/*
-	 * copy[3] = "expa", materialize it here because copy[3] shares the
-	 * same register with i which just became dead.
-	 */
-	li.w		copy3, 0x6b206574
-
 	/* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */
 	OP_4REG	add.w	line0, copy
 	st.w		state0, output, 0
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b2ed0308c0ea..eb5bb6d36899 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -18,12 +18,13 @@ config M68K
 	select DMA_DIRECT_REMAP if M68K_NONCOHERENT_DMA && !COLDFIRE
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
-	select GENERIC_IOMAP if HAS_IOPORT
+	select GENERIC_IOMAP if HAS_IOPORT && MMU && !COLDFIRE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_LIB_ASHLDI3
 	select GENERIC_LIB_ASHRDI3
 	select GENERIC_LIB_LSHRDI3
 	select GENERIC_LIB_MULDI3
+	select GENERIC_PCI_IOMAP if PCI
 	select HAS_IOPORT if PCI || ISA || ATARI_ROM_ISA
 	select HAVE_ARCH_LIBGCC_H
 	select HAVE_ARCH_SECCOMP
diff --git a/arch/m68k/amiga/amisound.c b/arch/m68k/amiga/amisound.c
index 714fe8ec6afa..5fd93dfab809 100644
--- a/arch/m68k/amiga/amisound.c
+++ b/arch/m68k/amiga/amisound.c
@@ -78,7 +78,7 @@ void amiga_mksound( unsigned int hz, unsigned int ticks )
 		return;
 
 	local_irq_save(flags);
-	del_timer( &sound_timer );
+	timer_delete(&sound_timer);
 
 	if (hz > 20 && hz < 32767) {
 		unsigned long period = (clock_constant / hz);
diff --git a/arch/m68k/configs/amcore_defconfig b/arch/m68k/configs/amcore_defconfig
index 67a0d157122d..60767811e34a 100644
--- a/arch/m68k/configs/amcore_defconfig
+++ b/arch/m68k/configs/amcore_defconfig
@@ -2,7 +2,6 @@ CONFIG_LOCALVERSION="amcore-002"
 CONFIG_DEFAULT_HOSTNAME="amcore"
 CONFIG_SYSVIPC=y
 # CONFIG_FHANDLE is not set
-# CONFIG_USELIB is not set
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_AIO is not set
@@ -89,4 +88,3 @@ CONFIG_PANIC_ON_OOPS=y
 # CONFIG_CRYPTO_ECHAINIV is not set
 CONFIG_CRYPTO_ANSI_CPRNG=y
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index dbf2ea561c85..77f78d326a32 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -299,7 +299,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_AMIGA=m
@@ -336,6 +335,7 @@ CONFIG_ATA=y
 CONFIG_PATA_GAYLE=y
 CONFIG_PATA_BUDDHA=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -486,7 +486,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -552,7 +551,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index b0fd199cc0a4..f4031aa5d37f 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -295,7 +295,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -316,6 +315,7 @@ CONFIG_SCSI_SAS_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -443,7 +443,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -509,7 +508,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index bb5b2d3b6c10..fa92131cf4b3 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -302,7 +302,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_ATARI=m
@@ -331,6 +330,7 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_FALCON=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -463,7 +463,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -529,7 +528,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 8315a13bab73..9c2afc477061 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -292,7 +292,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -314,6 +313,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_BVME6000_SCSI=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -435,7 +435,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -501,7 +500,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 350370657e5f..e7cdab059d96 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -294,7 +294,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -315,6 +314,7 @@ CONFIG_SCSI_SAS_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -445,7 +445,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -511,7 +510,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index f942b4755702..0a79751c20a5 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -293,7 +293,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_SWIM=m
 CONFIG_ZRAM=m
@@ -320,6 +319,7 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_PLATFORM=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -462,7 +462,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -528,7 +527,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index b1eaad02efab..f8ca490ee65a 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -313,7 +313,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
@@ -363,6 +362,7 @@ CONFIG_PATA_GAYLE=y
 CONFIG_PATA_BUDDHA=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -549,7 +549,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -615,7 +614,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 6309a4442bb3..88fdcea906f3 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -291,7 +291,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -313,6 +312,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MVME147_SCSI=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -435,7 +435,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -501,7 +500,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 3feb0731f814..8acbe83dac72 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -292,7 +292,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -314,6 +313,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MVME16x_SCSI=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -436,7 +436,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -502,7 +501,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index ea04b1b0da7d..e3095301f3c5 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -293,7 +293,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
@@ -320,6 +319,7 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_FALCON=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -452,7 +452,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -518,7 +517,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index f52d9af92153..948e48ddd128 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -288,7 +288,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -310,6 +309,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_SUN3_SCSI=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -433,7 +433,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -499,7 +498,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index f348447824da..5bcf9181c37c 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -289,7 +289,6 @@ CONFIG_NET_IFE=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_TEST_ASYNC_DRIVER_PROBE=m
-CONFIG_DM_KUNIT_TEST=m
 CONFIG_CONNECTOR=m
 CONFIG_ZRAM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -311,6 +310,7 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_SUN3X_ESP=y
 CONFIG_MD=y
+CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -433,7 +433,6 @@ CONFIG_OMFS_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_QNX6FS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_EROFS_FS=m
 CONFIG_NFS_FS=y
@@ -499,7 +498,7 @@ CONFIG_ENCRYPTED_KEYS=m
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 2c96e8480173..516371d5587a 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -123,10 +123,6 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 #define PCI_IO_SIZE	0x00010000		/* 64k */
 #define PCI_IO_MASK	(PCI_IO_SIZE - 1)
 
-#define HAVE_ARCH_PIO_SIZE
-#define PIO_OFFSET	0
-#define PIO_MASK	0xffff
-#define PIO_RESERVED	0x10000
 #define PCI_IOBASE	((void __iomem *) PCI_IO_PA)
 #define PCI_SPACE_LIMIT	PCI_IO_MASK
 #endif /* CONFIG_PCI */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index 8f2676c3a988..3c43c09d4489 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -95,10 +95,24 @@ static inline void set_fc(unsigned long val)
 			      "movec %0,%/dfc\n\t"
 			      : /* no outputs */ : "r" (val) : "memory");
 }
+
+static inline unsigned long get_fc(void)
+{
+	unsigned long val;
+
+	__asm__ ("movec %/dfc,%0" : "=r" (val) : );
+
+	return val;
+}
 #else
 static inline void set_fc(unsigned long val)
 {
 }
+
+static inline unsigned long get_fc(void)
+{
+	return USER_DATA;
+}
 #endif /* CONFIG_CPU_HAS_ADDRESS_SPACES */
 
 struct thread_struct {
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index f1ae4ed890db..1e21c758b774 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -17,11 +17,8 @@
 
 extern const char bad_pmd_string[];
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {
@@ -44,8 +41,10 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
 	pgd_t *new_pgd;
 
 	new_pgd = __pgd_alloc(mm, 0);
-	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
-	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	if (likely(new_pgd != NULL)) {
+		memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
+		memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	}
 	return new_pgd;
 }
 
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 15c1a595a1de..0fba32552836 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -147,8 +147,7 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 			break;
 
 		case BI_COMMAND_LINE:
-			strscpy(m68k_command_line, data,
-				sizeof(m68k_command_line));
+			strscpy(m68k_command_line, data);
 			break;
 
 		case BI_RNG_SEED: {
@@ -243,8 +242,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_initial_init_mm((void *)PAGE_OFFSET, _etext, _edata, _end);
 
 #if defined(CONFIG_BOOTPARAM)
-	strncpy(m68k_command_line, CONFIG_BOOTPARAM_STRING, CL_SIZE);
-	m68k_command_line[CL_SIZE - 1] = 0;
+	strscpy(m68k_command_line, CONFIG_BOOTPARAM_STRING, CL_SIZE);
 #endif /* CONFIG_BOOTPARAM */
 	process_uboot_commandline(&m68k_command_line[0], CL_SIZE);
 	*cmdline_p = m68k_command_line;
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index c926da9d5ec2..f9872098f5ca 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <linux/fb.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/console.h>
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index f5ed71f1910d..9fe47112c586 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -466,3 +466,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c
index 8bb1cb3a7490..5e52ea150d5c 100644
--- a/arch/m68k/kernel/uboot.c
+++ b/arch/m68k/kernel/uboot.c
@@ -10,7 +10,6 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <linux/fb.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/console.h>
diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c
index faea2265a540..6312d5b600a5 100644
--- a/arch/m68k/mac/macboing.c
+++ b/arch/m68k/mac/macboing.c
@@ -183,7 +183,7 @@ void mac_mksound( unsigned int freq, unsigned int length )
 
 	local_irq_save(flags);
 
-	del_timer( &mac_sound_timer );
+	timer_delete(&mac_sound_timer);
 
 	for ( i = 0; i < 0x800; i++ )
 		mac_asc_regs[ i ] = 0;
@@ -277,7 +277,7 @@ static void mac_quadra_ring_bell(struct timer_list *unused)
 
 	local_irq_save(flags);
 
-	del_timer( &mac_sound_timer );
+	timer_delete(&mac_sound_timer);
 
 	if ( mac_bell_duration-- > 0 )
 	{
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 8b11d0d545aa..488411af1b3f 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -121,7 +121,5 @@ static inline void init_pointer_tables(void)
 
 void __init mem_init(void)
 {
-	/* this will put all memory onto the freelists */
-	memblock_free_all();
 	init_pointer_tables();
 }
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 119bd32efcfb..b39fc3717d8e 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -17,6 +17,7 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/sched/mm.h>
+#include <linux/string_choices.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
@@ -370,8 +371,8 @@ int mmu_emu_handle_fault (unsigned long vaddr, int read_flag, int kernel_fault)
 	}
 
 #ifdef DEBUG_MMU_EMU
-	pr_info("%s: vaddr=%lx type=%s crp=%p\n", __func__, vaddr,
-		read_flag ? "read" : "write", crp);
+	pr_info("%s: vaddr=%lx type=%s crp=%px\n", __func__, vaddr,
+		str_read_write(read_flag), crp);
 #endif
 
 	segment = (vaddr >> SUN3_PMEG_SIZE_BITS) & 0x7FF;
@@ -417,7 +418,7 @@ int mmu_emu_handle_fault (unsigned long vaddr, int read_flag, int kernel_fault)
 		pte_val (*pte) |= SUN3_PAGE_ACCESSED;
 
 #ifdef DEBUG_MMU_EMU
-	pr_info("seg:%ld crp:%p ->", get_fs().seg, crp);
+	pr_info("seg:%ld crp:%px ->", get_fc(), crp);
 	print_pte_vaddr (vaddr);
 	pr_cont("\n");
 #endif
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 680f568b77f2..7b6e97828e55 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -472,3 +472,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 4520c5741579..31d475cdb1c5 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -52,19 +52,6 @@ static void __init highmem_init(void)
 	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
 	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
 }
-
-static void __meminit highmem_setup(void)
-{
-	unsigned long pfn;
-
-	for (pfn = max_low_pfn; pfn < max_pfn; ++pfn) {
-		struct page *page = pfn_to_page(pfn);
-
-		/* FIXME not sure about */
-		if (!memblock_is_reserved(pfn << PAGE_SHIFT))
-			free_highmem_page(page);
-	}
-}
 #endif /* CONFIG_HIGHMEM */
 
 /*
@@ -104,17 +91,13 @@ void __init setup_memory(void)
 	 *
 	 * min_low_pfn - the first page (mm/bootmem.c - node_boot_start)
 	 * max_low_pfn
-	 * max_mapnr - the first unused page (mm/bootmem.c - node_low_pfn)
 	 */
 
 	/* memory start is from the kernel end (aligned) to higher addr */
 	min_low_pfn = memory_start >> PAGE_SHIFT; /* minimum for allocation */
-	/* RAM is assumed contiguous */
-	max_mapnr = memory_size >> PAGE_SHIFT;
 	max_low_pfn = ((u64)memory_start + (u64)lowmem_size) >> PAGE_SHIFT;
 	max_pfn = ((u64)memory_start + (u64)memory_size) >> PAGE_SHIFT;
 
-	pr_info("%s: max_mapnr: %#lx\n", __func__, max_mapnr);
 	pr_info("%s: min_low_pfn: %#lx\n", __func__, min_low_pfn);
 	pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
 	pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn);
@@ -124,14 +107,6 @@ void __init setup_memory(void)
 
 void __init mem_init(void)
 {
-	high_memory = (void *)__va(memory_start + lowmem_size - 1);
-
-	/* this will put all memory onto the freelists */
-	memblock_free_all();
-#ifdef CONFIG_HIGHMEM
-	highmem_setup();
-#endif
-
 	mem_init_done = 1;
 }
 
@@ -143,7 +118,7 @@ int page_is_ram(unsigned long pfn)
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-static void mm_cmdline_setup(void)
+static void __init mm_cmdline_setup(void)
 {
 	unsigned long maxmem = 0;
 	char *p = cmd_line;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 1924f2d83932..fc0772c1bad4 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -38,7 +38,6 @@ config MIPS
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_GETTIMEOFDAY
-	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_ISA_DMA if EISA
@@ -47,10 +46,12 @@ config MIPS
 	select GENERIC_LIB_CMPDI2
 	select GENERIC_LIB_LSHRDI3
 	select GENERIC_LIB_UCMPDI2
+	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GUP_GET_PXX_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT
 	select HAS_IOPORT if !NO_IOPORT_MAP || ISA
 	select HAVE_ARCH_COMPILER_H
@@ -2617,6 +2618,7 @@ config RELOCATABLE
 		   CPU_MIPS32_R6 || CPU_MIPS64_R6 || \
 		   CPU_P5600 || CAVIUM_OCTEON_SOC || \
 		   CPU_LOONGSON64
+	select ARCH_VMLINUX_NEEDS_RELOCS
 	help
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded someplace besides the default 1MB.
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index be8cb44a89fd..d9057e29bc62 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -100,10 +100,6 @@ LDFLAGS_vmlinux			+= -G 0 -static -n -nostdlib
 KBUILD_AFLAGS_MODULE		+= -mlong-calls
 KBUILD_CFLAGS_MODULE		+= -mlong-calls
 
-ifeq ($(CONFIG_RELOCATABLE),y)
-LDFLAGS_vmlinux			+= --emit-relocs
-endif
-
 cflags-y += -ffreestanding
 
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -EB
diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink
index 6cfdc149d3bc..ea0add7d56b2 100644
--- a/arch/mips/Makefile.postlink
+++ b/arch/mips/Makefile.postlink
@@ -22,7 +22,7 @@ quiet_cmd_relocs = RELOCS  $@
 
 # `@true` prevents complaint when there is nothing to be done
 
-vmlinux: FORCE
+vmlinux vmlinux.unstripped: FORCE
 	@true
 ifeq ($(CONFIG_CPU_LOONGSON3_WORKAROUNDS),y)
 	$(call if_changed,ls3_llsc)
diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c
index 8ccf167c167e..e8c38aaf46a2 100644
--- a/arch/mips/ath25/ar2315.c
+++ b/arch/mips/ath25/ar2315.c
@@ -149,8 +149,8 @@ void __init ar2315_arch_init_irq(void)
 
 	ath25_irq_dispatch = ar2315_irq_dispatch;
 
-	domain = irq_domain_add_linear(NULL, AR2315_MISC_IRQ_COUNT,
-				       &ar2315_misc_irq_domain_ops, NULL);
+	domain = irq_domain_create_linear(NULL, AR2315_MISC_IRQ_COUNT,
+					  &ar2315_misc_irq_domain_ops, NULL);
 	if (!domain)
 		panic("Failed to add IRQ domain");
 
diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c
index cfa103518113..4a1d874be766 100644
--- a/arch/mips/ath25/ar5312.c
+++ b/arch/mips/ath25/ar5312.c
@@ -143,8 +143,8 @@ void __init ar5312_arch_init_irq(void)
 
 	ath25_irq_dispatch = ar5312_irq_dispatch;
 
-	domain = irq_domain_add_linear(NULL, AR5312_MISC_IRQ_COUNT,
-				       &ar5312_misc_irq_domain_ops, NULL);
+	domain = irq_domain_create_linear(NULL, AR5312_MISC_IRQ_COUNT,
+					  &ar5312_misc_irq_domain_ops, NULL);
 	if (!domain)
 		panic("Failed to add IRQ domain");
 
diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts
index 5d33f26fd28c..8455778928b7 100644
--- a/arch/mips/boot/dts/ingenic/gcw0.dts
+++ b/arch/mips/boot/dts/ingenic/gcw0.dts
@@ -91,7 +91,7 @@
 			"MIC1N", "Built-in Mic";
 		simple-audio-card,pin-switches = "Speaker", "Headphones";
 
-		simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_LOW>;
+		simple-audio-card,hp-det-gpios = <&gpf 21 GPIO_ACTIVE_LOW>;
 		simple-audio-card,aux-devs = <&speaker_amp>, <&headphones_amp>;
 
 		simple-audio-card,bitclock-master = <&dai_codec>;
diff --git a/arch/mips/boot/dts/ingenic/rs90.dts b/arch/mips/boot/dts/ingenic/rs90.dts
index e8df70dd42bf..6d2c8aea5f49 100644
--- a/arch/mips/boot/dts/ingenic/rs90.dts
+++ b/arch/mips/boot/dts/ingenic/rs90.dts
@@ -148,7 +148,7 @@
 			"Speaker", "OUTR";
 		simple-audio-card,pin-switches = "Speaker";
 
-		simple-audio-card,hp-det-gpio = <&gpd 16 GPIO_ACTIVE_LOW>;
+		simple-audio-card,hp-det-gpios = <&gpd 16 GPIO_ACTIVE_LOW>;
 		simple-audio-card,aux-devs = <&amp>;
 
 		simple-audio-card,bitclock-master = <&dai_codec>;
diff --git a/arch/mips/boot/dts/mobileye/eyeq6h.dtsi b/arch/mips/boot/dts/mobileye/eyeq6h.dtsi
index 4a1a43f351d3..dabd5ed778b7 100644
--- a/arch/mips/boot/dts/mobileye/eyeq6h.dtsi
+++ b/arch/mips/boot/dts/mobileye/eyeq6h.dtsi
@@ -32,6 +32,10 @@
 		#interrupt-cells = <1>;
 	};
 
+	coherency-manager {
+		compatible = "mobileye,eyeq6-cm";
+	};
+
 	xtal: clock-30000000 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
diff --git a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
index 18107ca0a06b..7743d014631a 100644
--- a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
+++ b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
@@ -5,7 +5,7 @@
 
 /dts-v1/;
 
-/include/ "mt7628a.dtsi"
+#include "mt7628a.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
diff --git a/arch/mips/boot/dts/ralink/mt7620a.dtsi b/arch/mips/boot/dts/ralink/mt7620a.dtsi
index 1f6e5320f486..d66045948a83 100644
--- a/arch/mips/boot/dts/ralink/mt7620a.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7620a.dtsi
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/mediatek,mtmips-sysc.h>
+
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -25,9 +27,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		sysc@0 {
-			compatible = "ralink,mt7620a-sysc";
+		sysc: syscon@0 {
+			compatible = "ralink,mt7620-sysc", "syscon";
 			reg = <0x0 0x100>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		intc: intc@200 {
@@ -50,6 +54,8 @@
 			compatible = "ralink,mt7620a-uart", "ralink,rt2880-uart", "ns16550a";
 			reg = <0xc00 0x100>;
 
+			clocks = <&sysc MT7620_CLK_UARTLITE>;
+
 			interrupt-parent = <&intc>;
 			interrupts = <12>;
 
diff --git a/arch/mips/boot/dts/ralink/mt7620a_eval.dts b/arch/mips/boot/dts/ralink/mt7620a_eval.dts
index 8de8f89f31b8..da483ee65b61 100644
--- a/arch/mips/boot/dts/ralink/mt7620a_eval.dts
+++ b/arch/mips/boot/dts/ralink/mt7620a_eval.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /dts-v1/;
 
-/include/ "mt7620a.dtsi"
+#include "mt7620a.dtsi"
 
 / {
 	compatible = "ralink,mt7620a-eval-board", "ralink,mt7620a-soc";
diff --git a/arch/mips/boot/dts/ralink/mt7628a.dtsi b/arch/mips/boot/dts/ralink/mt7628a.dtsi
index 45a15e005cc4..0212700c4fb4 100644
--- a/arch/mips/boot/dts/ralink/mt7628a.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7628a.dtsi
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/mediatek,mtmips-sysc.h>
 
 / {
 	#address-cells = <1>;
@@ -16,11 +17,6 @@
 		};
 	};
 
-	resetc: reset-controller {
-		compatible = "ralink,rt2880-reset";
-		#reset-cells = <1>;
-	};
-
 	cpuintc: interrupt-controller {
 		#address-cells = <0>;
 		#interrupt-cells = <1>;
@@ -36,9 +32,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		sysc: system-controller@0 {
-			compatible = "ralink,mt7620a-sysc", "syscon";
+		sysc: syscon@0 {
+			compatible = "ralink,mt7628-sysc", "syscon";
 			reg = <0x0 0x60>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		pinmux: pinmux@60 {
@@ -138,7 +136,7 @@
 			compatible = "mediatek,mt7621-wdt";
 			reg = <0x100 0x30>;
 
-			resets = <&resetc 8>;
+			resets = <&sysc 8>;
 			reset-names = "wdt";
 
 			interrupt-parent = <&intc>;
@@ -154,7 +152,7 @@
 			interrupt-controller;
 			#interrupt-cells = <1>;
 
-			resets = <&resetc 9>;
+			resets = <&sysc 9>;
 			reset-names = "intc";
 
 			interrupt-parent = <&cpuintc>;
@@ -190,7 +188,9 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinmux_spi_spi>;
 
-			resets = <&resetc 18>;
+			clocks = <&sysc MT76X8_CLK_SPI1>;
+
+			resets = <&sysc 18>;
 			reset-names = "spi";
 
 			#address-cells = <1>;
@@ -206,7 +206,9 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinmux_i2c_i2c>;
 
-			resets = <&resetc 16>;
+			clocks = <&sysc MT76X8_CLK_I2C>;
+
+			resets = <&sysc 16>;
 			reset-names = "i2c";
 
 			#address-cells = <1>;
@@ -222,7 +224,9 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinmux_uart0_uart>;
 
-			resets = <&resetc 12>;
+			clocks = <&sysc MT76X8_CLK_UART0>;
+
+			resets = <&sysc 12>;
 			reset-names = "uart0";
 
 			interrupt-parent = <&intc>;
@@ -238,7 +242,9 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinmux_uart1_uart>;
 
-			resets = <&resetc 19>;
+			clocks = <&sysc MT76X8_CLK_UART1>;
+
+			resets = <&sysc 19>;
 			reset-names = "uart1";
 
 			interrupt-parent = <&intc>;
@@ -254,7 +260,9 @@
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinmux_uart2_uart>;
 
-			resets = <&resetc 20>;
+			clocks = <&sysc MT76X8_CLK_UART2>;
+
+			resets = <&sysc 20>;
 			reset-names = "uart2";
 
 			interrupt-parent = <&intc>;
@@ -271,7 +279,7 @@
 		#phy-cells = <0>;
 
 		ralink,sysctl = <&sysc>;
-		resets = <&resetc 22 &resetc 25>;
+		resets = <&sysc 22 &sysc 25>;
 		reset-names = "host", "device";
 	};
 
@@ -290,6 +298,8 @@
 		compatible = "mediatek,mt7628-wmac";
 		reg = <0x10300000 0x100000>;
 
+		clocks = <&sysc MT76X8_CLK_WMAC>;
+
 		interrupt-parent = <&cpuintc>;
 		interrupts = <6>;
 
diff --git a/arch/mips/boot/dts/ralink/omega2p.dts b/arch/mips/boot/dts/ralink/omega2p.dts
index 5884fd48f59a..51a40ab6df2b 100644
--- a/arch/mips/boot/dts/ralink/omega2p.dts
+++ b/arch/mips/boot/dts/ralink/omega2p.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "mt7628a.dtsi"
+#include "mt7628a.dtsi"
 
 / {
 	compatible = "onion,omega2+", "ralink,mt7688a-soc", "ralink,mt7628a-soc";
diff --git a/arch/mips/boot/dts/ralink/rt2880.dtsi b/arch/mips/boot/dts/ralink/rt2880.dtsi
index 8fc1987d9063..1f2ea3434324 100644
--- a/arch/mips/boot/dts/ralink/rt2880.dtsi
+++ b/arch/mips/boot/dts/ralink/rt2880.dtsi
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/mediatek,mtmips-sysc.h>
+
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -25,9 +27,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		sysc@0 {
-			compatible = "ralink,rt2880-sysc";
+		sysc: syscon@0 {
+			compatible = "ralink,rt2880-sysc", "syscon";
 			reg = <0x0 0x100>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		intc: intc@200 {
@@ -50,6 +54,8 @@
 			compatible = "ralink,rt2880-uart", "ns16550a";
 			reg = <0xc00 0x100>;
 
+			clocks = <&sysc RT2880_CLK_UARTLITE>;
+
 			interrupt-parent = <&intc>;
 			interrupts = <8>;
 
diff --git a/arch/mips/boot/dts/ralink/rt2880_eval.dts b/arch/mips/boot/dts/ralink/rt2880_eval.dts
index 759bc1dd5b83..9854a4b120e9 100644
--- a/arch/mips/boot/dts/ralink/rt2880_eval.dts
+++ b/arch/mips/boot/dts/ralink/rt2880_eval.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /dts-v1/;
 
-/include/ "rt2880.dtsi"
+#include "rt2880.dtsi"
 
 / {
 	compatible = "ralink,rt2880-eval-board", "ralink,rt2880-soc";
diff --git a/arch/mips/boot/dts/ralink/rt3050.dtsi b/arch/mips/boot/dts/ralink/rt3050.dtsi
index 23062333a76d..a7d9bb9bc1af 100644
--- a/arch/mips/boot/dts/ralink/rt3050.dtsi
+++ b/arch/mips/boot/dts/ralink/rt3050.dtsi
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/mediatek,mtmips-sysc.h>
+
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -25,9 +27,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		sysc@0 {
-			compatible = "ralink,rt3052-sysc", "ralink,rt3050-sysc";
+		sysc: syscon@0 {
+			compatible = "ralink,rt3052-sysc", "ralink,rt3050-sysc", "syscon";
 			reg = <0x0 0x100>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		intc: intc@200 {
@@ -50,6 +54,8 @@
 			compatible = "ralink,rt3052-uart", "ralink,rt2880-uart", "ns16550a";
 			reg = <0xc00 0x100>;
 
+			clocks = <&sysc RT305X_CLK_UARTLITE>;
+
 			interrupt-parent = <&intc>;
 			interrupts = <12>;
 
diff --git a/arch/mips/boot/dts/ralink/rt3883.dtsi b/arch/mips/boot/dts/ralink/rt3883.dtsi
index 61132cf157e5..11d111a06037 100644
--- a/arch/mips/boot/dts/ralink/rt3883.dtsi
+++ b/arch/mips/boot/dts/ralink/rt3883.dtsi
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/mediatek,mtmips-sysc.h>
+
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -25,9 +27,11 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 
-		sysc@0 {
-			compatible = "ralink,rt3883-sysc", "ralink,rt3050-sysc";
+		sysc: syscon@0 {
+			compatible = "ralink,rt3883-sysc", "syscon";
 			reg = <0x0 0x100>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		intc: intc@200 {
@@ -50,6 +54,8 @@
 			compatible = "ralink,rt3883-uart", "ralink,rt2880-uart", "ns16550a";
 			reg = <0xc00 0x100>;
 
+			clocks = <&sysc RT3883_CLK_UARTLITE>;
+
 			interrupt-parent = <&intc>;
 			interrupts = <12>;
 
diff --git a/arch/mips/boot/dts/ralink/rt3883_eval.dts b/arch/mips/boot/dts/ralink/rt3883_eval.dts
index c22bc84df219..a095a1fe9415 100644
--- a/arch/mips/boot/dts/ralink/rt3883_eval.dts
+++ b/arch/mips/boot/dts/ralink/rt3883_eval.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /dts-v1/;
 
-/include/ "rt3883.dtsi"
+#include "rt3883.dtsi"
 
 / {
 	compatible = "ralink,rt3883-eval-board", "ralink,rt3883-soc";
diff --git a/arch/mips/boot/dts/realtek/cisco_sg220-26.dts b/arch/mips/boot/dts/realtek/cisco_sg220-26.dts
index 1cdbb09297ef..fab3d552404d 100644
--- a/arch/mips/boot/dts/realtek/cisco_sg220-26.dts
+++ b/arch/mips/boot/dts/realtek/cisco_sg220-26.dts
@@ -2,9 +2,10 @@
 
 /dts-v1/;
 
-#include "rtl83xx.dtsi"
 #include "rtl838x.dtsi"
 
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	model = "Cisco SG220-26";
 	compatible = "cisco,sg220-26", "realtek,rtl8382-soc";
@@ -18,6 +19,13 @@
 		device_type = "memory";
 		reg = <0x0 0x8000000>;
 	};
+
+	gpio-restart {
+		compatible = "gpio-restart";
+		gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+		priority = <192>;
+		open-source;
+	};
 };
 
 &uart0 {
diff --git a/arch/mips/boot/dts/realtek/rtl838x.dtsi b/arch/mips/boot/dts/realtek/rtl838x.dtsi
index 722106e39194..ce522a6af262 100644
--- a/arch/mips/boot/dts/realtek/rtl838x.dtsi
+++ b/arch/mips/boot/dts/realtek/rtl838x.dtsi
@@ -1,6 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-or-later OR BSD-2-Clause
 
 / {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -9,8 +17,7 @@
 			device_type = "cpu";
 			compatible = "mips,mips4KEc";
 			reg = <0>;
-			clocks = <&baseclk 0>;
-			clock-names = "cpu";
+			clocks = <&baseclk>;
 		};
 	};
 
@@ -19,4 +26,104 @@
 		#clock-cells = <0>;
 		clock-frequency = <500000000>;
 	};
+
+	cpuintc: cpuintc {
+		compatible = "mti,cpu-interrupt-controller";
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	lx_clk: clock-lexra {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <200000000>;
+	};
+
+	soc@18000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x18000000 0x10000>;
+
+		spi0: spi@1200 {
+			compatible = "realtek,rtl8380-spi";
+			reg = <0x1200 0x100>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		uart0: serial@2000 {
+			compatible = "ns16550a";
+			reg = <0x2000 0x100>;
+
+			clocks = <&lx_clk>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <31>;
+
+			reg-io-width = <1>;
+			reg-shift = <2>;
+			fifo-size = <1>;
+			no-loopback-test;
+
+			status = "disabled";
+		};
+
+		uart1: serial@2100 {
+			compatible = "ns16550a";
+			reg = <0x2100 0x100>;
+
+			clocks = <&lx_clk>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <30>;
+
+			reg-io-width = <1>;
+			reg-shift = <2>;
+			fifo-size = <1>;
+			no-loopback-test;
+
+			status = "disabled";
+		};
+
+		intc: interrupt-controller@3000 {
+			compatible = "realtek,rtl8380-intc", "realtek,rtl-intc";
+			reg = <0x3000 0x20>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>, <3>, <4>, <5>, <6>;
+		};
+
+		watchdog: watchdog@3150 {
+			compatible = "realtek,rtl8380-wdt";
+			reg = <0x3150 0xc>;
+
+			realtek,reset-mode = "soc";
+
+			clocks = <&lx_clk>;
+			timeout-sec = <20>;
+
+			interrupt-parent = <&intc>;
+			interrupt-names = "phase1", "phase2";
+			interrupts = <19>, <18>;
+		};
+
+		gpio0: gpio@3500 {
+			compatible = "realtek,rtl8380-gpio", "realtek,otto-gpio";
+			reg = <0x3500 0x1c>;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			ngpios = <24>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupt-parent = <&intc>;
+			interrupts = <23>;
+		};
+	};
 };
diff --git a/arch/mips/boot/dts/realtek/rtl83xx.dtsi b/arch/mips/boot/dts/realtek/rtl83xx.dtsi
deleted file mode 100644
index 03ddc61f7c9e..000000000000
--- a/arch/mips/boot/dts/realtek/rtl83xx.dtsi
+++ /dev/null
@@ -1,59 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later OR BSD-2-Clause
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		serial0 = &uart0;
-		serial1 = &uart1;
-	};
-
-	cpuintc: cpuintc {
-		compatible = "mti,cpu-interrupt-controller";
-		#address-cells = <0>;
-		#interrupt-cells = <1>;
-		interrupt-controller;
-	};
-
-	soc: soc {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0x0 0x18000000 0x10000>;
-
-		uart0: serial@2000 {
-			compatible = "ns16550a";
-			reg = <0x2000 0x100>;
-
-			clock-frequency = <200000000>;
-
-			interrupt-parent = <&cpuintc>;
-			interrupts = <31>;
-
-			reg-io-width = <1>;
-			reg-shift = <2>;
-			fifo-size = <1>;
-			no-loopback-test;
-
-			status = "disabled";
-		};
-
-		uart1: serial@2100 {
-			compatible = "ns16550a";
-			reg = <0x2100 0x100>;
-
-			clock-frequency = <200000000>;
-
-			interrupt-parent = <&cpuintc>;
-			interrupts = <30>;
-
-			reg-io-width = <1>;
-			reg-shift = <2>;
-			fifo-size = <1>;
-			no-loopback-test;
-
-			status = "disabled";
-		};
-	};
-};
diff --git a/arch/mips/boot/dts/realtek/rtl930x.dtsi b/arch/mips/boot/dts/realtek/rtl930x.dtsi
index 17577457d159..f2e57ea3a60c 100644
--- a/arch/mips/boot/dts/realtek/rtl930x.dtsi
+++ b/arch/mips/boot/dts/realtek/rtl930x.dtsi
@@ -1,10 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0-or-later OR BSD-2-Clause
 
-#include "rtl83xx.dtsi"
-
 / {
 	compatible = "realtek,rtl9302-soc";
 
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
+	cpuintc: cpuintc {
+		compatible = "mti,cpu-interrupt-controller";
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -13,8 +26,7 @@
 			device_type = "cpu";
 			compatible = "mips,mips34Kc";
 			reg = <0>;
-			clocks = <&baseclk 0>;
-			clock-names = "cpu";
+			clocks = <&baseclk>;
 		};
 	};
 
@@ -58,64 +70,84 @@
 			status = "disabled";
 		};
 	};
-};
 
-&soc {
-	ranges = <0x0 0x18000000 0x20000>;
+	soc: soc@18000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x18000000 0x20000>;
 
-	intc: interrupt-controller@3000 {
-		compatible = "realtek,rtl9300-intc", "realtek,rtl-intc";
-		reg = <0x3000 0x18>, <0x3018 0x18>;
-		interrupt-controller;
-		#interrupt-cells = <1>;
+		intc: interrupt-controller@3000 {
+			compatible = "realtek,rtl9300-intc", "realtek,rtl-intc";
+			reg = <0x3000 0x18>, <0x3018 0x18>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
 
-		interrupt-parent = <&cpuintc>;
-		interrupts = <2>, <3>, <4>, <5>, <6>, <7>;
-	};
+			interrupt-parent = <&cpuintc>;
+			interrupts = <2>, <3>, <4>, <5>, <6>, <7>;
+		};
 
-	spi0: spi@1200 {
-		compatible = "realtek,rtl8380-spi";
-		reg = <0x1200 0x100>;
+		spi0: spi@1200 {
+			compatible = "realtek,rtl8380-spi";
+			reg = <0x1200 0x100>;
 
-		#address-cells = <1>;
-		#size-cells = <0>;
-	};
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
 
-	timer0: timer@3200 {
-		compatible = "realtek,rtl9302-timer", "realtek,otto-timer";
-		reg = <0x3200 0x10>, <0x3210 0x10>, <0x3220 0x10>,
-		    <0x3230 0x10>, <0x3240 0x10>;
+		timer0: timer@3200 {
+			compatible = "realtek,rtl9302-timer", "realtek,otto-timer";
+			reg = <0x3200 0x10>, <0x3210 0x10>, <0x3220 0x10>,
+			    <0x3230 0x10>, <0x3240 0x10>;
 
-		interrupt-parent = <&intc>;
-		interrupts = <7>, <8>, <9>, <10>, <11>;
-		clocks = <&lx_clk>;
-	};
+			interrupt-parent = <&intc>;
+			interrupts = <7>, <8>, <9>, <10>, <11>;
+			clocks = <&lx_clk>;
+		};
 
-	snand: spi@1a400 {
-		compatible = "realtek,rtl9301-snand";
-		reg = <0x1a400 0x44>;
-		interrupt-parent = <&intc>;
-		interrupts = <19>;
-		clocks = <&lx_clk>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		status = "disabled";
-	};
-};
+		snand: spi@1a400 {
+			compatible = "realtek,rtl9301-snand";
+			reg = <0x1a400 0x44>;
+			interrupt-parent = <&intc>;
+			interrupts = <19>;
+			clocks = <&lx_clk>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
 
-&uart0 {
-	/delete-property/ clock-frequency;
-	clocks = <&lx_clk>;
+		uart0: serial@2000 {
+			compatible = "ns16550a";
+			reg = <0x2000 0x100>;
 
-	interrupt-parent = <&intc>;
-	interrupts = <30>;
-};
+			clocks = <&lx_clk>;
 
-&uart1 {
-	/delete-property/ clock-frequency;
-	clocks = <&lx_clk>;
+			interrupt-parent = <&intc>;
+			interrupts = <30>;
 
-	interrupt-parent = <&intc>;
-	interrupts = <31>;
-};
+			reg-io-width = <1>;
+			reg-shift = <2>;
+			fifo-size = <1>;
+			no-loopback-test;
 
+			status = "disabled";
+		};
+
+		uart1: serial@2100 {
+			compatible = "ns16550a";
+			reg = <0x2100 0x100>;
+
+			clocks = <&lx_clk>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <31>;
+
+			reg-io-width = <1>;
+			reg-shift = <2>;
+			fifo-size = <1>;
+			no-loopback-test;
+
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c
index a88d66c46d7f..9863e1d5c62e 100644
--- a/arch/mips/boot/tools/relocs.c
+++ b/arch/mips/boot/tools/relocs.c
@@ -468,6 +468,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 			Elf_Sym *sym, const char *symname))
 {
 	int i;
+	struct section *extab_sec = sec_lookup("__ex_table");
+	int extab_index = extab_sec ? extab_sec - secs : -1;
 
 	/* Walk through the relocations */
 	for (i = 0; i < ehdr.e_shnum; i++) {
@@ -480,6 +482,9 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (sec->shdr.sh_type != SHT_REL_TYPE)
 			continue;
 
+		if (sec->shdr.sh_info == extab_index)
+			continue;
+
 		sec_symtab  = sec->link;
 		sec_applies = &secs[sec->shdr.sh_info];
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index 450e979ef5d9..11f4aa6e80e9 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -23,6 +23,12 @@ config CAVIUM_OCTEON_CVMSEG_SIZE
 	  legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is
 	  between zero and 6192 bytes).
 
+config CRYPTO_SHA256_OCTEON
+	tristate
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_LIB_SHA256_GENERIC
+
 endif # CPU_CAVIUM_OCTEON
 
 if CAVIUM_OCTEON_SOC
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index 5ee4ade99b99..fbc84eb7fedf 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -19,22 +19,26 @@
  * any later version.
  */
 
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/md5.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/string.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
+#include <linux/unaligned.h>
 
 #include "octeon-crypto.h"
 
+struct octeon_md5_state {
+	__le32 hash[MD5_HASH_WORDS];
+	u64 byte_count;
+};
+
 /*
  * We pass everything as 64-bit. OCTEON can handle misaligned data.
  */
 
-static void octeon_md5_store_hash(struct md5_state *ctx)
+static void octeon_md5_store_hash(struct octeon_md5_state *ctx)
 {
 	u64 *hash = (u64 *)ctx->hash;
 
@@ -42,7 +46,7 @@ static void octeon_md5_store_hash(struct md5_state *ctx)
 	write_octeon_64bit_hash_dword(hash[1], 1);
 }
 
-static void octeon_md5_read_hash(struct md5_state *ctx)
+static void octeon_md5_read_hash(struct octeon_md5_state *ctx)
 {
 	u64 *hash = (u64 *)ctx->hash;
 
@@ -66,13 +70,12 @@ static void octeon_md5_transform(const void *_block)
 
 static int octeon_md5_init(struct shash_desc *desc)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = MD5_H0;
-	mctx->hash[1] = MD5_H1;
-	mctx->hash[2] = MD5_H2;
-	mctx->hash[3] = MD5_H3;
-	cpu_to_le32_array(mctx->hash, 4);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
@@ -81,52 +84,38 @@ static int octeon_md5_init(struct shash_desc *desc)
 static int octeon_md5_update(struct shash_desc *desc, const u8 *data,
 			     unsigned int len)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
-	const u32 avail = sizeof(mctx->block) - (mctx->byte_count & 0x3f);
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
 
 	mctx->byte_count += len;
-
-	if (avail > len) {
-		memcpy((char *)mctx->block + (sizeof(mctx->block) - avail),
-		       data, len);
-		return 0;
-	}
-
-	memcpy((char *)mctx->block + (sizeof(mctx->block) - avail), data,
-	       avail);
-
 	flags = octeon_crypto_enable(&state);
 	octeon_md5_store_hash(mctx);
 
-	octeon_md5_transform(mctx->block);
-	data += avail;
-	len -= avail;
-
-	while (len >= sizeof(mctx->block)) {
+	do {
 		octeon_md5_transform(data);
-		data += sizeof(mctx->block);
-		len -= sizeof(mctx->block);
-	}
+		data += MD5_HMAC_BLOCK_SIZE;
+		len -= MD5_HMAC_BLOCK_SIZE;
+	} while (len >= MD5_HMAC_BLOCK_SIZE);
 
 	octeon_md5_read_hash(mctx);
 	octeon_crypto_disable(&state, flags);
-
-	memcpy(mctx->block, data, len);
-
-	return 0;
+	mctx->byte_count -= len;
+	return len;
 }
 
-static int octeon_md5_final(struct shash_desc *desc, u8 *out)
+static int octeon_md5_finup(struct shash_desc *desc, const u8 *src,
+			    unsigned int offset, u8 *out)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
-	const unsigned int offset = mctx->byte_count & 0x3f;
-	char *p = (char *)mctx->block + offset;
+	struct octeon_md5_state *mctx = shash_desc_ctx(desc);
 	int padding = 56 - (offset + 1);
 	struct octeon_cop2_state state;
+	u32 block[MD5_BLOCK_WORDS];
 	unsigned long flags;
+	char *p;
 
+	p = memcpy(block, src, offset);
+	p += offset;
 	*p++ = 0x80;
 
 	flags = octeon_crypto_enable(&state);
@@ -134,39 +123,56 @@ static int octeon_md5_final(struct shash_desc *desc, u8 *out)
 
 	if (padding < 0) {
 		memset(p, 0x00, padding + sizeof(u64));
-		octeon_md5_transform(mctx->block);
-		p = (char *)mctx->block;
+		octeon_md5_transform(block);
+		p = (char *)block;
 		padding = 56;
 	}
 
 	memset(p, 0, padding);
-	mctx->block[14] = mctx->byte_count << 3;
-	mctx->block[15] = mctx->byte_count >> 29;
-	cpu_to_le32_array(mctx->block + 14, 2);
-	octeon_md5_transform(mctx->block);
+	mctx->byte_count += offset;
+	block[14] = mctx->byte_count << 3;
+	block[15] = mctx->byte_count >> 29;
+	cpu_to_le32_array(block + 14, 2);
+	octeon_md5_transform(block);
 
 	octeon_md5_read_hash(mctx);
 	octeon_crypto_disable(&state, flags);
 
+	memzero_explicit(block, sizeof(block));
 	memcpy(out, mctx->hash, sizeof(mctx->hash));
-	memset(mctx, 0, sizeof(*mctx));
 
 	return 0;
 }
 
 static int octeon_md5_export(struct shash_desc *desc, void *out)
 {
-	struct md5_state *ctx = shash_desc_ctx(desc);
-
-	memcpy(out, ctx, sizeof(*ctx));
+	struct octeon_md5_state *ctx = shash_desc_ctx(desc);
+	union {
+		u8 *u8;
+		u32 *u32;
+		u64 *u64;
+	} p = { .u8 = out };
+	int i;
+
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		put_unaligned(le32_to_cpu(ctx->hash[i]), p.u32++);
+	put_unaligned(ctx->byte_count, p.u64);
 	return 0;
 }
 
 static int octeon_md5_import(struct shash_desc *desc, const void *in)
 {
-	struct md5_state *ctx = shash_desc_ctx(desc);
-
-	memcpy(ctx, in, sizeof(*ctx));
+	struct octeon_md5_state *ctx = shash_desc_ctx(desc);
+	union {
+		const u8 *u8;
+		const u32 *u32;
+		const u64 *u64;
+	} p = { .u8 = in };
+	int i;
+
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		ctx->hash[i] = cpu_to_le32(get_unaligned(p.u32++));
+	ctx->byte_count = get_unaligned(p.u64);
 	return 0;
 }
 
@@ -174,15 +180,16 @@ static struct shash_alg alg = {
 	.digestsize	=	MD5_DIGEST_SIZE,
 	.init		=	octeon_md5_init,
 	.update		=	octeon_md5_update,
-	.final		=	octeon_md5_final,
+	.finup		=	octeon_md5_finup,
 	.export		=	octeon_md5_export,
 	.import		=	octeon_md5_import,
-	.descsize	=	sizeof(struct md5_state),
-	.statesize	=	sizeof(struct md5_state),
+	.statesize	=	MD5_STATE_SIZE,
+	.descsize	=	sizeof(struct octeon_md5_state),
 	.base		=	{
 		.cra_name	=	"md5",
 		.cra_driver_name=	"octeon-md5",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha1.c b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
index 37a07b3c4568..e70f21a473da 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha1.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
@@ -13,15 +13,13 @@
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  */
 
-#include <linux/mm.h>
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
 
 #include "octeon-crypto.h"
 
@@ -58,49 +56,23 @@ static void octeon_sha1_read_hash(struct sha1_state *sctx)
 	memzero_explicit(&hash_tail.dword, sizeof(hash_tail.dword));
 }
 
-static void octeon_sha1_transform(const void *_block)
+static void octeon_sha1_transform(struct sha1_state *sctx, const u8 *src,
+				  int blocks)
 {
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_dword(block[0], 0);
-	write_octeon_64bit_block_dword(block[1], 1);
-	write_octeon_64bit_block_dword(block[2], 2);
-	write_octeon_64bit_block_dword(block[3], 3);
-	write_octeon_64bit_block_dword(block[4], 4);
-	write_octeon_64bit_block_dword(block[5], 5);
-	write_octeon_64bit_block_dword(block[6], 6);
-	octeon_sha1_start(block[7]);
-}
-
-static void __octeon_sha1_update(struct sha1_state *sctx, const u8 *data,
-				 unsigned int len)
-{
-	unsigned int partial;
-	unsigned int done;
-	const u8 *src;
-
-	partial = sctx->count % SHA1_BLOCK_SIZE;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) >= SHA1_BLOCK_SIZE) {
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buffer + partial, data,
-			       done + SHA1_BLOCK_SIZE);
-			src = sctx->buffer;
-		}
-
-		do {
-			octeon_sha1_transform(src);
-			done += SHA1_BLOCK_SIZE;
-			src = data + done;
-		} while (done + SHA1_BLOCK_SIZE <= len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buffer + partial, src, len - done);
+	do {
+		const u64 *block = (const u64 *)src;
+
+		write_octeon_64bit_block_dword(block[0], 0);
+		write_octeon_64bit_block_dword(block[1], 1);
+		write_octeon_64bit_block_dword(block[2], 2);
+		write_octeon_64bit_block_dword(block[3], 3);
+		write_octeon_64bit_block_dword(block[4], 4);
+		write_octeon_64bit_block_dword(block[5], 5);
+		write_octeon_64bit_block_dword(block[6], 6);
+		octeon_sha1_start(block[7]);
+
+		src += SHA1_BLOCK_SIZE;
+	} while (--blocks);
 }
 
 static int octeon_sha1_update(struct shash_desc *desc, const u8 *data,
@@ -109,95 +81,47 @@ static int octeon_sha1_update(struct shash_desc *desc, const u8 *data,
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha1 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
-		return crypto_sha1_update(desc, data, len);
+	int remain;
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha1_store_hash(sctx);
 
-	__octeon_sha1_update(sctx, data, len);
+	remain = sha1_base_do_update_blocks(desc, data, len,
+					    octeon_sha1_transform);
 
 	octeon_sha1_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	return 0;
+	return remain;
 }
 
-static int octeon_sha1_final(struct shash_desc *desc, u8 *out)
+static int octeon_sha1_finup(struct shash_desc *desc, const u8 *src,
+			     unsigned int len, u8 *out)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
-	static const u8 padding[64] = { 0x80, };
 	struct octeon_cop2_state state;
-	__be32 *dst = (__be32 *)out;
-	unsigned int pad_len;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits;
-	int i;
-
-	/* Save number of bits. */
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64. */
-	index = sctx->count & 0x3f;
-	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha1_store_hash(sctx);
 
-	__octeon_sha1_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha1_update(sctx, (const u8 *)&bits, sizeof(bits));
+	sha1_base_do_finup(desc, src, len, octeon_sha1_transform);
 
 	octeon_sha1_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest */
-	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int octeon_sha1_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int octeon_sha1_import(struct shash_desc *desc, const void *in)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
+	return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg octeon_sha1_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	octeon_sha1_update,
-	.final		=	octeon_sha1_final,
-	.export		=	octeon_sha1_export,
-	.import		=	octeon_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
+	.finup		=	octeon_sha1_finup,
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"octeon-sha1",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha256.c b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
index 435e4a6e7f13..f93faaf1f4af 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha256.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Cryptographic API.
- *
- * SHA-224 and SHA-256 Secure Hash Algorithm.
+ * SHA-256 Secure Hash Algorithm.
  *
  * Adapted for OCTEON by Aaro Koskinen <aaro.koskinen@iki.fi>.
  *
@@ -14,15 +12,10 @@
  * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
  */
 
-#include <linux/mm.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <asm/byteorder.h>
 #include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 #include "octeon-crypto.h"
 
@@ -30,212 +23,51 @@
  * We pass everything as 64-bit. OCTEON can handle misaligned data.
  */
 
-static void octeon_sha256_store_hash(struct sha256_state *sctx)
-{
-	u64 *hash = (u64 *)sctx->state;
-
-	write_octeon_64bit_hash_dword(hash[0], 0);
-	write_octeon_64bit_hash_dword(hash[1], 1);
-	write_octeon_64bit_hash_dword(hash[2], 2);
-	write_octeon_64bit_hash_dword(hash[3], 3);
-}
-
-static void octeon_sha256_read_hash(struct sha256_state *sctx)
-{
-	u64 *hash = (u64 *)sctx->state;
-
-	hash[0] = read_octeon_64bit_hash_dword(0);
-	hash[1] = read_octeon_64bit_hash_dword(1);
-	hash[2] = read_octeon_64bit_hash_dword(2);
-	hash[3] = read_octeon_64bit_hash_dword(3);
-}
-
-static void octeon_sha256_transform(const void *_block)
-{
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_dword(block[0], 0);
-	write_octeon_64bit_block_dword(block[1], 1);
-	write_octeon_64bit_block_dword(block[2], 2);
-	write_octeon_64bit_block_dword(block[3], 3);
-	write_octeon_64bit_block_dword(block[4], 4);
-	write_octeon_64bit_block_dword(block[5], 5);
-	write_octeon_64bit_block_dword(block[6], 6);
-	octeon_sha256_start(block[7]);
-}
-
-static void __octeon_sha256_update(struct sha256_state *sctx, const u8 *data,
-				   unsigned int len)
-{
-	unsigned int partial;
-	unsigned int done;
-	const u8 *src;
-
-	partial = sctx->count % SHA256_BLOCK_SIZE;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) >= SHA256_BLOCK_SIZE) {
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buf + partial, data,
-			       done + SHA256_BLOCK_SIZE);
-			src = sctx->buf;
-		}
-
-		do {
-			octeon_sha256_transform(src);
-			done += SHA256_BLOCK_SIZE;
-			src = data + done;
-		} while (done + SHA256_BLOCK_SIZE <= len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buf + partial, src, len - done);
-}
-
-static int octeon_sha256_update(struct shash_desc *desc, const u8 *data,
-				unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	struct octeon_cop2_state state;
-	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha256 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
-		return crypto_sha256_update(desc, data, len);
-
-	flags = octeon_crypto_enable(&state);
-	octeon_sha256_store_hash(sctx);
-
-	__octeon_sha256_update(sctx, data, len);
-
-	octeon_sha256_read_hash(sctx);
-	octeon_crypto_disable(&state, flags);
-
-	return 0;
-}
-
-static int octeon_sha256_final(struct shash_desc *desc, u8 *out)
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
 {
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	static const u8 padding[64] = { 0x80, };
-	struct octeon_cop2_state state;
-	__be32 *dst = (__be32 *)out;
-	unsigned int pad_len;
+	struct octeon_cop2_state cop2_state;
+	u64 *state64 = (u64 *)state;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits;
-	int i;
-
-	/* Save number of bits. */
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64. */
-	index = sctx->count & 0x3f;
-	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
-
-	flags = octeon_crypto_enable(&state);
-	octeon_sha256_store_hash(sctx);
-
-	__octeon_sha256_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha256_update(sctx, (const u8 *)&bits, sizeof(bits));
-
-	octeon_sha256_read_hash(sctx);
-	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int octeon_sha224_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA256_DIGEST_SIZE];
-
-	octeon_sha256_final(desc, D);
 
-	memcpy(hash, D, SHA224_DIGEST_SIZE);
-	memzero_explicit(D, SHA256_DIGEST_SIZE);
-
-	return 0;
-}
-
-static int octeon_sha256_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int octeon_sha256_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg octeon_sha256_algs[2] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	octeon_sha256_update,
-	.final		=	octeon_sha256_final,
-	.export		=	octeon_sha256_export,
-	.import		=	octeon_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"octeon-sha256",
-		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	octeon_sha256_update,
-	.final		=	octeon_sha224_final,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"octeon-sha224",
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init octeon_sha256_mod_init(void)
-{
 	if (!octeon_has_crypto())
-		return -ENOTSUPP;
-	return crypto_register_shashes(octeon_sha256_algs,
-				       ARRAY_SIZE(octeon_sha256_algs));
+		return sha256_blocks_generic(state, data, nblocks);
+
+	flags = octeon_crypto_enable(&cop2_state);
+	write_octeon_64bit_hash_dword(state64[0], 0);
+	write_octeon_64bit_hash_dword(state64[1], 1);
+	write_octeon_64bit_hash_dword(state64[2], 2);
+	write_octeon_64bit_hash_dword(state64[3], 3);
+
+	do {
+		const u64 *block = (const u64 *)data;
+
+		write_octeon_64bit_block_dword(block[0], 0);
+		write_octeon_64bit_block_dword(block[1], 1);
+		write_octeon_64bit_block_dword(block[2], 2);
+		write_octeon_64bit_block_dword(block[3], 3);
+		write_octeon_64bit_block_dword(block[4], 4);
+		write_octeon_64bit_block_dword(block[5], 5);
+		write_octeon_64bit_block_dword(block[6], 6);
+		octeon_sha256_start(block[7]);
+
+		data += SHA256_BLOCK_SIZE;
+	} while (--nblocks);
+
+	state64[0] = read_octeon_64bit_hash_dword(0);
+	state64[1] = read_octeon_64bit_hash_dword(1);
+	state64[2] = read_octeon_64bit_hash_dword(2);
+	state64[3] = read_octeon_64bit_hash_dword(3);
+	octeon_crypto_disable(&cop2_state, flags);
 }
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
 
-static void __exit octeon_sha256_mod_fini(void)
+bool sha256_is_arch_optimized(void)
 {
-	crypto_unregister_shashes(octeon_sha256_algs,
-				  ARRAY_SIZE(octeon_sha256_algs));
+	return octeon_has_crypto();
 }
-
-module_init(octeon_sha256_mod_init);
-module_exit(octeon_sha256_mod_fini);
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm (OCTEON)");
+MODULE_DESCRIPTION("SHA-256 Secure Hash Algorithm (OCTEON)");
 MODULE_AUTHOR("Aaro Koskinen <aaro.koskinen@iki.fi>");
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha512.c b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
index 2dee9354e33f..215311053db3 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha512.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
@@ -13,15 +13,12 @@
  * Copyright (c) 2003 Kyle McMartin <kyle@debian.org>
  */
 
-#include <linux/mm.h>
+#include <asm/octeon/octeon.h>
+#include <crypto/internal/hash.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <linux/init.h>
-#include <linux/types.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/byteorder.h>
-#include <asm/octeon/octeon.h>
-#include <crypto/internal/hash.h>
 
 #include "octeon-crypto.h"
 
@@ -53,60 +50,31 @@ static void octeon_sha512_read_hash(struct sha512_state *sctx)
 	sctx->state[7] = read_octeon_64bit_hash_sha512(7);
 }
 
-static void octeon_sha512_transform(const void *_block)
+static void octeon_sha512_transform(struct sha512_state *sctx,
+				    const u8 *src, int blocks)
 {
-	const u64 *block = _block;
-
-	write_octeon_64bit_block_sha512(block[0], 0);
-	write_octeon_64bit_block_sha512(block[1], 1);
-	write_octeon_64bit_block_sha512(block[2], 2);
-	write_octeon_64bit_block_sha512(block[3], 3);
-	write_octeon_64bit_block_sha512(block[4], 4);
-	write_octeon_64bit_block_sha512(block[5], 5);
-	write_octeon_64bit_block_sha512(block[6], 6);
-	write_octeon_64bit_block_sha512(block[7], 7);
-	write_octeon_64bit_block_sha512(block[8], 8);
-	write_octeon_64bit_block_sha512(block[9], 9);
-	write_octeon_64bit_block_sha512(block[10], 10);
-	write_octeon_64bit_block_sha512(block[11], 11);
-	write_octeon_64bit_block_sha512(block[12], 12);
-	write_octeon_64bit_block_sha512(block[13], 13);
-	write_octeon_64bit_block_sha512(block[14], 14);
-	octeon_sha512_start(block[15]);
-}
-
-static void __octeon_sha512_update(struct sha512_state *sctx, const u8 *data,
-				   unsigned int len)
-{
-	unsigned int part_len;
-	unsigned int index;
-	unsigned int i;
-
-	/* Compute number of bytes mod 128. */
-	index = sctx->count[0] % SHA512_BLOCK_SIZE;
-
-	/* Update number of bytes. */
-	if ((sctx->count[0] += len) < len)
-		sctx->count[1]++;
-
-	part_len = SHA512_BLOCK_SIZE - index;
-
-	/* Transform as many times as possible. */
-	if (len >= part_len) {
-		memcpy(&sctx->buf[index], data, part_len);
-		octeon_sha512_transform(sctx->buf);
-
-		for (i = part_len; i + SHA512_BLOCK_SIZE <= len;
-			i += SHA512_BLOCK_SIZE)
-			octeon_sha512_transform(&data[i]);
-
-		index = 0;
-	} else {
-		i = 0;
-	}
-
-	/* Buffer remaining input. */
-	memcpy(&sctx->buf[index], &data[i], len - i);
+	do {
+		const u64 *block = (const u64 *)src;
+
+		write_octeon_64bit_block_sha512(block[0], 0);
+		write_octeon_64bit_block_sha512(block[1], 1);
+		write_octeon_64bit_block_sha512(block[2], 2);
+		write_octeon_64bit_block_sha512(block[3], 3);
+		write_octeon_64bit_block_sha512(block[4], 4);
+		write_octeon_64bit_block_sha512(block[5], 5);
+		write_octeon_64bit_block_sha512(block[6], 6);
+		write_octeon_64bit_block_sha512(block[7], 7);
+		write_octeon_64bit_block_sha512(block[8], 8);
+		write_octeon_64bit_block_sha512(block[9], 9);
+		write_octeon_64bit_block_sha512(block[10], 10);
+		write_octeon_64bit_block_sha512(block[11], 11);
+		write_octeon_64bit_block_sha512(block[12], 12);
+		write_octeon_64bit_block_sha512(block[13], 13);
+		write_octeon_64bit_block_sha512(block[14], 14);
+		octeon_sha512_start(block[15]);
+
+		src += SHA512_BLOCK_SIZE;
+	} while (--blocks);
 }
 
 static int octeon_sha512_update(struct shash_desc *desc, const u8 *data,
@@ -115,89 +83,48 @@ static int octeon_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct octeon_cop2_state state;
 	unsigned long flags;
-
-	/*
-	 * Small updates never reach the crypto engine, so the generic sha512 is
-	 * faster because of the heavyweight octeon_crypto_enable() /
-	 * octeon_crypto_disable().
-	 */
-	if ((sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
-		return crypto_sha512_update(desc, data, len);
+	int remain;
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha512_store_hash(sctx);
 
-	__octeon_sha512_update(sctx, data, len);
+	remain = sha512_base_do_update_blocks(desc, data, len,
+					      octeon_sha512_transform);
 
 	octeon_sha512_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	return 0;
+	return remain;
 }
 
-static int octeon_sha512_final(struct shash_desc *desc, u8 *hash)
+static int octeon_sha512_finup(struct shash_desc *desc, const u8 *src,
+			       unsigned int len, u8 *hash)
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
-	static u8 padding[128] = { 0x80, };
 	struct octeon_cop2_state state;
-	__be64 *dst = (__be64 *)hash;
-	unsigned int pad_len;
 	unsigned long flags;
-	unsigned int index;
-	__be64 bits[2];
-	int i;
-
-	/* Save number of bits. */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128. */
-	index = sctx->count[0] & 0x7f;
-	pad_len = (index < 112) ? (112 - index) : ((128+112) - index);
 
 	flags = octeon_crypto_enable(&state);
 	octeon_sha512_store_hash(sctx);
 
-	__octeon_sha512_update(sctx, padding, pad_len);
-
-	/* Append length (before padding). */
-	__octeon_sha512_update(sctx, (const u8 *)bits, sizeof(bits));
+	sha512_base_do_finup(desc, src, len, octeon_sha512_transform);
 
 	octeon_sha512_read_hash(sctx);
 	octeon_crypto_disable(&state, flags);
-
-	/* Store state in digest. */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(struct sha512_state));
-
-	return 0;
-}
-
-static int octeon_sha384_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[64];
-
-	octeon_sha512_final(desc, D);
-
-	memcpy(hash, D, 48);
-	memzero_explicit(D, 64);
-
-	return 0;
+	return sha512_base_finish(desc, hash);
 }
 
 static struct shash_alg octeon_sha512_algs[2] = { {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	octeon_sha512_update,
-	.final		=	octeon_sha512_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	octeon_sha512_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"octeon-sha512",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -205,12 +132,14 @@ static struct shash_alg octeon_sha512_algs[2] = { {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	octeon_sha512_update,
-	.final		=	octeon_sha384_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	octeon_sha512_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"octeon-sha384",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 8425a6b38aa2..5c3de175ef5b 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1503,9 +1503,9 @@ static int __init octeon_irq_init_ciu(
 	/* Mips internal */
 	octeon_irq_init_core();
 
-	ciu_domain = irq_domain_add_tree(
-		ciu_node, &octeon_irq_domain_ciu_ops, dd);
-	irq_set_default_host(ciu_domain);
+	ciu_domain = irq_domain_create_tree(of_fwnode_handle(ciu_node), &octeon_irq_domain_ciu_ops,
+					    dd);
+	irq_set_default_domain(ciu_domain);
 
 	/* CIU_0 */
 	for (i = 0; i < 16; i++) {
@@ -1637,8 +1637,8 @@ static int __init octeon_irq_init_gpio(
 	if (gpiod) {
 		/* gpio domain host_data is the base hwirq number. */
 		gpiod->base_hwirq = base_hwirq;
-		irq_domain_add_linear(
-			gpio_node, 16, &octeon_irq_domain_gpio_ops, gpiod);
+		irq_domain_create_linear(of_fwnode_handle(gpio_node), 16,
+					 &octeon_irq_domain_gpio_ops, gpiod);
 	} else {
 		pr_warn("Cannot allocate memory for GPIO irq_domain.\n");
 		return -ENOMEM;
@@ -2074,9 +2074,9 @@ static int __init octeon_irq_init_ciu2(
 	/* Mips internal */
 	octeon_irq_init_core();
 
-	ciu_domain = irq_domain_add_tree(
-		ciu_node, &octeon_irq_domain_ciu2_ops, NULL);
-	irq_set_default_host(ciu_domain);
+	ciu_domain = irq_domain_create_tree(of_fwnode_handle(ciu_node), &octeon_irq_domain_ciu2_ops,
+					    NULL);
+	irq_set_default_domain(ciu_domain);
 
 	/* CUI2 */
 	for (i = 0; i < 64; i++) {
@@ -2331,11 +2331,12 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node,
 	}
 	host_data->max_bits = val;
 
-	cib_domain = irq_domain_add_linear(ciu_node, host_data->max_bits,
-					   &octeon_irq_domain_cib_ops,
-					   host_data);
+	cib_domain = irq_domain_create_linear(of_fwnode_handle(ciu_node),
+					      host_data->max_bits,
+					      &octeon_irq_domain_cib_ops,
+					      host_data);
 	if (!cib_domain) {
-		pr_err("ERROR: Couldn't irq_domain_add_linear()\n");
+		pr_err("ERROR: Couldn't irq_domain_create_linear()\n");
 		return -ENOMEM;
 	}
 
@@ -2918,8 +2919,8 @@ static int __init octeon_irq_init_ciu3(struct device_node *ciu_node,
 	 * Initialize all domains to use the default domain. Specific major
 	 * blocks will overwrite the default domain as needed.
 	 */
-	domain = irq_domain_add_tree(ciu_node, &octeon_dflt_domain_ciu3_ops,
-				     ciu3_info);
+	domain = irq_domain_create_tree(of_fwnode_handle(ciu_node), &octeon_dflt_domain_ciu3_ops,
+					ciu3_info);
 	for (i = 0; i < MAX_CIU3_DOMAINS; i++)
 		ciu3_info->domain[i] = domain;
 
@@ -2929,7 +2930,7 @@ static int __init octeon_irq_init_ciu3(struct device_node *ciu_node,
 		/* Only do per CPU things if it is the CIU of the boot node. */
 		octeon_irq_ciu3_alloc_resources(ciu3_info);
 		if (node == 0)
-			irq_set_default_host(domain);
+			irq_set_default_domain(domain);
 
 		octeon_irq_use_ip4 = false;
 		/* Enable the CIU lines */
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 8caa03a41327..cba0b85c6707 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -82,7 +82,6 @@ CONFIG_LEDS_GPIO=y
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_PROC_PAGE_MONITOR is not set
-CONFIG_CRC_ITU_T=m
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/bcm47xx_defconfig b/arch/mips/configs/bcm47xx_defconfig
index 6a68a96d13f8..f56e8db5da95 100644
--- a/arch/mips/configs/bcm47xx_defconfig
+++ b/arch/mips/configs/bcm47xx_defconfig
@@ -69,7 +69,6 @@ CONFIG_USB_HCD_BCMA=y
 CONFIG_USB_HCD_SSB=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_CRC32_SARWATE=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_INFO_REDUCED=y
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index f7c4b3529a2c..8f7c36868204 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -238,8 +238,6 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
-CONFIG_CRC7=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig
index f523ee6f25bf..88ae0aa85364 100644
--- a/arch/mips/configs/cavium_octeon_defconfig
+++ b/arch/mips/configs/cavium_octeon_defconfig
@@ -157,7 +157,6 @@ CONFIG_CRYPTO_CBC=y
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5_OCTEON=y
 CONFIG_CRYPTO_SHA1_OCTEON=m
-CONFIG_CRYPTO_SHA256_OCTEON=m
 CONFIG_CRYPTO_SHA512_OCTEON=m
 CONFIG_CRYPTO_DES=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/mips/configs/cobalt_defconfig b/arch/mips/configs/cobalt_defconfig
index e835730ea7fa..b0b551efac7c 100644
--- a/arch/mips/configs/cobalt_defconfig
+++ b/arch/mips/configs/cobalt_defconfig
@@ -70,4 +70,3 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3_ACL=y
-CONFIG_LIBCRC32C=y
diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig
index 6eff21ff15d5..281dd7d0f805 100644
--- a/arch/mips/configs/db1xxx_defconfig
+++ b/arch/mips/configs/db1xxx_defconfig
@@ -216,7 +216,6 @@ CONFIG_CRYPTO_USER=y
 CONFIG_CRYPTO_CRYPTD=y
 CONFIG_CRYPTO_USER_API_HASH=y
 CONFIG_CRYPTO_USER_API_SKCIPHER=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/mips/configs/decstation_64_defconfig b/arch/mips/configs/decstation_64_defconfig
index da51b9731db0..85a4472cb058 100644
--- a/arch/mips/configs/decstation_64_defconfig
+++ b/arch/mips/configs/decstation_64_defconfig
@@ -168,7 +168,6 @@ CONFIG_NLS_ISO8859_14=m
 CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_UTF8=m
 CONFIG_CRYPTO_RSA=m
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -180,7 +179,6 @@ CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig
index 424e3f011fc2..a3b2c8da2dde 100644
--- a/arch/mips/configs/decstation_defconfig
+++ b/arch/mips/configs/decstation_defconfig
@@ -163,7 +163,6 @@ CONFIG_NLS_ISO8859_14=m
 CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_UTF8=m
 CONFIG_CRYPTO_RSA=m
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -175,7 +174,6 @@ CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig
index cfc8bf791792..a476717b8a6a 100644
--- a/arch/mips/configs/decstation_r4k_defconfig
+++ b/arch/mips/configs/decstation_r4k_defconfig
@@ -163,7 +163,6 @@ CONFIG_NLS_ISO8859_14=m
 CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_UTF8=m
 CONFIG_CRYPTO_RSA=m
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -175,7 +174,6 @@ CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 00329bb5de5a..114fcd67898d 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -218,5 +218,3 @@ CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_DEFLATE=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC7=m
diff --git a/arch/mips/configs/gcw0_defconfig b/arch/mips/configs/gcw0_defconfig
index bc1ef66e3999..8b7ad877e07a 100644
--- a/arch/mips/configs/gcw0_defconfig
+++ b/arch/mips/configs/gcw0_defconfig
@@ -13,7 +13,6 @@ CONFIG_MIPS_CMDLINE_DTB_EXTEND=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_BOUNCE is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig
index 92fc0edbac47..48c8feec958f 100644
--- a/arch/mips/configs/gpr_defconfig
+++ b/arch/mips/configs/gpr_defconfig
@@ -116,7 +116,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -274,7 +273,7 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_CRYPTO_AUTHENC=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index e22e8b825903..f1a8ccf2c459 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -161,7 +161,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -327,5 +326,4 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=m
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index b08a199767d1..5d079941fd20 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -63,7 +63,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -255,9 +254,6 @@ CONFIG_I2C_TAOS_EVM=m
 CONFIG_I2C_STUB=m
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
-CONFIG_MFD_PCF50633=m
-CONFIG_PCF50633_ADC=m
-CONFIG_PCF50633_GPIO=m
 # CONFIG_VGA_ARB is not set
 CONFIG_LEDS_LP3944=m
 CONFIG_LEDS_PCA955X=m
@@ -321,4 +317,3 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
diff --git a/arch/mips/configs/ip28_defconfig b/arch/mips/configs/ip28_defconfig
index e0040110a3ee..6db21e498faa 100644
--- a/arch/mips/configs/ip28_defconfig
+++ b/arch/mips/configs/ip28_defconfig
@@ -60,6 +60,5 @@ CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRYPTO_MANAGER=y
 # CONFIG_CRYPTO_HW is not set
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/mips/configs/ip30_defconfig b/arch/mips/configs/ip30_defconfig
index 270181a7320a..a4524e785469 100644
--- a/arch/mips/configs/ip30_defconfig
+++ b/arch/mips/configs/ip30_defconfig
@@ -179,4 +179,3 @@ CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_T10DIF=m
diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig
index 930c5f6ed182..d8ac11427f69 100644
--- a/arch/mips/configs/ip32_defconfig
+++ b/arch/mips/configs/ip32_defconfig
@@ -177,8 +177,6 @@ CONFIG_CRYPTO_SERPENT=y
 CONFIG_CRYPTO_TEA=y
 CONFIG_CRYPTO_TWOFISH=y
 CONFIG_CRYPTO_DEFLATE=y
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 71d6340497c9..5038a27d035f 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -297,7 +297,7 @@ CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 4390d30206d9..869a14b3184f 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -190,7 +190,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -347,7 +346,6 @@ CONFIG_CRAMFS=m
 CONFIG_VXFS_FS=m
 CONFIG_MINIX_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index d63d8be8cb50..41e1fea303ea 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -194,7 +194,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -354,7 +353,6 @@ CONFIG_CRAMFS=m
 CONFIG_VXFS_FS=m
 CONFIG_MINIX_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index b21f48863d81..1b98f6945c2d 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -64,7 +64,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index ecfa8a396c33..7b8905cb3400 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -66,7 +66,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index 5cb4f262a4ea..8249f6a51895 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -67,7 +67,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 5e1498296782..21cb37668763 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -68,7 +68,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index c8594505d676..3df9cd669683 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -65,7 +65,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 338bb6544a93..13ff1877e26e 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -191,7 +191,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -353,7 +352,6 @@ CONFIG_CRAMFS=m
 CONFIG_VXFS_FS=m
 CONFIG_MINIX_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 8e98c0796437..cbf9c35a6177 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -162,7 +162,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -663,7 +662,7 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5=y
diff --git a/arch/mips/configs/omega2p_defconfig b/arch/mips/configs/omega2p_defconfig
index 7c1c1b974d8f..e2bcdfd290a1 100644
--- a/arch/mips/configs/omega2p_defconfig
+++ b/arch/mips/configs/omega2p_defconfig
@@ -61,6 +61,7 @@ CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_MMC=y
+CONFIG_CLK_MTMIPS=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_MEMORY=y
 CONFIG_PHY_RALINK_USB=y
@@ -110,7 +111,6 @@ CONFIG_NLS_KOI8_U=y
 CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
-CONFIG_CRC16=y
 CONFIG_XZ_DEC=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 517f1b060bf4..9fb114ef5e2d 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -77,7 +77,6 @@ CONFIG_NET_SCH_CBQ=m
 CONFIG_NET_SCH_PRIO=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -154,7 +153,6 @@ CONFIG_JFFS2_FS=y
 CONFIG_JFFS2_SUMMARY=y
 CONFIG_JFFS2_COMPRESSION_OPTIONS=y
 CONFIG_SQUASHFS=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=m
 CONFIG_STRIP_ASM_SYMS=y
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 08e1c1f2f4de..7b5a5591ccc9 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -143,7 +143,6 @@ CONFIG_NET_SCH_GRED=m
 CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -336,7 +335,6 @@ CONFIG_MINIX_FS=m
 CONFIG_HPFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=m
 CONFIG_NFSD=m
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index 332f9094e847..8f9701efef19 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -128,8 +128,6 @@ CONFIG_SQUASHFS=y
 # CONFIG_SQUASHFS_ZLIB is not set
 CONFIG_SQUASHFS_XZ=y
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRC_ITU_T=m
-CONFIG_CRC32_SARWATE=y
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_POWERPC is not set
 # CONFIG_XZ_DEC_IA64 is not set
diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig
index ce855b644bb0..ae2afff00e01 100644
--- a/arch/mips/configs/sb1250_swarm_defconfig
+++ b/arch/mips/configs/sb1250_swarm_defconfig
@@ -99,4 +99,3 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_DEFLATE=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=m
diff --git a/arch/mips/configs/vocore2_defconfig b/arch/mips/configs/vocore2_defconfig
index 7c8ebb1b56da..2a9a9b12847d 100644
--- a/arch/mips/configs/vocore2_defconfig
+++ b/arch/mips/configs/vocore2_defconfig
@@ -61,6 +61,7 @@ CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_MMC=y
+CONFIG_CLK_MTMIPS=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_MEMORY=y
 CONFIG_PHY_RALINK_USB=y
@@ -110,7 +111,6 @@ CONFIG_NLS_KOI8_U=y
 CONFIG_NLS_UTF8=y
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
-CONFIG_CRC16=y
 CONFIG_XZ_DEC=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
index 08c0aa03fd56..aae8497b6872 100644
--- a/arch/mips/configs/xway_defconfig
+++ b/arch/mips/configs/xway_defconfig
@@ -140,8 +140,6 @@ CONFIG_SQUASHFS=y
 # CONFIG_SQUASHFS_ZLIB is not set
 CONFIG_SQUASHFS_XZ=y
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRC_ITU_T=m
-CONFIG_CRC32_SARWATE=y
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/mips/crypto/Kconfig b/arch/mips/crypto/Kconfig
index 7decd40c4e20..6bf073ae7613 100644
--- a/arch/mips/crypto/Kconfig
+++ b/arch/mips/crypto/Kconfig
@@ -2,15 +2,6 @@
 
 menu "Accelerated Cryptographic Algorithms for CPU (mips)"
 
-config CRYPTO_POLY1305_MIPS
-	tristate "Hash functions: Poly1305"
-	depends on MIPS
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
-	help
-	  Poly1305 authenticator algorithm (RFC7539)
-
-	  Architecture: mips
-
 config CRYPTO_MD5_OCTEON
 	tristate "Digests: MD5 (OCTEON)"
 	depends on CPU_CAVIUM_OCTEON
@@ -31,16 +22,6 @@ config CRYPTO_SHA1_OCTEON
 
 	  Architecture: mips OCTEON
 
-config CRYPTO_SHA256_OCTEON
-	tristate "Hash functions: SHA-224 and SHA-256 (OCTEON)"
-	depends on CPU_CAVIUM_OCTEON
-	select CRYPTO_SHA256
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: mips OCTEON using crypto instructions, when available
-
 config CRYPTO_SHA512_OCTEON
 	tristate "Hash functions: SHA-384 and SHA-512 (OCTEON)"
 	depends on CPU_CAVIUM_OCTEON
@@ -51,15 +32,4 @@ config CRYPTO_SHA512_OCTEON
 
 	  Architecture: mips OCTEON using crypto instructions, when available
 
-config CRYPTO_CHACHA_MIPS
-	tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (MIPS32r2)"
-	depends on CPU_MIPS32_R2
-	select CRYPTO_SKCIPHER
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
-	  stream cipher algorithms
-
-	  Architecture: MIPS32r2
-
 endmenu
diff --git a/arch/mips/crypto/Makefile b/arch/mips/crypto/Makefile
index fddc88281412..5adb631a69c1 100644
--- a/arch/mips/crypto/Makefile
+++ b/arch/mips/crypto/Makefile
@@ -3,20 +3,3 @@
 # Makefile for MIPS crypto files..
 #
 
-obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o
-chacha-mips-y := chacha-core.o chacha-glue.o
-AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
-
-obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
-poly1305-mips-y := poly1305-core.o poly1305-glue.o
-
-perlasm-flavour-$(CONFIG_32BIT) := o32
-perlasm-flavour-$(CONFIG_64BIT) := 64
-
-quiet_cmd_perlasm = PERLASM $@
-      cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
-
-$(obj)/poly1305-core.S: $(src)/poly1305-mips.pl FORCE
-	$(call if_changed,perlasm)
-
-targets += poly1305-core.S
diff --git a/arch/mips/crypto/chacha-glue.c b/arch/mips/crypto/chacha-glue.c
deleted file mode 100644
index d1fd23e6ef84..000000000000
--- a/arch/mips/crypto/chacha-glue.c
+++ /dev/null
@@ -1,152 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * MIPS accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/byteorder.h>
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-asmlinkage void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
-				  unsigned int bytes, int nrounds);
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-asmlinkage void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds);
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-static int chacha_mips_stream_xor(struct skcipher_request *req,
-				  const struct chacha_ctx *ctx, const u8 *iv)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	chacha_init_generic(state, ctx->key, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		chacha_crypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-			     nbytes, ctx->nrounds);
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha_mips(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return chacha_mips_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_mips(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 state[16];
-	u8 real_iv[16];
-
-	chacha_init_generic(state, ctx->key, req->iv);
-
-	hchacha_block(state, subctx.key, ctx->nrounds);
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_mips_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-mips",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_mips,
-		.decrypt		= chacha_mips,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-mips",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_mips,
-		.decrypt		= xchacha_mips,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-mips",
-		.base.cra_priority	= 200,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_mips,
-		.decrypt		= xchacha_mips,
-	}
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
-		crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER))
-		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (MIPS accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-mips");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-mips");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-mips");
diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c
deleted file mode 100644
index c03ad0bbe69c..000000000000
--- a/arch/mips/crypto/poly1305-glue.c
+++ /dev/null
@@ -1,192 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <linux/unaligned.h>
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/module.h>
-
-asmlinkage void poly1305_init_mips(void *state, const u8 *key);
-asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce);
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	poly1305_init_mips(&dctx->h, key);
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static int mips_poly1305_init(struct shash_desc *desc)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	dctx->buflen = 0;
-	dctx->rset = 0;
-	dctx->sset = false;
-
-	return 0;
-}
-
-static void mips_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
-				 u32 len, u32 hibit)
-{
-	if (unlikely(!dctx->sset)) {
-		if (!dctx->rset) {
-			poly1305_init_mips(&dctx->h, src);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (len >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(src +  0);
-			dctx->s[1] = get_unaligned_le32(src +  4);
-			dctx->s[2] = get_unaligned_le32(src +  8);
-			dctx->s[3] = get_unaligned_le32(src + 12);
-			src += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-		if (len < POLY1305_BLOCK_SIZE)
-			return;
-	}
-
-	len &= ~(POLY1305_BLOCK_SIZE - 1);
-
-	poly1305_blocks_mips(&dctx->h, src, len, hibit);
-}
-
-static int mips_poly1305_update(struct shash_desc *desc, const u8 *src,
-				unsigned int len)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		len -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			mips_poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(len >= POLY1305_BLOCK_SIZE)) {
-		mips_poly1305_blocks(dctx, src, len, 1);
-		src += round_down(len, POLY1305_BLOCK_SIZE);
-		len %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(len)) {
-		dctx->buflen = len;
-		memcpy(dctx->buf, src, len);
-	}
-	return 0;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_mips(&dctx->h, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
-
-		poly1305_blocks_mips(&dctx->h, src, len, 1);
-		src += len;
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_mips(&dctx->h, dst, dctx->s);
-	*dctx = (struct poly1305_desc_ctx){};
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int mips_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(!dctx->sset))
-		return -ENOKEY;
-
-	poly1305_final_arch(dctx, dst);
-	return 0;
-}
-
-static struct shash_alg mips_poly1305_alg = {
-	.init			= mips_poly1305_init,
-	.update			= mips_poly1305_update,
-	.final			= mips_poly1305_final,
-	.digestsize		= POLY1305_DIGEST_SIZE,
-	.descsize		= sizeof(struct poly1305_desc_ctx),
-
-	.base.cra_name		= "poly1305",
-	.base.cra_driver_name	= "poly1305-mips",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-};
-
-static int __init mips_poly1305_mod_init(void)
-{
-	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
-		crypto_register_shash(&mips_poly1305_alg) : 0;
-}
-
-static void __exit mips_poly1305_mod_exit(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
-		crypto_unregister_shash(&mips_poly1305_alg);
-}
-
-module_init(mips_poly1305_mod_init);
-module_exit(mips_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Poly1305 transform (MIPS accelerated");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-mips");
diff --git a/arch/mips/dec/prom/init.c b/arch/mips/dec/prom/init.c
index cb12eb211a49..8d74d7d6c05b 100644
--- a/arch/mips/dec/prom/init.c
+++ b/arch/mips/dec/prom/init.c
@@ -42,7 +42,7 @@ int (*__pmax_close)(int);
  * Detect which PROM the DECSTATION has, and set the callback vectors
  * appropriately.
  */
-void __init which_prom(s32 magic, s32 *prom_vec)
+static void __init which_prom(s32 magic, s32 *prom_vec)
 {
 	/*
 	 * No sign of the REX PROM's magic number means we assume a non-REX
diff --git a/arch/mips/include/asm/ds1287.h b/arch/mips/include/asm/ds1287.h
index 46cfb01f9a14..51cb61fd4c03 100644
--- a/arch/mips/include/asm/ds1287.h
+++ b/arch/mips/include/asm/ds1287.h
@@ -8,7 +8,7 @@
 #define __ASM_DS1287_H
 
 extern int ds1287_timer_state(void);
-extern void ds1287_set_base_clock(unsigned int clock);
+extern int ds1287_set_base_clock(unsigned int hz);
 extern int ds1287_clockevent_init(int irq);
 
 #endif
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index dc025888f6d2..b41fc1044668 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -91,4 +91,20 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+#ifndef __ASSEMBLY__
+/*
+ * Some syscall entry functions on mips start with "__sys_" (fork and clone,
+ * for instance). We should also match the sys_ variant with those.
+ */
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym,
+					       const char *name)
+{
+	return !strcmp(sym, name) ||
+		(!strncmp(sym, "__sys_", 6) && !strcmp(sym + 6, name + 4));
+}
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FTRACE_SYSCALLS */
 #endif /* _ASM_MIPS_FTRACE_H */
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index d0a86ce83de9..fbc71ddcf0f6 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index 0992cad9c632..c7d75807d13f 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -6,11 +6,10 @@
 #include <linux/linkage.h>
 
 extern void (*cpu_wait)(void);
-extern void r4k_wait(void);
-extern asmlinkage void __r4k_wait(void);
+extern asmlinkage void r4k_wait(void);
 extern void r4k_wait_irqoff(void);
 
-static inline int using_rollback_handler(void)
+static inline int using_skipover_handler(void)
 {
 	return cpu_wait == r4k_wait;
 }
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 0bddb568af7c..980187a83053 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -67,17 +67,6 @@ static inline void set_io_port_base(unsigned long base)
 }
 
 /*
- * Provide the necessary definitions for generic iomap. We make use of
- * mips_io_port_base for iomap(), but we don't reserve any low addresses for
- * use with I/O ports.
- */
-
-#define HAVE_ARCH_PIO_SIZE
-#define PIO_OFFSET	mips_io_port_base
-#define PIO_MASK	IO_SPACE_LIMIT
-#define PIO_RESERVED	0x0UL
-
-/*
  * Enforce in-order execution of data I/O.  In the MIPS architecture
  * these are equivalent to corresponding platform-specific memory
  * barriers defined in <asm/barrier.h>.  API pinched from PowerPC,
@@ -126,7 +115,7 @@ static inline unsigned long isa_virt_to_bus(volatile void *address)
 }
 
 void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
-		unsigned long prot_val);
+			   pgprot_t prot);
 void iounmap(const volatile void __iomem *addr);
 
 /*
@@ -141,7 +130,7 @@ void iounmap(const volatile void __iomem *addr);
  * address.
  */
 #define ioremap(offset, size)						\
-	ioremap_prot((offset), (size), _CACHE_UNCACHED)
+	ioremap_prot((offset), (size), __pgprot(_CACHE_UNCACHED))
 
 /*
  * ioremap_cache -	map bus memory into CPU space
@@ -159,7 +148,7 @@ void iounmap(const volatile void __iomem *addr);
  * memory-like regions on I/O busses.
  */
 #define ioremap_cache(offset, size)					\
-	ioremap_prot((offset), (size), _page_cachable_default)
+	ioremap_prot((offset), (size), __pgprot(_page_cachable_default))
 
 /*
  * ioremap_wc     -   map bus memory into CPU space
@@ -180,7 +169,7 @@ void iounmap(const volatile void __iomem *addr);
  * _CACHE_UNCACHED option (see cpu_probe() method).
  */
 #define ioremap_wc(offset, size)					\
-	ioremap_prot((offset), (size), boot_cpu_data.writecombine)
+	ioremap_prot((offset), (size), __pgprot(boot_cpu_data.writecombine))
 
 #if defined(CONFIG_CPU_CAVIUM_OCTEON)
 #define war_io_reorder_wmb()		wmb()
@@ -397,8 +386,8 @@ static inline void writes##bwlq(volatile void __iomem *mem,		\
 	}								\
 }									\
 									\
-static inline void reads##bwlq(volatile void __iomem *mem, void *addr,	\
-			       unsigned int count)			\
+static inline void reads##bwlq(const volatile void __iomem *mem,	\
+			       void *addr, unsigned int count)		\
 {									\
 	volatile type *__addr = addr;					\
 									\
@@ -555,6 +544,16 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 
 void __ioread64_copy(void *to, const void __iomem *from, size_t count);
 
+#if defined(CONFIG_PCI) && defined(CONFIG_PCI_DRIVERS_LEGACY)
+struct pci_dev;
+void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
+#define pci_iounmap pci_iounmap
+#endif
+
+#ifndef PCI_IOBASE
+#define PCI_IOBASE ((void __iomem *)mips_io_port_base)
+#endif
+
 #include <asm-generic/io.h>
 
 static inline void *isa_bus_to_virt(unsigned long address)
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index f7222eb594ea..c14b10821817 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -886,7 +886,6 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 extern int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 			     struct kvm_mips_interrupt *irq);
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 					 struct kvm_memory_slot *slot) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
diff --git a/arch/mips/include/asm/mach-loongson64/spaces.h b/arch/mips/include/asm/mach-loongson64/spaces.h
index ce04e998a37b..dbd26db5f2c5 100644
--- a/arch/mips/include/asm/mach-loongson64/spaces.h
+++ b/arch/mips/include/asm/mach-loongson64/spaces.h
@@ -7,9 +7,10 @@
 #endif /* CONFIG_64BIT */
 
 /* Skip 128k to trap NULL pointer dereferences */
-#define PCI_IOBASE	_AC(0xc000000000000000 + SZ_128K, UL)
+#define PCI_PORT_BASE	_AC(0xc000000000000000 + SZ_128K, UL)
+#define PCI_IOBASE	(void __iomem *)PCI_PORT_BASE
 #define PCI_IOSIZE	SZ_16M
-#define MAP_BASE	(PCI_IOBASE + PCI_IOSIZE)
+#define MAP_BASE	(PCI_PORT_BASE + PCI_IOSIZE)
 
 #define IO_SPACE_LIMIT  (PCI_IOSIZE - 1)
 
diff --git a/arch/mips/include/asm/mach-ralink/spaces.h b/arch/mips/include/asm/mach-ralink/spaces.h
index a9f0570d0f04..a63d106c89c6 100644
--- a/arch/mips/include/asm/mach-ralink/spaces.h
+++ b/arch/mips/include/asm/mach-ralink/spaces.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_MACH_RALINK_SPACES_H_
 #define __ASM_MACH_RALINK_SPACES_H_
 
-#define PCI_IOBASE	mips_io_port_base
+#define PCI_IOBASE	(void __iomem *)mips_io_port_base
 #define PCI_IOSIZE	SZ_64K
 #define IO_SPACE_LIMIT	(PCI_IOSIZE - 1)
 
diff --git a/arch/mips/include/asm/mach-rc32434/pci.h b/arch/mips/include/asm/mach-rc32434/pci.h
index 3eb767c8a4ee..e17ce82d02ba 100644
--- a/arch/mips/include/asm/mach-rc32434/pci.h
+++ b/arch/mips/include/asm/mach-rc32434/pci.h
@@ -167,7 +167,7 @@ struct pci_msu {
 #define PCI_CFGA_DEV		0x0000f800
 #define PCI_CFGA_DEV_INTERN	0
 #define PCI_CFGA_BUS_BIT	16
-#define PCI CFGA_BUS		0x00ff0000
+#define PCI_CFGA_BUS		0x00ff0000
 #define PCI_CFGA_BUS_TYPE0	0
 #define PCI_CFGA_EN		(1 << 31)
 
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 23ce951f445b..407f253bb4a1 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -59,6 +59,16 @@ extern phys_addr_t mips_cm_l2sync_phys_base(void);
  */
 extern int mips_cm_is64;
 
+/*
+ * mips_cm_is_l2_hci_broken  - determine if HCI is broken
+ *
+ * Some CM reports show that Hardware Cache Initialization is
+ * complete, but in reality it's not the case. They also incorrectly
+ * indicate that Hardware Cache Initialization is supported. This
+ * flags allows warning about this broken feature.
+ */
+extern bool mips_cm_is_l2_hci_broken;
+
 /**
  * mips_cm_error_report - Report CM cache errors
  */
@@ -98,6 +108,18 @@ static inline bool mips_cm_present(void)
 }
 
 /**
+ * mips_cm_update_property - update property from the device tree
+ *
+ * Retrieve the properties from the device tree if a CM node exist and
+ * update the internal variable based on this.
+ */
+#ifdef CONFIG_MIPS_CM
+extern void mips_cm_update_property(void);
+#else
+static inline void mips_cm_update_property(void) {}
+#endif
+
+/**
  * mips_cm_has_l2sync - determine whether an L2-only sync region is present
  *
  * Returns true if the system implements an L2-only sync region, else false.
@@ -255,6 +277,12 @@ GCR_ACCESSOR_RW(32, 0x130, l2_config)
 GCR_ACCESSOR_RO(32, 0x150, sys_config2)
 #define CM_GCR_SYS_CONFIG2_MAXVPW		GENMASK(3, 0)
 
+/* GCR_L2-RAM_CONFIG - Configuration & status of L2 cache RAMs */
+GCR_ACCESSOR_RW(64, 0x240, l2_ram_config)
+#define CM_GCR_L2_RAM_CONFIG_PRESENT		BIT(31)
+#define CM_GCR_L2_RAM_CONFIG_HCI_DONE		BIT(30)
+#define CM_GCR_L2_RAM_CONFIG_HCI_SUPPORTED	BIT(29)
+
 /* GCR_L2_PFT_CONTROL - Controls hardware L2 prefetching */
 GCR_ACCESSOR_RW(32, 0x300, l2_pft_control)
 #define CM_GCR_L2_PFT_CONTROL_PAGEMASK		GENMASK(31, 12)
@@ -266,6 +294,18 @@ GCR_ACCESSOR_RW(32, 0x308, l2_pft_control_b)
 #define CM_GCR_L2_PFT_CONTROL_B_CEN		BIT(8)
 #define CM_GCR_L2_PFT_CONTROL_B_PORTID		GENMASK(7, 0)
 
+/* GCR_L2_TAG_ADDR - Access addresses in L2 cache tags */
+GCR_ACCESSOR_RW(64, 0x600, l2_tag_addr)
+
+/* GCR_L2_TAG_STATE - Access L2 cache tag state */
+GCR_ACCESSOR_RW(64, 0x608, l2_tag_state)
+
+/* GCR_L2_DATA - Access data in L2 cache lines */
+GCR_ACCESSOR_RW(64, 0x610, l2_data)
+
+/* GCR_L2_ECC - Access ECC information from L2 cache lines */
+GCR_ACCESSOR_RW(64, 0x618, l2_ecc)
+
 /* GCR_L2SM_COP - L2 cache op state machine control */
 GCR_ACCESSOR_RW(32, 0x620, l2sm_cop)
 #define CM_GCR_L2SM_COP_PRESENT			BIT(31)
diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h
index 14226ea42036..602a21aee9d4 100644
--- a/arch/mips/include/asm/mmzone.h
+++ b/arch/mips/include/asm/mmzone.h
@@ -20,6 +20,4 @@
 #define nid_to_addrbase(nid) 0
 #endif
 
-extern void setup_zero_pages(void);
-
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index 26c7a6ede983..bbca420c96d3 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -48,11 +48,8 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 extern void pgd_init(void *addr);
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 85fa9962266a..ef72c46b5568 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
-#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last))
+#define MAX_REG_OFFSET \
+	(offsetof(struct pt_regs, __last) - sizeof(unsigned long))
 
 /**
  * regs_get_register() - get register value from its offset
diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h
index ab94e50f62b8..10d3ebd890cb 100644
--- a/arch/mips/include/asm/smp-cps.h
+++ b/arch/mips/include/asm/smp-cps.h
@@ -22,7 +22,12 @@ struct core_boot_config {
 	struct vpe_boot_config *vpe_config;
 };
 
-extern struct core_boot_config *mips_cps_core_bootcfg;
+struct cluster_boot_config {
+	unsigned long *core_power;
+	struct core_boot_config *core_config;
+};
+
+extern struct cluster_boot_config *mips_cps_cluster_bootcfg;
 
 extern void mips_cps_core_boot(int cca, void __iomem *gcr_base);
 extern void mips_cps_core_init(void);
diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h
index 4724a563c5bf..43a09f0dd3ff 100644
--- a/arch/mips/include/asm/socket.h
+++ b/arch/mips/include/asm/socket.h
@@ -36,15 +36,6 @@ enum sock_type {
 	SOCK_PACKET	= 10,
 };
 
-#define SOCK_MAX (SOCK_PACKET + 1)
-/* Mask which covers at least up to SOCK_MASK-1.  The
- *  * remaining bits are used as flags. */
-#define SOCK_TYPE_MASK 0xf
-
-/* Flags for socket, socketpair, paccept */
-#define SOCK_CLOEXEC	O_CLOEXEC
-#define SOCK_NONBLOCK	O_NONBLOCK
-
 #define ARCH_HAS_SOCKET_TYPES 1
 
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index 44a45f3fa4b0..fd32baa30e17 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -167,7 +167,7 @@ static __always_inline u64 read_r4k_count(void)
 
 #ifdef CONFIG_CLKSRC_MIPS_GIC
 
-static __always_inline u64 read_gic_count(const struct vdso_data *data)
+static __always_inline u64 read_gic_count(const struct vdso_time_data *data)
 {
 	void __iomem *gic = get_gic(data);
 	u32 hi, hi2, lo;
@@ -184,7 +184,7 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data)
 #endif
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 #ifdef CONFIG_CSRC_R4K
 	if (clock_mode == VDSO_CLOCKMODE_R4K)
@@ -209,10 +209,11 @@ static inline bool mips_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable mips_vdso_hres_capable
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return get_vdso_data();
+	return get_vdso_time_data();
 }
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/mips/include/asm/vdso/vdso.h b/arch/mips/include/asm/vdso/vdso.h
index 6cd88191fefa..acd0efcd3d93 100644
--- a/arch/mips/include/asm/vdso/vdso.h
+++ b/arch/mips/include/asm/vdso/vdso.h
@@ -5,16 +5,18 @@
  */
 
 #include <asm/sgidefs.h>
+#include <vdso/page.h>
+
+#define __VDSO_PAGES 4
 
 #ifndef __ASSEMBLY__
 
 #include <asm/asm.h>
-#include <asm/page.h>
 #include <asm/vdso.h>
 
-static inline unsigned long get_vdso_base(void)
+static inline const struct vdso_time_data *get_vdso_time_data(void)
 {
-	unsigned long addr;
+	const struct vdso_time_data *addr;
 
 	/*
 	 * We can't use cpu_has_mips_r6 since it needs the cpu_data[]
@@ -27,7 +29,7 @@ static inline unsigned long get_vdso_base(void)
 	 * We can't use addiupc because there is no label-label
 	 * support for the addiupc reloc
 	 */
-	__asm__("lapc	%0, _start			\n"
+	__asm__("lapc	%0, vdso_u_time_data		\n"
 		: "=r" (addr) : :);
 #else
 	/*
@@ -46,7 +48,7 @@ static inline unsigned long get_vdso_base(void)
 	"	.set noreorder				\n"
 	"	bal	1f				\n"
 	"	 nop					\n"
-	"	.word	_start - .			\n"
+	"	.word	vdso_u_time_data - .		\n"
 	"1:	lw	%0, 0($31)			\n"
 	"	" STR(PTR_ADDU) " %0, $31, %0		\n"
 	"	.set pop				\n"
@@ -58,14 +60,9 @@ static inline unsigned long get_vdso_base(void)
 	return addr;
 }
 
-static inline const struct vdso_data *get_vdso_data(void)
-{
-	return (const struct vdso_data *)(get_vdso_base() - PAGE_SIZE);
-}
-
 #ifdef CONFIG_CLKSRC_MIPS_GIC
 
-static inline void __iomem *get_gic(const struct vdso_data *data)
+static inline void __iomem *get_gic(const struct vdso_time_data *data)
 {
 	return (void __iomem *)((unsigned long)data & PAGE_MASK) - PAGE_SIZE;
 }
diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h
index a4582870aaea..2b1debb62dee 100644
--- a/arch/mips/include/asm/vdso/vsyscall.h
+++ b/arch/mips/include/asm/vdso/vsyscall.h
@@ -2,22 +2,12 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
+#include <asm/page.h>
+
 #ifndef __ASSEMBLY__
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline
-struct vdso_data *__mips_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __mips_get_k_vdso_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index b910ec54a3a1..1e29efcba46e 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -410,6 +410,9 @@ void output_cps_defines(void)
 {
 	COMMENT(" MIPS CPS offsets. ");
 
+	OFFSET(CLUSTERBOOTCFG_CORECONFIG, cluster_boot_config, core_config);
+	DEFINE(CLUSTERBOOTCFG_SIZE, sizeof(struct cluster_boot_config));
+
 	OFFSET(COREBOOTCFG_VPEMASK, core_boot_config, vpe_mask);
 	OFFSET(COREBOOTCFG_VPECONFIG, core_boot_config, vpe_config);
 	DEFINE(COREBOOTCFG_SIZE, sizeof(struct core_boot_config));
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index 9a47fbcd4638..de64d6bb7ba3 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -10,6 +10,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/irq.h>
 
+#include <asm/ds1287.h>
 #include <asm/time.h>
 
 int ds1287_timer_state(void)
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index f876309130ad..2ae7034a3d5c 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -19,6 +19,10 @@
 #define GCR_CPC_BASE_OFS	0x0088
 #define GCR_CL_COHERENCE_OFS	0x2008
 #define GCR_CL_ID_OFS		0x2028
+#define  CM3_GCR_Cx_ID_CLUSTER_SHF	8
+#define  CM3_GCR_Cx_ID_CLUSTER_MSK	(0xff << 8)
+#define  CM3_GCR_Cx_ID_CORENUM_SHF	0
+#define  CM3_GCR_Cx_ID_CORENUM_MSK	(0xff << 0)
 
 #define CPC_CL_VC_STOP_OFS	0x2020
 #define CPC_CL_VC_RUN_OFS	0x2028
@@ -271,12 +275,21 @@ LEAF(mips_cps_core_init)
  */
 LEAF(mips_cps_get_bootcfg)
 	/* Calculate a pointer to this cores struct core_boot_config */
+	PTR_LA	v0, mips_cps_cluster_bootcfg
+	PTR_L	v0, 0(v0)
 	lw	t0, GCR_CL_ID_OFS(s1)
+#ifdef CONFIG_CPU_MIPSR6
+	ext	t1, t0, CM3_GCR_Cx_ID_CLUSTER_SHF, 8
+	li	t2, CLUSTERBOOTCFG_SIZE
+	mul	t1, t1, t2
+	PTR_ADDU \
+		v0, v0, t1
+#endif
+	PTR_L	v0, CLUSTERBOOTCFG_CORECONFIG(v0)
+	andi	t0, t0, CM3_GCR_Cx_ID_CORENUM_MSK
 	li	t1, COREBOOTCFG_SIZE
 	mul	t0, t0, t1
-	PTR_LA	t1, mips_cps_core_bootcfg
-	PTR_L	t1, 0(t1)
-	PTR_ADDU v0, t0, t1
+	PTR_ADDU v0, v0, t0
 
 	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
 	li	t9, 0
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a572ce36a24f..08c0a01d9a29 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -104,48 +104,59 @@ handle_vcei:
 
 	__FINIT
 
-	.align	5	/* 32 byte rollback region */
-LEAF(__r4k_wait)
-	.set	push
-	.set	noreorder
-	/* start of rollback region */
-	LONG_L	t0, TI_FLAGS($28)
-	nop
-	andi	t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	 nop
-	nop
-	nop
-#ifdef CONFIG_CPU_MICROMIPS
-	nop
-	nop
-	nop
-	nop
-#endif
+	.section .cpuidle.text,"ax"
+	/* Align to 32 bytes for the maximum idle interrupt region size. */
+	.align	5
+LEAF(r4k_wait)
+	/* Keep the ISA bit clear for calculations on local labels here. */
+0:	.fill 	0
+	/* Start of idle interrupt region. */
+	local_irq_enable
+	/*
+	 * If an interrupt lands here, before going idle on the next
+	 * instruction, we must *NOT* go idle since the interrupt could
+	 * have set TIF_NEED_RESCHED or caused a timer to need resched.
+	 * Fall through -- see skipover_handler below -- and have the
+	 * idle loop take care of things.
+	 */
+1:	.fill	0
+	/* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up.  */
+	.if		1b - 0b > 32
+	.error	"overlong idle interrupt region"
+	.elseif	1b - 0b > 8
+	.align	4
+	.endif
+2:	.fill	0
+	.equ	r4k_wait_idle_size, 2b - 0b
+	/* End of idle interrupt region; size has to be a power of 2. */
 	.set	MIPS_ISA_ARCH_LEVEL_RAW
+r4k_wait_insn:
 	wait
-	/* end of rollback region (the region size must be power of two) */
-1:
+r4k_wait_exit:
+	.set	mips0
+	local_irq_disable
 	jr	ra
-	 nop
-	.set	pop
-	END(__r4k_wait)
+	END(r4k_wait)
+	.previous
 
-	.macro	BUILD_ROLLBACK_PROLOGUE handler
-	FEXPORT(rollback_\handler)
+	.macro	BUILD_SKIPOVER_PROLOGUE handler
+	FEXPORT(skipover_\handler)
 	.set	push
 	.set	noat
 	MFC0	k0, CP0_EPC
-	PTR_LA	k1, __r4k_wait
-	ori	k0, 0x1f	/* 32 byte rollback region */
-	xori	k0, 0x1f
+	/* Subtract/add 2 to let the ISA bit propagate through the mask.  */
+	PTR_LA	k1, r4k_wait_insn - 2
+	ori 	k0, r4k_wait_idle_size - 2
+	.set	noreorder
 	bne	k0, k1, \handler
+	PTR_ADDIU 	k0, r4k_wait_exit - r4k_wait_insn + 2
+	.set	reorder
 	MTC0	k0, CP0_EPC
 	.set pop
 	.endm
 
 	.align	5
-BUILD_ROLLBACK_PROLOGUE handle_int
+BUILD_SKIPOVER_PROLOGUE handle_int
 NESTED(handle_int, PT_SIZE, sp)
 	.cfi_signal_frame
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -265,7 +276,7 @@ NESTED(except_vec_ejtag_debug, 0, sp)
  * This prototype is copied to ebase + n*IntCtl.VS and patched
  * to invoke the handler
  */
-BUILD_ROLLBACK_PROLOGUE except_vec_vi
+BUILD_SKIPOVER_PROLOGUE except_vec_vi
 NESTED(except_vec_vi, 0, sp)
 	SAVE_SOME docfi=1
 	SAVE_AT docfi=1
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5abc8b7340f8..80e8a04a642e 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void)
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 }
 
-void __cpuidle r4k_wait(void)
-{
-	raw_local_irq_enable();
-	__r4k_wait();
-	raw_local_irq_disable();
-}
-
 /*
  * This variant is preferable as it allows testing need_resched and going to
  * sleep depending on the outcome atomically.  Unfortunately the "It is
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 3eb2cfb893e1..43cb1e20baed 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/of.h>
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
 
@@ -14,6 +15,7 @@
 void __iomem *mips_gcr_base;
 void __iomem *mips_cm_l2sync_base;
 int mips_cm_is64;
+bool mips_cm_is_l2_hci_broken;
 
 static char *cm2_tr[8] = {
 	"mem",	"gcr",	"gic",	"mmio",
@@ -237,6 +239,18 @@ static void mips_cm_probe_l2sync(void)
 	mips_cm_l2sync_base = ioremap(addr, MIPS_CM_L2SYNC_SIZE);
 }
 
+void mips_cm_update_property(void)
+{
+	struct device_node *cm_node;
+
+	cm_node = of_find_compatible_node(of_root, NULL, "mobileye,eyeq6-cm");
+	if (!cm_node)
+		return;
+	pr_info("HCI (Hardware Cache Init for the L2 cache) in GCR_L2_RAM_CONFIG from the CM3 is broken");
+	mips_cm_is_l2_hci_broken = true;
+	of_node_put(cm_node);
+}
+
 int mips_cm_probe(void)
 {
 	phys_addr_t addr;
@@ -308,7 +322,9 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
 		      FIELD_PREP(CM3_GCR_Cx_OTHER_VP, vp);
 
 		if (cm_rev >= CM_REV_CM3_5) {
-			val |= CM_GCR_Cx_OTHER_CLUSTER_EN;
+			if (cluster != cpu_cluster(&current_cpu_data))
+				val |= CM_GCR_Cx_OTHER_CLUSTER_EN;
+			val |= CM_GCR_Cx_OTHER_GIC_EN;
 			val |= FIELD_PREP(CM_GCR_Cx_OTHER_CLUSTER, cluster);
 			val |= FIELD_PREP(CM_GCR_Cx_OTHER_BLOCK, block);
 		} else {
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index c4d6b09136b1..196a070349b0 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -791,8 +791,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc,
 	if (!mipspmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, data, regs))
-		mipsxx_pmu_disable_event(idx);
+	perf_event_overflow(event, data, regs);
 }
 
 
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index d09ca77e624d..3de0e05e0511 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -57,10 +57,7 @@ static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
 
-/*
- * Used to synchronize entry to deep idle states. Actually per-core rather
- * than per-CPU.
- */
+/* Used to synchronize entry to deep idle states */
 static DEFINE_PER_CPU_ALIGNED(atomic_t, pm_barrier);
 
 /* Saved CPU state across the CPS_PM_POWER_GATED state */
@@ -104,17 +101,20 @@ static void coupled_barrier(atomic_t *a, unsigned online)
 int cps_pm_enter_state(enum cps_pm_state state)
 {
 	unsigned cpu = smp_processor_id();
+	unsigned int cluster = cpu_cluster(&current_cpu_data);
 	unsigned core = cpu_core(&current_cpu_data);
 	unsigned online, left;
 	cpumask_t *coupled_mask = this_cpu_ptr(&online_coupled);
 	u32 *core_ready_count, *nc_core_ready_count;
 	void *nc_addr;
 	cps_nc_entry_fn entry;
+	struct cluster_boot_config *cluster_cfg;
 	struct core_boot_config *core_cfg;
 	struct vpe_boot_config *vpe_cfg;
+	atomic_t *barrier;
 
 	/* Check that there is an entry function for this state */
-	entry = per_cpu(nc_asm_enter, core)[state];
+	entry = per_cpu(nc_asm_enter, cpu)[state];
 	if (!entry)
 		return -EINVAL;
 
@@ -138,7 +138,8 @@ int cps_pm_enter_state(enum cps_pm_state state)
 		if (!mips_cps_smp_in_use())
 			return -EINVAL;
 
-		core_cfg = &mips_cps_core_bootcfg[core];
+		cluster_cfg = &mips_cps_cluster_bootcfg[cluster];
+		core_cfg = &cluster_cfg->core_config[core];
 		vpe_cfg = &core_cfg->vpe_config[cpu_vpe_id(&current_cpu_data)];
 		vpe_cfg->pc = (unsigned long)mips_cps_pm_restore;
 		vpe_cfg->gp = (unsigned long)current_thread_info();
@@ -150,7 +151,7 @@ int cps_pm_enter_state(enum cps_pm_state state)
 	smp_mb__after_atomic();
 
 	/* Create a non-coherent mapping of the core ready_count */
-	core_ready_count = per_cpu(ready_count, core);
+	core_ready_count = per_cpu(ready_count, cpu);
 	nc_addr = kmap_noncoherent(virt_to_page(core_ready_count),
 				   (unsigned long)core_ready_count);
 	nc_addr += ((unsigned long)core_ready_count & ~PAGE_MASK);
@@ -158,7 +159,8 @@ int cps_pm_enter_state(enum cps_pm_state state)
 
 	/* Ensure ready_count is zero-initialised before the assembly runs */
 	WRITE_ONCE(*nc_core_ready_count, 0);
-	coupled_barrier(&per_cpu(pm_barrier, core), online);
+	barrier = &per_cpu(pm_barrier, cpumask_first(&cpu_sibling_map[cpu]));
+	coupled_barrier(barrier, online);
 
 	/* Run the generated entry code */
 	left = entry(online, nc_core_ready_count);
@@ -629,12 +631,14 @@ out_err:
 
 static int cps_pm_online_cpu(unsigned int cpu)
 {
-	enum cps_pm_state state;
-	unsigned core = cpu_core(&cpu_data[cpu]);
+	unsigned int sibling, core;
 	void *entry_fn, *core_rc;
+	enum cps_pm_state state;
+
+	core = cpu_core(&cpu_data[cpu]);
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
-		if (per_cpu(nc_asm_enter, core)[state])
+		if (per_cpu(nc_asm_enter, cpu)[state])
 			continue;
 		if (!test_bit(state, state_support))
 			continue;
@@ -646,16 +650,19 @@ static int cps_pm_online_cpu(unsigned int cpu)
 			clear_bit(state, state_support);
 		}
 
-		per_cpu(nc_asm_enter, core)[state] = entry_fn;
+		for_each_cpu(sibling, &cpu_sibling_map[cpu])
+			per_cpu(nc_asm_enter, sibling)[state] = entry_fn;
 	}
 
-	if (!per_cpu(ready_count, core)) {
+	if (!per_cpu(ready_count, cpu)) {
 		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count, core) = core_rc;
+
+		for_each_cpu(sibling, &cpu_sibling_map[cpu])
+			per_cpu(ready_count, sibling) = core_rc;
 	}
 
 	return 0;
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 61503a36067e..f7107479c7fa 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1326,24 +1326,8 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs)
 			return -1;
 	}
 
-#ifdef CONFIG_SECCOMP
-	if (unlikely(test_thread_flag(TIF_SECCOMP))) {
-		int ret, i;
-		struct seccomp_data sd;
-		unsigned long args[6];
-
-		sd.nr = current_thread_info()->syscall;
-		sd.arch = syscall_get_arch(current);
-		syscall_get_arguments(current, regs, args);
-		for (i = 0; i < 6; i++)
-			sd.args[i] = args[i];
-		sd.instruction_pointer = KSTK_EIP(current);
-
-		ret = __secure_computing(&sd);
-		if (ret == -1)
-			return ret;
-	}
-#endif
+	if (secure_computing())
+		return -1;
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 82c8f9b9573c..cc26d56f3ab6 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -36,11 +36,55 @@ enum label_id {
 
 UASM_L_LA(_not_nmi)
 
-static DECLARE_BITMAP(core_power, NR_CPUS);
 static u64 core_entry_reg;
 static phys_addr_t cps_vec_pa;
 
-struct core_boot_config *mips_cps_core_bootcfg;
+struct cluster_boot_config *mips_cps_cluster_bootcfg;
+
+static void power_up_other_cluster(unsigned int cluster)
+{
+	u32 stat, seq_state;
+	unsigned int timeout;
+
+	mips_cm_lock_other(cluster, CM_GCR_Cx_OTHER_CORE_CM, 0,
+			   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	stat = read_cpc_co_stat_conf();
+	mips_cm_unlock_other();
+
+	seq_state = stat & CPC_Cx_STAT_CONF_SEQSTATE;
+	seq_state >>= __ffs(CPC_Cx_STAT_CONF_SEQSTATE);
+	if (seq_state == CPC_Cx_STAT_CONF_SEQSTATE_U5)
+		return;
+
+	/* Set endianness & power up the CM */
+	mips_cm_lock_other(cluster, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+	write_cpc_redir_sys_config(IS_ENABLED(CONFIG_CPU_BIG_ENDIAN));
+	write_cpc_redir_pwrup_ctl(1);
+	mips_cm_unlock_other();
+
+	/* Wait for the CM to start up */
+	timeout = 1000;
+	mips_cm_lock_other(cluster, CM_GCR_Cx_OTHER_CORE_CM, 0,
+			   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	while (1) {
+		stat = read_cpc_co_stat_conf();
+		seq_state = stat & CPC_Cx_STAT_CONF_SEQSTATE;
+		seq_state >>= __ffs(CPC_Cx_STAT_CONF_SEQSTATE);
+		if (seq_state == CPC_Cx_STAT_CONF_SEQSTATE_U5)
+			break;
+
+		if (timeout) {
+			mdelay(1);
+			timeout--;
+		} else {
+			pr_warn("Waiting for cluster %u CM to power up... STAT_CONF=0x%x\n",
+				cluster, stat);
+			mdelay(1000);
+		}
+	}
+
+	mips_cm_unlock_other();
+}
 
 static unsigned __init core_vpe_count(unsigned int cluster, unsigned core)
 {
@@ -178,6 +222,9 @@ static void __init cps_smp_setup(void)
 			pr_cont(",");
 		pr_cont("{");
 
+		if (mips_cm_revision() >= CM_REV_CM3_5)
+			power_up_other_cluster(cl);
+
 		ncores = mips_cps_numcores(cl);
 		for (c = 0; c < ncores; c++) {
 			core_vpes = core_vpe_count(cl, c);
@@ -205,8 +252,8 @@ static void __init cps_smp_setup(void)
 
 	/* Indicate present CPUs (CPU being synonymous with VPE) */
 	for (v = 0; v < min_t(unsigned, nvpes, NR_CPUS); v++) {
-		set_cpu_possible(v, cpu_cluster(&cpu_data[v]) == 0);
-		set_cpu_present(v, cpu_cluster(&cpu_data[v]) == 0);
+		set_cpu_possible(v, true);
+		set_cpu_present(v, true);
 		__cpu_number_map[v] = v;
 		__cpu_logical_map[v] = v;
 	}
@@ -214,9 +261,6 @@ static void __init cps_smp_setup(void)
 	/* Set a coherent default CCA (CWB) */
 	change_c0_config(CONF_CM_CMASK, 0x5);
 
-	/* Core 0 is powered up (we're running on it) */
-	bitmap_set(core_power, 0, 1);
-
 	/* Initialise core 0 */
 	mips_cps_core_init();
 
@@ -238,8 +282,10 @@ static void __init cps_smp_setup(void)
 
 static void __init cps_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned ncores, core_vpes, c, cca;
+	unsigned int nclusters, ncores, core_vpes, c, cl, cca;
 	bool cca_unsuitable, cores_limited;
+	struct cluster_boot_config *cluster_bootcfg;
+	struct core_boot_config *core_bootcfg;
 
 	mips_mt_set_cpuoptions();
 
@@ -281,40 +327,66 @@ static void __init cps_prepare_cpus(unsigned int max_cpus)
 
 	setup_cps_vecs();
 
-	/* Allocate core boot configuration structs */
-	ncores = mips_cps_numcores(0);
-	mips_cps_core_bootcfg = kcalloc(ncores, sizeof(*mips_cps_core_bootcfg),
-					GFP_KERNEL);
-	if (!mips_cps_core_bootcfg) {
-		pr_err("Failed to allocate boot config for %u cores\n", ncores);
+	/* Allocate cluster boot configuration structs */
+	nclusters = mips_cps_numclusters();
+	mips_cps_cluster_bootcfg = kcalloc(nclusters,
+					   sizeof(*mips_cps_cluster_bootcfg),
+					   GFP_KERNEL);
+	if (!mips_cps_cluster_bootcfg)
 		goto err_out;
-	}
 
-	/* Allocate VPE boot configuration structs */
-	for (c = 0; c < ncores; c++) {
-		core_vpes = core_vpe_count(0, c);
-		mips_cps_core_bootcfg[c].vpe_config = kcalloc(core_vpes,
-				sizeof(*mips_cps_core_bootcfg[c].vpe_config),
+	if (nclusters > 1)
+		mips_cm_update_property();
+
+	for (cl = 0; cl < nclusters; cl++) {
+		/* Allocate core boot configuration structs */
+		ncores = mips_cps_numcores(cl);
+		core_bootcfg = kcalloc(ncores, sizeof(*core_bootcfg),
+					GFP_KERNEL);
+		if (!core_bootcfg)
+			goto err_out;
+		mips_cps_cluster_bootcfg[cl].core_config = core_bootcfg;
+
+		mips_cps_cluster_bootcfg[cl].core_power =
+			kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long),
 				GFP_KERNEL);
-		if (!mips_cps_core_bootcfg[c].vpe_config) {
-			pr_err("Failed to allocate %u VPE boot configs\n",
-			       core_vpes);
+		if (!mips_cps_cluster_bootcfg[cl].core_power)
 			goto err_out;
+
+		/* Allocate VPE boot configuration structs */
+		for (c = 0; c < ncores; c++) {
+			core_vpes = core_vpe_count(cl, c);
+			core_bootcfg[c].vpe_config = kcalloc(core_vpes,
+					sizeof(*core_bootcfg[c].vpe_config),
+					GFP_KERNEL);
+			if (!core_bootcfg[c].vpe_config)
+				goto err_out;
 		}
 	}
 
-	/* Mark this CPU as booted */
-	atomic_set(&mips_cps_core_bootcfg[cpu_core(&current_cpu_data)].vpe_mask,
-		   1 << cpu_vpe_id(&current_cpu_data));
+	/* Mark this CPU as powered up & booted */
+	cl = cpu_cluster(&current_cpu_data);
+	c = cpu_core(&current_cpu_data);
+	cluster_bootcfg = &mips_cps_cluster_bootcfg[cl];
+	core_bootcfg = &cluster_bootcfg->core_config[c];
+	bitmap_set(cluster_bootcfg->core_power, cpu_core(&current_cpu_data), 1);
+	atomic_set(&core_bootcfg->vpe_mask, 1 << cpu_vpe_id(&current_cpu_data));
 
 	return;
 err_out:
 	/* Clean up allocations */
-	if (mips_cps_core_bootcfg) {
-		for (c = 0; c < ncores; c++)
-			kfree(mips_cps_core_bootcfg[c].vpe_config);
-		kfree(mips_cps_core_bootcfg);
-		mips_cps_core_bootcfg = NULL;
+	if (mips_cps_cluster_bootcfg) {
+		for (cl = 0; cl < nclusters; cl++) {
+			cluster_bootcfg = &mips_cps_cluster_bootcfg[cl];
+			ncores = mips_cps_numcores(cl);
+			for (c = 0; c < ncores; c++) {
+				core_bootcfg = &cluster_bootcfg->core_config[c];
+				kfree(core_bootcfg->vpe_config);
+			}
+			kfree(mips_cps_cluster_bootcfg[c].core_config);
+		}
+		kfree(mips_cps_cluster_bootcfg);
+		mips_cps_cluster_bootcfg = NULL;
 	}
 
 	/* Effectively disable SMP by declaring CPUs not present */
@@ -325,13 +397,118 @@ err_out:
 	}
 }
 
-static void boot_core(unsigned int core, unsigned int vpe_id)
+static void init_cluster_l2(void)
 {
-	u32 stat, seq_state;
-	unsigned timeout;
+	u32 l2_cfg, l2sm_cop, result;
+
+	while (!mips_cm_is_l2_hci_broken) {
+		l2_cfg = read_gcr_redir_l2_ram_config();
+
+		/* If HCI is not supported, use the state machine below */
+		if (!(l2_cfg & CM_GCR_L2_RAM_CONFIG_PRESENT))
+			break;
+		if (!(l2_cfg & CM_GCR_L2_RAM_CONFIG_HCI_SUPPORTED))
+			break;
+
+		/* If the HCI_DONE bit is set, we're finished */
+		if (l2_cfg & CM_GCR_L2_RAM_CONFIG_HCI_DONE)
+			return;
+	}
+
+	l2sm_cop = read_gcr_redir_l2sm_cop();
+	if (WARN(!(l2sm_cop & CM_GCR_L2SM_COP_PRESENT),
+		 "L2 init not supported on this system yet"))
+		return;
+
+	/* Clear L2 tag registers */
+	write_gcr_redir_l2_tag_state(0);
+	write_gcr_redir_l2_ecc(0);
+
+	/* Ensure the L2 tag writes complete before the state machine starts */
+	mb();
+
+	/* Wait for the L2 state machine to be idle */
+	do {
+		l2sm_cop = read_gcr_redir_l2sm_cop();
+	} while (l2sm_cop & CM_GCR_L2SM_COP_RUNNING);
+
+	/* Start a store tag operation */
+	l2sm_cop = CM_GCR_L2SM_COP_TYPE_IDX_STORETAG;
+	l2sm_cop <<= __ffs(CM_GCR_L2SM_COP_TYPE);
+	l2sm_cop |= CM_GCR_L2SM_COP_CMD_START;
+	write_gcr_redir_l2sm_cop(l2sm_cop);
+
+	/* Ensure the state machine starts before we poll for completion */
+	mb();
+
+	/* Wait for the operation to be complete */
+	do {
+		l2sm_cop = read_gcr_redir_l2sm_cop();
+		result = l2sm_cop & CM_GCR_L2SM_COP_RESULT;
+		result >>= __ffs(CM_GCR_L2SM_COP_RESULT);
+	} while (!result);
+
+	WARN(result != CM_GCR_L2SM_COP_RESULT_DONE_OK,
+	     "L2 state machine failed cache init with error %u\n", result);
+}
+
+static void boot_core(unsigned int cluster, unsigned int core,
+		      unsigned int vpe_id)
+{
+	struct cluster_boot_config *cluster_cfg;
+	u32 access, stat, seq_state;
+	unsigned int timeout, ncores;
+
+	cluster_cfg = &mips_cps_cluster_bootcfg[cluster];
+	ncores = mips_cps_numcores(cluster);
+
+	if ((cluster != cpu_cluster(&current_cpu_data)) &&
+	    bitmap_empty(cluster_cfg->core_power, ncores)) {
+		power_up_other_cluster(cluster);
+
+		mips_cm_lock_other(cluster, core, 0,
+				   CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+
+		/* Ensure cluster GCRs are where we expect */
+		write_gcr_redir_base(read_gcr_base());
+		write_gcr_redir_cpc_base(read_gcr_cpc_base());
+		write_gcr_redir_gic_base(read_gcr_gic_base());
+
+		init_cluster_l2();
+
+		/* Mirror L2 configuration */
+		write_gcr_redir_l2_only_sync_base(read_gcr_l2_only_sync_base());
+		write_gcr_redir_l2_pft_control(read_gcr_l2_pft_control());
+		write_gcr_redir_l2_pft_control_b(read_gcr_l2_pft_control_b());
+
+		/* Mirror ECC/parity setup */
+		write_gcr_redir_err_control(read_gcr_err_control());
+
+		/* Set BEV base */
+		write_gcr_redir_bev_base(core_entry_reg);
+
+		mips_cm_unlock_other();
+	}
+
+	if (cluster != cpu_cluster(&current_cpu_data)) {
+		mips_cm_lock_other(cluster, core, 0,
+				   CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+
+		/* Ensure the core can access the GCRs */
+		access = read_gcr_redir_access();
+		access |= BIT(core);
+		write_gcr_redir_access(access);
+
+		mips_cm_unlock_other();
+	} else {
+		/* Ensure the core can access the GCRs */
+		access = read_gcr_access();
+		access |= BIT(core);
+		write_gcr_access(access);
+	}
 
 	/* Select the appropriate core */
-	mips_cm_lock_other(0, core, 0, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+	mips_cm_lock_other(cluster, core, 0, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 	/* Set its reset vector */
 	if (mips_cm_is64)
@@ -400,30 +577,42 @@ static void boot_core(unsigned int core, unsigned int vpe_id)
 	mips_cm_unlock_other();
 
 	/* The core is now powered up */
-	bitmap_set(core_power, core, 1);
+	bitmap_set(cluster_cfg->core_power, core, 1);
+
+	/*
+	 * Restore CM_PWRUP=0 so that the CM can power down if all the cores in
+	 * the cluster do (eg. if they're all removed via hotplug.
+	 */
+	if (mips_cm_revision() >= CM_REV_CM3_5) {
+		mips_cm_lock_other(cluster, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+		write_cpc_redir_pwrup_ctl(0);
+		mips_cm_unlock_other();
+	}
 }
 
 static void remote_vpe_boot(void *dummy)
 {
+	unsigned int cluster = cpu_cluster(&current_cpu_data);
 	unsigned core = cpu_core(&current_cpu_data);
-	struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core];
+	struct cluster_boot_config *cluster_cfg =
+		&mips_cps_cluster_bootcfg[cluster];
+	struct core_boot_config *core_cfg = &cluster_cfg->core_config[core];
 
 	mips_cps_boot_vpes(core_cfg, cpu_vpe_id(&current_cpu_data));
 }
 
 static int cps_boot_secondary(int cpu, struct task_struct *idle)
 {
+	unsigned int cluster = cpu_cluster(&cpu_data[cpu]);
 	unsigned core = cpu_core(&cpu_data[cpu]);
 	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
-	struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core];
+	struct cluster_boot_config *cluster_cfg =
+		&mips_cps_cluster_bootcfg[cluster];
+	struct core_boot_config *core_cfg = &cluster_cfg->core_config[core];
 	struct vpe_boot_config *vpe_cfg = &core_cfg->vpe_config[vpe_id];
 	unsigned int remote;
 	int err;
 
-	/* We don't yet support booting CPUs in other clusters */
-	if (cpu_cluster(&cpu_data[cpu]) != cpu_cluster(&raw_current_cpu_data))
-		return -ENOSYS;
-
 	vpe_cfg->pc = (unsigned long)&smp_bootstrap;
 	vpe_cfg->sp = __KSTK_TOS(idle);
 	vpe_cfg->gp = (unsigned long)task_thread_info(idle);
@@ -432,14 +621,15 @@ static int cps_boot_secondary(int cpu, struct task_struct *idle)
 
 	preempt_disable();
 
-	if (!test_bit(core, core_power)) {
+	if (!test_bit(core, cluster_cfg->core_power)) {
 		/* Boot a VPE on a powered down core */
-		boot_core(core, vpe_id);
+		boot_core(cluster, core, vpe_id);
 		goto out;
 	}
 
 	if (cpu_has_vp) {
-		mips_cm_lock_other(0, core, vpe_id, CM_GCR_Cx_OTHER_BLOCK_LOCAL);
+		mips_cm_lock_other(cluster, core, vpe_id,
+				   CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 		if (mips_cm_is64)
 			write_gcr_co_reset64_base(core_entry_reg);
 		else
@@ -576,12 +766,14 @@ static void cps_kexec_nonboot_cpu(void)
 static int cps_cpu_disable(void)
 {
 	unsigned cpu = smp_processor_id();
+	struct cluster_boot_config *cluster_cfg;
 	struct core_boot_config *core_cfg;
 
 	if (!cps_pm_support_state(CPS_PM_POWER_GATED))
 		return -EINVAL;
 
-	core_cfg = &mips_cps_core_bootcfg[cpu_core(&current_cpu_data)];
+	cluster_cfg = &mips_cps_cluster_bootcfg[cpu_cluster(&current_cpu_data)];
+	core_cfg = &cluster_cfg->core_config[cpu_core(&current_cpu_data)];
 	atomic_sub(1 << cpu_vpe_id(&current_cpu_data), &core_cfg->vpe_mask);
 	smp_mb__after_atomic();
 	set_cpu_online(cpu, false);
@@ -647,11 +839,15 @@ static void cps_cpu_die(unsigned int cpu) { }
 
 static void cps_cleanup_dead_cpu(unsigned cpu)
 {
+	unsigned int cluster = cpu_cluster(&cpu_data[cpu]);
 	unsigned core = cpu_core(&cpu_data[cpu]);
 	unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	ktime_t fail_time;
 	unsigned stat;
 	int err;
+	struct cluster_boot_config *cluster_cfg;
+
+	cluster_cfg = &mips_cps_cluster_bootcfg[cluster];
 
 	/*
 	 * Now wait for the CPU to actually offline. Without doing this that
@@ -703,7 +899,7 @@ static void cps_cleanup_dead_cpu(unsigned cpu)
 		} while (1);
 
 		/* Indicate the core is powered off */
-		bitmap_clear(core_power, core, 1);
+		bitmap_clear(cluster_cfg->core_power, core, 1);
 	} else if (cpu_has_mipsmt) {
 		/*
 		 * Have a CPU with access to the offlined CPUs registers wait
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 0b9b7e25b69a..aa70e371bb54 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -405,3 +405,4 @@
 464	n32	getxattrat			sys_getxattrat
 465	n32	listxattrat			sys_listxattrat
 466	n32	removexattrat			sys_removexattrat
+467	n32	open_tree_attr			sys_open_tree_attr
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c844cd5cda62..1e8c44c7b614 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -381,3 +381,4 @@
 464	n64	getxattrat			sys_getxattrat
 465	n64	listxattrat			sys_listxattrat
 466	n64	removexattrat			sys_removexattrat
+467	n64	open_tree_attr			sys_open_tree_attr
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 349b8aad1159..114a5a1a6230 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -454,3 +454,4 @@
 464	o32	getxattrat			sys_getxattrat
 465	o32	listxattrat			sys_listxattrat
 466	o32	removexattrat			sys_removexattrat
+467	o32	open_tree_attr			sys_open_tree_attr
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 39e248d0ed59..8ec1e185b35c 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -77,7 +77,7 @@
 #include "access-helper.h"
 
 extern void check_wait(void);
-extern asmlinkage void rollback_handle_int(void);
+extern asmlinkage void skipover_handle_int(void);
 extern asmlinkage void handle_int(void);
 extern asmlinkage void handle_adel(void);
 extern asmlinkage void handle_ades(void);
@@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
 {
 	extern const u8 except_vec_vi[];
 	extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
-	extern const u8 rollback_except_vec_vi[];
+	extern const u8 skipover_except_vec_vi[];
 	unsigned long handler;
 	unsigned long old_handler = vi_handlers[n];
 	int srssets = current_cpu_data.srsets;
@@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr)
 			change_c0_srsmap(0xf << n*4, 0 << n*4);
 	}
 
-	vec_start = using_rollback_handler() ? rollback_except_vec_vi :
+	vec_start = using_skipover_handler() ? skipover_except_vec_vi :
 					       except_vec_vi;
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
 	ori_offset = except_vec_vi_ori - vec_start + 2;
@@ -2426,8 +2426,8 @@ void __init trap_init(void)
 	if (board_be_init)
 		board_be_init();
 
-	set_except_vector(EXCCODE_INT, using_rollback_handler() ?
-					rollback_handle_int : handle_int);
+	set_except_vector(EXCCODE_INT, using_skipover_handler() ?
+					skipover_handle_int : handle_int);
 	set_except_vector(EXCCODE_MOD, handle_tlbm);
 	set_except_vector(EXCCODE_TLBL, handle_tlbl);
 	set_except_vector(EXCCODE_TLBS, handle_tlbs);
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 75c9d3618f58..de096777172f 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -15,6 +15,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/abi.h>
 #include <asm/mips-cps.h>
@@ -23,20 +24,7 @@
 #include <vdso/helpers.h>
 #include <vdso/vsyscall.h>
 
-/* Kernel-provided data used by the VDSO. */
-static union vdso_data_store mips_vdso_data __page_aligned_data;
-struct vdso_data *vdso_data = mips_vdso_data.data;
-
-/*
- * Mapping for the VDSO data/GIC pages. The real pages are mapped manually, as
- * what we map and where within the area they are mapped is determined at
- * runtime.
- */
-static struct page *no_pages[] = { NULL };
-static struct vm_special_mapping vdso_vvar_mapping = {
-	.name = "[vvar]",
-	.pages = no_pages,
-};
+static_assert(VDSO_NR_PAGES == __VDSO_PAGES);
 
 static void __init init_vdso_image(struct mips_vdso_image *image)
 {
@@ -90,7 +78,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mips_vdso_image *image = current->thread.abi->vdso;
 	struct mm_struct *mm = current->mm;
-	unsigned long gic_size, vvar_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base;
+	unsigned long gic_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base;
 	struct vm_area_struct *vma;
 	int ret;
 
@@ -119,8 +107,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 * the counter registers at the start.
 	 */
 	gic_size = mips_gic_present() ? PAGE_SIZE : 0;
-	vvar_size = gic_size + PAGE_SIZE;
-	size = vvar_size + image->size;
+	size = gic_size + VDSO_NR_PAGES * PAGE_SIZE + image->size;
 
 	/*
 	 * Find a region that's large enough for us to perform the
@@ -143,15 +130,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 */
 	if (cpu_has_dc_aliases) {
 		base = __ALIGN_MASK(base, shm_align_mask);
-		base += ((unsigned long)vdso_data - gic_size) & shm_align_mask;
+		base += ((unsigned long)vdso_k_time_data - gic_size) & shm_align_mask;
 	}
 
 	data_addr = base + gic_size;
-	vdso_addr = data_addr + PAGE_SIZE;
+	vdso_addr = data_addr + VDSO_NR_PAGES * PAGE_SIZE;
 
-	vma = _install_special_mapping(mm, base, vvar_size,
-				       VM_READ | VM_MAYREAD,
-				       &vdso_vvar_mapping);
+	vma = vdso_install_vvar_mapping(mm, data_addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;
@@ -161,6 +146,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (gic_size) {
 		gic_base = (unsigned long)mips_gic_base + MIPS_GIC_USER_OFS;
 		gic_pfn = PFN_DOWN(__pa(gic_base));
+		static const struct vm_special_mapping gic_mapping = {
+			.name	= "[gic]",
+			.pages	= (struct page **) { NULL },
+		};
+
+		vma = _install_special_mapping(mm, base, gic_size, VM_READ | VM_MAYREAD,
+					       &gic_mapping);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			goto out;
+		}
 
 		ret = io_remap_pfn_range(vma, base, gic_pfn, gic_size,
 					 pgprot_noncached(vma->vm_page_prot));
@@ -168,13 +164,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 			goto out;
 	}
 
-	/* Map data page. */
-	ret = remap_pfn_range(vma, data_addr,
-			      virt_to_phys(vdso_data) >> PAGE_SHIFT,
-			      PAGE_SIZE, vma->vm_page_prot);
-	if (ret)
-		goto out;
-
 	/* Map VDSO image. */
 	vma = _install_special_mapping(mm, vdso_addr, image->size,
 				       VM_READ | VM_EXEC |
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 60b43ea85c12..cef3c423a41a 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -288,9 +288,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup;
+	hrtimer_setup(&vcpu->arch.comparecount_timer, kvm_mips_comparecount_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	/*
 	 * Allocate space for host mode exception handlers that handle
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 8f208007b8e8..a112573b6e37 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -377,7 +377,7 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent)
 	for (i = 0; i < MAX_IM; i++)
 		irq_set_chained_handler(i + 2, ltq_hw_irq_handler);
 
-	ltq_domain = irq_domain_add_linear(node,
+	ltq_domain = irq_domain_create_linear(of_fwnode_handle(node),
 		(MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE,
 		&irq_domain_ops, 0);
 
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 9c024e6d5e54..9d75845ef78e 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -3,6 +3,8 @@
 # Makefile for MIPS-specific library files..
 #
 
+obj-y	+= crypto/
+
 lib-y	+= bitops.o csum_partial.o delay.o memcpy.o memset.o \
 	   mips-atomic.o strncpy_user.o \
 	   strnlen_user.o uncached.o
diff --git a/arch/mips/lib/crc32-mips.c b/arch/mips/lib/crc32-mips.c
index 083e5d693a16..45e4d2c9fbf5 100644
--- a/arch/mips/lib/crc32-mips.c
+++ b/arch/mips/lib/crc32-mips.c
@@ -16,15 +16,6 @@
 #include <asm/mipsregs.h>
 #include <linux/unaligned.h>
 
-enum crc_op_size {
-	b, h, w, d,
-};
-
-enum crc_type {
-	crc32,
-	crc32c,
-};
-
 #ifndef TOOLCHAIN_SUPPORTS_CRC
 #define _ASM_SET_CRC(OP, SZ, TYPE)					  \
 _ASM_MACRO_3R(OP, rt, rs, rt2,						  \
@@ -71,7 +62,7 @@ do {							\
 #define CRC32C(crc, value, size) \
 	_CRC32(crc, value, size, crc32c)
 
-static DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
 
 u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -117,10 +108,10 @@ u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
-u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	if (!static_branch_likely(&have_crc32))
-		return crc32c_le_base(crc, p, len);
+		return crc32c_base(crc, p, len);
 
 	if (IS_ENABLED(CONFIG_64BIT)) {
 		for (; len >= sizeof(u64); p += sizeof(u64), len -= sizeof(u64)) {
@@ -158,7 +149,7 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 	}
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -172,7 +163,7 @@ static int __init crc32_mips_init(void)
 		static_branch_enable(&have_crc32);
 	return 0;
 }
-arch_initcall(crc32_mips_init);
+subsys_initcall(crc32_mips_init);
 
 static void __exit crc32_mips_exit(void)
 {
diff --git a/arch/x86/boot/tools/.gitignore b/arch/mips/lib/crypto/.gitignore
index ae91f4d0d78b..0d47d4f21c6d 100644
--- a/arch/x86/boot/tools/.gitignore
+++ b/arch/mips/lib/crypto/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-build
+poly1305-core.S
diff --git a/arch/mips/lib/crypto/Kconfig b/arch/mips/lib/crypto/Kconfig
new file mode 100644
index 000000000000..0670a170c1be
--- /dev/null
+++ b/arch/mips/lib/crypto/Kconfig
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA_MIPS
+	tristate
+	depends on CPU_MIPS32_R2
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_MIPS
+	tristate
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
diff --git a/arch/mips/lib/crypto/Makefile b/arch/mips/lib/crypto/Makefile
new file mode 100644
index 000000000000..804488c7aded
--- /dev/null
+++ b/arch/mips/lib/crypto/Makefile
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o
+chacha-mips-y := chacha-core.o chacha-glue.o
+AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
+
+obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
+poly1305-mips-y := poly1305-core.o poly1305-glue.o
+
+perlasm-flavour-$(CONFIG_32BIT) := o32
+perlasm-flavour-$(CONFIG_64BIT) := 64
+
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
+
+$(obj)/poly1305-core.S: $(src)/poly1305-mips.pl FORCE
+	$(call if_changed,perlasm)
+
+targets += poly1305-core.S
diff --git a/arch/mips/crypto/chacha-core.S b/arch/mips/lib/crypto/chacha-core.S
index 5755f69cfe00..5755f69cfe00 100644
--- a/arch/mips/crypto/chacha-core.S
+++ b/arch/mips/lib/crypto/chacha-core.S
diff --git a/arch/mips/lib/crypto/chacha-glue.c b/arch/mips/lib/crypto/chacha-glue.c
new file mode 100644
index 000000000000..88c097594eb0
--- /dev/null
+++ b/arch/mips/lib/crypto/chacha-glue.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ChaCha and HChaCha functions (MIPS optimized)
+ *
+ * Copyright (C) 2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/chacha.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void chacha_crypt_arch(struct chacha_state *state,
+				  u8 *dst, const u8 *src,
+				  unsigned int bytes, int nrounds);
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+asmlinkage void hchacha_block_arch(const struct chacha_state *state,
+				   u32 out[HCHACHA_OUT_WORDS], int nrounds);
+EXPORT_SYMBOL(hchacha_block_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return true;
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+MODULE_DESCRIPTION("ChaCha and HChaCha functions (MIPS optimized)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/mips/lib/crypto/poly1305-glue.c b/arch/mips/lib/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..764a38a65200
--- /dev/null
+++ b/arch/mips/lib/crypto/poly1305-glue.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_block_init_arch(
+	struct poly1305_block_state *state,
+	const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks_arch(struct poly1305_block_state *state,
+				     const u8 *src, u32 len, u32 hibit);
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
+				   u8 digest[POLY1305_DIGEST_SIZE],
+				   const u32 nonce[4]);
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	return true;
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+MODULE_DESCRIPTION("Poly1305 transform (MIPS accelerated");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/mips/crypto/poly1305-mips.pl b/arch/mips/lib/crypto/poly1305-mips.pl
index b05bab884ed2..399f10c3e385 100644
--- a/arch/mips/crypto/poly1305-mips.pl
+++ b/arch/mips/lib/crypto/poly1305-mips.pl
@@ -93,9 +93,9 @@ $code.=<<___;
 #endif
 
 #ifdef	__KERNEL__
-# define poly1305_init   poly1305_init_mips
-# define poly1305_blocks poly1305_blocks_mips
-# define poly1305_emit   poly1305_emit_mips
+# define poly1305_init   poly1305_block_init_arch
+# define poly1305_blocks poly1305_blocks_arch
+# define poly1305_emit   poly1305_emit_arch
 #endif
 
 #if defined(__MIPSEB__) && !defined(MIPSEB)
@@ -565,9 +565,9 @@ $code.=<<___;
 #endif
 
 #ifdef	__KERNEL__
-# define poly1305_init   poly1305_init_mips
-# define poly1305_blocks poly1305_blocks_mips
-# define poly1305_emit   poly1305_emit_mips
+# define poly1305_init   poly1305_block_init_arch
+# define poly1305_blocks poly1305_blocks_arch
+# define poly1305_emit   poly1305_emit_arch
 #endif
 
 #if defined(__MIPSEB__) && !defined(MIPSEB)
diff --git a/arch/mips/lib/iomap-pci.c b/arch/mips/lib/iomap-pci.c
index a9cb28813f0b..1b7ce19fb3bb 100644
--- a/arch/mips/lib/iomap-pci.c
+++ b/arch/mips/lib/iomap-pci.c
@@ -43,4 +43,14 @@ void __iomem *__pci_ioport_map(struct pci_dev *dev,
 	return (void __iomem *) (ctrl->io_map_base + port);
 }
 
+void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{
+	struct pci_controller *ctrl = dev->bus->sysdata;
+	void __iomem *base = (void __iomem *)ctrl->io_map_base;
+
+	if (addr < base || addr > (base + resource_size(ctrl->io_resource)))
+		iounmap(addr);
+}
+EXPORT_SYMBOL(pci_iounmap);
+
 #endif /* CONFIG_PCI_DRIVERS_LEGACY */
diff --git a/arch/mips/loongson2ef/common/machtype.c b/arch/mips/loongson2ef/common/machtype.c
index 82f6de49f20f..e635e66d2e6c 100644
--- a/arch/mips/loongson2ef/common/machtype.c
+++ b/arch/mips/loongson2ef/common/machtype.c
@@ -48,8 +48,7 @@ void __init prom_init_machtype(void)
 		return;
 	}
 	p += strlen("machtype=");
-	strncpy(str, p, MACHTYPE_LEN);
-	str[MACHTYPE_LEN] = '\0';
+	strscpy(str, p);
 	p = strstr(str, " ");
 	if (p)
 		*p = '\0';
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index a35dd7311795..b9f90f33fc9a 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -128,7 +128,7 @@ void __init prom_init(void)
 	}
 
 	/* init base address of io space */
-	set_io_port_base(PCI_IOBASE);
+	set_io_port_base((unsigned long)PCI_IOBASE);
 
 	if (loongson_sysconf.early_config)
 		loongson_sysconf.early_config();
@@ -178,7 +178,7 @@ static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, resource_size_
 		return -EINVAL;
 	}
 
-	vaddr = PCI_IOBASE + range->io_start;
+	vaddr = (unsigned long)PCI_IOBASE + range->io_start;
 
 	vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
 
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index 8388400d052f..95d5f553ce19 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -164,13 +164,6 @@ void __init paging_init(void)
 	free_area_init(zones_size);
 }
 
-void __init mem_init(void)
-{
-	high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
-	memblock_free_all();
-	setup_zero_pages();	/* This comes from node 0 */
-}
-
 /* All PCI device belongs to logical Node-0 */
 int pcibus_to_node(struct pci_bus *bus)
 {
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 4583d1a2a73e..a673d3d68254 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -59,24 +59,16 @@ EXPORT_SYMBOL(zero_page_mask);
 /*
  * Not static inline because used by IP27 special magic initialization code
  */
-void setup_zero_pages(void)
+static void __init setup_zero_pages(void)
 {
-	unsigned int order, i;
-	struct page *page;
+	unsigned int order;
 
 	if (cpu_has_vce)
 		order = 3;
 	else
 		order = 0;
 
-	empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!empty_zero_page)
-		panic("Oh boy, that early out of memory?");
-
-	page = virt_to_page((void *)empty_zero_page);
-	split_page(page, order);
-	for (i = 0; i < (1 << order); i++, page++)
-		mark_page_reserved(page);
+	empty_zero_page = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE << order, PAGE_SIZE);
 
 	zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
@@ -423,17 +415,8 @@ void __init paging_init(void)
 		       " %ldk highmem ignored\n",
 		       (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10));
 		max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn;
-
-		max_mapnr = max_low_pfn;
-	} else if (highend_pfn) {
-		max_mapnr = highend_pfn;
-	} else {
-		max_mapnr = max_low_pfn;
 	}
-#else
-	max_mapnr = max_low_pfn;
 #endif
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 
 	free_area_init(max_zone_pfns);
 }
@@ -442,26 +425,7 @@ void __init paging_init(void)
 static struct kcore_list kcore_kseg0;
 #endif
 
-static inline void __init mem_init_free_highmem(void)
-{
-#ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
-	if (cpu_has_dc_aliases)
-		return;
-
-	for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
-		struct page *page = pfn_to_page(tmp);
-
-		if (!memblock_is_memory(PFN_PHYS(tmp)))
-			SetPageReserved(page);
-		else
-			free_highmem_page(page);
-	}
-#endif
-}
-
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/*
 	 * When PFN_PTE_SHIFT is greater than PAGE_SHIFT we won't have enough PTE
@@ -470,9 +434,7 @@ void __init mem_init(void)
 	BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
 
 	maar_init();
-	memblock_free_all();
 	setup_zero_pages();	/* Setup zeroed pages.  */
-	mem_init_free_highmem();
 
 #ifdef CONFIG_64BIT
 	if ((unsigned long) &_text > (unsigned long) CKSEG0)
@@ -482,6 +444,11 @@ void __init mem_init(void)
 				0x80000000 - 4, KCORE_TEXT);
 #endif
 }
+#else  /* CONFIG_NUMA */
+void __init arch_mm_preinit(void)
+{
+	setup_zero_pages();	/* This comes from node 0 */
+}
 #endif /* !CONFIG_NUMA */
 
 void free_init_pages(const char *what, unsigned long begin, unsigned long end)
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index d8243d61ef32..c6c4576cd4a8 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -44,9 +44,9 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
  * ioremap_prot gives the caller control over cache coherency attributes (CCA)
  */
 void __iomem *ioremap_prot(phys_addr_t phys_addr, unsigned long size,
-		unsigned long prot_val)
+			   pgprot_t prot)
 {
-	unsigned long flags = prot_val & _CACHE_MASK;
+	unsigned long flags = pgprot_val(prot) & _CACHE_MASK;
 	unsigned long offset, pfn, last_pfn;
 	struct vm_struct *area;
 	phys_addr_t last_addr;
diff --git a/arch/mips/mm/ioremap64.c b/arch/mips/mm/ioremap64.c
index 15e7820d6a5f..acc03ba20098 100644
--- a/arch/mips/mm/ioremap64.c
+++ b/arch/mips/mm/ioremap64.c
@@ -3,9 +3,9 @@
 #include <ioremap.h>
 
 void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
-		unsigned long prot_val)
+			   pgprot_t prot)
 {
-	unsigned long flags = prot_val & _CACHE_MASK;
+	unsigned long flags = pgprot_val(prot) & _CACHE_MASK;
 	u64 base = (flags == _CACHE_UNCACHED ? IO_BASE : UNCAC_BASE);
 	void __iomem *addr;
 
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index a925842ee125..17fa97ec6ffb 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -469,8 +469,8 @@ static int ar2315_pci_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	apc->domain = irq_domain_add_linear(NULL, AR2315_PCI_IRQ_COUNT,
-					    &ar2315_pci_irq_domain_ops, apc);
+	apc->domain = irq_domain_create_linear(NULL, AR2315_PCI_IRQ_COUNT,
+					       &ar2315_pci_irq_domain_ops, apc);
 	if (!apc->domain) {
 		dev_err(dev, "failed to add IRQ domain\n");
 		return -ENOMEM;
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 4ac68a534e4f..14454ece485d 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -208,9 +208,10 @@ static int rt3883_pci_irq_init(struct device *dev,
 	rt3883_pci_w32(rpc, 0, RT3883_PCI_REG_PCIENA);
 
 	rpc->irq_domain =
-		irq_domain_add_linear(rpc->intc_of_node, RT3883_PCI_IRQ_COUNT,
-				      &rt3883_pci_irq_domain_ops,
-				      rpc);
+		irq_domain_create_linear(of_fwnode_handle(rpc->intc_of_node),
+					 RT3883_PCI_IRQ_COUNT,
+					 &rt3883_pci_irq_domain_ops,
+					 rpc);
 	if (!rpc->irq_domain) {
 		dev_err(dev, "unable to add IRQ domain\n");
 		return -ENODEV;
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index dae856fb3e5b..e00c38620d14 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -620,7 +620,7 @@ static int bridge_probe(struct platform_device *pdev)
 	if (bridge_get_partnum(virt_to_phys((void *)bd->bridge_addr), partnum))
 		return -EPROBE_DEFER; /* not available yet */
 
-	parent = irq_get_default_host();
+	parent = irq_get_default_domain();
 	if (!parent)
 		return -ENODEV;
 	fn = irq_domain_alloc_named_fwnode("BRIDGE");
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 46aef0a1b22a..af5bbbea949b 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -176,7 +176,7 @@ static int __init intc_of_init(struct device_node *node,
 	/* route all INTC interrupts to MIPS HW0 interrupt */
 	rt_intc_w32(0, INTC_REG_TYPE);
 
-	domain = irq_domain_add_legacy(node, RALINK_INTC_IRQ_COUNT,
+	domain = irq_domain_create_legacy(of_fwnode_handle(node), RALINK_INTC_IRQ_COUNT,
 			RALINK_INTC_IRQ_BASE, 0, &irq_domain_ops, NULL);
 	if (!domain)
 		panic("Failed to add irqdomain");
diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c
index 8f0861c58080..8539f562f5b8 100644
--- a/arch/mips/sgi-ip22/ip22-reset.c
+++ b/arch/mips/sgi-ip22/ip22-reset.c
@@ -98,7 +98,7 @@ static void blink_timeout(struct timer_list *unused)
 
 static void debounce(struct timer_list *unused)
 {
-	del_timer(&debounce_timer);
+	timer_delete(&debounce_timer);
 	if (sgint->istat1 & SGINT_ISTAT1_PWR) {
 		/* Interrupt still being sent. */
 		debounce_timer.expires = jiffies + (HZ / 20); /* 0.05s	*/
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 00e63e9ef61d..288d4d17eddd 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -297,7 +297,7 @@ void __init arch_init_irq(void)
 	if (WARN_ON(domain == NULL))
 		return;
 
-	irq_set_default_host(domain);
+	irq_set_default_domain(domain);
 
 	irq_set_percpu_devid(IP27_HUB_PEND0_IRQ);
 	irq_set_chained_handler_and_data(IP27_HUB_PEND0_IRQ, ip27_do_irq_mask0,
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 1963313f55d8..2b3e46e2e607 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -406,8 +406,6 @@ void __init prom_meminit(void)
 	}
 }
 
-extern void setup_zero_pages(void);
-
 void __init paging_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES] = {0, };
@@ -416,10 +414,3 @@ void __init paging_init(void)
 	zones_size[ZONE_NORMAL] = max_low_pfn;
 	free_area_init(zones_size);
 }
-
-void __init mem_init(void)
-{
-	high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
-	memblock_free_all();
-	setup_zero_pages();	/* This comes from node 0 */
-}
diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c
index 423c32cb66ed..9fb905e2cf14 100644
--- a/arch/mips/sgi-ip30/ip30-irq.c
+++ b/arch/mips/sgi-ip30/ip30-irq.c
@@ -313,7 +313,7 @@ void __init arch_init_irq(void)
 	if (!domain)
 		return;
 
-	irq_set_default_host(domain);
+	irq_set_default_domain(domain);
 
 	irq_set_percpu_devid(IP30_HEART_L0_IRQ);
 	irq_set_chained_handler_and_data(IP30_HEART_L0_IRQ, ip30_normal_irq,
diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c
index 42fdb939c88d..03cb69937258 100644
--- a/arch/mips/sni/setup.c
+++ b/arch/mips/sni/setup.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/console.h>
-#include <linux/fb.h>
 #include <linux/screen_info.h>
 
 #ifdef CONFIG_FW_ARC
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index b289b2c1b294..fb4c493aaffa 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -2,7 +2,7 @@
 # Objects to go into the VDSO.
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso-y := elf.o vgettimeofday.o sigreturn.o
 
diff --git a/arch/mips/vdso/vdso.lds.S b/arch/mips/vdso/vdso.lds.S
index 836465e3bcb8..c8bbe56d89cb 100644
--- a/arch/mips/vdso/vdso.lds.S
+++ b/arch/mips/vdso/vdso.lds.S
@@ -5,6 +5,8 @@
  */
 
 #include <asm/sgidefs.h>
+#include <asm/vdso/vdso.h>
+#include <vdso/datapage.h>
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 OUTPUT_FORMAT("elf64-tradlittlemips", "elf64-tradbigmips", "elf64-tradlittlemips")
@@ -18,7 +20,8 @@ OUTPUT_ARCH(mips)
 
 SECTIONS
 {
-	PROVIDE(_start = .);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	/*
diff --git a/arch/nios2/Kbuild b/arch/nios2/Kbuild
index fc2952edd2de..fa64c5954b20 100644
--- a/arch/nios2/Kbuild
+++ b/arch/nios2/Kbuild
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-obj-y += kernel/ mm/ platform/ boot/dts/
+obj-y += kernel/ mm/ platform/
 
 # for cleaning
 subdir- += boot
diff --git a/arch/nios2/boot/dts/Makefile b/arch/nios2/boot/dts/Makefile
index 1a2e8996bec7..1b8f41c4154f 100644
--- a/arch/nios2/boot/dts/Makefile
+++ b/arch/nios2/boot/dts/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := $(patsubst %.dts,%.dtb.o,$(CONFIG_NIOS2_DTB_SOURCE))
+dtb-y := $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME))
 
-dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
+dtb-$(CONFIG_OF_ALL_DTBS) += $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 12a536b7bfbd..db122b093a8b 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -28,10 +28,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, addr)					\
-	do {								\
-		pagetable_dtor(page_ptdesc(pte));			\
-		tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-	} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif /* _ASM_NIOS2_PGALLOC_H */
diff --git a/arch/nios2/kernel/irq.c b/arch/nios2/kernel/irq.c
index 6b7890e5f7af..73568d8e21e0 100644
--- a/arch/nios2/kernel/irq.c
+++ b/arch/nios2/kernel/irq.c
@@ -69,10 +69,11 @@ void __init init_IRQ(void)
 
 	BUG_ON(!node);
 
-	domain = irq_domain_add_linear(node, NIOS2_CPU_NR_IRQS, &irq_ops, NULL);
+	domain = irq_domain_create_linear(of_fwnode_handle(node),
+					  NIOS2_CPU_NR_IRQS, &irq_ops, NULL);
 	BUG_ON(!domain);
 
-	irq_set_default_host(domain);
+	irq_set_default_domain(domain);
 	of_node_put(node);
 	/* Load the initial ienable value */
 	ienable = RDCTL(CTL_IENABLE);
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index db049249766f..4f8c14da6490 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -32,7 +32,7 @@ void __init early_init_devtree(void *params)
 	}
 #endif
 
-#ifdef CONFIG_NIOS2_DTB_SOURCE_BOOL
+#ifdef CONFIG_BUILTIN_DTB
 	if (be32_to_cpu((__be32) *dtb) == OF_DT_HEADER)
 		params = (void *)__dtb_start;
 #endif
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index da122a5fa43b..2a40150142c3 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -149,6 +149,8 @@ void __init setup_arch(char **cmdline_p)
 	memory_start = memblock_start_of_DRAM();
 	memory_end = memblock_end_of_DRAM();
 
+	pr_debug("%s: start=%lx, end=%lx\n", __func__, memory_start, memory_end);
+
 	setup_initial_init_mm(_stext, _etext, _edata, _end);
 	init_task.thread.kregs = &fake_regs;
 
@@ -156,7 +158,6 @@ void __init setup_arch(char **cmdline_p)
 	*cmdline_p = boot_command_line;
 
 	find_limits(&min_low_pfn, &max_low_pfn, &max_pfn);
-	max_mapnr = max_low_pfn;
 
 	memblock_reserve(__pa_symbol(_stext), _end - _stext);
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c
index a2278485de19..94efa3de3933 100644
--- a/arch/nios2/mm/init.c
+++ b/arch/nios2/mm/init.c
@@ -51,7 +51,7 @@ void __init paging_init(void)
 	pagetable_init();
 	pgd_current = swapper_pg_dir;
 
-	max_zone_pfn[ZONE_NORMAL] = max_mapnr;
+	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
 
 	/* pass the memory from the bootmem allocator to the main allocator */
 	free_area_init(max_zone_pfn);
@@ -60,20 +60,6 @@ void __init paging_init(void)
 			(unsigned long)empty_zero_page + PAGE_SIZE);
 }
 
-void __init mem_init(void)
-{
-	unsigned long end_mem   = memory_end; /* this must not include
-						kernel stack at top */
-
-	pr_debug("mem_init: start=%lx, end=%lx\n", memory_start, memory_end);
-
-	end_mem &= PAGE_MASK;
-	high_memory = __va(end_mem);
-
-	/* this will put all memory onto the freelists */
-	memblock_free_all();
-}
-
 void __init mmu_init(void)
 {
 	flush_tlb_all();
diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform
index e849daff6fd1..c75cadd92388 100644
--- a/arch/nios2/platform/Kconfig.platform
+++ b/arch/nios2/platform/Kconfig.platform
@@ -35,19 +35,20 @@ config NIOS2_DTB_PHYS_ADDR
 	help
 	  Physical address of a dtb blob.
 
-config NIOS2_DTB_SOURCE_BOOL
+config BUILTIN_DTB
 	bool "Compile and link device tree into kernel image"
 	depends on !COMPILE_TEST
+	select GENERIC_BUILTIN_DTB
 	help
 	  This allows you to specify a dts (device tree source) file
 	  which will be compiled and linked into the kernel image.
 
-config NIOS2_DTB_SOURCE
-	string "Device tree source file"
-	depends on NIOS2_DTB_SOURCE_BOOL
+config BUILTIN_DTB_NAME
+	string "Built-in device tree name"
+	depends on BUILTIN_DTB
 	default ""
 	help
-	  Absolute path to the device tree source (dts) file describing your
+	  Relative path to the device tree without suffix describing your
 	  system.
 
 comment "Nios II instructions"
diff --git a/arch/openrisc/include/asm/cacheflush.h b/arch/openrisc/include/asm/cacheflush.h
index 984c331ff5f4..0e60af486ec1 100644
--- a/arch/openrisc/include/asm/cacheflush.h
+++ b/arch/openrisc/include/asm/cacheflush.h
@@ -23,6 +23,9 @@
  */
 extern void local_dcache_page_flush(struct page *page);
 extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
 
 /*
  * Data cache flushing always happen on the local cpu. Instruction cache
@@ -39,6 +42,20 @@ extern void smp_icache_page_inv(struct page *page);
 #endif /* CONFIG_SMP */
 
 /*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+	local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+	local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+	local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
+
+/*
  * Synchronizes caches. Whenever a cpu writes executable code to memory, this
  * should be called to make sure the processor sees the newly written code.
  */
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index 5e4744153d0e..3cfc4cf0b019 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -15,16 +15,21 @@
 #ifndef __ASM_OPENRISC_CPUINFO_H
 #define __ASM_OPENRISC_CPUINFO_H
 
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+struct cache_desc {
+	u32 size;
+	u32 sets;
+	u32 block_size;
+	u32 ways;
+};
+
 struct cpuinfo_or1k {
 	u32 clock_frequency;
 
-	u32 icache_size;
-	u32 icache_block_size;
-	u32 icache_ways;
-
-	u32 dcache_size;
-	u32 dcache_block_size;
-	u32 dcache_ways;
+	struct cache_desc icache;
+	struct cache_desc dcache;
 
 	u16 coreid;
 };
@@ -32,4 +37,9 @@ struct cpuinfo_or1k {
 extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 extern void setup_cpuinfo(void);
 
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
+
 #endif /* __ASM_OPENRISC_CPUINFO_H */
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 3372f4e6ab4b..3f110931d8f6 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -64,10 +64,7 @@ extern inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 79129161f3e0..e4c7d9bdd598 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y	:= vmlinux.lds
 
 obj-y	:= head.o setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
-	   sys_call_table.o unwinder.o
+	   sys_call_table.o unwinder.o cacheinfo.o
 
 obj-$(CONFIG_SMP)		+= smp.o sync-timer.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
diff --git a/arch/openrisc/kernel/cacheinfo.c b/arch/openrisc/kernel/cacheinfo.c
new file mode 100644
index 000000000000..61230545e4ff
--- /dev/null
+++ b/arch/openrisc/kernel/cacheinfo.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OpenRISC cacheinfo support
+ *
+ * Based on work done for MIPS and LoongArch. All original copyrights
+ * apply as per the original source declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) 2025 Sahil Siddiq <sahilcdq@proton.me>
+ */
+
+#include <linux/cacheinfo.h>
+#include <asm/cpuinfo.h>
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+				unsigned int level, struct cache_desc *cache, int cpu)
+{
+	this_leaf->type = type;
+	this_leaf->level = level;
+	this_leaf->coherency_line_size = cache->block_size;
+	this_leaf->number_of_sets = cache->sets;
+	this_leaf->ways_of_associativity = cache->ways;
+	this_leaf->size = cache->size;
+	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	int leaves = 0, levels = 0;
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long iccfgr, dccfgr;
+
+	if (!(upr & SPR_UPR_UP)) {
+		printk(KERN_INFO
+		       "-- no UPR register... unable to detect configuration\n");
+		return -ENOENT;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		dccfgr = mfspr(SPR_DCCFGR);
+		cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+		cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
+		cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+		cpuinfo->dcache.size =
+		    cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->dcache.size, cpuinfo->dcache.block_size,
+		       cpuinfo->dcache.sets, cpuinfo->dcache.ways);
+	} else
+		printk(KERN_INFO "-- dcache disabled\n");
+
+	if (cpu_cache_is_present(SPR_UPR_ICP)) {
+		iccfgr = mfspr(SPR_ICCFGR);
+		cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+		cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
+		cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+		cpuinfo->icache.size =
+		    cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->icache.size, cpuinfo->icache.block_size,
+		       cpuinfo->icache.sets, cpuinfo->icache.ways);
+	} else
+		printk(KERN_INFO "-- icache disabled\n");
+
+	if (!leaves)
+		return -ENOENT;
+
+	levels = 1;
+
+	this_cpu_ci->num_leaves = leaves;
+	this_cpu_ci->num_levels = levels;
+
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	int level = 1;
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu);
+		this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ?
+					CACHE_WRITE_BACK : CACHE_WRITE_THROUGH;
+		this_leaf++;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_ICP))
+		ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu);
+
+	this_cpu_ci->cpu_map_populated = true;
+
+	return 0;
+}
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index b3edbb33b621..3a7b5baaa450 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -17,6 +17,7 @@
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
 #include <asm/spr_defs.h>
 #include <asm/tlbflush.h>
 
@@ -24,9 +25,6 @@ static int
 page_set_nocache(pte_t *pte, unsigned long addr,
 		 unsigned long next, struct mm_walk *walk)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	pte_val(*pte) |= _PAGE_CI;
 
 	/*
@@ -36,8 +34,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
 	/* Flush page out of dcache */
-	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
-		mtspr(SPR_DCBFR, cl);
+	local_dcache_range_flush(__pa(addr), __pa(next));
 
 	return 0;
 }
@@ -98,21 +95,14 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBFR, cl);
+		local_dcache_range_flush(addr, addr + size);
 		break;
 	case DMA_FROM_DEVICE:
 		/* Invalidate the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBIR, cl);
+		local_dcache_range_inv(addr, addr + size);
 		break;
 	default:
 		/*
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index be56eaafc8b9..a9fb9cc6779e 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -113,21 +113,6 @@ static void print_cpuinfo(void)
 		return;
 	}
 
-	if (upr & SPR_UPR_DCP)
-		printk(KERN_INFO
-		       "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->dcache_size, cpuinfo->dcache_block_size,
-		       cpuinfo->dcache_ways);
-	else
-		printk(KERN_INFO "-- dcache disabled\n");
-	if (upr & SPR_UPR_ICP)
-		printk(KERN_INFO
-		       "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->icache_size, cpuinfo->icache_block_size,
-		       cpuinfo->icache_ways);
-	else
-		printk(KERN_INFO "-- icache disabled\n");
-
 	if (upr & SPR_UPR_DMP)
 		printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n",
 		       1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
@@ -155,8 +140,6 @@ static void print_cpuinfo(void)
 void __init setup_cpuinfo(void)
 {
 	struct device_node *cpu;
-	unsigned long iccfgr, dccfgr;
-	unsigned long cache_set_size;
 	int cpu_id = smp_processor_id();
 	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
 
@@ -164,20 +147,6 @@ void __init setup_cpuinfo(void)
 	if (!cpu)
 		panic("Couldn't find CPU%d in device tree...\n", cpu_id);
 
-	iccfgr = mfspr(SPR_ICCFGR);
-	cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
-	cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
-	cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
-	cpuinfo->icache_size =
-	    cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
-
-	dccfgr = mfspr(SPR_DCCFGR);
-	cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
-	cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
-	cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
-	cpuinfo->dcache_size =
-	    cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
-
 	if (of_property_read_u32(cpu, "clock-frequency",
 				 &cpuinfo->clock_frequency)) {
 		printk(KERN_WARNING
@@ -294,14 +263,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	unsigned int vr, cpucfgr;
 	unsigned int avr;
 	unsigned int version;
+#ifdef CONFIG_SMP
 	struct cpuinfo_or1k *cpuinfo = v;
+	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
 
 	vr = mfspr(SPR_VR);
 	cpucfgr = mfspr(SPR_CPUCFGR);
 
-#ifdef CONFIG_SMP
-	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
-#endif
 	if (vr & SPR_VR_UVRP) {
 		vr = mfspr(SPR_VR2);
 		version = vr & SPR_VR2_VER;
@@ -320,14 +289,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
 	}
 	seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
-	seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
-	seq_printf(m, "dcache block size\t: %d bytes\n",
-		   cpuinfo->dcache_block_size);
-	seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
-	seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
-	seq_printf(m, "icache block size\t: %d bytes\n",
-		   cpuinfo->icache_block_size);
-	seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
 	seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
 		   1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
 		   1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index eb43b73f3855..0f265b8e73ec 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -14,31 +14,70 @@
 #include <asm/spr_defs.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
 #include <asm/tlbflush.h>
 
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
 {
-	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
-	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long mask = SPR_UPR_UP | cache_type;
+
+	return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+				       const unsigned short reg, const unsigned int cache_type)
+{
+	if (!cpu_cache_is_present(cache_type))
+		return;
 
-	while (line < paddr + PAGE_SIZE) {
-		mtspr(reg, line);
-		line += L1_CACHE_BYTES;
+	while (paddr < end) {
+		mtspr(reg, paddr);
+		paddr += L1_CACHE_BYTES;
 	}
 }
 
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+					    const unsigned int cache_type)
+{
+	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
+	unsigned long end = paddr + PAGE_SIZE;
+
+	paddr &= ~(L1_CACHE_BYTES - 1);
+
+	cache_loop(paddr, end, reg, cache_type);
+}
+
 void local_dcache_page_flush(struct page *page)
 {
-	cache_loop(page, SPR_DCBFR);
+	cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
 }
 EXPORT_SYMBOL(local_dcache_page_flush);
 
 void local_icache_page_inv(struct page *page)
 {
-	cache_loop(page, SPR_ICBIR);
+	cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
 }
 EXPORT_SYMBOL(local_icache_page_inv);
 
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
+
 void update_cache(struct vm_area_struct *vma, unsigned long address,
 	pte_t *pte)
 {
@@ -58,4 +97,3 @@ void update_cache(struct vm_area_struct *vma, unsigned long address,
 			sync_icache_dcache(folio_page(folio, nr));
 	}
 }
-
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index d0cb1a0126f9..e4904ca6f0a0 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -35,6 +35,7 @@
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/cacheflush.h>
 
 int mem_init_done;
 
@@ -176,8 +177,8 @@ void __init paging_init(void)
 	barrier();
 
 	/* Invalidate instruction caches after code modification */
-	mtspr(SPR_ICBIR, 0x900);
-	mtspr(SPR_ICBIR, 0xa00);
+	local_icache_block_inv(0x900);
+	local_icache_block_inv(0xa00);
 
 	/* New TLB miss handlers and kernel page tables are in now place.
 	 * Make sure that page flags get updated for all pages in TLB by
@@ -193,15 +194,9 @@ void __init mem_init(void)
 {
 	BUG_ON(!mem_map);
 
-	max_mapnr = max_low_pfn;
-	high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
-
 	/* clear the zero-page */
 	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
-	/* this will put all low memory onto the freelists */
-	memblock_free_all();
-
 	printk("mem_init_done ...........................................\n");
 	mem_init_done = 1;
 	return;
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index 5ce258f3fffa..94928d114d4c 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -132,11 +132,11 @@ CONFIG_I2C=y
 CONFIG_HWMON=m
 CONFIG_DRM=m
 CONFIG_DRM_DISPLAY_DP_AUX_CEC=y
-# CONFIG_DRM_I2C_CH7006 is not set
-# CONFIG_DRM_I2C_SIL164 is not set
 CONFIG_DRM_RADEON=m
 CONFIG_DRM_NOUVEAU=m
 # CONFIG_DRM_NOUVEAU_BACKLIGHT is not set
+# CONFIG_DRM_NOUVEAU_CH7006 is not set
+# CONFIG_DRM_NOUVEAU_SIL164 is not set
 CONFIG_DRM_VGEM=m
 CONFIG_DRM_UDL=m
 CONFIG_DRM_MGAG200=m
@@ -251,7 +251,7 @@ CONFIG_CIFS=m
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
 # CONFIG_CIFS_DEBUG is not set
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
@@ -264,8 +264,6 @@ CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA1=y
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_DEFLATE=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_FONTS=y
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index 19a804860ed5..d8cd7f858b2a 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -193,11 +193,11 @@ CONFIG_MEDIA_SUPPORT=m
 CONFIG_AGP=y
 CONFIG_AGP_PARISC=y
 CONFIG_DRM=y
-# CONFIG_DRM_I2C_CH7006 is not set
-# CONFIG_DRM_I2C_SIL164 is not set
 CONFIG_DRM_RADEON=y
 CONFIG_DRM_NOUVEAU=m
 # CONFIG_DRM_NOUVEAU_BACKLIGHT is not set
+# CONFIG_DRM_NOUVEAU_CH7006 is not set
+# CONFIG_DRM_NOUVEAU_SIL164 is not set
 CONFIG_DRM_MGAG200=m
 CONFIG_FB=y
 CONFIG_FB_PM2=m
@@ -268,7 +268,6 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_XATTR=y
 CONFIG_CONFIGFS_FS=y
-CONFIG_SYSV_FS=y
 CONFIG_NFS_FS=m
 CONFIG_NFS_V4=m
 CONFIG_NFS_V4_1=y
@@ -284,7 +283,6 @@ CONFIG_NLS_ASCII=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_ISO8859_2=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
@@ -293,8 +291,6 @@ CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_DEFLATE=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=m
-CONFIG_LIBCRC32C=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_STRIP_ASM_SYMS=y
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5b3a5429f71b..21e9ace17739 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 3143cf29ce27..f01ad3ad60b5 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -131,13 +131,10 @@ static inline void gsc_writeq(unsigned long long val, unsigned long addr)
 		       _PAGE_ACCESSED | _PAGE_NO_CACHE)
 
 #define ioremap_wc(addr, size)  \
-	ioremap_prot((addr), (size), _PAGE_IOREMAP)
+	ioremap_prot((addr), (size), __pgprot(_PAGE_IOREMAP))
 
 #define pci_iounmap			pci_iounmap
 
-void memcpy_fromio(void *dst, const volatile void __iomem *src, int count);
-#define memcpy_fromio memcpy_fromio
-
 /* Port-space IO */
 
 #define inb_p inb
@@ -227,36 +224,54 @@ extern void outsl (unsigned long port, const void *src, unsigned long count);
 #define F_EXTEND(x) ((unsigned long)((x) | (0xffffffff00000000ULL)))
 
 #ifdef CONFIG_64BIT
-#define ioread64 ioread64
-#define ioread64be ioread64be
-#define iowrite64 iowrite64
-#define iowrite64be iowrite64be
 extern u64 ioread64(const void __iomem *addr);
 extern u64 ioread64be(const void __iomem *addr);
+#define ioread64 ioread64
+#define ioread64be ioread64be
+
 extern void iowrite64(u64 val, void __iomem *addr);
 extern void iowrite64be(u64 val, void __iomem *addr);
+#define iowrite64 iowrite64
+#define iowrite64be iowrite64be
 #endif
 
-#include <asm-generic/iomap.h>
-/*
- * These get provided from <asm-generic/iomap.h> since parisc does not
- * select GENERIC_IOMAP.
- */
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+extern void ioport_unmap(void __iomem *);
 #define ioport_map ioport_map
 #define ioport_unmap ioport_unmap
+
+extern unsigned int ioread8(const void __iomem *);
+extern unsigned int ioread16(const void __iomem *);
+extern unsigned int ioread16be(const void __iomem *);
+extern unsigned int ioread32(const void __iomem *);
+extern unsigned int ioread32be(const void __iomem *);
 #define ioread8 ioread8
 #define ioread16 ioread16
 #define ioread32 ioread32
 #define ioread16be ioread16be
 #define ioread32be ioread32be
+
+extern void iowrite8(u8, void __iomem *);
+extern void iowrite16(u16, void __iomem *);
+extern void iowrite16be(u16, void __iomem *);
+extern void iowrite32(u32, void __iomem *);
+extern void iowrite32be(u32, void __iomem *);
 #define iowrite8 iowrite8
 #define iowrite16 iowrite16
 #define iowrite32 iowrite32
 #define iowrite16be iowrite16be
 #define iowrite32be iowrite32be
+
+extern void ioread8_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread16_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread32_rep(const void __iomem *port, void *buf, unsigned long count);
 #define ioread8_rep ioread8_rep
 #define ioread16_rep ioread16_rep
 #define ioread32_rep ioread32_rep
+
+extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
+extern void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count);
 #define iowrite8_rep iowrite8_rep
 #define iowrite16_rep iowrite16_rep
 #define iowrite32_rep iowrite32_rep
diff --git a/arch/parisc/include/asm/vdso.h b/arch/parisc/include/asm/vdso.h
index 2a2dc11b5545..5f581c1d6460 100644
--- a/arch/parisc/include/asm/vdso.h
+++ b/arch/parisc/include/asm/vdso.h
@@ -12,8 +12,6 @@
 #define VDSO64_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso64_offset_##name))
 #define VDSO32_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso32_offset_##name))
 
-extern struct vdso_data *vdso_data;
-
 #endif /* __ASSEMBLY __ */
 
 /* Default link addresses for the vDSOs */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index aa9cd4b951fe..96831c988606 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -132,16 +132,16 @@
 #define SO_PASSPIDFD		0x404A
 #define SO_PEERPIDFD		0x404B
 
-#define SO_DEVMEM_LINEAR	78
-#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
-#define SO_DEVMEM_DMABUF	79
-#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
-#define SO_DEVMEM_DONTNEED	80
-
 #define SCM_TS_OPT_ID		0x404C
 
 #define SO_RCVPRIORITY		0x404D
 
+#define SO_DEVMEM_LINEAR	0x404E
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	0x404F
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	0x4050
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 1c366b0d3134..509146a52725 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -43,7 +43,6 @@ EXPORT_SYMBOL($global$);
 #endif
 
 #include <asm/io.h>
-EXPORT_SYMBOL(memcpy_fromio);
 
 extern void $$divI(void);
 extern void $$divU(void);
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index 0f9b3b5914cf..b70b67adb855 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -63,6 +63,7 @@ static unsigned long pdt_entry[MAX_PDT_ENTRIES] __page_aligned_bss;
 #define PDT_ADDR_PERM_ERR	(pdt_type != PDT_PDC ? 2UL : 0UL)
 #define PDT_ADDR_SINGLE_ERR	1UL
 
+#ifdef CONFIG_PROC_FS
 /* report PDT entries via /proc/meminfo */
 void arch_report_meminfo(struct seq_file *m)
 {
@@ -74,6 +75,7 @@ void arch_report_meminfo(struct seq_file *m)
 	seq_printf(m, "PDT_cur_entries: %7lu\n",
 			pdt_status.pdt_entries);
 }
+#endif
 
 static int get_info_pat_new(void)
 {
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index 5e8e37a722ef..5e10f98ce7b5 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -475,9 +475,9 @@ static const struct file_operations perf_fops = {
 };
 
 static struct miscdevice perf_dev = {
-	MISC_DYNAMIC_MINOR,
-	PA_PERF_DEV,
-	&perf_fops
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= PA_PERF_DEV,
+	.fops	= &perf_fops,
 };
 
 /*
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index d9fc94c86965..94df3cb957e9 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -465,3 +465,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile
index 288f8b85978f..4ee8d17da229 100644
--- a/arch/parisc/kernel/vdso32/Makefile
+++ b/arch/parisc/kernel/vdso32/Makefile
@@ -1,5 +1,5 @@
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 KCOV_INSTRUMENT := n
 
diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile
index bc5d9553f311..c63f4069170f 100644
--- a/arch/parisc/kernel/vdso64/Makefile
+++ b/arch/parisc/kernel/vdso64/Makefile
@@ -1,5 +1,5 @@
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 KCOV_INSTRUMENT := n
 
diff --git a/arch/parisc/lib/io.c b/arch/parisc/lib/io.c
index 7461366a65c9..3c7e617f5a93 100644
--- a/arch/parisc/lib/io.c
+++ b/arch/parisc/lib/io.c
@@ -13,67 +13,6 @@
 #include <asm/io.h>
 
 /*
-** Copies a block of memory from a device in an efficient manner.
-** Assumes the device can cope with 32-bit transfers.  If it can't,
-** don't use this function.
-**
-** CR16 counts on C3000 reading 256 bytes from Symbios 896 RAM:
-**	27341/64    = 427 cyc per int
-**	61311/128   = 478 cyc per short
-**	122637/256  = 479 cyc per byte
-** Ergo bus latencies dominant (not transfer size).
-**      Minimize total number of transfers at cost of CPU cycles.
-**	TODO: only look at src alignment and adjust the stores to dest.
-*/
-void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
-	/* first compare alignment of src/dst */ 
-	if ( (((unsigned long)dst ^ (unsigned long)src) & 1) || (count < 2) )
-		goto bytecopy;
-
-	if ( (((unsigned long)dst ^ (unsigned long)src) & 2) || (count < 4) )
-		goto shortcopy;
-
-	/* Then check for misaligned start address */
-	if ((unsigned long)src & 1) {
-		*(u8 *)dst = readb(src);
-		src++;
-		dst++;
-		count--;
-		if (count < 2) goto bytecopy;
-	}
-
-	if ((unsigned long)src & 2) {
-		*(u16 *)dst = __raw_readw(src);
-		src += 2;
-		dst += 2;
-		count -= 2;
-	}
-
-	while (count > 3) {
-		*(u32 *)dst = __raw_readl(src);
-		dst += 4;
-		src += 4;
-		count -= 4;
-	}
-
- shortcopy:
-	while (count > 1) {
-		*(u16 *)dst = __raw_readw(src);
-		src += 2;
-		dst += 2;
-		count -= 2;
-	}
-
- bytecopy:
-	while (count--) {
-		*(char *)dst = readb(src);
-		src++;
-		dst++;
-	}
-}
-
-/*
  * Read COUNT 8-bit bytes from port PORT into memory starting at
  * SRC.
  */
@@ -123,15 +62,15 @@ void insw (unsigned long port, void *dst, unsigned long count)
 	unsigned char *p;
 
 	p = (unsigned char *)dst;
-	
+
 	if (!count)
 		return;
-	
+
 	switch (((unsigned long)p) & 0x3)
 	{
 	 case 0x00:			/* Buffer 32-bit aligned */
 		while (count>=2) {
-			
+
 			count -= 2;
 			l = cpu_to_le16(inw(port)) << 16;
 			l |= cpu_to_le16(inw(port));
@@ -142,13 +81,13 @@ void insw (unsigned long port, void *dst, unsigned long count)
 			*(unsigned short *)p = cpu_to_le16(inw(port));
 		}
 		break;
-	
+
 	 case 0x02:			/* Buffer 16-bit aligned */
 		*(unsigned short *)p = cpu_to_le16(inw(port));
 		p += 2;
 		count--;
 		while (count>=2) {
-			
+
 			count -= 2;
 			l = cpu_to_le16(inw(port)) << 16;
 			l |= cpu_to_le16(inw(port));
@@ -159,13 +98,13 @@ void insw (unsigned long port, void *dst, unsigned long count)
 			*(unsigned short *)p = cpu_to_le16(inw(port));
 		}
 		break;
-		
+
 	 case 0x01:			/* Buffer 8-bit aligned */
 	 case 0x03:
 		/* I don't bother with 32bit transfers
 		 * in this case, 16bit will have to do -- DE */
 		--count;
-		
+
 		l = cpu_to_le16(inw(port));
 		*p = l >> 8;
 		p++;
@@ -195,10 +134,10 @@ void insl (unsigned long port, void *dst, unsigned long count)
 	unsigned char *p;
 
 	p = (unsigned char *)dst;
-	
+
 	if (!count)
 		return;
-	
+
 	switch (((unsigned long) dst) & 0x3)
 	{
 	 case 0x00:			/* Buffer 32-bit aligned */
@@ -208,14 +147,14 @@ void insl (unsigned long port, void *dst, unsigned long count)
 			p += 4;
 		}
 		break;
-	
+
 	 case 0x02:			/* Buffer 16-bit aligned */
 		--count;
-		
+
 		l = cpu_to_le32(inl(port));
 		*(unsigned short *)p = l >> 16;
 		p += 2;
-		
+
 		while (count--)
 		{
 			l2 = cpu_to_le32(inl(port));
@@ -227,7 +166,7 @@ void insl (unsigned long port, void *dst, unsigned long count)
 		break;
 	 case 0x01:			/* Buffer 8-bit aligned */
 		--count;
-		
+
 		l = cpu_to_le32(inl(port));
 		*(unsigned char *)p = l >> 24;
 		p++;
@@ -244,7 +183,7 @@ void insl (unsigned long port, void *dst, unsigned long count)
 		break;
 	 case 0x03:			/* Buffer 8-bit aligned */
 		--count;
-		
+
 		l = cpu_to_le32(inl(port));
 		*p = l >> 24;
 		p++;
@@ -293,10 +232,10 @@ void outsw (unsigned long port, const void *src, unsigned long count)
 	const unsigned char *p;
 
 	p = (const unsigned char *)src;
-	
+
 	if (!count)
 		return;
-	
+
 	switch (((unsigned long)p) & 0x3)
 	{
 	 case 0x00:			/* Buffer 32-bit aligned */
@@ -311,13 +250,13 @@ void outsw (unsigned long port, const void *src, unsigned long count)
 			outw(le16_to_cpu(*(unsigned short*)p), port);
 		}
 		break;
-	
+
 	 case 0x02:			/* Buffer 16-bit aligned */
-		
+
 		outw(le16_to_cpu(*(unsigned short*)p), port);
 		p += 2;
 		count--;
-		
+
 		while (count>=2) {
 			count -= 2;
 			l = *(unsigned int *)p;
@@ -329,11 +268,11 @@ void outsw (unsigned long port, const void *src, unsigned long count)
 			outw(le16_to_cpu(*(unsigned short *)p), port);
 		}
 		break;
-		
-	 case 0x01:			/* Buffer 8-bit aligned */	
+
+	 case 0x01:			/* Buffer 8-bit aligned */
 		/* I don't bother with 32bit transfers
 		 * in this case, 16bit will have to do -- DE */
-		
+
 		l  = *p << 8;
 		p++;
 		count--;
@@ -348,7 +287,7 @@ void outsw (unsigned long port, const void *src, unsigned long count)
 		l2 = *(unsigned char *)p;
 		outw (le16_to_cpu(l | l2>>8), port);
 		break;
-	
+
 	}
 }
 
@@ -365,10 +304,10 @@ void outsl (unsigned long port, const void *src, unsigned long count)
 	const unsigned char *p;
 
 	p = (const unsigned char *)src;
-	
+
 	if (!count)
 		return;
-	
+
 	switch (((unsigned long)p) & 0x3)
 	{
 	 case 0x00:			/* Buffer 32-bit aligned */
@@ -378,13 +317,13 @@ void outsl (unsigned long port, const void *src, unsigned long count)
 			p += 4;
 		}
 		break;
-	
+
 	 case 0x02:			/* Buffer 16-bit aligned */
 		--count;
-		
+
 		l = *(unsigned short *)p;
 		p += 2;
-		
+
 		while (count--)
 		{
 			l2 = *(unsigned int *)p;
@@ -415,7 +354,7 @@ void outsl (unsigned long port, const void *src, unsigned long count)
 		break;
 	 case 0x03:			/* Buffer 8-bit aligned */
 		--count;
-		
+
 		l = *p << 24;
 		p++;
 
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 34495446e051..71829cb7bc81 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -97,9 +97,19 @@ handle_fpe(struct pt_regs *regs)
 
 	memcpy(regs->fr, frcopy, sizeof regs->fr);
 	if (signalcode != 0) {
-	    force_sig_fault(signalcode >> 24, signalcode & 0xffffff,
-			    (void __user *) regs->iaoq[0]);
-	    return -1;
+		int sig = signalcode >> 24;
+
+		if (sig == SIGFPE) {
+			/*
+			 * Clear floating point trap bit to avoid trapping
+			 * again on the first floating-point instruction in
+			 * the userspace signal handler.
+			 */
+			regs->fr[0] &= ~(1ULL << 38);
+		}
+		force_sig_fault(sig, signalcode & 0xffffff,
+				(void __user *) regs->iaoq[0]);
+		return -1;
 	}
 
 	return signalcode ? -1 : 0;
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index e9d18cf25b79..a94fe546d434 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 61c0a2477072..14270715d754 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -562,10 +562,6 @@ void __init mem_init(void)
 	BUILD_BUG_ON(TMPALIAS_MAP_START >= 0x80000000);
 #endif
 
-	high_memory = __va((max_pfn << PAGE_SHIFT));
-	set_max_mapnr(max_low_pfn);
-	memblock_free_all();
-
 #ifdef CONFIG_PA11
 	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
 		pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START);
diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c
index fd996472dfe7..0b65c4b3baee 100644
--- a/arch/parisc/mm/ioremap.c
+++ b/arch/parisc/mm/ioremap.c
@@ -14,7 +14,7 @@
 #include <linux/mm.h>
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot)
+			   pgprot_t prot)
 {
 #ifdef CONFIG_EISA
 	unsigned long end = phys_addr + size - 1;
@@ -41,6 +41,6 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
 		}
 	}
 
-	return generic_ioremap_prot(phys_addr, size, __pgprot(prot));
+	return generic_ioremap_prot(phys_addr, size, prot);
 }
 EXPORT_SYMBOL(ioremap_prot);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 424f188e62d9..c3e0cc83f120 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -148,6 +148,7 @@ config PPC
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PREEMPT_LAZY
+	select ARCH_HAS_PTDUMP
 	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
@@ -159,6 +160,7 @@ config PPC
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UBSAN
+	select ARCH_HAS_VDSO_ARCH_DATA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_HAVE_EXTRA_ELF_NOTES        if SPU_BASE
 	select ARCH_KEEP_MEMBLOCK
@@ -206,9 +208,9 @@ config PPC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP		if PCI
-	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select HAS_IOPORT			if PCI
 	select HAVE_ARCH_AUDITSYSCALL
@@ -275,6 +277,7 @@ config PPC
 	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_RETHOOK			if KPROBES
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
@@ -286,6 +289,7 @@ config PPC
 	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,$(m32-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r2 -mstack-protector-guard-offset=0)
 	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,$(m64-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r13 -mstack-protector-guard-offset=0)
 	select HAVE_STATIC_CALL			if PPC32
+	select HAVE_STATIC_CALL_INLINE		if PPC32
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN
@@ -411,12 +415,9 @@ config ARCH_HAS_ADD_PAGES
 config PPC_DCR_NATIVE
 	bool
 
-config PPC_DCR_MMIO
-	bool
-
 config PPC_DCR
 	bool
-	depends on PPC_DCR_NATIVE || PPC_DCR_MMIO
+	depends on PPC_DCR_NATIVE
 	default y
 
 config PPC_PCI_OF_BUS_MAP
@@ -442,11 +443,6 @@ config PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
 	  PCI domain dependent and each PCI controller on own domain can have
 	  256 PCI buses, like it is on other Linux architectures.
 
-config PPC_OF_PLATFORM_PCI
-	bool
-	depends on PCI
-	depends on PPC64 # not supported on 32 bits yet
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
@@ -721,6 +717,9 @@ config ARCH_SUPPORTS_CRASH_HOTPLUG
 	def_bool y
 	depends on PPC64
 
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_RESERVE
+
 config FA_DUMP
 	bool "Firmware-assisted dump"
 	depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)
@@ -896,7 +895,7 @@ config DATA_SHIFT
 	int "Data shift" if DATA_SHIFT_BOOL
 	default 24 if STRICT_KERNEL_RWX && PPC64
 	range 17 28 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
-	range 19 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
+	range 14 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
 	range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_85xx
 	default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
 	default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
@@ -909,10 +908,10 @@ config DATA_SHIFT
 	  On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
 	  Smaller is the alignment, greater is the number of necessary DBATs.
 
-	  On 8xx, large pages (512kb or 8M) are used to map kernel linear
-	  memory. Aligning to 8M reduces TLB misses as only 8M pages are used
-	  in that case. If PIN_TLB is selected, it must be aligned to 8M as
-	  8M pages will be pinned.
+	  On 8xx, large pages (16kb or 512kb or 8M) are used to map kernel
+	  linear memory. Aligning to 8M reduces TLB misses as only 8M pages
+	  are used in that case. If PIN_TLB is selected, it must be aligned
+	  to 8M as 8M pages will be pinned.
 
 config ARCH_FORCE_MAX_ORDER
 	int "Order of maximal physically contiguous allocations"
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 20d05605fa83..f15e5920080b 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -216,13 +216,6 @@ config PPC_EARLY_DEBUG_RTAS_PANEL
 	help
 	  Select this to enable early debugging via the RTAS panel.
 
-config PPC_EARLY_DEBUG_RTAS_CONSOLE
-	bool "RTAS Console"
-	depends on PPC_RTAS
-	select UDBG_RTAS_CONSOLE
-	help
-	  Select this to enable early debugging via the RTAS console.
-
 config PPC_EARLY_DEBUG_PAS_REALMODE
 	bool "PA Semi real mode"
 	depends on PPC_PASEMI
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 1ff6ad4f6cd2..a7ab087d412c 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -70,6 +70,7 @@ BOOTCPPFLAGS	:= -nostdinc $(LINUXINCLUDE)
 BOOTCPPFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
 
 BOOTCFLAGS	:= $(BOOTTARGETFLAGS) \
+		   -std=gnu11 \
 		   -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -O2 \
 		   -msoft-float -mno-altivec -mno-vsx \
@@ -173,7 +174,6 @@ src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
 src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S
 src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
-src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
 src-plat-$(CONFIG_MVME7100) += motload-head.S mvme7100.c
 
 src-plat-$(CONFIG_PPC_MICROWATT) += fixed-head.S microwatt.c
@@ -276,7 +276,6 @@ quiet_cmd_wrap	= WRAP    $@
 
 image-$(CONFIG_PPC_PSERIES)		+= zImage.pseries
 image-$(CONFIG_PPC_POWERNV)		+= zImage.pseries
-image-$(CONFIG_PPC_IBM_CELL_BLADE)	+= zImage.pseries
 image-$(CONFIG_PPC_PS3)			+= dtbImage.ps3
 image-$(CONFIG_PPC_CHRP)		+= zImage.chrp
 image-$(CONFIG_PPC_EFIKA)		+= zImage.chrp
diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
index 269e930b3b0b..c4e4d2a9b460 100644
--- a/arch/powerpc/boot/dts/microwatt.dts
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -1,4 +1,5 @@
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	#size-cells = <0x02>;
@@ -8,6 +9,7 @@
 
 	aliases {
 		serial0 = &UART0;
+		ethernet = &enet0;
 	};
 
 	reserved-memory {
@@ -35,40 +37,79 @@
 
 		ibm,powerpc-cpu-features {
 			display-name = "Microwatt";
-			isa = <3000>;
+			isa = <3010>;
 			device_type = "cpu-features";
 			compatible = "ibm,powerpc-cpu-features";
 
 			mmu-radix {
 				isa = <3000>;
-				usable-privilege = <2>;
+				usable-privilege = <6>;
+				os-support = <0>;
 			};
 
 			little-endian {
-				isa = <2050>;
-				usable-privilege = <3>;
+				isa = <0>;
+				usable-privilege = <7>;
+				os-support = <0>;
 				hwcap-bit-nr = <1>;
 			};
 
 			cache-inhibited-large-page {
-				isa = <2040>;
-				usable-privilege = <2>;
+				isa = <0>;
+				usable-privilege = <6>;
+				os-support = <0>;
 			};
 
 			fixed-point-v3 {
 				isa = <3000>;
-				usable-privilege = <3>;
+				usable-privilege = <7>;
 			};
 
 			no-execute {
-				isa = <2010>;
+				isa = <0x00>;
 				usable-privilege = <2>;
+				os-support = <0>;
 			};
 
 			floating-point {
+				hfscr-bit-nr = <0>;
 				hwcap-bit-nr = <27>;
 				isa = <0>;
-				usable-privilege = <3>;
+				usable-privilege = <7>;
+				hv-support = <1>;
+				os-support = <0>;
+			};
+
+			prefixed-instructions {
+				hfscr-bit-nr = <13>;
+				fscr-bit-nr = <13>;
+				isa = <3010>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				hv-support = <1>;
+			};
+
+			tar {
+				hfscr-bit-nr = <8>;
+				fscr-bit-nr = <8>;
+				isa = <2070>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				hv-support = <1>;
+				hwcap-bit-nr = <58>;
+			};
+
+			control-register {
+				isa = <0>;
+				usable-privilege = <7>;
+			};
+
+			system-call-vectored {
+				isa = <3000>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				fscr-bit-nr = <12>;
+				hwcap-bit-nr = <52>;
 			};
 		};
 
@@ -101,6 +142,36 @@
 			ibm,mmu-lpid-bits = <12>;
 			ibm,mmu-pid-bits = <20>;
 		};
+
+		PowerPC,Microwatt@1 {
+			i-cache-sets = <2>;
+			ibm,dec-bits = <64>;
+			reservation-granule-size = <64>;
+			clock-frequency = <100000000>;
+			timebase-frequency = <100000000>;
+			i-tlb-sets = <1>;
+			ibm,ppc-interrupt-server#s = <1>;
+			i-cache-block-size = <64>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <2>;
+			i-tlb-size = <64>;
+			cpu-version = <0x990000>;
+			status = "okay";
+			i-cache-size = <0x1000>;
+			ibm,processor-radix-AP-encodings = <0x0c 0xa0000010 0x20000015 0x4000001e>;
+			tlb-size = <0>;
+			tlb-sets = <0>;
+			device_type = "cpu";
+			d-tlb-size = <128>;
+			d-tlb-sets = <2>;
+			reg = <1>;
+			general-purpose;
+			64-bit;
+			d-cache-size = <0x1000>;
+			ibm,chip-id = <0>;
+			ibm,mmu-lpid-bits = <12>;
+			ibm,mmu-pid-bits = <20>;
+		};
 	};
 
 	soc@c0000000 {
@@ -113,8 +184,8 @@
 
 		interrupt-controller@4000 {
 			compatible = "openpower,xics-presentation", "ibm,ppc-xicp";
-			ibm,interrupt-server-ranges = <0x0 0x1>;
-			reg = <0x4000 0x100>;
+			ibm,interrupt-server-ranges = <0x0 0x2>;
+			reg = <0x4000 0x10 0x4010 0x10>;
 		};
 
 		ICS: interrupt-controller@5000 {
@@ -138,7 +209,18 @@
 			interrupts = <0x10 0x1>;
 		};
 
-		ethernet@8020000 {
+		gpio: gpio@7000 {
+			device_type = "gpio";
+			compatible = "faraday,ftgpio010";
+			gpio-controller;
+			#gpio-cells = <2>;
+			reg = <0x7000 0x80>;
+			interrupts = <0x14 1>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		enet0: ethernet@8020000 {
 			compatible = "litex,liteeth";
 			reg = <0x8021000 0x100
 				0x8020800 0x100
@@ -160,7 +242,6 @@
 			reg-names = "phy", "core", "reader", "writer", "irq";
 			bus-width = <4>;
 			interrupts = <0x13 1>;
-			cap-sd-highspeed;
 			clocks = <&sys_clk>;
 		};
 	};
diff --git a/arch/powerpc/boot/rs6000.h b/arch/powerpc/boot/rs6000.h
index a9d879155ef9..16df8f3c43f1 100644
--- a/arch/powerpc/boot/rs6000.h
+++ b/arch/powerpc/boot/rs6000.h
@@ -1,11 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* IBM RS/6000 "XCOFF" file definitions for BFD.
    Copyright (C) 1990, 1991 Free Software Foundation, Inc.
-   FIXME: Can someone provide a transliteration of this name into ASCII?
-   Using the following chars caused a compiler warning on HIUX (so I replaced
-   them with octal escapes), and isn't useful without an understanding of what
-   character set it is.
-   Written by Mimi Ph\373\364ng-Th\345o V\365 of IBM
+   Written by Mimi Phuong-Thao Vo of IBM
    and John Gilmore of Cygnus Support.  */
 
 /********************** FILE HEADER **********************/
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 1db60fe13802..3d8dc822282a 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -234,10 +234,8 @@ fi
 
 # suppress some warnings in recent ld versions
 nowarn="-z noexecstack"
-if ! ld_is_lld; then
-	if [ "$LD_VERSION" -ge "$(echo 2.39 | ld_version)" ]; then
-		nowarn="$nowarn --no-warn-rwx-segments"
-	fi
+if "${CROSS}ld" -v --no-warn-rwx-segments >/dev/null 2>&1; then
+	nowarn="$nowarn --no-warn-rwx-segments"
 fi
 
 platformo=$object/"$platform".o
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index 2479ab62d12f..98221bda380d 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -91,5 +91,4 @@ CONFIG_AFFS_FS=m
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index 20891c413149..5757625469c4 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -85,8 +85,6 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
index 1715ff547442..b99caba8724a 100644
--- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
@@ -73,6 +73,5 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_932=y
 CONFIG_NLS_ISO8859_8=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index e65c0057147f..11163052fdba 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -80,5 +80,4 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
index 17714bf0ed40..312d39e4242c 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
@@ -72,5 +72,4 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
index 58fae5131fa7..ac27f99faab8 100644
--- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
@@ -75,6 +75,5 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index da6fc203e2dc..7beb36a41d45 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -221,9 +221,6 @@ CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_CRYPTO_CBC=y
 CONFIG_CRYPTO_MD5=y
diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig
index e7080497048d..0a42072fa23c 100644
--- a/arch/powerpc/configs/85xx/stx_gp3_defconfig
+++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig
@@ -60,8 +60,6 @@ CONFIG_CRAMFS=m
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=m
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_BDI_SWITCH=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 3a6381aa9fdc..488d03ae6d6c 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -132,7 +132,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_CRYPTO_HMAC=y
diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config
index 0cb24b33c88e..e7bd265fae5a 100644
--- a/arch/powerpc/configs/86xx-hw.config
+++ b/arch/powerpc/configs/86xx-hw.config
@@ -5,7 +5,6 @@ CONFIG_BROADCOM_PHY=y
 # CONFIG_CARDBUS is not set
 CONFIG_CHR_DEV_SG=y
 CONFIG_CHR_DEV_ST=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_HMAC=y
 CONFIG_DS1682=y
 CONFIG_EEPROM_LEGACY=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index 97f4d4851735..3c6445c98a85 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -44,7 +44,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig
index 200bb1ecb560..69ef3dc31c4b 100644
--- a/arch/powerpc/configs/amigaone_defconfig
+++ b/arch/powerpc/configs/amigaone_defconfig
@@ -106,7 +106,6 @@ CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index b33f0034990c..3347192b77b8 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -25,7 +25,6 @@ CONFIG_PS3_DISK=y
 CONFIG_PS3_ROM=m
 CONFIG_PS3_FLASH=m
 CONFIG_PS3_LPM=m
-CONFIG_PPC_IBM_CELL_BLADE=y
 CONFIG_RTAS_FLASH=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -133,7 +132,6 @@ CONFIG_SKGE=m
 CONFIG_SKY2=m
 CONFIG_GELIC_NET=m
 CONFIG_GELIC_WIRELESS=y
-CONFIG_SPIDER_NET=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO_I8042 is not set
diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig
index fb314f75ad4b..b799c95480ae 100644
--- a/arch/powerpc/configs/chrp32_defconfig
+++ b/arch/powerpc/configs/chrp32_defconfig
@@ -110,7 +110,6 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index 50cc59eb36cf..354180ab94bc 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -47,7 +47,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index 3009b0efaf34..2f81bc2d819e 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -15,7 +15,6 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CGROUPS=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_CPUSETS=y
 CONFIG_CRAMFS=y
 CONFIG_CRYPTO_MD4=y
@@ -112,7 +111,6 @@ CONFIG_QNX4FS_FS=m
 CONFIG_RCU_TRACE=y
 CONFIG_RESET_CONTROLLER=y
 CONFIG_ROOT_NFS=y
-CONFIG_SYSV_FS=m
 CONFIG_SYSVIPC=y
 CONFIG_TMPFS=y
 CONFIG_UBIFS_FS=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 9215bed53291..428f17b45513 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -231,12 +231,11 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index d77eeb525366..cdd99657b71b 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -82,7 +82,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_CIFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
index fa707de761be..b564f9e33a0d 100644
--- a/arch/powerpc/configs/linkstation_defconfig
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -125,8 +125,6 @@ CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_932=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 83c4710017e9..a815d9e5e3e8 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -97,7 +97,6 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index 6f449411abf7..dfbdd5e8e108 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -38,5 +38,3 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC32_SLICEBY4=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 77306be62e9e..9bc2758a6a9a 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -70,7 +70,6 @@ CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_DEV_TALITOS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
@@ -78,4 +77,4 @@ CONFIG_DEBUG_VM_PGTABLE=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_BDI_SWITCH=y
 CONFIG_PPC_EARLY_DEBUG=y
-CONFIG_GENERIC_PTDUMP=y
+CONFIG_PTDUMP_DEBUGFS=y
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index d1c7fd5bf34b..fa2b3b9c5945 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -107,8 +107,6 @@ CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_932=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 61993944db40..8bbf51b38480 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -159,7 +159,6 @@ CONFIG_NFSD=y
 CONFIG_NFSD_V4=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index e8b3f67bf3f5..1bc3466bc909 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -276,7 +276,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 6b6d7467fecf..379229c982a4 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -317,7 +317,7 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5_PPC=m
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 8b595f67068c..41c930f74ed4 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -90,7 +90,6 @@ CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_CRYPTO_ECB=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 465eb96c755e..3423c405cad4 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -51,7 +51,6 @@ CONFIG_PS3_DISK=m
 CONFIG_PS3_ROM=m
 CONFIG_PS3_FLASH=m
 CONFIG_PS3_LPM=m
-CONFIG_PPC_IBM_CELL_BLADE=y
 CONFIG_RTAS_FLASH=m
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -228,7 +227,6 @@ CONFIG_NETXEN_NIC=m
 CONFIG_SUNGEM=y
 CONFIG_GELIC_NET=m
 CONFIG_GELIC_WIRELESS=y
-CONFIG_SPIDER_NET=m
 CONFIG_BROADCOM_PHY=m
 CONFIG_MARVELL_PHY=y
 CONFIG_PPP=m
@@ -379,7 +377,7 @@ CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_IMA_ARCH_POLICY=y
 CONFIG_IMA_APPRAISE_MODSIG=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_SERPENT=m
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 4c05f4e4d505..90247b2a0ab0 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -207,7 +207,6 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
@@ -221,7 +220,7 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index ca0c90e95837..242c1fab9d46 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -485,7 +485,6 @@ CONFIG_VIA_VELOCITY=m
 CONFIG_PCMCIA_XIRC2PS=m
 CONFIG_FDDI=y
 CONFIG_SKFP=m
-CONFIG_NET_SB1000=m
 CONFIG_BROADCOM_PHY=m
 CONFIG_CICADA_PHY=m
 CONFIG_DAVICOM_PHY=m
@@ -986,7 +985,6 @@ CONFIG_MINIX_FS=m
 CONFIG_OMFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=m
 CONFIG_NFS_V3_ACL=y
@@ -1075,7 +1073,7 @@ CONFIG_SECURITY_NETWORK_XFRM=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 2b175ddf82f0..0b48d2b776c4 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -148,8 +148,6 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 9d44e6630908..2b71a6dc399e 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -78,7 +78,6 @@ CONFIG_VIRTIO_BLK=m
 CONFIG_BLK_DEV_NVME=m
 CONFIG_NVME_MULTIPATH=y
 CONFIG_EEPROM_AT24=m
-# CONFIG_CXL is not set
 # CONFIG_OCXL is not set
 CONFIG_BLK_DEV_SD=m
 CONFIG_BLK_DEV_SR=m
@@ -279,9 +278,6 @@ CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY=y
 # CONFIG_INTEGRITY is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
-CONFIG_CRC_ITU_T=y
-CONFIG_LIBCRC32C=y
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_IA64 is not set
 # CONFIG_XZ_DEC_ARM is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index 7a978d396991..e415222bd839 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -75,4 +75,3 @@ CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index 383c0966e92f..425f10837a18 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -54,7 +54,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 5017a697b67b..7c714a19221e 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -114,7 +114,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_CIFS=m
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index 5b315e9756b3..caaa359f4742 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -3,10 +3,12 @@
 menu "Accelerated Cryptographic Algorithms for CPU (powerpc)"
 
 config CRYPTO_CURVE25519_PPC64
-	tristate "Public key crypto: Curve25519 (PowerPC64)"
+	tristate
 	depends on PPC64 && CPU_LITTLE_ENDIAN
+	select CRYPTO_KPP
 	select CRYPTO_LIB_CURVE25519_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+	default CRYPTO_LIB_CURVE25519_INTERNAL
 	help
 	  Curve25519 algorithm
 
@@ -15,7 +17,6 @@ config CRYPTO_CURVE25519_PPC64
 
 config CRYPTO_MD5_PPC
 	tristate "Digests: MD5"
-	depends on PPC
 	select CRYPTO_HASH
 	help
 	  MD5 message digest algorithm (RFC1321)
@@ -24,7 +25,6 @@ config CRYPTO_MD5_PPC
 
 config CRYPTO_SHA1_PPC
 	tristate "Hash functions: SHA-1"
-	depends on PPC
 	help
 	  SHA-1 secure hash algorithm (FIPS 180)
 
@@ -32,27 +32,16 @@ config CRYPTO_SHA1_PPC
 
 config CRYPTO_SHA1_PPC_SPE
 	tristate "Hash functions: SHA-1 (SPE)"
-	depends on PPC && SPE
+	depends on SPE
 	help
 	  SHA-1 secure hash algorithm (FIPS 180)
 
 	  Architecture: powerpc using
 	  - SPE (Signal Processing Engine) extensions
 
-config CRYPTO_SHA256_PPC_SPE
-	tristate "Hash functions: SHA-224 and SHA-256 (SPE)"
-	depends on PPC && SPE
-	select CRYPTO_SHA256
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: powerpc using
-	  - SPE (Signal Processing Engine) extensions
-
 config CRYPTO_AES_PPC_SPE
 	tristate "Ciphers: AES, modes: ECB/CBC/CTR/XTS (SPE)"
-	depends on PPC && SPE
+	depends on SPE
 	select CRYPTO_SKCIPHER
 	help
 	  Block ciphers: AES cipher algorithms (FIPS-197)
@@ -90,32 +79,6 @@ config CRYPTO_AES_GCM_P10
 	  Support for cryptographic acceleration instructions on Power10 or
 	  later CPU. This module supports stitched acceleration for AES/GCM.
 
-config CRYPTO_CHACHA20_P10
-	tristate "Ciphers: ChaCha20, XChacha20, XChacha12 (P10 or later)"
-	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_CHACHA_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
-	  stream cipher algorithms
-
-	  Architecture: PowerPC64
-	  - Power10 or later
-	  - Little-endian
-
-config CRYPTO_POLY1305_P10
-	tristate "Hash functions: Poly1305 (P10 or later)"
-	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
-	select CRYPTO_HASH
-	select CRYPTO_LIB_POLY1305_GENERIC
-	help
-	  Poly1305 authenticator algorithm (RFC7539)
-
-	  Architecture: PowerPC64
-	  - Power10 or later
-	  - Little-endian
-
 config CRYPTO_DEV_VMX
         bool "Support for VMX cryptographic acceleration instructions"
         depends on PPC64 && VSX
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 9b38f4a7bc15..8c2936ae466f 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -9,10 +9,7 @@ obj-$(CONFIG_CRYPTO_AES_PPC_SPE) += aes-ppc-spe.o
 obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
-obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
 obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
-obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
-obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
 obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
 obj-$(CONFIG_CRYPTO_CURVE25519_PPC64) += curve25519-ppc64le.o
 
@@ -20,10 +17,7 @@ aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-
 md5-ppc-y := md5-asm.o md5-glue.o
 sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
-sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
 aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
-chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
-poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
 vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
 curve25519-ppc64le-y := curve25519-ppc64le-core.o curve25519-ppc64le_asm.o
 
@@ -51,3 +45,4 @@ $(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
 OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y
 OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y
 OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y
+OBJECT_FILES_NON_STANDARD_ghashp8-ppc.o := y
diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c
index 679f52794baf..85f4fd4b1bdc 100644
--- a/arch/powerpc/crypto/aes-gcm-p10-glue.c
+++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c
@@ -35,9 +35,9 @@ MODULE_ALIAS_CRYPTO("aes");
 asmlinkage int aes_p10_set_encrypt_key(const u8 *userKey, const int bits,
 				       void *key);
 asmlinkage void aes_p10_encrypt(const u8 *in, u8 *out, const void *key);
-asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
+asmlinkage void aes_p10_gcm_encrypt(const u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
-asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
+asmlinkage void aes_p10_gcm_decrypt(const u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
 asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]);
 asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable,
@@ -261,7 +261,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv,
 		return ret;
 
 	while ((nbytes = walk.nbytes) > 0 && ret == 0) {
-		u8 *src = walk.src.virt.addr;
+		const u8 *src = walk.src.virt.addr;
 		u8 *dst = walk.dst.virt.addr;
 		u8 buf[AES_BLOCK_SIZE];
 
diff --git a/arch/powerpc/crypto/aes.c b/arch/powerpc/crypto/aes.c
index ec06189fbf99..3f1e5e894902 100644
--- a/arch/powerpc/crypto/aes.c
+++ b/arch/powerpc/crypto/aes.c
@@ -7,15 +7,15 @@
  * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
  */
 
-#include <linux/types.h>
-#include <linux/err.h>
-#include <linux/crypto.h>
-#include <linux/delay.h>
 #include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
 #include <crypto/internal/cipher.h>
 #include <crypto/internal/simd.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include "aesp8-ppc.h"
 
diff --git a/arch/powerpc/crypto/aes_cbc.c b/arch/powerpc/crypto/aes_cbc.c
index ed0debc7acb5..5f2a4f375eef 100644
--- a/arch/powerpc/crypto/aes_cbc.c
+++ b/arch/powerpc/crypto/aes_cbc.c
@@ -12,6 +12,10 @@
 #include <crypto/aes.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include "aesp8-ppc.h"
 
diff --git a/arch/powerpc/crypto/aes_ctr.c b/arch/powerpc/crypto/aes_ctr.c
index 9a3da8cd62f3..e27c4036e711 100644
--- a/arch/powerpc/crypto/aes_ctr.c
+++ b/arch/powerpc/crypto/aes_ctr.c
@@ -12,6 +12,10 @@
 #include <crypto/aes.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include "aesp8-ppc.h"
 
@@ -69,9 +73,9 @@ static int p8_aes_ctr_setkey(struct crypto_skcipher *tfm, const u8 *key,
 static void p8_aes_ctr_final(const struct p8_aes_ctr_ctx *ctx,
 			     struct skcipher_walk *walk)
 {
+	const u8 *src = walk->src.virt.addr;
 	u8 *ctrblk = walk->iv;
 	u8 keystream[AES_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
 	u8 *dst = walk->dst.virt.addr;
 	unsigned int nbytes = walk->nbytes;
 
diff --git a/arch/powerpc/crypto/aes_xts.c b/arch/powerpc/crypto/aes_xts.c
index dabbccb41550..9440e771cede 100644
--- a/arch/powerpc/crypto/aes_xts.c
+++ b/arch/powerpc/crypto/aes_xts.c
@@ -13,6 +13,10 @@
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/xts.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include "aesp8-ppc.h"
 
diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c
deleted file mode 100644
index 7c728755852e..000000000000
--- a/arch/powerpc/crypto/chacha-p10-glue.c
+++ /dev/null
@@ -1,227 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * PowerPC P10 (ppc64le) accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright 2023- IBM Corp. All rights reserved.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
-#include <linux/sizes.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
-
-asmlinkage void chacha_p10le_8x(u32 *state, u8 *dst, const u8 *src,
-				unsigned int len, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
-
-static void vsx_begin(void)
-{
-	preempt_disable();
-	enable_kernel_vsx();
-}
-
-static void vsx_end(void)
-{
-	disable_kernel_vsx();
-	preempt_enable();
-}
-
-static void chacha_p10_do_8x(u32 *state, u8 *dst, const u8 *src,
-			     unsigned int bytes, int nrounds)
-{
-	unsigned int l = bytes & ~0x0FF;
-
-	if (l > 0) {
-		chacha_p10le_8x(state, dst, src, l, nrounds);
-		bytes -= l;
-		src += l;
-		dst += l;
-		state[12] += l / CHACHA_BLOCK_SIZE;
-	}
-
-	if (bytes > 0)
-		chacha_crypt_generic(state, dst, src, bytes, nrounds);
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
-	hchacha_block_generic(state, stream, nrounds);
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
-		       int nrounds)
-{
-	if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
-	    !crypto_simd_usable())
-		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
-	do {
-		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
-		vsx_begin();
-		chacha_p10_do_8x(state, dst, src, todo, nrounds);
-		vsx_end();
-
-		bytes -= todo;
-		src += todo;
-		dst += todo;
-	} while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_p10_stream_xor(struct skcipher_request *req,
-				 const struct chacha_ctx *ctx, const u8 *iv)
-{
-	struct skcipher_walk walk;
-	u32 state[16];
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-	if (err)
-		return err;
-
-	chacha_init_generic(state, ctx->key, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = rounddown(nbytes, walk.stride);
-
-		if (!crypto_simd_usable()) {
-			chacha_crypt_generic(state, walk.dst.virt.addr,
-					     walk.src.virt.addr, nbytes,
-					     ctx->nrounds);
-		} else {
-			vsx_begin();
-			chacha_p10_do_8x(state, walk.dst.virt.addr,
-				      walk.src.virt.addr, nbytes, ctx->nrounds);
-			vsx_end();
-		}
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-		if (err)
-			break;
-	}
-
-	return err;
-}
-
-static int chacha_p10(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return chacha_p10_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_p10(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct chacha_ctx subctx;
-	u32 state[16];
-	u8 real_iv[16];
-
-	chacha_init_generic(state, ctx->key, req->iv);
-	hchacha_block_arch(state, subctx.key, ctx->nrounds);
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_p10_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-p10",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_p10,
-		.decrypt		= chacha_p10,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-p10",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_p10,
-		.decrypt		= xchacha_p10,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-p10",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_p10,
-		.decrypt		= xchacha_p10,
-	}
-};
-
-static int __init chacha_p10_init(void)
-{
-	if (!cpu_has_feature(CPU_FTR_ARCH_31))
-		return 0;
-
-	static_branch_enable(&have_p10);
-
-	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit chacha_p10_exit(void)
-{
-	if (!static_branch_likely(&have_p10))
-		return;
-
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_p10_init);
-module_exit(chacha_p10_exit);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)");
-MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-p10");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-p10");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-p10");
diff --git a/arch/powerpc/crypto/ghash.c b/arch/powerpc/crypto/ghash.c
index 77eca20bc7ac..7308735bdb33 100644
--- a/arch/powerpc/crypto/ghash.c
+++ b/arch/powerpc/crypto/ghash.c
@@ -11,19 +11,18 @@
  *   Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
  */
 
-#include <linux/types.h>
-#include <linux/err.h>
-#include <linux/crypto.h>
-#include <linux/delay.h>
-#include <asm/simd.h>
+#include "aesp8-ppc.h"
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/gf128mul.h>
 #include <crypto/ghash.h>
-#include <crypto/scatterwalk.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/b128ops.h>
-#include "aesp8-ppc.h"
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
 
 void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
 void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
@@ -39,15 +38,12 @@ struct p8_ghash_ctx {
 
 struct p8_ghash_desc_ctx {
 	u64 shash[2];
-	u8 buffer[GHASH_DIGEST_SIZE];
-	int bytes;
 };
 
 static int p8_ghash_init(struct shash_desc *desc)
 {
 	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	dctx->bytes = 0;
 	memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
 	return 0;
 }
@@ -74,27 +70,30 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
 }
 
 static inline void __ghash_block(struct p8_ghash_ctx *ctx,
-				 struct p8_ghash_desc_ctx *dctx)
+				 struct p8_ghash_desc_ctx *dctx,
+				 const u8 *src)
 {
 	if (crypto_simd_usable()) {
 		preempt_disable();
 		pagefault_disable();
 		enable_kernel_vsx();
-		gcm_ghash_p8(dctx->shash, ctx->htable,
-				dctx->buffer, GHASH_DIGEST_SIZE);
+		gcm_ghash_p8(dctx->shash, ctx->htable, src, GHASH_BLOCK_SIZE);
 		disable_kernel_vsx();
 		pagefault_enable();
 		preempt_enable();
 	} else {
-		crypto_xor((u8 *)dctx->shash, dctx->buffer, GHASH_BLOCK_SIZE);
+		crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE);
 		gf128mul_lle((be128 *)dctx->shash, &ctx->key);
 	}
 }
 
-static inline void __ghash_blocks(struct p8_ghash_ctx *ctx,
-				  struct p8_ghash_desc_ctx *dctx,
-				  const u8 *src, unsigned int srclen)
+static inline int __ghash_blocks(struct p8_ghash_ctx *ctx,
+				 struct p8_ghash_desc_ctx *dctx,
+				 const u8 *src, unsigned int srclen)
 {
+	int remain = srclen - round_down(srclen, GHASH_BLOCK_SIZE);
+
+	srclen -= remain;
 	if (crypto_simd_usable()) {
 		preempt_disable();
 		pagefault_disable();
@@ -105,62 +104,38 @@ static inline void __ghash_blocks(struct p8_ghash_ctx *ctx,
 		pagefault_enable();
 		preempt_enable();
 	} else {
-		while (srclen >= GHASH_BLOCK_SIZE) {
+		do {
 			crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE);
 			gf128mul_lle((be128 *)dctx->shash, &ctx->key);
 			srclen -= GHASH_BLOCK_SIZE;
 			src += GHASH_BLOCK_SIZE;
-		}
+		} while (srclen);
 	}
+
+	return remain;
 }
 
 static int p8_ghash_update(struct shash_desc *desc,
 			   const u8 *src, unsigned int srclen)
 {
-	unsigned int len;
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
 	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	if (dctx->bytes) {
-		if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
-			memcpy(dctx->buffer + dctx->bytes, src,
-				srclen);
-			dctx->bytes += srclen;
-			return 0;
-		}
-		memcpy(dctx->buffer + dctx->bytes, src,
-			GHASH_DIGEST_SIZE - dctx->bytes);
-
-		__ghash_block(ctx, dctx);
-
-		src += GHASH_DIGEST_SIZE - dctx->bytes;
-		srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
-		dctx->bytes = 0;
-	}
-	len = srclen & ~(GHASH_DIGEST_SIZE - 1);
-	if (len) {
-		__ghash_blocks(ctx, dctx, src, len);
-		src += len;
-		srclen -= len;
-	}
-	if (srclen) {
-		memcpy(dctx->buffer, src, srclen);
-		dctx->bytes = srclen;
-	}
-	return 0;
+	return __ghash_blocks(ctx, dctx, src, srclen);
 }
 
-static int p8_ghash_final(struct shash_desc *desc, u8 *out)
+static int p8_ghash_finup(struct shash_desc *desc, const u8 *src,
+			  unsigned int len, u8 *out)
 {
-	int i;
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
 	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	if (dctx->bytes) {
-		for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
-			dctx->buffer[i] = 0;
-		__ghash_block(ctx, dctx);
-		dctx->bytes = 0;
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
+
+		memcpy(buf, src, len);
+		__ghash_block(ctx, dctx, buf);
+		memzero_explicit(buf, sizeof(buf));
 	}
 	memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
 	return 0;
@@ -170,14 +145,14 @@ struct shash_alg p8_ghash_alg = {
 	.digestsize = GHASH_DIGEST_SIZE,
 	.init = p8_ghash_init,
 	.update = p8_ghash_update,
-	.final = p8_ghash_final,
+	.finup = p8_ghash_finup,
 	.setkey = p8_ghash_setkey,
-	.descsize = sizeof(struct p8_ghash_desc_ctx)
-		+ sizeof(struct ghash_desc_ctx),
+	.descsize = sizeof(struct p8_ghash_desc_ctx),
 	.base = {
 		 .cra_name = "ghash",
 		 .cra_driver_name = "p8_ghash",
 		 .cra_priority = 1000,
+		 .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		 .cra_blocksize = GHASH_BLOCK_SIZE,
 		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
 		 .cra_module = THIS_MODULE,
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index c24f605033bd..204440a90cd8 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -8,25 +8,13 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/md5.h>
-#include <asm/byteorder.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
 extern void ppc_md5_transform(u32 *state, const u8 *src, u32 blocks);
 
-static inline void ppc_md5_clear_context(struct md5_state *sctx)
-{
-	int count = sizeof(struct md5_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct md5_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
 static int ppc_md5_init(struct shash_desc *desc)
 {
 	struct md5_state *sctx = shash_desc_ctx(desc);
@@ -44,79 +32,34 @@ static int ppc_md5_update(struct shash_desc *desc, const u8 *data,
 			unsigned int len)
 {
 	struct md5_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->byte_count & 0x3f;
-	unsigned int avail = 64 - offset;
-	const u8 *src = data;
 
-	sctx->byte_count += len;
-
-	if (avail > len) {
-		memcpy((char *)sctx->block + offset, src, len);
-		return 0;
-	}
-
-	if (offset) {
-		memcpy((char *)sctx->block + offset, src, avail);
-		ppc_md5_transform(sctx->hash, (const u8 *)sctx->block, 1);
-		len -= avail;
-		src += avail;
-	}
-
-	if (len > 63) {
-		ppc_md5_transform(sctx->hash, src, len >> 6);
-		src += len & ~0x3f;
-		len &= 0x3f;
-	}
-
-	memcpy((char *)sctx->block, src, len);
-	return 0;
+	sctx->byte_count += round_down(len, MD5_HMAC_BLOCK_SIZE);
+	ppc_md5_transform(sctx->hash, data, len >> 6);
+	return len - round_down(len, MD5_HMAC_BLOCK_SIZE);
 }
 
-static int ppc_md5_final(struct shash_desc *desc, u8 *out)
+static int ppc_md5_finup(struct shash_desc *desc, const u8 *src,
+			 unsigned int offset, u8 *out)
 {
 	struct md5_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->byte_count & 0x3f;
-	const u8 *src = (const u8 *)sctx->block;
-	u8 *p = (u8 *)src + offset;
-	int padlen = 55 - offset;
-	__le64 *pbits = (__le64 *)((char *)sctx->block + 56);
+	__le64 block[MD5_BLOCK_WORDS] = {};
+	u8 *p = memcpy(block, src, offset);
 	__le32 *dst = (__le32 *)out;
+	__le64 *pbits;
 
+	src = p;
+	p += offset;
 	*p++ = 0x80;
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_md5_transform(sctx->hash, src, 1);
-		p = (char *)sctx->block;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
+	sctx->byte_count += offset;
+	pbits = &block[(MD5_BLOCK_WORDS / (offset > 55 ? 1 : 2)) - 1];
 	*pbits = cpu_to_le64(sctx->byte_count << 3);
-	ppc_md5_transform(sctx->hash, src, 1);
+	ppc_md5_transform(sctx->hash, src, (pbits - block + 1) / 8);
+	memzero_explicit(block, sizeof(block));
 
 	dst[0] = cpu_to_le32(sctx->hash[0]);
 	dst[1] = cpu_to_le32(sctx->hash[1]);
 	dst[2] = cpu_to_le32(sctx->hash[2]);
 	dst[3] = cpu_to_le32(sctx->hash[3]);
-
-	ppc_md5_clear_context(sctx);
-	return 0;
-}
-
-static int ppc_md5_export(struct shash_desc *desc, void *out)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int ppc_md5_import(struct shash_desc *desc, const void *in)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
 	return 0;
 }
 
@@ -124,15 +67,13 @@ static struct shash_alg alg = {
 	.digestsize	=	MD5_DIGEST_SIZE,
 	.init		=	ppc_md5_init,
 	.update		=	ppc_md5_update,
-	.final		=	ppc_md5_final,
-	.export		=	ppc_md5_export,
-	.import		=	ppc_md5_import,
-	.descsize	=	sizeof(struct md5_state),
-	.statesize	=	sizeof(struct md5_state),
+	.finup		=	ppc_md5_finup,
+	.descsize	=	MD5_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"md5",
 		.cra_driver_name=	"md5-ppc",
 		.cra_priority	=	200,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/poly1305-p10-glue.c b/arch/powerpc/crypto/poly1305-p10-glue.c
deleted file mode 100644
index 369686e9370b..000000000000
--- a/arch/powerpc/crypto/poly1305-p10-glue.c
+++ /dev/null
@@ -1,186 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Poly1305 authenticator algorithm, RFC7539.
- *
- * Copyright 2023- IBM Corp. All rights reserved.
- */
-
-#include <crypto/algapi.h>
-#include <linux/crypto.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/jump_label.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/cpufeature.h>
-#include <linux/unaligned.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
-
-asmlinkage void poly1305_p10le_4blocks(void *h, const u8 *m, u32 mlen);
-asmlinkage void poly1305_64s(void *h, const u8 *m, u32 mlen, int highbit);
-asmlinkage void poly1305_emit_64(void *h, void *s, u8 *dst);
-
-static void vsx_begin(void)
-{
-	preempt_disable();
-	enable_kernel_vsx();
-}
-
-static void vsx_end(void)
-{
-	disable_kernel_vsx();
-	preempt_enable();
-}
-
-static int crypto_poly1305_p10_init(struct shash_desc *desc)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	poly1305_core_init(&dctx->h);
-	dctx->buflen = 0;
-	dctx->rset = 0;
-	dctx->sset = false;
-
-	return 0;
-}
-
-static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx,
-					       const u8 *inp, unsigned int len)
-{
-	unsigned int acc = 0;
-
-	if (unlikely(!dctx->sset)) {
-		if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) {
-			struct poly1305_core_key *key = &dctx->core_r;
-
-			key->key.r64[0] = get_unaligned_le64(&inp[0]);
-			key->key.r64[1] = get_unaligned_le64(&inp[8]);
-			inp += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			acc += POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (len >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(&inp[0]);
-			dctx->s[1] = get_unaligned_le32(&inp[4]);
-			dctx->s[2] = get_unaligned_le32(&inp[8]);
-			dctx->s[3] = get_unaligned_le32(&inp[12]);
-			acc += POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-	}
-	return acc;
-}
-
-static int crypto_poly1305_p10_update(struct shash_desc *desc,
-				      const u8 *src, unsigned int srclen)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-	unsigned int bytes, used;
-
-	if (unlikely(dctx->buflen)) {
-		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		srclen -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf,
-							       POLY1305_BLOCK_SIZE))) {
-				vsx_begin();
-				poly1305_64s(&dctx->h, dctx->buf,
-						  POLY1305_BLOCK_SIZE, 1);
-				vsx_end();
-			}
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
-		used = crypto_poly1305_setdctxkey(dctx, src, bytes);
-		if (likely(used)) {
-			srclen -= used;
-			src += used;
-		}
-		if (crypto_simd_usable() && (srclen >= POLY1305_BLOCK_SIZE*4)) {
-			vsx_begin();
-			poly1305_p10le_4blocks(&dctx->h, src, srclen);
-			vsx_end();
-			src += srclen - (srclen % (POLY1305_BLOCK_SIZE * 4));
-			srclen %= POLY1305_BLOCK_SIZE * 4;
-		}
-		while (srclen >= POLY1305_BLOCK_SIZE) {
-			vsx_begin();
-			poly1305_64s(&dctx->h, src, POLY1305_BLOCK_SIZE, 1);
-			vsx_end();
-			srclen -= POLY1305_BLOCK_SIZE;
-			src += POLY1305_BLOCK_SIZE;
-		}
-	}
-
-	if (unlikely(srclen)) {
-		dctx->buflen = srclen;
-		memcpy(dctx->buf, src, srclen);
-	}
-
-	return 0;
-}
-
-static int crypto_poly1305_p10_final(struct shash_desc *desc, u8 *dst)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(!dctx->sset))
-		return -ENOKEY;
-
-	if ((dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		vsx_begin();
-		poly1305_64s(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-		vsx_end();
-		dctx->buflen = 0;
-	}
-
-	poly1305_emit_64(&dctx->h, &dctx->s, dst);
-	return 0;
-}
-
-static struct shash_alg poly1305_alg = {
-	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= crypto_poly1305_p10_init,
-	.update		= crypto_poly1305_p10_update,
-	.final		= crypto_poly1305_p10_final,
-	.descsize	= sizeof(struct poly1305_desc_ctx),
-	.base		= {
-		.cra_name		= "poly1305",
-		.cra_driver_name	= "poly1305-p10",
-		.cra_priority		= 300,
-		.cra_blocksize		= POLY1305_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	},
-};
-
-static int __init poly1305_p10_init(void)
-{
-	return crypto_register_shash(&poly1305_alg);
-}
-
-static void __exit poly1305_p10_exit(void)
-{
-	crypto_unregister_shash(&poly1305_alg);
-}
-
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, poly1305_p10_init);
-module_exit(poly1305_p10_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
-MODULE_DESCRIPTION("Optimized Poly1305 for P10");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-p10");
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
index 9170892a8557..04c88e173ce1 100644
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ b/arch/powerpc/crypto/sha1-spe-glue.c
@@ -7,16 +7,13 @@
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
  */
 
+#include <asm/switch_to.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <asm/byteorder.h>
-#include <asm/switch_to.h>
-#include <linux/hardirq.h>
+#include <linux/kernel.h>
+#include <linux/preempt.h>
+#include <linux/module.h>
 
 /*
  * MAX_BYTES defines the number of bytes that are allowed to be processed
@@ -30,7 +27,7 @@
  */
 #define MAX_BYTES 2048
 
-extern void ppc_spe_sha1_transform(u32 *state, const u8 *src, u32 blocks);
+asmlinkage void ppc_spe_sha1_transform(u32 *state, const u8 *src, u32 blocks);
 
 static void spe_begin(void)
 {
@@ -46,126 +43,45 @@ static void spe_end(void)
 	preempt_enable();
 }
 
-static inline void ppc_sha1_clear_context(struct sha1_state *sctx)
+static void ppc_spe_sha1_block(struct sha1_state *sctx, const u8 *src,
+			       int blocks)
 {
-	int count = sizeof(struct sha1_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct sha1_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
-static int ppc_spe_sha1_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	const unsigned int avail = 64 - offset;
-	unsigned int bytes;
-	const u8 *src = data;
-
-	if (avail > len) {
-		sctx->count += len;
-		memcpy((char *)sctx->buffer + offset, src, len);
-		return 0;
-	}
-
-	sctx->count += len;
-
-	if (offset) {
-		memcpy((char *)sctx->buffer + offset, src, avail);
+	do {
+		int unit = min(blocks, MAX_BYTES / SHA1_BLOCK_SIZE);
 
 		spe_begin();
-		ppc_spe_sha1_transform(sctx->state, (const u8 *)sctx->buffer, 1);
+		ppc_spe_sha1_transform(sctx->state, src, unit);
 		spe_end();
 
-		len -= avail;
-		src += avail;
-	}
-
-	while (len > 63) {
-		bytes = (len > MAX_BYTES) ? MAX_BYTES : len;
-		bytes = bytes & ~0x3f;
-
-		spe_begin();
-		ppc_spe_sha1_transform(sctx->state, src, bytes >> 6);
-		spe_end();
-
-		src += bytes;
-		len -= bytes;
-	}
-
-	memcpy((char *)sctx->buffer, src, len);
-	return 0;
-}
-
-static int ppc_spe_sha1_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	char *p = (char *)sctx->buffer + offset;
-	int padlen;
-	__be64 *pbits = (__be64 *)(((char *)&sctx->buffer) + 56);
-	__be32 *dst = (__be32 *)out;
-
-	padlen = 55 - offset;
-	*p++ = 0x80;
-
-	spe_begin();
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1);
-		p = (char *)sctx->buffer;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
-	*pbits = cpu_to_be64(sctx->count << 3);
-	ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1);
-
-	spe_end();
-
-	dst[0] = cpu_to_be32(sctx->state[0]);
-	dst[1] = cpu_to_be32(sctx->state[1]);
-	dst[2] = cpu_to_be32(sctx->state[2]);
-	dst[3] = cpu_to_be32(sctx->state[3]);
-	dst[4] = cpu_to_be32(sctx->state[4]);
-
-	ppc_sha1_clear_context(sctx);
-	return 0;
+		src += unit * SHA1_BLOCK_SIZE;
+		blocks -= unit;
+	} while (blocks);
 }
 
-static int ppc_spe_sha1_export(struct shash_desc *desc, void *out)
+static int ppc_spe_sha1_update(struct shash_desc *desc, const u8 *data,
+			unsigned int len)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
+	return sha1_base_do_update_blocks(desc, data, len, ppc_spe_sha1_block);
 }
 
-static int ppc_spe_sha1_import(struct shash_desc *desc, const void *in)
+static int ppc_spe_sha1_finup(struct shash_desc *desc, const u8 *src,
+			      unsigned int len, u8 *out)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
+	sha1_base_do_finup(desc, src, len, ppc_spe_sha1_block);
+	return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	ppc_spe_sha1_update,
-	.final		=	ppc_spe_sha1_final,
-	.export		=	ppc_spe_sha1_export,
-	.import		=	ppc_spe_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
+	.finup		=	ppc_spe_sha1_finup,
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-ppc-spe",
 		.cra_priority	=	300,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index f283bbd3f121..4593946aa9b3 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -13,107 +13,46 @@
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  */
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <asm/byteorder.h>
-
-void powerpc_sha_transform(u32 *state, const u8 *src);
-
-static int powerpc_sha1_update(struct shash_desc *desc, const u8 *data,
-			       unsigned int len)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial, done;
-	const u8 *src;
-
-	partial = sctx->count & 0x3f;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) > 63) {
-
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buffer + partial, data, done + 64);
-			src = sctx->buffer;
-		}
-
-		do {
-			powerpc_sha_transform(sctx->state, src);
-			done += 64;
-			src = data + done;
-		} while (done + 63 < len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buffer + partial, src, len - done);
-
-	return 0;
-}
+#include <linux/kernel.h>
+#include <linux/module.h>
 
+asmlinkage void powerpc_sha_transform(u32 *state, const u8 *src);
 
-/* Add padding and return the message digest. */
-static int powerpc_sha1_final(struct shash_desc *desc, u8 *out)
+static void powerpc_sha_block(struct sha1_state *sctx, const u8 *data,
+			      int blocks)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	__be32 *dst = (__be32 *)out;
-	u32 i, index, padlen;
-	__be64 bits;
-	static const u8 padding[64] = { 0x80, };
-
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64 */
-	index = sctx->count & 0x3f;
-	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	powerpc_sha1_update(desc, padding, padlen);
-
-	/* Append length */
-	powerpc_sha1_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	/* Store state in digest */
-	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof *sctx);
-
-	return 0;
+	do {
+		powerpc_sha_transform(sctx->state, data);
+		data += 64;
+	} while (--blocks);
 }
 
-static int powerpc_sha1_export(struct shash_desc *desc, void *out)
+static int powerpc_sha1_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
+	return sha1_base_do_update_blocks(desc, data, len, powerpc_sha_block);
 }
 
-static int powerpc_sha1_import(struct shash_desc *desc, const void *in)
+/* Add padding and return the message digest. */
+static int powerpc_sha1_finup(struct shash_desc *desc, const u8 *src,
+			      unsigned int len, u8 *out)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
+	sha1_base_do_finup(desc, src, len, powerpc_sha_block);
+	return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	powerpc_sha1_update,
-	.final		=	powerpc_sha1_final,
-	.export		=	powerpc_sha1_export,
-	.import		=	powerpc_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
+	.finup		=	powerpc_sha1_finup,
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-powerpc",
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
deleted file mode 100644
index 2997d13236e0..000000000000
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ /dev/null
@@ -1,235 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for SHA-256 implementation for SPE instructions (PPC)
- *
- * Based on generic implementation. The assembler module takes care 
- * about the SPE registers so it can run from interrupt context.
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <asm/byteorder.h>
-#include <asm/switch_to.h>
-#include <linux/hardirq.h>
-
-/*
- * MAX_BYTES defines the number of bytes that are allowed to be processed
- * between preempt_disable() and preempt_enable(). SHA256 takes ~2,000
- * operations per 64 bytes. e500 cores can issue two arithmetic instructions
- * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
- * Thus 1KB of input data will need an estimated maximum of 18,000 cycles.
- * Headroom for cache misses included. Even with the low end model clocked
- * at 667 MHz this equals to a critical time window of less than 27us.
- *
- */
-#define MAX_BYTES 1024
-
-extern void ppc_spe_sha256_transform(u32 *state, const u8 *src, u32 blocks);
-
-static void spe_begin(void)
-{
-	/* We just start SPE operations and will save SPE registers later. */
-	preempt_disable();
-	enable_kernel_spe();
-}
-
-static void spe_end(void)
-{
-	disable_kernel_spe();
-	/* reenable preemption */
-	preempt_enable();
-}
-
-static inline void ppc_sha256_clear_context(struct sha256_state *sctx)
-{
-	int count = sizeof(struct sha256_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct sha256_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
-static int ppc_spe_sha256_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	const unsigned int avail = 64 - offset;
-	unsigned int bytes;
-	const u8 *src = data;
-
-	if (avail > len) {
-		sctx->count += len;
-		memcpy((char *)sctx->buf + offset, src, len);
-		return 0;
-	}
-
-	sctx->count += len;
-
-	if (offset) {
-		memcpy((char *)sctx->buf + offset, src, avail);
-
-		spe_begin();
-		ppc_spe_sha256_transform(sctx->state, (const u8 *)sctx->buf, 1);
-		spe_end();
-
-		len -= avail;
-		src += avail;
-	}
-
-	while (len > 63) {
-		/* cut input data into smaller blocks */
-		bytes = (len > MAX_BYTES) ? MAX_BYTES : len;
-		bytes = bytes & ~0x3f;
-
-		spe_begin();
-		ppc_spe_sha256_transform(sctx->state, src, bytes >> 6);
-		spe_end();
-
-		src += bytes;
-		len -= bytes;
-	}
-
-	memcpy((char *)sctx->buf, src, len);
-	return 0;
-}
-
-static int ppc_spe_sha256_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	char *p = (char *)sctx->buf + offset;
-	int padlen;
-	__be64 *pbits = (__be64 *)(((char *)&sctx->buf) + 56);
-	__be32 *dst = (__be32 *)out;
-
-	padlen = 55 - offset;
-	*p++ = 0x80;
-
-	spe_begin();
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_spe_sha256_transform(sctx->state, sctx->buf, 1);
-		p = (char *)sctx->buf;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
-	*pbits = cpu_to_be64(sctx->count << 3);
-	ppc_spe_sha256_transform(sctx->state, sctx->buf, 1);
-
-	spe_end();
-
-	dst[0] = cpu_to_be32(sctx->state[0]);
-	dst[1] = cpu_to_be32(sctx->state[1]);
-	dst[2] = cpu_to_be32(sctx->state[2]);
-	dst[3] = cpu_to_be32(sctx->state[3]);
-	dst[4] = cpu_to_be32(sctx->state[4]);
-	dst[5] = cpu_to_be32(sctx->state[5]);
-	dst[6] = cpu_to_be32(sctx->state[6]);
-	dst[7] = cpu_to_be32(sctx->state[7]);
-
-	ppc_sha256_clear_context(sctx);
-	return 0;
-}
-
-static int ppc_spe_sha224_final(struct shash_desc *desc, u8 *out)
-{
-	__be32 D[SHA256_DIGEST_SIZE >> 2];
-	__be32 *dst = (__be32 *)out;
-
-	ppc_spe_sha256_final(desc, (u8 *)D);
-
-	/* avoid bytewise memcpy */
-	dst[0] = D[0];
-	dst[1] = D[1];
-	dst[2] = D[2];
-	dst[3] = D[3];
-	dst[4] = D[4];
-	dst[5] = D[5];
-	dst[6] = D[6];
-
-	/* clear sensitive data */
-	memzero_explicit(D, SHA256_DIGEST_SIZE);
-	return 0;
-}
-
-static int ppc_spe_sha256_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int ppc_spe_sha256_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg algs[2] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	ppc_spe_sha256_update,
-	.final		=	ppc_spe_sha256_final,
-	.export		=	ppc_spe_sha256_export,
-	.import		=	ppc_spe_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"sha256-ppc-spe",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	ppc_spe_sha256_update,
-	.final		=	ppc_spe_sha224_final,
-	.export		=	ppc_spe_sha256_export,
-	.import		=	ppc_spe_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"sha224-ppc-spe",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init ppc_spe_sha256_mod_init(void)
-{
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit ppc_spe_sha256_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(ppc_spe_sha256_mod_init);
-module_exit(ppc_spe_sha256_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, SPE optimized");
-
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha224-ppc-spe");
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha256-ppc-spe");
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index f0bba9c5f9c3..bb786694dd26 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -94,4 +94,10 @@ static inline int check_and_get_huge_psize(int shift)
 	return mmu_psize;
 }
 
+#define arch_has_huge_bootmem_alloc arch_has_huge_bootmem_alloc
+
+static inline bool arch_has_huge_bootmem_alloc(void)
+{
+	return (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled());
+}
 #endif
diff --git a/arch/powerpc/include/asm/cell-pmu.h b/arch/powerpc/include/asm/cell-pmu.h
index 6a79b5d1c44f..7fbefd64b4fb 100644
--- a/arch/powerpc/include/asm/cell-pmu.h
+++ b/arch/powerpc/include/asm/cell-pmu.h
@@ -20,36 +20,9 @@
 
 /* Macros for the pm_control register. */
 #define CBE_PM_16BIT_CTR(ctr)              (1 << (24 - ((ctr) & (NR_PHYS_CTRS - 1))))
-#define CBE_PM_ENABLE_PERF_MON             0x80000000
-#define CBE_PM_STOP_AT_MAX                 0x40000000
-#define CBE_PM_TRACE_MODE_GET(pm_control)  (((pm_control) >> 28) & 0x3)
-#define CBE_PM_TRACE_MODE_SET(mode)        (((mode)  & 0x3) << 28)
-#define CBE_PM_TRACE_BUF_OVFLW(bit)        (((bit) & 0x1) << 17)
-#define CBE_PM_COUNT_MODE_SET(count)       (((count) & 0x3) << 18)
-#define CBE_PM_FREEZE_ALL_CTRS             0x00100000
-#define CBE_PM_ENABLE_EXT_TRACE            0x00008000
-#define CBE_PM_SPU_ADDR_TRACE_SET(msk)     (((msk) & 0x3) << 9)
 
 /* Macros for the trace_address register. */
-#define CBE_PM_TRACE_BUF_FULL              0x00000800
 #define CBE_PM_TRACE_BUF_EMPTY             0x00000400
-#define CBE_PM_TRACE_BUF_DATA_COUNT(ta)    ((ta) & 0x3ff)
-#define CBE_PM_TRACE_BUF_MAX_COUNT         0x400
-
-/* Macros for the pm07_control registers. */
-#define CBE_PM_CTR_INPUT_MUX(pm07_control) (((pm07_control) >> 26) & 0x3f)
-#define CBE_PM_CTR_INPUT_CONTROL           0x02000000
-#define CBE_PM_CTR_POLARITY                0x01000000
-#define CBE_PM_CTR_COUNT_CYCLES            0x00800000
-#define CBE_PM_CTR_ENABLE                  0x00400000
-#define PM07_CTR_INPUT_MUX(x)              (((x) & 0x3F) << 26)
-#define PM07_CTR_INPUT_CONTROL(x)          (((x) & 1) << 25)
-#define PM07_CTR_POLARITY(x)               (((x) & 1) << 24)
-#define PM07_CTR_COUNT_CYCLES(x)           (((x) & 1) << 23)
-#define PM07_CTR_ENABLE(x)                 (((x) & 1) << 22)
-
-/* Macros for the pm_status register. */
-#define CBE_PM_CTR_OVERFLOW_INTR(ctr)      (1 << (31 - ((ctr) & 7)))
 
 enum pm_reg_name {
 	group_control,
@@ -62,33 +35,4 @@ enum pm_reg_name {
 	pm_start_stop,
 };
 
-/* Routines for reading/writing the PMU registers. */
-extern u32  cbe_read_phys_ctr(u32 cpu, u32 phys_ctr);
-extern void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val);
-extern u32  cbe_read_ctr(u32 cpu, u32 ctr);
-extern void cbe_write_ctr(u32 cpu, u32 ctr, u32 val);
-
-extern u32  cbe_read_pm07_control(u32 cpu, u32 ctr);
-extern void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val);
-extern u32  cbe_read_pm(u32 cpu, enum pm_reg_name reg);
-extern void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val);
-
-extern u32  cbe_get_ctr_size(u32 cpu, u32 phys_ctr);
-extern void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size);
-
-extern void cbe_enable_pm(u32 cpu);
-extern void cbe_disable_pm(u32 cpu);
-
-extern void cbe_read_trace_buffer(u32 cpu, u64 *buf);
-
-extern void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask);
-extern void cbe_disable_pm_interrupts(u32 cpu);
-extern u32  cbe_get_and_clear_pm_interrupts(u32 cpu);
-extern void cbe_sync_irq(int node);
-
-#define CBE_COUNT_SUPERVISOR_MODE       0
-#define CBE_COUNT_HYPERVISOR_MODE       1
-#define CBE_COUNT_PROBLEM_MODE          2
-#define CBE_COUNT_ALL_MODES             3
-
 #endif /* __ASM_CELL_PMU_H__ */
diff --git a/arch/powerpc/include/asm/cell-regs.h b/arch/powerpc/include/asm/cell-regs.h
index e1c431ef30e0..20f7339a3d4a 100644
--- a/arch/powerpc/include/asm/cell-regs.h
+++ b/arch/powerpc/include/asm/cell-regs.h
@@ -18,293 +18,6 @@
 
 #include <asm/cell-pmu.h>
 
-/*
- *
- * Some HID register definitions
- *
- */
-
-/* CBE specific HID0 bits */
-#define HID0_CBE_THERM_WAKEUP	0x0000020000000000ul
-#define HID0_CBE_SYSERR_WAKEUP	0x0000008000000000ul
-#define HID0_CBE_THERM_INT_EN	0x0000000400000000ul
-#define HID0_CBE_SYSERR_INT_EN	0x0000000200000000ul
-
-#define MAX_CBE		2
-
-/*
- *
- * Pervasive unit register definitions
- *
- */
-
-union spe_reg {
-	u64 val;
-	u8 spe[8];
-};
-
-union ppe_spe_reg {
-	u64 val;
-	struct {
-		u32 ppe;
-		u32 spe;
-	};
-};
-
-
-struct cbe_pmd_regs {
-	/* Debug Bus Control */
-	u64	pad_0x0000;					/* 0x0000 */
-
-	u64	group_control;					/* 0x0008 */
-
-	u8	pad_0x0010_0x00a8 [0x00a8 - 0x0010];		/* 0x0010 */
-
-	u64	debug_bus_control;				/* 0x00a8 */
-
-	u8	pad_0x00b0_0x0100 [0x0100 - 0x00b0];		/* 0x00b0 */
-
-	u64	trace_aux_data;					/* 0x0100 */
-	u64	trace_buffer_0_63;				/* 0x0108 */
-	u64	trace_buffer_64_127;				/* 0x0110 */
-	u64	trace_address;					/* 0x0118 */
-	u64	ext_tr_timer;					/* 0x0120 */
-
-	u8	pad_0x0128_0x0400 [0x0400 - 0x0128];		/* 0x0128 */
-
-	/* Performance Monitor */
-	u64	pm_status;					/* 0x0400 */
-	u64	pm_control;					/* 0x0408 */
-	u64	pm_interval;					/* 0x0410 */
-	u64	pm_ctr[4];					/* 0x0418 */
-	u64	pm_start_stop;					/* 0x0438 */
-	u64	pm07_control[8];				/* 0x0440 */
-
-	u8	pad_0x0480_0x0800 [0x0800 - 0x0480];		/* 0x0480 */
-
-	/* Thermal Sensor Registers */
-	union	spe_reg	ts_ctsr1;				/* 0x0800 */
-	u64	ts_ctsr2;					/* 0x0808 */
-	union	spe_reg	ts_mtsr1;				/* 0x0810 */
-	u64	ts_mtsr2;					/* 0x0818 */
-	union	spe_reg	ts_itr1;				/* 0x0820 */
-	u64	ts_itr2;					/* 0x0828 */
-	u64	ts_gitr;					/* 0x0830 */
-	u64	ts_isr;						/* 0x0838 */
-	u64	ts_imr;						/* 0x0840 */
-	union	spe_reg	tm_cr1;					/* 0x0848 */
-	u64	tm_cr2;						/* 0x0850 */
-	u64	tm_simr;					/* 0x0858 */
-	union	ppe_spe_reg tm_tpr;				/* 0x0860 */
-	union	spe_reg	tm_str1;				/* 0x0868 */
-	u64	tm_str2;					/* 0x0870 */
-	union	ppe_spe_reg tm_tsr;				/* 0x0878 */
-
-	/* Power Management */
-	u64	pmcr;						/* 0x0880 */
-#define CBE_PMD_PAUSE_ZERO_CONTROL	0x10000
-	u64	pmsr;						/* 0x0888 */
-
-	/* Time Base Register */
-	u64	tbr;						/* 0x0890 */
-
-	u8	pad_0x0898_0x0c00 [0x0c00 - 0x0898];		/* 0x0898 */
-
-	/* Fault Isolation Registers */
-	u64	checkstop_fir;					/* 0x0c00 */
-	u64	recoverable_fir;				/* 0x0c08 */
-	u64	spec_att_mchk_fir;				/* 0x0c10 */
-	u32	fir_mode_reg;					/* 0x0c18 */
-	u8	pad_0x0c1c_0x0c20 [4];				/* 0x0c1c */
-#define CBE_PMD_FIR_MODE_M8		0x00800
-	u64	fir_enable_mask;				/* 0x0c20 */
-
-	u8	pad_0x0c28_0x0ca8 [0x0ca8 - 0x0c28];		/* 0x0c28 */
-	u64	ras_esc_0;					/* 0x0ca8 */
-	u8	pad_0x0cb0_0x1000 [0x1000 - 0x0cb0];		/* 0x0cb0 */
-};
-
-extern struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np);
-extern struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu);
-
-/*
- * PMU shadow registers
- *
- * Many of the registers in the performance monitoring unit are write-only,
- * so we need to save a copy of what we write to those registers.
- *
- * The actual data counters are read/write. However, writing to the counters
- * only takes effect if the PMU is enabled. Otherwise the value is stored in
- * a hardware latch until the next time the PMU is enabled. So we save a copy
- * of the counter values if we need to read them back while the PMU is
- * disabled. The counter_value_in_latch field is a bitmap indicating which
- * counters currently have a value waiting to be written.
- */
-
-struct cbe_pmd_shadow_regs {
-	u32 group_control;
-	u32 debug_bus_control;
-	u32 trace_address;
-	u32 ext_tr_timer;
-	u32 pm_status;
-	u32 pm_control;
-	u32 pm_interval;
-	u32 pm_start_stop;
-	u32 pm07_control[NR_CTRS];
-
-	u32 pm_ctr[NR_PHYS_CTRS];
-	u32 counter_value_in_latch;
-};
-
-extern struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np);
-extern struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu);
-
-/*
- *
- * IIC unit register definitions
- *
- */
-
-struct cbe_iic_pending_bits {
-	u32 data;
-	u8 flags;
-	u8 class;
-	u8 source;
-	u8 prio;
-};
-
-#define CBE_IIC_IRQ_VALID	0x80
-#define CBE_IIC_IRQ_IPI		0x40
-
-struct cbe_iic_thread_regs {
-	struct cbe_iic_pending_bits pending;
-	struct cbe_iic_pending_bits pending_destr;
-	u64 generate;
-	u64 prio;
-};
-
-struct cbe_iic_regs {
-	u8	pad_0x0000_0x0400[0x0400 - 0x0000];		/* 0x0000 */
-
-	/* IIC interrupt registers */
-	struct	cbe_iic_thread_regs thread[2];			/* 0x0400 */
-
-	u64	iic_ir;						/* 0x0440 */
-#define CBE_IIC_IR_PRIO(x)      (((x) & 0xf) << 12)
-#define CBE_IIC_IR_DEST_NODE(x) (((x) & 0xf) << 4)
-#define CBE_IIC_IR_DEST_UNIT(x) ((x) & 0xf)
-#define CBE_IIC_IR_IOC_0        0x0
-#define CBE_IIC_IR_IOC_1S       0xb
-#define CBE_IIC_IR_PT_0         0xe
-#define CBE_IIC_IR_PT_1         0xf
-
-	u64	iic_is;						/* 0x0448 */
-#define CBE_IIC_IS_PMI		0x2
-
-	u8	pad_0x0450_0x0500[0x0500 - 0x0450];		/* 0x0450 */
-
-	/* IOC FIR */
-	u64	ioc_fir_reset;					/* 0x0500 */
-	u64	ioc_fir_set;					/* 0x0508 */
-	u64	ioc_checkstop_enable;				/* 0x0510 */
-	u64	ioc_fir_error_mask;				/* 0x0518 */
-	u64	ioc_syserr_enable;				/* 0x0520 */
-	u64	ioc_fir;					/* 0x0528 */
-
-	u8	pad_0x0530_0x1000[0x1000 - 0x0530];		/* 0x0530 */
-};
-
-extern struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np);
-extern struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu);
-
-
-struct cbe_mic_tm_regs {
-	u8	pad_0x0000_0x0040[0x0040 - 0x0000];		/* 0x0000 */
-
-	u64	mic_ctl_cnfg2;					/* 0x0040 */
-#define CBE_MIC_ENABLE_AUX_TRC		0x8000000000000000LL
-#define CBE_MIC_DISABLE_PWR_SAV_2	0x0200000000000000LL
-#define CBE_MIC_DISABLE_AUX_TRC_WRAP	0x0100000000000000LL
-#define CBE_MIC_ENABLE_AUX_TRC_INT	0x0080000000000000LL
-
-	u64	pad_0x0048;					/* 0x0048 */
-
-	u64	mic_aux_trc_base;				/* 0x0050 */
-	u64	mic_aux_trc_max_addr;				/* 0x0058 */
-	u64	mic_aux_trc_cur_addr;				/* 0x0060 */
-	u64	mic_aux_trc_grf_addr;				/* 0x0068 */
-	u64	mic_aux_trc_grf_data;				/* 0x0070 */
-
-	u64	pad_0x0078;					/* 0x0078 */
-
-	u64	mic_ctl_cnfg_0;					/* 0x0080 */
-#define CBE_MIC_DISABLE_PWR_SAV_0	0x8000000000000000LL
-
-	u64	pad_0x0088;					/* 0x0088 */
-
-	u64	slow_fast_timer_0;				/* 0x0090 */
-	u64	slow_next_timer_0;				/* 0x0098 */
-
-	u8	pad_0x00a0_0x00f8[0x00f8 - 0x00a0];		/* 0x00a0 */
-	u64    	mic_df_ecc_address_0;				/* 0x00f8 */
-
-	u8	pad_0x0100_0x01b8[0x01b8 - 0x0100];		/* 0x0100 */
-	u64    	mic_df_ecc_address_1;				/* 0x01b8 */
-
-	u64	mic_ctl_cnfg_1;					/* 0x01c0 */
-#define CBE_MIC_DISABLE_PWR_SAV_1	0x8000000000000000LL
-
-	u64	pad_0x01c8;					/* 0x01c8 */
-
-	u64	slow_fast_timer_1;				/* 0x01d0 */
-	u64	slow_next_timer_1;				/* 0x01d8 */
-
-	u8	pad_0x01e0_0x0208[0x0208 - 0x01e0];		/* 0x01e0 */
-	u64	mic_exc;					/* 0x0208 */
-#define CBE_MIC_EXC_BLOCK_SCRUB		0x0800000000000000ULL
-#define CBE_MIC_EXC_FAST_SCRUB		0x0100000000000000ULL
-
-	u64	mic_mnt_cfg;					/* 0x0210 */
-#define CBE_MIC_MNT_CFG_CHAN_0_POP	0x0002000000000000ULL
-#define CBE_MIC_MNT_CFG_CHAN_1_POP	0x0004000000000000ULL
-
-	u64	mic_df_config;					/* 0x0218 */
-#define CBE_MIC_ECC_DISABLE_0		0x4000000000000000ULL
-#define CBE_MIC_ECC_REP_SINGLE_0	0x2000000000000000ULL
-#define CBE_MIC_ECC_DISABLE_1		0x0080000000000000ULL
-#define CBE_MIC_ECC_REP_SINGLE_1	0x0040000000000000ULL
-
-	u8	pad_0x0220_0x0230[0x0230 - 0x0220];		/* 0x0220 */
-	u64	mic_fir;					/* 0x0230 */
-#define CBE_MIC_FIR_ECC_SINGLE_0_ERR	0x0200000000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_ERR	0x0100000000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_ERR	0x0080000000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_ERR	0x0040000000000000ULL
-#define CBE_MIC_FIR_ECC_ERR_MASK	0xffff000000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_CTE	0x0000020000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_CTE	0x0000010000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_CTE	0x0000008000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_CTE	0x0000004000000000ULL
-#define CBE_MIC_FIR_ECC_CTE_MASK	0x0000ffff00000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_RESET	0x0000000002000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_RESET	0x0000000001000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_RESET	0x0000000000800000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_RESET	0x0000000000400000ULL
-#define CBE_MIC_FIR_ECC_RESET_MASK	0x00000000ffff0000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_SET	0x0000000000000200ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_SET	0x0000000000000100ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_SET	0x0000000000000080ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_SET	0x0000000000000040ULL
-#define CBE_MIC_FIR_ECC_SET_MASK	0x000000000000ffffULL
-	u64	mic_fir_debug;					/* 0x0238 */
-
-	u8	pad_0x0240_0x1000[0x1000 - 0x0240];		/* 0x0240 */
-};
-
-extern struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np);
-extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
-
-
 /* Cell page table entries */
 #define CBE_IOPTE_PP_W		0x8000000000000000ul /* protection: write */
 #define CBE_IOPTE_PP_R		0x4000000000000000ul /* protection: read */
@@ -315,13 +28,4 @@ extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
 #define CBE_IOPTE_H		0x0000000000000800ul /* cache hint */
 #define CBE_IOPTE_IOID_Mask	0x00000000000007fful /* ioid */
 
-/* some utility functions to deal with SMT */
-extern u32 cbe_get_hw_thread_id(int cpu);
-extern u32 cbe_cpu_to_node(int cpu);
-extern u32 cbe_node_to_cpu(int node);
-
-/* Init this module early */
-extern void cbe_regs_init(void);
-
-
 #endif /* CBE_REGS_H */
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
index fd2e166ea02a..81bd176203ab 100644
--- a/arch/powerpc/include/asm/copro.h
+++ b/arch/powerpc/include/asm/copro.h
@@ -18,10 +18,4 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 
 int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
 
-
-#ifdef CONFIG_PPC_COPRO_BASE
-void copro_flush_all_slbs(struct mm_struct *mm);
-#else
-static inline void copro_flush_all_slbs(struct mm_struct *mm) {}
-#endif
 #endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h
new file mode 100644
index 000000000000..6467ce29b1fa
--- /dev/null
+++ b/arch/powerpc/include/asm/crash_reserve.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CRASH_RESERVE_H
+#define _ASM_POWERPC_CRASH_RESERVE_H
+
+/* crash kernel regions are Page size agliged */
+#define CRASH_ALIGN             PAGE_SIZE
+
+#endif /* _ASM_POWERPC_CRASH_RESERVE_H */
diff --git a/arch/powerpc/include/asm/dcr-generic.h b/arch/powerpc/include/asm/dcr-generic.h
deleted file mode 100644
index 099c28dd40b9..000000000000
--- a/arch/powerpc/include/asm/dcr-generic.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
- *                    <benh@kernel.crashing.org>
- */
-
-#ifndef _ASM_POWERPC_DCR_GENERIC_H
-#define _ASM_POWERPC_DCR_GENERIC_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-enum host_type_t {DCR_HOST_MMIO, DCR_HOST_NATIVE, DCR_HOST_INVALID};
-
-typedef struct {
-	enum host_type_t type;
-	union {
-		dcr_host_mmio_t mmio;
-		dcr_host_native_t native;
-	} host;
-} dcr_host_t;
-
-extern bool dcr_map_ok_generic(dcr_host_t host);
-
-extern dcr_host_t dcr_map_generic(struct device_node *dev, unsigned int dcr_n,
-			  unsigned int dcr_c);
-extern void dcr_unmap_generic(dcr_host_t host, unsigned int dcr_c);
-
-extern u32 dcr_read_generic(dcr_host_t host, unsigned int dcr_n);
-
-extern void dcr_write_generic(dcr_host_t host, unsigned int dcr_n, u32 value);
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_DCR_GENERIC_H */
-
-
diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h
deleted file mode 100644
index fc6d93ef4a13..000000000000
--- a/arch/powerpc/include/asm/dcr-mmio.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
- *                    <benh@kernel.crashing.org>
- */
-
-#ifndef _ASM_POWERPC_DCR_MMIO_H
-#define _ASM_POWERPC_DCR_MMIO_H
-#ifdef __KERNEL__
-
-#include <asm/io.h>
-
-typedef struct {
-	void __iomem *token;
-	unsigned int stride;
-	unsigned int base;
-} dcr_host_mmio_t;
-
-static inline bool dcr_map_ok_mmio(dcr_host_mmio_t host)
-{
-	return host.token != NULL;
-}
-
-extern dcr_host_mmio_t dcr_map_mmio(struct device_node *dev,
-				    unsigned int dcr_n,
-				    unsigned int dcr_c);
-extern void dcr_unmap_mmio(dcr_host_mmio_t host, unsigned int dcr_c);
-
-static inline u32 dcr_read_mmio(dcr_host_mmio_t host, unsigned int dcr_n)
-{
-	return in_be32(host.token + ((host.base + dcr_n) * host.stride));
-}
-
-static inline void dcr_write_mmio(dcr_host_mmio_t host,
-				  unsigned int dcr_n,
-				  u32 value)
-{
-	out_be32(host.token + ((host.base + dcr_n) * host.stride), value);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_DCR_MMIO_H */
-
-
diff --git a/arch/powerpc/include/asm/dcr.h b/arch/powerpc/include/asm/dcr.h
index 64030e3a1f30..180021cd0b30 100644
--- a/arch/powerpc/include/asm/dcr.h
+++ b/arch/powerpc/include/asm/dcr.h
@@ -10,46 +10,14 @@
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_PPC_DCR
 
-#ifdef CONFIG_PPC_DCR_NATIVE
 #include <asm/dcr-native.h>
-#endif
 
-#ifdef CONFIG_PPC_DCR_MMIO
-#include <asm/dcr-mmio.h>
-#endif
-
-
-/* Indirection layer for providing both NATIVE and MMIO support. */
-
-#if defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO)
-
-#include <asm/dcr-generic.h>
-
-#define DCR_MAP_OK(host)	dcr_map_ok_generic(host)
-#define dcr_map(dev, dcr_n, dcr_c) dcr_map_generic(dev, dcr_n, dcr_c)
-#define dcr_unmap(host, dcr_c) dcr_unmap_generic(host, dcr_c)
-#define dcr_read(host, dcr_n) dcr_read_generic(host, dcr_n)
-#define dcr_write(host, dcr_n, value) dcr_write_generic(host, dcr_n, value)
-
-#else
-
-#ifdef CONFIG_PPC_DCR_NATIVE
 typedef dcr_host_native_t dcr_host_t;
 #define DCR_MAP_OK(host)	dcr_map_ok_native(host)
 #define dcr_map(dev, dcr_n, dcr_c) dcr_map_native(dev, dcr_n, dcr_c)
 #define dcr_unmap(host, dcr_c) dcr_unmap_native(host, dcr_c)
 #define dcr_read(host, dcr_n) dcr_read_native(host, dcr_n)
 #define dcr_write(host, dcr_n, value) dcr_write_native(host, dcr_n, value)
-#else
-typedef dcr_host_mmio_t dcr_host_t;
-#define DCR_MAP_OK(host)	dcr_map_ok_mmio(host)
-#define dcr_map(dev, dcr_n, dcr_c) dcr_map_mmio(dev, dcr_n, dcr_c)
-#define dcr_unmap(host, dcr_c) dcr_unmap_mmio(host, dcr_c)
-#define dcr_read(host, dcr_n) dcr_read_mmio(host, dcr_n)
-#define dcr_write(host, dcr_n, value) dcr_write_mmio(host, dcr_n, value)
-#endif
-
-#endif /* defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO) */
 
 /*
  * additional helpers to read the DCR * base from the device-tree
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 47ed639f3b8f..a4dc27655b3e 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -38,9 +38,6 @@ struct dev_archdata {
 #ifdef CONFIG_FAIL_IOMMU
 	int fail_iommu;
 #endif
-#ifdef CONFIG_CXL_BASE
-	struct cxl_context	*cxl_ctx;
-#endif
 #ifdef CONFIG_PCI_IOV
 	void *iov_data;
 #endif
diff --git a/arch/powerpc/include/asm/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h
index d107abe1468f..acd61eb36d59 100644
--- a/arch/powerpc/include/asm/guest-state-buffer.h
+++ b/arch/powerpc/include/asm/guest-state-buffer.h
@@ -28,6 +28,21 @@
  /* Process Table Info */
 #define KVMPPC_GSID_PROCESS_TABLE		0x0006
 
+/* Guest Management Heap Size */
+#define KVMPPC_GSID_L0_GUEST_HEAP		0x0800
+
+/* Guest Management Heap Max Size */
+#define KVMPPC_GSID_L0_GUEST_HEAP_MAX		0x0801
+
+/* Guest Pagetable Size */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE	0x0802
+
+/* Guest Pagetable Max Size */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX	0x0803
+
+/* Guest Pagetable Reclaim in bytes */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM	0x0804
+
 /* H_GUEST_RUN_VCPU input buffer Info */
 #define KVMPPC_GSID_RUN_INPUT			0x0C00
 /* H_GUEST_RUN_VCPU output buffer Info */
@@ -106,6 +121,11 @@
 #define KVMPPC_GSE_GUESTWIDE_COUNT \
 	(KVMPPC_GSE_GUESTWIDE_END - KVMPPC_GSE_GUESTWIDE_START + 1)
 
+#define KVMPPC_GSE_HOSTWIDE_START KVMPPC_GSID_L0_GUEST_HEAP
+#define KVMPPC_GSE_HOSTWIDE_END KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+#define KVMPPC_GSE_HOSTWIDE_COUNT \
+	(KVMPPC_GSE_HOSTWIDE_END - KVMPPC_GSE_HOSTWIDE_START + 1)
+
 #define KVMPPC_GSE_META_START KVMPPC_GSID_RUN_INPUT
 #define KVMPPC_GSE_META_END KVMPPC_GSID_VPA
 #define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1)
@@ -130,7 +150,8 @@
 	(KVMPPC_GSE_INTR_REGS_END - KVMPPC_GSE_INTR_REGS_START + 1)
 
 #define KVMPPC_GSE_IDEN_COUNT                                 \
-	(KVMPPC_GSE_GUESTWIDE_COUNT + KVMPPC_GSE_META_COUNT + \
+	(KVMPPC_GSE_HOSTWIDE_COUNT + \
+	 KVMPPC_GSE_GUESTWIDE_COUNT + KVMPPC_GSE_META_COUNT + \
 	 KVMPPC_GSE_DW_REGS_COUNT + KVMPPC_GSE_W_REGS_COUNT + \
 	 KVMPPC_GSE_VSRS_COUNT + KVMPPC_GSE_INTR_REGS_COUNT)
 
@@ -139,10 +160,11 @@
  */
 enum {
 	KVMPPC_GS_CLASS_GUESTWIDE = 0x01,
-	KVMPPC_GS_CLASS_META = 0x02,
-	KVMPPC_GS_CLASS_DWORD_REG = 0x04,
-	KVMPPC_GS_CLASS_WORD_REG = 0x08,
-	KVMPPC_GS_CLASS_VECTOR = 0x10,
+	KVMPPC_GS_CLASS_HOSTWIDE = 0x02,
+	KVMPPC_GS_CLASS_META = 0x04,
+	KVMPPC_GS_CLASS_DWORD_REG = 0x08,
+	KVMPPC_GS_CLASS_WORD_REG = 0x10,
+	KVMPPC_GS_CLASS_VECTOR = 0x18,
 	KVMPPC_GS_CLASS_INTR = 0x20,
 };
 
@@ -164,6 +186,7 @@ enum {
  */
 enum {
 	KVMPPC_GS_FLAGS_WIDE = 0x01,
+	KVMPPC_GS_FLAGS_HOST_WIDE = 0x02,
 };
 
 /**
@@ -287,7 +310,7 @@ struct kvmppc_gs_msg_ops {
  * struct kvmppc_gs_msg - a guest state message
  * @bitmap: the guest state ids that should be included
  * @ops: modify message behavior for reading and writing to buffers
- * @flags: guest wide or thread wide
+ * @flags: host wide, guest wide or thread wide
  * @data: location where buffer data will be written to or from.
  *
  * A guest state message is allows flexibility in sending in receiving data
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dad2e7980f24..86326587e58d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 65d1f291393d..6df6dbbe1e7c 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -348,6 +348,7 @@
 #define H_SCM_FLUSH		0x44C
 #define H_GET_ENERGY_SCALE_INFO	0x450
 #define H_PKS_SIGNED_UPDATE	0x454
+#define H_HTM                   0x458
 #define H_WATCHDOG		0x45C
 #define H_GUEST_GET_CAPABILITIES 0x460
 #define H_GUEST_SET_CAPABILITIES 0x464
@@ -489,14 +490,48 @@
 #define H_RPTI_PAGE_ALL (-1UL)
 
 /* Flags for H_GUEST_{S,G}_STATE */
-#define H_GUEST_FLAGS_WIDE     (1UL<<(63-0))
+#define H_GUEST_FLAGS_WIDE     (1UL << (63 - 0))
+#define H_GUEST_FLAGS_HOST_WIDE	(1UL << (63 - 1))
 
 /* Flag values used for H_{S,G}SET_GUEST_CAPABILITIES */
-#define H_GUEST_CAP_COPY_MEM	(1UL<<(63-0))
-#define H_GUEST_CAP_POWER9	(1UL<<(63-1))
-#define H_GUEST_CAP_POWER10	(1UL<<(63-2))
-#define H_GUEST_CAP_POWER11	(1UL<<(63-3))
-#define H_GUEST_CAP_BITMAP2	(1UL<<(63-63))
+#define H_GUEST_CAP_COPY_MEM	(1UL << (63 - 0))
+#define H_GUEST_CAP_POWER9	(1UL << (63 - 1))
+#define H_GUEST_CAP_POWER10	(1UL << (63 - 2))
+#define H_GUEST_CAP_POWER11	(1UL << (63 - 3))
+#define H_GUEST_CAP_BITMAP2	(1UL << (63 - 63))
+
+/*
+ * Defines for H_HTM - Macros for hardware trace macro (HTM) function.
+ */
+#define H_HTM_FLAGS_HARDWARE_TARGET    (1ul << 63)
+#define H_HTM_FLAGS_LOGICAL_TARGET     (1ul << 62)
+#define H_HTM_FLAGS_PROCID_TARGET      (1ul << 61)
+#define H_HTM_FLAGS_NOWRAP             (1ul << 60)
+
+#define H_HTM_OP_SHIFT                 (63-15)
+#define H_HTM_OP(x)                    ((unsigned long)(x)<<H_HTM_OP_SHIFT)
+#define H_HTM_OP_CAPABILITIES          0x01
+#define H_HTM_OP_STATUS                        0x02
+#define H_HTM_OP_SETUP                 0x03
+#define H_HTM_OP_CONFIGURE             0x04
+#define H_HTM_OP_START                 0x05
+#define H_HTM_OP_STOP                  0x06
+#define H_HTM_OP_DECONFIGURE           0x07
+#define H_HTM_OP_DUMP_DETAILS          0x08
+#define H_HTM_OP_DUMP_DATA             0x09
+#define H_HTM_OP_DUMP_SYSMEM_CONF      0x0a
+#define H_HTM_OP_DUMP_SYSPROC_CONF     0x0b
+
+#define H_HTM_TYPE_SHIFT               (63-31)
+#define H_HTM_TYPE(x)                  ((unsigned long)(x)<<H_HTM_TYPE_SHIFT)
+#define H_HTM_TYPE_NEST                        0x01
+#define H_HTM_TYPE_CORE                        0x02
+#define H_HTM_TYPE_LLAT                        0x03
+#define H_HTM_TYPE_GLOBAL              0xff
+
+#define H_HTM_TARGET_NODE_INDEX(x)             ((unsigned long)(x)<<(63-15))
+#define H_HTM_TARGET_NODAL_CHIP_INDEX(x)       ((unsigned long)(x)<<(63-31))
+#define H_HTM_TARGET_CORE_INDEX_ON_CHIP(x)     ((unsigned long)(x)<<(63-47))
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
diff --git a/arch/powerpc/include/asm/io-defs.h b/arch/powerpc/include/asm/io-defs.h
index faf8617cc574..5c2be9b54a9d 100644
--- a/arch/powerpc/include/asm/io-defs.h
+++ b/arch/powerpc/include/asm/io-defs.h
@@ -1,61 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* This file is meant to be include multiple times by other headers */
-/* last 2 argments are used by platforms/cell/io-workarounds.[ch] */
 
-DEF_PCI_AC_RET(readb, u8, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readw, u16, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readl, u32, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readw_be, u16, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readl_be, u32, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_NORET(writeb, (u8 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writew, (u16 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writel, (u32 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writew_be, (u16 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writel_be, (u32 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-
-#ifdef __powerpc64__
-DEF_PCI_AC_RET(readq, u64, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readq_be, u64, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_NORET(writeq, (u64 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writeq_be, (u64 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-#endif /* __powerpc64__ */
-
-DEF_PCI_AC_RET(inb, u8, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_RET(inw, u16, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_RET(inl, u32, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_NORET(outb, (u8 val, unsigned long port), (val, port), pio, port)
-DEF_PCI_AC_NORET(outw, (u16 val, unsigned long port), (val, port), pio, port)
-DEF_PCI_AC_NORET(outl, (u32 val, unsigned long port), (val, port), pio, port)
-
-DEF_PCI_AC_NORET(readsb, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(readsw, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(readsl, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesb, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesw, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesl, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-
-DEF_PCI_AC_NORET(insb, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-
-DEF_PCI_AC_NORET(memset_io, (PCI_IO_ADDR a, int c, unsigned long n),
-		 (a, c, n), mem, a)
-DEF_PCI_AC_NORET(memcpy_fromio, (void *d, const PCI_IO_ADDR s, unsigned long n),
-		 (d, s, n), mem, s)
-DEF_PCI_AC_NORET(memcpy_toio, (PCI_IO_ADDR d, const void *s, unsigned long n),
-		 (d, s, n), mem, d)
+DEF_PCI_AC_RET(inb, u8, (unsigned long port), (port))
+DEF_PCI_AC_RET(inw, u16, (unsigned long port), (port))
+DEF_PCI_AC_RET(inl, u32, (unsigned long port), (port))
+DEF_PCI_AC_NORET(outb, (u8 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outw, (u16 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outl, (u32 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(insb, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c), (p, b, c))
diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
deleted file mode 100644
index 3cce499fbe27..000000000000
--- a/arch/powerpc/include/asm/io-workarounds.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Support PCI IO workaround
- *
- * (C) Copyright 2007-2008 TOSHIBA CORPORATION
- */
-
-#ifndef _IO_WORKAROUNDS_H
-#define _IO_WORKAROUNDS_H
-
-#ifdef CONFIG_PPC_IO_WORKAROUNDS
-#include <linux/io.h>
-#include <asm/pci-bridge.h>
-
-/* Bus info */
-struct iowa_bus {
-	struct pci_controller *phb;
-	struct ppc_pci_io *ops;
-	void   *private;
-};
-
-void iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
-		       int (*)(struct iowa_bus *, void *), void *);
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
-struct iowa_bus *iowa_pio_find_bus(unsigned long);
-
-extern struct ppc_pci_io spiderpci_ops;
-extern int spiderpci_iowa_init(struct iowa_bus *, void *);
-
-#define SPIDER_PCI_REG_BASE		0xd000
-#define SPIDER_PCI_REG_SIZE		0x1000
-#define SPIDER_PCI_VCI_CNTL_STAT	0x0110
-#define SPIDER_PCI_DUMMY_READ		0x0810
-#define SPIDER_PCI_DUMMY_READ_BASE	0x0814
-
-#endif
-
-#if defined(CONFIG_PPC_IO_WORKAROUNDS) && defined(CONFIG_PPC_INDIRECT_MMIO)
-extern bool io_workaround_inited;
-
-static inline bool iowa_is_active(void)
-{
-	return unlikely(io_workaround_inited);
-}
-#else
-static inline bool iowa_is_active(void)
-{
-	return false;
-}
-#endif
-
-void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-			   pgprot_t prot, void *caller);
-
-#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index fd92ac450169..7a89754842d6 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -65,8 +65,8 @@ extern resource_size_t isa_mem_base;
 extern bool isa_io_special;
 
 #ifdef CONFIG_PPC32
-#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
-#error CONFIG_PPC_INDIRECT_{PIO,MMIO} are not yet supported on 32 bits
+#ifdef CONFIG_PPC_INDIRECT_PIO
+#error CONFIG_PPC_INDIRECT_PIO is not yet supported on 32 bits
 #endif
 #endif
 
@@ -80,16 +80,12 @@ extern bool isa_io_special;
  *
  *	in_8, in_le16, in_be16, in_le32, in_be32, in_le64, in_be64
  *	out_8, out_le16, out_be16, out_le32, out_be32, out_le64, out_be64
- *	_insb, _insw_ns, _insl_ns, _outsb, _outsw_ns, _outsl_ns
+ *	_insb, _insw, _insl, _outsb, _outsw, _outsl
  *
  * Those operate directly on a kernel virtual address. Note that the prototype
  * for the out_* accessors has the arguments in opposite order from the usual
  * linux PCI accessors. Unlike those, they take the address first and the value
  * next.
- *
- * Note: I might drop the _ns suffix on the stream operations soon as it is
- * simply normal for stream operations to not swap in the first place.
- *
  */
 
 /* -mprefixed can generate offsets beyond range, fall back hack */
@@ -228,19 +224,10 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val)
  */
 extern void _insb(const volatile u8 __iomem *addr, void *buf, long count);
 extern void _outsb(volatile u8 __iomem *addr,const void *buf,long count);
-extern void _insw_ns(const volatile u16 __iomem *addr, void *buf, long count);
-extern void _outsw_ns(volatile u16 __iomem *addr, const void *buf, long count);
-extern void _insl_ns(const volatile u32 __iomem *addr, void *buf, long count);
-extern void _outsl_ns(volatile u32 __iomem *addr, const void *buf, long count);
-
-/* The _ns naming is historical and will be removed. For now, just #define
- * the non _ns equivalent names
- */
-#define _insw	_insw_ns
-#define _insl	_insl_ns
-#define _outsw	_outsw_ns
-#define _outsl	_outsl_ns
-
+extern void _insw(const volatile u16 __iomem *addr, void *buf, long count);
+extern void _outsw(volatile u16 __iomem *addr, const void *buf, long count);
+extern void _insl(const volatile u32 __iomem *addr, void *buf, long count);
+extern void _outsl(volatile u32 __iomem *addr, const void *buf, long count);
 
 /*
  * memset_io, memcpy_toio, memcpy_fromio base implementations are out of line
@@ -261,9 +248,9 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * for PowerPC is as close as possible to the x86 version of these, and thus
  * provides fairly heavy weight barriers for the non-raw versions
  *
- * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_MMIO
- * or CONFIG_PPC_INDIRECT_PIO are set allowing the platform to provide its
- * own implementation of some or all of the accessors.
+ * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_PIO
+ * is set allowing the platform to provide its own implementation of some
+ * of the accessors.
  */
 
 /*
@@ -274,116 +261,11 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
 #include <asm/eeh.h>
 #endif
 
-/* Shortcut to the MMIO argument pointer */
-#define PCI_IO_ADDR	volatile void __iomem *
-
-/* Indirect IO address tokens:
- *
- * When CONFIG_PPC_INDIRECT_MMIO is set, the platform can provide hooks
- * on all MMIOs. (Note that this is all 64 bits only for now)
- *
- * To help platforms who may need to differentiate MMIO addresses in
- * their hooks, a bitfield is reserved for use by the platform near the
- * top of MMIO addresses (not PIO, those have to cope the hard way).
- *
- * The highest address in the kernel virtual space are:
- *
- *  d0003fffffffffff	# with Hash MMU
- *  c00fffffffffffff	# with Radix MMU
- *
- * The top 4 bits are reserved as the region ID on hash, leaving us 8 bits
- * that can be used for the field.
- *
- * The direct IO mapping operations will then mask off those bits
- * before doing the actual access, though that only happen when
- * CONFIG_PPC_INDIRECT_MMIO is set, thus be careful when you use that
- * mechanism
- *
- * For PIO, there is a separate CONFIG_PPC_INDIRECT_PIO which makes
- * all PIO functions call through a hook.
- */
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-#define PCI_IO_IND_TOKEN_SHIFT	52
-#define PCI_IO_IND_TOKEN_MASK	(0xfful << PCI_IO_IND_TOKEN_SHIFT)
-#define PCI_FIX_ADDR(addr)						\
-	((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
-#define PCI_GET_ADDR_TOKEN(addr)					\
-	(((unsigned long)(addr) & PCI_IO_IND_TOKEN_MASK) >> 		\
-		PCI_IO_IND_TOKEN_SHIFT)
-#define PCI_SET_ADDR_TOKEN(addr, token) 				\
-do {									\
-	unsigned long __a = (unsigned long)(addr);			\
-	__a &= ~PCI_IO_IND_TOKEN_MASK;					\
-	__a |= ((unsigned long)(token)) << PCI_IO_IND_TOKEN_SHIFT;	\
-	(addr) = (void __iomem *)__a;					\
-} while(0)
-#else
-#define PCI_FIX_ADDR(addr) (addr)
-#endif
-
-
-/*
- * Non ordered and non-swapping "raw" accessors
- */
-
-static inline unsigned char __raw_readb(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned char __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readb __raw_readb
-
-static inline unsigned short __raw_readw(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned short __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readw __raw_readw
-
-static inline unsigned int __raw_readl(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned int __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readl __raw_readl
-
-static inline void __raw_writeb(unsigned char v, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writeb __raw_writeb
-
-static inline void __raw_writew(unsigned short v, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writew __raw_writew
-
-static inline void __raw_writel(unsigned int v, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writel __raw_writel
+#define _IO_PORT(port)	((volatile void __iomem *)(_IO_BASE + (port)))
 
 #ifdef __powerpc64__
-static inline unsigned long __raw_readq(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned long __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readq __raw_readq
-
-static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
-{
-	*(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writeq __raw_writeq
-
-static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr)
-{
-	__raw_writeq((__force unsigned long)cpu_to_be64(v), addr);
-}
-#define __raw_writeq_be __raw_writeq_be
-
 /*
- * Real mode versions of the above. Those instructions are only supposed
+ * Real mode versions of raw accessors. Those instructions are only supposed
  * to be used in hypervisor real mode as per the architecture spec.
  */
 static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr)
@@ -551,30 +433,23 @@ __do_out_asm(_rec_outl, "stwbrx")
  * possible to hook directly at the toplevel PIO operation if they have to
  * be handled differently
  */
-#define __do_writeb(val, addr)	out_8(PCI_FIX_ADDR(addr), val)
-#define __do_writew(val, addr)	out_le16(PCI_FIX_ADDR(addr), val)
-#define __do_writel(val, addr)	out_le32(PCI_FIX_ADDR(addr), val)
-#define __do_writeq(val, addr)	out_le64(PCI_FIX_ADDR(addr), val)
-#define __do_writew_be(val, addr) out_be16(PCI_FIX_ADDR(addr), val)
-#define __do_writel_be(val, addr) out_be32(PCI_FIX_ADDR(addr), val)
-#define __do_writeq_be(val, addr) out_be64(PCI_FIX_ADDR(addr), val)
 
 #ifdef CONFIG_EEH
-#define __do_readb(addr)	eeh_readb(PCI_FIX_ADDR(addr))
-#define __do_readw(addr)	eeh_readw(PCI_FIX_ADDR(addr))
-#define __do_readl(addr)	eeh_readl(PCI_FIX_ADDR(addr))
-#define __do_readq(addr)	eeh_readq(PCI_FIX_ADDR(addr))
-#define __do_readw_be(addr)	eeh_readw_be(PCI_FIX_ADDR(addr))
-#define __do_readl_be(addr)	eeh_readl_be(PCI_FIX_ADDR(addr))
-#define __do_readq_be(addr)	eeh_readq_be(PCI_FIX_ADDR(addr))
+#define __do_readb(addr)	eeh_readb(addr)
+#define __do_readw(addr)	eeh_readw(addr)
+#define __do_readl(addr)	eeh_readl(addr)
+#define __do_readq(addr)	eeh_readq(addr)
+#define __do_readw_be(addr)	eeh_readw_be(addr)
+#define __do_readl_be(addr)	eeh_readl_be(addr)
+#define __do_readq_be(addr)	eeh_readq_be(addr)
 #else /* CONFIG_EEH */
-#define __do_readb(addr)	in_8(PCI_FIX_ADDR(addr))
-#define __do_readw(addr)	in_le16(PCI_FIX_ADDR(addr))
-#define __do_readl(addr)	in_le32(PCI_FIX_ADDR(addr))
-#define __do_readq(addr)	in_le64(PCI_FIX_ADDR(addr))
-#define __do_readw_be(addr)	in_be16(PCI_FIX_ADDR(addr))
-#define __do_readl_be(addr)	in_be32(PCI_FIX_ADDR(addr))
-#define __do_readq_be(addr)	in_be64(PCI_FIX_ADDR(addr))
+#define __do_readb(addr)	in_8(addr)
+#define __do_readw(addr)	in_le16(addr)
+#define __do_readl(addr)	in_le32(addr)
+#define __do_readq(addr)	in_le64(addr)
+#define __do_readw_be(addr)	in_be16(addr)
+#define __do_readl_be(addr)	in_be32(addr)
+#define __do_readq_be(addr)	in_be64(addr)
 #endif /* !defined(CONFIG_EEH) */
 
 #ifdef CONFIG_PPC32
@@ -585,64 +460,185 @@ __do_out_asm(_rec_outl, "stwbrx")
 #define __do_inw(port)		_rec_inw(port)
 #define __do_inl(port)		_rec_inl(port)
 #else /* CONFIG_PPC32 */
-#define __do_outb(val, port)	writeb(val,(PCI_IO_ADDR)(_IO_BASE+port));
-#define __do_outw(val, port)	writew(val,(PCI_IO_ADDR)(_IO_BASE+port));
-#define __do_outl(val, port)	writel(val,(PCI_IO_ADDR)(_IO_BASE+port));
-#define __do_inb(port)		readb((PCI_IO_ADDR)(_IO_BASE + port));
-#define __do_inw(port)		readw((PCI_IO_ADDR)(_IO_BASE + port));
-#define __do_inl(port)		readl((PCI_IO_ADDR)(_IO_BASE + port));
+#define __do_outb(val, port)	writeb(val,_IO_PORT(port));
+#define __do_outw(val, port)	writew(val,_IO_PORT(port));
+#define __do_outl(val, port)	writel(val,_IO_PORT(port));
+#define __do_inb(port)		readb(_IO_PORT(port));
+#define __do_inw(port)		readw(_IO_PORT(port));
+#define __do_inl(port)		readl(_IO_PORT(port));
 #endif /* !CONFIG_PPC32 */
 
 #ifdef CONFIG_EEH
-#define __do_readsb(a, b, n)	eeh_readsb(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsw(a, b, n)	eeh_readsw(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsl(a, b, n)	eeh_readsl(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsb(a, b, n)	eeh_readsb(a, (b), (n))
+#define __do_readsw(a, b, n)	eeh_readsw(a, (b), (n))
+#define __do_readsl(a, b, n)	eeh_readsl(a, (b), (n))
 #else /* CONFIG_EEH */
-#define __do_readsb(a, b, n)	_insb(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsw(a, b, n)	_insw(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsl(a, b, n)	_insl(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsb(a, b, n)	_insb(a, (b), (n))
+#define __do_readsw(a, b, n)	_insw(a, (b), (n))
+#define __do_readsl(a, b, n)	_insl(a, (b), (n))
 #endif /* !CONFIG_EEH */
-#define __do_writesb(a, b, n)	_outsb(PCI_FIX_ADDR(a),(b),(n))
-#define __do_writesw(a, b, n)	_outsw(PCI_FIX_ADDR(a),(b),(n))
-#define __do_writesl(a, b, n)	_outsl(PCI_FIX_ADDR(a),(b),(n))
-
-#define __do_insb(p, b, n)	readsb((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
-#define __do_insw(p, b, n)	readsw((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
-#define __do_insl(p, b, n)	readsl((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n))
-#define __do_outsb(p, b, n)	writesb((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
-#define __do_outsw(p, b, n)	writesw((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
-#define __do_outsl(p, b, n)	writesl((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n))
-
-#define __do_memset_io(addr, c, n)	\
-				_memset_io(PCI_FIX_ADDR(addr), c, n)
-#define __do_memcpy_toio(dst, src, n)	\
-				_memcpy_toio(PCI_FIX_ADDR(dst), src, n)
+#define __do_writesb(a, b, n)	_outsb(a, (b), (n))
+#define __do_writesw(a, b, n)	_outsw(a, (b), (n))
+#define __do_writesl(a, b, n)	_outsl(a, (b), (n))
+
+#define __do_insb(p, b, n)	readsb(_IO_PORT(p), (b), (n))
+#define __do_insw(p, b, n)	readsw(_IO_PORT(p), (b), (n))
+#define __do_insl(p, b, n)	readsl(_IO_PORT(p), (b), (n))
+#define __do_outsb(p, b, n)	writesb(_IO_PORT(p),(b),(n))
+#define __do_outsw(p, b, n)	writesw(_IO_PORT(p),(b),(n))
+#define __do_outsl(p, b, n)	writesl(_IO_PORT(p),(b),(n))
 
 #ifdef CONFIG_EEH
 #define __do_memcpy_fromio(dst, src, n)	\
-				eeh_memcpy_fromio(dst, PCI_FIX_ADDR(src), n)
+				eeh_memcpy_fromio(dst, src, n)
 #else /* CONFIG_EEH */
 #define __do_memcpy_fromio(dst, src, n)	\
-				_memcpy_fromio(dst,PCI_FIX_ADDR(src),n)
+				_memcpy_fromio(dst, src, n)
 #endif /* !CONFIG_EEH */
 
-#ifdef CONFIG_PPC_INDIRECT_PIO
-#define DEF_PCI_HOOK_pio(x)	x
-#else
-#define DEF_PCI_HOOK_pio(x)	NULL
-#endif
+static inline u8 readb(const volatile void __iomem *addr)
+{
+	return __do_readb(addr);
+}
+#define readb readb
+
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __do_readw(addr);
+}
+#define readw readw
+
+static inline u32 readl(const volatile void __iomem *addr)
+{
+	return __do_readl(addr);
+}
+#define readl readl
+
+static inline u16 readw_be(const volatile void __iomem *addr)
+{
+	return __do_readw_be(addr);
+}
+
+static inline u32 readl_be(const volatile void __iomem *addr)
+{
+	return __do_readl_be(addr);
+}
 
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-#define DEF_PCI_HOOK_mem(x)	x
+static inline void writeb(u8 val, volatile void __iomem *addr)
+{
+	out_8(addr, val);
+}
+#define writeb writeb
+
+static inline void writew(u16 val, volatile void __iomem *addr)
+{
+	out_le16(addr, val);
+}
+#define writew writew
+
+static inline void writel(u32 val, volatile void __iomem *addr)
+{
+	out_le32(addr, val);
+}
+#define writel writel
+
+static inline void writew_be(u16 val, volatile void __iomem *addr)
+{
+	out_be16(addr, val);
+}
+
+static inline void writel_be(u32 val, volatile void __iomem *addr)
+{
+	out_be32(addr, val);
+}
+
+static inline void readsb(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsb(a, b, c);
+}
+#define readsb readsb
+
+static inline void readsw(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsw(a, b, c);
+}
+#define readsw readsw
+
+static inline void readsl(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsl(a, b, c);
+}
+#define readsl readsl
+
+static inline void writesb(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesb(a, b, c);
+}
+#define writesb writesb
+
+static inline void writesw(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesw(a, b, c);
+}
+#define writesw writesw
+
+static inline void writesl(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesl(a, b, c);
+}
+#define writesl writesl
+
+static inline void memset_io(volatile void __iomem *a, int c, unsigned long n)
+{
+	_memset_io(a, c, n);
+}
+#define memset_io memset_io
+
+static inline void memcpy_fromio(void *d, const volatile void __iomem *s, unsigned long n)
+{
+	__do_memcpy_fromio(d, s, n);
+}
+#define memcpy_fromio memcpy_fromio
+
+static inline void memcpy_toio(volatile void __iomem *d, const void *s, unsigned long n)
+{
+	_memcpy_toio(d, s, n);
+}
+#define memcpy_toio memcpy_toio
+
+#ifdef __powerpc64__
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return __do_readq(addr);
+}
+
+static inline u64 readq_be(const volatile void __iomem *addr)
+{
+	return __do_readq_be(addr);
+}
+
+static inline void writeq(u64 val, volatile void __iomem *addr)
+{
+	out_le64(addr, val);
+}
+
+static inline void writeq_be(u64 val, volatile void __iomem *addr)
+{
+	out_be64(addr, val);
+}
+#endif /* __powerpc64__ */
+
+#ifdef CONFIG_PPC_INDIRECT_PIO
+#define DEF_PCI_HOOK(x)	x
 #else
-#define DEF_PCI_HOOK_mem(x)	NULL
+#define DEF_PCI_HOOK(x)	NULL
 #endif
 
 /* Structure containing all the hooks */
 extern struct ppc_pci_io {
 
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	ret (*name) at;
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)	void (*name) at;
+#define DEF_PCI_AC_RET(name, ret, at, al)	ret (*name) at;
+#define DEF_PCI_AC_NORET(name, at, al)		void (*name) at;
 
 #include <asm/io-defs.h>
 
@@ -652,18 +648,18 @@ extern struct ppc_pci_io {
 } ppc_pci_io;
 
 /* The inline wrappers */
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
+#define DEF_PCI_AC_RET(name, ret, at, al)			\
 static inline ret name at					\
 {								\
-	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)	\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
 		return ppc_pci_io.name al;			\
 	return __do_##name al;					\
 }
 
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
+#define DEF_PCI_AC_NORET(name, at, al)		\
 static inline void name at					\
 {								\
-	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)		\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
 		ppc_pci_io.name al;				\
 	else							\
 		__do_##name al;					\
@@ -674,21 +670,7 @@ static inline void name at					\
 #undef DEF_PCI_AC_RET
 #undef DEF_PCI_AC_NORET
 
-/* Some drivers check for the presence of readq & writeq with
- * a #ifdef, so we make them happy here.
- */
-#define readb readb
-#define readw readw
-#define readl readl
-#define writeb writeb
-#define writew writew
-#define writel writel
-#define readsb readsb
-#define readsw readsw
-#define readsl readsl
-#define writesb writesb
-#define writesw writesw
-#define writesl writesl
+// Signal to asm-generic/io.h that we have implemented these.
 #define inb inb
 #define inw inw
 #define inl inl
@@ -705,9 +687,6 @@ static inline void name at					\
 #define readq	readq
 #define writeq	writeq
 #endif
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
 
 /*
  * We don't do relaxed operations yet, at least not with this semantic
@@ -738,35 +717,11 @@ static inline unsigned int ioread32be(const void __iomem *addr)
 #define ioread32be ioread32be
 
 #ifdef __powerpc64__
-static inline u64 ioread64_lo_hi(const void __iomem *addr)
-{
-	return readq(addr);
-}
-#define ioread64_lo_hi ioread64_lo_hi
-
-static inline u64 ioread64_hi_lo(const void __iomem *addr)
-{
-	return readq(addr);
-}
-#define ioread64_hi_lo ioread64_hi_lo
-
 static inline u64 ioread64be(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
 #define ioread64be ioread64be
-
-static inline u64 ioread64be_lo_hi(const void __iomem *addr)
-{
-	return readq_be(addr);
-}
-#define ioread64be_lo_hi ioread64be_lo_hi
-
-static inline u64 ioread64be_hi_lo(const void __iomem *addr)
-{
-	return readq_be(addr);
-}
-#define ioread64be_hi_lo ioread64be_hi_lo
 #endif /* __powerpc64__ */
 
 static inline void iowrite16be(u16 val, void __iomem *addr)
@@ -782,35 +737,11 @@ static inline void iowrite32be(u32 val, void __iomem *addr)
 #define iowrite32be iowrite32be
 
 #ifdef __powerpc64__
-static inline void iowrite64_lo_hi(u64 val, void __iomem *addr)
-{
-	writeq(val, addr);
-}
-#define iowrite64_lo_hi iowrite64_lo_hi
-
-static inline void iowrite64_hi_lo(u64 val, void __iomem *addr)
-{
-	writeq(val, addr);
-}
-#define iowrite64_hi_lo iowrite64_hi_lo
-
 static inline void iowrite64be(u64 val, void __iomem *addr)
 {
 	writeq_be(val, addr);
 }
 #define iowrite64be iowrite64be
-
-static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr)
-{
-	writeq_be(val, addr);
-}
-#define iowrite64be_lo_hi iowrite64be_lo_hi
-
-static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr)
-{
-	writeq_be(val, addr);
-}
-#define iowrite64be_hi_lo iowrite64be_hi_lo
 #endif /* __powerpc64__ */
 
 struct pci_dev;
@@ -895,7 +826,7 @@ void __iomem *ioremap_wt(phys_addr_t address, unsigned long size);
 
 void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
 #define ioremap_cache(addr, size) \
-	ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
+	ioremap_prot((addr), (size), PAGE_KERNEL)
 
 #define iounmap iounmap
 
@@ -1030,6 +961,14 @@ static inline void * bus_to_virt(unsigned long address)
 
 #include <asm-generic/io.h>
 
+#ifdef __powerpc64__
+static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr)
+{
+	__raw_writeq((__force unsigned long)cpu_to_be64(v), addr);
+}
+#define __raw_writeq_be __raw_writeq_be
+#endif // __powerpc64__
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_POWERPC_IO_H */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 04072b5f8962..b410021ad4c6 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -317,12 +317,6 @@ extern void iommu_flush_tce(struct iommu_table *tbl);
 extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
 extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir);
 
-#ifdef CONFIG_PPC_CELL_NATIVE
-extern bool iommu_fixed_is_weak;
-#else
-#define iommu_fixed_is_weak false
-#endif
-
 extern const struct dma_map_ops dma_iommu_ops;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 601e569303e1..70f2f0517509 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -94,8 +94,10 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long
 int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
 
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf);
-#define arch_kexec_locate_mem_hole arch_kexec_locate_mem_hole
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end);
+#define arch_check_excluded_range  arch_check_excluded_range
+
 
 int load_crashdump_segments_ppc64(struct kimage *image,
 				  struct kexec_buf *kbuf);
@@ -112,9 +114,9 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
 
 #ifdef CONFIG_CRASH_RESERVE
 int __init overlaps_crashkernel(unsigned long start, unsigned long size);
-extern void reserve_crashkernel(void);
+extern void arch_reserve_crashkernel(void);
 #else
-static inline void reserve_crashkernel(void) {}
+static inline void arch_reserve_crashkernel(void) {}
 static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
 #endif
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6e1108f8fce6..2d139c807577 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -902,7 +902,6 @@ struct kvm_vcpu_arch {
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index d99863cd6cde..049152f8d597 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -29,6 +29,7 @@ extern cpumask_var_t node_to_cpumask_map[];
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern unsigned long max_pfn;
 u64 memory_hotplug_max(void);
+u64 hot_add_drconf_memory_max(void);
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 71648c126970..f2b6cc4341bb 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -65,6 +65,35 @@ static inline long register_dtl(unsigned long cpu, unsigned long vpa)
 	return vpa_call(H_VPA_REG_DTL, cpu, vpa);
 }
 
+/*
+ * Invokes H_HTM hcall with parameters passed from htm_hcall_wrapper.
+ * flags: Set to hardwareTarget.
+ * target: Specifies target using node index, nodal chip index and core index.
+ * operation : action to perform ie configure, start, stop, deconfigure, trace
+ * based on the HTM type.
+ * param1, param2, param3: parameters for each action.
+ */
+static inline long htm_call(unsigned long flags, unsigned long target,
+               unsigned long operation, unsigned long param1,
+               unsigned long param2, unsigned long param3)
+{
+       return plpar_hcall_norets(H_HTM, flags, target, operation,
+                                 param1, param2, param3);
+}
+
+static inline long htm_hcall_wrapper(unsigned long flags, unsigned long nodeindex,
+               unsigned long nodalchipindex, unsigned long coreindexonchip,
+	       unsigned long type, unsigned long htm_op, unsigned long param1, unsigned long param2,
+	       unsigned long param3)
+{
+	return htm_call(H_HTM_FLAGS_HARDWARE_TARGET | flags,
+                       H_HTM_TARGET_NODE_INDEX(nodeindex) |
+                       H_HTM_TARGET_NODAL_CHIP_INDEX(nodalchipindex) |
+                       H_HTM_TARGET_CORE_INDEX_ON_CHIP(coreindexonchip),
+		       H_HTM_OP(htm_op) | H_HTM_TYPE(type),
+		       param1, param2, param3);
+}
+
 extern void vpa_init(int cpu);
 
 static inline long plpar_pte_enter(unsigned long flags,
diff --git a/arch/powerpc/include/asm/pmi.h b/arch/powerpc/include/asm/pmi.h
deleted file mode 100644
index 478f0a2fe7f4..000000000000
--- a/arch/powerpc/include/asm/pmi.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _POWERPC_PMI_H
-#define _POWERPC_PMI_H
-
-/*
- * Definitions for talking with PMI device on PowerPC
- *
- * PMI (Platform Management Interrupt) is a way to communicate
- * with the BMC (Baseboard Management Controller) via interrupts.
- * Unlike IPMI it is bidirectional and has a low latency.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#ifdef __KERNEL__
-
-#define PMI_TYPE_FREQ_CHANGE	0x01
-#define PMI_TYPE_POWER_BUTTON	0x02
-#define PMI_READ_TYPE		0
-#define PMI_READ_DATA0		1
-#define PMI_READ_DATA1		2
-#define PMI_READ_DATA2		3
-#define PMI_WRITE_TYPE		4
-#define PMI_WRITE_DATA0		5
-#define PMI_WRITE_DATA1		6
-#define PMI_WRITE_DATA2		7
-
-#define PMI_ACK			0x80
-
-#define PMI_TIMEOUT		100
-
-typedef struct {
-	u8	type;
-	u8	data0;
-	u8	data1;
-	u8	data2;
-} pmi_message_t;
-
-struct pmi_handler {
-	struct list_head node;
-	u8 type;
-	void (*handle_pmi_message) (pmi_message_t);
-};
-
-int pmi_register_handler(struct pmi_handler *);
-void pmi_unregister_handler(struct pmi_handler *);
-
-int pmi_send_message(pmi_message_t);
-
-#endif /* __KERNEL__ */
-#endif /* _POWERPC_PMI_H */
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index 8afc92860dbb..7e9a479951a3 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -10,7 +10,6 @@
 #include <linux/pci_hotplug.h>
 #include <linux/irq.h>
 #include <linux/of.h>
-#include <misc/cxl-base.h>
 #include <asm/opal-api.h>
 
 #define PCI_SLOT_ID_PREFIX	(1UL << 63)
@@ -25,25 +24,9 @@ extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state);
 extern int pnv_pci_set_power_state(uint64_t id, uint8_t state,
 				   struct opal_msg *msg);
 
-extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr,
-				  int enable);
-int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
-int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
-			   unsigned int virq);
-int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
-void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
-int pnv_cxl_get_irq_count(struct pci_dev *dev);
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
 int64_t pnv_opal_pci_msi_eoi(struct irq_data *d);
 bool is_pnv_opal_msi(struct irq_chip *chip);
 
-#ifdef CONFIG_CXL_BASE
-int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
-			       struct pci_dev *dev, int num);
-void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
-				  struct pci_dev *dev);
-#endif
-
 struct pnv_php_slot {
 	struct hotplug_slot		slot;
 	uint64_t			id;
diff --git a/arch/powerpc/include/asm/preempt.h b/arch/powerpc/include/asm/preempt.h
new file mode 100644
index 000000000000..000e2b9681f3
--- /dev/null
+++ b/arch/powerpc/include/asm/preempt.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POWERPC_PREEMPT_H
+#define __ASM_POWERPC_PREEMPT_H
+
+#include <asm-generic/preempt.h>
+
+#if defined(CONFIG_PREEMPT_DYNAMIC)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#define need_irq_preemption() \
+	(static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+#else
+#define need_irq_preemption()   (IS_ENABLED(CONFIG_PREEMPTION))
+#endif
+
+#endif /* __ASM_POWERPC_PREEMPT_H */
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index c0107d8ddd8c..f679a11a7e7f 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -17,6 +17,8 @@
 struct device_node;
 struct property;
 
+#define MIN_RMA			768		/* Minimum RMA (in MB) for CAS negotiation */
+
 #define OF_DT_BEGIN_NODE	0x1		/* Start of node, full name */
 #define OF_DT_END_NODE		0x2		/* End node */
 #define OF_DT_PROP		0x3		/* Property: name off, size,
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 04406162fc5a..75fa0293c508 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -515,6 +515,10 @@ extern char rtas_data_buf[RTAS_DATA_BUF_SIZE];
 extern unsigned long rtas_rmo_buf;
 
 extern struct mutex rtas_ibm_get_vpd_lock;
+extern struct mutex rtas_ibm_get_indices_lock;
+extern struct mutex rtas_ibm_set_dynamic_indicator_lock;
+extern struct mutex rtas_ibm_get_dynamic_sensor_state_lock;
+extern struct mutex rtas_ibm_physical_attestation_lock;
 
 #define GLOBAL_INTERRUPT_QUEUE 9005
 
diff --git a/arch/powerpc/include/asm/spu_priv1.h b/arch/powerpc/include/asm/spu_priv1.h
index 6fee411d973d..66b111fa1cd1 100644
--- a/arch/powerpc/include/asm/spu_priv1.h
+++ b/arch/powerpc/include/asm/spu_priv1.h
@@ -215,8 +215,6 @@ spu_disable_spu (struct spu_context *ctx)
  * and only intended to be used by the platform setup code.
  */
 
-extern const struct spu_priv1_ops spu_priv1_mmio_ops;
-
 extern const struct spu_management_ops spu_management_of_ops;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h
index de1018cc522b..e3d5d3823dac 100644
--- a/arch/powerpc/include/asm/static_call.h
+++ b/arch/powerpc/include/asm/static_call.h
@@ -26,4 +26,6 @@
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)	__PPC_SCT(name, "blr")
 #define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)	__PPC_SCT(name, "b .+20")
 
+#define CALL_INSN_SIZE		4
+
 #endif /* _ASM_POWERPC_STATIC_CALL_H */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 9bdd8080299b..f8885586efaf 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -89,9 +89,6 @@ static inline unsigned long tb_ticks_since(unsigned long tstamp)
 #define mulhdu(x, y)	mul_u64_u64_shr(x, y, 64)
 #endif
 
-extern void div128_by_32(u64 dividend_high, u64 dividend_low,
-			 unsigned divisor, struct div_result *dr);
-
 extern void secondary_cpu_time_init(void);
 extern void __init time_init(void);
 
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 16bacfe8c7a2..da15b5efe807 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -152,6 +152,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
 {
 	return cpu == cpu_first_thread_sibling(cpu);
 }
+#define topology_is_primary_thread topology_is_primary_thread
 
 static inline bool topology_smt_thread_allowed(unsigned int cpu)
 {
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 8d972bc98b55..1ca23fbfe087 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_VDSO_H
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
+#define __VDSO_PAGES		4
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/vdso/arch_data.h b/arch/powerpc/include/asm/vdso/arch_data.h
new file mode 100644
index 000000000000..c240a6b87518
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/arch_data.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * 		      IBM Corp.
+ */
+#ifndef _ASM_POWERPC_VDSO_ARCH_DATA_H
+#define _ASM_POWERPC_VDSO_ARCH_DATA_H
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+
+#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
+
+#ifdef CONFIG_PPC64
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
+	__u32 dcache_block_size;		/* L1 d-cache block size     */
+	__u32 icache_block_size;		/* L1 i-cache block size     */
+	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
+	__u32 icache_log_block_size;		/* L1 i-cache log block size */
+	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
+	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
+};
+
+#else /* CONFIG_PPC64 */
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
+	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
+	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
+};
+
+#endif /* CONFIG_PPC64 */
+
+#endif /* _ASM_POWERPC_VDSO_ARCH_DATA_H */
diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h
index 80ce0709725e..067a5396aac6 100644
--- a/arch/powerpc/include/asm/vdso/getrandom.h
+++ b/arch/powerpc/include/asm/vdso/getrandom.h
@@ -43,20 +43,21 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 			    (unsigned long)len, (unsigned long)flags);
 }
 
-static __always_inline struct vdso_rng_data *__arch_get_vdso_rng_data(void)
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void)
 {
-	struct vdso_arch_data *data;
+	struct vdso_rng_data *data;
 
 	asm (
 		"	bcl	20, 31, .+4 ;"
 		"0:	mflr	%0 ;"
-		"	addis	%0, %0, (_vdso_datapage - 0b)@ha ;"
-		"	addi	%0, %0, (_vdso_datapage - 0b)@l  ;"
+		"	addis	%0, %0, (vdso_u_rng_data - 0b)@ha ;"
+		"	addi	%0, %0, (vdso_u_rng_data - 0b)@l  ;"
 		: "=r" (data) : : "lr"
 	);
 
-	return &data->rng_data;
+	return data;
 }
+#define __arch_get_vdso_u_rng_data __arch_get_vdso_u_rng_data
 
 ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
 			     size_t opaque_len);
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index c6390890a60c..99c9d6f43fde 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -94,22 +94,12 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 #endif
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	return get_tb();
 }
 
-const struct vdso_data *__arch_get_vdso_data(void);
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return (void *)vd + (1U << CONFIG_PAGE_SHIFT);
-}
-#endif
-
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
 	return true;
 }
@@ -135,21 +125,22 @@ static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd);
+			       const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #endif
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time,
-				    const struct vdso_data *vd);
+				    const struct vdso_time_data *vd);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
index 48560a119559..c2c9ae1b22e7 100644
--- a/arch/powerpc/include/asm/vdso/vsyscall.h
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -6,19 +6,6 @@
 
 #include <asm/vdso_datapage.h>
 
-static __always_inline
-struct vdso_data *__arch_get_k_vdso_data(void)
-{
-	return vdso_data->data;
-}
-#define __arch_get_k_vdso_data __arch_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__arch_get_k_vdso_rng_data(void)
-{
-	return &vdso_data->rng_data;
-}
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index a202f5b63479..95d45a50355d 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -11,56 +11,18 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/unistd.h>
-#include <linux/time.h>
 #include <vdso/datapage.h>
 
-#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
-
-#ifdef CONFIG_PPC64
-
-struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
-	__u32 dcache_block_size;		/* L1 d-cache block size     */
-	__u32 icache_block_size;		/* L1 i-cache block size     */
-	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
-	__u32 icache_log_block_size;		/* L1 i-cache log block size */
-	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
-	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
-
-	struct vdso_rng_data rng_data;
-
-	struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
-};
-
-#else /* CONFIG_PPC64 */
-
-struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
-	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
-	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
-	struct vdso_rng_data rng_data;
-
-	struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT);
-};
-
-#endif /* CONFIG_PPC64 */
-
-extern struct vdso_arch_data *vdso_data;
-
 #else /* __ASSEMBLY__ */
 
-.macro get_datapage ptr offset=0
+.macro get_datapage ptr symbol
 	bcl	20, 31, .+4
 999:
 	mflr	\ptr
-	addis	\ptr, \ptr, (_vdso_datapage - 999b + \offset)@ha
-	addi	\ptr, \ptr, (_vdso_datapage - 999b + \offset)@l
+	addis	\ptr, \ptr, (\symbol - 999b)@ha
+	addi	\ptr, \ptr, (\symbol - 999b)@l
 .endm
 
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 89090485bec1..60ef312dab05 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -31,7 +31,6 @@
 #ifdef CONFIG_PPC_ICP_NATIVE
 extern int icp_native_init(void);
 extern void icp_native_flush_interrupt(void);
-extern void icp_native_cause_ipi_rm(int cpu);
 #else
 static inline int icp_native_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h
index f2d44b44f46c..535cdb1e411a 100644
--- a/arch/powerpc/include/asm/xmon.h
+++ b/arch/powerpc/include/asm/xmon.h
@@ -12,13 +12,11 @@
 
 #ifdef CONFIG_XMON
 extern void xmon_setup(void);
-void __init xmon_register_spus(struct list_head *list);
 struct pt_regs;
 extern int xmon(struct pt_regs *excp);
 extern irqreturn_t xmon_irq(int, void *);
 #else
 static inline void xmon_setup(void) { }
-static inline void xmon_register_spus(struct list_head *list) { }
 #endif
 
 #if defined(CONFIG_XMON) && defined(CONFIG_SMP)
diff --git a/arch/powerpc/include/uapi/asm/papr-indices.h b/arch/powerpc/include/uapi/asm/papr-indices.h
new file mode 100644
index 000000000000..c2999d89d52a
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-indices.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_INDICES_H_
+#define _UAPI_PAPR_INDICES_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+#define LOC_CODE_SIZE			80
+#define RTAS_GET_INDICES_BUF_SIZE	SZ_4K
+
+struct papr_indices_io_block {
+	union {
+		struct {
+			__u8 is_sensor; /* 0 for indicator and 1 for sensor */
+			__u32 indice_type;
+		} indices;
+		struct {
+			__u32 token; /* Sensor or indicator token */
+			__u32 state; /* get / set state */
+			/*
+			 * PAPR+ 12.3.2.4 Converged Location Code Rules - Length
+			 * Restrictions. 79 characters plus null.
+			 */
+			char location_code_str[LOC_CODE_SIZE]; /* location code */
+		} dynamic_param;
+	};
+};
+
+/*
+ * ioctls for /dev/papr-indices.
+ * PAPR_INDICES_IOC_GET: Returns a get-indices handle fd to read data
+ * PAPR_DYNAMIC_SENSOR_IOC_GET: Gets the state of the input sensor
+ * PAPR_DYNAMIC_INDICATOR_IOC_SET: Sets the new state for the input indicator
+ */
+#define PAPR_INDICES_IOC_GET		_IOW(PAPR_MISCDEV_IOC_ID, 3, struct papr_indices_io_block)
+#define PAPR_DYNAMIC_SENSOR_IOC_GET	_IOWR(PAPR_MISCDEV_IOC_ID, 4, struct papr_indices_io_block)
+#define PAPR_DYNAMIC_INDICATOR_IOC_SET	_IOW(PAPR_MISCDEV_IOC_ID, 5, struct papr_indices_io_block)
+
+
+#endif /* _UAPI_PAPR_INDICES_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-physical-attestation.h b/arch/powerpc/include/uapi/asm/papr-physical-attestation.h
new file mode 100644
index 000000000000..ea746837bb9a
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-physical-attestation.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_PHYSICAL_ATTESTATION_H_
+#define _UAPI_PAPR_PHYSICAL_ATTESTATION_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+#define PAPR_PHYATTEST_MAX_INPUT 4084 /* Max 4K buffer: 4K-12 */
+
+/*
+ * Defined in PAPR 2.13+ 21.6 Attestation Command Structures.
+ * User space pass this struct and the max size should be 4K.
+ */
+struct papr_phy_attest_io_block {
+	__u8 version;
+	__u8 command;
+	__u8 TCG_major_ver;
+	__u8 TCG_minor_ver;
+	__be32 length;
+	__be32 correlator;
+	__u8 payload[PAPR_PHYATTEST_MAX_INPUT];
+};
+
+/*
+ * ioctl for /dev/papr-physical-attestation. Returns a attestation
+ * command fd handle
+ */
+#define PAPR_PHY_ATTEST_IOC_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 8, struct papr_phy_attest_io_block)
+
+#endif /* _UAPI_PAPR_PHYSICAL_ATTESTATION_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-platform-dump.h b/arch/powerpc/include/uapi/asm/papr-platform-dump.h
new file mode 100644
index 000000000000..8a1c060e89a9
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-platform-dump.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_PLATFORM_DUMP_H_
+#define _UAPI_PAPR_PLATFORM_DUMP_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+/*
+ * ioctl for /dev/papr-platform-dump. Returns a platform-dump handle fd
+ * corresponding to dump tag.
+ */
+#define PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 6, __u64)
+#define PAPR_PLATFORM_DUMP_IOC_INVALIDATE    _IOW(PAPR_MISCDEV_IOC_ID, 7, __u64)
+
+#endif /* _UAPI_PAPR_PLATFORM_DUMP_H_ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f43c1198768c..9d1ab3971694 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -70,7 +70,7 @@ obj-y				:= cputable.o syscalls.o switch.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
-				   of_platform.o prom_parse.o firmware.o \
+				   prom_parse.o firmware.o \
 				   hw_breakpoint_constraints.o interrupt.o \
 				   kdebugfs.o stacktrace.o syscall.o
 obj-y				+= ptrace/
@@ -152,8 +152,6 @@ obj-$(CONFIG_PCI_MSI)		+= msi.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
-obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
-
 obj-y				+= trace/
 
 ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
@@ -162,9 +160,7 @@ endif
 
 obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
 
-ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),)
 obj-y				+= ppc_save_regs.o
-endif
 
 obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7a390bd4f4af..b3048f6d3822 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -334,7 +334,6 @@ int main(void)
 #endif /* ! CONFIG_PPC64 */
 
 	/* datapage offsets for use by vdso */
-	OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
 	OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
 #ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index f0ae39e77e37..4d64a5db50f3 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -136,7 +136,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pci_controller *phb = pci_bus_to_host(pdev->bus);
 
-	if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+	if (!phb->controller_ops.iommu_bypass_supported)
 		return false;
 	return phb->controller_ops.iommu_bypass_supported(pdev, mask);
 }
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 195b075d116c..b7229430ca94 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2537,27 +2537,8 @@ EXC_REAL_NONE(0x1000, 0x100)
 EXC_VIRT_NONE(0x5000, 0x100)
 EXC_REAL_NONE(0x1100, 0x100)
 EXC_VIRT_NONE(0x5100, 0x100)
-
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_system_error)
-	IVEC=0x1200
-	IHSRR=1
-INT_DEFINE_END(cbe_system_error)
-
-EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
-	GEN_INT_ENTRY cbe_system_error, virt=0
-EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
-EXC_VIRT_NONE(0x5200, 0x100)
-EXC_COMMON_BEGIN(cbe_system_error_common)
-	GEN_COMMON cbe_system_error
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_system_error_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
-#endif
 
 /**
  * Interrupt 0x1300 - Instruction Address Breakpoint Interrupt.
@@ -2708,26 +2689,8 @@ EXC_COMMON_BEGIN(denorm_exception_common)
 	b	interrupt_return_hsrr
 
 
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_maintenance)
-	IVEC=0x1600
-	IHSRR=1
-INT_DEFINE_END(cbe_maintenance)
-
-EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
-	GEN_INT_ENTRY cbe_maintenance, virt=0
-EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
-EXC_VIRT_NONE(0x5600, 0x100)
-EXC_COMMON_BEGIN(cbe_maintenance_common)
-	GEN_COMMON cbe_maintenance
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_maintenance_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
-#endif
 
 
 INT_DEFINE_BEGIN(altivec_assist)
@@ -2755,26 +2718,8 @@ EXC_COMMON_BEGIN(altivec_assist_common)
 	b	interrupt_return_srr
 
 
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_thermal)
-	IVEC=0x1800
-	IHSRR=1
-INT_DEFINE_END(cbe_thermal)
-
-EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
-	GEN_INT_ENTRY cbe_thermal, virt=0
-EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
-EXC_VIRT_NONE(0x5800, 0x100)
-EXC_COMMON_BEGIN(cbe_thermal_common)
-	GEN_COMMON cbe_thermal
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_thermal_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
-#endif
 
 
 #ifdef CONFIG_PPC_WATCHDOG
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 4b371c738213..8ca49e40c473 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,7 @@
 #include <asm/fadump-internal.h>
 #include <asm/setup.h>
 #include <asm/interrupt.h>
+#include <asm/prom.h>
 
 /*
  * The CPU who acquired the lock to trigger the fadump crash should
@@ -289,10 +290,8 @@ static void __init fadump_show_config(void)
 	if (!fw_dump.fadump_supported)
 		return;
 
-	pr_debug("Fadump enabled    : %s\n",
-				(fw_dump.fadump_enabled ? "yes" : "no"));
-	pr_debug("Dump Active       : %s\n",
-				(fw_dump.dump_active ? "yes" : "no"));
+	pr_debug("Fadump enabled    : %s\n", str_yes_no(fw_dump.fadump_enabled));
+	pr_debug("Dump Active       : %s\n", str_yes_no(fw_dump.dump_active));
 	pr_debug("Dump section sizes:\n");
 	pr_debug("    CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
 	pr_debug("    HPTE region size   : %lx\n", fw_dump.hpte_region_size);
@@ -751,7 +750,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
 	 * prstatus.pr_pid = ????
 	 */
 	elf_core_copy_regs(&prstatus.pr_reg, regs);
-	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+	buf = append_elf_note(buf, NN_PRSTATUS, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	return buf;
 }
@@ -1764,19 +1763,19 @@ void __init fadump_setup_param_area(void)
 		range_end = memblock_end_of_DRAM();
 	} else {
 		/*
-		 * Passing additional parameters is supported for hash MMU only
-		 * if the first memory block size is 768MB or higher.
+		 * Memory range for passing additional parameters for HASH MMU
+		 * must meet the following conditions:
+		 * 1. The first memory block size must be higher than the
+		 *    minimum RMA (MIN_RMA) size. Bootloader can use memory
+		 *    upto RMA size. So it should be avoided.
+		 * 2. The range should be between MIN_RMA and RMA size (ppc64_rma_size)
+		 * 3. It must not overlap with the fadump reserved area.
 		 */
-		if (ppc64_rma_size < 0x30000000)
+		if (ppc64_rma_size < MIN_RMA*1024*1024)
 			return;
 
-		/*
-		 * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving
-		 * memory for passing additional parameters in this range to avoid
-		 * being stomped on by PFW/bootloader.
-		 */
-		range_start = 0x2A000000;
-		range_end = range_start + 0x4000000;
+		range_start = MIN_RMA * 1024 * 1024;
+		range_end = min(ppc64_rma_size, fw_dump.boot_mem_top);
 	}
 
 	fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE,
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 8f4acc55407b..e0c681d0b076 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -25,6 +25,10 @@
 unsigned long global_dbcr0[NR_CPUS];
 #endif
 
+#if defined(CONFIG_PREEMPT_DYNAMIC)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
 static inline bool exit_must_hard_disable(void)
@@ -396,7 +400,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
-		if (IS_ENABLED(CONFIG_PREEMPTION)) {
+		if (need_irq_preemption()) {
 			/* Return to preemptible kernel context */
 			if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
 				if (preempt_count() == 0)
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
deleted file mode 100644
index c877f074d174..000000000000
--- a/arch/powerpc/kernel/io-workarounds.c
+++ /dev/null
@@ -1,197 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Support PCI IO workaround
- *
- *  Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *		       IBM, Corp.
- *  (C) Copyright 2007-2008 TOSHIBA CORPORATION
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/sched/mm.h>	/* for init_mm */
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-#include <asm/io-workarounds.h>
-#include <asm/pte-walk.h>
-
-
-#define IOWA_MAX_BUS	8
-
-static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
-static unsigned int iowa_bus_count;
-
-static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
-{
-	int i, j;
-	struct resource *res;
-	unsigned long vstart, vend;
-
-	for (i = 0; i < iowa_bus_count; i++) {
-		struct iowa_bus *bus = &iowa_busses[i];
-		struct pci_controller *phb = bus->phb;
-
-		if (vaddr) {
-			vstart = (unsigned long)phb->io_base_virt;
-			vend = vstart + phb->pci_io_size - 1;
-			if ((vaddr >= vstart) && (vaddr <= vend))
-				return bus;
-		}
-
-		if (paddr)
-			for (j = 0; j < 3; j++) {
-				res = &phb->mem_resources[j];
-				if (paddr >= res->start && paddr <= res->end)
-					return bus;
-			}
-	}
-
-	return NULL;
-}
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
-	struct iowa_bus *bus;
-	int token;
-
-	token = PCI_GET_ADDR_TOKEN(addr);
-
-	if (token && token <= iowa_bus_count)
-		bus = &iowa_busses[token - 1];
-	else {
-		unsigned long vaddr, paddr;
-
-		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
-		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
-			return NULL;
-
-		paddr = ppc_find_vmap_phys(vaddr);
-
-		bus = iowa_pci_find(vaddr, paddr);
-
-		if (bus == NULL)
-			return NULL;
-	}
-
-	return bus;
-}
-#else /* CONFIG_PPC_INDIRECT_MMIO */
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
-	return NULL;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-#ifdef CONFIG_PPC_INDIRECT_PIO
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
-	unsigned long vaddr = (unsigned long)pci_io_base + port;
-	return iowa_pci_find(vaddr, 0);
-}
-#else
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
-	return NULL;
-}
-#endif
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
-static ret iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name)			\
-		return bus->ops->name al;			\
-	return __do_##name al;					\
-}
-
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
-static void iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name) {		\
-		bus->ops->name al;				\
-		return;						\
-	}							\
-	__do_##name al;						\
-}
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-static const struct ppc_pci_io iowa_pci_io = {
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	.name = iowa_##name,
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)	.name = iowa_##name,
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-};
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-			   pgprot_t prot, void *caller)
-{
-	struct iowa_bus *bus;
-	void __iomem *res = __ioremap_caller(addr, size, prot, caller);
-	int busno;
-
-	bus = iowa_pci_find(0, (unsigned long)addr);
-	if (bus != NULL) {
-		busno = bus - iowa_busses;
-		PCI_SET_ADDR_TOKEN(res, busno + 1);
-	}
-	return res;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-bool io_workaround_inited;
-
-/* Enable IO workaround */
-static void io_workaround_init(void)
-{
-	if (io_workaround_inited)
-		return;
-	ppc_pci_io = iowa_pci_io;
-	io_workaround_inited = true;
-}
-
-/* Register new bus to support workaround */
-void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops,
-		       int (*initfunc)(struct iowa_bus *, void *), void *data)
-{
-	struct iowa_bus *bus;
-	struct device_node *np = phb->dn;
-
-	io_workaround_init();
-
-	if (iowa_bus_count >= IOWA_MAX_BUS) {
-		pr_err("IOWA:Too many pci bridges, "
-		       "workarounds disabled for %pOF\n", np);
-		return;
-	}
-
-	bus = &iowa_busses[iowa_bus_count];
-	bus->phb = phb;
-	bus->ops = ops;
-	bus->private = data;
-
-	if (initfunc)
-		if ((*initfunc)(bus, data))
-			return;
-
-	iowa_bus_count++;
-
-	pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np);
-}
-
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 6af535905984..bcc201c01514 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -31,13 +31,14 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count)
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		tmp = *(const volatile u8 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
 EXPORT_SYMBOL(_insb);
 
@@ -47,75 +48,80 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count)
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		*(volatile u8 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
 EXPORT_SYMBOL(_outsb);
 
-void _insw_ns(const volatile u16 __iomem *port, void *buf, long count)
+void _insw(const volatile u16 __iomem *port, void *buf, long count)
 {
 	u16 *tbuf = buf;
 	u16 tmp;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		tmp = *(const volatile u16 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
-EXPORT_SYMBOL(_insw_ns);
+EXPORT_SYMBOL(_insw);
 
-void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
+void _outsw(volatile u16 __iomem *port, const void *buf, long count)
 {
 	const u16 *tbuf = buf;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		*(volatile u16 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
-EXPORT_SYMBOL(_outsw_ns);
+EXPORT_SYMBOL(_outsw);
 
-void _insl_ns(const volatile u32 __iomem *port, void *buf, long count)
+void _insl(const volatile u32 __iomem *port, void *buf, long count)
 {
 	u32 *tbuf = buf;
 	u32 tmp;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		tmp = *(const volatile u32 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
-EXPORT_SYMBOL(_insl_ns);
+EXPORT_SYMBOL(_insl);
 
-void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
+void _outsl(volatile u32 __iomem *port, const void *buf, long count)
 {
 	const u32 *tbuf = buf;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
 		*(volatile u32 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
-EXPORT_SYMBOL(_outsl_ns);
+EXPORT_SYMBOL(_outsl);
 
 #define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
 
@@ -127,7 +133,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
 	lc |= lc << 8;
 	lc |= lc << 16;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && !IO_CHECK_ALIGN(p, 4)) {
 		*((volatile u8 *)p) = c;
 		p++;
@@ -143,7 +149,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
 		p++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memset_io);
 
@@ -152,7 +158,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 {
 	void *vsrc = (void __force *) src;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) {
 		*((u8 *)dest) = *((volatile u8 *)vsrc);
 		eieio();
@@ -174,7 +180,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 		dest++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memcpy_fromio);
 
@@ -182,7 +188,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 {
 	void *vdest = (void __force *) dest;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) {
 		*((volatile u8 *)vdest) = *((u8 *)src);
 		src++;
@@ -201,6 +207,6 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 		vdest++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memcpy_toio);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0ebae6e4c19d..244eb4857e7f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/dma-mapping.h>
 #include <linux/bitmap.h>
 #include <linux/iommu-helper.h>
@@ -769,8 +770,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	iommu_table_clear(tbl);
 
 	if (!welcomed) {
-		printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
-		       novmerge ? "disabled" : "enabled");
+		pr_info("IOMMU table initialized, virtual merging %s\n",
+			str_disabled_enabled(novmerge));
 		welcomed = 1;
 	}
 
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 34a5aec4908f..126bf3b06ab7 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -258,10 +258,6 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 			break;
 		}
 	}
-	if (i == hdr->e_shnum) {
-		pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name);
-		return -ENOEXEC;
-	}
 #endif
 
 	pr_debug("Looks like a total of %lu stubs, max\n", relocs);
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
deleted file mode 100644
index adc76fa58d1e..000000000000
--- a/arch/powerpc/kernel/of_platform.c
+++ /dev/null
@@ -1,102 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *    Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
- *			 <benh@kernel.crashing.org>
- *    and		 Arnd Bergmann, IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/mod_devicetable.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-#include <linux/atomic.h>
-
-#include <asm/errno.h>
-#include <asm/topology.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-#include <asm/eeh.h>
-
-#ifdef CONFIG_PPC_OF_PLATFORM_PCI
-
-/* The probing of PCI controllers from of_platform is currently
- * 64 bits only, mostly due to gratuitous differences between
- * the 32 and 64 bits PCI code on PowerPC and the 32 bits one
- * lacking some bits needed here.
- */
-
-static int of_pci_phb_probe(struct platform_device *dev)
-{
-	struct pci_controller *phb;
-
-	/* Check if we can do that ... */
-	if (ppc_md.pci_setup_phb == NULL)
-		return -ENODEV;
-
-	pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node);
-
-	/* Alloc and setup PHB data structure */
-	phb = pcibios_alloc_controller(dev->dev.of_node);
-	if (!phb)
-		return -ENODEV;
-
-	/* Setup parent in sysfs */
-	phb->parent = &dev->dev;
-
-	/* Setup the PHB using arch provided callback */
-	if (ppc_md.pci_setup_phb(phb)) {
-		pcibios_free_controller(phb);
-		return -ENODEV;
-	}
-
-	/* Process "ranges" property */
-	pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0);
-
-	/* Init pci_dn data structures */
-	pci_devs_phb_init_dynamic(phb);
-
-	/* Create EEH PE for the PHB */
-	eeh_phb_pe_create(phb);
-
-	/* Scan the bus */
-	pcibios_scan_phb(phb);
-	if (phb->bus == NULL)
-		return -ENXIO;
-
-	/* Claim resources. This might need some rework as well depending
-	 * whether we are doing probe-only or not, like assigning unassigned
-	 * resources etc...
-	 */
-	pcibios_claim_one_bus(phb->bus);
-
-	/* Add probed PCI devices to the device model */
-	pci_bus_add_devices(phb->bus);
-
-	return 0;
-}
-
-static const struct of_device_id of_pci_phb_ids[] = {
-	{ .type = "pci", },
-	{ .type = "pcix", },
-	{ .type = "pcie", },
-	{ .type = "pciex", },
-	{ .type = "ht", },
-	{}
-};
-
-static struct platform_driver of_pci_phb_driver = {
-	.probe = of_pci_phb_probe,
-	.driver = {
-		.name = "of-pci",
-		.of_match_table = of_pci_phb_ids,
-	},
-};
-
-builtin_platform_driver(of_pci_phb_driver);
-
-#endif /* CONFIG_PPC_OF_PLATFORM_PCI */
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index 3816a2bf2b84..d083b4517065 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -9,6 +9,7 @@
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/string.h>
 
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
@@ -56,7 +57,7 @@ static int __init proc_ppc64_init(void)
 {
 	struct proc_dir_entry *pde;
 
-	strcpy((char *)systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+	strscpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
 	systemcfg->version.major = SYSTEMCFG_MAJOR;
 	systemcfg->version.minor = SYSTEMCFG_MINOR;
 	systemcfg->processor = mfspr(SPRN_PVR);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ef91f71e07c4..855e09886503 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1000,7 +1000,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
 
 	WARN_ON(tm_suspend_disabled);
 
-	TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
+	TM_DEBUG("---- tm_reclaim on pid %d (NIP=%lx, "
 		 "ccr=%lx, msr=%lx, trap=%lx)\n",
 		 tsk->pid, thr->regs->nip,
 		 thr->regs->ccr, thr->regs->msr,
@@ -1008,7 +1008,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
 
 	tm_reclaim_thread(thr, TM_CAUSE_RESCHED);
 
-	TM_DEBUG("--- tm_reclaim on pid %d complete\n",
+	TM_DEBUG("---- tm_reclaim on pid %d complete\n",
 		 tsk->pid);
 
 out_and_saveregs:
@@ -2367,14 +2367,14 @@ void __no_sanitize_address show_stack(struct task_struct *tsk,
 				(sp + STACK_INT_FRAME_REGS);
 
 			lr = regs->link;
-			printk("%s--- interrupt: %lx at %pS\n",
+			printk("%s---- interrupt: %lx at %pS\n",
 			       loglvl, regs->trap, (void *)regs->nip);
 
 			// Detect the case of an empty pt_regs at the very base
 			// of the stack and suppress showing it in full.
 			if (!empty_user_regs(regs, tsk)) {
 				__show_regs(regs);
-				printk("%s--- interrupt: %lx\n", loglvl, regs->trap);
+				printk("%s---- interrupt: %lx\n", loglvl, regs->trap);
 			}
 
 			firstframe = 1;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index e0059842a1c6..9ed9dde7d231 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -860,7 +860,7 @@ void __init early_init_devtree(void *params)
 	 */
 	if (fadump_reserve_mem() == 0)
 #endif
-		reserve_crashkernel();
+		arch_reserve_crashkernel();
 	early_reserve_mem();
 
 	if (memory_limit > memblock_phys_mem_size())
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 57082fac4668..827c958677f8 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1061,7 +1061,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 		.virt_base = cpu_to_be32(0xffffffff),
 		.virt_size = cpu_to_be32(0xffffffff),
 		.load_base = cpu_to_be32(0xffffffff),
-		.min_rma = cpu_to_be32(512),		/* 512MB min RMA */
+		.min_rma = cpu_to_be32(MIN_RMA),
 		.min_load = cpu_to_be32(0xffffffff),	/* full client load */
 		.min_rma_percent = 0,	/* min RMA percentage of total RAM */
 		.max_pft_size = 48,	/* max log_2(hash table size) */
@@ -2889,11 +2889,11 @@ static void __init fixup_device_tree_pmac(void)
 	char type[8];
 	phandle node;
 
-	// Some pmacs are missing #size-cells on escc nodes
+	// Some pmacs are missing #size-cells on escc or i2s nodes
 	for (node = 0; prom_next_node(&node); ) {
 		type[0] = '\0';
 		prom_getprop(node, "device_type", type, sizeof(type));
-		if (prom_strcmp(type, "escc"))
+		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s"))
 			continue;
 
 		if (prom_getproplen(node, "#size-cells") != PROM_ERROR)
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 727ed4a14545..c6997df63287 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -215,7 +215,7 @@ static int do_seccomp(struct pt_regs *regs)
 	 * have already loaded -ENOSYS into r3, or seccomp has put
 	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
 	 */
-	if (__secure_computing(NULL))
+	if (__secure_computing())
 		return -1;
 
 	/*
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index d31c9799cab2..e61245c4468e 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -92,12 +92,12 @@ struct rtas_function {
  * Per-function locks for sequence-based RTAS functions.
  */
 static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
-static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
-static DEFINE_MUTEX(rtas_ibm_get_indices_lock);
 static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
-static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
-static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
 DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
 
 static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__CHECK_EXCEPTION] = {
@@ -798,66 +798,6 @@ void __init udbg_init_rtas_panel(void)
 	udbg_putc = call_rtas_display_status_delay;
 }
 
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
-
-/* If you think you're dying before early_init_dt_scan_rtas() does its
- * work, you can hard code the token values for your firmware here and
- * hardcode rtas.base/entry etc.
- */
-static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
-static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;
-
-static void udbg_rtascon_putc(char c)
-{
-	int tries;
-
-	if (!rtas.base)
-		return;
-
-	/* Add CRs before LFs */
-	if (c == '\n')
-		udbg_rtascon_putc('\r');
-
-	/* if there is more than one character to be displayed, wait a bit */
-	for (tries = 0; tries < 16; tries++) {
-		if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
-			break;
-		udelay(1000);
-	}
-}
-
-static int udbg_rtascon_getc_poll(void)
-{
-	int c;
-
-	if (!rtas.base)
-		return -1;
-
-	if (rtas_call(rtas_getchar_token, 0, 2, &c))
-		return -1;
-
-	return c;
-}
-
-static int udbg_rtascon_getc(void)
-{
-	int c;
-
-	while ((c = udbg_rtascon_getc_poll()) == -1)
-		;
-
-	return c;
-}
-
-
-void __init udbg_init_rtas_console(void)
-{
-	udbg_putc = udbg_rtascon_putc;
-	udbg_getc = udbg_rtascon_getc;
-	udbg_getc_poll = udbg_rtascon_getc_poll;
-}
-#endif /* CONFIG_UDBG_RTAS_CONSOLE */
-
 void rtas_progress(char *s, unsigned short hex)
 {
 	struct device_node *root;
@@ -2135,21 +2075,6 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 		rtas.size = *sizep;
 	}
 
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
-	basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
-	if (basep)
-		rtas_putchar_token = *basep;
-
-	basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
-	if (basep)
-		rtas_getchar_token = *basep;
-
-	if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
-	    rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
-		udbg_init_rtas_console();
-
-#endif
-
 	/* break now */
 	return 1;
 }
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index fbeb1cbac01b..afb690a172b4 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -52,7 +52,7 @@ static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 static ssize_t data_read(struct file *filep, struct kobject *kobj,
-			 struct bin_attribute *attr, char *buf, loff_t off,
+			 const struct bin_attribute *attr, char *buf, loff_t off,
 			 size_t count)
 {
 	char *data;
@@ -85,7 +85,7 @@ data_fail:
 }
 
 static ssize_t update_write(struct file *filep, struct kobject *kobj,
-			    struct bin_attribute *attr, char *buf, loff_t off,
+			    const struct bin_attribute *attr, char *buf, loff_t off,
 			    size_t count)
 {
 	int rc;
@@ -104,11 +104,11 @@ static struct kobj_attribute format_attr = __ATTR_RO(format);
 
 static struct kobj_attribute size_attr = __ATTR_RO(size);
 
-static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0);
+static struct bin_attribute data_attr __ro_after_init = __BIN_ATTR_RO(data, 0);
 
-static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0);
+static struct bin_attribute update_attr __ro_after_init = __BIN_ATTR_WO(update, 0);
 
-static struct bin_attribute *secvar_bin_attrs[] = {
+static const struct bin_attribute *const secvar_bin_attrs[] = {
 	&data_attr,
 	&update_attr,
 	NULL,
@@ -121,7 +121,7 @@ static struct attribute *secvar_attrs[] = {
 
 static const struct attribute_group secvar_attr_group = {
 	.attrs = secvar_attrs,
-	.bin_attrs = secvar_bin_attrs,
+	.bin_attrs_new = secvar_bin_attrs,
 };
 __ATTRIBUTE_GROUPS(secvar_attr);
 
@@ -130,7 +130,7 @@ static const struct kobj_type secvar_ktype = {
 	.default_groups = secvar_attr_groups,
 };
 
-static int update_kobj_size(void)
+static __init int update_kobj_size(void)
 {
 
 	u64 varsize;
@@ -145,7 +145,7 @@ static int update_kobj_size(void)
 	return 0;
 }
 
-static int secvar_sysfs_config(struct kobject *kobj)
+static __init int secvar_sysfs_config(struct kobject *kobj)
 {
 	struct attribute_group config_group = {
 		.name = "config",
@@ -158,7 +158,7 @@ static int secvar_sysfs_config(struct kobject *kobj)
 	return 0;
 }
 
-static int add_var(const char *name)
+static __init int add_var(const char *name)
 {
 	struct kobject *kobj;
 	int rc;
@@ -181,7 +181,7 @@ static int add_var(const char *name)
 	return 0;
 }
 
-static int secvar_sysfs_load(void)
+static __init int secvar_sysfs_load(void)
 {
 	u64 namesize = 0;
 	char *name;
@@ -209,7 +209,7 @@ static int secvar_sysfs_load(void)
 	return rc;
 }
 
-static int secvar_sysfs_load_static(void)
+static __init int secvar_sysfs_load_static(void)
 {
 	const char * const *name_ptr = secvar_ops->var_names;
 	int rc;
@@ -224,7 +224,7 @@ static int secvar_sysfs_load_static(void)
 	return 0;
 }
 
-static int secvar_sysfs_init(void)
+static __init int secvar_sysfs_init(void)
 {
 	u64 max_size;
 	int rc;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index a08b0ede4e64..68d47c53876c 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -957,8 +957,6 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Parse memory topology */
 	mem_topology_setup();
-	/* Set max_mapnr before paging_init() */
-	set_max_mapnr(max_pfn);
 	high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
 
 	/*
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e67f3048611f..7284c8021eeb 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -892,7 +892,7 @@ unsigned long memory_block_size_bytes(void)
 }
 #endif
 
-#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
+#ifdef CONFIG_PPC_INDIRECT_PIO
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c
index 7cfd0710e757..ec3101f95e53 100644
--- a/arch/powerpc/kernel/static_call.c
+++ b/arch/powerpc/kernel/static_call.c
@@ -8,26 +8,54 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	int err;
 	bool is_ret0 = (func == __static_call_return0);
-	unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func);
-	bool is_short = is_offset_in_branch_range((long)target - (long)tramp);
-
-	if (!tramp)
-		return;
+	unsigned long _tramp = (unsigned long)tramp;
+	unsigned long _func = (unsigned long)func;
+	unsigned long _ret0 = _tramp + PPC_SCT_RET0;
+	bool is_short = is_offset_in_branch_range((long)func - (long)(site ? : tramp));
 
 	mutex_lock(&text_mutex);
 
-	if (func && !is_short) {
-		err = patch_ulong(tramp + PPC_SCT_DATA, target);
-		if (err)
-			goto out;
+	if (site && tail) {
+		if (!func)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_BLR()));
+		else if (is_ret0)
+			err = patch_branch(site, _ret0, 0);
+		else if (is_short)
+			err = patch_branch(site, _func, 0);
+		else if (tramp)
+			err = patch_branch(site, _tramp, 0);
+		else
+			err = 0;
+	} else if (site) {
+		if (!func)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_NOP()));
+		else if (is_ret0)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_LI(_R3, 0)));
+		else if (is_short)
+			err = patch_branch(site, _func, BRANCH_SET_LINK);
+		else if (tramp)
+			err = patch_branch(site, _tramp, BRANCH_SET_LINK);
+		else
+			err = 0;
+	} else if (tramp) {
+		if (func && !is_short) {
+			err = patch_ulong(tramp + PPC_SCT_DATA, _func);
+			if (err)
+				goto out;
+		}
+
+		if (!func)
+			err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
+		else if (is_ret0)
+			err = patch_branch(tramp, _ret0, 0);
+		else if (is_short)
+			err = patch_branch(tramp, _func, 0);
+		else
+			err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
+	} else {
+		err = 0;
 	}
 
-	if (!func)
-		err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
-	else if (is_short)
-		err = patch_branch(tramp, target, 0);
-	else
-		err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
 out:
 	mutex_unlock(&text_mutex);
 
diff --git a/arch/powerpc/kernel/switch.S b/arch/powerpc/kernel/switch.S
index 608c0ce7cec6..59e3ee99db0e 100644
--- a/arch/powerpc/kernel/switch.S
+++ b/arch/powerpc/kernel/switch.S
@@ -39,7 +39,6 @@ flush_branch_caches:
 
 	// Flush the link stack
 	.rept 64
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 	b	1f
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index d8b4ab78bef0..9a084bdb8926 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -557,3 +557,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0727332ad86f..8224381c1dba 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -901,6 +901,38 @@ void secondary_cpu_time_init(void)
 	register_decrementer_clockevent(smp_processor_id());
 }
 
+/*
+ * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
+ * result.
+ */
+static __init void div128_by_32(u64 dividend_high, u64 dividend_low,
+				unsigned int divisor, struct div_result *dr)
+{
+	unsigned long a, b, c, d;
+	unsigned long w, x, y, z;
+	u64 ra, rb, rc;
+
+	a = dividend_high >> 32;
+	b = dividend_high & 0xffffffff;
+	c = dividend_low >> 32;
+	d = dividend_low & 0xffffffff;
+
+	w = a / divisor;
+	ra = ((u64)(a - (w * divisor)) << 32) + b;
+
+	rb = ((u64)do_div(ra, divisor) << 32) + c;
+	x = ra;
+
+	rc = ((u64)do_div(rb, divisor) << 32) + d;
+	y = rb;
+
+	do_div(rc, divisor);
+	z = rc;
+
+	dr->result_high = ((u64)w << 32) + x;
+	dr->result_low  = ((u64)y << 32) + z;
+}
+
 /* This function is only called on the boot processor */
 void __init time_init(void)
 {
@@ -950,7 +982,7 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
 	}
 
-	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+	vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec;
 #ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
 #endif
@@ -974,39 +1006,6 @@ void __init time_init(void)
 	enable_sched_clock_irqtime();
 }
 
-/*
- * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
- * result.
- */
-void div128_by_32(u64 dividend_high, u64 dividend_low,
-		  unsigned divisor, struct div_result *dr)
-{
-	unsigned long a, b, c, d;
-	unsigned long w, x, y, z;
-	u64 ra, rb, rc;
-
-	a = dividend_high >> 32;
-	b = dividend_high & 0xffffffff;
-	c = dividend_low >> 32;
-	d = dividend_low & 0xffffffff;
-
-	w = a / divisor;
-	ra = ((u64)(a - (w * divisor)) << 32) + b;
-
-	rb = ((u64) do_div(ra, divisor) << 32) + c;
-	x = ra;
-
-	rc = ((u64) do_div(rb, divisor) << 32) + d;
-	y = rb;
-
-	do_div(rc, divisor);
-	z = rc;
-
-	dr->result_high = ((u64)w << 32) + x;
-	dr->result_low  = ((u64)y << 32) + z;
-
-}
-
 /* We don't need to calibrate delay, we use the CPU timebase for that */
 void calibrate_delay(void)
 {
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 2f776f137a89..6dca92d5a6e8 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -115,10 +115,8 @@ static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long a
 {
 	struct module *mod = NULL;
 
-	preempt_disable();
-	mod = __module_text_address(ip);
-	preempt_enable();
-
+	scoped_guard(rcu)
+		mod = __module_text_address(ip);
 	if (!mod)
 		pr_err("No module loaded at addr=%lx\n", ip);
 
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index ac35015f04c6..5c6e545d1708 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -120,10 +120,8 @@ static struct module *ftrace_lookup_module(struct dyn_ftrace *rec)
 {
 	struct module *mod;
 
-	preempt_disable();
-	mod = __module_text_address(rec->ip);
-	preempt_enable();
-
+	scoped_guard(rcu)
+		mod = __module_text_address(rec->ip);
 	if (!mod)
 		pr_err("No module loaded at addr=%lx\n", rec->ip);
 
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 2c1b24100eca..3565c67fc638 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -212,10 +212,10 @@
 	bne-	1f
 
 	mr	r3, r15
+1:	mtlr	r3
 	.if \allregs == 0
 	REST_GPR(15, r1)
 	.endif
-1:	mtlr	r3
 #endif
 
 	/* Restore gprs */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index edf5cabe5dfd..cb8e9357383e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -263,10 +263,9 @@ static int __die(const char *str, struct pt_regs *regs, long err)
 {
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+	printk("%s PAGE_SIZE=%luK%s %s%s%s%s %s\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
 	       PAGE_SIZE / 1024, get_mmu_str(),
-	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
 	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
 	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
 	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 0a72a537f879..862b22b2b616 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -36,9 +36,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL)
 	/* RTAS panel debug */
 	udbg_init_rtas_panel();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE)
-	/* RTAS console debug */
-	udbg_init_rtas_console();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 43379365ce1b..219d67bcf747 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -17,7 +17,7 @@
 #include <linux/elf.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
@@ -32,6 +32,8 @@
 #include <asm/vdso_datapage.h>
 #include <asm/setup.h>
 
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
+
 /* The alignment of the vDSO */
 #define VDSO_ALIGNMENT	(1 << 16)
 
@@ -40,24 +42,6 @@ extern char vdso64_start, vdso64_end;
 
 long sys_ni_syscall(void);
 
-/*
- * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
- * Once the early boot kernel code no longer needs to muck around
- * with it, it will become dynamically allocated
- */
-static union {
-	struct vdso_arch_data	data;
-	u8			page[2 * PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_arch_data *vdso_data = &vdso_data_store.data;
-
-enum vvar_pages {
-	VVAR_BASE_PAGE_OFFSET,
-	VVAR_TIME_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
@@ -96,14 +80,6 @@ static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struc
 	mm->context.vdso = NULL;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf);
-
-static struct vm_special_mapping vvar_spec __ro_after_init = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso32_mremap,
@@ -116,73 +92,6 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.close = vdso_close,
 };
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return vvar_page;
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_spec))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_BASE_PAGE_OFFSET:
-		pfn = virt_to_pfn(vdso_data);
-		break;
-	case VVAR_TIME_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = virt_to_pfn(vdso_data->data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = virt_to_pfn(vdso_data->data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -191,7 +100,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 {
 	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
-	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+	unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
@@ -217,9 +126,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	/* Add required alignment. */
 	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
 
-	vma = _install_special_mapping(mm, vdso_base, vvar_size,
-				       VM_READ | VM_MAYREAD | VM_IO |
-				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+	vma = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -299,10 +206,10 @@ static void __init vdso_setup_syscall_map(void)
 
 	for (i = 0; i < NR_syscalls; i++) {
 		if (sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 		if (IS_ENABLED(CONFIG_COMPAT) &&
 		    compat_sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 	}
 }
 
@@ -352,10 +259,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
-	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
-	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
-	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+	vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size;
+	vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size;
+	vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+	vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
 #endif /* CONFIG_PPC64 */
 
 	vdso_setup_syscall_map();
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 0e3ed6fb199f..e8824f933326 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -3,7 +3,7 @@
 # List of files in the vdso, has to be asm only for now
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
 obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index 0085ae464dac..488d3ade11e6 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 #ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r10
+	get_datapage	r10 vdso_u_arch_data
 	mtlr	r12
   .cfi_restore	lr
 #endif
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f0166..d23b2e8e2a34 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr.	r4,r3
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 	mtlr	r12
 #ifdef __powerpc64__
 	addi	r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 #ifndef __powerpc64__
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 #endif
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index 5333848322ca..79c967212444 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -33,9 +33,9 @@
   .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
 	.ifeq	\call_time
-		get_datapage	r5 VDSO_DATA_OFFSET
+		get_datapage	r5 vdso_u_time_data
 	.else
-		get_datapage	r4 VDSO_DATA_OFFSET
+		get_datapage	r4 vdso_u_time_data
 	.endif
 	bl		CFUNC(DOTSYM(\funct))
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
index 1a1b0b6d681a..72a1012b8a20 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash          	: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
index e21b5506cad6..32102a05eaa7 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
index 55a287c9a736..6f5167d81af5 100644
--- a/arch/powerpc/kernel/vdso/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -7,43 +7,43 @@
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_data(vd, clock_id, res);
 }
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime32_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd)
+			       const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_time32_data(vd, clock_id, res);
 }
 #endif
 
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_gettimeofday_data(vd, tv, tz);
 }
 
-__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd)
 {
 	return __cvdso_time_data(vd, time);
 }
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index b4c9decc7a75..de6ee7d35cff 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -1,10 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef CONFIG_PPC64
-#define PROVIDE32(x)	PROVIDE(__unused__##x)
-#else
-#define PROVIDE32(x)	PROVIDE(x)
-#endif
-
 #define BSS_FIRST_SECTIONS *(.bss.prominit)
 #define EMITS_PT_NOTE
 #define RO_EXCEPTION_TABLE_ALIGN	0
@@ -127,7 +121,6 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	_etext = .;
-	PROVIDE32 (etext = .);
 
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
@@ -394,7 +387,6 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	_edata  =  .;
-	PROVIDE32 (edata = .);
 
 /*
  * And finally the bss
@@ -404,7 +396,6 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	_end = . ;
-	PROVIDE32 (end = .);
 
 	DWARF_DEBUG
 	ELF_DETAILS
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 8c464a5d8246..2429cb1c7baa 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -495,8 +495,7 @@ static void start_watchdog(void *arg)
 
 	*this_cpu_ptr(&wd_timer_tb) = get_tb();
 
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer->function = watchdog_timer_fn;
+	hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
 		      HRTIMER_MODE_REL_PINNED);
 }
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 58a930a47422..00e9c267b912 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -58,38 +58,20 @@ void machine_kexec(struct kimage *image)
 }
 
 #ifdef CONFIG_CRASH_RESERVE
-void __init reserve_crashkernel(void)
-{
-	unsigned long long crash_size, crash_base, total_mem_sz;
-	int ret;
 
-	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
-	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, total_mem_sz,
-			&crash_size, &crash_base, NULL, NULL);
-	if (ret == 0 && crash_size > 0) {
-		crashk_res.start = crash_base;
-		crashk_res.end = crash_base + crash_size - 1;
-	}
-
-	if (crashk_res.end == crashk_res.start) {
-		crashk_res.start = crashk_res.end = 0;
-		return;
-	}
-
-	/* We might have got these values via the command line or the
-	 * device tree, either way sanitise them now. */
-
-	crash_size = resource_size(&crashk_res);
+static unsigned long long __init get_crash_base(unsigned long long crash_base)
+{
 
 #ifndef CONFIG_NONSTATIC_KERNEL
-	if (crashk_res.start != KDUMP_KERNELBASE)
+	if (crash_base != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
-	crashk_res.start = KDUMP_KERNELBASE;
+	return KDUMP_KERNELBASE;
 #else
-	if (!crashk_res.start) {
+	unsigned long long crash_base_align;
+
+	if (!crash_base) {
 #ifdef CONFIG_PPC64
 		/*
 		 * On the LPAR platform place the crash kernel to mid of
@@ -101,53 +83,51 @@ void __init reserve_crashkernel(void)
 		 * kernel starts at 128MB offset on other platforms.
 		 */
 		if (firmware_has_feature(FW_FEATURE_LPAR))
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_512M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_512M);
 		else
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_128M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_128M);
 #else
-		crashk_res.start = KDUMP_KERNELBASE;
+		crash_base = KDUMP_KERNELBASE;
 #endif
 	}
 
-	crash_base = PAGE_ALIGN(crashk_res.start);
-	if (crash_base != crashk_res.start) {
-		printk("Crash kernel base must be aligned to 0x%lx\n",
-				PAGE_SIZE);
-		crashk_res.start = crash_base;
-	}
+	crash_base_align = PAGE_ALIGN(crash_base);
+	if (crash_base != crash_base_align)
+		pr_warn("Crash kernel base must be aligned to 0x%lx\n", PAGE_SIZE);
 
+	return crash_base_align;
 #endif
-	crash_size = PAGE_ALIGN(crash_size);
-	crashk_res.end = crashk_res.start + crash_size - 1;
+}
 
-	/* The crash region must not overlap the current kernel */
-	if (overlaps_crashkernel(__pa(_stext), _end - _stext)) {
-		printk(KERN_WARNING
-			"Crash kernel can not overlap current kernel\n");
-		crashk_res.start = crashk_res.end = 0;
+void __init arch_reserve_crashkernel(void)
+{
+	unsigned long long crash_size, crash_base, crash_end;
+	unsigned long long kernel_start, kernel_size;
+	unsigned long long total_mem_sz;
+	int ret;
+
+	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
+
+	/* use common parsing */
+	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
+				&crash_base, NULL, NULL);
+
+	if (ret)
 		return;
-	}
 
-	/* Crash kernel trumps memory limit */
-	if (memory_limit && memory_limit <= crashk_res.end) {
-		memory_limit = crashk_res.end + 1;
-		total_mem_sz = memory_limit;
-		printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
-		       memory_limit);
-	}
+	crash_base = get_crash_base(crash_base);
+	crash_end = crash_base + crash_size - 1;
 
-	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
-			"for crashkernel (System RAM: %ldMB)\n",
-			(unsigned long)(crash_size >> 20),
-			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(total_mem_sz >> 20));
+	kernel_start = __pa(_stext);
+	kernel_size = _end - _stext;
 
-	if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
-	    memblock_reserve(crashk_res.start, crash_size)) {
-		pr_err("Failed to reserve memory for crashkernel!\n");
-		crashk_res.start = crashk_res.end = 0;
+	/* The crash region must not overlap the current kernel */
+	if ((kernel_start + kernel_size > crash_base) && (kernel_start <= crash_end)) {
+		pr_warn("Crash kernel can not overlap current kernel\n");
 		return;
 	}
+
+	reserve_crashkernel_generic(crash_size, crash_base, 0, false);
 }
 
 int __init overlaps_crashkernel(unsigned long start, unsigned long size)
diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index 9ac3266e4965..a325c1c02f96 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -359,7 +359,10 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	if (TRAP(regs) == INTERRUPT_SYSTEM_RESET)
 		is_via_system_reset = 1;
 
-	crash_smp_send_stop();
+	if (IS_ENABLED(CONFIG_SMP))
+		crash_smp_send_stop();
+	else
+		crash_kexec_prepare();
 
 	crash_save_cpu(regs, crashing_cpu);
 
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index dc65c1391157..e7ef8b2a2554 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -49,201 +49,18 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL
 };
 
-/**
- * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
- *                              in the memory regions between buf_min & buf_max
- *                              for the buffer. If found, sets kbuf->mem.
- * @kbuf:                       Buffer contents and memory parameters.
- * @buf_min:                    Minimum address for the buffer.
- * @buf_max:                    Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
-				      u64 buf_min, u64 buf_max)
-{
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range_rev(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (start > buf_max)
-			continue;
-
-		/* Memory hole not found */
-		if (end < buf_min)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1,
-					       kbuf->buf_align);
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
- *                                  suitable buffer with top down approach.
- * @kbuf:                           Buffer contents and memory parameters.
- * @buf_min:                        Minimum address for the buffer.
- * @buf_max:                        Maximum address for the buffer.
- * @emem:                           Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
-					  u64 buf_min, u64 buf_max,
-					  const struct crash_mem *emem)
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end)
 {
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmax = buf_max;
-	for (i = (emem->nr_ranges - 1); i >= 0; i--) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (start > tmax)
-			continue;
-
-		if (end < tmax) {
-			tmin = (end < buf_min ? buf_min : end + 1);
-			ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
-
-		tmax = start - 1;
-
-		if (tmax < buf_min) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
-
-	if (!ret) {
-		tmin = buf_min;
-		ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-	}
-	return ret;
-}
-
-/**
- * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole
- *                               in the memory regions between buf_min & buf_max
- *                               for the buffer. If found, sets kbuf->mem.
- * @kbuf:                        Buffer contents and memory parameters.
- * @buf_min:                     Minimum address for the buffer.
- * @buf_max:                     Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
-				       u64 buf_min, u64 buf_max)
-{
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (end < buf_min)
-			continue;
-
-		/* Memory hole not found */
-		if (start > buf_max)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = start;
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
- *                                   suitable buffer with bottom up approach.
- * @kbuf:                            Buffer contents and memory parameters.
- * @buf_min:                         Minimum address for the buffer.
- * @buf_max:                         Maximum address for the buffer.
- * @emem:                            Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
-					   u64 buf_min, u64 buf_max,
-					   const struct crash_mem *emem)
-{
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmin = buf_min;
-	for (i = 0; i < emem->nr_ranges; i++) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (end < tmin)
-			continue;
-
-		if (start > tmin) {
-			tmax = (start > buf_max ? buf_max : start - 1);
-			ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
-
-		tmin = end + 1;
+	struct crash_mem *emem;
+	int i;
 
-		if (tmin > buf_max) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
+	emem = image->arch.exclude_ranges;
+	for (i = 0; i < emem->nr_ranges; i++)
+		if (start < emem->ranges[i].end && end > emem->ranges[i].start)
+			return 1;
 
-	if (!ret) {
-		tmax = buf_max;
-		ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-	}
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_CRASH_DUMP
@@ -1005,64 +822,6 @@ out:
 }
 
 /**
- * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal,
- *                              tce-table, reserved-ranges & such (exclude
- *                              memory ranges) as they can't be used for kexec
- *                              segment buffer. Sets kbuf->mem when a suitable
- *                              memory hole is found.
- * @kbuf:                       Buffer contents and memory parameters.
- *
- * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align.
- *
- * Returns 0 on success, negative errno on error.
- */
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
-{
-	struct crash_mem **emem;
-	u64 buf_min, buf_max;
-	int ret;
-
-	/* Look up the exclude ranges list while locating the memory hole */
-	emem = &(kbuf->image->arch.exclude_ranges);
-	if (!(*emem) || ((*emem)->nr_ranges == 0)) {
-		pr_warn("No exclude range list. Using the default locate mem hole method\n");
-		return kexec_locate_mem_hole(kbuf);
-	}
-
-	buf_min = kbuf->buf_min;
-	buf_max = kbuf->buf_max;
-	/* Segments for kdump kernel should be within crashkernel region */
-	if (IS_ENABLED(CONFIG_CRASH_DUMP) && kbuf->image->type == KEXEC_TYPE_CRASH) {
-		buf_min = (buf_min < crashk_res.start ?
-			   crashk_res.start : buf_min);
-		buf_max = (buf_max > crashk_res.end ?
-			   crashk_res.end : buf_max);
-	}
-
-	if (buf_min > buf_max) {
-		pr_err("Invalid buffer min and/or max values\n");
-		return -EINVAL;
-	}
-
-	if (kbuf->top_down)
-		ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
-						     *emem);
-	else
-		ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
-						      *emem);
-
-	/* Add the buffer allocated to the exclude list for the next lookup */
-	if (!ret) {
-		add_mem_range(emem, kbuf->mem, kbuf->memsz);
-		sort_memory_ranges(*emem, true);
-	} else {
-		pr_err("Failed to locate memory buffer of size %lu\n",
-		       kbuf->memsz);
-	}
-	return ret;
-}
-
-/**
  * arch_kexec_kernel_image_probe - Does additional handling needed to setup
  *                                 kexec segments.
  * @image:                         kexec image being loaded.
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index 104c9911f406..dd86e338307d 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -348,16 +348,13 @@ write_utlb:
 	rlwinm	r10, r24, 0, 22, 27
 
 	cmpwi	r10, PPC47x_TLB0_4K
-	bne	0f
 	li	r10, 0x1000			/* r10 = 4k */
-	ANNOTATE_INTRA_FUNCTION_CALL
-	bl	1f
+	beq	0f
 
-0:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bcl	20,31,$+4
+0:	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index dbfdc126bf14..2f2702c867f7 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -83,6 +83,7 @@ config KVM_BOOK3S_64_HV
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
 	select KVM_GENERIC_MMU_NOTIFIER
+	select KVM_BOOK3S_HV_PMU
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -171,6 +172,18 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
 	  those buggy L1s which saves the L2 state, at the cost of performance
 	  in all nested-capable guest entry/exit.
 
+config KVM_BOOK3S_HV_PMU
+	tristate "Hypervisor Perf events for KVM Book3s-HV"
+	depends on KVM_BOOK3S_64_HV
+	help
+	  Enable Book3s-HV Hypervisor Perf events PMU named 'kvm-hv'. These
+	  Perf events give an overview of hypervisor performance overall
+	  instead of a specific guests. Currently the PMU reports
+	  L0-Hypervisor stats on a kvm-hv enabled PSeries LPAR like:
+	  * Total/Used Guest-Heap
+	  * Total/Used Guest Page-table Memory
+	  * Total amount of Guest Page-table Memory reclaimed
+
 config KVM_BOOKE_HV
 	bool
 
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 5b7212edbb13..c7e4b62642ea 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -125,8 +125,6 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr,
 	return (u32*)pteg;
 }
 
-extern char etext[];
-
 int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 			bool iswrite)
 {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 86bff159c51e..7667563fb9ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -6041,7 +6041,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * the underlying calls, which will EOI the interrupt in real
 	 * mode, need an HW IRQ number mapped in the XICS IRQ domain.
 	 */
-	host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+	host_data = irq_domain_get_irq_data(irq_get_default_domain(), host_irq);
 	irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data);
 
 	if (i == pimap->n_mapped)
@@ -6541,10 +6541,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
 	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
 	.hcall_implemented = kvmppc_hcall_impl_hv,
-#ifdef CONFIG_KVM_XICS
-	.irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv,
-	.irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv,
-#endif
 	.configure_mmu = kvmhv_configure_mmu,
 	.get_rmmu_info = kvmhv_get_rmmu_info,
 	.set_smt_mode = kvmhv_set_smt_mode,
@@ -6662,6 +6658,22 @@ static int kvmppc_book3s_init_hv(void)
 		return r;
 	}
 
+#if defined(CONFIG_KVM_XICS)
+	/*
+	 * IRQ bypass is supported only for interrupts whose EOI operations are
+	 * handled via OPAL calls. Therefore, register IRQ bypass handlers
+	 * exclusively for PowerNV KVM when booted with 'xive=off', indicating
+	 * the use of the emulated XICS interrupt controller.
+	 */
+	if (!kvmhv_on_pseries()) {
+		pr_info("KVM-HV: Enabling IRQ bypass\n");
+		kvm_ops_hv.irq_bypass_add_producer =
+			kvmppc_irq_bypass_add_producer_hv;
+		kvm_ops_hv.irq_bypass_del_producer =
+			kvmppc_irq_bypass_del_producer_hv;
+	}
+#endif
+
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
 
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index e5c7ce1fb761..87691cf86cae 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -123,6 +123,12 @@ static size_t gs_msg_ops_vcpu_get_size(struct kvmppc_gs_msg *gsm)
 		case KVMPPC_GSID_PROCESS_TABLE:
 		case KVMPPC_GSID_RUN_INPUT:
 		case KVMPPC_GSID_RUN_OUTPUT:
+		  /* Host wide counters */
+		case KVMPPC_GSID_L0_GUEST_HEAP:
+		case KVMPPC_GSID_L0_GUEST_HEAP_MAX:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM:
 			break;
 		default:
 			size += kvmppc_gse_total_size(kvmppc_gsid_size(iden));
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ea7ad200b330..83f7504349d2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1524,14 +1524,12 @@ kvm_flush_link_stack:
 
 	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
 	.rept 32
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 
 	/* And on Power9 it's up to 64. */
 BEGIN_FTR_SECTION
 	.rept 32
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 1362c672387e..1302b5ac5672 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1555,7 +1555,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	struct kvmppc_xive_src_block *sb;
 	struct kvmppc_xive_irq_state *state;
 	struct irq_data *host_data =
-		irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+		irq_domain_get_irq_data(irq_get_default_domain(), host_irq);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
 	u16 idx;
 	u8 prio;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6a5be025a8af..791d1942a058 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -572,7 +572,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 
 /*
  * Return the number of jiffies until the next timeout.  If the timeout is
- * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA
+ * longer than the TIMER_NEXT_MAX_DELTA, then return TIMER_NEXT_MAX_DELTA
  * because the larger value can break the timer APIs.
  */
 static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
@@ -598,7 +598,7 @@ static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
 	if (do_div(nr_jiffies, tb_ticks_per_jiffy))
 		nr_jiffies++;
 
-	return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA);
+	return min_t(unsigned long long, nr_jiffies, TIMER_NEXT_MAX_DELTA);
 }
 
 static void arm_next_watchdog(struct kvm_vcpu *vcpu)
@@ -616,13 +616,13 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu)
 	spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
 	nr_jiffies = watchdog_next_timeout(vcpu);
 	/*
-	 * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA
+	 * If the number of jiffies of watchdog timer >= TIMER_NEXT_MAX_DELTA
 	 * then do not run the watchdog timer as this can break timer APIs.
 	 */
-	if (nr_jiffies < NEXT_TIMER_MAX_DELTA)
+	if (nr_jiffies < TIMER_NEXT_MAX_DELTA)
 		mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies);
 	else
-		del_timer(&vcpu->arch.wdt_timer);
+		timer_delete(&vcpu->arch.wdt_timer);
 	spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
 }
 
@@ -1441,7 +1441,7 @@ int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	del_timer_sync(&vcpu->arch.wdt_timer);
+	timer_delete_sync(&vcpu->arch.wdt_timer);
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
diff --git a/arch/powerpc/kvm/guest-state-buffer.c b/arch/powerpc/kvm/guest-state-buffer.c
index b80dbc58621f..871cf60ddeb6 100644
--- a/arch/powerpc/kvm/guest-state-buffer.c
+++ b/arch/powerpc/kvm/guest-state-buffer.c
@@ -92,6 +92,10 @@ static int kvmppc_gsid_class(u16 iden)
 	    (iden <= KVMPPC_GSE_GUESTWIDE_END))
 		return KVMPPC_GS_CLASS_GUESTWIDE;
 
+	if ((iden >= KVMPPC_GSE_HOSTWIDE_START) &&
+	    (iden <= KVMPPC_GSE_HOSTWIDE_END))
+		return KVMPPC_GS_CLASS_HOSTWIDE;
+
 	if ((iden >= KVMPPC_GSE_META_START) && (iden <= KVMPPC_GSE_META_END))
 		return KVMPPC_GS_CLASS_META;
 
@@ -118,6 +122,21 @@ static int kvmppc_gsid_type(u16 iden)
 	int type = -1;
 
 	switch (kvmppc_gsid_class(iden)) {
+	case KVMPPC_GS_CLASS_HOSTWIDE:
+		switch (iden) {
+		case KVMPPC_GSID_L0_GUEST_HEAP:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_HEAP_MAX:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM:
+			type = KVMPPC_GSE_BE64;
+			break;
+		}
+		break;
 	case KVMPPC_GS_CLASS_GUESTWIDE:
 		switch (iden) {
 		case KVMPPC_GSID_HOST_STATE_SIZE:
@@ -187,6 +206,9 @@ unsigned long kvmppc_gsid_flags(u16 iden)
 	case KVMPPC_GS_CLASS_GUESTWIDE:
 		flags = KVMPPC_GS_FLAGS_WIDE;
 		break;
+	case KVMPPC_GS_CLASS_HOSTWIDE:
+		flags = KVMPPC_GS_FLAGS_HOST_WIDE;
+		break;
 	case KVMPPC_GS_CLASS_META:
 	case KVMPPC_GS_CLASS_DWORD_REG:
 	case KVMPPC_GS_CLASS_WORD_REG:
@@ -310,6 +332,13 @@ static inline int kvmppc_gse_flatten_iden(u16 iden)
 
 	bit += KVMPPC_GSE_GUESTWIDE_COUNT;
 
+	if (class == KVMPPC_GS_CLASS_HOSTWIDE) {
+		bit += iden - KVMPPC_GSE_HOSTWIDE_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_HOSTWIDE_COUNT;
+
 	if (class == KVMPPC_GS_CLASS_META) {
 		bit += iden - KVMPPC_GSE_META_START;
 		return bit;
@@ -356,6 +385,12 @@ static inline u16 kvmppc_gse_unflatten_iden(int bit)
 	}
 	bit -= KVMPPC_GSE_GUESTWIDE_COUNT;
 
+	if (bit < KVMPPC_GSE_HOSTWIDE_COUNT) {
+		iden = KVMPPC_GSE_HOSTWIDE_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_HOSTWIDE_COUNT;
+
 	if (bit < KVMPPC_GSE_META_COUNT) {
 		iden = KVMPPC_GSE_META_START + bit;
 		return iden;
@@ -588,6 +623,8 @@ int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags)
 
 	if (flags & KVMPPC_GS_FLAGS_WIDE)
 		hflags |= H_GUEST_FLAGS_WIDE;
+	if (flags & KVMPPC_GS_FLAGS_HOST_WIDE)
+		hflags |= H_GUEST_FLAGS_HOST_WIDE;
 
 	rc = plpar_guest_set_state(hflags, gsb->guest_id, gsb->vcpu_id,
 				   __pa(gsb->hdr), gsb->capacity, &i);
@@ -613,6 +650,8 @@ int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags)
 
 	if (flags & KVMPPC_GS_FLAGS_WIDE)
 		hflags |= H_GUEST_FLAGS_WIDE;
+	if (flags & KVMPPC_GS_FLAGS_HOST_WIDE)
+		hflags |= H_GUEST_FLAGS_HOST_WIDE;
 
 	rc = plpar_guest_get_state(hflags, gsb->guest_id, gsb->vcpu_id,
 				   __pa(gsb->hdr), gsb->capacity, &i);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index ce1d91eed231..153587741864 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -550,12 +550,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+		fallthrough;
 	case KVM_CAP_SPAPR_TCE_64:
-		r = 1;
-		break;
 	case KVM_CAP_SPAPR_TCE_VFIO:
-		r = !!cpu_has_feature(CPU_FTR_HVMODE);
-		break;
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
@@ -766,8 +763,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int err;
 
-	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	hrtimer_setup(&vcpu->arch.dec_timer, kvmppc_decrementer_wakeup, CLOCK_REALTIME,
+		      HRTIMER_MODE_ABS);
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c
index bfd225329a18..5ccca306997a 100644
--- a/arch/powerpc/kvm/test-guest-state-buffer.c
+++ b/arch/powerpc/kvm/test-guest-state-buffer.c
@@ -5,6 +5,7 @@
 #include <kunit/test.h>
 
 #include <asm/guest-state-buffer.h>
+#include <asm/kvm_ppc.h>
 
 static void test_creating_buffer(struct kunit *test)
 {
@@ -141,6 +142,16 @@ static void test_gs_bitmap(struct kunit *test)
 		i++;
 	}
 
+	for (u16 iden = KVMPPC_GSID_L0_GUEST_HEAP;
+	     iden <= KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
 	for (u16 iden = KVMPPC_GSID_RUN_INPUT; iden <= KVMPPC_GSID_VPA;
 	     iden++) {
 		kvmppc_gsbm_set(&gsbm, iden);
@@ -309,12 +320,215 @@ static void test_gs_msg(struct kunit *test)
 	kvmppc_gsm_free(gsm);
 }
 
+/* Test data struct for hostwide/L0 counters */
+struct kvmppc_gs_msg_test_hostwide_data {
+	u64 guest_heap;
+	u64 guest_heap_max;
+	u64 guest_pgtable_size;
+	u64 guest_pgtable_size_max;
+	u64 guest_pgtable_reclaim;
+};
+
+static size_t test_hostwide_get_size(struct kvmppc_gs_msg *gsm)
+
+{
+	size_t size = 0;
+	u16 ids[] = {
+		KVMPPC_GSID_L0_GUEST_HEAP,
+		KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+static int test_hostwide_fill_info(struct kvmppc_gs_buff *gsb,
+				   struct kvmppc_gs_msg *gsm)
+{
+	struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data;
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP,
+				   data->guest_heap);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+				   data->guest_heap_max);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+				   data->guest_pgtable_size);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+				   data->guest_pgtable_size_max);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM,
+				   data->guest_pgtable_reclaim);
+
+	return 0;
+}
+
+static int test_hostwide_refresh_info(struct kvmppc_gs_msg *gsm,
+				      struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	if (gse)
+		data->guest_heap = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	if (gse)
+		data->guest_heap_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	if (gse)
+		data->guest_pgtable_size = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	if (gse)
+		data->guest_pgtable_size_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	if (gse)
+		data->guest_pgtable_reclaim = kvmppc_gse_get_u64(gse);
+
+	return 0;
+}
+
+static struct kvmppc_gs_msg_ops gs_msg_test_hostwide_ops = {
+	.get_size = test_hostwide_get_size,
+	.fill_info = test_hostwide_fill_info,
+	.refresh_info = test_hostwide_refresh_info,
+};
+
+static void test_gs_hostwide_msg(struct kunit *test)
+{
+	struct kvmppc_gs_msg_test_hostwide_data test_data = {
+		.guest_heap = 0xdeadbeef,
+		.guest_heap_max = ~0ULL,
+		.guest_pgtable_size = 0xff,
+		.guest_pgtable_size_max = 0xffffff,
+		.guest_pgtable_reclaim = 0xdeadbeef,
+	};
+	struct kvmppc_gs_msg *gsm;
+	struct kvmppc_gs_buff *gsb;
+
+	gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND,
+			     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm);
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	kvmppc_gsm_fill_info(gsm, gsb);
+
+	memset(&test_data, 0, sizeof(test_data));
+
+	kvmppc_gsm_refresh_info(gsm, gsb);
+	KUNIT_EXPECT_EQ(test, test_data.guest_heap, 0xdeadbeef);
+	KUNIT_EXPECT_EQ(test, test_data.guest_heap_max, ~0ULL);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size, 0xff);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size_max, 0xffffff);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_reclaim, 0xdeadbeef);
+
+	kvmppc_gsm_free(gsm);
+}
+
+/* Test if the H_GUEST_GET_STATE for hostwide counters works */
+static void test_gs_hostwide_counters(struct kunit *test)
+{
+	struct kvmppc_gs_msg_test_hostwide_data test_data;
+	struct kvmppc_gs_parser gsp = { 0 };
+
+	struct kvmppc_gs_msg *gsm;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	if (!kvmhv_on_pseries())
+		kunit_skip(test, "This test need a kmv-hv guest");
+
+	gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND,
+			     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm);
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	kvmppc_gsm_fill_info(gsm, gsb);
+
+	/* With HOST_WIDE flags guestid and vcpuid will be ignored */
+	rc = kvmppc_gsb_recv(gsb, KVMPPC_GS_FLAGS_HOST_WIDE);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	/* Parse the guest state buffer is successful */
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	/* Parse the GSB and get the counters */
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter missing");
+	kunit_info(test, "Guest Heap Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter max missing");
+	kunit_info(test, "Guest Heap Size Max=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size missing");
+	kunit_info(test, "Guest Page-table Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size-max missing");
+	kunit_info(test, "Guest Page-table Size Max=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table reclaim size missing");
+	kunit_info(test, "Guest Page-table Reclaim Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	kvmppc_gsm_free(gsm);
+	kvmppc_gsb_free(gsb);
+}
+
 static struct kunit_case guest_state_buffer_testcases[] = {
 	KUNIT_CASE(test_creating_buffer),
 	KUNIT_CASE(test_adding_element),
 	KUNIT_CASE(test_gs_bitmap),
 	KUNIT_CASE(test_gs_parsing),
 	KUNIT_CASE(test_gs_msg),
+	KUNIT_CASE(test_gs_hostwide_msg),
+	KUNIT_CASE(test_gs_hostwide_counters),
 	{}
 };
 
diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index 45817ab82bb4..14b0e23f601f 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -38,11 +38,7 @@ static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {}
 static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
 {
 	/* type has to be known at build time for optimization */
-
-	/* The BUILD_BUG_ON below breaks in funny ways, commented out
-	 * for now ... -BenH
 	BUILD_BUG_ON(!__builtin_constant_p(type));
-	*/
 	switch (type) {
 	case EXT_INTR_EXITS:
 		vcpu->stat.ext_intr_exits++;
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index dd8a4b52a0cc..481f968e42c7 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,6 +3,8 @@
 # Makefile for ppc-specific library files..
 #
 
+obj-y += crypto/
+
 CFLAGS_code-patching.o += -fno-stack-protector
 CFLAGS_feature-fixups.o += -fno-stack-protector
 
@@ -79,9 +81,9 @@ CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
 CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include)
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o
-crc32-powerpc-y := crc32-glue.o crc32c-vpmsum_asm.o
+crc32-powerpc-y := crc32.o crc32c-vpmsum_asm.o
 
 obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-powerpc.o
-crc-t10dif-powerpc-y := crc-t10dif-glue.o crct10dif-vpmsum_asm.o
+crc-t10dif-powerpc-y := crc-t10dif.o crct10dif-vpmsum_asm.o
 
 obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/crc-t10dif-glue.c b/arch/powerpc/lib/crc-t10dif.c
index 730850dbc51d..be23ded3a9df 100644
--- a/arch/powerpc/lib/crc-t10dif-glue.c
+++ b/arch/powerpc/lib/crc-t10dif.c
@@ -6,22 +6,22 @@
  * [based on crc32c-vpmsum_glue.c]
  */
 
-#include <linux/crc-t10dif.h>
+#include <asm/switch_to.h>
 #include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
 #include <linux/cpufeature.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
+#include <linux/crc-t10dif.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/uaccess.h>
 
 #define VMX_ALIGN		16
 #define VMX_ALIGN_MASK		(VMX_ALIGN-1)
 
 #define VECTOR_BREAKPOINT	64
 
-static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
 
 u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
 
@@ -71,19 +71,13 @@ static int __init crc_t10dif_powerpc_init(void)
 		static_branch_enable(&have_vec_crypto);
 	return 0;
 }
-arch_initcall(crc_t10dif_powerpc_init);
+subsys_initcall(crc_t10dif_powerpc_init);
 
 static void __exit crc_t10dif_powerpc_exit(void)
 {
 }
 module_exit(crc_t10dif_powerpc_exit);
 
-bool crc_t10dif_is_optimized(void)
-{
-	return static_key_enabled(&have_vec_crypto);
-}
-EXPORT_SYMBOL(crc_t10dif_is_optimized);
-
 MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
 MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
 MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/lib/crc32-vpmsum_core.S b/arch/powerpc/lib/crc-vpmsum-template.S
index b0f87f595b26..b0f87f595b26 100644
--- a/arch/powerpc/lib/crc32-vpmsum_core.S
+++ b/arch/powerpc/lib/crc-vpmsum-template.S
diff --git a/arch/powerpc/lib/crc32-glue.c b/arch/powerpc/lib/crc32.c
index 79cc954f499f..0d9befb6e7b8 100644
--- a/arch/powerpc/lib/crc32-glue.c
+++ b/arch/powerpc/lib/crc32.c
@@ -1,19 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/crc32.h>
+#include <asm/switch_to.h>
 #include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
 #include <linux/cpufeature.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
+#include <linux/crc32.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/uaccess.h>
 
 #define VMX_ALIGN		16
 #define VMX_ALIGN_MASK		(VMX_ALIGN-1)
 
 #define VECTOR_BREAKPOINT	512
 
-static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
 
 u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len);
 
@@ -23,18 +24,18 @@ u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
-u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	unsigned int prealign;
 	unsigned int tail;
 
 	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
 	    !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
-		return crc32c_le_base(crc, p, len);
+		return crc32c_base(crc, p, len);
 
 	if ((unsigned long)p & VMX_ALIGN_MASK) {
 		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
-		crc = crc32c_le_base(crc, p, prealign);
+		crc = crc32c_base(crc, p, prealign);
 		len -= prealign;
 		p += prealign;
 	}
@@ -52,12 +53,12 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 	tail = len & VMX_ALIGN_MASK;
 	if (tail) {
 		p += len & ~VMX_ALIGN_MASK;
-		crc = crc32c_le_base(crc, p, tail);
+		crc = crc32c_base(crc, p, tail);
 	}
 
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -72,7 +73,7 @@ static int __init crc32_powerpc_init(void)
 		static_branch_enable(&have_vec_crypto);
 	return 0;
 }
-arch_initcall(crc32_powerpc_init);
+subsys_initcall(crc32_powerpc_init);
 
 static void __exit crc32_powerpc_exit(void)
 {
diff --git a/arch/powerpc/lib/crc32c-vpmsum_asm.S b/arch/powerpc/lib/crc32c-vpmsum_asm.S
index bf442004ea1f..1b35c55cce0a 100644
--- a/arch/powerpc/lib/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/lib/crc32c-vpmsum_asm.S
@@ -839,4 +839,4 @@
 
 #define CRC_FUNCTION_NAME __crc32c_vpmsum
 #define REFLECT
-#include "crc32-vpmsum_core.S"
+#include "crc-vpmsum-template.S"
diff --git a/arch/powerpc/lib/crct10dif-vpmsum_asm.S b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
index f0b93a0fe168..47a6266d89a8 100644
--- a/arch/powerpc/lib/crct10dif-vpmsum_asm.S
+++ b/arch/powerpc/lib/crct10dif-vpmsum_asm.S
@@ -842,4 +842,4 @@
 	.octa 0x0000000000000000000000018bb70000
 
 #define CRC_FUNCTION_NAME __crct10dif_vpmsum
-#include "crc32-vpmsum_core.S"
+#include "crc-vpmsum-template.S"
diff --git a/arch/powerpc/lib/crypto/Kconfig b/arch/powerpc/lib/crypto/Kconfig
new file mode 100644
index 000000000000..3f9e1bbd9905
--- /dev/null
+++ b/arch/powerpc/lib/crypto/Kconfig
@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA20_P10
+	tristate
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_P10
+	tristate
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
+	depends on BROKEN # Needs to be fixed to work in softirq context
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+	select CRYPTO_LIB_POLY1305_GENERIC
+
+config CRYPTO_SHA256_PPC_SPE
+	tristate
+	depends on SPE
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
diff --git a/arch/powerpc/lib/crypto/Makefile b/arch/powerpc/lib/crypto/Makefile
new file mode 100644
index 000000000000..27f231f8e334
--- /dev/null
+++ b/arch/powerpc/lib/crypto/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
+chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
+poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
+
+obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
+sha256-ppc-spe-y := sha256.o sha256-spe-asm.o
diff --git a/arch/powerpc/lib/crypto/chacha-p10-glue.c b/arch/powerpc/lib/crypto/chacha-p10-glue.c
new file mode 100644
index 000000000000..fcd23c6f1590
--- /dev/null
+++ b/arch/powerpc/lib/crypto/chacha-p10-glue.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * ChaCha stream cipher (P10 accelerated)
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/sizes.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+asmlinkage void chacha_p10le_8x(const struct chacha_state *state, u8 *dst,
+				const u8 *src, unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+static void chacha_p10_do_8x(struct chacha_state *state, u8 *dst, const u8 *src,
+			     unsigned int bytes, int nrounds)
+{
+	unsigned int l = bytes & ~0x0FF;
+
+	if (l > 0) {
+		chacha_p10le_8x(state, dst, src, l, nrounds);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += l / CHACHA_BLOCK_SIZE;
+	}
+
+	if (bytes > 0)
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	hchacha_block_generic(state, out, nrounds);
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		vsx_begin();
+		chacha_p10_do_8x(state, dst, src, todo, nrounds);
+		vsx_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_p10);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_p10_init(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+	return 0;
+}
+subsys_initcall(chacha_p10_init);
+
+static void __exit chacha_p10_exit(void)
+{
+}
+module_exit(chacha_p10_exit);
+
+MODULE_DESCRIPTION("ChaCha stream cipher (P10 accelerated)");
+MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/powerpc/crypto/chacha-p10le-8x.S b/arch/powerpc/lib/crypto/chacha-p10le-8x.S
index 17bedb66b822..b29562bd5d40 100644
--- a/arch/powerpc/crypto/chacha-p10le-8x.S
+++ b/arch/powerpc/lib/crypto/chacha-p10le-8x.S
@@ -7,9 +7,6 @@
 #===================================================================================
 # Written by Danny Tsen <dtsen@us.ibm.com>
 #
-# chacha_p10le_8x(u32 *state, byte *dst, const byte *src,
-#				 size_t len, int nrounds);
-#
 # do rounds,  8 quarter rounds
 # 1.  a += b; d ^= a; d <<<= 16;
 # 2.  c += d; b ^= c; b <<<= 12;
@@ -575,7 +572,8 @@
 .endm
 
 #
-# chacha20_p10le_8x(u32 *state, byte *dst, const byte *src, size_t len, int nrounds);
+# void chacha_p10le_8x(const struct chacha_state *state, u8 *dst, const u8 *src,
+#		       unsigned int len, int nrounds);
 #
 SYM_FUNC_START(chacha_p10le_8x)
 .align 5
diff --git a/arch/powerpc/lib/crypto/poly1305-p10-glue.c b/arch/powerpc/lib/crypto/poly1305-p10-glue.c
new file mode 100644
index 000000000000..3f1664a724b6
--- /dev/null
+++ b/arch/powerpc/lib/crypto/poly1305-p10-glue.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Poly1305 authenticator algorithm, RFC7539.
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+#include <asm/switch_to.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_p10le_4blocks(struct poly1305_block_state *state, const u8 *m, u32 mlen);
+asmlinkage void poly1305_64s(struct poly1305_block_state *state, const u8 *m, u32 mlen, int highbit);
+asmlinkage void poly1305_emit_64(const struct poly1305_state *state, const u32 nonce[4], u8 digest[POLY1305_DIGEST_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+void poly1305_block_init_arch(struct poly1305_block_state *dctx,
+			      const u8 raw_key[POLY1305_BLOCK_SIZE])
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_block_init_generic(dctx, raw_key);
+
+	dctx->h = (struct poly1305_state){};
+	dctx->core_r.key.r64[0] = get_unaligned_le64(raw_key + 0);
+	dctx->core_r.key.r64[1] = get_unaligned_le64(raw_key + 8);
+}
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
+			  unsigned int len, u32 padbit)
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_blocks_generic(state, src, len, padbit);
+	vsx_begin();
+	if (len >= POLY1305_BLOCK_SIZE * 4) {
+		poly1305_p10le_4blocks(state, src, len);
+		src += len - (len % (POLY1305_BLOCK_SIZE * 4));
+		len %= POLY1305_BLOCK_SIZE * 4;
+	}
+	while (len >= POLY1305_BLOCK_SIZE) {
+		poly1305_64s(state, src, POLY1305_BLOCK_SIZE, padbit);
+		len -= POLY1305_BLOCK_SIZE;
+		src += POLY1305_BLOCK_SIZE;
+	}
+	vsx_end();
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+void poly1305_emit_arch(const struct poly1305_state *state,
+			u8 digest[POLY1305_DIGEST_SIZE],
+			const u32 nonce[4])
+{
+	if (!static_key_enabled(&have_p10))
+		return poly1305_emit_generic(state, digest, nonce);
+	poly1305_emit_64(state, nonce, digest);
+}
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_p10);
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init poly1305_p10_init(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+	return 0;
+}
+subsys_initcall(poly1305_p10_init);
+
+static void __exit poly1305_p10_exit(void)
+{
+}
+module_exit(poly1305_p10_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
+MODULE_DESCRIPTION("Optimized Poly1305 for P10");
diff --git a/arch/powerpc/crypto/poly1305-p10le_64.S b/arch/powerpc/lib/crypto/poly1305-p10le_64.S
index a3c1987f1ecd..a3c1987f1ecd 100644
--- a/arch/powerpc/crypto/poly1305-p10le_64.S
+++ b/arch/powerpc/lib/crypto/poly1305-p10le_64.S
diff --git a/arch/powerpc/crypto/sha256-spe-asm.S b/arch/powerpc/lib/crypto/sha256-spe-asm.S
index cd99d71dae34..cd99d71dae34 100644
--- a/arch/powerpc/crypto/sha256-spe-asm.S
+++ b/arch/powerpc/lib/crypto/sha256-spe-asm.S
diff --git a/arch/powerpc/lib/crypto/sha256.c b/arch/powerpc/lib/crypto/sha256.c
new file mode 100644
index 000000000000..6b0f079587eb
--- /dev/null
+++ b/arch/powerpc/lib/crypto/sha256.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 Secure Hash Algorithm, SPE optimized
+ *
+ * Based on generic implementation. The assembler module takes care
+ * about the SPE registers so it can run from interrupt context.
+ *
+ * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
+ */
+
+#include <asm/switch_to.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+
+/*
+ * MAX_BYTES defines the number of bytes that are allowed to be processed
+ * between preempt_disable() and preempt_enable(). SHA256 takes ~2,000
+ * operations per 64 bytes. e500 cores can issue two arithmetic instructions
+ * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
+ * Thus 1KB of input data will need an estimated maximum of 18,000 cycles.
+ * Headroom for cache misses included. Even with the low end model clocked
+ * at 667 MHz this equals to a critical time window of less than 27us.
+ *
+ */
+#define MAX_BYTES 1024
+
+extern void ppc_spe_sha256_transform(u32 *state, const u8 *src, u32 blocks);
+
+static void spe_begin(void)
+{
+	/* We just start SPE operations and will save SPE registers later. */
+	preempt_disable();
+	enable_kernel_spe();
+}
+
+static void spe_end(void)
+{
+	disable_kernel_spe();
+	/* reenable preemption */
+	preempt_enable();
+}
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	do {
+		/* cut input data into smaller blocks */
+		u32 unit = min_t(size_t, nblocks,
+				 MAX_BYTES / SHA256_BLOCK_SIZE);
+
+		spe_begin();
+		ppc_spe_sha256_transform(state, data, unit);
+		spe_end();
+
+		data += unit * SHA256_BLOCK_SIZE;
+		nblocks -= unit;
+	} while (nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return true;
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 Secure Hash Algorithm, SPE optimized");
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 58ed6bd613a6..54340912398f 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -45,7 +45,7 @@ int exit_vmx_usercopy(void)
 	 * set and we are preemptible. The hack here is to schedule a
 	 * decrementer to fire here and reschedule for us if necessary.
 	 */
-	if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched())
+	if (need_irq_preemption() && need_resched())
 		set_dec(1);
 	return 0;
 }
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 0fe2f085c05a..8c1582b2987d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -15,5 +15,5 @@ obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
-obj-$(CONFIG_PTDUMP_CORE)	+= ptdump/
+obj-$(CONFIG_PTDUMP)		+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 430d1d935a7c..e9e2dd70c060 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -27,8 +27,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/feature-fixups.h>
 
-#include <misc/cxl-base.h>
-
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) udbg_printf(fmt)
 #else
@@ -217,11 +215,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 static inline void tlbie(unsigned long vpn, int psize, int apsize,
 			 int ssize, int local)
 {
-	unsigned int use_local;
+	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
-	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();
-
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
 	if (lock_tlbie && !use_local)
@@ -789,10 +785,6 @@ static void native_flush_hash_range(unsigned long number, int local)
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;
-	unsigned int use_local;
-
-	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
-		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
 
 	local_irq_save(flags);
 
@@ -827,7 +819,8 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (use_local) {
+	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
+	    mmu_psize_defs[psize].tlbiel && local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
 			vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index c8b4fa71d4a7..5158aefe4873 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -56,7 +56,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/copro.h>
+#include <asm/spu.h>
 #include <asm/udbg.h>
 #include <asm/text-patching.h>
 #include <asm/fadump.h>
@@ -1358,18 +1358,6 @@ static void __init htab_initialize(void)
 	} else {
 		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
 
-#ifdef CONFIG_PPC_CELL
-		/*
-		 * Cell may require the hash table down low when using the
-		 * Axon IOMMU in order to fit the dynamic region over it, see
-		 * comments in cell/iommu.c
-		 */
-		if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
-			limit = 0x80000000;
-			pr_info("Hash table forced below 2G for Axon IOMMU\n");
-		}
-#endif /* CONFIG_PPC_CELL */
-
 		table = memblock_phys_alloc_range(htab_size_bytes,
 						  htab_size_bytes,
 						  0, limit);
@@ -1612,7 +1600,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
 		return;
 	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
-	copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
 	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
 
 		copy_mm_to_paca(mm);
@@ -1881,7 +1871,9 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 			       "to 4kB pages because of "
 			       "non-cacheable mapping\n");
 			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-			copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+			spu_flush_all_slbs(mm);
+#endif
 		}
 	}
 
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index ce64abea9e3e..8f7d41ce2ca1 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -10,7 +10,6 @@
 #include <linux/pkeys.h>
 #include <linux/debugfs.h>
 #include <linux/proc_fs.h>
-#include <misc/cxl-base.h>
 
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -587,7 +586,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 /*
  * Does the CPU support tlbie?
  */
-bool tlbie_capable __read_mostly = true;
+bool tlbie_capable __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
 EXPORT_SYMBOL(tlbie_capable);
 
 /*
@@ -595,7 +594,7 @@ EXPORT_SYMBOL(tlbie_capable);
  * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
  * guest address spaces.
  */
-bool tlbie_enabled __read_mostly = true;
+bool tlbie_enabled __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
 
 static int __init setup_disable_tlbie(char *str)
 {
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 311e2112d782..9f764bc42b8c 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -976,7 +976,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 	return 0;
 }
 
-
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
 bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
 	if (radix_enabled())
@@ -984,6 +984,7 @@ bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 
 	return false;
 }
+#endif
 
 int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 				unsigned long addr, unsigned long next)
@@ -1120,6 +1121,19 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 	pmd_t *pmd;
 	pte_t *pte;
 
+	/*
+	 * Make sure we align the start vmemmap addr so that we calculate
+	 * the correct start_pfn in altmap boundary check to decided whether
+	 * we should use altmap or RAM based backing memory allocation. Also
+	 * the address need to be aligned for set_pte operation.
+
+	 * If the start addr is already PMD_SIZE aligned we will try to use
+	 * a pmd mapping. We don't want to be too aggressive here beacause
+	 * that will cause more allocations in RAM. So only if the namespace
+	 * vmemmap start addr is PMD_SIZE aligned we will use PMD mapping.
+	 */
+
+	start = ALIGN_DOWN(start, PAGE_SIZE);
 	for (addr = start; addr < end; addr = next) {
 		next = pmd_addr_end(addr, end);
 
@@ -1145,8 +1159,8 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 			 * in altmap block allocation failures, in which case
 			 * we fallback to RAM for vmemmap allocation.
 			 */
-			if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) ||
-				       altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
+			if (!IS_ALIGNED(addr, PMD_SIZE) || (altmap &&
+			    altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
 				/*
 				 * make sure we don't create altmap mappings
 				 * covering things outside the device.
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index bc9a39821d1c..28bec5bc7879 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -22,7 +22,7 @@
 #include <linux/security.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
-#include <asm/copro.h>
+#include <asm/spu.h>
 #include <asm/hugetlb.h>
 #include <asm/mmu_context.h>
 
@@ -248,7 +248,9 @@ static void slice_convert(struct mm_struct *mm,
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-	copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
 }
 
 /*
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index f49fd873df8d..f5f8692e2c69 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -12,8 +12,6 @@
 #include <linux/export.h>
 #include <asm/reg.h>
 #include <asm/copro.h>
-#include <asm/spu.h>
-#include <misc/cxl-base.h>
 
 /*
  * This ought to be kept in sync with the powerpc specific do_page_fault
@@ -135,13 +133,4 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(copro_calculate_slb);
-
-void copro_flush_all_slbs(struct mm_struct *mm)
-{
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
-	cxl_slbia(mm);
-}
-EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
 #endif
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index c156fe0d53c3..806c74e0d5ab 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/pagemap.h>
 #include <linux/ptrace.h>
@@ -218,7 +219,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 	// Read/write fault blocked by KUAP is bad, it can never succeed.
 	if (bad_kuap_fault(regs, address, is_write)) {
 		pr_crit_ratelimited("Kernel attempted to %s user page (%lx) - exploit attempt? (uid: %d)\n",
-				    is_write ? "write" : "read", address,
+				    str_write_read(is_write), address,
 				    from_kuid(&init_user_ns, current_uid()));
 
 		// Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad
@@ -625,7 +626,7 @@ static void __bad_page_fault(struct pt_regs *regs, int sig)
 	case INTERRUPT_DATA_STORAGE:
 	case INTERRUPT_H_DATA_STORAGE:
 		pr_alert("BUG: %s on %s at 0x%08lx\n", msg,
-			 is_write ? "write" : "read", regs->dar);
+			 str_write_read(is_write), regs->dar);
 		break;
 	case INTERRUPT_DATA_SEGMENT:
 		pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 6b043180220a..d3c1b749dcfc 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -113,6 +113,7 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
 	gpage_freearray[nr_gpages] = 0;
 	list_add(&m->list, &huge_boot_pages[0]);
 	m->hstate = hstate;
+	m->flags = 0;
 	return 1;
 }
 
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index d96bbc001e73..b6f3ae03ca9e 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -41,6 +41,7 @@
 #include <linux/libfdt.h>
 #include <linux/memremap.h>
 #include <linux/memory.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -386,10 +387,13 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 }
 
 #endif
+
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {
 }
+#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 7b0afcabd89f..4b4feba9873b 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -4,7 +4,6 @@
 #include <linux/slab.h>
 #include <linux/mmzone.h>
 #include <linux/vmalloc.h>
-#include <asm/io-workarounds.h>
 
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);
@@ -14,8 +13,6 @@ void __iomem *ioremap(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 EXPORT_SYMBOL(ioremap);
@@ -25,8 +22,6 @@ void __iomem *ioremap_wc(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 EXPORT_SYMBOL(ioremap_wc);
@@ -36,22 +31,18 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_cached(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 
-void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long flags)
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, pgprot_t prot)
 {
-	pte_t pte = __pte(flags);
+	pte_t pte = __pte(pgprot_val(prot));
 	void *caller = __builtin_return_address(0);
 
 	/* writeable implies dirty for kernel addresses */
 	if (pte_write(pte))
 		pte = pte_mkdirty(pte);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
 	return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
 }
 EXPORT_SYMBOL(ioremap_prot);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index d24e5f166723..fb8b55bd2cd5 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -52,6 +52,6 @@ void iounmap(volatile void __iomem *token)
 	if (!slab_is_available())
 		return;
 
-	generic_iounmap(PCI_FIX_ADDR(token));
+	generic_iounmap(token);
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index c7708c8fad29..3ddbfdbfa941 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -273,7 +273,7 @@ void __init paging_init(void)
 	mark_nonram_nosave();
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
@@ -295,22 +295,6 @@ void __init mem_init(void)
 
 	kasan_late_init();
 
-	memblock_free_all();
-
-#ifdef CONFIG_HIGHMEM
-	{
-		unsigned long pfn, highmem_mapnr;
-
-		highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
-		for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
-			phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT;
-			struct page *page = pfn_to_page(pfn);
-			if (memblock_is_memory(paddr) && !memblock_is_reserved(paddr))
-				free_highmem_page(page);
-		}
-	}
-#endif /* CONFIG_HIGHMEM */
-
 #if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP)
 	/*
 	 * If smp is enabled, next_tlbcam_idx is initialized in the cpu up
@@ -319,28 +303,6 @@ void __init mem_init(void)
 	per_cpu(next_tlbcam_idx, smp_processor_id()) =
 		(mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
 #endif
-
-#ifdef CONFIG_PPC32
-	pr_info("Kernel virtual memory layout:\n");
-#ifdef CONFIG_KASAN
-	pr_info("  * 0x%08lx..0x%08lx  : kasan shadow mem\n",
-		KASAN_SHADOW_START, KASAN_SHADOW_END);
-#endif
-	pr_info("  * 0x%08lx..0x%08lx  : fixmap\n", FIXADDR_START, FIXADDR_TOP);
-#ifdef CONFIG_HIGHMEM
-	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
-		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
-#endif /* CONFIG_HIGHMEM */
-	if (ioremap_bot != IOREMAP_TOP)
-		pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
-			ioremap_bot, IOREMAP_TOP);
-	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
-		VMALLOC_START, VMALLOC_END);
-#ifdef MODULES_VADDR
-	pr_info("  * 0x%08lx..0x%08lx  : modules\n",
-		MODULES_VADDR, MODULES_END);
-#endif
-#endif /* CONFIG_PPC32 */
 }
 
 void free_initmem(void)
@@ -376,7 +338,7 @@ static int __init add_system_ram_resources(void)
 			 */
 			res->end = end - 1;
 			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-			WARN_ON(request_resource(&iomem_resource, res) < 0);
+			WARN_ON(insert_resource(&iomem_resource, res) < 0);
 		}
 	}
 
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 8b54f12d1889..ab1505cf42bf 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -54,20 +54,13 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 {
 	pmd_t *pmdp = pmd_off_k(va);
 	pte_t *ptep;
-
-	if (WARN_ON(psize != MMU_PAGE_512K && psize != MMU_PAGE_8M))
-		return -EINVAL;
+	unsigned int shift = mmu_psize_to_shift(psize);
 
 	if (new) {
 		if (WARN_ON(slab_is_available()))
 			return -EINVAL;
 
-		if (psize == MMU_PAGE_512K) {
-			ptep = early_pte_alloc_kernel(pmdp, va);
-			/* The PTE should never be already present */
-			if (WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
-				return -EINVAL;
-		} else {
+		if (psize == MMU_PAGE_8M) {
 			if (WARN_ON(!pmd_none(*pmdp) || !pmd_none(*(pmdp + 1))))
 				return -EINVAL;
 
@@ -78,20 +71,25 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 			pmd_populate_kernel(&init_mm, pmdp + 1, ptep);
 
 			ptep = (pte_t *)pmdp;
+		} else {
+			ptep = early_pte_alloc_kernel(pmdp, va);
+			/* The PTE should never be already present */
+			if (WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
+				return -EINVAL;
 		}
 	} else {
-		if (psize == MMU_PAGE_512K)
-			ptep = pte_offset_kernel(pmdp, va);
-		else
+		if (psize == MMU_PAGE_8M)
 			ptep = (pte_t *)pmdp;
+		else
+			ptep = pte_offset_kernel(pmdp, va);
 	}
 
 	if (WARN_ON(!ptep))
 		return -ENOMEM;
 
 	set_huge_pte_at(&init_mm, va, ptep,
-			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
-			1UL << mmu_psize_to_shift(psize));
+			arch_make_huge_pte(pfn_pte(pa >> PAGE_SHIFT, prot), shift, 0),
+			1UL << shift);
 
 	return 0;
 }
@@ -123,14 +121,18 @@ static int mmu_mapin_ram_chunk(unsigned long offset, unsigned long top,
 	unsigned long p = offset;
 	int err = 0;
 
-	WARN_ON(!IS_ALIGNED(offset, SZ_512K) || !IS_ALIGNED(top, SZ_512K));
+	WARN_ON(!IS_ALIGNED(offset, SZ_16K) || !IS_ALIGNED(top, SZ_16K));
 
+	for (; p < ALIGN(p, SZ_512K) && p < top && !err; p += SZ_16K, v += SZ_16K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_16K, new);
 	for (; p < ALIGN(p, SZ_8M) && p < top && !err; p += SZ_512K, v += SZ_512K)
 		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
 	for (; p < ALIGN_DOWN(top, SZ_8M) && p < top && !err; p += SZ_8M, v += SZ_8M)
 		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_8M, new);
 	for (; p < ALIGN_DOWN(top, SZ_512K) && p < top && !err; p += SZ_512K, v += SZ_512K)
 		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+	for (; p < ALIGN_DOWN(top, SZ_16K) && p < top && !err; p += SZ_16K, v += SZ_16K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_16K, new);
 
 	if (!new)
 		flush_tlb_kernel_range(PAGE_OFFSET + v, PAGE_OFFSET + top);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3c1da08304d0..603a0f652ba6 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1336,7 +1336,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	return nid;
 }
 
-static u64 hot_add_drconf_memory_max(void)
+u64 hot_add_drconf_memory_max(void)
 {
 	struct device_node *memory = NULL;
 	struct device_node *dn = NULL;
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 6beacaec63d3..4c26912c2e3c 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -51,8 +51,16 @@
 		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));					\
 	} while (0)
 
-/* Sign-extended 32-bit immediate load */
+/*
+ * Sign-extended 32-bit immediate load
+ *
+ * If this is a dummy pass (!image), account for
+ * maximum possible instructions.
+ */
 #define PPC_LI32(d, i)		do {					      \
+	if (!image)							      \
+		ctx->idx += 2;						      \
+	else {								      \
 		if ((int)(uintptr_t)(i) >= -32768 &&			      \
 				(int)(uintptr_t)(i) < 32768)		      \
 			EMIT(PPC_RAW_LI(d, i));				      \
@@ -60,10 +68,15 @@
 			EMIT(PPC_RAW_LIS(d, IMM_H(i)));			      \
 			if (IMM_L(i))					      \
 				EMIT(PPC_RAW_ORI(d, d, IMM_L(i)));	      \
-		} } while(0)
+		}							      \
+	} } while (0)
 
 #ifdef CONFIG_PPC64
+/* If dummy pass (!image), account for maximum possible instructions */
 #define PPC_LI64(d, i)		do {					      \
+	if (!image)							      \
+		ctx->idx += 5;						      \
+	else {								      \
 		if ((long)(i) >= -2147483648 &&				      \
 				(long)(i) < 2147483648)			      \
 			PPC_LI32(d, i);					      \
@@ -84,7 +97,8 @@
 			if ((uintptr_t)(i) & 0x000000000000ffffULL)	      \
 				EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) &       \
 							0xffff));             \
-		} } while (0)
+		}							      \
+	} } while (0)
 #define PPC_LI_ADDR	PPC_LI64
 
 #ifndef CONFIG_PPC_KERNEL_PCREL
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 2991bb171a9b..c0684733e9d6 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -504,10 +504,11 @@ static int invoke_bpf_prog(u32 *image, u32 *ro_image, struct codegen_context *ct
 	EMIT(PPC_RAW_ADDI(_R3, _R1, regs_off));
 	if (!p->jited)
 		PPC_LI_ADDR(_R4, (unsigned long)p->insnsi);
-	if (!create_branch(&branch_insn, (u32 *)&ro_image[ctx->idx], (unsigned long)p->bpf_func,
-			   BRANCH_SET_LINK)) {
-		if (image)
-			image[ctx->idx] = ppc_inst_val(branch_insn);
+	/* Account for max possible instructions during dummy pass for size calculation */
+	if (image && !create_branch(&branch_insn, (u32 *)&ro_image[ctx->idx],
+				    (unsigned long)p->bpf_func,
+				    BRANCH_SET_LINK)) {
+		image[ctx->idx] = ppc_inst_val(branch_insn);
 		ctx->idx++;
 	} else {
 		EMIT(PPC_RAW_LL(_R12, _R25, offsetof(struct bpf_prog, bpf_func)));
@@ -889,7 +890,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 			bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
 
 		/* Reserve space to patch branch instruction to skip fexit progs */
-		im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
+		if (ro_image) /* image is NULL for dummy pass */
+			im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
 		EMIT(PPC_RAW_NOP());
 	}
 
@@ -912,7 +914,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
+		if (ro_image) /* image is NULL for dummy pass */
+			im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
 		PPC_LI_ADDR(_R3, im);
 		ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
 						 (unsigned long)__bpf_tramp_exit);
@@ -973,25 +976,9 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 			     struct bpf_tramp_links *tlinks, void *func_addr)
 {
 	struct bpf_tramp_image im;
-	void *image;
 	int ret;
 
-	/*
-	 * Allocate a temporary buffer for __arch_prepare_bpf_trampoline().
-	 * This will NOT cause fragmentation in direct map, as we do not
-	 * call set_memory_*() on this buffer.
-	 *
-	 * We cannot use kvmalloc here, because we need image to be in
-	 * module memory range.
-	 */
-	image = bpf_jit_alloc_exec(PAGE_SIZE);
-	if (!image)
-		return -ENOMEM;
-
-	ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image,
-					    m, flags, tlinks, func_addr);
-	bpf_jit_free_exec(image);
-
+	ret = __arch_prepare_bpf_trampoline(&im, NULL, NULL, NULL, m, flags, tlinks, func_addr);
 	return ret;
 }
 
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index c4db278dae36..0aace304dfe1 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -313,7 +313,6 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		u64 func_addr;
 		u32 true_cond;
 		u32 tmp_idx;
-		int j;
 
 		if (i && (BPF_CLASS(code) == BPF_ALU64 || BPF_CLASS(code) == BPF_ALU) &&
 		    (BPF_CLASS(prevcode) == BPF_ALU64 || BPF_CLASS(prevcode) == BPF_ALU) &&
@@ -1099,13 +1098,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		 * 16 byte instruction that uses two 'struct bpf_insn'
 		 */
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
-			tmp_idx = ctx->idx;
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
-			/* padding to allow full 4 instructions for later patching */
-			if (!image)
-				for (j = ctx->idx - tmp_idx; j < 4; j++)
-					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 233703b06d7c..5daa77aee7f7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -227,7 +227,14 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *
 #ifdef CONFIG_PPC_KERNEL_PCREL
 	reladdr = func_addr - local_paca->kernelbase;
 
-	if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
+	/*
+	 * If fimage is NULL (the initial pass to find image size),
+	 * account for the maximum no. of instructions possible.
+	 */
+	if (!fimage) {
+		ctx->idx += 7;
+		return 0;
+	} else if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
 		EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)));
 		/* Align for subsequent prefix instruction */
 		if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8))
@@ -412,7 +419,6 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		u64 imm64;
 		u32 true_cond;
 		u32 tmp_idx;
-		int j;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -1046,12 +1052,7 @@ emit_clear:
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
 			imm64 = ((u64)(u32) insn[i].imm) |
 				    (((u64)(u32) insn[i+1].imm) << 32);
-			tmp_idx = ctx->idx;
 			PPC_LI64(dst_reg, imm64);
-			/* padding to allow full 5 instructions for later patching */
-			if (!image)
-				for (j = ctx->idx - tmp_idx; j < 5; j++)
-					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index ac2cf58d62db..7f53fcb7495a 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -18,6 +18,8 @@ obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
 
 obj-$(CONFIG_VPA_PMU) += vpa-pmu.o
 
+obj-$(CONFIG_KVM_BOOK3S_HV_PMU) += kvm-hv-pmu.o
+
 obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 2b79171ee185..8b0081441f85 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -132,7 +132,10 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) {}
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
+{
+}
 static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -444,7 +447,8 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
 {
 	if (!ppmu->bhrb_nr)
 		return;
@@ -2222,6 +2226,10 @@ static struct pmu power_pmu = {
 #define PERF_SAMPLE_ADDR_TYPE  (PERF_SAMPLE_ADDR |		\
 				PERF_SAMPLE_PHYS_ADDR |		\
 				PERF_SAMPLE_DATA_PAGE_SIZE)
+
+#define SIER_TYPE_SHIFT	15
+#define SIER_TYPE_MASK	(0x7ull << SIER_TYPE_SHIFT)
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -2231,6 +2239,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -2291,12 +2300,28 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		record = 0;
 
 	/*
+	 * SIER[46-48] presents instruction type of the sampled instruction.
+	 * In ISA v3.0 and before values "0" and "7" are considered reserved.
+	 * In ISA v3.1, value "7" has been used to indicate "larx/stcx".
+	 * Drop the sample if "type" has reserved values for this field with a
+	 * ISA version check.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
+			ppmu->get_mem_data_src) {
+		val = (regs->dar & SIER_TYPE_MASK) >> SIER_TYPE_SHIFT;
+		if (val == 0 || (val == 7 && !cpu_has_feature(CPU_FTR_ARCH_31))) {
+			record = 0;
+			atomic64_inc(&event->lost_samples);
+		}
+	}
+
+	/*
 	 * Finally record data if requested.
 	 */
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
+		perf_sample_data_init(&data, ~0ULL, last_period);
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR_TYPE)
 			perf_get_data_addr(event, regs, &data.addr);
@@ -2319,12 +2344,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			ppmu->get_mem_weight(&data.weight.full, event->attr.sample_type);
 			data.sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
-		if (perf_event_overflow(event, &data, regs))
-			power_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	} else if (period) {
 		/* Account for interrupt in case of invalid SIAR */
-		if (perf_event_account_interrupt(event))
-			power_pmu_stop(event, 0);
+		perf_event_account_interrupt(event);
 	}
 }
 
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 1a53ab08447c..7120ab20cbfe 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -590,6 +590,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -632,10 +633,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
-		if (perf_event_overflow(event, &data, regs))
-			fsl_emb_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 }
 
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index d400fa391c27..b0768f3d2893 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -998,7 +998,7 @@ e_out:
 }
 
 static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t offset, size_t count)
 {
 	long hret;
@@ -1108,14 +1108,14 @@ PAGE_0_ATTR(catalog_version, "%lld\n",
 		(unsigned long long)be64_to_cpu(page_0->version));
 PAGE_0_ATTR(catalog_len, "%lld\n",
 		(unsigned long long)be32_to_cpu(page_0->length) * 4096);
-static BIN_ATTR_RO(catalog, 0/* real length varies */);
+static const BIN_ATTR_RO(catalog, 0/* real length varies */);
 static DEVICE_ATTR_RO(domains);
 static DEVICE_ATTR_RO(sockets);
 static DEVICE_ATTR_RO(chipspersocket);
 static DEVICE_ATTR_RO(coresperchip);
 static DEVICE_ATTR_RO(cpumask);
 
-static struct bin_attribute *if_bin_attrs[] = {
+static const struct bin_attribute *const if_bin_attrs[] = {
 	&bin_attr_catalog,
 	NULL,
 };
@@ -1141,7 +1141,7 @@ static struct attribute *if_attrs[] = {
 
 static const struct attribute_group if_group = {
 	.name = "interface",
-	.bin_attrs = if_bin_attrs,
+	.bin_attrs_new = if_bin_attrs,
 	.attrs = if_attrs,
 };
 
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 56301b2bc8ae..2b3547fdba4a 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -319,10 +319,18 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
 		return;
 	}
 
-	sier = mfspr(SPRN_SIER);
+	/*
+	 * Use regs-dar for SPRN_SIER which is saved
+	 * during perf_read_regs at the beginning
+	 * of the PMU interrupt handler to avoid multiple
+	 * reads of SPRN_SIER
+	 */
+	sier = regs->dar;
 	val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
-	if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31)))
+	if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31))) {
+		dsrc->val = 0;
 		return;
+	}
 
 	idx = (sier & ISA207_SIER_LDST_MASK) >> ISA207_SIER_LDST_SHIFT;
 	sub_idx = (sier & ISA207_SIER_DATA_SRC_MASK) >> ISA207_SIER_DATA_SRC_SHIFT;
@@ -338,8 +346,12 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
 		 * to determine the exact instruction type. If the sampling
 		 * criteria is neither load or store, set the type as default
 		 * to NA.
+		 *
+		 * Use regs->dsisr for MMCRA which is saved during perf_read_regs
+		 * at the beginning of the PMU interrupt handler to avoid
+		 * multiple reads of SPRN_MMCRA
 		 */
-		mmcra = mfspr(SPRN_MMCRA);
+		mmcra = regs->dsisr;
 
 		op_type = (mmcra >> MMCRA_SAMP_ELIG_SHIFT) & MMCRA_SAMP_ELIG_MASK;
 		switch (op_type) {
diff --git a/arch/powerpc/perf/kvm-hv-pmu.c b/arch/powerpc/perf/kvm-hv-pmu.c
new file mode 100644
index 000000000000..ae264c9080ef
--- /dev/null
+++ b/arch/powerpc/perf/kvm-hv-pmu.c
@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Description: PMUs specific to running nested KVM-HV guests
+ * on Book3S processors (specifically POWER9 and later).
+ */
+
+#define pr_fmt(fmt)  "kvmppc-pmu: " fmt
+
+#include "asm-generic/local64.h"
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/ratelimit.h>
+#include <linux/kvm_host.h>
+#include <linux/gfp_types.h>
+#include <linux/pgtable.h>
+#include <linux/perf_event.h>
+#include <linux/spinlock_types.h>
+#include <linux/spinlock.h>
+
+#include <asm/types.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu.h>
+#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
+#include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/firmware.h>
+
+#include "asm/guest-state-buffer.h"
+
+enum kvmppc_pmu_eventid {
+	KVMPPC_EVENT_HOST_HEAP,
+	KVMPPC_EVENT_HOST_HEAP_MAX,
+	KVMPPC_EVENT_HOST_PGTABLE,
+	KVMPPC_EVENT_HOST_PGTABLE_MAX,
+	KVMPPC_EVENT_HOST_PGTABLE_RECLAIM,
+	KVMPPC_EVENT_MAX,
+};
+
+#define KVMPPC_PMU_EVENT_ATTR(_name, _id) \
+	PMU_EVENT_ATTR_ID(_name, kvmppc_events_sysfs_show, _id)
+
+static ssize_t kvmppc_events_sysfs_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+/* Holds the hostwide stats */
+static struct kvmppc_hostwide_stats {
+	u64 guest_heap;
+	u64 guest_heap_max;
+	u64 guest_pgtable_size;
+	u64 guest_pgtable_size_max;
+	u64 guest_pgtable_reclaim;
+} l0_stats;
+
+/* Protect access to l0_stats */
+static DEFINE_SPINLOCK(lock_l0_stats);
+
+/* GSB related structs needed to talk to L0 */
+static struct kvmppc_gs_msg *gsm_l0_stats;
+static struct kvmppc_gs_buff *gsb_l0_stats;
+static struct kvmppc_gs_parser gsp_l0_stats;
+
+static struct attribute *kvmppc_pmu_events_attr[] = {
+	KVMPPC_PMU_EVENT_ATTR(host_heap, KVMPPC_EVENT_HOST_HEAP),
+	KVMPPC_PMU_EVENT_ATTR(host_heap_max, KVMPPC_EVENT_HOST_HEAP_MAX),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable, KVMPPC_EVENT_HOST_PGTABLE),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable_max, KVMPPC_EVENT_HOST_PGTABLE_MAX),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable_reclaim, KVMPPC_EVENT_HOST_PGTABLE_RECLAIM),
+	NULL,
+};
+
+static const struct attribute_group kvmppc_pmu_events_group = {
+	.name = "events",
+	.attrs = kvmppc_pmu_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-5");
+static struct attribute *kvmppc_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group kvmppc_pmu_format_group = {
+	.name = "format",
+	.attrs = kvmppc_pmu_format_attr,
+};
+
+static const struct attribute_group *kvmppc_pmu_attr_groups[] = {
+	&kvmppc_pmu_events_group,
+	&kvmppc_pmu_format_group,
+	NULL,
+};
+
+/*
+ * Issue the hcall to get the L0-host stats.
+ * Should be called with l0-stat lock held
+ */
+static int kvmppc_update_l0_stats(void)
+{
+	int rc;
+
+	/* With HOST_WIDE flags guestid and vcpuid will be ignored */
+	rc = kvmppc_gsb_recv(gsb_l0_stats, KVMPPC_GS_FLAGS_HOST_WIDE);
+	if (rc)
+		goto out;
+
+	/* Parse the guest state buffer is successful */
+	rc = kvmppc_gse_parse(&gsp_l0_stats, gsb_l0_stats);
+	if (rc)
+		goto out;
+
+	/* Update the l0 returned stats*/
+	memset(&l0_stats, 0, sizeof(l0_stats));
+	rc = kvmppc_gsm_refresh_info(gsm_l0_stats, gsb_l0_stats);
+
+out:
+	return rc;
+}
+
+/* Update the value of the given perf_event */
+static int kvmppc_pmu_event_update(struct perf_event *event)
+{
+	int rc;
+	u64 curr_val, prev_val;
+	unsigned long flags;
+	unsigned int config = event->attr.config;
+
+	/* Ensure no one else is modifying the l0_stats */
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	rc = kvmppc_update_l0_stats();
+	if (!rc) {
+		switch (config) {
+		case KVMPPC_EVENT_HOST_HEAP:
+			curr_val = l0_stats.guest_heap;
+			break;
+		case KVMPPC_EVENT_HOST_HEAP_MAX:
+			curr_val = l0_stats.guest_heap_max;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE:
+			curr_val = l0_stats.guest_pgtable_size;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE_MAX:
+			curr_val = l0_stats.guest_pgtable_size_max;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE_RECLAIM:
+			curr_val = l0_stats.guest_pgtable_reclaim;
+			break;
+		default:
+			rc = -ENOENT;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+
+	/* If no error than update the perf event */
+	if (!rc) {
+		prev_val = local64_xchg(&event->hw.prev_count, curr_val);
+		if (curr_val > prev_val)
+			local64_add(curr_val - prev_val, &event->count);
+	}
+
+	return rc;
+}
+
+static int kvmppc_pmu_event_init(struct perf_event *event)
+{
+	unsigned int config = event->attr.config;
+
+	pr_debug("%s: Event(%p) id=%llu cpu=%x on_cpu=%x config=%u",
+		 __func__, event, event->id, event->cpu,
+		 event->oncpu, config);
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (config >= KVMPPC_EVENT_MAX)
+		return -EINVAL;
+
+	local64_set(&event->hw.prev_count, 0);
+	local64_set(&event->count, 0);
+
+	return 0;
+}
+
+static void kvmppc_pmu_del(struct perf_event *event, int flags)
+{
+	kvmppc_pmu_event_update(event);
+}
+
+static int kvmppc_pmu_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		return kvmppc_pmu_event_update(event);
+	return 0;
+}
+
+static void kvmppc_pmu_read(struct perf_event *event)
+{
+	kvmppc_pmu_event_update(event);
+}
+
+/* Return the size of the needed guest state buffer */
+static size_t hostwide_get_size(struct kvmppc_gs_msg *gsm)
+
+{
+	size_t size = 0;
+	const u16 ids[] = {
+		KVMPPC_GSID_L0_GUEST_HEAP,
+		KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+/* Populate the request guest state buffer */
+static int hostwide_fill_info(struct kvmppc_gs_buff *gsb,
+			      struct kvmppc_gs_msg *gsm)
+{
+	int rc = 0;
+	struct kvmppc_hostwide_stats  *stats = gsm->data;
+
+	/*
+	 * It doesn't matter what values are put into request buffer as
+	 * they are going to be overwritten anyways. But for the sake of
+	 * testcode and symmetry contents of existing stats are put
+	 * populated into the request guest state buffer.
+	 */
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_HEAP,
+					stats->guest_heap);
+
+	if (!rc && kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+					stats->guest_heap_max);
+
+	if (!rc && kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+					stats->guest_pgtable_size);
+	if (!rc &&
+	    kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+					stats->guest_pgtable_size_max);
+	if (!rc &&
+	    kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM,
+					stats->guest_pgtable_reclaim);
+
+	return rc;
+}
+
+/* Parse and update the host wide stats from returned gsb */
+static int hostwide_refresh_info(struct kvmppc_gs_msg *gsm,
+				 struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_hostwide_stats *stats = gsm->data;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	if (gse)
+		stats->guest_heap = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	if (gse)
+		stats->guest_heap_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	if (gse)
+		stats->guest_pgtable_size = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	if (gse)
+		stats->guest_pgtable_size_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	if (gse)
+		stats->guest_pgtable_reclaim = kvmppc_gse_get_u64(gse);
+
+	return 0;
+}
+
+/* gsb-message ops for setting up/parsing */
+static struct kvmppc_gs_msg_ops gsb_ops_l0_stats = {
+	.get_size = hostwide_get_size,
+	.fill_info = hostwide_fill_info,
+	.refresh_info = hostwide_refresh_info,
+};
+
+static int kvmppc_init_hostwide(void)
+{
+	int rc = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	/* already registered ? */
+	if (gsm_l0_stats) {
+		rc = 0;
+		goto out;
+	}
+
+	/* setup the Guest state message/buffer to talk to L0 */
+	gsm_l0_stats = kvmppc_gsm_new(&gsb_ops_l0_stats, &l0_stats,
+				      GSM_SEND, GFP_KERNEL);
+	if (!gsm_l0_stats) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Populate the Idents */
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_HEAP);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	/* allocate GSB. Guest/Vcpu Id is ignored */
+	gsb_l0_stats = kvmppc_gsb_new(kvmppc_gsm_size(gsm_l0_stats), 0, 0,
+				      GFP_KERNEL);
+	if (!gsb_l0_stats) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* ask the ops to fill in the info */
+	rc = kvmppc_gsm_fill_info(gsm_l0_stats, gsb_l0_stats);
+
+out:
+	if (rc) {
+		if (gsm_l0_stats)
+			kvmppc_gsm_free(gsm_l0_stats);
+		if (gsb_l0_stats)
+			kvmppc_gsb_free(gsb_l0_stats);
+		gsm_l0_stats = NULL;
+		gsb_l0_stats = NULL;
+	}
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+	return rc;
+}
+
+static void kvmppc_cleanup_hostwide(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	if (gsm_l0_stats)
+		kvmppc_gsm_free(gsm_l0_stats);
+	if (gsb_l0_stats)
+		kvmppc_gsb_free(gsb_l0_stats);
+	gsm_l0_stats = NULL;
+	gsb_l0_stats = NULL;
+
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+}
+
+/* L1 wide counters PMU */
+static struct pmu kvmppc_pmu = {
+	.module = THIS_MODULE,
+	.task_ctx_nr = perf_sw_context,
+	.name = "kvm-hv",
+	.event_init = kvmppc_pmu_event_init,
+	.add = kvmppc_pmu_add,
+	.del = kvmppc_pmu_del,
+	.read = kvmppc_pmu_read,
+	.attr_groups = kvmppc_pmu_attr_groups,
+	.type = -1,
+	.scope = PERF_PMU_SCOPE_SYS_WIDE,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init kvmppc_register_pmu(void)
+{
+	int rc = -EOPNOTSUPP;
+
+	/* only support events for nestedv2 right now */
+	if (kvmhv_is_nestedv2()) {
+		rc = kvmppc_init_hostwide();
+		if (rc)
+			goto out;
+
+		/* Register the pmu */
+		rc = perf_pmu_register(&kvmppc_pmu, kvmppc_pmu.name, -1);
+		if (rc)
+			goto out;
+
+		pr_info("Registered kvm-hv pmu");
+	}
+
+out:
+	return rc;
+}
+
+static void __exit kvmppc_unregister_pmu(void)
+{
+	if (kvmhv_is_nestedv2()) {
+		kvmppc_cleanup_hostwide();
+
+		if (kvmppc_pmu.type != -1)
+			perf_pmu_unregister(&kvmppc_pmu);
+
+		pr_info("kvmhv_pmu unregistered.\n");
+	}
+}
+
+module_init(kvmppc_register_pmu);
+module_exit(kvmppc_unregister_pmu);
+MODULE_DESCRIPTION("KVM PPC Book3s-hv PMU");
+MODULE_AUTHOR("Vaibhav Jain <vaibhav@linux.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/perf/vpa-pmu.c b/arch/powerpc/perf/vpa-pmu.c
index 6a5bfd2a13b5..840733468959 100644
--- a/arch/powerpc/perf/vpa-pmu.c
+++ b/arch/powerpc/perf/vpa-pmu.c
@@ -156,6 +156,7 @@ static void vpa_pmu_del(struct perf_event *event, int flags)
 }
 
 static struct pmu vpa_pmu = {
+	.module		= THIS_MODULE,
 	.task_ctx_nr	= perf_sw_context,
 	.name		= "vpa_pmu",
 	.event_init	= vpa_pmu_event_init,
diff --git a/arch/powerpc/platforms/44x/gpio.c b/arch/powerpc/platforms/44x/gpio.c
index e5f2319e5cbe..d540e261d85a 100644
--- a/arch/powerpc/platforms/44x/gpio.c
+++ b/arch/powerpc/platforms/44x/gpio.c
@@ -75,8 +75,7 @@ __ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 		clrbits32(&regs->or, GPIO_MASK(gpio));
 }
 
-static void
-ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -88,6 +87,8 @@ ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	spin_unlock_irqrestore(&chip->lock, flags);
 
 	pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val);
+
+	return 0;
 }
 
 static int ppc4xx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -179,7 +180,7 @@ static int __init ppc4xx_add_gpiochips(void)
 		gc->direction_input = ppc4xx_gpio_dir_in;
 		gc->direction_output = ppc4xx_gpio_dir_out;
 		gc->get = ppc4xx_gpio_get;
-		gc->set = ppc4xx_gpio_set;
+		gc->set_rv = ppc4xx_gpio_set;
 
 		ret = of_mm_gpiochip_add_data(np, mm_gc, ppc4xx_gc);
 		if (ret)
diff --git a/arch/powerpc/platforms/44x/uic.c b/arch/powerpc/platforms/44x/uic.c
index e3e148b9dd18..85daf841fd3f 100644
--- a/arch/powerpc/platforms/44x/uic.c
+++ b/arch/powerpc/platforms/44x/uic.c
@@ -37,7 +37,7 @@
 #define UIC_VR		0x7
 #define UIC_VCR		0x8
 
-struct uic *primary_uic;
+static struct uic *primary_uic;
 
 struct uic {
 	int index;
@@ -254,8 +254,9 @@ static struct uic * __init uic_init_one(struct device_node *node)
 	}
 	uic->dcrbase = *dcrreg;
 
-	uic->irqhost = irq_domain_add_linear(node, NR_UIC_INTS, &uic_host_ops,
-					     uic);
+	uic->irqhost = irq_domain_create_linear(of_fwnode_handle(node),
+						NR_UIC_INTS, &uic_host_ops,
+						uic);
 	if (! uic->irqhost)
 		return NULL; /* FIXME: panic? */
 
@@ -291,7 +292,7 @@ void __init uic_init_tree(void)
 	if (!primary_uic)
 		panic("Unable to initialize primary UIC %pOF\n", np);
 
-	irq_set_default_host(primary_uic->irqhost);
+	irq_set_default_domain(primary_uic->irqhost);
 	of_node_put(np);
 
 	/* The scan again for cascaded UICs */
@@ -327,5 +328,5 @@ unsigned int uic_get_irq(void)
 	msr = mfdcr(primary_uic->dcrbase + UIC_MSR);
 	src = 32 - ffs(msr);
 
-	return irq_linear_revmap(primary_uic->irqhost, src);
+	return irq_find_mapping(primary_uic->irqhost, src);
 }
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index e995eb30bf09..2cf3c6237337 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -188,7 +188,8 @@ mpc5121_ads_cpld_pic_init(void)
 
 	cpld_pic_node = of_node_get(np);
 
-	cpld_pic_host = irq_domain_add_linear(np, 16, &cpld_pic_host_ops, NULL);
+	cpld_pic_host = irq_domain_create_linear(of_fwnode_handle(np), 16,
+						 &cpld_pic_host_ops, NULL);
 	if (!cpld_pic_host) {
 		printk(KERN_ERR "CPLD PIC: failed to allocate irq host!\n");
 		goto end;
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 19626cd42406..bc7f83cfec1d 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -168,7 +168,7 @@ static void __init media5200_init_irq(void)
 
 	spin_lock_init(&media5200_irq.lock);
 
-	media5200_irq.irqhost = irq_domain_add_linear(fpga_np,
+	media5200_irq.irqhost = irq_domain_create_linear(of_fwnode_handle(fpga_np),
 			MEDIA5200_NUM_IRQS, &media5200_irq_ops, &media5200_irq);
 	if (!media5200_irq.irqhost)
 		goto out;
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 1ea591ec6083..bda707d848a6 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -247,9 +247,9 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
 	if (!cascade_virq)
 		return;
 
-	gpt->irqhost = irq_domain_add_linear(node, 1, &mpc52xx_gpt_irq_ops, gpt);
+	gpt->irqhost = irq_domain_create_linear(of_fwnode_handle(node), 1, &mpc52xx_gpt_irq_ops, gpt);
 	if (!gpt->irqhost) {
-		dev_err(gpt->dev, "irq_domain_add_linear() failed\n");
+		dev_err(gpt->dev, "irq_domain_create_linear() failed\n");
 		return;
 	}
 
@@ -280,7 +280,7 @@ static int mpc52xx_gpt_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 	return (in_be32(&gpt->regs->status) >> 8) & 1;
 }
 
-static void
+static int
 mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 {
 	struct mpc52xx_gpt_priv *gpt = gpiochip_get_data(gc);
@@ -293,6 +293,8 @@ mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_GPIO_MASK, r);
 	raw_spin_unlock_irqrestore(&gpt->lock, flags);
+
+	return 0;
 }
 
 static int mpc52xx_gpt_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -334,7 +336,7 @@ static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt)
 	gpt->gc.direction_input  = mpc52xx_gpt_gpio_dir_in;
 	gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out;
 	gpt->gc.get = mpc52xx_gpt_gpio_get;
-	gpt->gc.set = mpc52xx_gpt_gpio_set;
+	gpt->gc.set_rv = mpc52xx_gpt_gpio_set;
 	gpt->gc.base = -1;
 	gpt->gc.parent = gpt->dev;
 
@@ -369,7 +371,7 @@ struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq)
 	mutex_lock(&mpc52xx_gpt_list_mutex);
 	list_for_each(pos, &mpc52xx_gpt_list) {
 		gpt = container_of(pos, struct mpc52xx_gpt_priv, list);
-		if (gpt->irqhost && irq == irq_linear_revmap(gpt->irqhost, 0)) {
+		if (gpt->irqhost && irq == irq_find_mapping(gpt->irqhost, 0)) {
 			mutex_unlock(&mpc52xx_gpt_list_mutex);
 			return gpt;
 		}
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 1e0a5e9644dc..eb6a4e745c08 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -446,14 +446,14 @@ void __init mpc52xx_init_irq(void)
 	 * As last step, add an irq host to translate the real
 	 * hw irq information provided by the ofw to linux virq
 	 */
-	mpc52xx_irqhost = irq_domain_add_linear(picnode,
+	mpc52xx_irqhost = irq_domain_create_linear(of_fwnode_handle(picnode),
 	                                 MPC52xx_IRQ_HIGHTESTHWIRQ,
 	                                 &mpc52xx_irqhost_ops, NULL);
 
 	if (!mpc52xx_irqhost)
 		panic(__FILE__ ": Cannot allocate the IRQ host\n");
 
-	irq_set_default_host(mpc52xx_irqhost);
+	irq_set_default_domain(mpc52xx_irqhost);
 
 	pr_info("MPC52xx PIC is up and running!\n");
 }
@@ -515,5 +515,5 @@ unsigned int mpc52xx_get_irq(void)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpc52xx_irqhost, irq);
+	return irq_find_mapping(mpc52xx_irqhost, irq);
 }
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 4d8fa9ed1a67..6e37dfc6c5c9 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -92,10 +92,11 @@ static void mcu_power_off(void)
 	mutex_unlock(&mcu->lock);
 }
 
-static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct mcu *mcu = gpiochip_get_data(gc);
 	u8 bit = 1 << (4 + gpio);
+	int ret;
 
 	mutex_lock(&mcu->lock);
 	if (val)
@@ -103,14 +104,16 @@ static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	else
 		mcu->reg_ctrl |= bit;
 
-	i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL, mcu->reg_ctrl);
+	ret = i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
+					mcu->reg_ctrl);
 	mutex_unlock(&mcu->lock);
+
+	return ret;
 }
 
 static int mcu_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	mcu_gpio_set(gc, gpio, val);
-	return 0;
+	return mcu_gpio_set(gc, gpio, val);
 }
 
 static int mcu_gpiochip_add(struct mcu *mcu)
@@ -123,7 +126,7 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 	gc->can_sleep = 1;
 	gc->ngpio = MCU_NUM_GPIO;
 	gc->base = -1;
-	gc->set = mcu_gpio_set;
+	gc->set_rv = mcu_gpio_set;
 	gc->direction_output = mcu_gpio_dir_out;
 	gc->parent = dev;
 
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 60e0b8947ce6..4b69fb321a68 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -83,7 +83,7 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq)
 		if (cause >> (i + 16))
 			break;
 	}
-	return irq_linear_revmap(socrates_fpga_pic_irq_host,
+	return irq_find_mapping(socrates_fpga_pic_irq_host,
 			(irq_hw_number_t)i);
 }
 
@@ -278,7 +278,7 @@ void __init socrates_fpga_pic_init(struct device_node *pic)
 	int i;
 
 	/* Setup an irq_domain structure */
-	socrates_fpga_pic_irq_host = irq_domain_add_linear(pic,
+	socrates_fpga_pic_irq_host = irq_domain_create_linear(of_fwnode_handle(pic),
 		    SOCRATES_FPGA_NUM_IRQS, &socrates_fpga_pic_host_ops, NULL);
 	if (socrates_fpga_pic_irq_host == NULL) {
 		pr_err("FPGA PIC: Unable to allocate host\n");
diff --git a/arch/powerpc/platforms/8xx/cpm1-ic.c b/arch/powerpc/platforms/8xx/cpm1-ic.c
index a18fc7c99f83..a49d4a9ab3bc 100644
--- a/arch/powerpc/platforms/8xx/cpm1-ic.c
+++ b/arch/powerpc/platforms/8xx/cpm1-ic.c
@@ -59,7 +59,7 @@ static int cpm_get_irq(struct irq_desc *desc)
 	cpm_vec = in_be16(&data->reg->cpic_civr);
 	cpm_vec >>= 11;
 
-	return irq_linear_revmap(data->host, cpm_vec);
+	return irq_find_mapping(data->host, cpm_vec);
 }
 
 static void cpm_cascade(struct irq_desc *desc)
@@ -110,7 +110,8 @@ static int cpm_pic_probe(struct platform_device *pdev)
 
 	out_be32(&data->reg->cpic_cimr, 0);
 
-	data->host = irq_domain_add_linear(dev->of_node, 64, &cpm_pic_host_ops, data);
+	data->host = irq_domain_create_linear(of_fwnode_handle(dev->of_node),
+					      64, &cpm_pic_host_ops, data);
 	if (!data->host)
 		return -ENODEV;
 
diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c
index 1dc095ad48fc..7462c221115c 100644
--- a/arch/powerpc/platforms/8xx/cpm1.c
+++ b/arch/powerpc/platforms/8xx/cpm1.c
@@ -417,7 +417,7 @@ static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, in
 	out_be16(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
 	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -428,6 +428,8 @@ static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
 	__cpm1_gpio16_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio)
@@ -497,7 +499,7 @@ int cpm1_gpiochip_add16(struct device *dev)
 	gc->direction_input = cpm1_gpio16_dir_in;
 	gc->direction_output = cpm1_gpio16_dir_out;
 	gc->get = cpm1_gpio16_get;
-	gc->set = cpm1_gpio16_set;
+	gc->set_rv = cpm1_gpio16_set;
 	gc->to_irq = cpm1_gpio16_to_irq;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
@@ -554,7 +556,7 @@ static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, in
 	out_be32(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
 	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -565,6 +567,8 @@ static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 	__cpm1_gpio32_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -618,7 +622,7 @@ int cpm1_gpiochip_add32(struct device *dev)
 	gc->direction_input = cpm1_gpio32_dir_in;
 	gc->direction_output = cpm1_gpio32_dir_out;
 	gc->get = cpm1_gpio32_get;
-	gc->set = cpm1_gpio32_set;
+	gc->set_rv = cpm1_gpio32_set;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c
index ea6b0e523c60..933d6ab7f512 100644
--- a/arch/powerpc/platforms/8xx/pic.c
+++ b/arch/powerpc/platforms/8xx/pic.c
@@ -80,7 +80,7 @@ unsigned int mpc8xx_get_irq(void)
 	if (irq == PIC_VEC_SPURRIOUS)
 		return 0;
 
-        return irq_linear_revmap(mpc8xx_pic_host, irq);
+        return irq_find_mapping(mpc8xx_pic_host, irq);
 
 }
 
@@ -146,7 +146,8 @@ void __init mpc8xx_pic_init(void)
 	if (!siu_reg)
 		goto out;
 
-	mpc8xx_pic_host = irq_domain_add_linear(np, 64, &mpc8xx_pic_host_ops, NULL);
+	mpc8xx_pic_host = irq_domain_create_linear(of_fwnode_handle(np), 64,
+						   &mpc8xx_pic_host_ops, NULL);
 	if (!mpc8xx_pic_host)
 		printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n");
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a454149ae02f..fea3766eac0f 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -70,10 +70,6 @@ config PPC_DT_CPU_FTRS
 	  firmware provides this binding.
 	  If you're not sure say Y.
 
-config UDBG_RTAS_CONSOLE
-	bool "RTAS based debug console"
-	depends on PPC_RTAS
-
 config PPC_SMP_MUXED_IPI
 	bool
 	help
@@ -186,12 +182,6 @@ config PPC_INDIRECT_PIO
 	bool
 	select GENERIC_IOMAP
 
-config PPC_INDIRECT_MMIO
-	bool
-
-config PPC_IO_WORKAROUNDS
-	bool
-
 source "drivers/cpufreq/Kconfig"
 
 menu "CPUIdle driver"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 1453ccc900c4..613b383ed8b3 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -449,6 +449,19 @@ config PPC_RADIX_MMU_DEFAULT
 
 	  If you're unsure, say Y.
 
+config PPC_RADIX_BROADCAST_TLBIE
+	bool
+	depends on PPC_RADIX_MMU
+	help
+	  Power ISA v3.0 and later implementations in the Linux Compliancy Subset
+	  and lower are not required to implement broadcast TLBIE instructions.
+	  Platforms with CPUs that do implement TLBIE broadcast, that is, where
+	  a TLB invalidation instruction performed on one CPU operates on the
+	  TLBs of all CPUs in the system, should select this option.  If this
+	  option is selected, the disable_tlbie kernel command line option can
+	  be used to cause global TLB invalidations to be done via IPIs; without
+	  it, IPIs will be used unconditionally.
+
 config PPC_KERNEL_PREFIXED
 	depends on PPC_HAVE_PREFIXED_SUPPORT
 	depends on CC_HAS_PREFIXED
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index 2c8dc0886912..33f852a7625f 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -109,7 +109,7 @@ static void __init amigaone_init_IRQ(void)
 
 	i8259_init(pic, int_ack);
 	ppc_md.get_irq = i8259_irq;
-	irq_set_default_host(i8259_get_host());
+	irq_set_default_domain(i8259_get_host());
 }
 
 static int __init request_isa_regions(void)
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 34669b060f36..db65bfcd1e74 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -3,42 +3,6 @@ config PPC_CELL
 	select PPC_64S_HASH_MMU if PPC64
 	bool
 
-config PPC_CELL_COMMON
-	bool
-	select PPC_CELL
-	select PPC_DCR_MMIO
-	select PPC_INDIRECT_PIO
-	select PPC_INDIRECT_MMIO
-	select PPC_HASH_MMU_NATIVE
-	select PPC_RTAS
-	select IRQ_EDGE_EOI_HANDLER
-
-config PPC_CELL_NATIVE
-	bool
-	select PPC_CELL_COMMON
-	select MPIC
-	select PPC_IO_WORKAROUNDS
-	select IBM_EMAC_EMAC4 if IBM_EMAC
-	select IBM_EMAC_RGMII if IBM_EMAC
-	select IBM_EMAC_ZMII if IBM_EMAC #test only
-	select IBM_EMAC_TAH if IBM_EMAC  #test only
-
-config PPC_IBM_CELL_BLADE
-	bool "IBM Cell Blade"
-	depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
-	select PPC_CELL_NATIVE
-	select PPC_OF_PLATFORM_PCI
-	select FORCE_PCI
-	select MMIO_NVRAM
-	select PPC_UDBG_16550
-	select UDBG_RTAS_CONSOLE
-
-config AXON_MSI
-	bool
-	depends on PPC_IBM_CELL_BLADE && PCI_MSI
-	select IRQ_DOMAIN_NOMAP
-	default y
-
 menu "Cell Broadband Engine options"
 	depends on PPC_CELL
 
@@ -57,48 +21,4 @@ config SPU_BASE
 	bool
 	select PPC_COPRO_BASE
 
-config CBE_RAS
-	bool "RAS features for bare metal Cell BE"
-	depends on PPC_CELL_NATIVE
-	default y
-
-config PPC_IBM_CELL_RESETBUTTON
-	bool "IBM Cell Blade Pinhole reset button"
-	depends on CBE_RAS && PPC_IBM_CELL_BLADE
-	default y
-	help
-	  Support Pinhole Resetbutton on IBM Cell blades.
-	  This adds a method to trigger system reset via front panel pinhole button.
-
-config PPC_IBM_CELL_POWERBUTTON
-	tristate "IBM Cell Blade power button"
-	depends on PPC_IBM_CELL_BLADE && INPUT_EVDEV
-	default y
-	help
-	  Support Powerbutton on IBM Cell blades.
-	  This will enable the powerbutton as an input device.
-
-config CBE_THERM
-	tristate "CBE thermal support"
-	default m
-	depends on CBE_RAS && SPU_BASE
-
-config PPC_PMI
-	tristate
-	default y
-	depends on CPU_FREQ_CBE_PMI || PPC_IBM_CELL_POWERBUTTON
-	help
-	  PMI (Platform Management Interrupt) is a way to
-	  communicate with the BMC (Baseboard Management Controller).
-	  It is used in some IBM Cell blades.
-
-config CBE_CPUFREQ_SPU_GOVERNOR
-	tristate "CBE frequency scaling based on SPU usage"
-	depends on SPU_FS && CPU_FREQ
-	default m
-	help
-	  This governor checks for spu usage to adjust the cpu frequency.
-	  If no spu is running on a given cpu, that cpu will be throttled to
-	  the minimal possible frequency.
-
 endmenu
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 7ea6692f67e2..7e5ff239c376 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,27 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_PPC_CELL_COMMON)		+= cbe_regs.o interrupt.o pervasive.o
-
-obj-$(CONFIG_PPC_CELL_NATIVE)		+= iommu.o setup.o spider-pic.o \
-					   pmu.o spider-pci.o
-obj-$(CONFIG_CBE_RAS)			+= ras.o
-
-obj-$(CONFIG_CBE_THERM)			+= cbe_thermal.o
-obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR)	+= cpufreq_spudemand.o
-
-obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON)	+= cbe_powerbutton.o
-
-ifdef CONFIG_SMP
-obj-$(CONFIG_PPC_CELL_NATIVE)		+= smp.o
-endif
-
-# needed only when building loadable spufs.ko
-spu-priv1-$(CONFIG_PPC_CELL_COMMON)	+= spu_priv1_mmio.o
-spu-manage-$(CONFIG_PPC_CELL_COMMON)	+= spu_manage.o
-
 obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
 					   spu_syscalls.o \
-					   $(spu-priv1-y) \
-					   $(spu-manage-y) \
 					   spufs/
-
-obj-$(CONFIG_AXON_MSI)			+= axon_msi.o
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
deleted file mode 100644
index d243f7fd8982..000000000000
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ /dev/null
@@ -1,481 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2007, Michael Ellerman, IBM Corporation.
- */
-
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <linux/debugfs.h>
-#include <linux/of.h>
-#include <linux/of_irq.h>
-#include <linux/platform_device.h>
-
-#include <asm/dcr.h>
-#include <asm/machdep.h>
-
-#include "cell.h"
-
-/*
- * MSIC registers, specified as offsets from dcr_base
- */
-#define MSIC_CTRL_REG	0x0
-
-/* Base Address registers specify FIFO location in BE memory */
-#define MSIC_BASE_ADDR_HI_REG	0x3
-#define MSIC_BASE_ADDR_LO_REG	0x4
-
-/* Hold the read/write offsets into the FIFO */
-#define MSIC_READ_OFFSET_REG	0x5
-#define MSIC_WRITE_OFFSET_REG	0x6
-
-
-/* MSIC control register flags */
-#define MSIC_CTRL_ENABLE		0x0001
-#define MSIC_CTRL_FIFO_FULL_ENABLE	0x0002
-#define MSIC_CTRL_IRQ_ENABLE		0x0008
-#define MSIC_CTRL_FULL_STOP_ENABLE	0x0010
-
-/*
- * The MSIC can be configured to use a FIFO of 32KB, 64KB, 128KB or 256KB.
- * Currently we're using a 64KB FIFO size.
- */
-#define MSIC_FIFO_SIZE_SHIFT	16
-#define MSIC_FIFO_SIZE_BYTES	(1 << MSIC_FIFO_SIZE_SHIFT)
-
-/*
- * To configure the FIFO size as (1 << n) bytes, we write (n - 15) into bits
- * 8-9 of the MSIC control reg.
- */
-#define MSIC_CTRL_FIFO_SIZE	(((MSIC_FIFO_SIZE_SHIFT - 15) << 8) & 0x300)
-
-/*
- * We need to mask the read/write offsets to make sure they stay within
- * the bounds of the FIFO. Also they should always be 16-byte aligned.
- */
-#define MSIC_FIFO_SIZE_MASK	((MSIC_FIFO_SIZE_BYTES - 1) & ~0xFu)
-
-/* Each entry in the FIFO is 16 bytes, the first 4 bytes hold the irq # */
-#define MSIC_FIFO_ENTRY_SIZE	0x10
-
-
-struct axon_msic {
-	struct irq_domain *irq_domain;
-	__le32 *fifo_virt;
-	dma_addr_t fifo_phys;
-	dcr_host_t dcr_host;
-	u32 read_offset;
-#ifdef DEBUG
-	u32 __iomem *trigger;
-#endif
-};
-
-#ifdef DEBUG
-void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic);
-#else
-static inline void axon_msi_debug_setup(struct device_node *dn,
-					struct axon_msic *msic) { }
-#endif
-
-
-static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
-{
-	pr_devel("axon_msi: dcr_write(0x%x, 0x%x)\n", val, dcr_n);
-
-	dcr_write(msic->dcr_host, dcr_n, val);
-}
-
-static void axon_msi_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct axon_msic *msic = irq_desc_get_handler_data(desc);
-	u32 write_offset, msi;
-	int idx;
-	int retry = 0;
-
-	write_offset = dcr_read(msic->dcr_host, MSIC_WRITE_OFFSET_REG);
-	pr_devel("axon_msi: original write_offset 0x%x\n", write_offset);
-
-	/* write_offset doesn't wrap properly, so we have to mask it */
-	write_offset &= MSIC_FIFO_SIZE_MASK;
-
-	while (msic->read_offset != write_offset && retry < 100) {
-		idx  = msic->read_offset / sizeof(__le32);
-		msi  = le32_to_cpu(msic->fifo_virt[idx]);
-		msi &= 0xFFFF;
-
-		pr_devel("axon_msi: woff %x roff %x msi %x\n",
-			  write_offset, msic->read_offset, msi);
-
-		if (msi < irq_get_nr_irqs() && irq_get_chip_data(msi) == msic) {
-			generic_handle_irq(msi);
-			msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
-		} else {
-			/*
-			 * Reading the MSIC_WRITE_OFFSET_REG does not
-			 * reliably flush the outstanding DMA to the
-			 * FIFO buffer. Here we were reading stale
-			 * data, so we need to retry.
-			 */
-			udelay(1);
-			retry++;
-			pr_devel("axon_msi: invalid irq 0x%x!\n", msi);
-			continue;
-		}
-
-		if (retry) {
-			pr_devel("axon_msi: late irq 0x%x, retry %d\n",
-				 msi, retry);
-			retry = 0;
-		}
-
-		msic->read_offset += MSIC_FIFO_ENTRY_SIZE;
-		msic->read_offset &= MSIC_FIFO_SIZE_MASK;
-	}
-
-	if (retry) {
-		printk(KERN_WARNING "axon_msi: irq timed out\n");
-
-		msic->read_offset += MSIC_FIFO_ENTRY_SIZE;
-		msic->read_offset &= MSIC_FIFO_SIZE_MASK;
-	}
-
-	chip->irq_eoi(&desc->irq_data);
-}
-
-static struct axon_msic *find_msi_translator(struct pci_dev *dev)
-{
-	struct irq_domain *irq_domain;
-	struct device_node *dn, *tmp;
-	const phandle *ph;
-	struct axon_msic *msic = NULL;
-
-	dn = of_node_get(pci_device_to_OF_node(dev));
-	if (!dn) {
-		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
-		return NULL;
-	}
-
-	for (; dn; dn = of_get_next_parent(dn)) {
-		ph = of_get_property(dn, "msi-translator", NULL);
-		if (ph)
-			break;
-	}
-
-	if (!ph) {
-		dev_dbg(&dev->dev,
-			"axon_msi: no msi-translator property found\n");
-		goto out_error;
-	}
-
-	tmp = dn;
-	dn = of_find_node_by_phandle(*ph);
-	of_node_put(tmp);
-	if (!dn) {
-		dev_dbg(&dev->dev,
-			"axon_msi: msi-translator doesn't point to a node\n");
-		goto out_error;
-	}
-
-	irq_domain = irq_find_host(dn);
-	if (!irq_domain) {
-		dev_dbg(&dev->dev, "axon_msi: no irq_domain found for node %pOF\n",
-			dn);
-		goto out_error;
-	}
-
-	msic = irq_domain->host_data;
-
-out_error:
-	of_node_put(dn);
-
-	return msic;
-}
-
-static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
-{
-	struct device_node *dn;
-	int len;
-	const u32 *prop;
-
-	dn = of_node_get(pci_device_to_OF_node(dev));
-	if (!dn) {
-		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
-		return -ENODEV;
-	}
-
-	for (; dn; dn = of_get_next_parent(dn)) {
-		if (!dev->no_64bit_msi) {
-			prop = of_get_property(dn, "msi-address-64", &len);
-			if (prop)
-				break;
-		}
-
-		prop = of_get_property(dn, "msi-address-32", &len);
-		if (prop)
-			break;
-	}
-
-	if (!prop) {
-		dev_dbg(&dev->dev,
-			"axon_msi: no msi-address-(32|64) properties found\n");
-		of_node_put(dn);
-		return -ENOENT;
-	}
-
-	switch (len) {
-	case 8:
-		msg->address_hi = prop[0];
-		msg->address_lo = prop[1];
-		break;
-	case 4:
-		msg->address_hi = 0;
-		msg->address_lo = prop[0];
-		break;
-	default:
-		dev_dbg(&dev->dev,
-			"axon_msi: malformed msi-address-(32|64) property\n");
-		of_node_put(dn);
-		return -EINVAL;
-	}
-
-	of_node_put(dn);
-
-	return 0;
-}
-
-static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	unsigned int virq, rc;
-	struct msi_desc *entry;
-	struct msi_msg msg;
-	struct axon_msic *msic;
-
-	msic = find_msi_translator(dev);
-	if (!msic)
-		return -ENODEV;
-
-	rc = setup_msi_msg_address(dev, &msg);
-	if (rc)
-		return rc;
-
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_NOTASSOCIATED) {
-		virq = irq_create_direct_mapping(msic->irq_domain);
-		if (!virq) {
-			dev_warn(&dev->dev,
-				 "axon_msi: virq allocation failed!\n");
-			return -1;
-		}
-		dev_dbg(&dev->dev, "axon_msi: allocated virq 0x%x\n", virq);
-
-		irq_set_msi_desc(virq, entry);
-		msg.data = virq;
-		pci_write_msi_msg(virq, &msg);
-	}
-
-	return 0;
-}
-
-static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
-{
-	struct msi_desc *entry;
-
-	dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n");
-
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ASSOCIATED) {
-		irq_set_msi_desc(entry->irq, NULL);
-		irq_dispose_mapping(entry->irq);
-		entry->irq = 0;
-	}
-}
-
-static struct irq_chip msic_irq_chip = {
-	.irq_mask	= pci_msi_mask_irq,
-	.irq_unmask	= pci_msi_unmask_irq,
-	.irq_shutdown	= pci_msi_mask_irq,
-	.name		= "AXON-MSI",
-};
-
-static int msic_host_map(struct irq_domain *h, unsigned int virq,
-			 irq_hw_number_t hw)
-{
-	irq_set_chip_data(virq, h->host_data);
-	irq_set_chip_and_handler(virq, &msic_irq_chip, handle_simple_irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops msic_host_ops = {
-	.map	= msic_host_map,
-};
-
-static void axon_msi_shutdown(struct platform_device *device)
-{
-	struct axon_msic *msic = dev_get_drvdata(&device->dev);
-	u32 tmp;
-
-	pr_devel("axon_msi: disabling %pOF\n",
-		 irq_domain_get_of_node(msic->irq_domain));
-	tmp  = dcr_read(msic->dcr_host, MSIC_CTRL_REG);
-	tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE;
-	msic_dcr_write(msic, MSIC_CTRL_REG, tmp);
-}
-
-static int axon_msi_probe(struct platform_device *device)
-{
-	struct device_node *dn = device->dev.of_node;
-	struct axon_msic *msic;
-	unsigned int virq;
-	int dcr_base, dcr_len;
-
-	pr_devel("axon_msi: setting up dn %pOF\n", dn);
-
-	msic = kzalloc(sizeof(*msic), GFP_KERNEL);
-	if (!msic) {
-		printk(KERN_ERR "axon_msi: couldn't allocate msic for %pOF\n",
-		       dn);
-		goto out;
-	}
-
-	dcr_base = dcr_resource_start(dn, 0);
-	dcr_len = dcr_resource_len(dn, 0);
-
-	if (dcr_base == 0 || dcr_len == 0) {
-		printk(KERN_ERR
-		       "axon_msi: couldn't parse dcr properties on %pOF\n",
-			dn);
-		goto out_free_msic;
-	}
-
-	msic->dcr_host = dcr_map(dn, dcr_base, dcr_len);
-	if (!DCR_MAP_OK(msic->dcr_host)) {
-		printk(KERN_ERR "axon_msi: dcr_map failed for %pOF\n",
-		       dn);
-		goto out_free_msic;
-	}
-
-	msic->fifo_virt = dma_alloc_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES,
-					     &msic->fifo_phys, GFP_KERNEL);
-	if (!msic->fifo_virt) {
-		printk(KERN_ERR "axon_msi: couldn't allocate fifo for %pOF\n",
-		       dn);
-		goto out_free_msic;
-	}
-
-	virq = irq_of_parse_and_map(dn, 0);
-	if (!virq) {
-		printk(KERN_ERR "axon_msi: irq parse and map failed for %pOF\n",
-		       dn);
-		goto out_free_fifo;
-	}
-	memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
-
-	/* We rely on being able to stash a virq in a u16, so limit irqs to < 65536 */
-	msic->irq_domain = irq_domain_add_nomap(dn, 65536, &msic_host_ops, msic);
-	if (!msic->irq_domain) {
-		printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %pOF\n",
-		       dn);
-		goto out_free_fifo;
-	}
-
-	irq_set_handler_data(virq, msic);
-	irq_set_chained_handler(virq, axon_msi_cascade);
-	pr_devel("axon_msi: irq 0x%x setup for axon_msi\n", virq);
-
-	/* Enable the MSIC hardware */
-	msic_dcr_write(msic, MSIC_BASE_ADDR_HI_REG, msic->fifo_phys >> 32);
-	msic_dcr_write(msic, MSIC_BASE_ADDR_LO_REG,
-				  msic->fifo_phys & 0xFFFFFFFF);
-	msic_dcr_write(msic, MSIC_CTRL_REG,
-			MSIC_CTRL_IRQ_ENABLE | MSIC_CTRL_ENABLE |
-			MSIC_CTRL_FIFO_SIZE);
-
-	msic->read_offset = dcr_read(msic->dcr_host, MSIC_WRITE_OFFSET_REG)
-				& MSIC_FIFO_SIZE_MASK;
-
-	dev_set_drvdata(&device->dev, msic);
-
-	cell_pci_controller_ops.setup_msi_irqs = axon_msi_setup_msi_irqs;
-	cell_pci_controller_ops.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
-
-	axon_msi_debug_setup(dn, msic);
-
-	printk(KERN_DEBUG "axon_msi: setup MSIC on %pOF\n", dn);
-
-	return 0;
-
-out_free_fifo:
-	dma_free_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, msic->fifo_virt,
-			  msic->fifo_phys);
-out_free_msic:
-	kfree(msic);
-out:
-
-	return -1;
-}
-
-static const struct of_device_id axon_msi_device_id[] = {
-	{
-		.compatible	= "ibm,axon-msic"
-	},
-	{}
-};
-
-static struct platform_driver axon_msi_driver = {
-	.probe		= axon_msi_probe,
-	.shutdown	= axon_msi_shutdown,
-	.driver = {
-		.name = "axon-msi",
-		.of_match_table = axon_msi_device_id,
-	},
-};
-
-static int __init axon_msi_init(void)
-{
-	return platform_driver_register(&axon_msi_driver);
-}
-subsys_initcall(axon_msi_init);
-
-
-#ifdef DEBUG
-static int msic_set(void *data, u64 val)
-{
-	struct axon_msic *msic = data;
-	out_le32(msic->trigger, val);
-	return 0;
-}
-
-static int msic_get(void *data, u64 *val)
-{
-	*val = 0;
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(fops_msic, msic_get, msic_set, "%llu\n");
-
-void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic)
-{
-	char name[8];
-	struct resource res;
-
-	if (of_address_to_resource(dn, 0, &res)) {
-		pr_devel("axon_msi: couldn't get reg property\n");
-		return;
-	}
-
-	msic->trigger = ioremap(res.start, 0x4);
-	if (!msic->trigger) {
-		pr_devel("axon_msi: ioremap failed\n");
-		return;
-	}
-
-	snprintf(name, sizeof(name), "msic_%d", of_node_to_nid(dn));
-
-	debugfs_create_file(name, 0600, arch_debugfs_dir, msic, &fops_msic);
-}
-#endif /* DEBUG */
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
deleted file mode 100644
index 3d121acdf69b..000000000000
--- a/arch/powerpc/platforms/cell/cbe_powerbutton.c
+++ /dev/null
@@ -1,106 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * driver for powerbutton on IBM cell blades
- *
- * (C) Copyright IBM Corp. 2005-2008
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/input.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <asm/pmi.h>
-
-static struct input_dev *button_dev;
-static struct platform_device *button_pdev;
-
-static void cbe_powerbutton_handle_pmi(pmi_message_t pmi_msg)
-{
-	BUG_ON(pmi_msg.type != PMI_TYPE_POWER_BUTTON);
-
-	input_report_key(button_dev, KEY_POWER, 1);
-	input_sync(button_dev);
-	input_report_key(button_dev, KEY_POWER, 0);
-	input_sync(button_dev);
-}
-
-static struct pmi_handler cbe_pmi_handler = {
-	.type			= PMI_TYPE_POWER_BUTTON,
-	.handle_pmi_message	= cbe_powerbutton_handle_pmi,
-};
-
-static int __init cbe_powerbutton_init(void)
-{
-	int ret = 0;
-	struct input_dev *dev;
-
-	if (!of_machine_is_compatible("IBM,CBPLUS-1.0")) {
-		printk(KERN_ERR "%s: Not a cell blade.\n", __func__);
-		ret = -ENODEV;
-		goto out;
-	}
-
-	dev = input_allocate_device();
-	if (!dev) {
-		ret = -ENOMEM;
-		printk(KERN_ERR "%s: Not enough memory.\n", __func__);
-		goto out;
-	}
-
-	set_bit(EV_KEY, dev->evbit);
-	set_bit(KEY_POWER, dev->keybit);
-
-	dev->name = "Power Button";
-	dev->id.bustype = BUS_HOST;
-
-	/* this makes the button look like an acpi power button
-	 * no clue whether anyone relies on that though */
-	dev->id.product = 0x02;
-	dev->phys = "LNXPWRBN/button/input0";
-
-	button_pdev = platform_device_register_simple("power_button", 0, NULL, 0);
-	if (IS_ERR(button_pdev)) {
-		ret = PTR_ERR(button_pdev);
-		goto out_free_input;
-	}
-
-	dev->dev.parent = &button_pdev->dev;
-	ret = input_register_device(dev);
-	if (ret) {
-		printk(KERN_ERR "%s: Failed to register device\n", __func__);
-		goto out_free_pdev;
-	}
-
-	button_dev = dev;
-
-	ret = pmi_register_handler(&cbe_pmi_handler);
-	if (ret) {
-		printk(KERN_ERR "%s: Failed to register with pmi.\n", __func__);
-		goto out_free_pdev;
-	}
-
-	goto out;
-
-out_free_pdev:
-	platform_device_unregister(button_pdev);
-out_free_input:
-	input_free_device(dev);
-out:
-	return ret;
-}
-
-static void __exit cbe_powerbutton_exit(void)
-{
-	pmi_unregister_handler(&cbe_pmi_handler);
-	platform_device_unregister(button_pdev);
-	input_free_device(button_dev);
-}
-
-module_init(cbe_powerbutton_init);
-module_exit(cbe_powerbutton_exit);
-
-MODULE_DESCRIPTION("Driver for powerbutton on IBM cell blades");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
deleted file mode 100644
index 99b3558753e9..000000000000
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ /dev/null
@@ -1,298 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * cbe_regs.c
- *
- * Accessor routines for the various MMIO register blocks of the CBE
- *
- * (c) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
- */
-
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/export.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/ptrace.h>
-#include <asm/cell-regs.h>
-
-/*
- * Current implementation uses "cpu" nodes. We build our own mapping
- * array of cpu numbers to cpu nodes locally for now to allow interrupt
- * time code to have a fast path rather than call of_get_cpu_node(). If
- * we implement cpu hotplug, we'll have to install an appropriate notifier
- * in order to release references to the cpu going away
- */
-static struct cbe_regs_map
-{
-	struct device_node *cpu_node;
-	struct device_node *be_node;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	struct cbe_iic_regs __iomem *iic_regs;
-	struct cbe_mic_tm_regs __iomem *mic_tm_regs;
-	struct cbe_pmd_shadow_regs pmd_shadow_regs;
-} cbe_regs_maps[MAX_CBE];
-static int cbe_regs_map_count;
-
-static struct cbe_thread_map
-{
-	struct device_node *cpu_node;
-	struct device_node *be_node;
-	struct cbe_regs_map *regs;
-	unsigned int thread_id;
-	unsigned int cbe_id;
-} cbe_thread_map[NR_CPUS];
-
-static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = {CPU_BITS_NONE} };
-static cpumask_t cbe_first_online_cpu = { CPU_BITS_NONE };
-
-static struct cbe_regs_map *cbe_find_map(struct device_node *np)
-{
-	int i;
-	struct device_node *tmp_np;
-
-	if (!of_node_is_type(np, "spe")) {
-		for (i = 0; i < cbe_regs_map_count; i++)
-			if (cbe_regs_maps[i].cpu_node == np ||
-			    cbe_regs_maps[i].be_node == np)
-				return &cbe_regs_maps[i];
-		return NULL;
-	}
-
-	if (np->data)
-		return np->data;
-
-	/* walk up path until cpu or be node was found */
-	tmp_np = np;
-	do {
-		tmp_np = tmp_np->parent;
-		/* on a correct devicetree we wont get up to root */
-		BUG_ON(!tmp_np);
-	} while (!of_node_is_type(tmp_np, "cpu") ||
-		 !of_node_is_type(tmp_np, "be"));
-
-	np->data = cbe_find_map(tmp_np);
-
-	return np->data;
-}
-
-struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->pmd_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_pmd_regs);
-
-struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->pmd_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_cpu_pmd_regs);
-
-struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return &map->pmd_shadow_regs;
-}
-
-struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return &map->pmd_shadow_regs;
-}
-
-struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->iic_regs;
-}
-
-struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->iic_regs;
-}
-
-struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->mic_tm_regs;
-}
-
-struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->mic_tm_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_cpu_mic_tm_regs);
-
-u32 cbe_get_hw_thread_id(int cpu)
-{
-	return cbe_thread_map[cpu].thread_id;
-}
-EXPORT_SYMBOL_GPL(cbe_get_hw_thread_id);
-
-u32 cbe_cpu_to_node(int cpu)
-{
-	return cbe_thread_map[cpu].cbe_id;
-}
-EXPORT_SYMBOL_GPL(cbe_cpu_to_node);
-
-u32 cbe_node_to_cpu(int node)
-{
-	return cpumask_first(&cbe_local_mask[node]);
-
-}
-EXPORT_SYMBOL_GPL(cbe_node_to_cpu);
-
-static struct device_node *__init cbe_get_be_node(int cpu_id)
-{
-	struct device_node *np;
-
-	for_each_node_by_type (np, "be") {
-		int len,i;
-		const phandle *cpu_handle;
-
-		cpu_handle = of_get_property(np, "cpus", &len);
-
-		/*
-		 * the CAB SLOF tree is non compliant, so we just assume
-		 * there is only one node
-		 */
-		if (WARN_ON_ONCE(!cpu_handle))
-			return np;
-
-		for (i = 0; i < len; i++) {
-			struct device_node *ch_np = of_find_node_by_phandle(cpu_handle[i]);
-			struct device_node *ci_np = of_get_cpu_node(cpu_id, NULL);
-
-			of_node_put(ch_np);
-			of_node_put(ci_np);
-
-			if (ch_np == ci_np)
-				return np;
-		}
-	}
-
-	return NULL;
-}
-
-static void __init cbe_fill_regs_map(struct cbe_regs_map *map)
-{
-	if(map->be_node) {
-		struct device_node *be, *np, *parent_np;
-
-		be = map->be_node;
-
-		for_each_node_by_type(np, "pervasive") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->pmd_regs = of_iomap(np, 0);
-			of_node_put(parent_np);
-		}
-
-		for_each_node_by_type(np, "CBEA-Internal-Interrupt-Controller") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->iic_regs = of_iomap(np, 2);
-			of_node_put(parent_np);
-		}
-
-		for_each_node_by_type(np, "mic-tm") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->mic_tm_regs = of_iomap(np, 0);
-			of_node_put(parent_np);
-		}
-	} else {
-		struct device_node *cpu;
-		/* That hack must die die die ! */
-		const struct address_prop {
-			unsigned long address;
-			unsigned int len;
-		} __attribute__((packed)) *prop;
-
-		cpu = map->cpu_node;
-
-		prop = of_get_property(cpu, "pervasive", NULL);
-		if (prop != NULL)
-			map->pmd_regs = ioremap(prop->address, prop->len);
-
-		prop = of_get_property(cpu, "iic", NULL);
-		if (prop != NULL)
-			map->iic_regs = ioremap(prop->address, prop->len);
-
-		prop = of_get_property(cpu, "mic-tm", NULL);
-		if (prop != NULL)
-			map->mic_tm_regs = ioremap(prop->address, prop->len);
-	}
-}
-
-
-void __init cbe_regs_init(void)
-{
-	int i;
-	unsigned int thread_id;
-	struct device_node *cpu;
-
-	/* Build local fast map of CPUs */
-	for_each_possible_cpu(i) {
-		cbe_thread_map[i].cpu_node = of_get_cpu_node(i, &thread_id);
-		cbe_thread_map[i].be_node = cbe_get_be_node(i);
-		cbe_thread_map[i].thread_id = thread_id;
-	}
-
-	/* Find maps for each device tree CPU */
-	for_each_node_by_type(cpu, "cpu") {
-		struct cbe_regs_map *map;
-		unsigned int cbe_id;
-
-		cbe_id = cbe_regs_map_count++;
-		map = &cbe_regs_maps[cbe_id];
-
-		if (cbe_regs_map_count > MAX_CBE) {
-			printk(KERN_ERR "cbe_regs: More BE chips than supported"
-			       "!\n");
-			cbe_regs_map_count--;
-			of_node_put(cpu);
-			return;
-		}
-		of_node_put(map->cpu_node);
-		map->cpu_node = of_node_get(cpu);
-
-		for_each_possible_cpu(i) {
-			struct cbe_thread_map *thread = &cbe_thread_map[i];
-
-			if (thread->cpu_node == cpu) {
-				thread->regs = map;
-				thread->cbe_id = cbe_id;
-				map->be_node = thread->be_node;
-				cpumask_set_cpu(i, &cbe_local_mask[cbe_id]);
-				if(thread->thread_id == 0)
-					cpumask_set_cpu(i, &cbe_first_online_cpu);
-			}
-		}
-
-		cbe_fill_regs_map(map);
-	}
-}
-
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
deleted file mode 100644
index c295c6714f9b..000000000000
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ /dev/null
@@ -1,387 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * thermal support for the cell processor
- *
- * This module adds some sysfs attributes to cpu and spu nodes.
- * Base for measurements are the digital thermal sensors (DTS)
- * located on the chip.
- * The accuracy is 2 degrees, starting from 65 up to 125 degrees celsius
- * The attributes can be found under
- * /sys/devices/system/cpu/cpuX/thermal
- * /sys/devices/system/spu/spuX/thermal
- *
- * The following attributes are added for each node:
- * temperature:
- *	contains the current temperature measured by the DTS
- * throttle_begin:
- *	throttling begins when temperature is greater or equal to
- *	throttle_begin. Setting this value to 125 prevents throttling.
- * throttle_end:
- *	throttling is being ceased, if the temperature is lower than
- *	throttle_end. Due to a delay between applying throttling and
- *	a reduced temperature this value should be less than throttle_begin.
- *	A value equal to throttle_begin provides only a very little hysteresis.
- * throttle_full_stop:
- *	If the temperatrue is greater or equal to throttle_full_stop,
- *	full throttling is applied to the cpu or spu. This value should be
- *	greater than throttle_begin and throttle_end. Setting this value to
- *	65 prevents the unit from running code at all.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/cpu.h>
-#include <linux/stringify.h>
-#include <asm/spu.h>
-#include <asm/io.h>
-#include <asm/cell-regs.h>
-
-#include "spu_priv1_mmio.h"
-
-#define TEMP_MIN 65
-#define TEMP_MAX 125
-
-#define DEVICE_PREFIX_ATTR(_prefix,_name,_mode)			\
-struct device_attribute attr_ ## _prefix ## _ ## _name = {	\
-	.attr = { .name = __stringify(_name), .mode = _mode },	\
-	.show	= _prefix ## _show_ ## _name,			\
-	.store	= _prefix ## _store_ ## _name,			\
-};
-
-static inline u8 reg_to_temp(u8 reg_value)
-{
-	return ((reg_value & 0x3f) << 1) + TEMP_MIN;
-}
-
-static inline u8 temp_to_reg(u8 temp)
-{
-	return ((temp - TEMP_MIN) >> 1) & 0x3f;
-}
-
-static struct cbe_pmd_regs __iomem *get_pmd_regs(struct device *dev)
-{
-	struct spu *spu;
-
-	spu = container_of(dev, struct spu, dev);
-
-	return cbe_get_pmd_regs(spu_devnode(spu));
-}
-
-/* returns the value for a given spu in a given register */
-static u8 spu_read_register_value(struct device *dev, union spe_reg __iomem *reg)
-{
-	union spe_reg value;
-	struct spu *spu;
-
-	spu = container_of(dev, struct spu, dev);
-	value.val = in_be64(&reg->val);
-
-	return value.spe[spu->spe_id];
-}
-
-static ssize_t spu_show_temp(struct device *dev, struct device_attribute *attr,
-			char *buf)
-{
-	u8 value;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-
-	pmd_regs = get_pmd_regs(dev);
-
-	value = spu_read_register_value(dev, &pmd_regs->ts_ctsr1);
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-static ssize_t show_throttle(struct cbe_pmd_regs __iomem *pmd_regs, char *buf, int pos)
-{
-	u64 value;
-
-	value = in_be64(&pmd_regs->tm_tpr.val);
-	/* access the corresponding byte */
-	value >>= pos;
-	value &= 0x3F;
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-static ssize_t store_throttle(struct cbe_pmd_regs __iomem *pmd_regs, const char *buf, size_t size, int pos)
-{
-	u64 reg_value;
-	unsigned int temp;
-	u64 new_value;
-	int ret;
-
-	ret = sscanf(buf, "%u", &temp);
-
-	if (ret != 1 || temp < TEMP_MIN || temp > TEMP_MAX)
-		return -EINVAL;
-
-	new_value = temp_to_reg(temp);
-
-	reg_value = in_be64(&pmd_regs->tm_tpr.val);
-
-	/* zero out bits for new value */
-	reg_value &= ~(0xffull << pos);
-	/* set bits to new value */
-	reg_value |= new_value << pos;
-
-	out_be64(&pmd_regs->tm_tpr.val, reg_value);
-	return size;
-}
-
-static ssize_t spu_show_throttle_end(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 0);
-}
-
-static ssize_t spu_show_throttle_begin(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 8);
-}
-
-static ssize_t spu_show_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 16);
-}
-
-static ssize_t spu_store_throttle_end(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 0);
-}
-
-static ssize_t spu_store_throttle_begin(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 8);
-}
-
-static ssize_t spu_store_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 16);
-}
-
-static ssize_t ppe_show_temp(struct device *dev, char *buf, int pos)
-{
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	u64 value;
-
-	pmd_regs = cbe_get_cpu_pmd_regs(dev->id);
-	value = in_be64(&pmd_regs->ts_ctsr2);
-
-	value = (value >> pos) & 0x3f;
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-
-/* shows the temperature of the DTS on the PPE,
- * located near the linear thermal sensor */
-static ssize_t ppe_show_temp0(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return ppe_show_temp(dev, buf, 32);
-}
-
-/* shows the temperature of the second DTS on the PPE */
-static ssize_t ppe_show_temp1(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return ppe_show_temp(dev, buf, 0);
-}
-
-static ssize_t ppe_show_throttle_end(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 32);
-}
-
-static ssize_t ppe_show_throttle_begin(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 40);
-}
-
-static ssize_t ppe_show_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 48);
-}
-
-static ssize_t ppe_store_throttle_end(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 32);
-}
-
-static ssize_t ppe_store_throttle_begin(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 40);
-}
-
-static ssize_t ppe_store_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 48);
-}
-
-
-static struct device_attribute attr_spu_temperature = {
-	.attr = {.name = "temperature", .mode = 0400 },
-	.show = spu_show_temp,
-};
-
-static DEVICE_PREFIX_ATTR(spu, throttle_end, 0600);
-static DEVICE_PREFIX_ATTR(spu, throttle_begin, 0600);
-static DEVICE_PREFIX_ATTR(spu, throttle_full_stop, 0600);
-
-
-static struct attribute *spu_attributes[] = {
-	&attr_spu_temperature.attr,
-	&attr_spu_throttle_end.attr,
-	&attr_spu_throttle_begin.attr,
-	&attr_spu_throttle_full_stop.attr,
-	NULL,
-};
-
-static const struct attribute_group spu_attribute_group = {
-	.name	= "thermal",
-	.attrs	= spu_attributes,
-};
-
-static struct device_attribute attr_ppe_temperature0 = {
-	.attr = {.name = "temperature0", .mode = 0400 },
-	.show = ppe_show_temp0,
-};
-
-static struct device_attribute attr_ppe_temperature1 = {
-	.attr = {.name = "temperature1", .mode = 0400 },
-	.show = ppe_show_temp1,
-};
-
-static DEVICE_PREFIX_ATTR(ppe, throttle_end, 0600);
-static DEVICE_PREFIX_ATTR(ppe, throttle_begin, 0600);
-static DEVICE_PREFIX_ATTR(ppe, throttle_full_stop, 0600);
-
-static struct attribute *ppe_attributes[] = {
-	&attr_ppe_temperature0.attr,
-	&attr_ppe_temperature1.attr,
-	&attr_ppe_throttle_end.attr,
-	&attr_ppe_throttle_begin.attr,
-	&attr_ppe_throttle_full_stop.attr,
-	NULL,
-};
-
-static struct attribute_group ppe_attribute_group = {
-	.name	= "thermal",
-	.attrs	= ppe_attributes,
-};
-
-/*
- * initialize throttling with default values
- */
-static int __init init_default_values(void)
-{
-	int cpu;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	struct device *dev;
-	union ppe_spe_reg tpr;
-	union spe_reg str1;
-	u64 str2;
-	union spe_reg cr1;
-	u64 cr2;
-
-	/* TPR defaults */
-	/* ppe
-	 *	1F - no full stop
-	 *	08 - dynamic throttling starts if over 80 degrees
-	 *	03 - dynamic throttling ceases if below 70 degrees */
-	tpr.ppe = 0x1F0803;
-	/* spe
-	 *	10 - full stopped when over 96 degrees
-	 *	08 - dynamic throttling starts if over 80 degrees
-	 *	03 - dynamic throttling ceases if below 70 degrees
-	 */
-	tpr.spe = 0x100803;
-
-	/* STR defaults */
-	/* str1
-	 *	10 - stop 16 of 32 cycles
-	 */
-	str1.val = 0x1010101010101010ull;
-	/* str2
-	 *	10 - stop 16 of 32 cycles
-	 */
-	str2 = 0x10;
-
-	/* CR defaults */
-	/* cr1
-	 *	4 - normal operation
-	 */
-	cr1.val = 0x0404040404040404ull;
-	/* cr2
-	 *	4 - normal operation
-	 */
-	cr2 = 0x04;
-
-	for_each_possible_cpu (cpu) {
-		pr_debug("processing cpu %d\n", cpu);
-		dev = get_cpu_device(cpu);
-
-		if (!dev) {
-			pr_info("invalid dev pointer for cbe_thermal\n");
-			return -EINVAL;
-		}
-
-		pmd_regs = cbe_get_cpu_pmd_regs(dev->id);
-
-		if (!pmd_regs) {
-			pr_info("invalid CBE regs pointer for cbe_thermal\n");
-			return -EINVAL;
-		}
-
-		out_be64(&pmd_regs->tm_str2, str2);
-		out_be64(&pmd_regs->tm_str1.val, str1.val);
-		out_be64(&pmd_regs->tm_tpr.val, tpr.val);
-		out_be64(&pmd_regs->tm_cr1.val, cr1.val);
-		out_be64(&pmd_regs->tm_cr2, cr2);
-	}
-
-	return 0;
-}
-
-
-static int __init thermal_init(void)
-{
-	int rc = init_default_values();
-
-	if (rc == 0) {
-		spu_add_dev_attr_group(&spu_attribute_group);
-		cpu_add_dev_attr_group(&ppe_attribute_group);
-	}
-
-	return rc;
-}
-module_init(thermal_init);
-
-static void __exit thermal_exit(void)
-{
-	spu_remove_dev_attr_group(&spu_attribute_group);
-	cpu_remove_dev_attr_group(&ppe_attribute_group);
-}
-module_exit(thermal_exit);
-
-MODULE_DESCRIPTION("Cell processor thermal driver");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-
diff --git a/arch/powerpc/platforms/cell/cell.h b/arch/powerpc/platforms/cell/cell.h
deleted file mode 100644
index d5142e905ab3..000000000000
--- a/arch/powerpc/platforms/cell/cell.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Cell Platform common data structures
- *
- * Copyright 2015, Daniel Axtens, IBM Corporation
- */
-
-#ifndef CELL_H
-#define CELL_H
-
-#include <asm/pci-bridge.h>
-
-extern struct pci_controller_ops cell_pci_controller_ops;
-
-#endif
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
deleted file mode 100644
index 79172ba36eca..000000000000
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ /dev/null
@@ -1,134 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * spu aware cpufreq governor for the cell processor
- *
- * © Copyright IBM Corporation 2006-2008
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/cpufreq.h>
-#include <linux/sched.h>
-#include <linux/sched/loadavg.h>
-#include <linux/module.h>
-#include <linux/timer.h>
-#include <linux/workqueue.h>
-#include <linux/atomic.h>
-#include <asm/machdep.h>
-#include <asm/spu.h>
-
-#define POLL_TIME	100000		/* in µs */
-#define EXP		753		/* exp(-1) in fixed-point */
-
-struct spu_gov_info_struct {
-	unsigned long busy_spus;	/* fixed-point */
-	struct cpufreq_policy *policy;
-	struct delayed_work work;
-	unsigned int poll_int;		/* µs */
-};
-static DEFINE_PER_CPU(struct spu_gov_info_struct, spu_gov_info);
-
-static int calc_freq(struct spu_gov_info_struct *info)
-{
-	int cpu;
-	int busy_spus;
-
-	cpu = info->policy->cpu;
-	busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
-
-	info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1);
-	pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n",
-			cpu, busy_spus, info->busy_spus);
-
-	return info->policy->max * info->busy_spus / FIXED_1;
-}
-
-static void spu_gov_work(struct work_struct *work)
-{
-	struct spu_gov_info_struct *info;
-	int delay;
-	unsigned long target_freq;
-
-	info = container_of(work, struct spu_gov_info_struct, work.work);
-
-	/* after cancel_delayed_work_sync we unset info->policy */
-	BUG_ON(info->policy == NULL);
-
-	target_freq = calc_freq(info);
-	__cpufreq_driver_target(info->policy, target_freq, CPUFREQ_RELATION_H);
-
-	delay = usecs_to_jiffies(info->poll_int);
-	schedule_delayed_work_on(info->policy->cpu, &info->work, delay);
-}
-
-static void spu_gov_init_work(struct spu_gov_info_struct *info)
-{
-	int delay = usecs_to_jiffies(info->poll_int);
-	INIT_DEFERRABLE_WORK(&info->work, spu_gov_work);
-	schedule_delayed_work_on(info->policy->cpu, &info->work, delay);
-}
-
-static void spu_gov_cancel_work(struct spu_gov_info_struct *info)
-{
-	cancel_delayed_work_sync(&info->work);
-}
-
-static int spu_gov_start(struct cpufreq_policy *policy)
-{
-	unsigned int cpu = policy->cpu;
-	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
-	struct spu_gov_info_struct *affected_info;
-	int i;
-
-	if (!cpu_online(cpu)) {
-		printk(KERN_ERR "cpu %d is not online\n", cpu);
-		return -EINVAL;
-	}
-
-	if (!policy->cur) {
-		printk(KERN_ERR "no cpu specified in policy\n");
-		return -EINVAL;
-	}
-
-	/* initialize spu_gov_info for all affected cpus */
-	for_each_cpu(i, policy->cpus) {
-		affected_info = &per_cpu(spu_gov_info, i);
-		affected_info->policy = policy;
-	}
-
-	info->poll_int = POLL_TIME;
-
-	/* setup timer */
-	spu_gov_init_work(info);
-
-	return 0;
-}
-
-static void spu_gov_stop(struct cpufreq_policy *policy)
-{
-	unsigned int cpu = policy->cpu;
-	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
-	int i;
-
-	/* cancel timer */
-	spu_gov_cancel_work(info);
-
-	/* clean spu_gov_info for all affected cpus */
-	for_each_cpu (i, policy->cpus) {
-		info = &per_cpu(spu_gov_info, i);
-		info->policy = NULL;
-	}
-}
-
-static struct cpufreq_governor spu_governor = {
-	.name = "spudemand",
-	.start = spu_gov_start,
-	.stop = spu_gov_stop,
-	.owner = THIS_MODULE,
-};
-cpufreq_governor_init(spu_governor);
-cpufreq_governor_exit(spu_governor);
-
-MODULE_DESCRIPTION("SPU-aware cpufreq governor for the cell processor");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
deleted file mode 100644
index 03ee8152ee97..000000000000
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ /dev/null
@@ -1,390 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cell Internal Interrupt Controller
- *
- * Copyright (C) 2006 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *                    IBM, Corp.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * TODO:
- * - Fix various assumptions related to HW CPU numbers vs. linux CPU numbers
- *   vs node numbers in the setup code
- * - Implement proper handling of maxcpus=1/2 (that is, routing of irqs from
- *   a non-active node to the active node)
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/export.h>
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/ioport.h>
-#include <linux/kernel_stat.h>
-#include <linux/pgtable.h>
-#include <linux/of_address.h>
-
-#include <asm/io.h>
-#include <asm/ptrace.h>
-#include <asm/machdep.h>
-#include <asm/cell-regs.h>
-
-#include "interrupt.h"
-
-struct iic {
-	struct cbe_iic_thread_regs __iomem *regs;
-	u8 target_id;
-	u8 eoi_stack[16];
-	int eoi_ptr;
-	struct device_node *node;
-};
-
-static DEFINE_PER_CPU(struct iic, cpu_iic);
-#define IIC_NODE_COUNT	2
-static struct irq_domain *iic_host;
-
-/* Convert between "pending" bits and hw irq number */
-static irq_hw_number_t iic_pending_to_hwnum(struct cbe_iic_pending_bits bits)
-{
-	unsigned char unit = bits.source & 0xf;
-	unsigned char node = bits.source >> 4;
-	unsigned char class = bits.class & 3;
-
-	/* Decode IPIs */
-	if (bits.flags & CBE_IIC_IRQ_IPI)
-		return IIC_IRQ_TYPE_IPI | (bits.prio >> 4);
-	else
-		return (node << IIC_IRQ_NODE_SHIFT) | (class << 4) | unit;
-}
-
-static void iic_mask(struct irq_data *d)
-{
-}
-
-static void iic_unmask(struct irq_data *d)
-{
-}
-
-static void iic_eoi(struct irq_data *d)
-{
-	struct iic *iic = this_cpu_ptr(&cpu_iic);
-	out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]);
-	BUG_ON(iic->eoi_ptr < 0);
-}
-
-static struct irq_chip iic_chip = {
-	.name = "CELL-IIC",
-	.irq_mask = iic_mask,
-	.irq_unmask = iic_unmask,
-	.irq_eoi = iic_eoi,
-};
-
-
-static void iic_ioexc_eoi(struct irq_data *d)
-{
-}
-
-static void iic_ioexc_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct cbe_iic_regs __iomem *node_iic =
-		(void __iomem *)irq_desc_get_handler_data(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
-	unsigned int base = (irq & 0xffffff00) | IIC_IRQ_TYPE_IOEXC;
-	unsigned long bits, ack;
-	int cascade;
-
-	for (;;) {
-		bits = in_be64(&node_iic->iic_is);
-		if (bits == 0)
-			break;
-		/* pre-ack edge interrupts */
-		ack = bits & IIC_ISR_EDGE_MASK;
-		if (ack)
-			out_be64(&node_iic->iic_is, ack);
-		/* handle them */
-		for (cascade = 63; cascade >= 0; cascade--)
-			if (bits & (0x8000000000000000UL >> cascade))
-				generic_handle_domain_irq(iic_host,
-							  base | cascade);
-		/* post-ack level interrupts */
-		ack = bits & ~IIC_ISR_EDGE_MASK;
-		if (ack)
-			out_be64(&node_iic->iic_is, ack);
-	}
-	chip->irq_eoi(&desc->irq_data);
-}
-
-
-static struct irq_chip iic_ioexc_chip = {
-	.name = "CELL-IOEX",
-	.irq_mask = iic_mask,
-	.irq_unmask = iic_unmask,
-	.irq_eoi = iic_ioexc_eoi,
-};
-
-/* Get an IRQ number from the pending state register of the IIC */
-static unsigned int iic_get_irq(void)
-{
-	struct cbe_iic_pending_bits pending;
-	struct iic *iic;
-	unsigned int virq;
-
-	iic = this_cpu_ptr(&cpu_iic);
-	*(unsigned long *) &pending =
-		in_be64((u64 __iomem *) &iic->regs->pending_destr);
-	if (!(pending.flags & CBE_IIC_IRQ_VALID))
-		return 0;
-	virq = irq_linear_revmap(iic_host, iic_pending_to_hwnum(pending));
-	if (!virq)
-		return 0;
-	iic->eoi_stack[++iic->eoi_ptr] = pending.prio;
-	BUG_ON(iic->eoi_ptr > 15);
-	return virq;
-}
-
-void iic_setup_cpu(void)
-{
-	out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff);
-}
-
-u8 iic_get_target_id(int cpu)
-{
-	return per_cpu(cpu_iic, cpu).target_id;
-}
-
-EXPORT_SYMBOL_GPL(iic_get_target_id);
-
-#ifdef CONFIG_SMP
-
-/* Use the highest interrupt priorities for IPI */
-static inline int iic_msg_to_irq(int msg)
-{
-	return IIC_IRQ_TYPE_IPI + 0xf - msg;
-}
-
-void iic_message_pass(int cpu, int msg)
-{
-	out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - msg) << 4);
-}
-
-static void iic_request_ipi(int msg)
-{
-	int virq;
-
-	virq = irq_create_mapping(iic_host, iic_msg_to_irq(msg));
-	if (!virq) {
-		printk(KERN_ERR
-		       "iic: failed to map IPI %s\n", smp_ipi_name[msg]);
-		return;
-	}
-
-	/*
-	 * If smp_request_message_ipi encounters an error it will notify
-	 * the error.  If a message is not needed it will return non-zero.
-	 */
-	if (smp_request_message_ipi(virq, msg))
-		irq_dispose_mapping(virq);
-}
-
-void iic_request_IPIs(void)
-{
-	iic_request_ipi(PPC_MSG_CALL_FUNCTION);
-	iic_request_ipi(PPC_MSG_RESCHEDULE);
-	iic_request_ipi(PPC_MSG_TICK_BROADCAST);
-	iic_request_ipi(PPC_MSG_NMI_IPI);
-}
-
-#endif /* CONFIG_SMP */
-
-
-static int iic_host_match(struct irq_domain *h, struct device_node *node,
-			  enum irq_domain_bus_token bus_token)
-{
-	return of_device_is_compatible(node,
-				    "IBM,CBEA-Internal-Interrupt-Controller");
-}
-
-static int iic_host_map(struct irq_domain *h, unsigned int virq,
-			irq_hw_number_t hw)
-{
-	switch (hw & IIC_IRQ_TYPE_MASK) {
-	case IIC_IRQ_TYPE_IPI:
-		irq_set_chip_and_handler(virq, &iic_chip, handle_percpu_irq);
-		break;
-	case IIC_IRQ_TYPE_IOEXC:
-		irq_set_chip_and_handler(virq, &iic_ioexc_chip,
-					 handle_edge_eoi_irq);
-		break;
-	default:
-		irq_set_chip_and_handler(virq, &iic_chip, handle_edge_eoi_irq);
-	}
-	return 0;
-}
-
-static int iic_host_xlate(struct irq_domain *h, struct device_node *ct,
-			   const u32 *intspec, unsigned int intsize,
-			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-
-{
-	unsigned int node, ext, unit, class;
-	const u32 *val;
-
-	if (!of_device_is_compatible(ct,
-				     "IBM,CBEA-Internal-Interrupt-Controller"))
-		return -ENODEV;
-	if (intsize != 1)
-		return -ENODEV;
-	val = of_get_property(ct, "#interrupt-cells", NULL);
-	if (val == NULL || *val != 1)
-		return -ENODEV;
-
-	node = intspec[0] >> 24;
-	ext = (intspec[0] >> 16) & 0xff;
-	class = (intspec[0] >> 8) & 0xff;
-	unit = intspec[0] & 0xff;
-
-	/* Check if node is in supported range */
-	if (node > 1)
-		return -EINVAL;
-
-	/* Build up interrupt number, special case for IO exceptions */
-	*out_hwirq = (node << IIC_IRQ_NODE_SHIFT);
-	if (unit == IIC_UNIT_IIC && class == 1)
-		*out_hwirq |= IIC_IRQ_TYPE_IOEXC | ext;
-	else
-		*out_hwirq |= IIC_IRQ_TYPE_NORMAL |
-			(class << IIC_IRQ_CLASS_SHIFT) | unit;
-
-	/* Dummy flags, ignored by iic code */
-	*out_flags = IRQ_TYPE_EDGE_RISING;
-
-	return 0;
-}
-
-static const struct irq_domain_ops iic_host_ops = {
-	.match = iic_host_match,
-	.map = iic_host_map,
-	.xlate = iic_host_xlate,
-};
-
-static void __init init_one_iic(unsigned int hw_cpu, unsigned long addr,
-				struct device_node *node)
-{
-	/* XXX FIXME: should locate the linux CPU number from the HW cpu
-	 * number properly. We are lucky for now
-	 */
-	struct iic *iic = &per_cpu(cpu_iic, hw_cpu);
-
-	iic->regs = ioremap(addr, sizeof(struct cbe_iic_thread_regs));
-	BUG_ON(iic->regs == NULL);
-
-	iic->target_id = ((hw_cpu & 2) << 3) | ((hw_cpu & 1) ? 0xf : 0xe);
-	iic->eoi_stack[0] = 0xff;
-	iic->node = of_node_get(node);
-	out_be64(&iic->regs->prio, 0);
-
-	printk(KERN_INFO "IIC for CPU %d target id 0x%x : %pOF\n",
-	       hw_cpu, iic->target_id, node);
-}
-
-static int __init setup_iic(void)
-{
-	struct device_node *dn;
-	struct resource r0, r1;
-	unsigned int node, cascade, found = 0;
-	struct cbe_iic_regs __iomem *node_iic;
-	const u32 *np;
-
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (!of_device_is_compatible(dn,
-				     "IBM,CBEA-Internal-Interrupt-Controller"))
-			continue;
-		np = of_get_property(dn, "ibm,interrupt-server-ranges", NULL);
-		if (np == NULL) {
-			printk(KERN_WARNING "IIC: CPU association not found\n");
-			of_node_put(dn);
-			return -ENODEV;
-		}
-		if (of_address_to_resource(dn, 0, &r0) ||
-		    of_address_to_resource(dn, 1, &r1)) {
-			printk(KERN_WARNING "IIC: Can't resolve addresses\n");
-			of_node_put(dn);
-			return -ENODEV;
-		}
-		found++;
-		init_one_iic(np[0], r0.start, dn);
-		init_one_iic(np[1], r1.start, dn);
-
-		/* Setup cascade for IO exceptions. XXX cleanup tricks to get
-		 * node vs CPU etc...
-		 * Note that we configure the IIC_IRR here with a hard coded
-		 * priority of 1. We might want to improve that later.
-		 */
-		node = np[0] >> 1;
-		node_iic = cbe_get_cpu_iic_regs(np[0]);
-		cascade = node << IIC_IRQ_NODE_SHIFT;
-		cascade |= 1 << IIC_IRQ_CLASS_SHIFT;
-		cascade |= IIC_UNIT_IIC;
-		cascade = irq_create_mapping(iic_host, cascade);
-		if (!cascade)
-			continue;
-		/*
-		 * irq_data is a generic pointer that gets passed back
-		 * to us later, so the forced cast is fine.
-		 */
-		irq_set_handler_data(cascade, (void __force *)node_iic);
-		irq_set_chained_handler(cascade, iic_ioexc_cascade);
-		out_be64(&node_iic->iic_ir,
-			 (1 << 12)		/* priority */ |
-			 (node << 4)		/* dest node */ |
-			 IIC_UNIT_THREAD_0	/* route them to thread 0 */);
-		/* Flush pending (make sure it triggers if there is
-		 * anything pending
-		 */
-		out_be64(&node_iic->iic_is, 0xfffffffffffffffful);
-	}
-
-	if (found)
-		return 0;
-	else
-		return -ENODEV;
-}
-
-void __init iic_init_IRQ(void)
-{
-	/* Setup an irq host data structure */
-	iic_host = irq_domain_add_linear(NULL, IIC_SOURCE_COUNT, &iic_host_ops,
-					 NULL);
-	BUG_ON(iic_host == NULL);
-	irq_set_default_host(iic_host);
-
-	/* Discover and initialize iics */
-	if (setup_iic() < 0)
-		panic("IIC: Failed to initialize !\n");
-
-	/* Set master interrupt handling function */
-	ppc_md.get_irq = iic_get_irq;
-
-	/* Enable on current CPU */
-	iic_setup_cpu();
-}
-
-void iic_set_interrupt_routing(int cpu, int thread, int priority)
-{
-	struct cbe_iic_regs __iomem *iic_regs = cbe_get_cpu_iic_regs(cpu);
-	u64 iic_ir = 0;
-	int node = cpu >> 1;
-
-	/* Set which node and thread will handle the next interrupt */
-	iic_ir |= CBE_IIC_IR_PRIO(priority) |
-		  CBE_IIC_IR_DEST_NODE(node);
-	if (thread == 0)
-		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_0);
-	else
-		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_1);
-	out_be64(&iic_regs->iic_ir, iic_ir);
-}
diff --git a/arch/powerpc/platforms/cell/interrupt.h b/arch/powerpc/platforms/cell/interrupt.h
deleted file mode 100644
index a47902248541..000000000000
--- a/arch/powerpc/platforms/cell/interrupt.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_CELL_PIC_H
-#define ASM_CELL_PIC_H
-#ifdef __KERNEL__
-/*
- * Mapping of IIC pending bits into per-node interrupt numbers.
- *
- * Interrupt numbers are in the range 0...0x1ff where the top bit
- * (0x100) represent the source node. Only 2 nodes are supported with
- * the current code though it's trivial to extend that if necessary using
- * higher level bits
- *
- * The bottom 8 bits are split into 2 type bits and 6 data bits that
- * depend on the type:
- *
- * 00 (0x00 | data) : normal interrupt. data is (class << 4) | source
- * 01 (0x40 | data) : IO exception. data is the exception number as
- *                    defined by bit numbers in IIC_SR
- * 10 (0x80 | data) : IPI. data is the IPI number (obtained from the priority)
- *                    and node is always 0 (IPIs are per-cpu, their source is
- *                    not relevant)
- * 11 (0xc0 | data) : reserved
- *
- * In addition, interrupt number 0x80000000 is defined as always invalid
- * (that is the node field is expected to never extend to move than 23 bits)
- *
- */
-
-enum {
-	IIC_IRQ_INVALID		= 0x80000000u,
-	IIC_IRQ_NODE_MASK	= 0x100,
-	IIC_IRQ_NODE_SHIFT	= 8,
-	IIC_IRQ_MAX		= 0x1ff,
-	IIC_IRQ_TYPE_MASK	= 0xc0,
-	IIC_IRQ_TYPE_NORMAL	= 0x00,
-	IIC_IRQ_TYPE_IOEXC	= 0x40,
-	IIC_IRQ_TYPE_IPI	= 0x80,
-	IIC_IRQ_CLASS_SHIFT	= 4,
-	IIC_IRQ_CLASS_0		= 0x00,
-	IIC_IRQ_CLASS_1		= 0x10,
-	IIC_IRQ_CLASS_2		= 0x20,
-	IIC_SOURCE_COUNT	= 0x200,
-
-	/* Here are defined the various source/dest units. Avoid using those
-	 * definitions if you can, they are mostly here for reference
-	 */
-	IIC_UNIT_SPU_0		= 0x4,
-	IIC_UNIT_SPU_1		= 0x7,
-	IIC_UNIT_SPU_2		= 0x3,
-	IIC_UNIT_SPU_3		= 0x8,
-	IIC_UNIT_SPU_4		= 0x2,
-	IIC_UNIT_SPU_5		= 0x9,
-	IIC_UNIT_SPU_6		= 0x1,
-	IIC_UNIT_SPU_7		= 0xa,
-	IIC_UNIT_IOC_0		= 0x0,
-	IIC_UNIT_IOC_1		= 0xb,
-	IIC_UNIT_THREAD_0	= 0xe, /* target only */
-	IIC_UNIT_THREAD_1	= 0xf, /* target only */
-	IIC_UNIT_IIC		= 0xe, /* source only (IO exceptions) */
-
-	/* Base numbers for the external interrupts */
-	IIC_IRQ_EXT_IOIF0	=
-		IIC_IRQ_TYPE_NORMAL | IIC_IRQ_CLASS_2 | IIC_UNIT_IOC_0,
-	IIC_IRQ_EXT_IOIF1	=
-		IIC_IRQ_TYPE_NORMAL | IIC_IRQ_CLASS_2 | IIC_UNIT_IOC_1,
-
-	/* Base numbers for the IIC_ISR interrupts */
-	IIC_IRQ_IOEX_TMI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 63,
-	IIC_IRQ_IOEX_PMI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 62,
-	IIC_IRQ_IOEX_ATI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 61,
-	IIC_IRQ_IOEX_MATBFI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 60,
-	IIC_IRQ_IOEX_ELDI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 59,
-
-	/* Which bits in IIC_ISR are edge sensitive */
-	IIC_ISR_EDGE_MASK	= 0x4ul,
-};
-
-extern void iic_init_IRQ(void);
-extern void iic_message_pass(int cpu, int msg);
-extern void iic_request_IPIs(void);
-extern void iic_setup_cpu(void);
-
-extern u8 iic_get_target_id(int cpu);
-
-extern void spider_init_IRQ(void);
-
-extern void iic_set_interrupt_routing(int cpu, int thread, int priority);
-
-#endif
-#endif /* ASM_CELL_PIC_H */
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
deleted file mode 100644
index 62c9679b8ca3..000000000000
--- a/arch/powerpc/platforms/cell/iommu.c
+++ /dev/null
@@ -1,1060 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * IOMMU implementation for Cell Broadband Processor Architecture
- *
- * (C) Copyright IBM Corporation 2006-2008
- *
- * Author: Jeremy Kerr <jk@ozlabs.org>
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irqdomain.h>
-#include <linux/notifier.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/memblock.h>
-
-#include <asm/prom.h>
-#include <asm/iommu.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/udbg.h>
-#include <asm/firmware.h>
-#include <asm/cell-regs.h>
-
-#include "cell.h"
-#include "interrupt.h"
-
-/* Define CELL_IOMMU_REAL_UNMAP to actually unmap non-used pages
- * instead of leaving them mapped to some dummy page. This can be
- * enabled once the appropriate workarounds for spider bugs have
- * been enabled
- */
-#define CELL_IOMMU_REAL_UNMAP
-
-/* Define CELL_IOMMU_STRICT_PROTECTION to enforce protection of
- * IO PTEs based on the transfer direction. That can be enabled
- * once spider-net has been fixed to pass the correct direction
- * to the DMA mapping functions
- */
-#define CELL_IOMMU_STRICT_PROTECTION
-
-
-#define NR_IOMMUS			2
-
-/* IOC mmap registers */
-#define IOC_Reg_Size			0x2000
-
-#define IOC_IOPT_CacheInvd		0x908
-#define IOC_IOPT_CacheInvd_NE_Mask	0xffe0000000000000ul
-#define IOC_IOPT_CacheInvd_IOPTE_Mask	0x000003fffffffff8ul
-#define IOC_IOPT_CacheInvd_Busy		0x0000000000000001ul
-
-#define IOC_IOST_Origin			0x918
-#define IOC_IOST_Origin_E		0x8000000000000000ul
-#define IOC_IOST_Origin_HW		0x0000000000000800ul
-#define IOC_IOST_Origin_HL		0x0000000000000400ul
-
-#define IOC_IO_ExcpStat			0x920
-#define IOC_IO_ExcpStat_V		0x8000000000000000ul
-#define IOC_IO_ExcpStat_SPF_Mask	0x6000000000000000ul
-#define IOC_IO_ExcpStat_SPF_S		0x6000000000000000ul
-#define IOC_IO_ExcpStat_SPF_P		0x2000000000000000ul
-#define IOC_IO_ExcpStat_ADDR_Mask	0x00000007fffff000ul
-#define IOC_IO_ExcpStat_RW_Mask		0x0000000000000800ul
-#define IOC_IO_ExcpStat_IOID_Mask	0x00000000000007fful
-
-#define IOC_IO_ExcpMask			0x928
-#define IOC_IO_ExcpMask_SFE		0x4000000000000000ul
-#define IOC_IO_ExcpMask_PFE		0x2000000000000000ul
-
-#define IOC_IOCmd_Offset		0x1000
-
-#define IOC_IOCmd_Cfg			0xc00
-#define IOC_IOCmd_Cfg_TE		0x0000800000000000ul
-
-
-/* Segment table entries */
-#define IOSTE_V			0x8000000000000000ul /* valid */
-#define IOSTE_H			0x4000000000000000ul /* cache hint */
-#define IOSTE_PT_Base_RPN_Mask  0x3ffffffffffff000ul /* base RPN of IOPT */
-#define IOSTE_NPPT_Mask		0x0000000000000fe0ul /* no. pages in IOPT */
-#define IOSTE_PS_Mask		0x0000000000000007ul /* page size */
-#define IOSTE_PS_4K		0x0000000000000001ul /*   - 4kB  */
-#define IOSTE_PS_64K		0x0000000000000003ul /*   - 64kB */
-#define IOSTE_PS_1M		0x0000000000000005ul /*   - 1MB  */
-#define IOSTE_PS_16M		0x0000000000000007ul /*   - 16MB */
-
-
-/* IOMMU sizing */
-#define IO_SEGMENT_SHIFT	28
-#define IO_PAGENO_BITS(shift)	(IO_SEGMENT_SHIFT - (shift))
-
-/* The high bit needs to be set on every DMA address */
-#define SPIDER_DMA_OFFSET	0x80000000ul
-
-struct iommu_window {
-	struct list_head list;
-	struct cbe_iommu *iommu;
-	unsigned long offset;
-	unsigned long size;
-	unsigned int ioid;
-	struct iommu_table table;
-};
-
-#define NAMESIZE 8
-struct cbe_iommu {
-	int nid;
-	char name[NAMESIZE];
-	void __iomem *xlate_regs;
-	void __iomem *cmd_regs;
-	unsigned long *stab;
-	unsigned long *ptab;
-	void *pad_page;
-	struct list_head windows;
-};
-
-/* Static array of iommus, one per node
- *   each contains a list of windows, keyed from dma_window property
- *   - on bus setup, look for a matching window, or create one
- *   - on dev setup, assign iommu_table ptr
- */
-static struct cbe_iommu iommus[NR_IOMMUS];
-static int cbe_nr_iommus;
-
-static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte,
-		long n_ptes)
-{
-	u64 __iomem *reg;
-	u64 val;
-	long n;
-
-	reg = iommu->xlate_regs + IOC_IOPT_CacheInvd;
-
-	while (n_ptes > 0) {
-		/* we can invalidate up to 1 << 11 PTEs at once */
-		n = min(n_ptes, 1l << 11);
-		val = (((n /*- 1*/) << 53) & IOC_IOPT_CacheInvd_NE_Mask)
-			| (__pa(pte) & IOC_IOPT_CacheInvd_IOPTE_Mask)
-		        | IOC_IOPT_CacheInvd_Busy;
-
-		out_be64(reg, val);
-		while (in_be64(reg) & IOC_IOPT_CacheInvd_Busy)
-			;
-
-		n_ptes -= n;
-		pte += n;
-	}
-}
-
-static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
-		unsigned long uaddr, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	unsigned long *io_pte, base_pte;
-	struct iommu_window *window =
-		container_of(tbl, struct iommu_window, table);
-
-	/* implementing proper protection causes problems with the spidernet
-	 * driver - check mapping directions later, but allow read & write by
-	 * default for now.*/
-#ifdef CELL_IOMMU_STRICT_PROTECTION
-	/* to avoid referencing a global, we use a trick here to setup the
-	 * protection bit. "prot" is setup to be 3 fields of 4 bits appended
-	 * together for each of the 3 supported direction values. It is then
-	 * shifted left so that the fields matching the desired direction
-	 * lands on the appropriate bits, and other bits are masked out.
-	 */
-	const unsigned long prot = 0xc48;
-	base_pte =
-		((prot << (52 + 4 * direction)) &
-		 (CBE_IOPTE_PP_W | CBE_IOPTE_PP_R)) |
-		CBE_IOPTE_M | CBE_IOPTE_SO_RW |
-		(window->ioid & CBE_IOPTE_IOID_Mask);
-#else
-	base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M |
-		CBE_IOPTE_SO_RW | (window->ioid & CBE_IOPTE_IOID_Mask);
-#endif
-	if (unlikely(attrs & DMA_ATTR_WEAK_ORDERING))
-		base_pte &= ~CBE_IOPTE_SO_RW;
-
-	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
-
-	for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift))
-		io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask);
-
-	mb();
-
-	invalidate_tce_cache(window->iommu, io_pte, npages);
-
-	pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n",
-		 index, npages, direction, base_pte);
-	return 0;
-}
-
-static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
-{
-
-	int i;
-	unsigned long *io_pte, pte;
-	struct iommu_window *window =
-		container_of(tbl, struct iommu_window, table);
-
-	pr_debug("tce_free_cell(index=%lx,n=%lx)\n", index, npages);
-
-#ifdef CELL_IOMMU_REAL_UNMAP
-	pte = 0;
-#else
-	/* spider bridge does PCI reads after freeing - insert a mapping
-	 * to a scratch page instead of an invalid entry */
-	pte = CBE_IOPTE_PP_R | CBE_IOPTE_M | CBE_IOPTE_SO_RW |
-		__pa(window->iommu->pad_page) |
-		(window->ioid & CBE_IOPTE_IOID_Mask);
-#endif
-
-	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
-
-	for (i = 0; i < npages; i++)
-		io_pte[i] = pte;
-
-	mb();
-
-	invalidate_tce_cache(window->iommu, io_pte, npages);
-}
-
-static irqreturn_t ioc_interrupt(int irq, void *data)
-{
-	unsigned long stat, spf;
-	struct cbe_iommu *iommu = data;
-
-	stat = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
-	spf = stat & IOC_IO_ExcpStat_SPF_Mask;
-
-	/* Might want to rate limit it */
-	printk(KERN_ERR "iommu: DMA exception 0x%016lx\n", stat);
-	printk(KERN_ERR "  V=%d, SPF=[%c%c], RW=%s, IOID=0x%04x\n",
-	       !!(stat & IOC_IO_ExcpStat_V),
-	       (spf == IOC_IO_ExcpStat_SPF_S) ? 'S' : ' ',
-	       (spf == IOC_IO_ExcpStat_SPF_P) ? 'P' : ' ',
-	       (stat & IOC_IO_ExcpStat_RW_Mask) ? "Read" : "Write",
-	       (unsigned int)(stat & IOC_IO_ExcpStat_IOID_Mask));
-	printk(KERN_ERR "  page=0x%016lx\n",
-	       stat & IOC_IO_ExcpStat_ADDR_Mask);
-
-	/* clear interrupt */
-	stat &= ~IOC_IO_ExcpStat_V;
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat, stat);
-
-	return IRQ_HANDLED;
-}
-
-static int __init cell_iommu_find_ioc(int nid, unsigned long *base)
-{
-	struct device_node *np;
-	struct resource r;
-
-	*base = 0;
-
-	/* First look for new style /be nodes */
-	for_each_node_by_name(np, "ioc") {
-		if (of_node_to_nid(np) != nid)
-			continue;
-		if (of_address_to_resource(np, 0, &r)) {
-			printk(KERN_ERR "iommu: can't get address for %pOF\n",
-			       np);
-			continue;
-		}
-		*base = r.start;
-		of_node_put(np);
-		return 0;
-	}
-
-	/* Ok, let's try the old way */
-	for_each_node_by_type(np, "cpu") {
-		const unsigned int *nidp;
-		const unsigned long *tmp;
-
-		nidp = of_get_property(np, "node-id", NULL);
-		if (nidp && *nidp == nid) {
-			tmp = of_get_property(np, "ioc-translation", NULL);
-			if (tmp) {
-				*base = *tmp;
-				of_node_put(np);
-				return 0;
-			}
-		}
-	}
-
-	return -ENODEV;
-}
-
-static void __init cell_iommu_setup_stab(struct cbe_iommu *iommu,
-				unsigned long dbase, unsigned long dsize,
-				unsigned long fbase, unsigned long fsize)
-{
-	struct page *page;
-	unsigned long segments, stab_size;
-
-	segments = max(dbase + dsize, fbase + fsize) >> IO_SEGMENT_SHIFT;
-
-	pr_debug("%s: iommu[%d]: segments: %lu\n",
-			__func__, iommu->nid, segments);
-
-	/* set up the segment table */
-	stab_size = segments * sizeof(unsigned long);
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(stab_size));
-	BUG_ON(!page);
-	iommu->stab = page_address(page);
-	memset(iommu->stab, 0, stab_size);
-}
-
-static unsigned long *__init cell_iommu_alloc_ptab(struct cbe_iommu *iommu,
-		unsigned long base, unsigned long size, unsigned long gap_base,
-		unsigned long gap_size, unsigned long page_shift)
-{
-	struct page *page;
-	int i;
-	unsigned long reg, segments, pages_per_segment, ptab_size,
-		      n_pte_pages, start_seg, *ptab;
-
-	start_seg = base >> IO_SEGMENT_SHIFT;
-	segments  = size >> IO_SEGMENT_SHIFT;
-	pages_per_segment = 1ull << IO_PAGENO_BITS(page_shift);
-	/* PTEs for each segment must start on a 4K boundary */
-	pages_per_segment = max(pages_per_segment,
-				(1 << 12) / sizeof(unsigned long));
-
-	ptab_size = segments * pages_per_segment * sizeof(unsigned long);
-	pr_debug("%s: iommu[%d]: ptab_size: %lu, order: %d\n", __func__,
-			iommu->nid, ptab_size, get_order(ptab_size));
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(ptab_size));
-	BUG_ON(!page);
-
-	ptab = page_address(page);
-	memset(ptab, 0, ptab_size);
-
-	/* number of 4K pages needed for a page table */
-	n_pte_pages = (pages_per_segment * sizeof(unsigned long)) >> 12;
-
-	pr_debug("%s: iommu[%d]: stab at %p, ptab at %p, n_pte_pages: %lu\n",
-			__func__, iommu->nid, iommu->stab, ptab,
-			n_pte_pages);
-
-	/* initialise the STEs */
-	reg = IOSTE_V | ((n_pte_pages - 1) << 5);
-
-	switch (page_shift) {
-	case 12: reg |= IOSTE_PS_4K;  break;
-	case 16: reg |= IOSTE_PS_64K; break;
-	case 20: reg |= IOSTE_PS_1M;  break;
-	case 24: reg |= IOSTE_PS_16M; break;
-	default: BUG();
-	}
-
-	gap_base = gap_base >> IO_SEGMENT_SHIFT;
-	gap_size = gap_size >> IO_SEGMENT_SHIFT;
-
-	pr_debug("Setting up IOMMU stab:\n");
-	for (i = start_seg; i < (start_seg + segments); i++) {
-		if (i >= gap_base && i < (gap_base + gap_size)) {
-			pr_debug("\toverlap at %d, skipping\n", i);
-			continue;
-		}
-		iommu->stab[i] = reg | (__pa(ptab) + (n_pte_pages << 12) *
-					(i - start_seg));
-		pr_debug("\t[%d] 0x%016lx\n", i, iommu->stab[i]);
-	}
-
-	return ptab;
-}
-
-static void __init cell_iommu_enable_hardware(struct cbe_iommu *iommu)
-{
-	int ret;
-	unsigned long reg, xlate_base;
-	unsigned int virq;
-
-	if (cell_iommu_find_ioc(iommu->nid, &xlate_base))
-		panic("%s: missing IOC register mappings for node %d\n",
-		      __func__, iommu->nid);
-
-	iommu->xlate_regs = ioremap(xlate_base, IOC_Reg_Size);
-	iommu->cmd_regs = iommu->xlate_regs + IOC_IOCmd_Offset;
-
-	/* ensure that the STEs have updated */
-	mb();
-
-	/* setup interrupts for the iommu. */
-	reg = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat,
-			reg & ~IOC_IO_ExcpStat_V);
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpMask,
-			IOC_IO_ExcpMask_PFE | IOC_IO_ExcpMask_SFE);
-
-	virq = irq_create_mapping(NULL,
-			IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT));
-	BUG_ON(!virq);
-
-	ret = request_irq(virq, ioc_interrupt, 0, iommu->name, iommu);
-	BUG_ON(ret);
-
-	/* set the IOC segment table origin register (and turn on the iommu) */
-	reg = IOC_IOST_Origin_E | __pa(iommu->stab) | IOC_IOST_Origin_HW;
-	out_be64(iommu->xlate_regs + IOC_IOST_Origin, reg);
-	in_be64(iommu->xlate_regs + IOC_IOST_Origin);
-
-	/* turn on IO translation */
-	reg = in_be64(iommu->cmd_regs + IOC_IOCmd_Cfg) | IOC_IOCmd_Cfg_TE;
-	out_be64(iommu->cmd_regs + IOC_IOCmd_Cfg, reg);
-}
-
-static void __init cell_iommu_setup_hardware(struct cbe_iommu *iommu,
-	unsigned long base, unsigned long size)
-{
-	cell_iommu_setup_stab(iommu, base, size, 0, 0);
-	iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0,
-					    IOMMU_PAGE_SHIFT_4K);
-	cell_iommu_enable_hardware(iommu);
-}
-
-static inline u32 cell_iommu_get_ioid(struct device_node *np)
-{
-	const u32 *ioid;
-
-	ioid = of_get_property(np, "ioid", NULL);
-	if (ioid == NULL) {
-		printk(KERN_WARNING "iommu: missing ioid for %pOF using 0\n",
-		       np);
-		return 0;
-	}
-
-	return *ioid;
-}
-
-static struct iommu_table_ops cell_iommu_ops = {
-	.set = tce_build_cell,
-	.clear = tce_free_cell
-};
-
-static struct iommu_window * __init
-cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
-			unsigned long offset, unsigned long size,
-			unsigned long pte_offset)
-{
-	struct iommu_window *window;
-	struct page *page;
-	u32 ioid;
-
-	ioid = cell_iommu_get_ioid(np);
-
-	window = kzalloc_node(sizeof(*window), GFP_KERNEL, iommu->nid);
-	BUG_ON(window == NULL);
-
-	window->offset = offset;
-	window->size = size;
-	window->ioid = ioid;
-	window->iommu = iommu;
-
-	window->table.it_blocksize = 16;
-	window->table.it_base = (unsigned long)iommu->ptab;
-	window->table.it_index = iommu->nid;
-	window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K;
-	window->table.it_offset =
-		(offset >> window->table.it_page_shift) + pte_offset;
-	window->table.it_size = size >> window->table.it_page_shift;
-	window->table.it_ops = &cell_iommu_ops;
-
-	if (!iommu_init_table(&window->table, iommu->nid, 0, 0))
-		panic("Failed to initialize iommu table");
-
-	pr_debug("\tioid      %d\n", window->ioid);
-	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
-	pr_debug("\tbase      0x%016lx\n", window->table.it_base);
-	pr_debug("\toffset    0x%lx\n", window->table.it_offset);
-	pr_debug("\tsize      %ld\n", window->table.it_size);
-
-	list_add(&window->list, &iommu->windows);
-
-	if (offset != 0)
-		return window;
-
-	/* We need to map and reserve the first IOMMU page since it's used
-	 * by the spider workaround. In theory, we only need to do that when
-	 * running on spider but it doesn't really matter.
-	 *
-	 * This code also assumes that we have a window that starts at 0,
-	 * which is the case on all spider based blades.
-	 */
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
-	BUG_ON(!page);
-	iommu->pad_page = page_address(page);
-	clear_page(iommu->pad_page);
-
-	__set_bit(0, window->table.it_map);
-	tce_build_cell(&window->table, window->table.it_offset, 1,
-		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE, 0);
-
-	return window;
-}
-
-static struct cbe_iommu *cell_iommu_for_node(int nid)
-{
-	int i;
-
-	for (i = 0; i < cbe_nr_iommus; i++)
-		if (iommus[i].nid == nid)
-			return &iommus[i];
-	return NULL;
-}
-
-static unsigned long cell_dma_nommu_offset;
-
-static unsigned long dma_iommu_fixed_base;
-static bool cell_iommu_enabled;
-
-/* iommu_fixed_is_weak is set if booted with iommu_fixed=weak */
-bool iommu_fixed_is_weak;
-
-static struct iommu_table *cell_get_iommu_table(struct device *dev)
-{
-	struct iommu_window *window;
-	struct cbe_iommu *iommu;
-
-	/* Current implementation uses the first window available in that
-	 * node's iommu. We -might- do something smarter later though it may
-	 * never be necessary
-	 */
-	iommu = cell_iommu_for_node(dev_to_node(dev));
-	if (iommu == NULL || list_empty(&iommu->windows)) {
-		dev_err(dev, "iommu: missing iommu for %pOF (node %d)\n",
-		       dev->of_node, dev_to_node(dev));
-		return NULL;
-	}
-	window = list_entry(iommu->windows.next, struct iommu_window, list);
-
-	return &window->table;
-}
-
-static u64 cell_iommu_get_fixed_address(struct device *dev);
-
-static void cell_dma_dev_setup(struct device *dev)
-{
-	if (cell_iommu_enabled) {
-		u64 addr = cell_iommu_get_fixed_address(dev);
-
-		if (addr != OF_BAD_ADDR)
-			dev->archdata.dma_offset = addr + dma_iommu_fixed_base;
-		set_iommu_table_base(dev, cell_get_iommu_table(dev));
-	} else {
-		dev->archdata.dma_offset = cell_dma_nommu_offset;
-	}
-}
-
-static void cell_pci_dma_dev_setup(struct pci_dev *dev)
-{
-	cell_dma_dev_setup(&dev->dev);
-}
-
-static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action,
-			      void *data)
-{
-	struct device *dev = data;
-
-	/* We are only interested in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	if (cell_iommu_enabled)
-		dev->dma_ops = &dma_iommu_ops;
-	cell_dma_dev_setup(dev);
-	return 0;
-}
-
-static struct notifier_block cell_of_bus_notifier = {
-	.notifier_call = cell_of_bus_notify
-};
-
-static int __init cell_iommu_get_window(struct device_node *np,
-					 unsigned long *base,
-					 unsigned long *size)
-{
-	const __be32 *dma_window;
-	unsigned long index;
-
-	/* Use ibm,dma-window if available, else, hard code ! */
-	dma_window = of_get_property(np, "ibm,dma-window", NULL);
-	if (dma_window == NULL) {
-		*base = 0;
-		*size = 0x80000000u;
-		return -ENODEV;
-	}
-
-	of_parse_dma_window(np, dma_window, &index, base, size);
-	return 0;
-}
-
-static struct cbe_iommu * __init cell_iommu_alloc(struct device_node *np)
-{
-	struct cbe_iommu *iommu;
-	int nid, i;
-
-	/* Get node ID */
-	nid = of_node_to_nid(np);
-	if (nid < 0) {
-		printk(KERN_ERR "iommu: failed to get node for %pOF\n",
-		       np);
-		return NULL;
-	}
-	pr_debug("iommu: setting up iommu for node %d (%pOF)\n",
-		 nid, np);
-
-	/* XXX todo: If we can have multiple windows on the same IOMMU, which
-	 * isn't the case today, we probably want here to check whether the
-	 * iommu for that node is already setup.
-	 * However, there might be issue with getting the size right so let's
-	 * ignore that for now. We might want to completely get rid of the
-	 * multiple window support since the cell iommu supports per-page ioids
-	 */
-
-	if (cbe_nr_iommus >= NR_IOMMUS) {
-		printk(KERN_ERR "iommu: too many IOMMUs detected ! (%pOF)\n",
-		       np);
-		return NULL;
-	}
-
-	/* Init base fields */
-	i = cbe_nr_iommus++;
-	iommu = &iommus[i];
-	iommu->stab = NULL;
-	iommu->nid = nid;
-	snprintf(iommu->name, sizeof(iommu->name), "iommu%d", i);
-	INIT_LIST_HEAD(&iommu->windows);
-
-	return iommu;
-}
-
-static void __init cell_iommu_init_one(struct device_node *np,
-				       unsigned long offset)
-{
-	struct cbe_iommu *iommu;
-	unsigned long base, size;
-
-	iommu = cell_iommu_alloc(np);
-	if (!iommu)
-		return;
-
-	/* Obtain a window for it */
-	cell_iommu_get_window(np, &base, &size);
-
-	pr_debug("\ttranslating window 0x%lx...0x%lx\n",
-		 base, base + size - 1);
-
-	/* Initialize the hardware */
-	cell_iommu_setup_hardware(iommu, base, size);
-
-	/* Setup the iommu_table */
-	cell_iommu_setup_window(iommu, np, base, size,
-				offset >> IOMMU_PAGE_SHIFT_4K);
-}
-
-static void __init cell_disable_iommus(void)
-{
-	int node;
-	unsigned long base, val;
-	void __iomem *xregs, *cregs;
-
-	/* Make sure IOC translation is disabled on all nodes */
-	for_each_online_node(node) {
-		if (cell_iommu_find_ioc(node, &base))
-			continue;
-		xregs = ioremap(base, IOC_Reg_Size);
-		if (xregs == NULL)
-			continue;
-		cregs = xregs + IOC_IOCmd_Offset;
-
-		pr_debug("iommu: cleaning up iommu on node %d\n", node);
-
-		out_be64(xregs + IOC_IOST_Origin, 0);
-		(void)in_be64(xregs + IOC_IOST_Origin);
-		val = in_be64(cregs + IOC_IOCmd_Cfg);
-		val &= ~IOC_IOCmd_Cfg_TE;
-		out_be64(cregs + IOC_IOCmd_Cfg, val);
-		(void)in_be64(cregs + IOC_IOCmd_Cfg);
-
-		iounmap(xregs);
-	}
-}
-
-static int __init cell_iommu_init_disabled(void)
-{
-	struct device_node *np = NULL;
-	unsigned long base = 0, size;
-
-	/* When no iommu is present, we use direct DMA ops */
-
-	/* First make sure all IOC translation is turned off */
-	cell_disable_iommus();
-
-	/* If we have no Axon, we set up the spider DMA magic offset */
-	np = of_find_node_by_name(NULL, "axon");
-	if (!np)
-		cell_dma_nommu_offset = SPIDER_DMA_OFFSET;
-	of_node_put(np);
-
-	/* Now we need to check to see where the memory is mapped
-	 * in PCI space. We assume that all busses use the same dma
-	 * window which is always the case so far on Cell, thus we
-	 * pick up the first pci-internal node we can find and check
-	 * the DMA window from there.
-	 */
-	for_each_node_by_name(np, "axon") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		if (cell_iommu_get_window(np, &base, &size) == 0)
-			break;
-	}
-	if (np == NULL) {
-		for_each_node_by_name(np, "pci-internal") {
-			if (np->parent == NULL || np->parent->parent != NULL)
-				continue;
-			if (cell_iommu_get_window(np, &base, &size) == 0)
-				break;
-		}
-	}
-	of_node_put(np);
-
-	/* If we found a DMA window, we check if it's big enough to enclose
-	 * all of physical memory. If not, we force enable IOMMU
-	 */
-	if (np && size < memblock_end_of_DRAM()) {
-		printk(KERN_WARNING "iommu: force-enabled, dma window"
-		       " (%ldMB) smaller than total memory (%lldMB)\n",
-		       size >> 20, memblock_end_of_DRAM() >> 20);
-		return -ENODEV;
-	}
-
-	cell_dma_nommu_offset += base;
-
-	if (cell_dma_nommu_offset != 0)
-		cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-
-	printk("iommu: disabled, direct DMA offset is 0x%lx\n",
-	       cell_dma_nommu_offset);
-
-	return 0;
-}
-
-/*
- *  Fixed IOMMU mapping support
- *
- *  This code adds support for setting up a fixed IOMMU mapping on certain
- *  cell machines. For 64-bit devices this avoids the performance overhead of
- *  mapping and unmapping pages at runtime. 32-bit devices are unable to use
- *  the fixed mapping.
- *
- *  The fixed mapping is established at boot, and maps all of physical memory
- *  1:1 into device space at some offset. On machines with < 30 GB of memory
- *  we setup the fixed mapping immediately above the normal IOMMU window.
- *
- *  For example a machine with 4GB of memory would end up with the normal
- *  IOMMU window from 0-2GB and the fixed mapping window from 2GB to 6GB. In
- *  this case a 64-bit device wishing to DMA to 1GB would be told to DMA to
- *  3GB, plus any offset required by firmware. The firmware offset is encoded
- *  in the "dma-ranges" property.
- *
- *  On machines with 30GB or more of memory, we are unable to place the fixed
- *  mapping above the normal IOMMU window as we would run out of address space.
- *  Instead we move the normal IOMMU window to coincide with the hash page
- *  table, this region does not need to be part of the fixed mapping as no
- *  device should ever be DMA'ing to it. We then setup the fixed mapping
- *  from 0 to 32GB.
- */
-
-static u64 cell_iommu_get_fixed_address(struct device *dev)
-{
-	u64 best_size, dev_addr = OF_BAD_ADDR;
-	struct device_node *np;
-	struct of_range_parser parser;
-	struct of_range range;
-
-	/* We can be called for platform devices that have no of_node */
-	np = of_node_get(dev->of_node);
-	if (!np)
-		goto out;
-
-	while ((np = of_get_next_parent(np))) {
-		if (of_pci_dma_range_parser_init(&parser, np))
-			continue;
-
-		if (of_range_count(&parser))
-			break;
-	}
-
-	if (!np) {
-		dev_dbg(dev, "iommu: no dma-ranges found\n");
-		goto out;
-	}
-
-	best_size = 0;
-	for_each_of_range(&parser, &range) {
-		if (!range.cpu_addr)
-			continue;
-
-		if (range.size > best_size) {
-			best_size = range.size;
-			dev_addr = range.bus_addr;
-		}
-	}
-
-	if (!best_size)
-		dev_dbg(dev, "iommu: no suitable range found!\n");
-
-out:
-	of_node_put(np);
-
-	return dev_addr;
-}
-
-static bool cell_pci_iommu_bypass_supported(struct pci_dev *pdev, u64 mask)
-{
-	return mask == DMA_BIT_MASK(64) &&
-		cell_iommu_get_fixed_address(&pdev->dev) != OF_BAD_ADDR;
-}
-
-static void __init insert_16M_pte(unsigned long addr, unsigned long *ptab,
-			   unsigned long base_pte)
-{
-	unsigned long segment, offset;
-
-	segment = addr >> IO_SEGMENT_SHIFT;
-	offset = (addr >> 24) - (segment << IO_PAGENO_BITS(24));
-	ptab = ptab + (segment * (1 << 12) / sizeof(unsigned long));
-
-	pr_debug("iommu: addr %lx ptab %p segment %lx offset %lx\n",
-		  addr, ptab, segment, offset);
-
-	ptab[offset] = base_pte | (__pa(addr) & CBE_IOPTE_RPN_Mask);
-}
-
-static void __init cell_iommu_setup_fixed_ptab(struct cbe_iommu *iommu,
-	struct device_node *np, unsigned long dbase, unsigned long dsize,
-	unsigned long fbase, unsigned long fsize)
-{
-	unsigned long base_pte, uaddr, ioaddr, *ptab;
-
-	ptab = cell_iommu_alloc_ptab(iommu, fbase, fsize, dbase, dsize, 24);
-
-	dma_iommu_fixed_base = fbase;
-
-	pr_debug("iommu: mapping 0x%lx pages from 0x%lx\n", fsize, fbase);
-
-	base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M |
-		(cell_iommu_get_ioid(np) & CBE_IOPTE_IOID_Mask);
-
-	if (iommu_fixed_is_weak)
-		pr_info("IOMMU: Using weak ordering for fixed mapping\n");
-	else {
-		pr_info("IOMMU: Using strong ordering for fixed mapping\n");
-		base_pte |= CBE_IOPTE_SO_RW;
-	}
-
-	for (uaddr = 0; uaddr < fsize; uaddr += (1 << 24)) {
-		/* Don't touch the dynamic region */
-		ioaddr = uaddr + fbase;
-		if (ioaddr >= dbase && ioaddr < (dbase + dsize)) {
-			pr_debug("iommu: fixed/dynamic overlap, skipping\n");
-			continue;
-		}
-
-		insert_16M_pte(uaddr, ptab, base_pte);
-	}
-
-	mb();
-}
-
-static int __init cell_iommu_fixed_mapping_init(void)
-{
-	unsigned long dbase, dsize, fbase, fsize, hbase, hend;
-	struct cbe_iommu *iommu;
-	struct device_node *np;
-
-	/* The fixed mapping is only supported on axon machines */
-	np = of_find_node_by_name(NULL, "axon");
-	of_node_put(np);
-
-	if (!np) {
-		pr_debug("iommu: fixed mapping disabled, no axons found\n");
-		return -1;
-	}
-
-	/* We must have dma-ranges properties for fixed mapping to work */
-	np = of_find_node_with_property(NULL, "dma-ranges");
-	of_node_put(np);
-
-	if (!np) {
-		pr_debug("iommu: no dma-ranges found, no fixed mapping\n");
-		return -1;
-	}
-
-	/* The default setup is to have the fixed mapping sit after the
-	 * dynamic region, so find the top of the largest IOMMU window
-	 * on any axon, then add the size of RAM and that's our max value.
-	 * If that is > 32GB we have to do other shennanigans.
-	 */
-	fbase = 0;
-	for_each_node_by_name(np, "axon") {
-		cell_iommu_get_window(np, &dbase, &dsize);
-		fbase = max(fbase, dbase + dsize);
-	}
-
-	fbase = ALIGN(fbase, 1 << IO_SEGMENT_SHIFT);
-	fsize = memblock_phys_mem_size();
-
-	if ((fbase + fsize) <= 0x800000000ul)
-		hbase = 0; /* use the device tree window */
-	else {
-		/* If we're over 32 GB we need to cheat. We can't map all of
-		 * RAM with the fixed mapping, and also fit the dynamic
-		 * region. So try to place the dynamic region where the hash
-		 * table sits, drivers never need to DMA to it, we don't
-		 * need a fixed mapping for that area.
-		 */
-		if (!htab_address) {
-			pr_debug("iommu: htab is NULL, on LPAR? Huh?\n");
-			return -1;
-		}
-		hbase = __pa(htab_address);
-		hend  = hbase + htab_size_bytes;
-
-		/* The window must start and end on a segment boundary */
-		if ((hbase != ALIGN(hbase, 1 << IO_SEGMENT_SHIFT)) ||
-		    (hend != ALIGN(hend, 1 << IO_SEGMENT_SHIFT))) {
-			pr_debug("iommu: hash window not segment aligned\n");
-			return -1;
-		}
-
-		/* Check the hash window fits inside the real DMA window */
-		for_each_node_by_name(np, "axon") {
-			cell_iommu_get_window(np, &dbase, &dsize);
-
-			if (hbase < dbase || (hend > (dbase + dsize))) {
-				pr_debug("iommu: hash window doesn't fit in"
-					 "real DMA window\n");
-				of_node_put(np);
-				return -1;
-			}
-		}
-
-		fbase = 0;
-	}
-
-	/* Setup the dynamic regions */
-	for_each_node_by_name(np, "axon") {
-		iommu = cell_iommu_alloc(np);
-		BUG_ON(!iommu);
-
-		if (hbase == 0)
-			cell_iommu_get_window(np, &dbase, &dsize);
-		else {
-			dbase = hbase;
-			dsize = htab_size_bytes;
-		}
-
-		printk(KERN_DEBUG "iommu: node %d, dynamic window 0x%lx-0x%lx "
-			"fixed window 0x%lx-0x%lx\n", iommu->nid, dbase,
-			 dbase + dsize, fbase, fbase + fsize);
-
-		cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize);
-		iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0,
-						    IOMMU_PAGE_SHIFT_4K);
-		cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize,
-					     fbase, fsize);
-		cell_iommu_enable_hardware(iommu);
-		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
-	}
-
-	cell_pci_controller_ops.iommu_bypass_supported =
-		cell_pci_iommu_bypass_supported;
-	return 0;
-}
-
-static int iommu_fixed_disabled;
-
-static int __init setup_iommu_fixed(char *str)
-{
-	struct device_node *pciep;
-
-	if (strcmp(str, "off") == 0)
-		iommu_fixed_disabled = 1;
-
-	/* If we can find a pcie-endpoint in the device tree assume that
-	 * we're on a triblade or a CAB so by default the fixed mapping
-	 * should be set to be weakly ordered; but only if the boot
-	 * option WASN'T set for strong ordering
-	 */
-	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
-
-	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
-		iommu_fixed_is_weak = true;
-
-	of_node_put(pciep);
-
-	return 1;
-}
-__setup("iommu_fixed=", setup_iommu_fixed);
-
-static int __init cell_iommu_init(void)
-{
-	struct device_node *np;
-
-	/* If IOMMU is disabled or we have little enough RAM to not need
-	 * to enable it, we setup a direct mapping.
-	 *
-	 * Note: should we make sure we have the IOMMU actually disabled ?
-	 */
-	if (iommu_is_off ||
-	    (!iommu_force_on && memblock_end_of_DRAM() <= 0x80000000ull))
-		if (cell_iommu_init_disabled() == 0)
-			goto bail;
-
-	/* Setup various callbacks */
-	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-
-	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
-		goto done;
-
-	/* Create an iommu for each /axon node.  */
-	for_each_node_by_name(np, "axon") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		cell_iommu_init_one(np, 0);
-	}
-
-	/* Create an iommu for each toplevel /pci-internal node for
-	 * old hardware/firmware
-	 */
-	for_each_node_by_name(np, "pci-internal") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		cell_iommu_init_one(np, SPIDER_DMA_OFFSET);
-	}
- done:
-	/* Setup default PCI iommu ops */
-	set_pci_dma_ops(&dma_iommu_ops);
-	cell_iommu_enabled = true;
- bail:
-	/* Register callbacks on OF platform device addition/removal
-	 * to handle linking them to the right DMA operations
-	 */
-	bus_register_notifier(&platform_bus_type, &cell_of_bus_notifier);
-
-	return 0;
-}
-machine_arch_initcall(cell, cell_iommu_init);
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
deleted file mode 100644
index 58d967ee38b3..000000000000
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ /dev/null
@@ -1,125 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * CBE Pervasive Monitor and Debug
- *
- * (C) Copyright IBM Corporation 2005
- *
- * Authors: Maximino Aguilar (maguilar@us.ibm.com)
- *          Michael N. Day (mnday@us.ibm.com)
- */
-
-#undef DEBUG
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/kallsyms.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/reg.h>
-#include <asm/cell-regs.h>
-#include <asm/cpu_has_feature.h>
-
-#include "pervasive.h"
-#include "ras.h"
-
-static void cbe_power_save(void)
-{
-	unsigned long ctrl, thread_switch_control;
-
-	/* Ensure our interrupt state is properly tracked */
-	if (!prep_irq_for_idle())
-		return;
-
-	ctrl = mfspr(SPRN_CTRLF);
-
-	/* Enable DEC and EE interrupt request */
-	thread_switch_control  = mfspr(SPRN_TSC_CELL);
-	thread_switch_control |= TSC_CELL_EE_ENABLE | TSC_CELL_EE_BOOST;
-
-	switch (ctrl & CTRL_CT) {
-	case CTRL_CT0:
-		thread_switch_control |= TSC_CELL_DEC_ENABLE_0;
-		break;
-	case CTRL_CT1:
-		thread_switch_control |= TSC_CELL_DEC_ENABLE_1;
-		break;
-	default:
-		printk(KERN_WARNING "%s: unknown configuration\n",
-			__func__);
-		break;
-	}
-	mtspr(SPRN_TSC_CELL, thread_switch_control);
-
-	/*
-	 * go into low thread priority, medium priority will be
-	 * restored for us after wake-up.
-	 */
-	HMT_low();
-
-	/*
-	 * atomically disable thread execution and runlatch.
-	 * External and Decrementer exceptions are still handled when the
-	 * thread is disabled but now enter in cbe_system_reset_exception()
-	 */
-	ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
-	mtspr(SPRN_CTRLT, ctrl);
-
-	/* Re-enable interrupts in MSR */
-	__hard_irq_enable();
-}
-
-static int cbe_system_reset_exception(struct pt_regs *regs)
-{
-	switch (regs->msr & SRR1_WAKEMASK) {
-	case SRR1_WAKEDEC:
-		set_dec(1);
-		break;
-	case SRR1_WAKEEE:
-		/*
-		 * Handle these when interrupts get re-enabled and we take
-		 * them as regular exceptions. We are in an NMI context
-		 * and can't handle these here.
-		 */
-		break;
-	case SRR1_WAKEMT:
-		return cbe_sysreset_hack();
-#ifdef CONFIG_CBE_RAS
-	case SRR1_WAKESYSERR:
-		cbe_system_error_exception(regs);
-		break;
-	case SRR1_WAKETHERM:
-		cbe_thermal_exception(regs);
-		break;
-#endif /* CONFIG_CBE_RAS */
-	default:
-		/* do system reset */
-		return 0;
-	}
-	/* everything handled */
-	return 1;
-}
-
-void __init cbe_pervasive_init(void)
-{
-	int cpu;
-
-	if (!cpu_has_feature(CPU_FTR_PAUSE_ZERO))
-		return;
-
-	for_each_possible_cpu(cpu) {
-		struct cbe_pmd_regs __iomem *regs = cbe_get_cpu_pmd_regs(cpu);
-		if (!regs)
-			continue;
-
-		 /* Enable Pause(0) control bit */
-		out_be64(&regs->pmcr, in_be64(&regs->pmcr) |
-					    CBE_PMD_PAUSE_ZERO_CONTROL);
-	}
-
-	ppc_md.power_save = cbe_power_save;
-	ppc_md.system_reset_exception = cbe_system_reset_exception;
-}
diff --git a/arch/powerpc/platforms/cell/pervasive.h b/arch/powerpc/platforms/cell/pervasive.h
deleted file mode 100644
index 0da74ab10716..000000000000
--- a/arch/powerpc/platforms/cell/pervasive.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Cell Pervasive Monitor and Debug interface and HW structures
- *
- * (C) Copyright IBM Corporation 2005
- *
- * Authors: Maximino Aguilar (maguilar@us.ibm.com)
- *          David J. Erb (djerb@us.ibm.com)
- */
-
-
-#ifndef PERVASIVE_H
-#define PERVASIVE_H
-
-extern void cbe_pervasive_init(void);
-
-#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
-extern int cbe_sysreset_hack(void);
-#else
-static inline int cbe_sysreset_hack(void)
-{
-	return 1;
-}
-#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
-
-#endif
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
deleted file mode 100644
index b207a7f99be5..000000000000
--- a/arch/powerpc/platforms/cell/pmu.c
+++ /dev/null
@@ -1,412 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cell Broadband Engine Performance Monitor
- *
- * (C) Copyright IBM Corporation 2001,2006
- *
- * Author:
- *    David Erb (djerb@us.ibm.com)
- *    Kevin Corry (kevcorry@us.ibm.com)
- */
-
-#include <linux/interrupt.h>
-#include <linux/irqdomain.h>
-#include <linux/types.h>
-#include <linux/export.h>
-#include <asm/io.h>
-#include <asm/irq_regs.h>
-#include <asm/machdep.h>
-#include <asm/pmc.h>
-#include <asm/reg.h>
-#include <asm/spu.h>
-#include <asm/cell-regs.h>
-
-#include "interrupt.h"
-
-/*
- * When writing to write-only mmio addresses, save a shadow copy. All of the
- * registers are 32-bit, but stored in the upper-half of a 64-bit field in
- * pmd_regs.
- */
-
-#define WRITE_WO_MMIO(reg, x)					\
-	do {							\
-		u32 _x = (x);					\
-		struct cbe_pmd_regs __iomem *pmd_regs;		\
-		struct cbe_pmd_shadow_regs *shadow_regs;	\
-		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
-		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
-		out_be64(&(pmd_regs->reg), (((u64)_x) << 32));	\
-		shadow_regs->reg = _x;				\
-	} while (0)
-
-#define READ_SHADOW_REG(val, reg)				\
-	do {							\
-		struct cbe_pmd_shadow_regs *shadow_regs;	\
-		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
-		(val) = shadow_regs->reg;			\
-	} while (0)
-
-#define READ_MMIO_UPPER32(val, reg)				\
-	do {							\
-		struct cbe_pmd_regs __iomem *pmd_regs;		\
-		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
-		(val) = (u32)(in_be64(&pmd_regs->reg) >> 32);	\
-	} while (0)
-
-/*
- * Physical counter registers.
- * Each physical counter can act as one 32-bit counter or two 16-bit counters.
- */
-
-u32 cbe_read_phys_ctr(u32 cpu, u32 phys_ctr)
-{
-	u32 val_in_latch, val = 0;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		READ_SHADOW_REG(val_in_latch, counter_value_in_latch);
-
-		/* Read the latch or the actual counter, whichever is newer. */
-		if (val_in_latch & (1 << phys_ctr)) {
-			READ_SHADOW_REG(val, pm_ctr[phys_ctr]);
-		} else {
-			READ_MMIO_UPPER32(val, pm_ctr[phys_ctr]);
-		}
-	}
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_phys_ctr);
-
-void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val)
-{
-	struct cbe_pmd_shadow_regs *shadow_regs;
-	u32 pm_ctrl;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		/* Writing to a counter only writes to a hardware latch.
-		 * The new value is not propagated to the actual counter
-		 * until the performance monitor is enabled.
-		 */
-		WRITE_WO_MMIO(pm_ctr[phys_ctr], val);
-
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		if (pm_ctrl & CBE_PM_ENABLE_PERF_MON) {
-			/* The counters are already active, so we need to
-			 * rewrite the pm_control register to "re-enable"
-			 * the PMU.
-			 */
-			cbe_write_pm(cpu, pm_control, pm_ctrl);
-		} else {
-			shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
-			shadow_regs->counter_value_in_latch |= (1 << phys_ctr);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_write_phys_ctr);
-
-/*
- * "Logical" counter registers.
- * These will read/write 16-bits or 32-bits depending on the
- * current size of the counter. Counters 4 - 7 are always 16-bit.
- */
-
-u32 cbe_read_ctr(u32 cpu, u32 ctr)
-{
-	u32 val;
-	u32 phys_ctr = ctr & (NR_PHYS_CTRS - 1);
-
-	val = cbe_read_phys_ctr(cpu, phys_ctr);
-
-	if (cbe_get_ctr_size(cpu, phys_ctr) == 16)
-		val = (ctr < NR_PHYS_CTRS) ? (val >> 16) : (val & 0xffff);
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_ctr);
-
-void cbe_write_ctr(u32 cpu, u32 ctr, u32 val)
-{
-	u32 phys_ctr;
-	u32 phys_val;
-
-	phys_ctr = ctr & (NR_PHYS_CTRS - 1);
-
-	if (cbe_get_ctr_size(cpu, phys_ctr) == 16) {
-		phys_val = cbe_read_phys_ctr(cpu, phys_ctr);
-
-		if (ctr < NR_PHYS_CTRS)
-			val = (val << 16) | (phys_val & 0xffff);
-		else
-			val = (val & 0xffff) | (phys_val & 0xffff0000);
-	}
-
-	cbe_write_phys_ctr(cpu, phys_ctr, val);
-}
-EXPORT_SYMBOL_GPL(cbe_write_ctr);
-
-/*
- * Counter-control registers.
- * Each "logical" counter has a corresponding control register.
- */
-
-u32 cbe_read_pm07_control(u32 cpu, u32 ctr)
-{
-	u32 pm07_control = 0;
-
-	if (ctr < NR_CTRS)
-		READ_SHADOW_REG(pm07_control, pm07_control[ctr]);
-
-	return pm07_control;
-}
-EXPORT_SYMBOL_GPL(cbe_read_pm07_control);
-
-void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val)
-{
-	if (ctr < NR_CTRS)
-		WRITE_WO_MMIO(pm07_control[ctr], val);
-}
-EXPORT_SYMBOL_GPL(cbe_write_pm07_control);
-
-/*
- * Other PMU control registers. Most of these are write-only.
- */
-
-u32 cbe_read_pm(u32 cpu, enum pm_reg_name reg)
-{
-	u32 val = 0;
-
-	switch (reg) {
-	case group_control:
-		READ_SHADOW_REG(val, group_control);
-		break;
-
-	case debug_bus_control:
-		READ_SHADOW_REG(val, debug_bus_control);
-		break;
-
-	case trace_address:
-		READ_MMIO_UPPER32(val, trace_address);
-		break;
-
-	case ext_tr_timer:
-		READ_SHADOW_REG(val, ext_tr_timer);
-		break;
-
-	case pm_status:
-		READ_MMIO_UPPER32(val, pm_status);
-		break;
-
-	case pm_control:
-		READ_SHADOW_REG(val, pm_control);
-		break;
-
-	case pm_interval:
-		READ_MMIO_UPPER32(val, pm_interval);
-		break;
-
-	case pm_start_stop:
-		READ_SHADOW_REG(val, pm_start_stop);
-		break;
-	}
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_pm);
-
-void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val)
-{
-	switch (reg) {
-	case group_control:
-		WRITE_WO_MMIO(group_control, val);
-		break;
-
-	case debug_bus_control:
-		WRITE_WO_MMIO(debug_bus_control, val);
-		break;
-
-	case trace_address:
-		WRITE_WO_MMIO(trace_address, val);
-		break;
-
-	case ext_tr_timer:
-		WRITE_WO_MMIO(ext_tr_timer, val);
-		break;
-
-	case pm_status:
-		WRITE_WO_MMIO(pm_status, val);
-		break;
-
-	case pm_control:
-		WRITE_WO_MMIO(pm_control, val);
-		break;
-
-	case pm_interval:
-		WRITE_WO_MMIO(pm_interval, val);
-		break;
-
-	case pm_start_stop:
-		WRITE_WO_MMIO(pm_start_stop, val);
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_write_pm);
-
-/*
- * Get/set the size of a physical counter to either 16 or 32 bits.
- */
-
-u32 cbe_get_ctr_size(u32 cpu, u32 phys_ctr)
-{
-	u32 pm_ctrl, size = 0;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		size = (pm_ctrl & CBE_PM_16BIT_CTR(phys_ctr)) ? 16 : 32;
-	}
-
-	return size;
-}
-EXPORT_SYMBOL_GPL(cbe_get_ctr_size);
-
-void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size)
-{
-	u32 pm_ctrl;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		switch (ctr_size) {
-		case 16:
-			pm_ctrl |= CBE_PM_16BIT_CTR(phys_ctr);
-			break;
-
-		case 32:
-			pm_ctrl &= ~CBE_PM_16BIT_CTR(phys_ctr);
-			break;
-		}
-		cbe_write_pm(cpu, pm_control, pm_ctrl);
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_set_ctr_size);
-
-/*
- * Enable/disable the entire performance monitoring unit.
- * When we enable the PMU, all pending writes to counters get committed.
- */
-
-void cbe_enable_pm(u32 cpu)
-{
-	struct cbe_pmd_shadow_regs *shadow_regs;
-	u32 pm_ctrl;
-
-	shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
-	shadow_regs->counter_value_in_latch = 0;
-
-	pm_ctrl = cbe_read_pm(cpu, pm_control) | CBE_PM_ENABLE_PERF_MON;
-	cbe_write_pm(cpu, pm_control, pm_ctrl);
-}
-EXPORT_SYMBOL_GPL(cbe_enable_pm);
-
-void cbe_disable_pm(u32 cpu)
-{
-	u32 pm_ctrl;
-	pm_ctrl = cbe_read_pm(cpu, pm_control) & ~CBE_PM_ENABLE_PERF_MON;
-	cbe_write_pm(cpu, pm_control, pm_ctrl);
-}
-EXPORT_SYMBOL_GPL(cbe_disable_pm);
-
-/*
- * Reading from the trace_buffer.
- * The trace buffer is two 64-bit registers. Reading from
- * the second half automatically increments the trace_address.
- */
-
-void cbe_read_trace_buffer(u32 cpu, u64 *buf)
-{
-	struct cbe_pmd_regs __iomem *pmd_regs = cbe_get_cpu_pmd_regs(cpu);
-
-	*buf++ = in_be64(&pmd_regs->trace_buffer_0_63);
-	*buf++ = in_be64(&pmd_regs->trace_buffer_64_127);
-}
-EXPORT_SYMBOL_GPL(cbe_read_trace_buffer);
-
-/*
- * Enabling/disabling interrupts for the entire performance monitoring unit.
- */
-
-u32 cbe_get_and_clear_pm_interrupts(u32 cpu)
-{
-	/* Reading pm_status clears the interrupt bits. */
-	return cbe_read_pm(cpu, pm_status);
-}
-EXPORT_SYMBOL_GPL(cbe_get_and_clear_pm_interrupts);
-
-void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask)
-{
-	/* Set which node and thread will handle the next interrupt. */
-	iic_set_interrupt_routing(cpu, thread, 0);
-
-	/* Enable the interrupt bits in the pm_status register. */
-	if (mask)
-		cbe_write_pm(cpu, pm_status, mask);
-}
-EXPORT_SYMBOL_GPL(cbe_enable_pm_interrupts);
-
-void cbe_disable_pm_interrupts(u32 cpu)
-{
-	cbe_get_and_clear_pm_interrupts(cpu);
-	cbe_write_pm(cpu, pm_status, 0);
-}
-EXPORT_SYMBOL_GPL(cbe_disable_pm_interrupts);
-
-static irqreturn_t cbe_pm_irq(int irq, void *dev_id)
-{
-	perf_irq(get_irq_regs());
-	return IRQ_HANDLED;
-}
-
-static int __init cbe_init_pm_irq(void)
-{
-	unsigned int irq;
-	int rc, node;
-
-	for_each_online_node(node) {
-		irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI |
-					       (node << IIC_IRQ_NODE_SHIFT));
-		if (!irq) {
-			printk("ERROR: Unable to allocate irq for node %d\n",
-			       node);
-			return -EINVAL;
-		}
-
-		rc = request_irq(irq, cbe_pm_irq,
-				 0, "cbe-pmu-0", NULL);
-		if (rc) {
-			printk("ERROR: Request for irq on node %d failed\n",
-			       node);
-			return rc;
-		}
-	}
-
-	return 0;
-}
-machine_arch_initcall(cell, cbe_init_pm_irq);
-
-void cbe_sync_irq(int node)
-{
-	unsigned int irq;
-
-	irq = irq_find_mapping(NULL,
-			       IIC_IRQ_IOEX_PMI
-			       | (node << IIC_IRQ_NODE_SHIFT));
-
-	if (!irq) {
-		printk(KERN_WARNING "ERROR, unable to get existing irq %d " \
-		"for node %d\n", irq, node);
-		return;
-	}
-
-	synchronize_irq(irq);
-}
-EXPORT_SYMBOL_GPL(cbe_sync_irq);
-
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
deleted file mode 100644
index f6b87926530c..000000000000
--- a/arch/powerpc/platforms/cell/ras.c
+++ /dev/null
@@ -1,352 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2006-2008, IBM Corporation.
- */
-
-#undef DEBUG
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/reboot.h>
-#include <linux/kexec.h>
-#include <linux/crash_dump.h>
-#include <linux/of.h>
-
-#include <asm/kexec.h>
-#include <asm/reg.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/rtas.h>
-#include <asm/cell-regs.h>
-
-#include "ras.h"
-#include "pervasive.h"
-
-static void dump_fir(int cpu)
-{
-	struct cbe_pmd_regs __iomem *pregs = cbe_get_cpu_pmd_regs(cpu);
-	struct cbe_iic_regs __iomem *iregs = cbe_get_cpu_iic_regs(cpu);
-
-	if (pregs == NULL)
-		return;
-
-	/* Todo: do some nicer parsing of bits and based on them go down
-	 * to other sub-units FIRs and not only IIC
-	 */
-	printk(KERN_ERR "Global Checkstop FIR    : 0x%016llx\n",
-	       in_be64(&pregs->checkstop_fir));
-	printk(KERN_ERR "Global Recoverable FIR  : 0x%016llx\n",
-	       in_be64(&pregs->checkstop_fir));
-	printk(KERN_ERR "Global MachineCheck FIR : 0x%016llx\n",
-	       in_be64(&pregs->spec_att_mchk_fir));
-
-	if (iregs == NULL)
-		return;
-	printk(KERN_ERR "IOC FIR                 : 0x%016llx\n",
-	       in_be64(&iregs->ioc_fir));
-
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_system_error_exception)
-{
-	int cpu = smp_processor_id();
-
-	printk(KERN_ERR "System Error Interrupt on CPU %d !\n", cpu);
-	dump_fir(cpu);
-	dump_stack();
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_maintenance_exception)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Nothing implemented for the maintenance interrupt at this point
-	 */
-
-	printk(KERN_ERR "Unhandled Maintenance interrupt on CPU %d !\n", cpu);
-	dump_stack();
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_thermal_exception)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Nothing implemented for the thermal interrupt at this point
-	 */
-
-	printk(KERN_ERR "Unhandled Thermal interrupt on CPU %d !\n", cpu);
-	dump_stack();
-}
-
-static int cbe_machine_check_handler(struct pt_regs *regs)
-{
-	int cpu = smp_processor_id();
-
-	printk(KERN_ERR "Machine Check Interrupt on CPU %d !\n", cpu);
-	dump_fir(cpu);
-
-	/* No recovery from this code now, lets continue */
-	return 0;
-}
-
-struct ptcal_area {
-	struct list_head list;
-	int nid;
-	int order;
-	struct page *pages;
-};
-
-static LIST_HEAD(ptcal_list);
-
-static int ptcal_start_tok, ptcal_stop_tok;
-
-static int __init cbe_ptcal_enable_on_node(int nid, int order)
-{
-	struct ptcal_area *area;
-	int ret = -ENOMEM;
-	unsigned long addr;
-
-	if (is_kdump_kernel())
-		rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
-
-	area = kmalloc(sizeof(*area), GFP_KERNEL);
-	if (!area)
-		goto out_err;
-
-	area->nid = nid;
-	area->order = order;
-	area->pages = __alloc_pages_node(area->nid,
-						GFP_KERNEL|__GFP_THISNODE,
-						area->order);
-
-	if (!area->pages) {
-		printk(KERN_WARNING "%s: no page on node %d\n",
-			__func__, area->nid);
-		goto out_free_area;
-	}
-
-	/*
-	 * We move the ptcal area to the middle of the allocated
-	 * page, in order to avoid prefetches in memcpy and similar
-	 * functions stepping on it.
-	 */
-	addr = __pa(page_address(area->pages)) + (PAGE_SIZE >> 1);
-	printk(KERN_DEBUG "%s: enabling PTCAL on node %d address=0x%016lx\n",
-			__func__, area->nid, addr);
-
-	ret = -EIO;
-	if (rtas_call(ptcal_start_tok, 3, 1, NULL, area->nid,
-				(unsigned int)(addr >> 32),
-				(unsigned int)(addr & 0xffffffff))) {
-		printk(KERN_ERR "%s: error enabling PTCAL on node %d!\n",
-				__func__, nid);
-		goto out_free_pages;
-	}
-
-	list_add(&area->list, &ptcal_list);
-
-	return 0;
-
-out_free_pages:
-	__free_pages(area->pages, area->order);
-out_free_area:
-	kfree(area);
-out_err:
-	return ret;
-}
-
-static int __init cbe_ptcal_enable(void)
-{
-	const u32 *size;
-	struct device_node *np;
-	int order, found_mic = 0;
-
-	np = of_find_node_by_path("/rtas");
-	if (!np)
-		return -ENODEV;
-
-	size = of_get_property(np, "ibm,cbe-ptcal-size", NULL);
-	if (!size) {
-		of_node_put(np);
-		return -ENODEV;
-	}
-
-	pr_debug("%s: enabling PTCAL, size = 0x%x\n", __func__, *size);
-	order = get_order(*size);
-	of_node_put(np);
-
-	/* support for malta device trees, with be@/mic@ nodes */
-	for_each_node_by_type(np, "mic-tm") {
-		cbe_ptcal_enable_on_node(of_node_to_nid(np), order);
-		found_mic = 1;
-	}
-
-	if (found_mic)
-		return 0;
-
-	/* support for older device tree - use cpu nodes */
-	for_each_node_by_type(np, "cpu") {
-		const u32 *nid = of_get_property(np, "node-id", NULL);
-		if (!nid) {
-			printk(KERN_ERR "%s: node %pOF is missing node-id?\n",
-					__func__, np);
-			continue;
-		}
-		cbe_ptcal_enable_on_node(*nid, order);
-		found_mic = 1;
-	}
-
-	return found_mic ? 0 : -ENODEV;
-}
-
-static int cbe_ptcal_disable(void)
-{
-	struct ptcal_area *area, *tmp;
-	int ret = 0;
-
-	pr_debug("%s: disabling PTCAL\n", __func__);
-
-	list_for_each_entry_safe(area, tmp, &ptcal_list, list) {
-		/* disable ptcal on this node */
-		if (rtas_call(ptcal_stop_tok, 1, 1, NULL, area->nid)) {
-			printk(KERN_ERR "%s: error disabling PTCAL "
-					"on node %d!\n", __func__,
-					area->nid);
-			ret = -EIO;
-			continue;
-		}
-
-		/* ensure we can access the PTCAL area */
-		memset(page_address(area->pages), 0,
-				1 << (area->order + PAGE_SHIFT));
-
-		/* clean up */
-		list_del(&area->list);
-		__free_pages(area->pages, area->order);
-		kfree(area);
-	}
-
-	return ret;
-}
-
-static int cbe_ptcal_notify_reboot(struct notifier_block *nb,
-		unsigned long code, void *data)
-{
-	return cbe_ptcal_disable();
-}
-
-static void cbe_ptcal_crash_shutdown(void)
-{
-	cbe_ptcal_disable();
-}
-
-static struct notifier_block cbe_ptcal_reboot_notifier = {
-	.notifier_call = cbe_ptcal_notify_reboot
-};
-
-#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
-static int sysreset_hack;
-
-static int __init cbe_sysreset_init(void)
-{
-	struct cbe_pmd_regs __iomem *regs;
-
-	sysreset_hack = of_machine_is_compatible("IBM,CBPLUS-1.0");
-	if (!sysreset_hack)
-		return 0;
-
-	regs = cbe_get_cpu_pmd_regs(0);
-	if (!regs)
-		return 0;
-
-	/* Enable JTAG system-reset hack */
-	out_be32(&regs->fir_mode_reg,
-		in_be32(&regs->fir_mode_reg) |
-		CBE_PMD_FIR_MODE_M8);
-
-	return 0;
-}
-device_initcall(cbe_sysreset_init);
-
-int cbe_sysreset_hack(void)
-{
-	struct cbe_pmd_regs __iomem *regs;
-
-	/*
-	 * The BMC can inject user triggered system reset exceptions,
-	 * but cannot set the system reset reason in srr1,
-	 * so check an extra register here.
-	 */
-	if (sysreset_hack && (smp_processor_id() == 0)) {
-		regs = cbe_get_cpu_pmd_regs(0);
-		if (!regs)
-			return 0;
-		if (in_be64(&regs->ras_esc_0) & 0x0000ffff) {
-			out_be64(&regs->ras_esc_0, 0);
-			return 0;
-		}
-	}
-	return 1;
-}
-#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
-
-static int __init cbe_ptcal_init(void)
-{
-	int ret;
-	ptcal_start_tok = rtas_function_token(RTAS_FN_IBM_CBE_START_PTCAL);
-	ptcal_stop_tok = rtas_function_token(RTAS_FN_IBM_CBE_STOP_PTCAL);
-
-	if (ptcal_start_tok == RTAS_UNKNOWN_SERVICE
-			|| ptcal_stop_tok == RTAS_UNKNOWN_SERVICE)
-		return -ENODEV;
-
-	ret = register_reboot_notifier(&cbe_ptcal_reboot_notifier);
-	if (ret)
-		goto out1;
-
-	ret = crash_shutdown_register(&cbe_ptcal_crash_shutdown);
-	if (ret)
-		goto out2;
-
-	return cbe_ptcal_enable();
-
-out2:
-	unregister_reboot_notifier(&cbe_ptcal_reboot_notifier);
-out1:
-	printk(KERN_ERR "Can't disable PTCAL, so not enabling\n");
-	return ret;
-}
-
-arch_initcall(cbe_ptcal_init);
-
-void __init cbe_ras_init(void)
-{
-	unsigned long hid0;
-
-	/*
-	 * Enable System Error & thermal interrupts and wakeup conditions
-	 */
-
-	hid0 = mfspr(SPRN_HID0);
-	hid0 |= HID0_CBE_THERM_INT_EN | HID0_CBE_THERM_WAKEUP |
-		HID0_CBE_SYSERR_INT_EN | HID0_CBE_SYSERR_WAKEUP;
-	mtspr(SPRN_HID0, hid0);
-	mb();
-
-	/*
-	 * Install machine check handler. Leave setting of precise mode to
-	 * what the firmware did for now
-	 */
-	ppc_md.machine_check_exception = cbe_machine_check_handler;
-	mb();
-
-	/*
-	 * For now, we assume that IOC_FIR is already set to forward some
-	 * error conditions to the System Error handler. If that is not true
-	 * then it will have to be fixed up here.
-	 */
-}
diff --git a/arch/powerpc/platforms/cell/ras.h b/arch/powerpc/platforms/cell/ras.h
deleted file mode 100644
index 226dbd48efad..000000000000
--- a/arch/powerpc/platforms/cell/ras.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef RAS_H
-#define RAS_H
-
-#include <asm/interrupt.h>
-
-DECLARE_INTERRUPT_HANDLER(cbe_system_error_exception);
-DECLARE_INTERRUPT_HANDLER(cbe_maintenance_exception);
-DECLARE_INTERRUPT_HANDLER(cbe_thermal_exception);
-
-extern void cbe_ras_init(void);
-
-#endif /* RAS_H */
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
deleted file mode 100644
index f64a1ef98aa8..000000000000
--- a/arch/powerpc/platforms/cell/setup.c
+++ /dev/null
@@ -1,274 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/arch/powerpc/platforms/cell/cell_setup.c
- *
- *  Copyright (C) 1995  Linus Torvalds
- *  Adapted from 'alpha' version by Gary Thomas
- *  Modified by Cort Dougan (cort@cs.nmt.edu)
- *  Modified by PPC64 Team, IBM Corp
- *  Modified by Cell Team, IBM Deutschland Entwicklung GmbH
- */
-#undef DEBUG
-
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/export.h>
-#include <linux/unistd.h>
-#include <linux/user.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/seq_file.h>
-#include <linux/root_dev.h>
-#include <linux/console.h>
-#include <linux/mutex.h>
-#include <linux/memory_hotplug.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-
-#include <asm/mmu.h>
-#include <asm/processor.h>
-#include <asm/io.h>
-#include <asm/rtas.h>
-#include <asm/pci-bridge.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-#include <asm/machdep.h>
-#include <asm/time.h>
-#include <asm/nvram.h>
-#include <asm/cputable.h>
-#include <asm/ppc-pci.h>
-#include <asm/irq.h>
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-#include <asm/cell-regs.h>
-#include <asm/io-workarounds.h>
-
-#include "cell.h"
-#include "interrupt.h"
-#include "pervasive.h"
-#include "ras.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-static void cell_show_cpuinfo(struct seq_file *m)
-{
-	struct device_node *root;
-	const char *model = "";
-
-	root = of_find_node_by_path("/");
-	if (root)
-		model = of_get_property(root, "model", NULL);
-	seq_printf(m, "machine\t\t: CHRP %s\n", model);
-	of_node_put(root);
-}
-
-static void cell_progress(char *s, unsigned short hex)
-{
-	printk("*** %04x : %s\n", hex, s ? s : "");
-}
-
-static void cell_fixup_pcie_rootcomplex(struct pci_dev *dev)
-{
-	struct pci_controller *hose;
-	const char *s;
-	int i;
-
-	if (!machine_is(cell))
-		return;
-
-	/* We're searching for a direct child of the PHB */
-	if (dev->bus->self != NULL || dev->devfn != 0)
-		return;
-
-	hose = pci_bus_to_host(dev->bus);
-	if (hose == NULL)
-		return;
-
-	/* Only on PCIE */
-	if (!of_device_is_compatible(hose->dn, "pciex"))
-		return;
-
-	/* And only on axon */
-	s = of_get_property(hose->dn, "model", NULL);
-	if (!s || strcmp(s, "Axon") != 0)
-		return;
-
-	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
-		dev->resource[i].start = dev->resource[i].end = 0;
-		dev->resource[i].flags = 0;
-	}
-
-	printk(KERN_DEBUG "PCI: Hiding resources on Axon PCIE RC %s\n",
-	       pci_name(dev));
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, cell_fixup_pcie_rootcomplex);
-
-static int cell_setup_phb(struct pci_controller *phb)
-{
-	const char *model;
-	struct device_node *np;
-
-	int rc = rtas_setup_phb(phb);
-	if (rc)
-		return rc;
-
-	phb->controller_ops = cell_pci_controller_ops;
-
-	np = phb->dn;
-	model = of_get_property(np, "model", NULL);
-	if (model == NULL || !of_node_name_eq(np, "pci"))
-		return 0;
-
-	/* Setup workarounds for spider */
-	if (strcmp(model, "Spider"))
-		return 0;
-
-	iowa_register_bus(phb, &spiderpci_ops, &spiderpci_iowa_init,
-				  (void *)SPIDER_PCI_REG_BASE);
-	return 0;
-}
-
-static const struct of_device_id cell_bus_ids[] __initconst = {
-	{ .type = "soc", },
-	{ .compatible = "soc", },
-	{ .type = "spider", },
-	{ .type = "axon", },
-	{ .type = "plb5", },
-	{ .type = "plb4", },
-	{ .type = "opb", },
-	{ .type = "ebc", },
-	{},
-};
-
-static int __init cell_publish_devices(void)
-{
-	struct device_node *root = of_find_node_by_path("/");
-	struct device_node *np;
-	int node;
-
-	/* Publish OF platform devices for southbridge IOs */
-	of_platform_bus_probe(NULL, cell_bus_ids, NULL);
-
-	/* On spider based blades, we need to manually create the OF
-	 * platform devices for the PCI host bridges
-	 */
-	for_each_child_of_node(root, np) {
-		if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "pciex"))
-			continue;
-		of_platform_device_create(np, NULL, NULL);
-	}
-
-	of_node_put(root);
-
-	/* There is no device for the MIC memory controller, thus we create
-	 * a platform device for it to attach the EDAC driver to.
-	 */
-	for_each_online_node(node) {
-		if (cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(node)) == NULL)
-			continue;
-		platform_device_register_simple("cbe-mic", node, NULL, 0);
-	}
-
-	return 0;
-}
-machine_subsys_initcall(cell, cell_publish_devices);
-
-static void __init mpic_init_IRQ(void)
-{
-	struct device_node *dn;
-	struct mpic *mpic;
-
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (!of_device_is_compatible(dn, "CBEA,platform-open-pic"))
-			continue;
-
-		/* The MPIC driver will get everything it needs from the
-		 * device-tree, just pass 0 to all arguments
-		 */
-		mpic = mpic_alloc(dn, 0, MPIC_SECONDARY | MPIC_NO_RESET,
-				0, 0, " MPIC     ");
-		if (mpic == NULL)
-			continue;
-		mpic_init(mpic);
-	}
-}
-
-
-static void __init cell_init_irq(void)
-{
-	iic_init_IRQ();
-	spider_init_IRQ();
-	mpic_init_IRQ();
-}
-
-static void __init cell_set_dabrx(void)
-{
-	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
-}
-
-static void __init cell_setup_arch(void)
-{
-#ifdef CONFIG_SPU_BASE
-	spu_priv1_ops = &spu_priv1_mmio_ops;
-	spu_management_ops = &spu_management_of_ops;
-#endif
-
-	cbe_regs_init();
-
-	cell_set_dabrx();
-
-#ifdef CONFIG_CBE_RAS
-	cbe_ras_init();
-#endif
-
-#ifdef CONFIG_SMP
-	smp_init_cell();
-#endif
-	/* init to some ~sane value until calibrate_delay() runs */
-	loops_per_jiffy = 50000000;
-
-	/* Find and initialize PCI host bridges */
-	init_pci_config_tokens();
-
-	cbe_pervasive_init();
-
-	mmio_nvram_init();
-}
-
-static int __init cell_probe(void)
-{
-	if (!of_machine_is_compatible("IBM,CBEA") &&
-	    !of_machine_is_compatible("IBM,CPBW-1.0"))
-		return 0;
-
-	pm_power_off = rtas_power_off;
-
-	return 1;
-}
-
-define_machine(cell) {
-	.name			= "Cell",
-	.probe			= cell_probe,
-	.setup_arch		= cell_setup_arch,
-	.show_cpuinfo		= cell_show_cpuinfo,
-	.restart		= rtas_restart,
-	.halt			= rtas_halt,
-	.get_boot_time		= rtas_get_boot_time,
-	.get_rtc_time		= rtas_get_rtc_time,
-	.set_rtc_time		= rtas_set_rtc_time,
-	.progress		= cell_progress,
-	.init_IRQ       	= cell_init_irq,
-	.pci_setup_phb		= cell_setup_phb,
-};
-
-struct pci_controller_ops cell_pci_controller_ops;
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
deleted file mode 100644
index 0e8f20ecca08..000000000000
--- a/arch/powerpc/platforms/cell/smp.c
+++ /dev/null
@@ -1,162 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SMP support for BPA machines.
- *
- * Dave Engebretsen, Peter Bergner, and
- * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
- *
- * Plus various changes from other IBM teams...
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/cache.h>
-#include <linux/err.h>
-#include <linux/device.h>
-#include <linux/cpu.h>
-#include <linux/pgtable.h>
-
-#include <asm/ptrace.h>
-#include <linux/atomic.h>
-#include <asm/irq.h>
-#include <asm/page.h>
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/paca.h>
-#include <asm/machdep.h>
-#include <asm/cputable.h>
-#include <asm/firmware.h>
-#include <asm/rtas.h>
-#include <asm/cputhreads.h>
-#include <asm/text-patching.h>
-
-#include "interrupt.h"
-#include <asm/udbg.h>
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-/*
- * The Primary thread of each non-boot processor was started from the OF client
- * interface by prom_hold_cpus and is spinning on secondary_hold_spinloop.
- */
-static cpumask_t of_spin_map;
-
-/**
- * smp_startup_cpu() - start the given cpu
- * @lcpu: Logical CPU ID of the CPU to be started.
- *
- * At boot time, there is nothing to do for primary threads which were
- * started from Open Firmware.  For anything else, call RTAS with the
- * appropriate start location.
- *
- * Returns:
- *	0	- failure
- *	1	- success
- */
-static inline int smp_startup_cpu(unsigned int lcpu)
-{
-	int status;
-	unsigned long start_here =
-			__pa(ppc_function_entry(generic_secondary_smp_init));
-	unsigned int pcpu;
-	int start_cpu;
-
-	if (cpumask_test_cpu(lcpu, &of_spin_map))
-		/* Already started by OF and sitting in spin loop */
-		return 1;
-
-	pcpu = get_hard_smp_processor_id(lcpu);
-
-	/*
-	 * If the RTAS start-cpu token does not exist then presume the
-	 * cpu is already spinning.
-	 */
-	start_cpu = rtas_function_token(RTAS_FN_START_CPU);
-	if (start_cpu == RTAS_UNKNOWN_SERVICE)
-		return 1;
-
-	status = rtas_call(start_cpu, 3, 1, NULL, pcpu, start_here, lcpu);
-	if (status != 0) {
-		printk(KERN_ERR "start-cpu failed: %i\n", status);
-		return 0;
-	}
-
-	return 1;
-}
-
-static void smp_cell_setup_cpu(int cpu)
-{
-	if (cpu != boot_cpuid)
-		iic_setup_cpu();
-
-	/*
-	 * change default DABRX to allow user watchpoints
-	 */
-	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
-}
-
-static int smp_cell_kick_cpu(int nr)
-{
-	if (nr < 0 || nr >= nr_cpu_ids)
-		return -EINVAL;
-
-	if (!smp_startup_cpu(nr))
-		return -ENOENT;
-
-	/*
-	 * The processor is currently spinning, waiting for the
-	 * cpu_start field to become non-zero After we set cpu_start,
-	 * the processor will continue on to secondary_start
-	 */
-	paca_ptrs[nr]->cpu_start = 1;
-
-	return 0;
-}
-
-static struct smp_ops_t bpa_iic_smp_ops = {
-	.message_pass	= iic_message_pass,
-	.probe		= iic_request_IPIs,
-	.kick_cpu	= smp_cell_kick_cpu,
-	.setup_cpu	= smp_cell_setup_cpu,
-	.cpu_bootable	= smp_generic_cpu_bootable,
-};
-
-/* This is called very early */
-void __init smp_init_cell(void)
-{
-	int i;
-
-	DBG(" -> smp_init_cell()\n");
-
-	smp_ops = &bpa_iic_smp_ops;
-
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) {
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, &of_spin_map);
-		}
-	} else
-		cpumask_copy(&of_spin_map, cpu_present_mask);
-
-	cpumask_clear_cpu(boot_cpuid, &of_spin_map);
-
-	/* Non-lpar has additional take/give timebase */
-	if (rtas_function_token(RTAS_FN_FREEZE_TIME_BASE) != RTAS_UNKNOWN_SERVICE) {
-		smp_ops->give_timebase = rtas_give_timebase;
-		smp_ops->take_timebase = rtas_take_timebase;
-	}
-
-	DBG(" <- smp_init_cell()\n");
-}
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
deleted file mode 100644
index 68439445b1c3..000000000000
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ /dev/null
@@ -1,170 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * IO workarounds for PCI on Celleb/Cell platform
- *
- * (C) Copyright 2006-2007 TOSHIBA CORPORATION
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/of_address.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-
-#include <asm/ppc-pci.h>
-#include <asm/pci-bridge.h>
-#include <asm/io-workarounds.h>
-
-#define SPIDER_PCI_DISABLE_PREFETCH
-
-struct spiderpci_iowa_private {
-	void __iomem *regs;
-};
-
-static void spiderpci_io_flush(struct iowa_bus *bus)
-{
-	struct spiderpci_iowa_private *priv;
-
-	priv = bus->private;
-	in_be32(priv->regs + SPIDER_PCI_DUMMY_READ);
-	iosync();
-}
-
-#define SPIDER_PCI_MMIO_READ(name, ret)					\
-static ret spiderpci_##name(const PCI_IO_ADDR addr)			\
-{									\
-	ret val = __do_##name(addr);					\
-	spiderpci_io_flush(iowa_mem_find_bus(addr));			\
-	return val;							\
-}
-
-#define SPIDER_PCI_MMIO_READ_STR(name)					\
-static void spiderpci_##name(const PCI_IO_ADDR addr, void *buf, 	\
-			     unsigned long count)			\
-{									\
-	__do_##name(addr, buf, count);					\
-	spiderpci_io_flush(iowa_mem_find_bus(addr));			\
-}
-
-SPIDER_PCI_MMIO_READ(readb, u8)
-SPIDER_PCI_MMIO_READ(readw, u16)
-SPIDER_PCI_MMIO_READ(readl, u32)
-SPIDER_PCI_MMIO_READ(readq, u64)
-SPIDER_PCI_MMIO_READ(readw_be, u16)
-SPIDER_PCI_MMIO_READ(readl_be, u32)
-SPIDER_PCI_MMIO_READ(readq_be, u64)
-SPIDER_PCI_MMIO_READ_STR(readsb)
-SPIDER_PCI_MMIO_READ_STR(readsw)
-SPIDER_PCI_MMIO_READ_STR(readsl)
-
-static void spiderpci_memcpy_fromio(void *dest, const PCI_IO_ADDR src,
-				    unsigned long n)
-{
-	__do_memcpy_fromio(dest, src, n);
-	spiderpci_io_flush(iowa_mem_find_bus(src));
-}
-
-static int __init spiderpci_pci_setup_chip(struct pci_controller *phb,
-					   void __iomem *regs)
-{
-	void *dummy_page_va;
-	dma_addr_t dummy_page_da;
-
-#ifdef SPIDER_PCI_DISABLE_PREFETCH
-	u32 val = in_be32(regs + SPIDER_PCI_VCI_CNTL_STAT);
-	pr_debug("SPIDER_IOWA:PVCI_Control_Status was 0x%08x\n", val);
-	out_be32(regs + SPIDER_PCI_VCI_CNTL_STAT, val | 0x8);
-#endif /* SPIDER_PCI_DISABLE_PREFETCH */
-
-	/* setup dummy read */
-	/*
-	 * On CellBlade, we can't know that which XDR memory is used by
-	 * kmalloc() to allocate dummy_page_va.
-	 * In order to improve the performance, the XDR which is used to
-	 * allocate dummy_page_va is the nearest the spider-pci.
-	 * We have to select the CBE which is the nearest the spider-pci
-	 * to allocate memory from the best XDR, but I don't know that
-	 * how to do.
-	 *
-	 * Celleb does not have this problem, because it has only one XDR.
-	 */
-	dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!dummy_page_va) {
-		pr_err("SPIDERPCI-IOWA:Alloc dummy_page_va failed.\n");
-		return -1;
-	}
-
-	dummy_page_da = dma_map_single(phb->parent, dummy_page_va,
-				       PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(phb->parent, dummy_page_da)) {
-		pr_err("SPIDER-IOWA:Map dummy page filed.\n");
-		kfree(dummy_page_va);
-		return -1;
-	}
-
-	out_be32(regs + SPIDER_PCI_DUMMY_READ_BASE, dummy_page_da);
-
-	return 0;
-}
-
-int __init spiderpci_iowa_init(struct iowa_bus *bus, void *data)
-{
-	void __iomem *regs = NULL;
-	struct spiderpci_iowa_private *priv;
-	struct device_node *np = bus->phb->dn;
-	struct resource r;
-	unsigned long offset = (unsigned long)data;
-
-	pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%pOF)\n",
-		 np);
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		pr_err("SPIDERPCI-IOWA:"
-		       "Can't allocate struct spiderpci_iowa_private");
-		return -1;
-	}
-
-	if (of_address_to_resource(np, 0, &r)) {
-		pr_err("SPIDERPCI-IOWA:Can't get resource.\n");
-		goto error;
-	}
-
-	regs = ioremap(r.start + offset, SPIDER_PCI_REG_SIZE);
-	if (!regs) {
-		pr_err("SPIDERPCI-IOWA:ioremap failed.\n");
-		goto error;
-	}
-	priv->regs = regs;
-	bus->private = priv;
-
-	if (spiderpci_pci_setup_chip(bus->phb, regs))
-		goto error;
-
-	return 0;
-
-error:
-	kfree(priv);
-	bus->private = NULL;
-
-	if (regs)
-		iounmap(regs);
-
-	return -1;
-}
-
-struct ppc_pci_io spiderpci_ops = {
-	.readb = spiderpci_readb,
-	.readw = spiderpci_readw,
-	.readl = spiderpci_readl,
-	.readq = spiderpci_readq,
-	.readw_be = spiderpci_readw_be,
-	.readl_be = spiderpci_readl_be,
-	.readq_be = spiderpci_readq_be,
-	.readsb = spiderpci_readsb,
-	.readsw = spiderpci_readsw,
-	.readsl = spiderpci_readsl,
-	.memcpy_fromio = spiderpci_memcpy_fromio,
-};
-
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
deleted file mode 100644
index 11df737c8c6a..000000000000
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ /dev/null
@@ -1,344 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * External Interrupt Controller on Spider South Bridge
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Arnd Bergmann <arndb@de.ibm.com>
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/ioport.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-
-#include "interrupt.h"
-
-/* register layout taken from Spider spec, table 7.4-4 */
-enum {
-	TIR_DEN		= 0x004, /* Detection Enable Register */
-	TIR_MSK		= 0x084, /* Mask Level Register */
-	TIR_EDC		= 0x0c0, /* Edge Detection Clear Register */
-	TIR_PNDA	= 0x100, /* Pending Register A */
-	TIR_PNDB	= 0x104, /* Pending Register B */
-	TIR_CS		= 0x144, /* Current Status Register */
-	TIR_LCSA	= 0x150, /* Level Current Status Register A */
-	TIR_LCSB	= 0x154, /* Level Current Status Register B */
-	TIR_LCSC	= 0x158, /* Level Current Status Register C */
-	TIR_LCSD	= 0x15c, /* Level Current Status Register D */
-	TIR_CFGA	= 0x200, /* Setting Register A0 */
-	TIR_CFGB	= 0x204, /* Setting Register B0 */
-			/* 0x208 ... 0x3ff Setting Register An/Bn */
-	TIR_PPNDA	= 0x400, /* Packet Pending Register A */
-	TIR_PPNDB	= 0x404, /* Packet Pending Register B */
-	TIR_PIERA	= 0x408, /* Packet Output Error Register A */
-	TIR_PIERB	= 0x40c, /* Packet Output Error Register B */
-	TIR_PIEN	= 0x444, /* Packet Output Enable Register */
-	TIR_PIPND	= 0x454, /* Packet Output Pending Register */
-	TIRDID		= 0x484, /* Spider Device ID Register */
-	REISTIM		= 0x500, /* Reissue Command Timeout Time Setting */
-	REISTIMEN	= 0x504, /* Reissue Command Timeout Setting */
-	REISWAITEN	= 0x508, /* Reissue Wait Control*/
-};
-
-#define SPIDER_CHIP_COUNT	4
-#define SPIDER_SRC_COUNT	64
-#define SPIDER_IRQ_INVALID	63
-
-struct spider_pic {
-	struct irq_domain		*host;
-	void __iomem		*regs;
-	unsigned int		node_id;
-};
-static struct spider_pic spider_pics[SPIDER_CHIP_COUNT];
-
-static struct spider_pic *spider_irq_data_to_pic(struct irq_data *d)
-{
-	return irq_data_get_irq_chip_data(d);
-}
-
-static void __iomem *spider_get_irq_config(struct spider_pic *pic,
-					   unsigned int src)
-{
-	return pic->regs + TIR_CFGA + 8 * src;
-}
-
-static void spider_unmask_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
-
-	out_be32(cfg, in_be32(cfg) | 0x30000000u);
-}
-
-static void spider_mask_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
-
-	out_be32(cfg, in_be32(cfg) & ~0x30000000u);
-}
-
-static void spider_ack_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	unsigned int src = irqd_to_hwirq(d);
-
-	/* Reset edge detection logic if necessary
-	 */
-	if (irqd_is_level_type(d))
-		return;
-
-	/* Only interrupts 47 to 50 can be set to edge */
-	if (src < 47 || src > 50)
-		return;
-
-	/* Perform the clear of the edge logic */
-	out_be32(pic->regs + TIR_EDC, 0x100 | (src & 0xf));
-}
-
-static int spider_set_irq_type(struct irq_data *d, unsigned int type)
-{
-	unsigned int sense = type & IRQ_TYPE_SENSE_MASK;
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	unsigned int hw = irqd_to_hwirq(d);
-	void __iomem *cfg = spider_get_irq_config(pic, hw);
-	u32 old_mask;
-	u32 ic;
-
-	/* Note that only level high is supported for most interrupts */
-	if (sense != IRQ_TYPE_NONE && sense != IRQ_TYPE_LEVEL_HIGH &&
-	    (hw < 47 || hw > 50))
-		return -EINVAL;
-
-	/* Decode sense type */
-	switch(sense) {
-	case IRQ_TYPE_EDGE_RISING:
-		ic = 0x3;
-		break;
-	case IRQ_TYPE_EDGE_FALLING:
-		ic = 0x2;
-		break;
-	case IRQ_TYPE_LEVEL_LOW:
-		ic = 0x0;
-		break;
-	case IRQ_TYPE_LEVEL_HIGH:
-	case IRQ_TYPE_NONE:
-		ic = 0x1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Configure the source. One gross hack that was there before and
-	 * that I've kept around is the priority to the BE which I set to
-	 * be the same as the interrupt source number. I don't know whether
-	 * that's supposed to make any kind of sense however, we'll have to
-	 * decide that, but for now, I'm not changing the behaviour.
-	 */
-	old_mask = in_be32(cfg) & 0x30000000u;
-	out_be32(cfg, old_mask | (ic << 24) | (0x7 << 16) |
-		 (pic->node_id << 4) | 0xe);
-	out_be32(cfg + 4, (0x2 << 16) | (hw & 0xff));
-
-	return 0;
-}
-
-static struct irq_chip spider_pic = {
-	.name = "SPIDER",
-	.irq_unmask = spider_unmask_irq,
-	.irq_mask = spider_mask_irq,
-	.irq_ack = spider_ack_irq,
-	.irq_set_type = spider_set_irq_type,
-};
-
-static int spider_host_map(struct irq_domain *h, unsigned int virq,
-			irq_hw_number_t hw)
-{
-	irq_set_chip_data(virq, h->host_data);
-	irq_set_chip_and_handler(virq, &spider_pic, handle_level_irq);
-
-	/* Set default irq type */
-	irq_set_irq_type(virq, IRQ_TYPE_NONE);
-
-	return 0;
-}
-
-static int spider_host_xlate(struct irq_domain *h, struct device_node *ct,
-			   const u32 *intspec, unsigned int intsize,
-			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-
-{
-	/* Spider interrupts have 2 cells, first is the interrupt source,
-	 * second, well, I don't know for sure yet ... We mask the top bits
-	 * because old device-trees encode a node number in there
-	 */
-	*out_hwirq = intspec[0] & 0x3f;
-	*out_flags = IRQ_TYPE_LEVEL_HIGH;
-	return 0;
-}
-
-static const struct irq_domain_ops spider_host_ops = {
-	.map = spider_host_map,
-	.xlate = spider_host_xlate,
-};
-
-static void spider_irq_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct spider_pic *pic = irq_desc_get_handler_data(desc);
-	unsigned int cs;
-
-	cs = in_be32(pic->regs + TIR_CS) >> 24;
-	if (cs != SPIDER_IRQ_INVALID)
-		generic_handle_domain_irq(pic->host, cs);
-
-	chip->irq_eoi(&desc->irq_data);
-}
-
-/* For hooking up the cascade we have a problem. Our device-tree is
- * crap and we don't know on which BE iic interrupt we are hooked on at
- * least not the "standard" way. We can reconstitute it based on two
- * informations though: which BE node we are connected to and whether
- * we are connected to IOIF0 or IOIF1. Right now, we really only care
- * about the IBM cell blade and we know that its firmware gives us an
- * interrupt-map property which is pretty strange.
- */
-static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
-{
-	unsigned int virq;
-	const u32 *imap, *tmp;
-	int imaplen, intsize, unit;
-	struct device_node *iic;
-	struct device_node *of_node;
-
-	of_node = irq_domain_get_of_node(pic->host);
-
-	/* First, we check whether we have a real "interrupts" in the device
-	 * tree in case the device-tree is ever fixed
-	 */
-	virq = irq_of_parse_and_map(of_node, 0);
-	if (virq)
-		return virq;
-
-	/* Now do the horrible hacks */
-	tmp = of_get_property(of_node, "#interrupt-cells", NULL);
-	if (tmp == NULL)
-		return 0;
-	intsize = *tmp;
-	imap = of_get_property(of_node, "interrupt-map", &imaplen);
-	if (imap == NULL || imaplen < (intsize + 1))
-		return 0;
-	iic = of_find_node_by_phandle(imap[intsize]);
-	if (iic == NULL)
-		return 0;
-	imap += intsize + 1;
-	tmp = of_get_property(iic, "#interrupt-cells", NULL);
-	if (tmp == NULL) {
-		of_node_put(iic);
-		return 0;
-	}
-	intsize = *tmp;
-	/* Assume unit is last entry of interrupt specifier */
-	unit = imap[intsize - 1];
-	/* Ok, we have a unit, now let's try to get the node */
-	tmp = of_get_property(iic, "ibm,interrupt-server-ranges", NULL);
-	if (tmp == NULL) {
-		of_node_put(iic);
-		return 0;
-	}
-	/* ugly as hell but works for now */
-	pic->node_id = (*tmp) >> 1;
-	of_node_put(iic);
-
-	/* Ok, now let's get cracking. You may ask me why I just didn't match
-	 * the iic host from the iic OF node, but that way I'm still compatible
-	 * with really really old old firmwares for which we don't have a node
-	 */
-	/* Manufacture an IIC interrupt number of class 2 */
-	virq = irq_create_mapping(NULL,
-				  (pic->node_id << IIC_IRQ_NODE_SHIFT) |
-				  (2 << IIC_IRQ_CLASS_SHIFT) |
-				  unit);
-	if (!virq)
-		printk(KERN_ERR "spider_pic: failed to map cascade !");
-	return virq;
-}
-
-
-static void __init spider_init_one(struct device_node *of_node, int chip,
-				   unsigned long addr)
-{
-	struct spider_pic *pic = &spider_pics[chip];
-	int i, virq;
-
-	/* Map registers */
-	pic->regs = ioremap(addr, 0x1000);
-	if (pic->regs == NULL)
-		panic("spider_pic: can't map registers !");
-
-	/* Allocate a host */
-	pic->host = irq_domain_add_linear(of_node, SPIDER_SRC_COUNT,
-					  &spider_host_ops, pic);
-	if (pic->host == NULL)
-		panic("spider_pic: can't allocate irq host !");
-
-	/* Go through all sources and disable them */
-	for (i = 0; i < SPIDER_SRC_COUNT; i++) {
-		void __iomem *cfg = pic->regs + TIR_CFGA + 8 * i;
-		out_be32(cfg, in_be32(cfg) & ~0x30000000u);
-	}
-
-	/* do not mask any interrupts because of level */
-	out_be32(pic->regs + TIR_MSK, 0x0);
-
-	/* enable interrupt packets to be output */
-	out_be32(pic->regs + TIR_PIEN, in_be32(pic->regs + TIR_PIEN) | 0x1);
-
-	/* Hook up the cascade interrupt to the iic and nodeid */
-	virq = spider_find_cascade_and_node(pic);
-	if (!virq)
-		return;
-	irq_set_handler_data(virq, pic);
-	irq_set_chained_handler(virq, spider_irq_cascade);
-
-	printk(KERN_INFO "spider_pic: node %d, addr: 0x%lx %pOF\n",
-	       pic->node_id, addr, of_node);
-
-	/* Enable the interrupt detection enable bit. Do this last! */
-	out_be32(pic->regs + TIR_DEN, in_be32(pic->regs + TIR_DEN) | 0x1);
-}
-
-void __init spider_init_IRQ(void)
-{
-	struct resource r;
-	struct device_node *dn;
-	int chip = 0;
-
-	/* XXX node numbers are totally bogus. We _hope_ we get the device
-	 * nodes in the right order here but that's definitely not guaranteed,
-	 * we need to get the node from the device tree instead.
-	 * There is currently no proper property for it (but our whole
-	 * device-tree is bogus anyway) so all we can do is pray or maybe test
-	 * the address and deduce the node-id
-	 */
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (of_device_is_compatible(dn, "CBEA,platform-spider-pic")) {
-			if (of_address_to_resource(dn, 0, &r)) {
-				printk(KERN_WARNING "spider-pic: Failed\n");
-				continue;
-			}
-		} else if (of_device_is_compatible(dn, "sti,platform-spider-pic")
-			   && (chip < 2)) {
-			static long hard_coded_pics[] =
-				{ 0x24000008000ul, 0x34000008000ul};
-			r.start = hard_coded_pics[chip];
-		} else
-			continue;
-		spider_init_one(dn, chip++, r.start);
-	}
-}
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index dea6f0f25897..2c07387201d0 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -23,7 +23,6 @@
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
 #include <asm/spu_csa.h>
-#include <asm/xmon.h>
 #include <asm/kexec.h>
 
 const struct spu_management_ops *spu_management_ops;
@@ -772,7 +771,6 @@ static int __init init_spu_base(void)
 		fb_append_extra_logo(&logo_spe_clut224, ret);
 
 	mutex_lock(&spu_full_list_mutex);
-	xmon_register_spus(&spu_full_list);
 	crash_register_spus(&spu_full_list);
 	mutex_unlock(&spu_full_list_mutex);
 	spu_add_dev_attr(&dev_attr_stat);
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
deleted file mode 100644
index f464a1f2e568..000000000000
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ /dev/null
@@ -1,530 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * spu management operations for of based platforms
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- * Copyright 2006 Sony Corp.
- * (C) Copyright 2007 TOSHIBA CORPORATION
- */
-
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/export.h>
-#include <linux/ptrace.h>
-#include <linux/wait.h>
-#include <linux/mm.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/firmware.h>
-
-#include "spufs/spufs.h"
-#include "interrupt.h"
-#include "spu_priv1_mmio.h"
-
-struct device_node *spu_devnode(struct spu *spu)
-{
-	return spu->devnode;
-}
-
-EXPORT_SYMBOL_GPL(spu_devnode);
-
-static u64 __init find_spu_unit_number(struct device_node *spe)
-{
-	const unsigned int *prop;
-	int proplen;
-
-	/* new device trees should provide the physical-id attribute */
-	prop = of_get_property(spe, "physical-id", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	/* celleb device tree provides the unit-id */
-	prop = of_get_property(spe, "unit-id", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	/* legacy device trees provide the id in the reg attribute */
-	prop = of_get_property(spe, "reg", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	return 0;
-}
-
-static void spu_unmap(struct spu *spu)
-{
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
-		iounmap(spu->priv1);
-	iounmap(spu->priv2);
-	iounmap(spu->problem);
-	iounmap((__force u8 __iomem *)spu->local_store);
-}
-
-static int __init spu_map_interrupts_old(struct spu *spu,
-	struct device_node *np)
-{
-	unsigned int isrc;
-	const u32 *tmp;
-	int nid;
-
-	/* Get the interrupt source unit from the device-tree */
-	tmp = of_get_property(np, "isrc", NULL);
-	if (!tmp)
-		return -ENODEV;
-	isrc = tmp[0];
-
-	tmp = of_get_property(np->parent->parent, "node-id", NULL);
-	if (!tmp) {
-		printk(KERN_WARNING "%s: can't find node-id\n", __func__);
-		nid = spu->node;
-	} else
-		nid = tmp[0];
-
-	/* Add the node number */
-	isrc |= nid << IIC_IRQ_NODE_SHIFT;
-
-	/* Now map interrupts of all 3 classes */
-	spu->irqs[0] = irq_create_mapping(NULL, IIC_IRQ_CLASS_0 | isrc);
-	spu->irqs[1] = irq_create_mapping(NULL, IIC_IRQ_CLASS_1 | isrc);
-	spu->irqs[2] = irq_create_mapping(NULL, IIC_IRQ_CLASS_2 | isrc);
-
-	/* Right now, we only fail if class 2 failed */
-	if (!spu->irqs[2])
-		return -EINVAL;
-
-	return 0;
-}
-
-static void __iomem * __init spu_map_prop_old(struct spu *spu,
-					      struct device_node *n,
-					      const char *name)
-{
-	const struct address_prop {
-		unsigned long address;
-		unsigned int len;
-	} __attribute__((packed)) *prop;
-	int proplen;
-
-	prop = of_get_property(n, name, &proplen);
-	if (prop == NULL || proplen != sizeof (struct address_prop))
-		return NULL;
-
-	return ioremap(prop->address, prop->len);
-}
-
-static int __init spu_map_device_old(struct spu *spu)
-{
-	struct device_node *node = spu->devnode;
-	const char *prop;
-	int ret;
-
-	ret = -ENODEV;
-	spu->name = of_get_property(node, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	prop = of_get_property(node, "local-store", NULL);
-	if (!prop)
-		goto out;
-	spu->local_store_phys = *(unsigned long *)prop;
-
-	/* we use local store as ram, not io memory */
-	spu->local_store = (void __force *)
-		spu_map_prop_old(spu, node, "local-store");
-	if (!spu->local_store)
-		goto out;
-
-	prop = of_get_property(node, "problem", NULL);
-	if (!prop)
-		goto out_unmap;
-	spu->problem_phys = *(unsigned long *)prop;
-
-	spu->problem = spu_map_prop_old(spu, node, "problem");
-	if (!spu->problem)
-		goto out_unmap;
-
-	spu->priv2 = spu_map_prop_old(spu, node, "priv2");
-	if (!spu->priv2)
-		goto out_unmap;
-
-	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		spu->priv1 = spu_map_prop_old(spu, node, "priv1");
-		if (!spu->priv1)
-			goto out_unmap;
-	}
-
-	ret = 0;
-	goto out;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	return ret;
-}
-
-static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
-{
-	int i;
-
-	for (i=0; i < 3; i++) {
-		spu->irqs[i] = irq_of_parse_and_map(np, i);
-		if (!spu->irqs[i])
-			goto err;
-	}
-	return 0;
-
-err:
-	pr_debug("failed to map irq %x for spu %s\n", i, spu->name);
-	for (; i >= 0; i--) {
-		if (spu->irqs[i])
-			irq_dispose_mapping(spu->irqs[i]);
-	}
-	return -EINVAL;
-}
-
-static int __init spu_map_resource(struct spu *spu, int nr,
-			    void __iomem** virt, unsigned long *phys)
-{
-	struct device_node *np = spu->devnode;
-	struct resource resource = { };
-	unsigned long len;
-	int ret;
-
-	ret = of_address_to_resource(np, nr, &resource);
-	if (ret)
-		return ret;
-	if (phys)
-		*phys = resource.start;
-	len = resource_size(&resource);
-	*virt = ioremap(resource.start, len);
-	if (!*virt)
-		return -EINVAL;
-	return 0;
-}
-
-static int __init spu_map_device(struct spu *spu)
-{
-	struct device_node *np = spu->devnode;
-	int ret = -ENODEV;
-
-	spu->name = of_get_property(np, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	ret = spu_map_resource(spu, 0, (void __iomem**)&spu->local_store,
-			       &spu->local_store_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 0\n",
-			 np);
-		goto out;
-	}
-	ret = spu_map_resource(spu, 1, (void __iomem**)&spu->problem,
-			       &spu->problem_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 1\n",
-			 np);
-		goto out_unmap;
-	}
-	ret = spu_map_resource(spu, 2, (void __iomem**)&spu->priv2, NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 2\n",
-			 np);
-		goto out_unmap;
-	}
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
-		ret = spu_map_resource(spu, 3,
-			       (void __iomem**)&spu->priv1, NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 3\n",
-			 np);
-		goto out_unmap;
-	}
-	pr_debug("spu_new: %pOF maps:\n", np);
-	pr_debug("  local store   : 0x%016lx -> 0x%p\n",
-		 spu->local_store_phys, spu->local_store);
-	pr_debug("  problem state : 0x%016lx -> 0x%p\n",
-		 spu->problem_phys, spu->problem);
-	pr_debug("  priv2         :                       0x%p\n", spu->priv2);
-	pr_debug("  priv1         :                       0x%p\n", spu->priv1);
-
-	return 0;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	pr_debug("failed to map spe %s: %d\n", spu->name, ret);
-	return ret;
-}
-
-static int __init of_enumerate_spus(int (*fn)(void *data))
-{
-	int ret;
-	struct device_node *node;
-	unsigned int n = 0;
-
-	ret = -ENODEV;
-	for_each_node_by_type(node, "spe") {
-		ret = fn(node);
-		if (ret) {
-			printk(KERN_WARNING "%s: Error initializing %pOFn\n",
-				__func__, node);
-			of_node_put(node);
-			break;
-		}
-		n++;
-	}
-	return ret ? ret : n;
-}
-
-static int __init of_create_spu(struct spu *spu, void *data)
-{
-	int ret;
-	struct device_node *spe = (struct device_node *)data;
-	static int legacy_map = 0, legacy_irq = 0;
-
-	spu->devnode = of_node_get(spe);
-	spu->spe_id = find_spu_unit_number(spe);
-
-	spu->node = of_node_to_nid(spe);
-	if (spu->node >= MAX_NUMNODES) {
-		printk(KERN_WARNING "SPE %pOF on node %d ignored,"
-		       " node number too big\n", spe, spu->node);
-		printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n");
-		ret = -ENODEV;
-		goto out;
-	}
-
-	ret = spu_map_device(spu);
-	if (ret) {
-		if (!legacy_map) {
-			legacy_map = 1;
-			printk(KERN_WARNING "%s: Legacy device tree found, "
-				"trying to map old style\n", __func__);
-		}
-		ret = spu_map_device_old(spu);
-		if (ret) {
-			printk(KERN_ERR "Unable to map %s\n",
-				spu->name);
-			goto out;
-		}
-	}
-
-	ret = spu_map_interrupts(spu, spe);
-	if (ret) {
-		if (!legacy_irq) {
-			legacy_irq = 1;
-			printk(KERN_WARNING "%s: Legacy device tree found, "
-				"trying old style irq\n", __func__);
-		}
-		ret = spu_map_interrupts_old(spu, spe);
-		if (ret) {
-			printk(KERN_ERR "%s: could not map interrupts\n",
-				spu->name);
-			goto out_unmap;
-		}
-	}
-
-	pr_debug("Using SPE %s %p %p %p %p %d\n", spu->name,
-		spu->local_store, spu->problem, spu->priv1,
-		spu->priv2, spu->number);
-	goto out;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	return ret;
-}
-
-static int of_destroy_spu(struct spu *spu)
-{
-	spu_unmap(spu);
-	of_node_put(spu->devnode);
-	return 0;
-}
-
-static void enable_spu_by_master_run(struct spu_context *ctx)
-{
-	ctx->ops->master_start(ctx);
-}
-
-static void disable_spu_by_master_run(struct spu_context *ctx)
-{
-	ctx->ops->master_stop(ctx);
-}
-
-/* Hardcoded affinity idxs for qs20 */
-#define QS20_SPES_PER_BE 8
-static int qs20_reg_idxs[QS20_SPES_PER_BE] =   { 0, 2, 4, 6, 7, 5, 3, 1 };
-static int qs20_reg_memory[QS20_SPES_PER_BE] = { 1, 1, 0, 0, 0, 0, 0, 0 };
-
-static struct spu *__init spu_lookup_reg(int node, u32 reg)
-{
-	struct spu *spu;
-	const u32 *spu_reg;
-
-	list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
-		spu_reg = of_get_property(spu_devnode(spu), "reg", NULL);
-		if (*spu_reg == reg)
-			return spu;
-	}
-	return NULL;
-}
-
-static void __init init_affinity_qs20_harcoded(void)
-{
-	int node, i;
-	struct spu *last_spu, *spu;
-	u32 reg;
-
-	for (node = 0; node < MAX_NUMNODES; node++) {
-		last_spu = NULL;
-		for (i = 0; i < QS20_SPES_PER_BE; i++) {
-			reg = qs20_reg_idxs[i];
-			spu = spu_lookup_reg(node, reg);
-			if (!spu)
-				continue;
-			spu->has_mem_affinity = qs20_reg_memory[reg];
-			if (last_spu)
-				list_add_tail(&spu->aff_list,
-						&last_spu->aff_list);
-			last_spu = spu;
-		}
-	}
-}
-
-static int __init of_has_vicinity(void)
-{
-	struct device_node *dn;
-
-	for_each_node_by_type(dn, "spe") {
-		if (of_property_present(dn, "vicinity"))  {
-			of_node_put(dn);
-			return 1;
-		}
-	}
-	return 0;
-}
-
-static struct spu *__init devnode_spu(int cbe, struct device_node *dn)
-{
-	struct spu *spu;
-
-	list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list)
-		if (spu_devnode(spu) == dn)
-			return spu;
-	return NULL;
-}
-
-static struct spu * __init
-neighbour_spu(int cbe, struct device_node *target, struct device_node *avoid)
-{
-	struct spu *spu;
-	struct device_node *spu_dn;
-	const phandle *vic_handles;
-	int lenp, i;
-
-	list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list) {
-		spu_dn = spu_devnode(spu);
-		if (spu_dn == avoid)
-			continue;
-		vic_handles = of_get_property(spu_dn, "vicinity", &lenp);
-		for (i=0; i < (lenp / sizeof(phandle)); i++) {
-			if (vic_handles[i] == target->phandle)
-				return spu;
-		}
-	}
-	return NULL;
-}
-
-static void __init init_affinity_node(int cbe)
-{
-	struct spu *spu, *last_spu;
-	struct device_node *vic_dn, *last_spu_dn;
-	phandle avoid_ph;
-	const phandle *vic_handles;
-	int lenp, i, added;
-
-	last_spu = list_first_entry(&cbe_spu_info[cbe].spus, struct spu,
-								cbe_list);
-	avoid_ph = 0;
-	for (added = 1; added < cbe_spu_info[cbe].n_spus; added++) {
-		last_spu_dn = spu_devnode(last_spu);
-		vic_handles = of_get_property(last_spu_dn, "vicinity", &lenp);
-
-		/*
-		 * Walk through each phandle in vicinity property of the spu
-		 * (typically two vicinity phandles per spe node)
-		 */
-		for (i = 0; i < (lenp / sizeof(phandle)); i++) {
-			if (vic_handles[i] == avoid_ph)
-				continue;
-
-			vic_dn = of_find_node_by_phandle(vic_handles[i]);
-			if (!vic_dn)
-				continue;
-
-			if (of_node_name_eq(vic_dn, "spe") ) {
-				spu = devnode_spu(cbe, vic_dn);
-				avoid_ph = last_spu_dn->phandle;
-			} else {
-				/*
-				 * "mic-tm" and "bif0" nodes do not have
-				 * vicinity property. So we need to find the
-				 * spe which has vic_dn as neighbour, but
-				 * skipping the one we came from (last_spu_dn)
-				 */
-				spu = neighbour_spu(cbe, vic_dn, last_spu_dn);
-				if (!spu)
-					continue;
-				if (of_node_name_eq(vic_dn, "mic-tm")) {
-					last_spu->has_mem_affinity = 1;
-					spu->has_mem_affinity = 1;
-				}
-				avoid_ph = vic_dn->phandle;
-			}
-
-			of_node_put(vic_dn);
-
-			list_add_tail(&spu->aff_list, &last_spu->aff_list);
-			last_spu = spu;
-			break;
-		}
-	}
-}
-
-static void __init init_affinity_fw(void)
-{
-	int cbe;
-
-	for (cbe = 0; cbe < MAX_NUMNODES; cbe++)
-		init_affinity_node(cbe);
-}
-
-static int __init init_affinity(void)
-{
-	if (of_has_vicinity()) {
-		init_affinity_fw();
-	} else {
-		if (of_machine_is_compatible("IBM,CPBW-1.0"))
-			init_affinity_qs20_harcoded();
-		else
-			printk("No affinity configuration found\n");
-	}
-
-	return 0;
-}
-
-const struct spu_management_ops spu_management_of_ops = {
-	.enumerate_spus = of_enumerate_spus,
-	.create_spu = of_create_spu,
-	.destroy_spu = of_destroy_spu,
-	.enable_spu = enable_spu_by_master_run,
-	.disable_spu = disable_spu_by_master_run,
-	.init_affinity = init_affinity,
-};
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
deleted file mode 100644
index d150e3987304..000000000000
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ /dev/null
@@ -1,167 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * spu hypervisor abstraction for direct hardware access.
- *
- *  (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *  Copyright 2006 Sony Corp.
- */
-
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/ptrace.h>
-#include <linux/wait.h>
-#include <linux/mm.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/sched.h>
-
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/firmware.h>
-
-#include "interrupt.h"
-#include "spu_priv1_mmio.h"
-
-static void int_mask_and(struct spu *spu, int class, u64 mask)
-{
-	u64 old_mask;
-
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask & mask);
-}
-
-static void int_mask_or(struct spu *spu, int class, u64 mask)
-{
-	u64 old_mask;
-
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask | mask);
-}
-
-static void int_mask_set(struct spu *spu, int class, u64 mask)
-{
-	out_be64(&spu->priv1->int_mask_RW[class], mask);
-}
-
-static u64 int_mask_get(struct spu *spu, int class)
-{
-	return in_be64(&spu->priv1->int_mask_RW[class]);
-}
-
-static void int_stat_clear(struct spu *spu, int class, u64 stat)
-{
-	out_be64(&spu->priv1->int_stat_RW[class], stat);
-}
-
-static u64 int_stat_get(struct spu *spu, int class)
-{
-	return in_be64(&spu->priv1->int_stat_RW[class]);
-}
-
-static void cpu_affinity_set(struct spu *spu, int cpu)
-{
-	u64 target;
-	u64 route;
-
-	if (nr_cpus_node(spu->node)) {
-		const struct cpumask *spumask = cpumask_of_node(spu->node),
-			*cpumask = cpumask_of_node(cpu_to_node(cpu));
-
-		if (!cpumask_intersects(spumask, cpumask))
-			return;
-	}
-
-	target = iic_get_target_id(cpu);
-	route = target << 48 | target << 32 | target << 16;
-	out_be64(&spu->priv1->int_route_RW, route);
-}
-
-static u64 mfc_dar_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_dar_RW);
-}
-
-static u64 mfc_dsisr_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_dsisr_RW);
-}
-
-static void mfc_dsisr_set(struct spu *spu, u64 dsisr)
-{
-	out_be64(&spu->priv1->mfc_dsisr_RW, dsisr);
-}
-
-static void mfc_sdr_setup(struct spu *spu)
-{
-	out_be64(&spu->priv1->mfc_sdr_RW, mfspr(SPRN_SDR1));
-}
-
-static void mfc_sr1_set(struct spu *spu, u64 sr1)
-{
-	out_be64(&spu->priv1->mfc_sr1_RW, sr1);
-}
-
-static u64 mfc_sr1_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_sr1_RW);
-}
-
-static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id)
-{
-	out_be64(&spu->priv1->mfc_tclass_id_RW, tclass_id);
-}
-
-static u64 mfc_tclass_id_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_tclass_id_RW);
-}
-
-static void tlb_invalidate(struct spu *spu)
-{
-	out_be64(&spu->priv1->tlb_invalidate_entry_W, 0ul);
-}
-
-static void resource_allocation_groupID_set(struct spu *spu, u64 id)
-{
-	out_be64(&spu->priv1->resource_allocation_groupID_RW, id);
-}
-
-static u64 resource_allocation_groupID_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->resource_allocation_groupID_RW);
-}
-
-static void resource_allocation_enable_set(struct spu *spu, u64 enable)
-{
-	out_be64(&spu->priv1->resource_allocation_enable_RW, enable);
-}
-
-static u64 resource_allocation_enable_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->resource_allocation_enable_RW);
-}
-
-const struct spu_priv1_ops spu_priv1_mmio_ops =
-{
-	.int_mask_and = int_mask_and,
-	.int_mask_or = int_mask_or,
-	.int_mask_set = int_mask_set,
-	.int_mask_get = int_mask_get,
-	.int_stat_clear = int_stat_clear,
-	.int_stat_get = int_stat_get,
-	.cpu_affinity_set = cpu_affinity_set,
-	.mfc_dar_get = mfc_dar_get,
-	.mfc_dsisr_get = mfc_dsisr_get,
-	.mfc_dsisr_set = mfc_dsisr_set,
-	.mfc_sdr_setup = mfc_sdr_setup,
-	.mfc_sr1_set = mfc_sr1_set,
-	.mfc_sr1_get = mfc_sr1_get,
-	.mfc_tclass_id_set = mfc_tclass_id_set,
-	.mfc_tclass_id_get = mfc_tclass_id_get,
-	.tlb_invalidate = tlb_invalidate,
-	.resource_allocation_groupID_set = resource_allocation_groupID_set,
-	.resource_allocation_groupID_get = resource_allocation_groupID_get,
-	.resource_allocation_enable_set = resource_allocation_enable_set,
-	.resource_allocation_enable_get = resource_allocation_enable_get,
-};
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.h b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
deleted file mode 100644
index 04f0db339dc1..000000000000
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * spu hypervisor abstraction for direct hardware access.
- *
- *  Copyright (C) 2006 Sony Computer Entertainment Inc.
- *  Copyright 2006 Sony Corp.
- */
-
-#ifndef SPU_PRIV1_MMIO_H
-#define SPU_PRIV1_MMIO_H
-
-struct device_node *spu_devnode(struct spu *spu);
-
-#endif /* SPU_PRIV1_MMIO_H */
diff --git a/arch/powerpc/platforms/cell/spufs/gang.c b/arch/powerpc/platforms/cell/spufs/gang.c
index 827d338deaf4..2c2999de6bfa 100644
--- a/arch/powerpc/platforms/cell/spufs/gang.c
+++ b/arch/powerpc/platforms/cell/spufs/gang.c
@@ -25,6 +25,7 @@ struct spu_gang *alloc_spu_gang(void)
 	mutex_init(&gang->aff_mutex);
 	INIT_LIST_HEAD(&gang->list);
 	INIT_LIST_HEAD(&gang->aff_list_head);
+	gang->alive = 1;
 
 out:
 	return gang;
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 70236d1df3d3..9f9e4b871627 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -192,13 +192,32 @@ static int spufs_fill_dir(struct dentry *dir,
 			return -ENOMEM;
 		ret = spufs_new_file(dir->d_sb, dentry, files->ops,
 					files->mode & mode, files->size, ctx);
-		if (ret)
+		if (ret) {
+			dput(dentry);
 			return ret;
+		}
 		files++;
 	}
 	return 0;
 }
 
+static void unuse_gang(struct dentry *dir)
+{
+	struct inode *inode = dir->d_inode;
+	struct spu_gang *gang = SPUFS_I(inode)->i_gang;
+
+	if (gang) {
+		bool dead;
+
+		inode_lock(inode); // exclusion with spufs_create_context()
+		dead = !--gang->alive;
+		inode_unlock(inode);
+
+		if (dead)
+			simple_recursive_removal(dir, NULL);
+	}
+}
+
 static int spufs_dir_close(struct inode *inode, struct file *file)
 {
 	struct inode *parent;
@@ -213,6 +232,7 @@ static int spufs_dir_close(struct inode *inode, struct file *file)
 	inode_unlock(parent);
 	WARN_ON(ret);
 
+	unuse_gang(dir->d_parent);
 	return dcache_dir_close(inode, file);
 }
 
@@ -405,7 +425,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 {
 	int ret;
 	int affinity;
-	struct spu_gang *gang;
+	struct spu_gang *gang = SPUFS_I(inode)->i_gang;
 	struct spu_context *neighbor;
 	struct path path = {.mnt = mnt, .dentry = dentry};
 
@@ -420,11 +440,15 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	if ((flags & SPU_CREATE_ISOLATE) && !isolated_loader)
 		return -ENODEV;
 
-	gang = NULL;
+	if (gang) {
+		if (!gang->alive)
+			return -ENOENT;
+		gang->alive++;
+	}
+
 	neighbor = NULL;
 	affinity = flags & (SPU_CREATE_AFFINITY_MEM | SPU_CREATE_AFFINITY_SPU);
 	if (affinity) {
-		gang = SPUFS_I(inode)->i_gang;
 		if (!gang)
 			return -EINVAL;
 		mutex_lock(&gang->aff_mutex);
@@ -436,8 +460,11 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	}
 
 	ret = spufs_mkdir(inode, dentry, flags, mode & 0777);
-	if (ret)
+	if (ret) {
+		if (neighbor)
+			put_spu_context(neighbor);
 		goto out_aff_unlock;
+	}
 
 	if (affinity) {
 		spufs_set_affinity(flags, SPUFS_I(d_inode(dentry))->i_ctx,
@@ -453,6 +480,8 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 out_aff_unlock:
 	if (affinity)
 		mutex_unlock(&gang->aff_mutex);
+	if (ret && gang)
+		gang->alive--; // can't reach 0
 	return ret;
 }
 
@@ -482,6 +511,7 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_fop = &simple_dir_operations;
 
 	d_instantiate(dentry, inode);
+	dget(dentry);
 	inc_nlink(dir);
 	inc_nlink(d_inode(dentry));
 	return ret;
@@ -492,6 +522,21 @@ out:
 	return ret;
 }
 
+static int spufs_gang_close(struct inode *inode, struct file *file)
+{
+	unuse_gang(file->f_path.dentry);
+	return dcache_dir_close(inode, file);
+}
+
+static const struct file_operations spufs_gang_fops = {
+	.open		= dcache_dir_open,
+	.release	= spufs_gang_close,
+	.llseek		= dcache_dir_lseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= dcache_readdir,
+	.fsync		= noop_fsync,
+};
+
 static int spufs_gang_open(const struct path *path)
 {
 	int ret;
@@ -511,7 +556,7 @@ static int spufs_gang_open(const struct path *path)
 		return PTR_ERR(filp);
 	}
 
-	filp->f_op = &simple_dir_operations;
+	filp->f_op = &spufs_gang_fops;
 	fd_install(ret, filp);
 	return ret;
 }
@@ -526,10 +571,8 @@ static int spufs_create_gang(struct inode *inode,
 	ret = spufs_mkgang(inode, dentry, mode & 0777);
 	if (!ret) {
 		ret = spufs_gang_open(&path);
-		if (ret < 0) {
-			int err = simple_rmdir(inode, dentry);
-			WARN_ON(err);
-		}
+		if (ret < 0)
+			unuse_gang(dentry);
 	}
 	return ret;
 }
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 610ca8570682..8e7ed010bfde 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -508,7 +508,7 @@ static void __spu_del_from_rq(struct spu_context *ctx)
 
 	if (!list_empty(&ctx->rq)) {
 		if (!--spu_prio->nr_waiting)
-			del_timer(&spusched_timer);
+			timer_delete(&spusched_timer);
 		list_del_init(&ctx->rq);
 
 		if (list_empty(&spu_prio->runq[prio]))
@@ -1126,8 +1126,8 @@ void spu_sched_exit(void)
 
 	remove_proc_entry("spu_loadavg", NULL);
 
-	del_timer_sync(&spusched_timer);
-	del_timer_sync(&spuloadavg_timer);
+	timer_delete_sync(&spusched_timer);
+	timer_delete_sync(&spuloadavg_timer);
 	kthread_stop(spusched_task);
 
 	for (node = 0; node < MAX_NUMNODES; node++) {
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 84958487f696..d33787c57c39 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -151,6 +151,8 @@ struct spu_gang {
 	int aff_flags;
 	struct spu *aff_ref_spu;
 	atomic_t aff_sched_count;
+
+	int alive;
 };
 
 /* Flag bits for spu_gang aff_flags */
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 36ee3a5056a1..c1bfa4c3444c 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -486,7 +486,7 @@ static void __init chrp_find_8259(void)
 	i8259_init(pic, chrp_int_ack);
 	if (ppc_md.get_irq == NULL) {
 		ppc_md.get_irq = i8259_irq;
-		irq_set_default_host(i8259_get_host());
+		irq_set_default_domain(i8259_get_host());
 	}
 	if (chrp_mpic != NULL) {
 		cascade_irq = irq_of_parse_and_map(pic, 0);
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 4d9200bdba78..91a8f0a7086e 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -149,8 +149,9 @@ static struct irq_domain * __init flipper_pic_init(struct device_node *np)
 
 	__flipper_quiesce(io_base);
 
-	irq_domain = irq_domain_add_linear(np, FLIPPER_NR_IRQS,
-				  &flipper_irq_domain_ops, io_base);
+	irq_domain = irq_domain_create_linear(of_fwnode_handle(np),
+					      FLIPPER_NR_IRQS,
+					      &flipper_irq_domain_ops, io_base);
 	if (!irq_domain) {
 		pr_err("failed to allocate irq_domain\n");
 		return NULL;
@@ -172,7 +173,7 @@ unsigned int flipper_pic_get_irq(void)
 		return 0;	/* no more IRQs pending */
 
 	irq = __ffs(irq_status);
-	return irq_linear_revmap(flipper_irq_host, irq);
+	return irq_find_mapping(flipper_irq_host, irq);
 }
 
 /*
@@ -190,7 +191,7 @@ void __init flipper_pic_probe(void)
 	flipper_irq_host = flipper_pic_init(np);
 	BUG_ON(!flipper_irq_host);
 
-	irq_set_default_host(flipper_irq_host);
+	irq_set_default_domain(flipper_irq_host);
 
 	of_node_put(np);
 }
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 4d2d92de30af..b57e87b0b3ce 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -175,8 +175,9 @@ static struct irq_domain *__init hlwd_pic_init(struct device_node *np)
 
 	__hlwd_quiesce(io_base);
 
-	irq_domain = irq_domain_add_linear(np, HLWD_NR_IRQS,
-					   &hlwd_irq_domain_ops, io_base);
+	irq_domain = irq_domain_create_linear(of_fwnode_handle(np),
+					      HLWD_NR_IRQS,
+					      &hlwd_irq_domain_ops, io_base);
 	if (!irq_domain) {
 		pr_err("failed to allocate irq_domain\n");
 		iounmap(io_base);
@@ -189,7 +190,7 @@ static struct irq_domain *__init hlwd_pic_init(struct device_node *np)
 unsigned int hlwd_pic_get_irq(void)
 {
 	unsigned int hwirq = __hlwd_pic_get_irq(hlwd_irq_host);
-	return hwirq ? irq_linear_revmap(hlwd_irq_host, hwirq) : 0;
+	return hwirq ? irq_find_mapping(hlwd_irq_host, hwirq) : 0;
 }
 
 /*
diff --git a/arch/powerpc/platforms/microwatt/Kconfig b/arch/powerpc/platforms/microwatt/Kconfig
index 6af443a1db99..cb2aff635bb0 100644
--- a/arch/powerpc/platforms/microwatt/Kconfig
+++ b/arch/powerpc/platforms/microwatt/Kconfig
@@ -1,11 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_MICROWATT
-	depends on PPC_BOOK3S_64 && !SMP
+	depends on PPC_BOOK3S_64
 	bool "Microwatt SoC platform"
 	select PPC_XICS
 	select PPC_ICS_NATIVE
 	select PPC_ICP_NATIVE
 	select PPC_UDBG_16550
+	select COMMON_CLK
 	help
           This option enables support for FPGA-based Microwatt implementations.
 
diff --git a/arch/powerpc/platforms/microwatt/Makefile b/arch/powerpc/platforms/microwatt/Makefile
index 116d6d3ad3f0..d973b2ab4042 100644
--- a/arch/powerpc/platforms/microwatt/Makefile
+++ b/arch/powerpc/platforms/microwatt/Makefile
@@ -1 +1,2 @@
 obj-y	+= setup.o rng.o
+obj-$(CONFIG_SMP) += smp.o
diff --git a/arch/powerpc/platforms/microwatt/microwatt.h b/arch/powerpc/platforms/microwatt/microwatt.h
index 335417e95e66..891aa2800768 100644
--- a/arch/powerpc/platforms/microwatt/microwatt.h
+++ b/arch/powerpc/platforms/microwatt/microwatt.h
@@ -3,5 +3,6 @@
 #define _MICROWATT_H
 
 void microwatt_rng_init(void);
+void microwatt_init_smp(void);
 
 #endif /* _MICROWATT_H */
diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c
index 5e1c0997170d..6af2ccef736c 100644
--- a/arch/powerpc/platforms/microwatt/setup.c
+++ b/arch/powerpc/platforms/microwatt/setup.c
@@ -29,15 +29,33 @@ static int __init microwatt_populate(void)
 }
 machine_arch_initcall(microwatt, microwatt_populate);
 
+static int __init microwatt_probe(void)
+{
+	/* Main reason for having this is to start the other CPU(s) */
+	if (IS_ENABLED(CONFIG_SMP))
+		microwatt_init_smp();
+	return 1;
+}
+
 static void __init microwatt_setup_arch(void)
 {
 	microwatt_rng_init();
 }
 
+static void microwatt_idle(void)
+{
+	if (!prep_irq_for_idle_irqsoff())
+		return;
+
+	__asm__ __volatile__ ("wait");
+}
+
 define_machine(microwatt) {
 	.name			= "microwatt",
 	.compatible		= "microwatt-soc",
+	.probe			= microwatt_probe,
 	.init_IRQ		= microwatt_init_IRQ,
 	.setup_arch		= microwatt_setup_arch,
 	.progress		= udbg_progress,
+	.power_save		= microwatt_idle,
 };
diff --git a/arch/powerpc/platforms/microwatt/smp.c b/arch/powerpc/platforms/microwatt/smp.c
new file mode 100644
index 000000000000..7dbf2ca73d47
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/smp.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/*
+ * SMP support functions for Microwatt
+ * Copyright 2025 Paul Mackerras <paulus@ozlabs.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/io.h>
+#include <asm/early_ioremap.h>
+#include <asm/ppc-opcode.h>
+#include <asm/reg.h>
+#include <asm/smp.h>
+#include <asm/xics.h>
+
+#include "microwatt.h"
+
+static void __init microwatt_smp_probe(void)
+{
+	xics_smp_probe();
+}
+
+static void microwatt_smp_setup_cpu(int cpu)
+{
+	if (cpu != 0)
+		xics_setup_cpu();
+}
+
+static struct smp_ops_t microwatt_smp_ops = {
+	.probe		= microwatt_smp_probe,
+	.message_pass	= NULL,		/* Use smp_muxed_ipi_message_pass */
+	.kick_cpu	= smp_generic_kick_cpu,
+	.setup_cpu	= microwatt_smp_setup_cpu,
+};
+
+/* XXX get from device tree */
+#define SYSCON_BASE	0xc0000000
+#define SYSCON_LENGTH	0x100
+
+#define SYSCON_CPU_CTRL	0x58
+
+void __init microwatt_init_smp(void)
+{
+	volatile unsigned char __iomem *syscon;
+	int ncpus;
+	int timeout;
+
+	syscon = early_ioremap(SYSCON_BASE, SYSCON_LENGTH);
+	if (syscon == NULL) {
+		pr_err("Failed to map SYSCON\n");
+		return;
+	}
+	ncpus = (readl(syscon + SYSCON_CPU_CTRL) >> 8) & 0xff;
+	if (ncpus < 2)
+		goto out;
+
+	smp_ops = &microwatt_smp_ops;
+
+	/*
+	 * Write two instructions at location 0:
+	 * mfspr r3, PIR
+	 * b __secondary_hold
+	 */
+	*(unsigned int *)KERNELBASE = PPC_RAW_MFSPR(3, SPRN_PIR);
+	*(unsigned int *)(KERNELBASE+4) = PPC_RAW_BRANCH(&__secondary_hold - (char *)(KERNELBASE+4));
+
+	/* enable the other CPUs, they start at location 0 */
+	writel((1ul << ncpus) - 1, syscon + SYSCON_CPU_CTRL);
+
+	timeout = 10000;
+	while (!__secondary_hold_acknowledge) {
+		if (--timeout == 0)
+			break;
+		barrier();
+	}
+
+ out:
+	early_iounmap((void *)syscon, SYSCON_LENGTH);
+}
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 0761d98e5be3..d03b41336901 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -228,7 +228,7 @@ static void __init nemo_init_IRQ(struct mpic *mpic)
 	irq_set_chained_handler(gpio_virq, sb600_8259_cascade);
 	mpic_unmask_irq(irq_get_irq_data(gpio_virq));
 
-	irq_set_default_host(mpic->irqhost);
+	irq_set_default_domain(mpic->irqhost);
 }
 
 #else
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index c097d591670e..a0ae58636e10 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -347,7 +347,7 @@ static irqreturn_t kw_i2c_irq(int irq, void *dev_id)
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
-	del_timer(&host->timeout_timer);
+	timer_delete(&host->timeout_timer);
 	kw_i2c_handle_interrupt(host, kw_read_reg(reg_isr));
 	if (host->state != state_idle) {
 		host->timeout_timer.expires = jiffies + KW_POLL_TIMEOUT;
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 2202bf77c7a3..c37783a03d25 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -250,7 +250,7 @@ static unsigned int pmac_pic_get_irq(void)
 	raw_spin_unlock_irqrestore(&pmac_pic_lock, flags);
 	if (unlikely(irq < 0))
 		return 0;
-	return irq_linear_revmap(pmac_pic_host, irq);
+	return irq_find_mapping(pmac_pic_host, irq);
 }
 
 static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node,
@@ -327,10 +327,11 @@ static void __init pmac_pic_probe_oldstyle(void)
 	/*
 	 * Allocate an irq host
 	 */
-	pmac_pic_host = irq_domain_add_linear(master, max_irqs,
-					      &pmac_pic_host_ops, NULL);
+	pmac_pic_host = irq_domain_create_linear(of_fwnode_handle(master),
+						 max_irqs,
+						 &pmac_pic_host_ops, NULL);
 	BUG_ON(pmac_pic_host == NULL);
-	irq_set_default_host(pmac_pic_host);
+	irq_set_default_domain(pmac_pic_host);
 
 	/* Get addresses of first controller if we have a node for it */
 	BUG_ON(of_address_to_resource(master, 0, &r));
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 6de1cd5d8a58..e119ced05d10 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -45,6 +45,7 @@
 #include <linux/root_dev.h>
 #include <linux/bitops.h>
 #include <linux/suspend.h>
+#include <linux/string_choices.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 
@@ -238,8 +239,7 @@ static void __init l2cr_init(void)
 				_set_L2CR(0);
 				_set_L2CR(*l2cr);
 				pr_info("L2CR overridden (0x%x), backside cache is %s\n",
-					*l2cr, ((*l2cr) & 0x80000000) ?
-					"enabled" : "disabled");
+					*l2cr, str_enabled_disabled((*l2cr) & 0x80000000));
 			}
 			of_node_put(np);
 			break;
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 09e7fe24fac1..88e92af8acf9 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -190,7 +190,7 @@ static int __init psurge_secondary_ipi_init(void)
 {
 	int rc = -ENOMEM;
 
-	psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL);
+	psurge_host = irq_domain_create_nomap(NULL, ~0, &psurge_host_ops, NULL);
 
 	if (psurge_host)
 		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 8633891b7aa5..b4426a35aca3 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/time.h>
@@ -77,7 +78,7 @@ long __init pmac_time_init(void)
 		delta |= 0xFF000000UL;
 	dst = ((pmac_xpram_read(PMAC_XPRAM_MACHINE_LOC + 0x8) & 0x80) != 0);
 	printk("GMT Delta read from XPRAM: %d minutes, DST: %s\n", delta/60,
-		dst ? "on" : "off");
+		str_on_off(dst));
 #endif
 	return delta;
 }
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 70a46acc70d6..95d7ba73d43d 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -17,6 +17,7 @@ config PPC_POWERNV
 	select MMU_NOTIFIER
 	select FORCE_SMP
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config OPAL_PRD
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 19f0fc5c6f1b..9e5d0c847ee2 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_PRESERVE_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_OPAL_CORE)	+= opal-core.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o pci-ioda-tce.o
 obj-$(CONFIG_PCI_IOV)   += pci-sriov.o
-obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
index c9a9b759cc92..e652da8f986f 100644
--- a/arch/powerpc/platforms/powernv/opal-core.c
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -149,7 +149,7 @@ static Elf64_Word *__init auxv_to_elf64_notes(Elf64_Word *buf,
 	/* end of vector */
 	bufp[idx++] = cpu_to_be64(AT_NULL);
 
-	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_AUXV,
+	buf = append_elf64_note(buf, NN_AUXV, NT_AUXV,
 				oc_conf->auxv_buf, AUXV_DESC_SZ);
 	return buf;
 }
@@ -159,7 +159,7 @@ static Elf64_Word *__init auxv_to_elf64_notes(Elf64_Word *buf,
  * Returns number of bytes read on success, -errno on failure.
  */
 static ssize_t read_opalcore(struct file *file, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *to,
+			     const struct bin_attribute *bin_attr, char *to,
 			     loff_t pos, size_t count)
 {
 	struct opalcore *m;
@@ -206,9 +206,9 @@ static ssize_t read_opalcore(struct file *file, struct kobject *kobj,
 	return (tpos - pos);
 }
 
-static struct bin_attribute opal_core_attr = {
+static struct bin_attribute opal_core_attr __ro_after_init = {
 	.attr = {.name = "core", .mode = 0400},
-	.read = read_opalcore
+	.read_new = read_opalcore
 };
 
 /*
@@ -252,7 +252,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 	 * crashing CPU's prstatus.
 	 */
 	first_cpu_note = buf;
-	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+	buf = append_elf64_note(buf, NN_PRSTATUS, NT_PRSTATUS,
 				&prstatus, sizeof(prstatus));
 
 	for (i = 0; i < oc_conf->num_cpus; i++, bufp += size_per_thread) {
@@ -279,7 +279,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 		fill_prstatus(&prstatus, thread_pir, &regs);
 
 		if (thread_pir != oc_conf->crashing_cpu) {
-			buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME,
+			buf = append_elf64_note(buf, NN_PRSTATUS,
 						NT_PRSTATUS, &prstatus,
 						sizeof(prstatus));
 		} else {
@@ -287,7 +287,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 			 * Add crashing CPU as the first NT_PRSTATUS note for
 			 * GDB to process the core file appropriately.
 			 */
-			append_elf64_note(first_cpu_note, CRASH_CORE_NOTE_NAME,
+			append_elf64_note(first_cpu_note, NN_PRSTATUS,
 					  NT_PRSTATUS, &prstatus,
 					  sizeof(prstatus));
 		}
@@ -599,7 +599,7 @@ static struct attribute *mpipl_attr[] = {
 	NULL,
 };
 
-static struct bin_attribute *mpipl_bin_attr[] = {
+static const struct bin_attribute *const mpipl_bin_attr[] = {
 	&opal_core_attr,
 	NULL,
 
@@ -607,7 +607,7 @@ static struct bin_attribute *mpipl_bin_attr[] = {
 
 static const struct attribute_group mpipl_group = {
 	.attrs = mpipl_attr,
-	.bin_attrs =  mpipl_bin_attr,
+	.bin_attrs_new =  mpipl_bin_attr,
 };
 
 static int __init opalcore_init(void)
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 608e4b68c5ea..27e25693cf39 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -286,7 +286,7 @@ out:
 }
 
 static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj,
-			      struct bin_attribute *bin_attr,
+			      const struct bin_attribute *bin_attr,
 			      char *buffer, loff_t pos, size_t count)
 {
 	ssize_t rc;
@@ -342,7 +342,7 @@ static void create_dump_obj(uint32_t id, size_t size, uint32_t type)
 	dump->dump_attr.attr.name = "dump";
 	dump->dump_attr.attr.mode = 0400;
 	dump->dump_attr.size = size;
-	dump->dump_attr.read = dump_attr_read;
+	dump->dump_attr.read_new = dump_attr_read;
 
 	dump->id = id;
 	dump->size = size;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 5db1e733143b..de33f354e9fd 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -156,7 +156,7 @@ static const struct kobj_type elog_ktype = {
 #define OPAL_MAX_ERRLOG_SIZE	16384
 
 static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj,
-			     struct bin_attribute *bin_attr,
+			     const struct bin_attribute *bin_attr,
 			     char *buffer, loff_t pos, size_t count)
 {
 	int opal_rc;
@@ -203,7 +203,7 @@ static void create_elog_obj(uint64_t id, size_t size, uint64_t type)
 	elog->raw_attr.attr.name = "raw";
 	elog->raw_attr.attr.mode = 0400;
 	elog->raw_attr.size = size;
-	elog->raw_attr.read = raw_attr_read;
+	elog->raw_attr.read_new = raw_attr_read;
 
 	elog->id = id;
 	elog->size = size;
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index d5ea04e8e4c5..fd8c8621e973 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -432,7 +432,7 @@ static int alloc_image_buf(char *buffer, size_t count)
  * and pre-allocate required memory.
  */
 static ssize_t image_data_write(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buffer, loff_t pos, size_t count)
 {
 	int rc;
@@ -493,7 +493,7 @@ out:
 static const struct bin_attribute image_data_attr = {
 	.attr = {.name = "image", .mode = 0200},
 	.size = MAX_IMAGE_SIZE,	/* Limit image size */
-	.write = image_data_write,
+	.write_new = image_data_write,
 };
 
 static struct kobj_attribute validate_attribute =
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index d92759c21fae..e180bd8e1400 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -191,7 +191,8 @@ int __init opal_event_init(void)
 	 * fall back to the legacy method (opal_event_request(...))
 	 * anyway. */
 	dn = of_find_compatible_node(NULL, NULL, "ibm,opal-event");
-	opal_event_irqchip.domain = irq_domain_add_linear(dn, MAX_NUM_EVENTS,
+	opal_event_irqchip.domain = irq_domain_create_linear(of_fwnode_handle(dn),
+				MAX_NUM_EVENTS,
 				&opal_event_domain_ops, &opal_event_irqchip);
 	of_node_put(dn);
 	if (!opal_event_irqchip.domain) {
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index 22d6efe17b0d..f1988d0ab45c 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -94,15 +94,15 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 }
 
 static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *to,
+				const struct bin_attribute *bin_attr, char *to,
 				loff_t pos, size_t count)
 {
 	return opal_msglog_copy(to, pos, count);
 }
 
-static struct bin_attribute opal_msglog_attr = {
+static struct bin_attribute opal_msglog_attr __ro_after_init = {
 	.attr = {.name = "msglog", .mode = 0400},
-	.read = opal_msglog_read
+	.read_new = opal_msglog_read
 };
 
 struct memcons *__init memcons_init(struct device_node *node, const char *mc_prop_name)
diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
deleted file mode 100644
index 7e419de71db8..000000000000
--- a/arch/powerpc/platforms/powernv/pci-cxl.c
+++ /dev/null
@@ -1,153 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2014-2016 IBM Corp.
- */
-
-#include <linux/module.h>
-#include <misc/cxl-base.h>
-#include <asm/pnv-pci.h>
-#include <asm/opal.h>
-
-#include "pci.h"
-
-int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	pe_info(pe, "Switching PHB to CXL\n");
-
-	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, mode, pe->pe_number);
-	if (rc == OPAL_UNSUPPORTED)
-		dev_err(&dev->dev, "Required cxl mode not supported by firmware - update skiboot\n");
-	else if (rc)
-		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
-
-	return rc;
-}
-EXPORT_SYMBOL(pnv_phb_to_cxl_mode);
-
-/* Find PHB for cxl dev and allocate MSI hwirqs?
- * Returns the absolute hardware IRQ number
- */
-int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
-
-	if (hwirq < 0) {
-		dev_warn(&dev->dev, "Failed to find a free MSI\n");
-		return -ENOSPC;
-	}
-
-	return phb->msi_base + hwirq;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
-
-void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
-
-void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
-				  struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq;
-
-	for (i = 1; i < CXL_IRQ_RANGES; i++) {
-		if (!irqs->range[i])
-			continue;
-		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
-			 i, irqs->offset[i],
-			 irqs->range[i]);
-		hwirq = irqs->offset[i] - phb->msi_base;
-		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
-				       irqs->range[i]);
-	}
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
-
-int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
-			       struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq, try;
-
-	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
-
-	/* 0 is reserved for the multiplexed PSL DSI interrupt */
-	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
-		try = num;
-		while (try) {
-			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
-			if (hwirq >= 0)
-				break;
-			try /= 2;
-		}
-		if (!try)
-			goto fail;
-
-		irqs->offset[i] = phb->msi_base + hwirq;
-		irqs->range[i] = try;
-		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
-			 i, irqs->offset[i], irqs->range[i]);
-		num -= try;
-	}
-	if (num)
-		goto fail;
-
-	return 0;
-fail:
-	pnv_cxl_release_hwirq_ranges(irqs, dev);
-	return -ENOSPC;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
-
-int pnv_cxl_get_irq_count(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	return phb->msi_bmp.irq_count;
-}
-EXPORT_SYMBOL(pnv_cxl_get_irq_count);
-
-int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
-			   unsigned int virq)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	unsigned int xive_num = hwirq - phb->msi_base;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	if (!(pe = pnv_ioda_get_pe(dev)))
-		return -ENODEV;
-
-	/* Assign XIVE to PE */
-	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
-	if (rc) {
-		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
-			"hwirq 0x%x XIVE 0x%x PE\n",
-			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
-		return -EIO;
-	}
-	pnv_set_msi_irq_chip(phb, virq);
-
-	return 0;
-}
-EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index b0a14e48175c..d8ccf2c9b98a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -39,8 +39,6 @@
 #include <asm/mmzone.h>
 #include <asm/xive.h>
 
-#include <misc/cxl-base.h>
-
 #include "powernv.h"
 #include "pci.h"
 #include "../../../../drivers/pci/pci.h"
@@ -1636,47 +1634,6 @@ int64_t pnv_opal_pci_msi_eoi(struct irq_data *d)
 	return opal_pci_msi_eoi(phb->opal_id, d->parent_data->hwirq);
 }
 
-/*
- * The IRQ data is mapped in the XICS domain, with OPAL HW IRQ numbers
- */
-static void pnv_ioda2_msi_eoi(struct irq_data *d)
-{
-	int64_t rc;
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
-	struct pnv_phb *phb = hose->private_data;
-
-	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
-	WARN_ON_ONCE(rc);
-
-	icp_native_eoi(d);
-}
-
-/* P8/CXL only */
-void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
-{
-	struct irq_data *idata;
-	struct irq_chip *ichip;
-
-	/* The MSI EOI OPAL call is only needed on PHB3 */
-	if (phb->model != PNV_PHB_MODEL_PHB3)
-		return;
-
-	if (!phb->ioda.irq_chip_init) {
-		/*
-		 * First time we setup an MSI IRQ, we need to setup the
-		 * corresponding IRQ chip to route correctly.
-		 */
-		idata = irq_get_irq_data(virq);
-		ichip = irq_data_get_irq_chip(idata);
-		phb->ioda.irq_chip_init = 1;
-		phb->ioda.irq_chip = *ichip;
-		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
-	}
-	irq_set_chip(virq, &phb->ioda.irq_chip);
-	irq_set_chip_data(virq, phb->hose);
-}
-
 static struct irq_chip pnv_pci_msi_irq_chip;
 
 /*
@@ -1924,7 +1881,7 @@ static const struct irq_domain_ops pnv_irq_domain_ops = {
 static int __init pnv_msi_allocate_domains(struct pci_controller *hose, unsigned int count)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct irq_domain *parent = irq_get_default_host();
+	struct irq_domain *parent = irq_get_default_domain();
 
 	hose->fwnode = irq_domain_alloc_named_id_fwnode("PNV-MSI", phb->opal_id);
 	if (!hose->fwnode)
@@ -1940,7 +1897,7 @@ static int __init pnv_msi_allocate_domains(struct pci_controller *hose, unsigned
 		return -ENOMEM;
 	}
 
-	hose->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(hose->dn),
+	hose->msi_domain = pci_msi_create_irq_domain(of_fwnode_handle(hose->dn),
 						     &pnv_msi_domain_info,
 						     hose->dev_domain);
 	if (!hose->msi_domain) {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 35f566aa0424..b2c1da025410 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -14,7 +14,6 @@
 #include <linux/io.h>
 #include <linux/msi.h>
 #include <linux/iommu.h>
-#include <linux/sched/mm.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -33,8 +32,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static DEFINE_MUTEX(tunnel_mutex);
-
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
 	struct device_node *node = np;
@@ -744,64 +741,6 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 	return tbl;
 }
 
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-	return of_node_get(hose->dn);
-}
-EXPORT_SYMBOL(pnv_pci_get_phb_node);
-
-int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
-{
-	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
-	u64 tunnel_bar;
-	__be64 val;
-	int rc;
-
-	if (!opal_check_token(OPAL_PCI_GET_PBCQ_TUNNEL_BAR))
-		return -ENXIO;
-	if (!opal_check_token(OPAL_PCI_SET_PBCQ_TUNNEL_BAR))
-		return -ENXIO;
-
-	mutex_lock(&tunnel_mutex);
-	rc = opal_pci_get_pbcq_tunnel_bar(phb->opal_id, &val);
-	if (rc != OPAL_SUCCESS) {
-		rc = -EIO;
-		goto out;
-	}
-	tunnel_bar = be64_to_cpu(val);
-	if (enable) {
-		/*
-		* Only one device per PHB can use atomics.
-		* Our policy is first-come, first-served.
-		*/
-		if (tunnel_bar) {
-			if (tunnel_bar != addr)
-				rc = -EBUSY;
-			else
-				rc = 0;	/* Setting same address twice is ok */
-			goto out;
-		}
-	} else {
-		/*
-		* The device that owns atomics and wants to release
-		* them must pass the same address with enable == 0.
-		*/
-		if (tunnel_bar != addr) {
-			rc = -EPERM;
-			goto out;
-		}
-		addr = 0x0ULL;
-	}
-	rc = opal_pci_set_pbcq_tunnel_bar(phb->opal_id, addr);
-	rc = opal_error_code(rc);
-out:
-	mutex_unlock(&tunnel_mutex);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
-
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 93fba1f8661f..42075501663b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -163,7 +163,6 @@ struct pnv_phb {
 		unsigned int		*io_segmap;
 
 		/* IRQ chip */
-		int			irq_chip_init;
 		struct irq_chip		irq_chip;
 
 		/* Sorted list of used PE's based
@@ -281,7 +280,6 @@ extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 extern struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn);
 extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
-extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
 extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 		__u64 window_size, __u32 levels);
 extern int pnv_eeh_post_init(void);
diff --git a/arch/powerpc/platforms/powernv/ultravisor.c b/arch/powerpc/platforms/powernv/ultravisor.c
index 67c8c4b2d8b1..157d9a8134e4 100644
--- a/arch/powerpc/platforms/powernv/ultravisor.c
+++ b/arch/powerpc/platforms/powernv/ultravisor.c
@@ -32,15 +32,15 @@ int __init early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
 static struct memcons *uv_memcons;
 
 static ssize_t uv_msglog_read(struct file *file, struct kobject *kobj,
-			      struct bin_attribute *bin_attr, char *to,
+			      const struct bin_attribute *bin_attr, char *to,
 			      loff_t pos, size_t count)
 {
 	return memcons_copy(uv_memcons, to, pos, count);
 }
 
-static struct bin_attribute uv_msglog_attr = {
+static struct bin_attribute uv_msglog_attr __ro_after_init = {
 	.attr = {.name = "msglog", .mode = 0400},
-	.read = uv_msglog_read
+	.read_new = uv_msglog_read
 };
 
 static int __init uv_init(void)
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 61722133eb2d..22d91ac424dd 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/reboot.h>
 #include <linux/rcuwait.h>
+#include <linux/string_choices.h>
 
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
@@ -724,7 +725,7 @@ static irqreturn_t ps3_notification_interrupt(int irq, void *data)
 static int ps3_notification_read_write(struct ps3_notification_device *dev,
 				       u64 lpar, int write)
 {
-	const char *op = write ? "write" : "read";
+	const char *op = str_write_read(write);
 	unsigned long flags;
 	int res;
 
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index af3fe9f04f24..a4ad4b49eef7 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -743,8 +743,8 @@ void __init ps3_init_IRQ(void)
 	unsigned cpu;
 	struct irq_domain *host;
 
-	host = irq_domain_add_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
-	irq_set_default_host(host);
+	host = irq_domain_create_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
+	irq_set_default_domain(host);
 
 	for_each_possible_cpu(cpu) {
 		struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index 4a2520ec6d7f..61b37c9400b2 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -190,10 +190,10 @@ static void spu_unmap(struct spu *spu)
 static int __init setup_areas(struct spu *spu)
 {
 	struct table {char* name; unsigned long addr; unsigned long size;};
-	unsigned long shadow_flags = pgprot_val(pgprot_noncached_wc(PAGE_KERNEL_RO));
 
 	spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr,
-					      sizeof(struct spe_shadow), shadow_flags);
+					      sizeof(struct spe_shadow),
+					      pgprot_noncached_wc(PAGE_KERNEL_RO));
 	if (!spu_pdata(spu)->shadow) {
 		pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__);
 		goto fail_ioremap;
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 42fc66e97539..fa3c2fff082a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -23,6 +23,7 @@ config PPC_PSERIES
 	select FORCE_SMP
 	select SWIOTLB
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config PARAVIRT
@@ -128,6 +129,15 @@ config CMM
 	  will be reused for other LPARs. The interface allows firmware to
 	  balance memory across many LPARs.
 
+config HTMDUMP
+	tristate "PowerVM data dumper"
+	depends on PPC_PSERIES && DEBUG_FS
+	default m
+	help
+	  Select this option, if you want to enable the kernel debugfs
+	  interface to dump the Hardware Trace Macro (HTM) function data
+	  in the LPAR.
+
 config HV_PERF_CTRS
 	bool "Hypervisor supplied PMU events (24x7 & GPCI)"
 	default y
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 7bf506f6b8c8..57222678bb3f 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -3,7 +3,8 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   of_helpers.o rtas-work-area.o papr-sysparm.o \
-			   papr-vpd.o \
+			   papr-rtas-common.o papr-vpd.o papr-indices.o \
+			   papr-platform-dump.o papr-phy-attest.o \
 			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o mobility.o rng.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o \
@@ -19,6 +20,7 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_CMM)		+= cmm.o
+obj-$(CONFIG_HTMDUMP)		+= htmdump.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
diff --git a/arch/powerpc/platforms/pseries/htmdump.c b/arch/powerpc/platforms/pseries/htmdump.c
new file mode 100644
index 000000000000..742ec52c9d4d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/htmdump.c
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) IBM Corporation, 2024
+ */
+
+#define pr_fmt(fmt) "htmdump: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/kvm_guest.h>
+
+static void *htm_buf;
+static void *htm_status_buf;
+static void *htm_info_buf;
+static void *htm_caps_buf;
+static u32 nodeindex;
+static u32 nodalchipindex;
+static u32 coreindexonchip;
+static u32 htmtype;
+static u32 htmconfigure;
+static u32 htmstart;
+static u32 htmsetup;
+static u64 htmflags;
+
+static struct dentry *htmdump_debugfs_dir;
+#define	HTM_ENABLE	1
+#define	HTM_DISABLE	0
+#define	HTM_NOWRAP	1
+#define	HTM_WRAP	0
+
+/*
+ * Check the return code for H_HTM hcall.
+ * Return non-zero value (1) if either H_PARTIAL or H_SUCCESS
+ * is returned. For other return codes:
+ * Return zero if H_NOT_AVAILABLE.
+ * Return -EBUSY if hcall return busy.
+ * Return -EINVAL if any parameter or operation is not valid.
+ * Return -EPERM if HTM Virtualization Engine Technology code
+ * is not applied.
+ * Return -EIO if the HTM state is not valid.
+ */
+static ssize_t htm_return_check(long rc)
+{
+	switch (rc) {
+	case H_SUCCESS:
+	/* H_PARTIAL for the case where all available data can't be
+	 * returned due to buffer size constraint.
+	 */
+	case H_PARTIAL:
+		break;
+	/* H_NOT_AVAILABLE indicates reading from an offset outside the range,
+	 * i.e. past end of file.
+	 */
+	case H_NOT_AVAILABLE:
+		return 0;
+	case H_BUSY:
+	case H_LONG_BUSY_ORDER_1_MSEC:
+	case H_LONG_BUSY_ORDER_10_MSEC:
+	case H_LONG_BUSY_ORDER_100_MSEC:
+	case H_LONG_BUSY_ORDER_1_SEC:
+	case H_LONG_BUSY_ORDER_10_SEC:
+	case H_LONG_BUSY_ORDER_100_SEC:
+		return -EBUSY;
+	case H_PARAMETER:
+	case H_P2:
+	case H_P3:
+	case H_P4:
+	case H_P5:
+	case H_P6:
+		return -EINVAL;
+	case H_STATE:
+		return -EIO;
+	case H_AUTHORITY:
+		return -EPERM;
+	}
+
+	/*
+	 * Return 1 for H_SUCCESS/H_PARTIAL
+	 */
+	return 1;
+}
+
+static ssize_t htmdump_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_buf = filp->private_data;
+	unsigned long page, read_size, available;
+	loff_t offset;
+	long rc, ret;
+
+	page = ALIGN_DOWN(*ppos, PAGE_SIZE);
+	offset = (*ppos) % PAGE_SIZE;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm dump (H_HTM_OP_DUMP_DATA)
+	 * - last three values are address, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf),
+				   PAGE_SIZE, page);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_DUMP_DATA, returning %ld\n", ret);
+		return ret;
+	}
+
+	available = PAGE_SIZE;
+	read_size = min(count, available);
+	*ppos += read_size;
+	return simple_read_from_buffer(ubuf, count, &offset, htm_buf, available);
+}
+
+static const struct file_operations htmdump_fops = {
+	.llseek = NULL,
+	.read	= htmdump_read,
+	.open	= simple_open,
+};
+
+static int  htmconfigure_set(void *data, u64 val)
+{
+	long rc, ret;
+	unsigned long param1 = -1, param2 = -1;
+
+	/*
+	 * value as 1 : configure HTM.
+	 * value as 0 : deconfigure HTM. Return -EINVAL for
+	 * other values.
+	 */
+	if (val == HTM_ENABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm configure (H_HTM_OP_CONFIGURE)
+		 * - If htmflags is set, param1 and param2 will be -1
+		 *   which is an indicator to use default htm mode reg mask
+		 *   and htm mode reg value.
+		 * - last three values are unused, hence set to zero
+		 */
+		if (!htmflags) {
+			param1 = 0;
+			param2 = 0;
+		}
+
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			   htmtype, H_HTM_OP_CONFIGURE, param1, param2, 0);
+	} else if (val == HTM_DISABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm deconfigure (H_HTM_OP_DECONFIGURE)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				htmtype, H_HTM_OP_DECONFIGURE, 0, 0, 0);
+	} else
+		return -EINVAL;
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmconfigure if operation succeeds */
+	htmconfigure = val;
+
+	return 0;
+}
+
+static int htmconfigure_get(void *data, u64 *val)
+{
+	*val = htmconfigure;
+	return 0;
+}
+
+static int  htmstart_set(void *data, u64 val)
+{
+	long rc, ret;
+
+	/*
+	 * value as 1: start HTM
+	 * value as 0: stop HTM
+	 * Return -EINVAL for other values.
+	 */
+	if (val == HTM_ENABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm start (H_HTM_OP_START)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			   htmtype, H_HTM_OP_START, 0, 0, 0);
+
+	} else if (val == HTM_DISABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm stop (H_HTM_OP_STOP)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				htmtype, H_HTM_OP_STOP, 0, 0, 0);
+	} else
+		return -EINVAL;
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmstart if H_HTM_OP_START/H_HTM_OP_STOP operation succeeds */
+	htmstart = val;
+
+	return 0;
+}
+
+static int htmstart_get(void *data, u64 *val)
+{
+	*val = htmstart;
+	return 0;
+}
+
+static ssize_t htmstatus_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_status_buf = filp->private_data;
+	long rc, ret;
+	u64 *num_entries;
+	u64 to_copy;
+	int htmstatus_flag;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm status (H_HTM_OP_STATUS)
+	 * - last three values as addr, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_buf),
+				   PAGE_SIZE, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_STATUS, returning %ld\n", ret);
+		return ret;
+	}
+
+	/*
+	 * HTM status buffer, start of buffer + 0x10 gives the
+	 * number of HTM entries in the buffer. Each nest htm status
+	 * entry is 0x6 bytes where each core htm status entry is
+	 * 0x8 bytes.
+	 * So total count to copy is:
+	 * 32 bytes (for first 7 fields) + (number of HTM entries * entry size)
+	 */
+	num_entries = htm_status_buf + 0x10;
+	if (htmtype == 0x2)
+		htmstatus_flag = 0x8;
+	else
+		htmstatus_flag = 0x6;
+	to_copy = 32 + (be64_to_cpu(*num_entries) * htmstatus_flag);
+	return simple_read_from_buffer(ubuf, count, ppos, htm_status_buf, to_copy);
+}
+
+static const struct file_operations htmstatus_fops = {
+	.llseek = NULL,
+	.read	= htmstatus_read,
+	.open	= simple_open,
+};
+
+static ssize_t htminfo_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_info_buf = filp->private_data;
+	long rc, ret;
+	u64 *num_entries;
+	u64 to_copy;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm status (H_HTM_OP_STATUS)
+	 * - last three values as addr, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_buf),
+				   PAGE_SIZE, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_DUMP_SYSPROC_CONF, returning %ld\n", ret);
+		return ret;
+	}
+
+	/*
+	 * HTM status buffer, start of buffer + 0x10 gives the
+	 * number of HTM entries in the buffer. Each entry of processor
+	 * is 16 bytes.
+	 *
+	 * So total count to copy is:
+	 * 32 bytes (for first 5 fields) + (number of HTM entries * entry size)
+	 */
+	num_entries = htm_info_buf + 0x10;
+	to_copy = 32 + (be64_to_cpu(*num_entries) * 16);
+	return simple_read_from_buffer(ubuf, count, ppos, htm_info_buf, to_copy);
+}
+
+static ssize_t htmcaps_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_caps_buf = filp->private_data;
+	long rc, ret;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm capabilities (H_HTM_OP_CAPABILITIES)
+	 * - last three values as addr, size (0x80 for Capabilities Output Buffer
+	 *   and zero
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_buf),
+				   0x80, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_CAPABILITIES, returning %ld\n", ret);
+		return ret;
+	}
+
+	return simple_read_from_buffer(ubuf, count, ppos, htm_caps_buf, 0x80);
+}
+
+static const struct file_operations htminfo_fops = {
+	.llseek = NULL,
+	.read   = htminfo_read,
+	.open   = simple_open,
+};
+
+static const struct file_operations htmcaps_fops = {
+	.llseek = NULL,
+	.read   = htmcaps_read,
+	.open   = simple_open,
+};
+
+static int  htmsetup_set(void *data, u64 val)
+{
+	long rc, ret;
+
+	/*
+	 * Input value: HTM buffer size in the power of 2
+	 * example: hex value 0x21 ( decimal: 33 ) is for
+	 * 8GB
+	 * Invoke H_HTM call with:
+	 * - operation as htm start (H_HTM_OP_SETUP)
+	 * - parameter 1 set to input value.
+	 * - last two values are unused, hence set to zero
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			htmtype, H_HTM_OP_SETUP, val, 0, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_SETUP, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmsetup if H_HTM_OP_SETUP operation succeeds */
+	htmsetup = val;
+
+	return 0;
+}
+
+static int htmsetup_get(void *data, u64 *val)
+{
+	*val = htmsetup;
+	return 0;
+}
+
+static int  htmflags_set(void *data, u64 val)
+{
+	/*
+	 * Input value:
+	 * Currently supported flag value is to enable/disable
+	 * HTM buffer wrap. wrap is used along with "configure"
+	 * to prevent HTM buffer from wrapping.
+	 * Writing 1 will set noWrap while configuring HTM
+	 */
+	if (val == HTM_NOWRAP)
+		htmflags = H_HTM_FLAGS_NOWRAP;
+	else if (val == HTM_WRAP)
+		htmflags = 0;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int htmflags_get(void *data, u64 *val)
+{
+	*val = htmflags;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(htmconfigure_fops, htmconfigure_get, htmconfigure_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmstart_fops, htmstart_get, htmstart_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmsetup_fops, htmsetup_get, htmsetup_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmflags_fops, htmflags_get, htmflags_set, "%llu\n");
+
+static int htmdump_init_debugfs(void)
+{
+	htm_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_buf) {
+		pr_err("Failed to allocate htmdump buf\n");
+		return -ENOMEM;
+	}
+
+	htmdump_debugfs_dir = debugfs_create_dir("htmdump",
+						  arch_debugfs_dir);
+
+	debugfs_create_u32("nodeindex", 0600,
+			htmdump_debugfs_dir, &nodeindex);
+	debugfs_create_u32("nodalchipindex", 0600,
+			htmdump_debugfs_dir, &nodalchipindex);
+	debugfs_create_u32("coreindexonchip", 0600,
+			htmdump_debugfs_dir, &coreindexonchip);
+	debugfs_create_u32("htmtype", 0600,
+			htmdump_debugfs_dir, &htmtype);
+	debugfs_create_file("trace", 0400, htmdump_debugfs_dir, htm_buf, &htmdump_fops);
+
+	/*
+	 * Debugfs interface files to control HTM operations:
+	 */
+	debugfs_create_file("htmconfigure", 0600, htmdump_debugfs_dir, NULL, &htmconfigure_fops);
+	debugfs_create_file("htmstart", 0600, htmdump_debugfs_dir, NULL, &htmstart_fops);
+	debugfs_create_file("htmsetup", 0600, htmdump_debugfs_dir, NULL, &htmsetup_fops);
+	debugfs_create_file("htmflags", 0600, htmdump_debugfs_dir, NULL, &htmflags_fops);
+
+	/* Debugfs interface file to present status of HTM */
+	htm_status_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_status_buf) {
+		pr_err("Failed to allocate htmstatus buf\n");
+		return -ENOMEM;
+	}
+
+	/* Debugfs interface file to present System Processor Configuration */
+	htm_info_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_info_buf) {
+		pr_err("Failed to allocate htm info buf\n");
+		return -ENOMEM;
+	}
+
+	/* Debugfs interface file to present HTM capabilities */
+	htm_caps_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_caps_buf) {
+		pr_err("Failed to allocate htm caps buf\n");
+		return -ENOMEM;
+	}
+
+	debugfs_create_file("htmstatus", 0400, htmdump_debugfs_dir, htm_status_buf, &htmstatus_fops);
+	debugfs_create_file("htminfo", 0400, htmdump_debugfs_dir, htm_info_buf, &htminfo_fops);
+	debugfs_create_file("htmcaps", 0400, htmdump_debugfs_dir, htm_caps_buf, &htmcaps_fops);
+
+	return 0;
+}
+
+static int __init htmdump_init(void)
+{
+	/* Disable on kvm guest */
+	if (is_kvm_guest()) {
+		pr_info("htmdump not supported inside KVM guest\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (htmdump_init_debugfs())
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit htmdump_exit(void)
+{
+	debugfs_remove_recursive(htmdump_debugfs_dir);
+	kfree(htm_buf);
+}
+
+module_init(htmdump_init);
+module_exit(htmdump_exit);
+MODULE_DESCRIPTION("PHYP Hardware Trace Macro (HTM) data dumper");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index ae6f7a235d8b..eec333dd2e59 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -52,7 +52,8 @@ enum {
 enum {
 	DDW_EXT_SIZE = 0,
 	DDW_EXT_RESET_DMA_WIN = 1,
-	DDW_EXT_QUERY_OUT_SIZE = 2
+	DDW_EXT_QUERY_OUT_SIZE = 2,
+	DDW_EXT_LIMITED_ADDR_MODE = 3
 };
 
 static struct iommu_table *iommu_pseries_alloc_table(int node)
@@ -196,7 +197,7 @@ static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
 
 static void tce_free_pSeries(struct iommu_table *tbl)
 {
-	if (!tbl->it_userspace)
+	if (tbl->it_userspace)
 		tce_iommu_userspace_view_free(tbl);
 }
 
@@ -1284,17 +1285,13 @@ static LIST_HEAD(failed_ddw_pdn_list);
 
 static phys_addr_t ddw_memory_hotplug_max(void)
 {
-	resource_size_t max_addr = memory_hotplug_max();
-	struct device_node *memory;
+	resource_size_t max_addr;
 
-	for_each_node_by_type(memory, "memory") {
-		struct resource res;
-
-		if (of_address_to_resource(memory, 0, &res))
-			continue;
-
-		max_addr = max_t(resource_size_t, max_addr, res.end + 1);
-	}
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+	max_addr = hot_add_drconf_memory_max();
+#else
+	max_addr = memblock_end_of_DRAM();
+#endif
 
 	return max_addr;
 }
@@ -1331,6 +1328,54 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
 			 ret);
 }
 
+/*
+ * Platforms support placing PHB in limited address mode starting with LoPAR
+ * level 2.13 implement. In this mode, the DMA address returned by DDW is over
+ * 4GB but, less than 64-bits. This benefits IO adapters that don't support
+ * 64-bits for DMA addresses.
+ */
+static int limited_dma_window(struct pci_dev *dev, struct device_node *par_dn)
+{
+	int ret;
+	u32 cfg_addr, reset_dma_win, las_supported;
+	u64 buid;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
+	if (ret)
+		goto out;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_LIMITED_ADDR_MODE, &las_supported);
+
+	/* Limited Address Space extension available on the platform but DDW in
+	 * limited addressing mode not supported
+	 */
+	if (!ret && !las_supported)
+		ret = -EPROTO;
+
+	if (ret) {
+		dev_info(&dev->dev, "Limited Address Space for DDW not Supported, err: %d", ret);
+		goto out;
+	}
+
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8);
+
+	ret = rtas_call(reset_dma_win, 4, 1, NULL, cfg_addr, BUID_HI(buid),
+			BUID_LO(buid), 1);
+	if (ret)
+		dev_info(&dev->dev,
+			 "ibm,reset-pe-dma-windows(%x) for Limited Addr Support: %x %x %x returned %d ",
+			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
+			 ret);
+
+out:
+	return ret;
+}
+
 /* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */
 static int iommu_get_page_shift(u32 query_page_size)
 {
@@ -1398,7 +1443,7 @@ static struct property *ddw_property_create(const char *propname, u32 liobn, u64
  *
  * returns true if can map all pages (direct mapping), false otherwise..
  */
-static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
+static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mask)
 {
 	int len = 0, ret;
 	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
@@ -1417,6 +1462,9 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	bool pmem_present;
 	struct pci_dn *pci = PCI_DN(pdn);
 	struct property *default_win = NULL;
+	bool limited_addr_req = false, limited_addr_enabled = false;
+	int dev_max_ddw;
+	int ddw_sz;
 
 	dn = of_find_node_by_type(NULL, "ibm,pmemory");
 	pmem_present = dn != NULL;
@@ -1443,7 +1491,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * the ibm,ddw-applicable property holds the tokens for:
 	 * ibm,query-pe-dma-window
 	 * ibm,create-pe-dma-window
-	 * ibm,remove-pe-dma-window
 	 * for the given node in that order.
 	 * the property is actually in the parent, not the PE
 	 */
@@ -1463,6 +1510,20 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_failed;
 
+	/* DMA Limited Addressing required? This is when the driver has
+	 * requested to create DDW but supports mask which is less than 64-bits
+	 */
+	limited_addr_req = (dma_mask != DMA_BIT_MASK(64));
+
+	/* place the PHB in Limited Addressing mode */
+	if (limited_addr_req) {
+		if (limited_dma_window(dev, pdn))
+			goto out_failed;
+
+		/* PHB is in Limited address mode */
+		limited_addr_enabled = true;
+	}
+
 	/*
 	 * If there is no window available, remove the default DMA window,
 	 * if it's present. This will make all the resources available to the
@@ -1509,6 +1570,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		goto out_failed;
 	}
 
+	/* Maximum DMA window size that the device can address (in log2) */
+	dev_max_ddw = fls64(dma_mask);
+
+	/* If the device DMA mask is less than 64-bits, make sure the DMA window
+	 * size is not bigger than what the device can access
+	 */
+	ddw_sz = min(order_base_2(query.largest_available_block << page_shift),
+			dev_max_ddw);
+
 	/*
 	 * The "ibm,pmemory" can appear anywhere in the address space.
 	 * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
@@ -1517,23 +1587,21 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 */
 	len = max_ram_len;
 	if (pmem_present) {
-		if (query.largest_available_block >=
-		    (1ULL << (MAX_PHYSMEM_BITS - page_shift)))
+		if (ddw_sz >= MAX_PHYSMEM_BITS)
 			len = MAX_PHYSMEM_BITS;
 		else
 			dev_info(&dev->dev, "Skipping ibm,pmemory");
 	}
 
 	/* check if the available block * number of ptes will map everything */
-	if (query.largest_available_block < (1ULL << (len - page_shift))) {
+	if (ddw_sz < len) {
 		dev_dbg(&dev->dev,
 			"can't map partition max 0x%llx with %llu %llu-sized pages\n",
 			1ULL << len,
 			query.largest_available_block,
 			1ULL << page_shift);
 
-		len = order_base_2(query.largest_available_block << page_shift);
-
+		len = ddw_sz;
 		dynamic_mapping = true;
 	} else {
 		direct_mapping = !default_win_removed ||
@@ -1547,8 +1615,9 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		 */
 		if (default_win_removed && pmem_present && !direct_mapping) {
 			/* DDW is big enough to be split */
-			if ((query.largest_available_block << page_shift) >=
-			     MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) {
+			if ((1ULL << ddw_sz) >=
+			    MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) {
+
 				direct_mapping = true;
 
 				/* offset of the Dynamic part of DDW */
@@ -1559,8 +1628,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			dynamic_mapping = true;
 
 			/* create max size DDW possible */
-			len = order_base_2(query.largest_available_block
-							<< page_shift);
+			len = ddw_sz;
 		}
 	}
 
@@ -1600,7 +1668,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	if (direct_mapping) {
 		/* DDW maps the whole partition, so enable direct DMA mapping */
-		ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
+		ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >> PAGE_SHIFT,
 					    win64->value, tce_setrange_multi_pSeriesLP_walk);
 		if (ret) {
 			dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
@@ -1689,7 +1757,7 @@ out_remove_win:
 	__remove_dma_window(pdn, ddw_avail, create.liobn);
 
 out_failed:
-	if (default_win_removed)
+	if (default_win_removed || limited_addr_enabled)
 		reset_dma_window(dev, pdn);
 
 	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
@@ -1708,6 +1776,9 @@ out_unlock:
 		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset +
 						(1ULL << max_ram_len);
 
+	dev_info(&dev->dev, "lsa_required: %x, lsa_enabled: %x, direct mapping: %x\n",
+			limited_addr_req, limited_addr_enabled, direct_mapping);
+
 	return direct_mapping;
 }
 
@@ -1833,8 +1904,11 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
 	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 
-	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (dma_mask < DMA_BIT_MASK(64))
+	/* For DDW, DMA mask should be more than 32-bits. For mask more then
+	 * 32-bits but less then 64-bits, DMA addressing is supported in
+	 * Limited Addressing mode.
+	 */
+	if (dma_mask <= DMA_BIT_MASK(32))
 		return false;
 
 	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
@@ -1847,7 +1921,7 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 	 */
 	pdn = pci_dma_find(dn, NULL);
 	if (pdn && PCI_DN(pdn))
-		return enable_ddw(pdev, pdn);
+		return enable_ddw(pdev, pdn, dma_mask);
 
 	return false;
 }
@@ -2349,11 +2423,17 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	struct memory_notify *arg = data;
 	int ret = 0;
 
+	/* This notifier can get called when onlining persistent memory as well.
+	 * TCEs are not pre-mapped for persistent memory. Persistent memory will
+	 * always be above ddw_memory_hotplug_max()
+	 */
+
 	switch (action) {
 	case MEM_GOING_ONLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			if (window->direct) {
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
 				ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
 						arg->nr_pages, window->prop);
 			}
@@ -2365,7 +2445,8 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	case MEM_OFFLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			if (window->direct) {
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
 				ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
 						arg->nr_pages, window->prop);
 			}
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index fdc2f7f38dc9..ee1c8c6898a3 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -525,7 +525,12 @@ static struct msi_domain_info pseries_msi_domain_info = {
 
 static void pseries_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	__pci_read_msi_msg(irq_data_get_msi_desc(data), msg);
+	struct pci_dev *dev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+
+	if (dev->current_state == PCI_D0)
+		__pci_read_msi_msg(irq_data_get_msi_desc(data), msg);
+	else
+		get_cached_msi_msg(data->irq, msg);
 }
 
 static struct irq_chip pseries_msi_irq_chip = {
@@ -611,7 +616,7 @@ static const struct irq_domain_ops pseries_irq_domain_ops = {
 static int __pseries_msi_allocate_domains(struct pci_controller *phb,
 					  unsigned int count)
 {
-	struct irq_domain *parent = irq_get_default_host();
+	struct irq_domain *parent = irq_get_default_domain();
 
 	phb->fwnode = irq_domain_alloc_named_id_fwnode("pSeries-MSI",
 						       phb->global_number);
@@ -628,7 +633,7 @@ static int __pseries_msi_allocate_domains(struct pci_controller *phb,
 		return -ENOMEM;
 	}
 
-	phb->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(phb->dn),
+	phb->msi_domain = pci_msi_create_irq_domain(of_fwnode_handle(phb->dn),
 						    &pseries_msi_domain_info,
 						    phb->dev_domain);
 	if (!phb->msi_domain) {
diff --git a/arch/powerpc/platforms/pseries/papr-indices.c b/arch/powerpc/platforms/pseries/papr-indices.c
new file mode 100644
index 000000000000..3c7545591c45
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-indices.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-indices: " fmt
+
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-indices.h>
+#include "papr-rtas-common.h"
+
+/*
+ * Function-specific return values for ibm,set-dynamic-indicator and
+ * ibm,get-dynamic-sensor-state RTAS calls.
+ * PAPR+ v2.13 7.3.18 and 7.3.19.
+ */
+#define RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR	-3
+
+/**
+ * struct rtas_get_indices_params - Parameters (in and out) for
+ *                                      ibm,get-indices.
+ * @is_sensor:	In: Caller-provided whether sensor or indicator.
+ * @indice_type:In: Caller-provided indice (sensor or indicator) token
+ * @work_area:	In: Caller-provided work area buffer for results.
+ * @next:	In: Sequence number. Out: Next sequence number.
+ * @status:	Out: RTAS call status.
+ */
+struct rtas_get_indices_params {
+	u8 is_sensor;
+	u32 indice_type;
+	struct rtas_work_area *work_area;
+	u32 next;
+	s32 status;
+};
+
+/*
+ * rtas_ibm_get_indices() - Call ibm,get-indices to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_indices_params.
+ *
+ * Calls ibm,get-indices until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_indices() multiple times
+ * to retrieve all indices data for the provided indice type. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of
+ * indices retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_indices(struct rtas_get_indices_params *params)
+{
+	struct rtas_work_area *work_area = params->work_area;
+	const s32 token = rtas_function_token(RTAS_FN_IBM_GET_INDICES);
+	u32 rets;
+	s32 fwrc;
+	int ret;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	lockdep_assert_held(&rtas_ibm_get_indices_lock);
+
+	do {
+		fwrc = rtas_call(token, 5, 2, &rets, params->is_sensor,
+				params->indice_type,
+				rtas_work_area_phys(work_area),
+				rtas_work_area_size(work_area),
+				params->next);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER: /* Indicator type is not supported */
+		ret = -EINVAL;
+		break;
+	case RTAS_SEQ_START_OVER:
+		ret = -EAGAIN;
+		pr_info_ratelimited("Indices changed during retrieval, retrying\n");
+		params->next = 1;
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		params->next = rets;
+		ret = 0;
+		break;
+	case RTAS_SEQ_COMPLETE:
+		params->next = 0;
+		ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-indices status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal indices sequence APIs. A sequence is a series of calls to
+ * ibm,get-indices for a given location code. The sequence ends when
+ * an error is encountered or all indices for the input has been
+ * returned.
+ */
+
+/*
+ * indices_sequence_begin() - Begin a indices retrieval sequence.
+ *
+ * Context: May sleep.
+ */
+static void indices_sequence_begin(struct papr_rtas_sequence *seq)
+{
+	struct rtas_get_indices_params  *param;
+
+	param = (struct rtas_get_indices_params *)seq->params;
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_get_indices_lock);
+	param->work_area = rtas_work_area_alloc(RTAS_GET_INDICES_BUF_SIZE);
+	param->next = 1;
+	param->status = 0;
+}
+
+/*
+ * indices_sequence_end() - Finalize a indices retrieval sequence.
+ *
+ * Releases resources obtained by indices_sequence_begin().
+ */
+static void indices_sequence_end(struct papr_rtas_sequence *seq)
+{
+	struct rtas_get_indices_params *param;
+
+	param =  (struct rtas_get_indices_params *)seq->params;
+	rtas_work_area_free(param->work_area);
+	mutex_unlock(&rtas_ibm_get_indices_lock);
+}
+
+/*
+ * Work function to be passed to papr_rtas_blob_generate().
+ *
+ * ibm,get-indices RTAS call fills the work area with the certain
+ * format but does not return the bytes written in the buffer. So
+ * instead of kernel parsing this work area to determine the buffer
+ * length, copy the complete work area (RTAS_GET_INDICES_BUF_SIZE)
+ * to the blob and let the user space to obtain the data.
+ * Means RTAS_GET_INDICES_BUF_SIZE data will be returned for each
+ * read().
+ */
+
+static const char *indices_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
+{
+	struct rtas_get_indices_params *p;
+	bool init_state;
+
+	p = (struct rtas_get_indices_params *)seq->params;
+	init_state = (p->next == 1) ? true : false;
+
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
+		return NULL;
+	if (papr_rtas_sequence_set_err(seq, rtas_ibm_get_indices(p)))
+		return NULL;
+
+	*len = RTAS_GET_INDICES_BUF_SIZE;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+/*
+ * papr_indices_handle_read - returns indices blob data to the user space
+ *
+ * ibm,get-indices RTAS call fills the work area with the certian
+ * format but does not return the bytes written in the buffer and
+ * copied RTAS_GET_INDICES_BUF_SIZE data to the blob for each RTAS
+ * call. So send RTAS_GET_INDICES_BUF_SIZE buffer to the user space
+ * for each read().
+ */
+static ssize_t papr_indices_handle_read(struct file *file,
+		char __user *buf, size_t size, loff_t *off)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	/* we should not instantiate a handle without any data attached. */
+	if (!papr_rtas_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	if (size < RTAS_GET_INDICES_BUF_SIZE) {
+		pr_err_once("Invalid buffer length %ld, expect %d\n",
+				size, RTAS_GET_INDICES_BUF_SIZE);
+		return -EINVAL;
+	} else if (size > RTAS_GET_INDICES_BUF_SIZE)
+		size = RTAS_GET_INDICES_BUF_SIZE;
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+static const struct file_operations papr_indices_handle_ops = {
+	.read = papr_indices_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
+};
+
+/*
+ * papr_indices_create_handle() - Create a fd-based handle for reading
+ *                                indices data
+ * @ubuf: Input parameters to RTAS call such as whether sensor or indicator
+ *        and indice type in user memory
+ *
+ * Handler for PAPR_INDICES_IOC_GET ioctl command. Validates @ubuf
+ * and instantiates an immutable indices "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested indices is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-indices call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_indices_create_handle(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_rtas_sequence seq = {};
+	struct rtas_get_indices_params params = {};
+	int fd;
+
+	if (get_user(params.is_sensor, &ubuf->indices.is_sensor))
+		return -EFAULT;
+
+	if (get_user(params.indice_type, &ubuf->indices.indice_type))
+		return -EFAULT;
+
+	seq = (struct papr_rtas_sequence) {
+		.begin = indices_sequence_begin,
+		.end = indices_sequence_end,
+		.work = indices_sequence_fill_work_area,
+	};
+
+	seq.params = &params;
+	fd = papr_rtas_setup_file_interface(&seq,
+			&papr_indices_handle_ops, "[papr-indices]");
+
+	return fd;
+}
+
+/*
+ * Create work area with the input parameters. This function is used
+ * for both ibm,set-dynamic-indicator and ibm,get-dynamic-sensor-state
+ * RTAS Calls.
+ */
+static struct rtas_work_area *
+papr_dynamic_indice_buf_from_user(struct papr_indices_io_block __user *ubuf,
+				struct papr_indices_io_block *kbuf)
+{
+	struct rtas_work_area *work_area;
+	u32 length;
+	__be32 len_be;
+
+	if (copy_from_user(kbuf, ubuf, sizeof(*kbuf)))
+		return ERR_PTR(-EFAULT);
+
+
+	if (!string_is_terminated(kbuf->dynamic_param.location_code_str,
+			ARRAY_SIZE(kbuf->dynamic_param.location_code_str)))
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * The input data in the work area should be as follows:
+	 * - 32-bit integer length of the location code string,
+	 *   including NULL.
+	 * - Location code string, NULL terminated, identifying the
+	 *   token (sensor or indicator).
+	 * PAPR 2.13 - R1–7.3.18–5 ibm,set-dynamic-indicator
+	 *           - R1–7.3.19–5 ibm,get-dynamic-sensor-state
+	 */
+	/*
+	 * Length that user space passed should also include NULL
+	 * terminator.
+	 */
+	length = strlen(kbuf->dynamic_param.location_code_str) + 1;
+	if (length > LOC_CODE_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	len_be = cpu_to_be32(length);
+
+	work_area = rtas_work_area_alloc(LOC_CODE_SIZE + sizeof(u32));
+	memcpy(rtas_work_area_raw_buf(work_area), &len_be, sizeof(u32));
+	memcpy((rtas_work_area_raw_buf(work_area) + sizeof(u32)),
+			&kbuf->dynamic_param.location_code_str, length);
+
+	return work_area;
+}
+
+/**
+ * papr_dynamic_indicator_ioc_set - ibm,set-dynamic-indicator RTAS Call
+ * PAPR 2.13 7.3.18
+ *
+ * @ubuf: Input parameters to RTAS call such as indicator token and
+ *        new state.
+ *
+ * Returns success or -errno.
+ */
+static long papr_dynamic_indicator_ioc_set(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_indices_io_block kbuf;
+	struct rtas_work_area *work_area;
+	s32 fwrc, token, ret;
+
+	token = rtas_function_token(RTAS_FN_IBM_SET_DYNAMIC_INDICATOR);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	mutex_lock(&rtas_ibm_set_dynamic_indicator_lock);
+	work_area = papr_dynamic_indice_buf_from_user(ubuf, &kbuf);
+	if (IS_ERR(work_area)) {
+		ret = PTR_ERR(work_area);
+		goto out;
+	}
+
+	do {
+		fwrc = rtas_call(token, 3, 1, NULL,
+				kbuf.dynamic_param.token,
+				kbuf.dynamic_param.state,
+				rtas_work_area_phys(work_area));
+	} while (rtas_busy_delay(fwrc));
+
+	rtas_work_area_free(work_area);
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		ret = 0;
+		break;
+	case RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR:	/* No such indicator */
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		pr_err("unexpected ibm,set-dynamic-indicator result %d\n",
+			fwrc);
+		fallthrough;
+	case RTAS_HARDWARE_ERROR:	/* Hardware/platform error */
+		ret = -EIO;
+		break;
+	}
+
+out:
+	mutex_unlock(&rtas_ibm_set_dynamic_indicator_lock);
+	return ret;
+}
+
+/**
+ * papr_dynamic_sensor_ioc_get - ibm,get-dynamic-sensor-state RTAS Call
+ * PAPR 2.13 7.3.19
+ *
+ * @ubuf: Input parameters to RTAS call such as sensor token
+ *        Copies the state in user space buffer.
+ *
+ *
+ * Returns success or -errno.
+ */
+
+static long papr_dynamic_sensor_ioc_get(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_indices_io_block kbuf;
+	struct rtas_work_area *work_area;
+	s32 fwrc, token, ret;
+	u32 rets;
+
+	token = rtas_function_token(RTAS_FN_IBM_GET_DYNAMIC_SENSOR_STATE);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	mutex_lock(&rtas_ibm_get_dynamic_sensor_state_lock);
+	work_area = papr_dynamic_indice_buf_from_user(ubuf, &kbuf);
+	if (IS_ERR(work_area)) {
+		ret = PTR_ERR(work_area);
+		goto out;
+	}
+
+	do {
+		fwrc = rtas_call(token, 2, 2, &rets,
+				kbuf.dynamic_param.token,
+				rtas_work_area_phys(work_area));
+	} while (rtas_busy_delay(fwrc));
+
+	rtas_work_area_free(work_area);
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		if (put_user(rets, &ubuf->dynamic_param.state))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	case RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR:	/* No such indicator */
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		pr_err("unexpected ibm,get-dynamic-sensor result %d\n",
+				fwrc);
+		fallthrough;
+	case RTAS_HARDWARE_ERROR:	/* Hardware/platform error */
+		ret = -EIO;
+		break;
+	}
+
+out:
+	mutex_unlock(&rtas_ibm_get_dynamic_sensor_state_lock);
+	return ret;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-indices.
+ */
+static long papr_indices_dev_ioctl(struct file *filp, unsigned int ioctl,
+				unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_INDICES_IOC_GET:
+		ret = papr_indices_create_handle(argp);
+		break;
+	case PAPR_DYNAMIC_SENSOR_IOC_GET:
+		ret = papr_dynamic_sensor_ioc_get(argp);
+		break;
+	case PAPR_DYNAMIC_INDICATOR_IOC_SET:
+		if (filp->f_mode & FMODE_WRITE)
+			ret = papr_dynamic_indicator_ioc_set(argp);
+		else
+			ret = -EBADF;
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct file_operations papr_indices_ops = {
+	.unlocked_ioctl = papr_indices_dev_ioctl,
+};
+
+static struct miscdevice papr_indices_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-indices",
+	.fops = &papr_indices_ops,
+};
+
+static __init int papr_indices_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_INDICES))
+		return -ENODEV;
+
+	if (!rtas_function_implemented(RTAS_FN_IBM_SET_DYNAMIC_INDICATOR))
+		return -ENODEV;
+
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_DYNAMIC_SENSOR_STATE))
+		return -ENODEV;
+
+	return misc_register(&papr_indices_dev);
+}
+machine_device_initcall(pseries, papr_indices_init);
diff --git a/arch/powerpc/platforms/pseries/papr-phy-attest.c b/arch/powerpc/platforms/pseries/papr-phy-attest.c
new file mode 100644
index 000000000000..1907f2411567
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-phy-attest.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-phy-attest: " fmt
+
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-physical-attestation.h>
+#include "papr-rtas-common.h"
+
+/**
+ * struct rtas_phy_attest_params - Parameters (in and out) for
+ * ibm,physical-attestation.
+ *
+ * @cmd:  In: Caller-provided attestation command buffer. Must be
+ *        RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for attestation
+ *             command structure
+ *             Out: Caller-provided work area buffer for the response
+ * @cmd_len:   In: Caller-provided attestation command structure
+ *             length
+ * @sequence:  In: Sequence number. Out: Next sequence number.
+ * @written:   Out: Bytes written by ibm,physical-attestation to
+ *             @work_area.
+ * @status:    Out: RTAS call status.
+ */
+struct rtas_phy_attest_params {
+	struct papr_phy_attest_io_block cmd;
+	struct rtas_work_area *work_area;
+	u32 cmd_len;
+	u32 sequence;
+	u32 written;
+	s32 status;
+};
+
+/**
+ * rtas_physical_attestation() - Call ibm,physical-attestation to
+ * fill a work area buffer.
+ * @params: See &struct rtas_phy_attest_params.
+ *
+ * Calls ibm,physical-attestation until it errors or successfully
+ * deposits data into the supplied work area. Handles RTAS retry
+ * statuses. Maps RTAS error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_physical_attestation()
+ * multiple times to retrieve all the data for the provided
+ * attestation command. Only one sequence should be in progress at
+ * any time; starting a new sequence will disrupt any sequence
+ * already in progress. Serialization of attestation retrieval
+ * sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_physical_attestation(struct rtas_phy_attest_params *params)
+{
+	struct rtas_work_area *work_area;
+	s32 fwrc, token;
+	u32 rets[2];
+	int ret;
+
+	work_area = params->work_area;
+	token = rtas_function_token(RTAS_FN_IBM_PHYSICAL_ATTESTATION);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	lockdep_assert_held(&rtas_ibm_physical_attestation_lock);
+
+	do {
+		fwrc = rtas_call(token, 3, 3, rets,
+				 rtas_work_area_phys(work_area),
+				 params->cmd_len,
+				 params->sequence);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		params->sequence = rets[0];
+		fallthrough;
+	case RTAS_SEQ_COMPLETE:
+		params->written = rets[1];
+		/*
+		 * Kernel or firmware bug, do not continue.
+		 */
+		if (WARN(params->written > rtas_work_area_size(work_area),
+			 "possible write beyond end of work area"))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-phy_attest status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal physical-attestation sequence APIs. A physical-attestation
+ * sequence is a series of calls to get ibm,physical-attestation
+ * for a given attestation command. The sequence ends when an error
+ * is encountered or all data for the attestation command has been
+ * returned.
+ */
+
+/**
+ * phy_attest_sequence_begin() - Begin a response data for attestation
+ * command retrieval sequence.
+ * @seq: user specified parameters for RTAS call from seq struct.
+ *
+ * Context: May sleep.
+ */
+static void phy_attest_sequence_begin(struct papr_rtas_sequence *seq)
+{
+	struct rtas_phy_attest_params *param;
+
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_physical_attestation_lock);
+	param =  (struct rtas_phy_attest_params *)seq->params;
+	param->work_area = rtas_work_area_alloc(SZ_4K);
+	memcpy(rtas_work_area_raw_buf(param->work_area), &param->cmd,
+			param->cmd_len);
+	param->sequence = 1;
+	param->status = 0;
+}
+
+/**
+ * phy_attest_sequence_end() - Finalize a attestation command
+ * response retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by phy_attest_sequence_begin().
+ */
+static void phy_attest_sequence_end(struct papr_rtas_sequence *seq)
+{
+	struct rtas_phy_attest_params *param;
+
+	param =  (struct rtas_phy_attest_params *)seq->params;
+	rtas_work_area_free(param->work_area);
+	mutex_unlock(&rtas_ibm_physical_attestation_lock);
+	kfree(param);
+}
+
+/*
+ * Generator function to be passed to papr_rtas_blob_generate().
+ */
+static const char *phy_attest_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
+{
+	struct rtas_phy_attest_params *p;
+	bool init_state;
+
+	p = (struct rtas_phy_attest_params *)seq->params;
+	init_state = (p->written == 0) ? true : false;
+
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
+		return NULL;
+	if (papr_rtas_sequence_set_err(seq, rtas_physical_attestation(p)))
+		return NULL;
+	*len = p->written;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+static const struct file_operations papr_phy_attest_handle_ops = {
+	.read = papr_rtas_common_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
+};
+
+/**
+ * papr_phy_attest_create_handle() - Create a fd-based handle for
+ * reading the response for the given attestation command.
+ * @ulc: Attestation command in user memory; defines the scope of
+ *       data for the attestation command to retrieve.
+ *
+ * Handler for PAPR_PHYSICAL_ATTESTATION_IOC_CREATE_HANDLE ioctl
+ * command. Validates @ulc and instantiates an immutable response
+ * "blob" for attestation command. The blob is attached to a file
+ * descriptor for reading by user space. The memory backing the blob
+ * is freed when the file is released.
+ *
+ * The entire requested response buffer for the attestation command
+ * retrieved by this call and all necessary RTAS interactions are
+ * performed before returning the fd to user space. This keeps the
+ * read handler simple and ensures that kernel can prevent
+ * interleaving ibm,physical-attestation call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_phy_attest_create_handle(struct papr_phy_attest_io_block __user *ulc)
+{
+	struct rtas_phy_attest_params *params;
+	struct papr_rtas_sequence seq = {};
+	int fd;
+
+	/*
+	 * Freed in phy_attest_sequence_end().
+	 */
+	params =  kzalloc(sizeof(*params), GFP_KERNEL_ACCOUNT);
+	if (!params)
+		return -ENOMEM;
+
+	if (copy_from_user(&params->cmd, ulc,
+			sizeof(struct papr_phy_attest_io_block)))
+		return -EFAULT;
+
+	params->cmd_len = be32_to_cpu(params->cmd.length);
+	seq = (struct papr_rtas_sequence) {
+		.begin = phy_attest_sequence_begin,
+		.end = phy_attest_sequence_end,
+		.work = phy_attest_sequence_fill_work_area,
+	};
+
+	seq.params = (void *)params;
+
+	fd = papr_rtas_setup_file_interface(&seq,
+			&papr_phy_attest_handle_ops,
+			"[papr-physical-attestation]");
+
+	return fd;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-physical-attestation.
+ */
+static long papr_phy_attest_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_PHY_ATTEST_IOC_HANDLE:
+		ret = papr_phy_attest_create_handle(argp);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_phy_attest_ops = {
+	.unlocked_ioctl = papr_phy_attest_dev_ioctl,
+};
+
+static struct miscdevice papr_phy_attest_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-physical-attestation",
+	.fops = &papr_phy_attest_ops,
+};
+
+static __init int papr_phy_attest_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_PHYSICAL_ATTESTATION))
+		return -ENODEV;
+
+	return misc_register(&papr_phy_attest_dev);
+}
+machine_device_initcall(pseries, papr_phy_attest_init);
diff --git a/arch/powerpc/platforms/pseries/papr-platform-dump.c b/arch/powerpc/platforms/pseries/papr-platform-dump.c
new file mode 100644
index 000000000000..f8d55eccdb6b
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-platform-dump.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-platform-dump: " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-platform-dump.h>
+
+/*
+ * Function-specific return values for ibm,platform-dump, derived from
+ * PAPR+ v2.13 7.3.3.4.1 "ibm,platform-dump RTAS Call".
+ */
+#define	RTAS_IBM_PLATFORM_DUMP_COMPLETE	0	/* Complete dump retrieved. */
+#define	RTAS_IBM_PLATFORM_DUMP_CONTINUE	1	/* Continue dump */
+#define	RTAS_NOT_AUTHORIZED		-9002	/* Not Authorized */
+
+#define	RTAS_IBM_PLATFORM_DUMP_START	2 /* Linux status to start dump */
+
+/**
+ * struct ibm_platform_dump_params - Parameters (in and out) for
+ *                                              ibm,platform-dump
+ * @work_area:		In: work area buffer for results.
+ * @buf_length:		In: work area buffer length in bytes
+ * @dump_tag_hi:	In: Most-significant 32 bits of a Dump_Tag representing
+ *                      an id of the dump being processed.
+ * @dump_tag_lo:	In: Least-significant 32 bits of a Dump_Tag representing
+ *                      an id of the dump being processed.
+ * @sequence_hi:	In: Sequence number in most-significant 32 bits.
+ *                      Out: Next sequence number in most-significant 32 bits.
+ * @sequence_lo:	In: Sequence number in Least-significant 32 bits
+ *                      Out: Next sequence number in Least-significant 32 bits.
+ * @bytes_ret_hi:	Out: Bytes written in most-significant 32 bits.
+ * @bytes_ret_lo:	Out: Bytes written in Least-significant 32 bits.
+ * @status:		Out: RTAS call status.
+ * @list:		Maintain the list of dumps are in progress. Can
+ *                      retrieve multiple dumps with different dump IDs at
+ *                      the same time but not with the same dump ID. This list
+ *                      is used to determine whether the dump for the same ID
+ *                      is in progress.
+ */
+struct ibm_platform_dump_params {
+	struct rtas_work_area	*work_area;
+	u32			buf_length;
+	u32			dump_tag_hi;
+	u32			dump_tag_lo;
+	u32			sequence_hi;
+	u32			sequence_lo;
+	u32			bytes_ret_hi;
+	u32			bytes_ret_lo;
+	s32			status;
+	struct list_head	list;
+};
+
+/*
+ * Multiple dumps with different dump IDs can be retrieved at the same
+ * time, but not with dame dump ID. platform_dump_list_mutex and
+ * platform_dump_list are used to prevent this behavior.
+ */
+static DEFINE_MUTEX(platform_dump_list_mutex);
+static LIST_HEAD(platform_dump_list);
+
+/**
+ * rtas_ibm_platform_dump() - Call ibm,platform-dump to fill a work area
+ * buffer.
+ * @params: See &struct ibm_platform_dump_params.
+ * @buf_addr: Address of dump buffer (work_area)
+ * @buf_length: Length of the buffer in bytes (min. 1024)
+ *
+ * Calls ibm,platform-dump until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * Can request multiple dumps with different dump IDs at the same time,
+ * but not with the same dump ID which is prevented with the check in
+ * the ioctl code (papr_platform_dump_create_handle()).
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 for dump complete and 1 for continue dump
+ */
+static int rtas_ibm_platform_dump(struct ibm_platform_dump_params *params,
+				phys_addr_t buf_addr, u32 buf_length)
+{
+	u32 rets[4];
+	s32 fwrc;
+	int ret = 0;
+
+	do {
+		fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP),
+				6, 5,
+				rets,
+				params->dump_tag_hi,
+				params->dump_tag_lo,
+				params->sequence_hi,
+				params->sequence_lo,
+				buf_addr,
+				buf_length);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_NOT_AUTHORIZED:
+		ret = -EPERM;
+		break;
+	case RTAS_IBM_PLATFORM_DUMP_CONTINUE:
+	case RTAS_IBM_PLATFORM_DUMP_COMPLETE:
+		params->sequence_hi = rets[0];
+		params->sequence_lo = rets[1];
+		params->bytes_ret_hi = rets[2];
+		params->bytes_ret_lo = rets[3];
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,platform-dump status %d\n",
+				fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Platform dump is used with multiple RTAS calls to retrieve the
+ * complete dump for the provided dump ID. Once the complete dump is
+ * retrieved, the hypervisor returns dump complete status (0) for the
+ * last RTAS call and expects the caller issues one more call with
+ * NULL buffer to invalidate the dump so that the hypervisor can remove
+ * the dump.
+ *
+ * After the specific dump is invalidated in the hypervisor, expect the
+ * dump complete status for the new sequence - the user space initiates
+ * new request for the same dump ID.
+ */
+static ssize_t papr_platform_dump_handle_read(struct file *file,
+		char __user *buf, size_t size, loff_t *off)
+{
+	struct ibm_platform_dump_params *params = file->private_data;
+	u64 total_bytes;
+	s32 fwrc;
+
+	/*
+	 * Dump already completed with the previous read calls.
+	 * In case if the user space issues further reads, returns
+	 * -EINVAL.
+	 */
+	if (!params->buf_length) {
+		pr_warn_once("Platform dump completed for dump ID %llu\n",
+			(u64) (((u64)params->dump_tag_hi << 32) |
+				params->dump_tag_lo));
+		return -EINVAL;
+	}
+
+	/*
+	 * The hypervisor returns status 0 if no more data available to
+	 * download. The dump will be invalidated with ioctl (see below).
+	 */
+	if (params->status == RTAS_IBM_PLATFORM_DUMP_COMPLETE) {
+		params->buf_length = 0;
+		/*
+		 * Returns 0 to the user space so that user
+		 * space read stops.
+		 */
+		return 0;
+	}
+
+	if (size < SZ_1K) {
+		pr_err_once("Buffer length should be minimum 1024 bytes\n");
+		return -EINVAL;
+	} else if (size > params->buf_length) {
+		/*
+		 * Allocate 4K work area. So if the user requests > 4K,
+		 * resize the buffer length.
+		 */
+		size = params->buf_length;
+	}
+
+	fwrc = rtas_ibm_platform_dump(params,
+			rtas_work_area_phys(params->work_area),
+			size);
+	if (fwrc < 0)
+		return fwrc;
+
+	total_bytes = (u64) (((u64)params->bytes_ret_hi << 32) |
+			params->bytes_ret_lo);
+
+	/*
+	 * Kernel or firmware bug, do not continue.
+	 */
+	if (WARN(total_bytes > size, "possible write beyond end of work area"))
+		return -EFAULT;
+
+	if (copy_to_user(buf, rtas_work_area_raw_buf(params->work_area),
+			total_bytes))
+		return -EFAULT;
+
+	return total_bytes;
+}
+
+static int papr_platform_dump_handle_release(struct inode *inode,
+					struct file *file)
+{
+	struct ibm_platform_dump_params *params = file->private_data;
+
+	if (params->work_area)
+		rtas_work_area_free(params->work_area);
+
+	mutex_lock(&platform_dump_list_mutex);
+	list_del(&params->list);
+	mutex_unlock(&platform_dump_list_mutex);
+
+	kfree(params);
+	file->private_data = NULL;
+	return 0;
+}
+
+/*
+ * This ioctl is used to invalidate the dump assuming the user space
+ * issue this ioctl after obtain the complete dump.
+ * Issue the last RTAS call with NULL buffer to invalidate the dump
+ * which means dump will be freed in the hypervisor.
+ */
+static long papr_platform_dump_invalidate_ioctl(struct file *file,
+				unsigned int ioctl, unsigned long arg)
+{
+	struct ibm_platform_dump_params *params;
+	u64 __user *argp = (void __user *)arg;
+	u64 param_dump_tag, dump_tag;
+
+	if (ioctl != PAPR_PLATFORM_DUMP_IOC_INVALIDATE)
+		return -ENOIOCTLCMD;
+
+	if (get_user(dump_tag, argp))
+		return -EFAULT;
+
+	/*
+	 * private_data is freeded during release(), so should not
+	 * happen.
+	 */
+	if (!file->private_data) {
+		pr_err("No valid FD to invalidate dump for the ID(%llu)\n",
+				dump_tag);
+		return -EINVAL;
+	}
+
+	params = file->private_data;
+	param_dump_tag = (u64) (((u64)params->dump_tag_hi << 32) |
+				params->dump_tag_lo);
+	if (dump_tag != param_dump_tag) {
+		pr_err("Invalid dump ID(%llu) to invalidate dump\n",
+				dump_tag);
+		return -EINVAL;
+	}
+
+	if (params->status != RTAS_IBM_PLATFORM_DUMP_COMPLETE) {
+		pr_err("Platform dump is not complete, but requested "
+			"to invalidate dump for ID(%llu)\n",
+			dump_tag);
+		return -EINPROGRESS;
+	}
+
+	return rtas_ibm_platform_dump(params, 0, 0);
+}
+
+static const struct file_operations papr_platform_dump_handle_ops = {
+	.read = papr_platform_dump_handle_read,
+	.release = papr_platform_dump_handle_release,
+	.unlocked_ioctl	= papr_platform_dump_invalidate_ioctl,
+};
+
+/**
+ * papr_platform_dump_create_handle() - Create a fd-based handle for
+ * reading platform dump
+ *
+ * Handler for PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE ioctl command
+ * Allocates RTAS parameter struct and work area and attached to the
+ * file descriptor for reading by user space with the multiple RTAS
+ * calls until the dump is completed. This memory allocation is freed
+ * when the file is released.
+ *
+ * Multiple dump requests with different IDs are allowed at the same
+ * time, but not with the same dump ID. So if the user space is
+ * already opened file descriptor for the specific dump ID, return
+ * -EALREADY for the next request.
+ *
+ * @dump_tag: Dump ID for the dump requested to retrieve from the
+ *		hypervisor
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_platform_dump_create_handle(u64 dump_tag)
+{
+	struct ibm_platform_dump_params *params;
+	u64 param_dump_tag;
+	struct file *file;
+	long err;
+	int fd;
+
+	/*
+	 * Return failure if the user space is already opened FD for
+	 * the specific dump ID. This check will prevent multiple dump
+	 * requests for the same dump ID at the same time. Generally
+	 * should not expect this, but in case.
+	 */
+	list_for_each_entry(params, &platform_dump_list, list) {
+		param_dump_tag = (u64) (((u64)params->dump_tag_hi << 32) |
+					params->dump_tag_lo);
+		if (dump_tag == param_dump_tag) {
+			pr_err("Platform dump for ID(%llu) is already in progress\n",
+					dump_tag);
+			return -EALREADY;
+		}
+	}
+
+	params =  kzalloc(sizeof(struct ibm_platform_dump_params),
+			GFP_KERNEL_ACCOUNT);
+	if (!params)
+		return -ENOMEM;
+
+	params->work_area = rtas_work_area_alloc(SZ_4K);
+	params->buf_length = SZ_4K;
+	params->dump_tag_hi = (u32)(dump_tag >> 32);
+	params->dump_tag_lo = (u32)(dump_tag & 0x00000000ffffffffULL);
+	params->status = RTAS_IBM_PLATFORM_DUMP_START;
+
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		err = fd;
+		goto free_area;
+	}
+
+	file = anon_inode_getfile_fmode("[papr-platform-dump]",
+				&papr_platform_dump_handle_ops,
+				(void *)params, O_RDONLY,
+				FMODE_LSEEK | FMODE_PREAD);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto put_fd;
+	}
+
+	fd_install(fd, file);
+
+	list_add(&params->list, &platform_dump_list);
+
+	pr_info("%s (%d) initiated platform dump for dump tag %llu\n",
+		current->comm, current->pid, dump_tag);
+	return fd;
+put_fd:
+	put_unused_fd(fd);
+free_area:
+	rtas_work_area_free(params->work_area);
+	kfree(params);
+	return err;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-platform-dump.
+ */
+static long papr_platform_dump_dev_ioctl(struct file *filp,
+					unsigned int ioctl,
+					unsigned long arg)
+{
+	u64 __user *argp = (void __user *)arg;
+	u64 dump_tag;
+	long ret;
+
+	if (get_user(dump_tag, argp))
+		return -EFAULT;
+
+	switch (ioctl) {
+	case PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE:
+		mutex_lock(&platform_dump_list_mutex);
+		ret = papr_platform_dump_create_handle(dump_tag);
+		mutex_unlock(&platform_dump_list_mutex);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_platform_dump_ops = {
+	.unlocked_ioctl = papr_platform_dump_dev_ioctl,
+};
+
+static struct miscdevice papr_platform_dump_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-platform-dump",
+	.fops = &papr_platform_dump_ops,
+};
+
+static __init int papr_platform_dump_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_PLATFORM_DUMP))
+		return -ENODEV;
+
+	return misc_register(&papr_platform_dump_dev);
+}
+machine_device_initcall(pseries, papr_platform_dump_init);
diff --git a/arch/powerpc/platforms/pseries/papr-rtas-common.c b/arch/powerpc/platforms/pseries/papr-rtas-common.c
new file mode 100644
index 000000000000..33c606e3378a
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-rtas-common.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-common: " fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/signal.h>
+#include "papr-rtas-common.h"
+
+/*
+ * Sequence based RTAS HCALL has to issue multiple times to retrieve
+ * complete data from the hypervisor. For some of these RTAS calls,
+ * the OS should not interleave calls with different input until the
+ * sequence is completed. So data is collected for these calls during
+ * ioctl handle and export to user space with read() handle.
+ * This file provides common functions needed for such sequence based
+ * RTAS calls Ex: ibm,get-vpd and ibm,get-indices.
+ */
+
+bool papr_rtas_blob_has_data(const struct papr_rtas_blob *blob)
+{
+	return blob->data && blob->len;
+}
+
+void papr_rtas_blob_free(const struct papr_rtas_blob *blob)
+{
+	if (blob) {
+		kvfree(blob->data);
+		kfree(blob);
+	}
+}
+
+/**
+ * papr_rtas_blob_extend() - Append data to a &struct papr_rtas_blob.
+ * @blob: The blob to extend.
+ * @data: The new data to append to @blob.
+ * @len:  The length of @data.
+ *
+ * Context: May sleep.
+ * Return: -ENOMEM on allocation failure, 0 otherwise.
+ */
+static int papr_rtas_blob_extend(struct papr_rtas_blob *blob,
+				const char *data, size_t len)
+{
+	const size_t new_len = blob->len + len;
+	const size_t old_len = blob->len;
+	const char *old_ptr = blob->data;
+	char *new_ptr;
+
+	new_ptr = kvrealloc(old_ptr, new_len, GFP_KERNEL_ACCOUNT);
+	if (!new_ptr)
+		return -ENOMEM;
+
+	memcpy(&new_ptr[old_len], data, len);
+	blob->data = new_ptr;
+	blob->len = new_len;
+	return 0;
+}
+
+/**
+ * papr_rtas_blob_generate() - Construct a new &struct papr_rtas_blob.
+ * @seq: work function of the caller that is called to obtain
+ *       data with the caller RTAS call.
+ *
+ * The @work callback is invoked until it returns NULL. @seq is
+ * passed to @work in its first argument on each call. When
+ * @work returns data, it should store the data length in its
+ * second argument.
+ *
+ * Context: May sleep.
+ * Return: A completely populated &struct papr_rtas_blob, or NULL on error.
+ */
+static const struct papr_rtas_blob *
+papr_rtas_blob_generate(struct papr_rtas_sequence *seq)
+{
+	struct papr_rtas_blob *blob;
+	const char *buf;
+	size_t len;
+	int err = 0;
+
+	blob  = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
+	if (!blob)
+		return NULL;
+
+	if (!seq->work)
+		return ERR_PTR(-EINVAL);
+
+
+	while (err == 0 && (buf = seq->work(seq, &len)))
+		err = papr_rtas_blob_extend(blob, buf, len);
+
+	if (err != 0 || !papr_rtas_blob_has_data(blob))
+		goto free_blob;
+
+	return blob;
+free_blob:
+	papr_rtas_blob_free(blob);
+	return NULL;
+}
+
+int papr_rtas_sequence_set_err(struct papr_rtas_sequence *seq, int err)
+{
+	/* Preserve the first error recorded. */
+	if (seq->error == 0)
+		seq->error = err;
+
+	return seq->error;
+}
+
+/*
+ * Higher-level retrieval code below. These functions use the
+ * papr_rtas_blob_* and sequence_* APIs defined above to create fd-based
+ * handles for consumption by user space.
+ */
+
+/**
+ * papr_rtas_run_sequence() - Run a single retrieval sequence.
+ * @seq:	Functions of the caller to complete the sequence
+ *
+ * Context: May sleep. Holds a mutex and an RTAS work area for its
+ *          duration. Typically performs multiple sleepable slab
+ *          allocations.
+ *
+ * Return: A populated &struct papr_rtas_blob on success. Encoded error
+ * pointer otherwise.
+ */
+static const struct papr_rtas_blob *papr_rtas_run_sequence(struct papr_rtas_sequence *seq)
+{
+	const struct papr_rtas_blob *blob;
+
+	if (seq->begin)
+		seq->begin(seq);
+
+	blob = papr_rtas_blob_generate(seq);
+	if (!blob)
+		papr_rtas_sequence_set_err(seq, -ENOMEM);
+
+	if (seq->end)
+		seq->end(seq);
+
+
+	if (seq->error) {
+		papr_rtas_blob_free(blob);
+		return ERR_PTR(seq->error);
+	}
+
+	return blob;
+}
+
+/**
+ * papr_rtas_retrieve() - Return the data blob that is exposed to
+ * user space.
+ * @seq: RTAS call specific functions to be invoked until the
+ *       sequence is completed.
+ *
+ * Run sequences against @param until a blob is successfully
+ * instantiated, or a hard error is encountered, or a fatal signal is
+ * pending.
+ *
+ * Context: May sleep.
+ * Return: A fully populated data blob when successful. Encoded error
+ * pointer otherwise.
+ */
+const struct papr_rtas_blob *papr_rtas_retrieve(struct papr_rtas_sequence *seq)
+{
+	const struct papr_rtas_blob *blob;
+
+	/*
+	 * EAGAIN means the sequence returns error with a -4 (data
+	 * changed and need to start the sequence) status from RTAS calls
+	 * and we should attempt a new sequence. PAPR+ (v2.13 R1–7.3.20–5
+	 * - ibm,get-vpd, R1–7.3.17–6 - ibm,get-indices) indicates that
+	 * this should be a transient condition, not something that
+	 * happens continuously. But we'll stop trying on a fatal signal.
+	 */
+	do {
+		blob = papr_rtas_run_sequence(seq);
+		if (!IS_ERR(blob)) /* Success. */
+			break;
+		if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
+			break;
+		cond_resched();
+	} while (!fatal_signal_pending(current));
+
+	return blob;
+}
+
+/**
+ * papr_rtas_setup_file_interface - Complete the sequence and obtain
+ * the data and export to user space with fd-based handles. Then the
+ * user spave gets the data with read() handle.
+ * @seq: RTAS call specific functions to get the data.
+ * @fops: RTAS call specific file operations such as read().
+ * @name: RTAS call specific char device node.
+ *
+ * Return: FD handle for consumption by user space
+ */
+long papr_rtas_setup_file_interface(struct papr_rtas_sequence *seq,
+				const struct file_operations *fops,
+				char *name)
+{
+	const struct papr_rtas_blob *blob;
+	struct file *file;
+	long ret;
+	int fd;
+
+	blob = papr_rtas_retrieve(seq);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		ret = fd;
+		goto free_blob;
+	}
+
+	file = anon_inode_getfile_fmode(name, fops, (void *)blob,
+			O_RDONLY, FMODE_LSEEK | FMODE_PREAD);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto put_fd;
+	}
+
+	fd_install(fd, file);
+	return fd;
+
+put_fd:
+	put_unused_fd(fd);
+free_blob:
+	papr_rtas_blob_free(blob);
+	return ret;
+}
+
+/*
+ * papr_rtas_sequence_should_stop() - Determine whether RTAS retrieval
+ *                                    sequence should continue.
+ *
+ * Examines the sequence error state and outputs of the last call to
+ * the specific RTAS to determine whether the sequence in progress
+ * should continue or stop.
+ *
+ * Return: True if the sequence has encountered an error or if all data
+ *         for this sequence has been retrieved. False otherwise.
+ */
+bool papr_rtas_sequence_should_stop(const struct papr_rtas_sequence *seq,
+				s32 status, bool init_state)
+{
+	bool done;
+
+	if (seq->error)
+		return true;
+
+	switch (status) {
+	case RTAS_SEQ_COMPLETE:
+		if (init_state)
+			done = false; /* Initial state. */
+		else
+			done = true; /* All data consumed. */
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		done = false; /* More data available. */
+		break;
+	default:
+		done = true; /* Error encountered. */
+		break;
+	}
+
+	return done;
+}
+
+/*
+ * User space read to retrieve data for the corresponding RTAS call.
+ * papr_rtas_blob is filled with the data using the corresponding RTAS
+ * call sequence API.
+ */
+ssize_t papr_rtas_common_handle_read(struct file *file,
+	       char __user *buf, size_t size, loff_t *off)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	/* We should not instantiate a handle without any data attached. */
+	if (!papr_rtas_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+int papr_rtas_common_handle_release(struct inode *inode,
+		struct file *file)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	papr_rtas_blob_free(blob);
+
+	return 0;
+}
+
+loff_t papr_rtas_common_handle_seek(struct file *file, loff_t off,
+					int whence)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	return fixed_size_llseek(file, off, whence, blob->len);
+}
diff --git a/arch/powerpc/platforms/pseries/papr-rtas-common.h b/arch/powerpc/platforms/pseries/papr-rtas-common.h
new file mode 100644
index 000000000000..4ceabcaf4905
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-rtas-common.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_POWERPC_PAPR_RTAS_COMMON_H
+#define _ASM_POWERPC_PAPR_RTAS_COMMON_H
+
+#include <linux/types.h>
+
+/*
+ * Return codes for sequence based RTAS calls.
+ * Not listed under PAPR+ v2.13 7.2.8: "Return Codes".
+ * But defined in the specific section of each RTAS call.
+ */
+#define RTAS_SEQ_COMPLETE	0 /* All data has been retrieved. */
+#define RTAS_SEQ_MORE_DATA	1 /* More data is available */
+#define RTAS_SEQ_START_OVER	-4 /* Data changed, restart call sequence. */
+
+/*
+ * Internal "blob" APIs for accumulating RTAS call results into
+ * an immutable buffer to be attached to a file descriptor.
+ */
+struct papr_rtas_blob {
+	const char *data;
+	size_t len;
+};
+
+/**
+ * struct papr_sequence - State for managing a sequence of RTAS calls.
+ * @error:  Shall be zero as long as the sequence has not encountered an error,
+ *          -ve errno otherwise. Use papr_rtas_sequence_set_err() to update.
+ * @params: Parameter block to pass to rtas_*() calls.
+ * @begin: Work area allocation and initialize the needed parameter
+ *         values passed to RTAS call
+ * @end: Free the allocated work area
+ * @work: Obtain data with RTAS call and invoke it until the sequence is
+ *        completed.
+ *
+ */
+struct papr_rtas_sequence {
+	int error;
+	void *params;
+	void (*begin)(struct papr_rtas_sequence *seq);
+	void (*end)(struct papr_rtas_sequence *seq);
+	const char *(*work)(struct papr_rtas_sequence *seq, size_t *len);
+};
+
+extern bool papr_rtas_blob_has_data(const struct papr_rtas_blob *blob);
+extern void papr_rtas_blob_free(const struct papr_rtas_blob *blob);
+extern int papr_rtas_sequence_set_err(struct papr_rtas_sequence *seq,
+		int err);
+extern const struct papr_rtas_blob *papr_rtas_retrieve(struct papr_rtas_sequence *seq);
+extern long papr_rtas_setup_file_interface(struct papr_rtas_sequence *seq,
+			const struct file_operations *fops, char *name);
+extern bool papr_rtas_sequence_should_stop(const struct papr_rtas_sequence *seq,
+				s32 status, bool init_state);
+extern ssize_t papr_rtas_common_handle_read(struct file *file,
+			char __user *buf, size_t size, loff_t *off);
+extern int papr_rtas_common_handle_release(struct inode *inode,
+					struct file *file);
+extern loff_t papr_rtas_common_handle_seek(struct file *file, loff_t off,
+					int whence);
+#endif /* _ASM_POWERPC_PAPR_RTAS_COMMON_H */
+
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
index 1574176e3ffc..f38c188fc4a1 100644
--- a/arch/powerpc/platforms/pseries/papr-vpd.c
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -2,7 +2,6 @@
 
 #define pr_fmt(fmt) "papr-vpd: " fmt
 
-#include <linux/anon_inodes.h>
 #include <linux/build_bug.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -20,14 +19,7 @@
 #include <asm/rtas-work-area.h>
 #include <asm/rtas.h>
 #include <uapi/asm/papr-vpd.h>
-
-/*
- * Function-specific return values for ibm,get-vpd, derived from PAPR+
- * v2.13 7.3.20 "ibm,get-vpd RTAS Call".
- */
-#define RTAS_IBM_GET_VPD_COMPLETE    0 /* All VPD has been retrieved. */
-#define RTAS_IBM_GET_VPD_MORE_DATA   1 /* More VPD is available. */
-#define RTAS_IBM_GET_VPD_START_OVER -4 /* VPD changed, restart call sequence. */
+#include "papr-rtas-common.h"
 
 /**
  * struct rtas_ibm_get_vpd_params - Parameters (in and out) for ibm,get-vpd.
@@ -91,13 +83,14 @@ static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
 	case RTAS_INVALID_PARAMETER:
 		ret = -EINVAL;
 		break;
-	case RTAS_IBM_GET_VPD_START_OVER:
+	case RTAS_SEQ_START_OVER:
 		ret = -EAGAIN;
+		pr_info_ratelimited("VPD changed during retrieval, retrying\n");
 		break;
-	case RTAS_IBM_GET_VPD_MORE_DATA:
+	case RTAS_SEQ_MORE_DATA:
 		params->sequence = rets[0];
 		fallthrough;
-	case RTAS_IBM_GET_VPD_COMPLETE:
+	case RTAS_SEQ_COMPLETE:
 		params->written = rets[1];
 		/*
 		 * Kernel or firmware bug, do not continue.
@@ -119,91 +112,6 @@ static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
 }
 
 /*
- * Internal VPD "blob" APIs for accumulating ibm,get-vpd results into
- * an immutable buffer to be attached to a file descriptor.
- */
-struct vpd_blob {
-	const char *data;
-	size_t len;
-};
-
-static bool vpd_blob_has_data(const struct vpd_blob *blob)
-{
-	return blob->data && blob->len;
-}
-
-static void vpd_blob_free(const struct vpd_blob *blob)
-{
-	if (blob) {
-		kvfree(blob->data);
-		kfree(blob);
-	}
-}
-
-/**
- * vpd_blob_extend() - Append data to a &struct vpd_blob.
- * @blob: The blob to extend.
- * @data: The new data to append to @blob.
- * @len:  The length of @data.
- *
- * Context: May sleep.
- * Return: -ENOMEM on allocation failure, 0 otherwise.
- */
-static int vpd_blob_extend(struct vpd_blob *blob, const char *data, size_t len)
-{
-	const size_t new_len = blob->len + len;
-	const size_t old_len = blob->len;
-	const char *old_ptr = blob->data;
-	char *new_ptr;
-
-	new_ptr = kvrealloc(old_ptr, new_len, GFP_KERNEL_ACCOUNT);
-	if (!new_ptr)
-		return -ENOMEM;
-
-	memcpy(&new_ptr[old_len], data, len);
-	blob->data = new_ptr;
-	blob->len = new_len;
-	return 0;
-}
-
-/**
- * vpd_blob_generate() - Construct a new &struct vpd_blob.
- * @generator: Function that supplies the blob data.
- * @arg:       Context pointer supplied by caller, passed to @generator.
- *
- * The @generator callback is invoked until it returns NULL. @arg is
- * passed to @generator in its first argument on each call. When
- * @generator returns data, it should store the data length in its
- * second argument.
- *
- * Context: May sleep.
- * Return: A completely populated &struct vpd_blob, or NULL on error.
- */
-static const struct vpd_blob *
-vpd_blob_generate(const char * (*generator)(void *, size_t *), void *arg)
-{
-	struct vpd_blob *blob;
-	const char *buf;
-	size_t len;
-	int err = 0;
-
-	blob  = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
-	if (!blob)
-		return NULL;
-
-	while (err == 0 && (buf = generator(arg, &len)))
-		err = vpd_blob_extend(blob, buf, len);
-
-	if (err != 0 || !vpd_blob_has_data(blob))
-		goto free_blob;
-
-	return blob;
-free_blob:
-	vpd_blob_free(blob);
-	return NULL;
-}
-
-/*
  * Internal VPD sequence APIs. A VPD sequence is a series of calls to
  * ibm,get-vpd for a given location code. The sequence ends when an
  * error is encountered or all VPD for the location code has been
@@ -211,30 +119,14 @@ free_blob:
  */
 
 /**
- * struct vpd_sequence - State for managing a VPD sequence.
- * @error:  Shall be zero as long as the sequence has not encountered an error,
- *          -ve errno otherwise. Use vpd_sequence_set_err() to update this.
- * @params: Parameter block to pass to rtas_ibm_get_vpd().
- */
-struct vpd_sequence {
-	int error;
-	struct rtas_ibm_get_vpd_params params;
-};
-
-/**
  * vpd_sequence_begin() - Begin a VPD retrieval sequence.
- * @seq:      Uninitialized sequence state.
- * @loc_code: Location code that defines the scope of the VPD to return.
- *
- * Initializes @seq with the resources necessary to carry out a VPD
- * sequence. Callers must pass @seq to vpd_sequence_end() regardless
- * of whether the sequence succeeds.
+ * @seq: vpd call parameters from sequence struct
  *
  * Context: May sleep.
  */
-static void vpd_sequence_begin(struct vpd_sequence *seq,
-			       const struct papr_location_code *loc_code)
+static void vpd_sequence_begin(struct papr_rtas_sequence *seq)
 {
+	struct rtas_ibm_get_vpd_params *vpd_params;
 	/*
 	 * Use a static data structure for the location code passed to
 	 * RTAS to ensure it's in the RMA and avoid a separate work
@@ -242,6 +134,7 @@ static void vpd_sequence_begin(struct vpd_sequence *seq,
 	 */
 	static struct papr_location_code static_loc_code;
 
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
 	/*
 	 * We could allocate the work area before acquiring the
 	 * function lock, but that would allow concurrent requests to
@@ -249,14 +142,12 @@ static void vpd_sequence_begin(struct vpd_sequence *seq,
 	 * allocate the work area under the lock.
 	 */
 	mutex_lock(&rtas_ibm_get_vpd_lock);
-	static_loc_code = *loc_code;
-	*seq = (struct vpd_sequence) {
-		.params = {
-			.work_area = rtas_work_area_alloc(SZ_4K),
-			.loc_code = &static_loc_code,
-			.sequence = 1,
-		},
-	};
+	static_loc_code = *(struct papr_location_code *)vpd_params->loc_code;
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
+	vpd_params->work_area = rtas_work_area_alloc(SZ_4K);
+	vpd_params->loc_code = &static_loc_code;
+	vpd_params->sequence = 1;
+	vpd_params->status = 0;
 }
 
 /**
@@ -265,180 +156,39 @@ static void vpd_sequence_begin(struct vpd_sequence *seq,
  *
  * Releases resources obtained by vpd_sequence_begin().
  */
-static void vpd_sequence_end(struct vpd_sequence *seq)
-{
-	rtas_work_area_free(seq->params.work_area);
-	mutex_unlock(&rtas_ibm_get_vpd_lock);
-}
-
-/**
- * vpd_sequence_should_stop() - Determine whether a VPD retrieval sequence
- *                              should continue.
- * @seq: VPD sequence state.
- *
- * Examines the sequence error state and outputs of the last call to
- * ibm,get-vpd to determine whether the sequence in progress should
- * continue or stop.
- *
- * Return: True if the sequence has encountered an error or if all VPD for
- *         this sequence has been retrieved. False otherwise.
- */
-static bool vpd_sequence_should_stop(const struct vpd_sequence *seq)
-{
-	bool done;
-
-	if (seq->error)
-		return true;
-
-	switch (seq->params.status) {
-	case 0:
-		if (seq->params.written == 0)
-			done = false; /* Initial state. */
-		else
-			done = true; /* All data consumed. */
-		break;
-	case 1:
-		done = false; /* More data available. */
-		break;
-	default:
-		done = true; /* Error encountered. */
-		break;
-	}
-
-	return done;
-}
-
-static int vpd_sequence_set_err(struct vpd_sequence *seq, int err)
+static void vpd_sequence_end(struct papr_rtas_sequence *seq)
 {
-	/* Preserve the first error recorded. */
-	if (seq->error == 0)
-		seq->error = err;
+	struct rtas_ibm_get_vpd_params *vpd_params;
 
-	return seq->error;
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
+	rtas_work_area_free(vpd_params->work_area);
+	mutex_unlock(&rtas_ibm_get_vpd_lock);
 }
 
 /*
- * Generator function to be passed to vpd_blob_generate().
+ * Generator function to be passed to papr_rtas_blob_generate().
  */
-static const char *vpd_sequence_fill_work_area(void *arg, size_t *len)
+static const char *vpd_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
 {
-	struct vpd_sequence *seq = arg;
-	struct rtas_ibm_get_vpd_params *p = &seq->params;
+	struct rtas_ibm_get_vpd_params *p;
+	bool init_state;
+
+	p = (struct rtas_ibm_get_vpd_params *)seq->params;
+	init_state = (p->written == 0) ? true : false;
 
-	if (vpd_sequence_should_stop(seq))
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
 		return NULL;
-	if (vpd_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
+	if (papr_rtas_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
 		return NULL;
 	*len = p->written;
 	return rtas_work_area_raw_buf(p->work_area);
 }
 
-/*
- * Higher-level VPD retrieval code below. These functions use the
- * vpd_blob_* and vpd_sequence_* APIs defined above to create fd-based
- * VPD handles for consumption by user space.
- */
-
-/**
- * papr_vpd_run_sequence() - Run a single VPD retrieval sequence.
- * @loc_code: Location code that defines the scope of VPD to return.
- *
- * Context: May sleep. Holds a mutex and an RTAS work area for its
- *          duration. Typically performs multiple sleepable slab
- *          allocations.
- *
- * Return: A populated &struct vpd_blob on success. Encoded error
- * pointer otherwise.
- */
-static const struct vpd_blob *papr_vpd_run_sequence(const struct papr_location_code *loc_code)
-{
-	const struct vpd_blob *blob;
-	struct vpd_sequence seq;
-
-	vpd_sequence_begin(&seq, loc_code);
-	blob = vpd_blob_generate(vpd_sequence_fill_work_area, &seq);
-	if (!blob)
-		vpd_sequence_set_err(&seq, -ENOMEM);
-	vpd_sequence_end(&seq);
-
-	if (seq.error) {
-		vpd_blob_free(blob);
-		return ERR_PTR(seq.error);
-	}
-
-	return blob;
-}
-
-/**
- * papr_vpd_retrieve() - Return the VPD for a location code.
- * @loc_code: Location code that defines the scope of VPD to return.
- *
- * Run VPD sequences against @loc_code until a blob is successfully
- * instantiated, or a hard error is encountered, or a fatal signal is
- * pending.
- *
- * Context: May sleep.
- * Return: A fully populated VPD blob when successful. Encoded error
- * pointer otherwise.
- */
-static const struct vpd_blob *papr_vpd_retrieve(const struct papr_location_code *loc_code)
-{
-	const struct vpd_blob *blob;
-
-	/*
-	 * EAGAIN means the sequence errored with a -4 (VPD changed)
-	 * status from ibm,get-vpd, and we should attempt a new
-	 * sequence. PAPR+ v2.13 R1–7.3.20–5 indicates that this
-	 * should be a transient condition, not something that happens
-	 * continuously. But we'll stop trying on a fatal signal.
-	 */
-	do {
-		blob = papr_vpd_run_sequence(loc_code);
-		if (!IS_ERR(blob)) /* Success. */
-			break;
-		if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
-			break;
-		pr_info_ratelimited("VPD changed during retrieval, retrying\n");
-		cond_resched();
-	} while (!fatal_signal_pending(current));
-
-	return blob;
-}
-
-static ssize_t papr_vpd_handle_read(struct file *file, char __user *buf, size_t size, loff_t *off)
-{
-	const struct vpd_blob *blob = file->private_data;
-
-	/* bug: we should not instantiate a handle without any data attached. */
-	if (!vpd_blob_has_data(blob)) {
-		pr_err_once("handle without data\n");
-		return -EIO;
-	}
-
-	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
-}
-
-static int papr_vpd_handle_release(struct inode *inode, struct file *file)
-{
-	const struct vpd_blob *blob = file->private_data;
-
-	vpd_blob_free(blob);
-
-	return 0;
-}
-
-static loff_t papr_vpd_handle_seek(struct file *file, loff_t off, int whence)
-{
-	const struct vpd_blob *blob = file->private_data;
-
-	return fixed_size_llseek(file, off, whence, blob->len);
-}
-
-
 static const struct file_operations papr_vpd_handle_ops = {
-	.read = papr_vpd_handle_read,
-	.llseek = papr_vpd_handle_seek,
-	.release = papr_vpd_handle_release,
+	.read = papr_rtas_common_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
 };
 
 /**
@@ -460,10 +210,9 @@ static const struct file_operations papr_vpd_handle_ops = {
  */
 static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
 {
+	struct rtas_ibm_get_vpd_params vpd_params = {};
+	struct papr_rtas_sequence seq = {};
 	struct papr_location_code klc;
-	const struct vpd_blob *blob;
-	struct file *file;
-	long err;
 	int fd;
 
 	if (copy_from_user(&klc, ulc, sizeof(klc)))
@@ -472,31 +221,19 @@ static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
 	if (!string_is_terminated(klc.str, ARRAY_SIZE(klc.str)))
 		return -EINVAL;
 
-	blob = papr_vpd_retrieve(&klc);
-	if (IS_ERR(blob))
-		return PTR_ERR(blob);
+	seq = (struct papr_rtas_sequence) {
+		.begin = vpd_sequence_begin,
+		.end = vpd_sequence_end,
+		.work = vpd_sequence_fill_work_area,
+	};
 
-	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		err = fd;
-		goto free_blob;
-	}
+	vpd_params.loc_code = &klc;
+	seq.params = (void *)&vpd_params;
 
-	file = anon_inode_getfile("[papr-vpd]", &papr_vpd_handle_ops,
-				  (void *)blob, O_RDONLY);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
-		goto put_fd;
-	}
+	fd = papr_rtas_setup_file_interface(&seq, &papr_vpd_handle_ops,
+			"[papr-vpd]");
 
-	file->f_mode |= FMODE_LSEEK | FMODE_PREAD;
-	fd_install(fd, file);
 	return fd;
-put_fd:
-	put_unused_fd(fd);
-free_blob:
-	vpd_blob_free(blob);
-	return err;
 }
 
 /*
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 24a177d164f1..0834a9a12600 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -12,7 +12,6 @@ obj-$(CONFIG_PPC_MSI_BITMAP)	+= msi_bitmap.o
 
 obj-$(CONFIG_PPC_MPC106)	+= grackle.o
 obj-$(CONFIG_PPC_DCR_NATIVE)	+= dcr-low.o
-obj-$(CONFIG_PPC_PMI)		+= pmi.o
 obj-$(CONFIG_U3_DART)		+= dart_iommu.o
 obj-$(CONFIG_MMIO_NVRAM)	+= mmio_nvram.o
 obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o fsl_mpic_err.o
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index e14493685fe8..4a59ed1d62ce 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -207,7 +207,7 @@ unsigned int cpm2_get_irq(void)
 
 	if (irq == 0)
 		return(-1);
-	return irq_linear_revmap(cpm2_pic_host, irq);
+	return irq_find_mapping(cpm2_pic_host, irq);
 }
 
 static int cpm2_pic_host_map(struct irq_domain *h, unsigned int virq,
@@ -259,7 +259,8 @@ void cpm2_pic_init(struct device_node *node)
 	out_be32(&cpm2_intctl->ic_scprrl, 0x05309770);
 
 	/* create a legacy host */
-	cpm2_pic_host = irq_domain_add_linear(node, 64, &cpm2_pic_host_ops, NULL);
+	cpm2_pic_host = irq_domain_create_linear(of_fwnode_handle(node), 64,
+						 &cpm2_pic_host_ops, NULL);
 	if (cpm2_pic_host == NULL) {
 		printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n");
 		return;
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 47db732981a8..e22fc638dbc7 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -138,7 +138,7 @@ static void __cpm2_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
 	out_be32(&iop->dat, cpm2_gc->cpdata);
 }
 
-static void cpm2_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm2_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
 	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(gc);
@@ -150,6 +150,8 @@ static void cpm2_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 	__cpm2_gpio32_set(mm_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm2_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm2_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -208,7 +210,7 @@ int cpm2_gpiochip_add32(struct device *dev)
 	gc->direction_input = cpm2_gpio32_dir_in;
 	gc->direction_output = cpm2_gpio32_dir_out;
 	gc->get = cpm2_gpio32_get;
-	gc->set = cpm2_gpio32_set;
+	gc->set_rv = cpm2_gpio32_set;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index 70ce66eadff1..cb44a69958e7 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -11,107 +11,6 @@
 #include <linux/of_address.h>
 #include <asm/dcr.h>
 
-#ifdef CONFIG_PPC_DCR_MMIO
-static struct device_node *find_dcr_parent(struct device_node *node)
-{
-	struct device_node *par, *tmp;
-	const u32 *p;
-
-	for (par = of_node_get(node); par;) {
-		if (of_property_read_bool(par, "dcr-controller"))
-			break;
-		p = of_get_property(par, "dcr-parent", NULL);
-		tmp = par;
-		if (p == NULL)
-			par = of_get_parent(par);
-		else
-			par = of_find_node_by_phandle(*p);
-		of_node_put(tmp);
-	}
-	return par;
-}
-#endif
-
-#if defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO)
-
-bool dcr_map_ok_generic(dcr_host_t host)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		return dcr_map_ok_native(host.host.native);
-	else if (host.type == DCR_HOST_MMIO)
-		return dcr_map_ok_mmio(host.host.mmio);
-	else
-		return false;
-}
-EXPORT_SYMBOL_GPL(dcr_map_ok_generic);
-
-dcr_host_t dcr_map_generic(struct device_node *dev,
-			   unsigned int dcr_n,
-			   unsigned int dcr_c)
-{
-	dcr_host_t host;
-	struct device_node *dp;
-	const char *prop;
-
-	host.type = DCR_HOST_INVALID;
-
-	dp = find_dcr_parent(dev);
-	if (dp == NULL)
-		return host;
-
-	prop = of_get_property(dp, "dcr-access-method", NULL);
-
-	pr_debug("dcr_map_generic(dcr-access-method = %s)\n", prop);
-
-	if (!strcmp(prop, "native")) {
-		host.type = DCR_HOST_NATIVE;
-		host.host.native = dcr_map_native(dev, dcr_n, dcr_c);
-	} else if (!strcmp(prop, "mmio")) {
-		host.type = DCR_HOST_MMIO;
-		host.host.mmio = dcr_map_mmio(dev, dcr_n, dcr_c);
-	}
-
-	of_node_put(dp);
-	return host;
-}
-EXPORT_SYMBOL_GPL(dcr_map_generic);
-
-void dcr_unmap_generic(dcr_host_t host, unsigned int dcr_c)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		dcr_unmap_native(host.host.native, dcr_c);
-	else if (host.type == DCR_HOST_MMIO)
-		dcr_unmap_mmio(host.host.mmio, dcr_c);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-}
-EXPORT_SYMBOL_GPL(dcr_unmap_generic);
-
-u32 dcr_read_generic(dcr_host_t host, unsigned int dcr_n)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		return dcr_read_native(host.host.native, dcr_n);
-	else if (host.type == DCR_HOST_MMIO)
-		return dcr_read_mmio(host.host.mmio, dcr_n);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dcr_read_generic);
-
-void dcr_write_generic(dcr_host_t host, unsigned int dcr_n, u32 value)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		dcr_write_native(host.host.native, dcr_n, value);
-	else if (host.type == DCR_HOST_MMIO)
-		dcr_write_mmio(host.host.mmio, dcr_n, value);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-}
-EXPORT_SYMBOL_GPL(dcr_write_generic);
-
-#endif /* defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO) */
-
 unsigned int dcr_resource_start(const struct device_node *np,
 				unsigned int index)
 {
@@ -137,86 +36,5 @@ unsigned int dcr_resource_len(const struct device_node *np, unsigned int index)
 }
 EXPORT_SYMBOL_GPL(dcr_resource_len);
 
-#ifdef CONFIG_PPC_DCR_MMIO
-
-static u64 of_translate_dcr_address(struct device_node *dev,
-				    unsigned int dcr_n,
-				    unsigned int *out_stride)
-{
-	struct device_node *dp;
-	const u32 *p;
-	unsigned int stride;
-	u64 ret = OF_BAD_ADDR;
-
-	dp = find_dcr_parent(dev);
-	if (dp == NULL)
-		return OF_BAD_ADDR;
-
-	/* Stride is not properly defined yet, default to 0x10 for Axon */
-	p = of_get_property(dp, "dcr-mmio-stride", NULL);
-	stride = (p == NULL) ? 0x10 : *p;
-
-	/* XXX FIXME: Which property name is to use of the 2 following ? */
-	p = of_get_property(dp, "dcr-mmio-range", NULL);
-	if (p == NULL)
-		p = of_get_property(dp, "dcr-mmio-space", NULL);
-	if (p == NULL)
-		goto done;
-
-	/* Maybe could do some better range checking here */
-	ret = of_translate_address(dp, p);
-	if (ret != OF_BAD_ADDR)
-		ret += (u64)(stride) * (u64)dcr_n;
-	if (out_stride)
-		*out_stride = stride;
-
- done:
-	of_node_put(dp);
-	return ret;
-}
-
-dcr_host_mmio_t dcr_map_mmio(struct device_node *dev,
-			     unsigned int dcr_n,
-			     unsigned int dcr_c)
-{
-	dcr_host_mmio_t ret = { .token = NULL, .stride = 0, .base = dcr_n };
-	u64 addr;
-
-	pr_debug("dcr_map(%pOF, 0x%x, 0x%x)\n",
-		 dev, dcr_n, dcr_c);
-
-	addr = of_translate_dcr_address(dev, dcr_n, &ret.stride);
-	pr_debug("translates to addr: 0x%llx, stride: 0x%x\n",
-		 (unsigned long long) addr, ret.stride);
-	if (addr == OF_BAD_ADDR)
-		return ret;
-	pr_debug("mapping 0x%x bytes\n", dcr_c * ret.stride);
-	ret.token = ioremap(addr, dcr_c * ret.stride);
-	if (ret.token == NULL)
-		return ret;
-	pr_debug("mapped at 0x%p -> base is 0x%p\n",
-		 ret.token, ret.token - dcr_n * ret.stride);
-	ret.token -= dcr_n * ret.stride;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dcr_map_mmio);
-
-void dcr_unmap_mmio(dcr_host_mmio_t host, unsigned int dcr_c)
-{
-	dcr_host_mmio_t h = host;
-
-	if (h.token == NULL)
-		return;
-	h.token += host.base * h.stride;
-	iounmap(h.token);
-	h.token = NULL;
-}
-EXPORT_SYMBOL_GPL(dcr_unmap_mmio);
-
-#endif /* defined(CONFIG_PPC_DCR_MMIO) */
-
-#ifdef CONFIG_PPC_DCR_NATIVE
 DEFINE_SPINLOCK(dcr_ind_lock);
 EXPORT_SYMBOL_GPL(dcr_ind_lock);
-#endif	/* defined(CONFIG_PPC_DCR_NATIVE) */
-
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index 040827671d21..b6f9774038e1 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -175,7 +175,7 @@ unsigned int ehv_pic_get_irq(void)
 	 * this will also setup revmap[] in the slow path for the first
 	 * time, next calls will always use fast path by indexing revmap
 	 */
-	return irq_linear_revmap(global_ehv_pic->irqhost, irq);
+	return irq_find_mapping(global_ehv_pic->irqhost, irq);
 }
 
 static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node,
@@ -269,8 +269,9 @@ void __init ehv_pic_init(void)
 		return;
 	}
 
-	ehv_pic->irqhost = irq_domain_add_linear(np, NR_EHV_PIC_INTS,
-						 &ehv_pic_host_ops, ehv_pic);
+	ehv_pic->irqhost = irq_domain_create_linear(of_fwnode_handle(np),
+						    NR_EHV_PIC_INTS,
+						    &ehv_pic_host_ops, ehv_pic);
 	if (!ehv_pic->irqhost) {
 		of_node_put(np);
 		kfree(ehv_pic);
@@ -291,5 +292,5 @@ void __init ehv_pic_init(void)
 	ehv_pic->coreint_flag = of_property_read_bool(np, "has-external-proxy");
 
 	global_ehv_pic = ehv_pic;
-	irq_set_default_host(global_ehv_pic->irqhost);
+	irq_set_default_domain(global_ehv_pic->irqhost);
 }
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 7b9a5ea9cad9..4fe8a7b1b288 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -412,7 +412,7 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	}
 	platform_set_drvdata(dev, msi);
 
-	msi->irqhost = irq_domain_add_linear(dev->dev.of_node,
+	msi->irqhost = irq_domain_create_linear(of_fwnode_handle(dev->dev.of_node),
 				      NR_MSI_IRQS_MAX, &fsl_msi_host_ops, msi);
 
 	if (msi->irqhost == NULL) {
diff --git a/arch/powerpc/sysdev/ge/ge_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c
index a6c424680c37..0bc3f0b36528 100644
--- a/arch/powerpc/sysdev/ge/ge_pic.c
+++ b/arch/powerpc/sysdev/ge/ge_pic.c
@@ -214,8 +214,9 @@ void __init gef_pic_init(struct device_node *np)
 	}
 
 	/* Setup an irq_domain structure */
-	gef_pic_irq_host = irq_domain_add_linear(np, GEF_PIC_NUM_IRQS,
-					  &gef_pic_host_ops, NULL);
+	gef_pic_irq_host = irq_domain_create_linear(of_fwnode_handle(np),
+						    GEF_PIC_NUM_IRQS,
+						    &gef_pic_host_ops, NULL);
 	if (gef_pic_irq_host == NULL)
 		return;
 
@@ -244,7 +245,7 @@ unsigned int gef_pic_get_irq(void)
 			if (active & (0x1 << hwirq))
 				break;
 		}
-		virq = irq_linear_revmap(gef_pic_irq_host,
+		virq = irq_find_mapping(gef_pic_irq_host,
 			(irq_hw_number_t)hwirq);
 	}
 
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 06e391485da7..99bb2b916949 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -260,8 +260,8 @@ void i8259_init(struct device_node *node, unsigned long intack_addr)
 	raw_spin_unlock_irqrestore(&i8259_lock, flags);
 
 	/* create a legacy host */
-	i8259_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0,
-					   &i8259_host_ops, NULL);
+	i8259_host = irq_domain_create_legacy(of_fwnode_handle(node), NR_IRQS_LEGACY, 0, 0,
+					      &i8259_host_ops, NULL);
 	if (i8259_host == NULL) {
 		printk(KERN_ERR "i8259: failed to allocate irq host !\n");
 		return;
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 5f69e2d50f26..70be2105865d 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -711,8 +711,9 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 	if (ipic == NULL)
 		return NULL;
 
-	ipic->irqhost = irq_domain_add_linear(node, NR_IPIC_INTS,
-					      &ipic_host_ops, ipic);
+	ipic->irqhost = irq_domain_create_linear(of_fwnode_handle(node),
+						 NR_IPIC_INTS,
+						 &ipic_host_ops, ipic);
 	if (ipic->irqhost == NULL) {
 		kfree(ipic);
 		return NULL;
@@ -757,13 +758,12 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 	ipic_write(ipic->regs, IPIC_SEMSR, temp);
 
 	primary_ipic = ipic;
-	irq_set_default_host(primary_ipic->irqhost);
+	irq_set_default_domain(primary_ipic->irqhost);
 
 	ipic_write(ipic->regs, IPIC_SIMSR_H, 0);
 	ipic_write(ipic->regs, IPIC_SIMSR_L, 0);
 
-	printk ("IPIC (%d IRQ sources) at %p\n", NR_IPIC_INTS,
-			primary_ipic->regs);
+	pr_info("IPIC (%d IRQ sources) at MMIO %pa\n", NR_IPIC_INTS, &res.start);
 
 	return ipic;
 }
@@ -801,7 +801,7 @@ unsigned int ipic_get_irq(void)
 	if (irq == 0)    /* 0 --> no irq is pending */
 		return 0;
 
-	return irq_linear_revmap(primary_ipic->irqhost, irq);
+	return irq_find_mapping(primary_ipic->irqhost, irq);
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index d94cf36b0f65..ad7310bba00b 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -27,6 +27,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/syscore_ops.h>
 #include <linux/ratelimit.h>
 #include <linux/pgtable.h>
@@ -474,9 +475,9 @@ static void __init mpic_scan_ht_msi(struct mpic *mpic, u8 __iomem *devbase,
 		addr = addr | ((u64)readl(base + HT_MSI_ADDR_HI) << 32);
 	}
 
-	printk(KERN_DEBUG "mpic:   - HT:%02x.%x %s MSI mapping found @ 0x%llx\n",
-		PCI_SLOT(devfn), PCI_FUNC(devfn),
-		flags & HT_MSI_FLAGS_ENABLE ? "enabled" : "disabled", addr);
+	pr_debug("mpic:   - HT:%02x.%x %s MSI mapping found @ 0x%llx\n",
+		 PCI_SLOT(devfn), PCI_FUNC(devfn),
+		 str_enabled_disabled(flags & HT_MSI_FLAGS_ENABLE), addr);
 
 	if (!(flags & HT_MSI_FLAGS_ENABLE))
 		writeb(flags | HT_MSI_FLAGS_ENABLE, base + HT_MSI_FLAGS);
@@ -1483,9 +1484,9 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
 	mpic->isu_mask = (1 << mpic->isu_shift) - 1;
 
-	mpic->irqhost = irq_domain_add_linear(mpic->node,
-				       intvec_top,
-				       &mpic_host_ops, mpic);
+	mpic->irqhost = irq_domain_create_linear(of_fwnode_handle(mpic->node),
+						 intvec_top,
+						 &mpic_host_ops, mpic);
 
 	/*
 	 * FIXME: The code leaks the MPIC object and mappings here; this
@@ -1520,7 +1521,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 
 	if (!(mpic->flags & MPIC_SECONDARY)) {
 		mpic_primary = mpic;
-		irq_set_default_host(mpic->irqhost);
+		irq_set_default_domain(mpic->irqhost);
 	}
 
 	return mpic;
@@ -1785,7 +1786,7 @@ static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpic->irqhost, src);
+	return irq_find_mapping(mpic->irqhost, src);
 }
 
 unsigned int mpic_get_one_irq(struct mpic *mpic)
@@ -1823,7 +1824,7 @@ unsigned int mpic_get_coreint_irq(void)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpic->irqhost, src);
+	return irq_find_mapping(mpic->irqhost, src);
 #else
 	return 0;
 #endif
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
deleted file mode 100644
index 2511e586fe31..000000000000
--- a/arch/powerpc/sysdev/pmi.c
+++ /dev/null
@@ -1,267 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * pmi driver
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * PMI (Platform Management Interrupt) is a way to communicate
- * with the BMC (Baseboard Management Controller) via interrupts.
- * Unlike IPMI it is bidirectional and has a low latency.
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/completion.h>
-#include <linux/spinlock.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/workqueue.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/platform_device.h>
-
-#include <asm/io.h>
-#include <asm/pmi.h>
-
-struct pmi_data {
-	struct list_head	handler;
-	spinlock_t		handler_spinlock;
-	spinlock_t		pmi_spinlock;
-	struct mutex		msg_mutex;
-	pmi_message_t		msg;
-	struct completion	*completion;
-	struct platform_device	*dev;
-	int			irq;
-	u8 __iomem		*pmi_reg;
-	struct work_struct	work;
-};
-
-static struct pmi_data *data;
-
-static irqreturn_t pmi_irq_handler(int irq, void *dev_id)
-{
-	u8 type;
-	int rc;
-
-	spin_lock(&data->pmi_spinlock);
-
-	type = ioread8(data->pmi_reg + PMI_READ_TYPE);
-	pr_debug("pmi: got message of type %d\n", type);
-
-	if (type & PMI_ACK && !data->completion) {
-		printk(KERN_WARNING "pmi: got unexpected ACK message.\n");
-		rc = -EIO;
-		goto unlock;
-	}
-
-	if (data->completion && !(type & PMI_ACK)) {
-		printk(KERN_WARNING "pmi: expected ACK, but got %d\n", type);
-		rc = -EIO;
-		goto unlock;
-	}
-
-	data->msg.type = type;
-	data->msg.data0 = ioread8(data->pmi_reg + PMI_READ_DATA0);
-	data->msg.data1 = ioread8(data->pmi_reg + PMI_READ_DATA1);
-	data->msg.data2 = ioread8(data->pmi_reg + PMI_READ_DATA2);
-	rc = 0;
-unlock:
-	spin_unlock(&data->pmi_spinlock);
-
-	if (rc == -EIO) {
-		rc = IRQ_HANDLED;
-		goto out;
-	}
-
-	if (data->msg.type & PMI_ACK) {
-		complete(data->completion);
-		rc = IRQ_HANDLED;
-		goto out;
-	}
-
-	schedule_work(&data->work);
-
-	rc = IRQ_HANDLED;
-out:
-	return rc;
-}
-
-
-static const struct of_device_id pmi_match[] = {
-	{ .type = "ibm,pmi", .name = "ibm,pmi" },
-	{ .type = "ibm,pmi" },
-	{},
-};
-
-MODULE_DEVICE_TABLE(of, pmi_match);
-
-static void pmi_notify_handlers(struct work_struct *work)
-{
-	struct pmi_handler *handler;
-
-	spin_lock(&data->handler_spinlock);
-	list_for_each_entry(handler, &data->handler, node) {
-		pr_debug("pmi: notifying handler %p\n", handler);
-		if (handler->type == data->msg.type)
-			handler->handle_pmi_message(data->msg);
-	}
-	spin_unlock(&data->handler_spinlock);
-}
-
-static int pmi_of_probe(struct platform_device *dev)
-{
-	struct device_node *np = dev->dev.of_node;
-	int rc;
-
-	if (data) {
-		printk(KERN_ERR "pmi: driver has already been initialized.\n");
-		rc = -EBUSY;
-		goto out;
-	}
-
-	data = kzalloc(sizeof(struct pmi_data), GFP_KERNEL);
-	if (!data) {
-		printk(KERN_ERR "pmi: could not allocate memory.\n");
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	data->pmi_reg = of_iomap(np, 0);
-	if (!data->pmi_reg) {
-		printk(KERN_ERR "pmi: invalid register address.\n");
-		rc = -EFAULT;
-		goto error_cleanup_data;
-	}
-
-	INIT_LIST_HEAD(&data->handler);
-
-	mutex_init(&data->msg_mutex);
-	spin_lock_init(&data->pmi_spinlock);
-	spin_lock_init(&data->handler_spinlock);
-
-	INIT_WORK(&data->work, pmi_notify_handlers);
-
-	data->dev = dev;
-
-	data->irq = irq_of_parse_and_map(np, 0);
-	if (!data->irq) {
-		printk(KERN_ERR "pmi: invalid interrupt.\n");
-		rc = -EFAULT;
-		goto error_cleanup_iomap;
-	}
-
-	rc = request_irq(data->irq, pmi_irq_handler, 0, "pmi", NULL);
-	if (rc) {
-		printk(KERN_ERR "pmi: can't request IRQ %d: returned %d\n",
-				data->irq, rc);
-		goto error_cleanup_iomap;
-	}
-
-	printk(KERN_INFO "pmi: found pmi device at addr %p.\n", data->pmi_reg);
-
-	goto out;
-
-error_cleanup_iomap:
-	iounmap(data->pmi_reg);
-
-error_cleanup_data:
-	kfree(data);
-
-out:
-	return rc;
-}
-
-static void pmi_of_remove(struct platform_device *dev)
-{
-	struct pmi_handler *handler, *tmp;
-
-	free_irq(data->irq, NULL);
-	iounmap(data->pmi_reg);
-
-	spin_lock(&data->handler_spinlock);
-
-	list_for_each_entry_safe(handler, tmp, &data->handler, node)
-		list_del(&handler->node);
-
-	spin_unlock(&data->handler_spinlock);
-
-	kfree(data);
-	data = NULL;
-}
-
-static struct platform_driver pmi_of_platform_driver = {
-	.probe		= pmi_of_probe,
-	.remove		= pmi_of_remove,
-	.driver = {
-		.name = "pmi",
-		.of_match_table = pmi_match,
-	},
-};
-module_platform_driver(pmi_of_platform_driver);
-
-int pmi_send_message(pmi_message_t msg)
-{
-	unsigned long flags;
-	DECLARE_COMPLETION_ONSTACK(completion);
-
-	if (!data)
-		return -ENODEV;
-
-	mutex_lock(&data->msg_mutex);
-
-	data->msg = msg;
-	pr_debug("pmi_send_message: msg is %08x\n", *(u32*)&msg);
-
-	data->completion = &completion;
-
-	spin_lock_irqsave(&data->pmi_spinlock, flags);
-	iowrite8(msg.data0, data->pmi_reg + PMI_WRITE_DATA0);
-	iowrite8(msg.data1, data->pmi_reg + PMI_WRITE_DATA1);
-	iowrite8(msg.data2, data->pmi_reg + PMI_WRITE_DATA2);
-	iowrite8(msg.type, data->pmi_reg + PMI_WRITE_TYPE);
-	spin_unlock_irqrestore(&data->pmi_spinlock, flags);
-
-	pr_debug("pmi_send_message: wait for completion\n");
-
-	wait_for_completion_interruptible_timeout(data->completion,
-						  PMI_TIMEOUT);
-
-	data->completion = NULL;
-
-	mutex_unlock(&data->msg_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pmi_send_message);
-
-int pmi_register_handler(struct pmi_handler *handler)
-{
-	if (!data)
-		return -ENODEV;
-
-	spin_lock(&data->handler_spinlock);
-	list_add_tail(&handler->node, &data->handler);
-	spin_unlock(&data->handler_spinlock);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pmi_register_handler);
-
-void pmi_unregister_handler(struct pmi_handler *handler)
-{
-	if (!data)
-		return;
-
-	pr_debug("pmi: unregistering handler %p\n", handler);
-
-	spin_lock(&data->handler_spinlock);
-	list_del(&handler->node);
-	spin_unlock(&data->handler_spinlock);
-}
-EXPORT_SYMBOL_GPL(pmi_unregister_handler);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-MODULE_DESCRIPTION("IBM Platform Management Interrupt driver");
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 0e42f7bad7db..07d0f6a83879 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -404,8 +404,8 @@ void __init tsi108_pci_int_init(struct device_node *node)
 {
 	DBG("Tsi108_pci_int_init: initializing PCI interrupts\n");
 
-	pci_irq_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0,
-					     &pci_irq_domain_ops, NULL);
+	pci_irq_host = irq_domain_create_legacy(of_fwnode_handle(node), NR_IRQS_LEGACY, 0, 0,
+						&pci_irq_domain_ops, NULL);
 	if (pci_irq_host == NULL) {
 		printk(KERN_ERR "pci_irq_host: failed to allocate irq domain!\n");
 		return;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 700b67476a7d..4e89158a577c 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -145,27 +145,6 @@ static void icp_native_cause_ipi(int cpu)
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-void icp_native_cause_ipi_rm(int cpu)
-{
-	/*
-	 * Currently not used to send IPIs to another CPU
-	 * on the same core. Only caller is KVM real mode.
-	 * Need the physical address of the XICS to be
-	 * previously saved in kvm_hstate in the paca.
-	 */
-	void __iomem *xics_phys;
-
-	/*
-	 * Just like the cause_ipi functions, it is required to
-	 * include a full barrier before causing the IPI.
-	 */
-	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
-	mb();
-	__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
-}
-#endif
-
 /*
  * Called when an interrupt is received on an off-line CPU to
  * clear the interrupt, so that the CPU can go back to nap mode.
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index d3a4156e8788..c3fa539a9898 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -472,7 +472,7 @@ static int __init xics_allocate_domain(void)
 		return -ENOMEM;
 	}
 
-	irq_set_default_host(xics_host);
+	irq_set_default_domain(xics_host);
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index a6c388bdf5d0..f10592405024 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1464,10 +1464,10 @@ static const struct irq_domain_ops xive_irq_domain_ops = {
 
 static void __init xive_init_host(struct device_node *np)
 {
-	xive_irq_domain = irq_domain_add_tree(np, &xive_irq_domain_ops, NULL);
+	xive_irq_domain = irq_domain_create_tree(of_fwnode_handle(np), &xive_irq_domain_ops, NULL);
 	if (WARN_ON(xive_irq_domain == NULL))
 		return;
-	irq_set_default_host(xive_irq_domain);
+	irq_set_default_domain(xive_irq_domain);
 }
 
 static void xive_cleanup_cpu_queues(unsigned int cpu, struct xive_cpu *xc)
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index d778011060a8..d74b147126b7 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -16,7 +16,4 @@ ccflags-$(CONFIG_CC_IS_CLANG) += -Wframe-larger-than=4096
 
 obj-y			+= xmon.o nonstdio.o spr_access.o xmon_bpts.o
 
-ifdef CONFIG_XMON_DISASSEMBLY
-obj-y			+= ppc-dis.o ppc-opc.o
-obj-$(CONFIG_SPU_BASE)	+= spu-dis.o spu-opc.o
-endif
+obj-$(CONFIG_XMON_DISASSEMBLY) += ppc-dis.o ppc-opc.o
diff --git a/arch/powerpc/xmon/spu-dis.c b/arch/powerpc/xmon/spu-dis.c
deleted file mode 100644
index 4b0a4e640f08..000000000000
--- a/arch/powerpc/xmon/spu-dis.c
+++ /dev/null
@@ -1,237 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* Disassemble SPU instructions
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-#include <linux/string.h>
-#include "nonstdio.h"
-#include "ansidecl.h"
-#include "spu.h"
-#include "dis-asm.h"
-
-/* This file provides a disassembler function which uses
-   the disassembler interface defined in dis-asm.h.   */
-
-extern const struct spu_opcode spu_opcodes[];
-extern const int spu_num_opcodes;
-
-#define SPU_DISASM_TBL_SIZE (1 << 11)
-static const struct spu_opcode *spu_disassemble_table[SPU_DISASM_TBL_SIZE];
-
-static void
-init_spu_disassemble (void)
-{
-  int i;
-
-  /* If two instructions have the same opcode then we prefer the first
-   * one.  In most cases it is just an alternate mnemonic. */
-  for (i = 0; i < spu_num_opcodes; i++)
-    {
-      int o = spu_opcodes[i].opcode;
-      if (o >= SPU_DISASM_TBL_SIZE)
-	continue; /* abort (); */
-      if (spu_disassemble_table[o] == 0)
-	spu_disassemble_table[o] = &spu_opcodes[i];
-    }
-}
-
-/* Determine the instruction from the 10 least significant bits. */
-static const struct spu_opcode *
-get_index_for_opcode (unsigned int insn)
-{
-  const struct spu_opcode *index;
-  unsigned int opcode = insn >> (32-11);
-
-  /* Init the table.  This assumes that element 0/opcode 0 (currently
-   * NOP) is always used */
-  if (spu_disassemble_table[0] == 0)
-    init_spu_disassemble ();
-
-  if ((index = spu_disassemble_table[opcode & 0x780]) != 0
-      && index->insn_type == RRR)
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7f0]) != 0
-      && (index->insn_type == RI18 || index->insn_type == LBT))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7f8]) != 0
-      && index->insn_type == RI10)
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7fc]) != 0
-      && (index->insn_type == RI16))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7fe]) != 0
-      && (index->insn_type == RI8))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7ff]) != 0)
-    return index;
-
-  return NULL;
-}
-
-/* Print a Spu instruction.  */
-
-int
-print_insn_spu (unsigned long insn, unsigned long memaddr)
-{
-  int value;
-  int hex_value;
-  const struct spu_opcode *index;
-  enum spu_insns tag;
-
-  index = get_index_for_opcode (insn);
-
-  if (index == 0)
-    {
-      printf(".long 0x%lx", insn);
-    }
-  else
-    {
-      int i;
-      int paren = 0;
-      tag = (enum spu_insns)(index - spu_opcodes);
-      printf("%s", index->mnemonic);
-      if (tag == M_BI || tag == M_BISL || tag == M_IRET || tag == M_BISLED
-	  || tag == M_BIHNZ || tag == M_BIHZ || tag == M_BINZ || tag == M_BIZ
-          || tag == M_SYNC || tag == M_HBR)
-	{
-	  int fb = (insn >> (32-18)) & 0x7f;
-	  if (fb & 0x40)
-	    printf(tag == M_SYNC ? "c" : "p");
-	  if (fb & 0x20)
-	    printf("d");
-	  if (fb & 0x10)
-	    printf("e");
-	}
-      if (index->arg[0] != 0)
-	printf("\t");
-      hex_value = 0;
-      for (i = 1;  i <= index->arg[0]; i++)
-	{
-	  int arg = index->arg[i];
-	  if (arg != A_P && !paren && i > 1)
-	    printf(",");
-
-	  switch (arg)
-	    {
-	    case A_T:
-	      printf("$%lu",
-				     DECODE_INSN_RT (insn));
-	      break;
-	    case A_A:
-	      printf("$%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_B:
-	      printf("$%lu",
-				     DECODE_INSN_RB (insn));
-	      break;
-	    case A_C:
-	      printf("$%lu",
-				     DECODE_INSN_RC (insn));
-	      break;
-	    case A_S:
-	      printf("$sp%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_H:
-	      printf("$ch%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_P:
-	      paren++;
-	      printf("(");
-	      break;
-	    case A_U7A:
-	      printf("%lu",
-				     173 - DECODE_INSN_U8 (insn));
-	      break;
-	    case A_U7B:
-	      printf("%lu",
-				     155 - DECODE_INSN_U8 (insn));
-	      break;
-	    case A_S3:
-	    case A_S6:
-	    case A_S7:
-	    case A_S7N:
-	    case A_U3:
-	    case A_U5:
-	    case A_U6:
-	    case A_U7:
-	      hex_value = DECODE_INSN_I7 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_S11:
-	      print_address(memaddr + DECODE_INSN_I9a (insn) * 4);
-	      break;
-	    case A_S11I:
-	      print_address(memaddr + DECODE_INSN_I9b (insn) * 4);
-	      break;
-	    case A_S10:
-	    case A_S10B:
-	      hex_value = DECODE_INSN_I10 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_S14:
-	      hex_value = DECODE_INSN_I10 (insn) * 16;
-	      printf("%d", hex_value);
-	      break;
-	    case A_S16:
-	      hex_value = DECODE_INSN_I16 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_X16:
-	      hex_value = DECODE_INSN_U16 (insn);
-	      printf("%u", hex_value);
-	      break;
-	    case A_R18:
-	      value = DECODE_INSN_I16 (insn) * 4;
-	      if (value == 0)
-		printf("%d", value);
-	      else
-		{
-		  hex_value = memaddr + value;
-		  print_address(hex_value & 0x3ffff);
-		}
-	      break;
-	    case A_S18:
-	      value = DECODE_INSN_U16 (insn) * 4;
-	      if (value == 0)
-		printf("%d", value);
-	      else
-		print_address(value);
-	      break;
-	    case A_U18:
-	      value = DECODE_INSN_U18 (insn);
-	      if (value == 0 || 1)
-		{
-		  hex_value = value;
-		  printf("%u", value);
-		}
-	      else
-		print_address(value);
-	      break;
-	    case A_U14:
-	      hex_value = DECODE_INSN_U14 (insn);
-	      printf("%u", hex_value);
-	      break;
-	    }
-	  if (arg != A_P && paren)
-	    {
-	      printf(")");
-	      paren--;
-	    }
-	}
-      if (hex_value > 16)
-	printf("\t# %x", hex_value);
-    }
-  return 4;
-}
diff --git a/arch/powerpc/xmon/spu-insns.h b/arch/powerpc/xmon/spu-insns.h
deleted file mode 100644
index 7e1126a19909..000000000000
--- a/arch/powerpc/xmon/spu-insns.h
+++ /dev/null
@@ -1,399 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* SPU ELF support for BFD.
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of BFD, the Binary File Descriptor library.
-
- */
-
-/* SPU Opcode Table
-
--=-=-= FORMAT =-=-=-
-                                             		                                             
-       +----+-------+-------+-------+-------+  		       +------------+-------+-------+-------+
-RRR    | op |  RC   |  RB   |  RA   |  RT   |		RI7    | op         |  I7   |  RA   |  RT   |
-       +----+-------+-------+-------+-------+		       +------------+-------+-------+-------+
-        0  3       1       1       2       3		        0          1       1       2       3 
-                   0       7       4       1		                   0       7       4       1 
-
-       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
-RI8    | op        |   I8   |  RA   |  RT   |		RI10   | op      |   I10    |  RA   |  RT   |
-       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
-        0         9        1       2       3		        0       7          1       2       3 
-                           7       4       1		                           7       4       1 
-
-       +----------+-----------------+-------+		       +--------+-------------------+-------+
-RI16   | op       |       I16       |  RT   |		RI18   | op     |       I18         |  RT   |
-       +----------+-----------------+-------+		       +--------+-------------------+-------+
-        0        8                 2       3		        0      6                   2       3 
-                                   4       1		                                   4       1 
-
-       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
-RR     | op         |  RB   |  RA   |  RT   |		LBT    | op    |RO|       I16       |  RO   |
-       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
-        0          1       1       2       3		        0     6  8                 2       3 
-                   0       7       4       1		                                   4       1 
-
-							       +------------+----+--+-------+-------+
-							LBTI   | op         | // |RO|  RA   |  RO   |
-							       +------------+----+--+-------+-------+
-							        0          1    1  1       2       3
-							                   0    5  7       4       1
-
--=-=-= OPCODE =-=-=-
-
-OPCODE field specifies the most significant 11bit of the instruction. Some formats don't have 11bits for opcode field, and in this
-case, bit field other than op are defined as 0s. For example, opcode of fma instruction which is RRR format is defined as 0x700,
-since 0x700 -> 11'b11100000000, this means opcode is 4'b1110, and other 7bits are defined as 7'b0000000.
-
--=-=-= ASM_FORMAT =-=-=-
-
-RRR category						RI7 category                               
-	ASM_RRR		mnemonic RC, RA, RB, RT		        ASM_RI4         mnemonic RT, RA, I4
-							        ASM_RI7         mnemonic RT, RA, I7
-
-RI8 category						RI10 category                               
-	ASM_RUI8	mnemonic RT, RA, UI8		        ASM_AI10        mnemonic RA, I10    
-							        ASM_RI10        mnemonic RT, RA, R10
-							        ASM_RI10IDX     mnemonic RT, I10(RA)
-
-RI16 category						RI18 category                           
-	ASM_I16W	mnemonic I16W			        ASM_RI18        mnemonic RT, I18
-	ASM_RI16	mnemonic RT, I16
-	ASM_RI16W	mnemonic RT, I16W
-
-RR category						LBT category                                    
-	ASM_MFSPR	mnemonic RT, SA			        ASM_LBT         mnemonic brinst, brtarg 
-	ASM_MTSPR	mnemonic SA, RT			                                                
-	ASM_NOOP	mnemonic			LBTI category                                   
-	ASM_RA		mnemonic RA			        ASM_LBTI        mnemonic brinst, RA     
-	ASM_RAB		mnemonic RA, RB
-	ASM_RDCH	mnemonic RT, CA
-	ASM_RR		mnemonic RT, RA, RB
-	ASM_RT		mnemonic RT
-	ASM_RTA		mnemonic RT, RA
-	ASM_WRCH	mnemonic CA, RT
-
-Note that RRR instructions have the names for RC and RT reversed from
-what's in the ISA, in order to put RT in the same position it appears
-for other formats.
-
--=-=-= DEPENDENCY =-=-=-
-
-DEPENDENCY filed consists of 5 digits. This represents which register is used as source and which register is used as target.
-The first(most significant) digit is always 0. Then it is followd by RC, RB, RA and RT digits.
-If the digit is 0, this means the corresponding register is not used in the instruction.
-If the digit is 1, this means the corresponding register is used as a source in the instruction.
-If the digit is 2, this means the corresponding register is used as a target in the instruction.
-If the digit is 3, this means the corresponding register is used as both source and target in the instruction.
-For example, fms instruction has 00113 as the DEPENDENCY field. This means RC is not used in this operation, RB and RA are
-used as sources and RT is the target.
-
--=-=-= PIPE =-=-=-
-
-This field shows which execution pipe is used for the instruction
-
-pipe0 execution pipelines:
-	FP6	SP floating pipeline
-	FP7	integer operations executed in SP floating pipeline
-	FPD	DP floating pipeline
-	FX2	FXU pipeline
-	FX3	Rotate/Shift pipeline
-	FXB	Byte pipeline
-	NOP	No pipeline
-
-pipe1 execution pipelines:
-	BR	Branch pipeline
-	LNOP	No pipeline
-	LS	Load/Store pipeline
-	SHUF	Shuffle pipeline
-	SPR	SPR/CH pipeline
-
-*/
-
-#define _A0() {0}
-#define _A1(a) {1,a}
-#define _A2(a,b) {2,a,b}
-#define _A3(a,b,c) {3,a,b,c}
-#define _A4(a,b,c,d) {4,a,b,c,d}
-
-/*    TAG		FORMAT	OPCODE	MNEMONIC	ASM_FORMAT	DEPENDENCY	PIPE	COMMENT				*/
-/*									0[RC][RB][RA][RT]					*/
-/*									1:src, 2:target						*/
-
-APUOP(M_BR,		RI16,	0x190,	"br",		_A1(A_R18),	00000,	BR)	/* BRel          IP<-IP+I16 */
-APUOP(M_BRSL,		RI16,	0x198,	"brsl",		_A2(A_T,A_R18),	00002,	BR)	/* BRelSetLink   RT,IP<-IP,IP+I16 */
-APUOP(M_BRA,		RI16,	0x180,	"bra",		_A1(A_S18),	00000,	BR)	/* BRAbs         IP<-I16 */
-APUOP(M_BRASL,		RI16,	0x188,	"brasl",	_A2(A_T,A_S18),	00002,	BR)	/* BRAbsSetLink  RT,IP<-IP,I16 */
-APUOP(M_FSMBI,		RI16,	0x194,	"fsmbi",	_A2(A_T,A_X16),	00002,	SHUF)	/* FormSelMask%I RT<-fsm(I16) */
-APUOP(M_LQA,		RI16,	0x184,	"lqa",		_A2(A_T,A_S18),	00002,	LS)	/* LoadQAbs      RT<-M[I16] */
-APUOP(M_LQR,		RI16,	0x19C,	"lqr",		_A2(A_T,A_R18),	00002,	LS)	/* LoadQRel      RT<-M[IP+I16] */
-APUOP(M_STOP,		RR,	0x000,	"stop",		_A0(),		00000,	BR)	/* STOP          stop */
-APUOP(M_STOP2,		RR,	0x000,	"stop",		_A1(A_U14),	00000,	BR)	/* STOP          stop */
-APUOP(M_STOPD,		RR,	0x140,	"stopd",	_A3(A_T,A_A,A_B),         00111,	BR)	/* STOPD         stop (with register dependencies) */
-APUOP(M_LNOP,		RR,	0x001,	"lnop",		_A0(),		00000,	LNOP)	/* LNOP          no_operation */
-APUOP(M_SYNC,		RR,	0x002,	"sync",		_A0(),		00000,	BR)	/* SYNC          flush_pipe */
-APUOP(M_DSYNC,		RR,	0x003,	"dsync",	_A0(),		00000,	BR)	/* DSYNC         flush_store_queue */
-APUOP(M_MFSPR,		RR,	0x00c,	"mfspr",	_A2(A_T,A_S),	00002,	SPR)	/* MFSPR         RT<-SA */
-APUOP(M_RDCH,		RR,	0x00d,	"rdch",		_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHannel   RT<-CA:data */
-APUOP(M_RCHCNT,		RR,	0x00f,	"rchcnt",	_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHanCouNT RT<-CA:count */
-APUOP(M_HBRA,		LBT,	0x080,	"hbra",		_A2(A_S11,A_S18),	00000,	LS)	/* HBRA          BTB[B9]<-M[I16] */
-APUOP(M_HBRR,		LBT,	0x090,	"hbrr",		_A2(A_S11,A_R18),	00000,	LS)	/* HBRR          BTB[B9]<-M[IP+I16] */
-APUOP(M_BRZ,		RI16,	0x100,	"brz",		_A2(A_T,A_R18),	00001,	BR)	/* BRZ           IP<-IP+I16_if(RT) */
-APUOP(M_BRNZ,		RI16,	0x108,	"brnz",		_A2(A_T,A_R18),	00001,	BR)	/* BRNZ          IP<-IP+I16_if(RT) */
-APUOP(M_BRHZ,		RI16,	0x110,	"brhz",		_A2(A_T,A_R18),	00001,	BR)	/* BRHZ          IP<-IP+I16_if(RT) */
-APUOP(M_BRHNZ,		RI16,	0x118,	"brhnz",	_A2(A_T,A_R18),	00001,	BR)	/* BRHNZ         IP<-IP+I16_if(RT) */
-APUOP(M_STQA,		RI16,	0x104,	"stqa",		_A2(A_T,A_S18),	00001,	LS)	/* SToreQAbs     M[I16]<-RT */
-APUOP(M_STQR,		RI16,	0x11C,	"stqr",		_A2(A_T,A_R18),	00001,	LS)	/* SToreQRel     M[IP+I16]<-RT */
-APUOP(M_MTSPR,		RR,	0x10c,	"mtspr",	_A2(A_S,A_T),	00001,	SPR)	/* MTSPR         SA<-RT */
-APUOP(M_WRCH,		RR,	0x10d,	"wrch",		_A2(A_H,A_T),	00001,	SPR)	/* ChanWRite     CA<-RT */
-APUOP(M_LQD,		RI10,	0x1a0,	"lqd",		_A4(A_T,A_S14,A_P,A_A),	00012,	LS)	/* LoadQDisp     RT<-M[Ra+I10] */
-APUOP(M_BI,		RR,	0x1a8,	"bi",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOP(M_BISL,		RR,	0x1a9,	"bisl",		_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOP(M_IRET,  		RR,	0x1aa,	"iret",	        _A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOP(M_IRET2, 		RR,	0x1aa,	"iret",	        _A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOP(M_BISLED,		RR,	0x1ab,	"bisled",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOP(M_HBR,		LBTI,	0x1ac,	"hbr",		_A2(A_S11I,A_A),	00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
-APUOP(M_FREST,		RR,	0x1b8,	"frest",	_A2(A_T,A_A),	00012,	SHUF)	/* FREST         RT<-recip(RA) */
-APUOP(M_FRSQEST,	RR,	0x1b9,	"frsqest",	_A2(A_T,A_A),	00012,	SHUF)	/* FRSQEST       RT<-rsqrt(RA) */
-APUOP(M_FSM,		RR,	0x1b4,	"fsm",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_FSMH,		RR,	0x1b5,	"fsmh",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_FSMB,		RR,	0x1b6,	"fsmb",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_GB,		RR,	0x1b0,	"gb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_GBH,		RR,	0x1b1,	"gbh",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_GBB,		RR,	0x1b2,	"gbb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_CBD,		RI7,	0x1f4,	"cbd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CHD,		RI7,	0x1f5,	"chd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CWD,		RI7,	0x1f6,	"cwd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CDD,		RI7,	0x1f7,	"cdd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_ROTQBII,	RI7,	0x1f8,	"rotqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* ROTQBII       RT<-RA<<<I7 */
-APUOP(M_ROTQBYI,	RI7,	0x1fc,	"rotqbyi",	_A3(A_T,A_A,A_S7N),	00012,	SHUF)	/* ROTQBYI       RT<-RA<<<(I7*8) */
-APUOP(M_ROTQMBII,	RI7,	0x1f9,	"rotqmbii",	_A3(A_T,A_A,A_S3),	00012,	SHUF)	/* ROTQMBII      RT<-RA<<I7 */
-APUOP(M_ROTQMBYI,	RI7,	0x1fd,	"rotqmbyi",	_A3(A_T,A_A,A_S6),	00012,	SHUF)	/* ROTQMBYI      RT<-RA<<I7 */
-APUOP(M_SHLQBII,	RI7,	0x1fb,	"shlqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* SHLQBII       RT<-RA<<I7 */
-APUOP(M_SHLQBYI,	RI7,	0x1ff,	"shlqbyi",	_A3(A_T,A_A,A_U5),	00012,	SHUF)	/* SHLQBYI       RT<-RA<<I7 */
-APUOP(M_STQD,		RI10,	0x120,	"stqd",		_A4(A_T,A_S14,A_P,A_A),	00011,	LS)	/* SToreQDisp    M[Ra+I10]<-RT */
-APUOP(M_BIHNZ,		RR,	0x12b,	"bihnz",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOP(M_BIHZ,		RR,	0x12a,	"bihz",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOP(M_BINZ,		RR,	0x129,	"binz",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOP(M_BIZ,		RR,	0x128,	"biz",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOP(M_CBX,		RR,	0x1d4,	"cbx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CHX,		RR,	0x1d5,	"chx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CWX,		RR,	0x1d6,	"cwx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CDX,		RR,	0x1d7,	"cdx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_LQX,		RR,	0x1c4,	"lqx",		_A3(A_T,A_A,A_B),		00112,	LS)	/* LoadQindeX    RT<-M[Ra+Rb] */
-APUOP(M_ROTQBI,		RR,	0x1d8,	"rotqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQBI        RT<-RA<<<Rb */
-APUOP(M_ROTQMBI,	RR,	0x1d9,	"rotqmbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQMBI       RT<-RA<<Rb */
-APUOP(M_SHLQBI,		RR,	0x1db,	"shlqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBI        RT<-RA<<Rb */
-APUOP(M_ROTQBY,		RR,	0x1dc,	"rotqby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBY        RT<-RA<<<(Rb*8) */
-APUOP(M_ROTQMBY,	RR,	0x1dd,	"rotqmby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBY       RT<-RA<<Rb */
-APUOP(M_SHLQBY,		RR,	0x1df,	"shlqby",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBY        RT<-RA<<Rb */
-APUOP(M_ROTQBYBI,	RR,	0x1cc,	"rotqbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBYBI      RT<-RA<<Rb */
-APUOP(M_ROTQMBYBI,	RR,	0x1cd,	"rotqmbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBYBI     RT<-RA<<Rb */
-APUOP(M_SHLQBYBI,	RR,	0x1cf,	"shlqbybi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBYBI      RT<-RA<<Rb */
-APUOP(M_STQX,		RR,	0x144,	"stqx",		_A3(A_T,A_A,A_B),		00111,	LS)	/* SToreQindeX   M[Ra+Rb]<-RT */
-APUOP(M_SHUFB,		RRR,	0x580,	"shufb",	_A4(A_C,A_A,A_B,A_T),	02111,	SHUF)	/* SHUFfleBytes  RC<-f(RA,RB,RT) */
-APUOP(M_IL,		RI16,	0x204,	"il",		_A2(A_T,A_S16),	00002,	FX2)	/* ImmLoad       RT<-sxt(I16) */
-APUOP(M_ILH,		RI16,	0x20c,	"ilh",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadH      RT<-I16 */
-APUOP(M_ILHU,		RI16,	0x208,	"ilhu",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadHUpper RT<-I16<<16 */
-APUOP(M_ILA,		RI18,	0x210,	"ila",		_A2(A_T,A_U18),	00002,	FX2)	/* ImmLoadAddr   RT<-zxt(I18) */
-APUOP(M_NOP,		RR,	0x201,	"nop",		_A1(A_T),		00000,	NOP)	/* XNOP          no_operation */
-APUOP(M_NOP2,		RR,	0x201,	"nop",		_A0(),		00000,	NOP)	/* XNOP          no_operation */
-APUOP(M_IOHL,		RI16,	0x304,	"iohl",		_A2(A_T,A_X16),	00003,	FX2)	/* AddImmeXt     RT<-RT+sxt(I16) */
-APUOP(M_ANDBI,		RI10,	0x0b0,	"andbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ANDHI,		RI10,	0x0a8,	"andhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ANDI,		RI10,	0x0a0,	"andi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ORBI,		RI10,	0x030,	"orbi",		_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORHI,		RI10,	0x028,	"orhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORI,		RI10,	0x020,	"ori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORX,		RR,	0x1f0,	"orx",		_A2(A_T,A_A),		00012,	BR)	/* ORX           RT<-RA.w0|RA.w1|RA.w2|RA.w3 */
-APUOP(M_XORBI,		RI10,	0x230,	"xorbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_XORHI,		RI10,	0x228,	"xorhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_XORI,		RI10,	0x220,	"xori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_AHI,		RI10,	0x0e8,	"ahi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
-APUOP(M_AI,		RI10,	0x0e0,	"ai",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
-APUOP(M_SFHI,		RI10,	0x068,	"sfhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
-APUOP(M_SFI,		RI10,	0x060,	"sfi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
-APUOP(M_CGTBI,		RI10,	0x270,	"cgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CGTHI,		RI10,	0x268,	"cgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CGTI,		RI10,	0x260,	"cgti",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CLGTBI,		RI10,	0x2f0,	"clgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CLGTHI,		RI10,	0x2e8,	"clgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CLGTI,		RI10,	0x2e0,	"clgti",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CEQBI,		RI10,	0x3f0,	"ceqbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_CEQHI,		RI10,	0x3e8,	"ceqhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_CEQI,		RI10,	0x3e0,	"ceqi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_HGTI,		RI10,	0x278,	"hgti",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
-APUOP(M_HGTI2,		RI10,	0x278,	"hgti",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
-APUOP(M_HLGTI,		RI10,	0x2f8,	"hlgti",	_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
-APUOP(M_HLGTI2,		RI10,	0x2f8,	"hlgti",	_A2(A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
-APUOP(M_HEQI,		RI10,	0x3f8,	"heqi",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
-APUOP(M_HEQI2,		RI10,	0x3f8,	"heqi",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
-APUOP(M_MPYI,		RI10,	0x3a0,	"mpyi",		_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYI          RT<-RA*I10 */
-APUOP(M_MPYUI,		RI10,	0x3a8,	"mpyui",	_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYUI         RT<-RA*I10 */
-APUOP(M_CFLTS,		RI8,	0x3b0,	"cflts",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTS         RT<-int(RA,I8) */
-APUOP(M_CFLTU,		RI8,	0x3b2,	"cfltu",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTU         RT<-int(RA,I8) */
-APUOP(M_CSFLT,		RI8,	0x3b4,	"csflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CSFLT         RT<-flt(RA,I8) */
-APUOP(M_CUFLT,		RI8,	0x3b6,	"cuflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CUFLT         RT<-flt(RA,I8) */
-APUOP(M_FESD,		RR,	0x3b8,	"fesd",		_A2(A_T,A_A),	00012,	FPD)	/* FESD          RT<-double(RA) */
-APUOP(M_FRDS,		RR,	0x3b9,	"frds",		_A2(A_T,A_A),	00012,	FPD)	/* FRDS          RT<-single(RA) */
-APUOP(M_FSCRRD,		RR,	0x398,	"fscrrd",	_A1(A_T),		00002,	FPD)	/* FSCRRD        RT<-FP_status */
-APUOP(M_FSCRWR,		RR,	0x3ba,	"fscrwr",	_A2(A_T,A_A),	00010,	FP7)	/* FSCRWR        FP_status<-RA */
-APUOP(M_FSCRWR2,	RR,	0x3ba,	"fscrwr",	_A1(A_A),		00010,	FP7)	/* FSCRWR        FP_status<-RA */
-APUOP(M_CLZ,		RR,	0x2a5,	"clz",		_A2(A_T,A_A),	00012,	FX2)	/* CLZ           RT<-clz(RA) */
-APUOP(M_CNTB,		RR,	0x2b4,	"cntb",		_A2(A_T,A_A),	00012,	FXB)	/* CNT           RT<-pop(RA) */
-APUOP(M_XSBH,		RR,	0x2b6,	"xsbh",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignBtoH   RT<-sign_ext(RA) */
-APUOP(M_XSHW,		RR,	0x2ae,	"xshw",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignHtoW   RT<-sign_ext(RA) */
-APUOP(M_XSWD,		RR,	0x2a6,	"xswd",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignWtoD   RT<-sign_ext(RA) */
-APUOP(M_ROTI,		RI7,	0x078,	"roti",		_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
-APUOP(M_ROTMI,		RI7,	0x079,	"rotmi",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
-APUOP(M_ROTMAI,		RI7,	0x07a,	"rotmai",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
-APUOP(M_SHLI,		RI7,	0x07b,	"shli",		_A3(A_T,A_A,A_U6),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
-APUOP(M_ROTHI,		RI7,	0x07c,	"rothi",	_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
-APUOP(M_ROTHMI,		RI7,	0x07d,	"rothmi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
-APUOP(M_ROTMAHI,	RI7,	0x07e,	"rotmahi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
-APUOP(M_SHLHI,		RI7,	0x07f,	"shlhi",	_A3(A_T,A_A,A_U5),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
-APUOP(M_A,		RR,	0x0c0,	"a",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
-APUOP(M_AH,		RR,	0x0c8,	"ah",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
-APUOP(M_SF,		RR,	0x040,	"sf",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
-APUOP(M_SFH,		RR,	0x048,	"sfh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
-APUOP(M_CGT,		RR,	0x240,	"cgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CGTB,		RR,	0x250,	"cgtb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CGTH,		RR,	0x248,	"cgth",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CLGT,		RR,	0x2c0,	"clgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CLGTB,		RR,	0x2d0,	"clgtb",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CLGTH,		RR,	0x2c8,	"clgth",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CEQ,		RR,	0x3c0,	"ceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_CEQB,		RR,	0x3d0,	"ceqb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_CEQH,		RR,	0x3c8,	"ceqh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_HGT,		RR,	0x258,	"hgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
-APUOP(M_HGT2,		RR,	0x258,	"hgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
-APUOP(M_HLGT,		RR,	0x2d8,	"hlgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
-APUOP(M_HLGT2,		RR,	0x2d8,	"hlgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
-APUOP(M_HEQ,		RR,	0x3d8,	"heq",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
-APUOP(M_HEQ2,		RR,	0x3d8,	"heq",		_A2(A_A,A_B),	00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
-APUOP(M_FCEQ,		RR,	0x3c2,	"fceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCEQ          RT<-(RA=RB) */
-APUOP(M_FCMEQ,		RR,	0x3ca,	"fcmeq",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMEQ         RT<-(|RA|=|RB|) */
-APUOP(M_FCGT,		RR,	0x2c2,	"fcgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCGT          RT<-(RA<RB) */
-APUOP(M_FCMGT,		RR,	0x2ca,	"fcmgt",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMGT         RT<-(|RA|<|RB|) */
-APUOP(M_AND,		RR,	0x0c1,	"and",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* AND           RT<-RA&RB */
-APUOP(M_NAND,		RR,	0x0c9,	"nand",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NAND          RT<-!(RA&RB) */
-APUOP(M_OR,		RR,	0x041,	"or",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* OR            RT<-RA|RB */
-APUOP(M_NOR,		RR,	0x049,	"nor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NOR           RT<-!(RA&RB) */
-APUOP(M_XOR,		RR,	0x241,	"xor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* XOR           RT<-RA^RB */
-APUOP(M_EQV,		RR,	0x249,	"eqv",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* EQuiValent    RT<-!(RA^RB) */
-APUOP(M_ANDC,		RR,	0x2c1,	"andc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ANDComplement RT<-RA&!RB */
-APUOP(M_ORC,		RR,	0x2c9,	"orc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ORComplement  RT<-RA|!RB */
-APUOP(M_ABSDB,		RR,	0x053,	"absdb",	_A3(A_T,A_A,A_B),		00112,	FXB)	/* ABSoluteDiff  RT<-|RA-RB| */
-APUOP(M_AVGB,		RR,	0x0d3,	"avgb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* AVG%          RT<-(RA+RB+1)/2 */
-APUOP(M_SUMB,		RR,	0x253,	"sumb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* SUM%          RT<-f(RA,RB) */
-APUOP(M_DFA,		RR,	0x2cc,	"dfa",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFAdd         RT<-RA+RB */
-APUOP(M_DFM,		RR,	0x2ce,	"dfm",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFMul         RT<-RA*RB */
-APUOP(M_DFS,		RR,	0x2cd,	"dfs",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFSub         RT<-RA-RB */
-APUOP(M_FA,		RR,	0x2c4,	"fa",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FAdd          RT<-RA+RB */
-APUOP(M_FM,		RR,	0x2c6,	"fm",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FMul          RT<-RA*RB */
-APUOP(M_FS,		RR,	0x2c5,	"fs",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FSub          RT<-RA-RB */
-APUOP(M_MPY,		RR,	0x3c4,	"mpy",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPY           RT<-RA*RB */
-APUOP(M_MPYH,		RR,	0x3c5,	"mpyh",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYH          RT<-(RAh*RB)<<16 */
-APUOP(M_MPYHH,		RR,	0x3c6,	"mpyhh",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHH         RT<-RAh*RBh */
-APUOP(M_MPYHHU,		RR,	0x3ce,	"mpyhhu",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHHU        RT<-RAh*RBh */
-APUOP(M_MPYS,		RR,	0x3c7,	"mpys",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYS          RT<-(RA*RB)>>16 */
-APUOP(M_MPYU,		RR,	0x3cc,	"mpyu",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYU          RT<-RA*RB */
-APUOP(M_FI,		RR,	0x3d4,	"fi",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* FInterpolate  RT<-f(RA,RB) */
-APUOP(M_ROT,		RR,	0x058,	"rot",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
-APUOP(M_ROTM,		RR,	0x059,	"rotm",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
-APUOP(M_ROTMA,		RR,	0x05a,	"rotma",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
-APUOP(M_SHL,		RR,	0x05b,	"shl",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
-APUOP(M_ROTH,		RR,	0x05c,	"roth",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
-APUOP(M_ROTHM,		RR,	0x05d,	"rothm",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
-APUOP(M_ROTMAH,		RR,	0x05e,	"rotmah",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
-APUOP(M_SHLH,		RR,	0x05f,	"shlh",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
-APUOP(M_MPYHHA,		RR,	0x346,	"mpyhha",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHA        RT<-RAh*RBh+RT */
-APUOP(M_MPYHHAU,	RR,	0x34e,	"mpyhhau",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHAU       RT<-RAh*RBh+RT */
-APUOP(M_DFMA,		RR,	0x35c,	"dfma",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMAdd        RT<-RT+RA*RB */
-APUOP(M_DFMS,		RR,	0x35d,	"dfms",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMSub        RT<-RA*RB-RT */
-APUOP(M_DFNMS,		RR,	0x35e,	"dfnms",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMSub       RT<-RT-RA*RB */
-APUOP(M_DFNMA,		RR,	0x35f,	"dfnma",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMAdd       RT<-(-RT)-RA*RB */
-APUOP(M_FMA,		RRR,	0x700,	"fma",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMAdd         RC<-RT+RA*RB */
-APUOP(M_FMS,		RRR,	0x780,	"fms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMSub         RC<-RA*RB-RT */
-APUOP(M_FNMS,		RRR,	0x680,	"fnms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FNMSub        RC<-RT-RA*RB */
-APUOP(M_MPYA,		RRR,	0x600,	"mpya",		_A4(A_C,A_A,A_B,A_T),	02111,	FP7)	/* MPYA          RC<-RA*RB+RT */
-APUOP(M_SELB,		RRR,	0x400,	"selb",		_A4(A_C,A_A,A_B,A_T),	02111,	FX2)	/* SELectBits    RC<-RA&RT|RB&!RT */
-/* for system function call, this uses op-code of mtspr */
-APUOP(M_SYSCALL,	RI7,    0x10c,	"syscall",      _A3(A_T,A_A,A_S7N),	00002,	SPR)        /* System Call */
-/*
-pseudo instruction:
-system call
-value of I9	operation
-0	halt
-1		rt[0] = open(MEM[ra[0]],	ra[1])
-2		rt[0] = close(ra[0])
-3		rt[0] = read(ra[0],	MEM[ra[1]],	ra[2])
-4		rt[0] = write(ra[0],	MEM[ra[1]],	ra[2])
-5		printf(MEM[ra[0]],	ra[1],	ra[2],	ra[3])
-42		rt[0] = clock()
-52		rt[0] = lseek(ra0,	ra1,	ra2)
-
-*/
-
-
-/* new multiprecision add/sub */
-APUOP(M_ADDX,		RR,	0x340,	"addx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
-APUOP(M_CG,		RR,	0x0c2,	"cg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
-APUOP(M_CGX,		RR,	0x342,	"cgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
-APUOP(M_SFX,		RR,	0x341,	"sfx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
-APUOP(M_BG,		RR,	0x042,	"bg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
-APUOP(M_BGX,		RR,	0x343,	"bgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
-
-/*
-
-The following ops are a subset of above except with feature bits set.
-Feature bits are bits 11-17 of the instruction:
-
-  11 - C & P feature bit
-  12 - disable interrupts
-  13 - enable interrupts
-
-*/
-APUOPFB(M_BID,		RR,	0x1a8,	0x20,	"bid",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOPFB(M_BIE,		RR,	0x1a8,	0x10,	"bie",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOPFB(M_BISLD,	RR,	0x1a9,	0x20,	"bisld",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOPFB(M_BISLE,	RR,	0x1a9,	0x10,	"bisle",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOPFB(M_IRETD,  	RR,	0x1aa,	0x20,	"iretd",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETD2,  	RR,	0x1aa,	0x20,	"iretd",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETE,  	RR,	0x1aa,	0x10,	"irete",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETE2,  	RR,	0x1aa,	0x10,	"irete",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_BISLEDD,	RR,	0x1ab,	0x20,	"bisledd",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOPFB(M_BISLEDE,	RR,	0x1ab,	0x10,	"bislede",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOPFB(M_BIHNZD,	RR,	0x12b,	0x20,	"bihnzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOPFB(M_BIHNZE,	RR,	0x12b,	0x10,	"bihnze",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOPFB(M_BIHZD,	RR,	0x12a,	0x20,	"bihzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BIHZE,	RR,	0x12a,	0x10,	"bihze",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BINZD,	RR,	0x129,	0x20,	"binzd",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOPFB(M_BINZE,	RR,	0x129,	0x10,	"binze",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOPFB(M_BIZD,		RR,	0x128,	0x20,	"bizd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIZE,		RR,	0x128,	0x10,	"bize",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_SYNCC,	RR,	0x002,	0x40,	"syncc",	_A0(),		00000,	BR)	/* SYNCC          flush_pipe */
-APUOPFB(M_HBRP,		LBTI,	0x1ac,	0x40,	"hbrp",		_A0(),	        00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
-
-/* Synonyms required by the AS manual. */
-APUOP(M_LR,		RI10,	0x020,	"lr",		_A2(A_T,A_A),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_BIHT,		RR,	0x12b,	"biht", 	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOP(M_BIHF,		RR,	0x12a,	"bihf",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOP(M_BIT,		RR,	0x129,	"bit",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOP(M_BIF,		RR,	0x128,	"bif",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIHTD,	RR,	0x12b,	0x20,	"bihtd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
-APUOPFB(M_BIHTE,	RR,	0x12b,	0x10,	"bihte",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
-APUOPFB(M_BIHFD,	RR,	0x12a,	0x20,	"bihfd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BIHFE,	RR,	0x12a,	0x10,	"bihfe",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BITD, 	RR,	0x129,	0x20,	"bitd", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
-APUOPFB(M_BITE, 	RR,	0x129,	0x10,	"bite", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
-APUOPFB(M_BIFD,		RR,	0x128,	0x20,	"bifd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIFE,		RR,	0x128,	0x10,	"bife",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-
-#undef _A0
-#undef _A1
-#undef _A2
-#undef _A3
-#undef _A4
diff --git a/arch/powerpc/xmon/spu-opc.c b/arch/powerpc/xmon/spu-opc.c
deleted file mode 100644
index 6d8197cc540b..000000000000
--- a/arch/powerpc/xmon/spu-opc.c
+++ /dev/null
@@ -1,34 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* SPU opcode list
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/bug.h>
-#include "spu.h"
-
-/* This file holds the Spu opcode table */
-
-
-/*
-   Example contents of spu-insn.h
-      id_tag	mode	mode	type	opcode	mnemonic	asmtype	    dependency		FPU	L/S?	branch?	instruction   
-                QUAD	WORD                                               (0,RC,RB,RA,RT)    latency  			              		
-   APUOP(M_LQD,	1,	0,	RI9,	0x1f8,	"lqd",		ASM_RI9IDX,	00012,		FXU,	1,	0)	Load Quadword d-form 
- */
-
-const struct spu_opcode spu_opcodes[] = {
-#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
-#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
-#include "spu-insns.h"
-#undef APUOP
-#undef APUOPFB
-};
-
-const int spu_num_opcodes = ARRAY_SIZE(spu_opcodes);
diff --git a/arch/powerpc/xmon/spu.h b/arch/powerpc/xmon/spu.h
deleted file mode 100644
index 2d13b1a5fa87..000000000000
--- a/arch/powerpc/xmon/spu.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* SPU ELF support for BFD.
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-
-/* These two enums are from rel_apu/common/spu_asm_format.h */
-/* definition of instruction format */
-typedef enum {
-  RRR,
-  RI18,
-  RI16,
-  RI10,
-  RI8,
-  RI7,
-  RR,
-  LBT,
-  LBTI,
-  IDATA,
-  UNKNOWN_IFORMAT
-} spu_iformat;
-
-/* These values describe assembly instruction arguments.  They indicate
- * how to encode, range checking and which relocation to use. */
-typedef enum {
-  A_T,  /* register at pos 0 */
-  A_A,  /* register at pos 7 */
-  A_B,  /* register at pos 14 */
-  A_C,  /* register at pos 21 */
-  A_S,  /* special purpose register at pos 7 */
-  A_H,  /* channel register at pos 7 */
-  A_P,  /* parenthesis, this has to separate regs from immediates */
-  A_S3,
-  A_S6,
-  A_S7N,
-  A_S7,
-  A_U7A,
-  A_U7B,
-  A_S10B,
-  A_S10,
-  A_S11,
-  A_S11I,
-  A_S14,
-  A_S16,
-  A_S18,
-  A_R18,
-  A_U3,
-  A_U5,
-  A_U6,
-  A_U7,
-  A_U14,
-  A_X16,
-  A_U18,
-  A_MAX
-} spu_aformat;
-
-enum spu_insns {
-#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	TAG,
-#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	TAG,
-#include "spu-insns.h"
-#undef APUOP
-#undef APUOPFB
-        M_SPU_MAX
-};
-
-struct spu_opcode
-{
-   spu_iformat insn_type;
-   unsigned int opcode;
-   char *mnemonic;
-   int arg[5];
-};
-
-#define SIGNED_EXTRACT(insn,size,pos) (((int)((insn) << (32-size-pos))) >> (32-size))
-#define UNSIGNED_EXTRACT(insn,size,pos) (((insn) >> pos) & ((1 << size)-1))
-
-#define DECODE_INSN_RT(insn) (insn & 0x7f)
-#define DECODE_INSN_RA(insn) ((insn >> 7) & 0x7f)
-#define DECODE_INSN_RB(insn) ((insn >> 14) & 0x7f)
-#define DECODE_INSN_RC(insn) ((insn >> 21) & 0x7f)
-
-#define DECODE_INSN_I10(insn) SIGNED_EXTRACT(insn,10,14)
-#define DECODE_INSN_U10(insn) UNSIGNED_EXTRACT(insn,10,14)
-
-/* For branching, immediate loads, hbr and  lqa/stqa. */
-#define DECODE_INSN_I16(insn) SIGNED_EXTRACT(insn,16,7)
-#define DECODE_INSN_U16(insn) UNSIGNED_EXTRACT(insn,16,7)
-
-/* for stop */
-#define DECODE_INSN_U14(insn) UNSIGNED_EXTRACT(insn,14,0)
-
-/* For ila */
-#define DECODE_INSN_I18(insn) SIGNED_EXTRACT(insn,18,7)
-#define DECODE_INSN_U18(insn) UNSIGNED_EXTRACT(insn,18,7)
-
-/* For rotate and shift and generate control mask */
-#define DECODE_INSN_I7(insn) SIGNED_EXTRACT(insn,7,14)
-#define DECODE_INSN_U7(insn) UNSIGNED_EXTRACT(insn,7,14)
-
-/* For float <-> int conversion */
-#define DECODE_INSN_I8(insn)  SIGNED_EXTRACT(insn,8,14)
-#define DECODE_INSN_U8(insn) UNSIGNED_EXTRACT(insn,8,14)
-
-/* For hbr  */
-#define DECODE_INSN_I9a(insn) ((SIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_I9b(insn) ((SIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_U9a(insn) ((UNSIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_U9b(insn) ((UNSIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 268859e4df87..cb3a3244ae6f 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -41,8 +41,6 @@
 #include <asm/rtas.h>
 #include <asm/sstep.h>
 #include <asm/irq_regs.h>
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
 #include <asm/setjmp.h>
 #include <asm/reg.h>
 #include <asm/debug.h>
@@ -188,8 +186,6 @@ static void xmon_print_symbol(unsigned long address, const char *mid,
 			      const char *after);
 static const char *getvecname(unsigned long vec);
 
-static int do_spu_cmd(void);
-
 #ifdef CONFIG_44x
 static void dump_tlb_44x(void);
 #endif
@@ -272,13 +268,6 @@ Commands:\n\
   P 	list processes/tasks\n\
   r	print registers\n\
   s	single step\n"
-#ifdef CONFIG_SPU_BASE
-"  ss	stop execution on all spus\n\
-  sr	restore execution on stopped spus\n\
-  sf  #	dump spu fields for spu # (in hex)\n\
-  sd  #	dump spu local store for spu # (in hex)\n\
-  sdi #	disassemble spu local store for spu # (in hex)\n"
-#endif
 "  S	print special registers\n\
   Sa    print all SPRs\n\
   Sr #	read SPR #\n\
@@ -1112,8 +1101,6 @@ cmds(struct pt_regs *excp)
 			cacheflush();
 			break;
 		case 's':
-			if (do_spu_cmd() == 0)
-				break;
 			if (do_step(excp))
 				return cmd;
 			break;
@@ -1271,11 +1258,7 @@ static int xmon_batch_next_cpu(void)
 {
 	unsigned long cpu;
 
-	while (!cpumask_empty(&xmon_batch_cpus)) {
-		cpu = cpumask_next_wrap(smp_processor_id(), &xmon_batch_cpus,
-					xmon_batch_start_cpu, true);
-		if (cpu >= nr_cpu_ids)
-			break;
+	for_each_cpu_wrap(cpu, &xmon_batch_cpus, xmon_batch_start_cpu) {
 		if (xmon_batch_start_cpu == -1)
 			xmon_batch_start_cpu = cpu;
 		if (xmon_switch_cpu(cpu))
@@ -1787,7 +1770,7 @@ static void xmon_show_stack(unsigned long sp, unsigned long lr,
 				       sp + STACK_INT_FRAME_REGS);
 				break;
 			}
-			printf("--- Exception: %lx %s at ", regs.trap,
+			printf("---- Exception: %lx %s at ", regs.trap,
 			       getvecname(TRAP(&regs)));
 			pc = regs.nip;
 			lr = regs.link;
@@ -4107,263 +4090,3 @@ void __init xmon_setup(void)
 	if (xmon_early)
 		debugger(NULL);
 }
-
-#ifdef CONFIG_SPU_BASE
-
-struct spu_info {
-	struct spu *spu;
-	u64 saved_mfc_sr1_RW;
-	u32 saved_spu_runcntl_RW;
-	unsigned long dump_addr;
-	u8 stopped_ok;
-};
-
-#define XMON_NUM_SPUS	16	/* Enough for current hardware */
-
-static struct spu_info spu_info[XMON_NUM_SPUS];
-
-void __init xmon_register_spus(struct list_head *list)
-{
-	struct spu *spu;
-
-	list_for_each_entry(spu, list, full_list) {
-		if (spu->number >= XMON_NUM_SPUS) {
-			WARN_ON(1);
-			continue;
-		}
-
-		spu_info[spu->number].spu = spu;
-		spu_info[spu->number].stopped_ok = 0;
-		spu_info[spu->number].dump_addr = (unsigned long)
-				spu_info[spu->number].spu->local_store;
-	}
-}
-
-static void stop_spus(void)
-{
-	struct spu *spu;
-	volatile int i;
-	u64 tmp;
-
-	for (i = 0; i < XMON_NUM_SPUS; i++) {
-		if (!spu_info[i].spu)
-			continue;
-
-		if (setjmp(bus_error_jmp) == 0) {
-			catch_memory_errors = 1;
-			sync();
-
-			spu = spu_info[i].spu;
-
-			spu_info[i].saved_spu_runcntl_RW =
-				in_be32(&spu->problem->spu_runcntl_RW);
-
-			tmp = spu_mfc_sr1_get(spu);
-			spu_info[i].saved_mfc_sr1_RW = tmp;
-
-			tmp &= ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
-			spu_mfc_sr1_set(spu, tmp);
-
-			sync();
-			__delay(200);
-
-			spu_info[i].stopped_ok = 1;
-
-			printf("Stopped spu %.2d (was %s)\n", i,
-					spu_info[i].saved_spu_runcntl_RW ?
-					"running" : "stopped");
-		} else {
-			catch_memory_errors = 0;
-			printf("*** Error stopping spu %.2d\n", i);
-		}
-		catch_memory_errors = 0;
-	}
-}
-
-static void restart_spus(void)
-{
-	struct spu *spu;
-	volatile int i;
-
-	for (i = 0; i < XMON_NUM_SPUS; i++) {
-		if (!spu_info[i].spu)
-			continue;
-
-		if (!spu_info[i].stopped_ok) {
-			printf("*** Error, spu %d was not successfully stopped"
-					", not restarting\n", i);
-			continue;
-		}
-
-		if (setjmp(bus_error_jmp) == 0) {
-			catch_memory_errors = 1;
-			sync();
-
-			spu = spu_info[i].spu;
-			spu_mfc_sr1_set(spu, spu_info[i].saved_mfc_sr1_RW);
-			out_be32(&spu->problem->spu_runcntl_RW,
-					spu_info[i].saved_spu_runcntl_RW);
-
-			sync();
-			__delay(200);
-
-			printf("Restarted spu %.2d\n", i);
-		} else {
-			catch_memory_errors = 0;
-			printf("*** Error restarting spu %.2d\n", i);
-		}
-		catch_memory_errors = 0;
-	}
-}
-
-#define DUMP_WIDTH	23
-#define DUMP_VALUE(format, field, value)				\
-do {									\
-	if (setjmp(bus_error_jmp) == 0) {				\
-		catch_memory_errors = 1;				\
-		sync();							\
-		printf("  %-*s = "format"\n", DUMP_WIDTH,		\
-				#field, value);				\
-		sync();							\
-		__delay(200);						\
-	} else {							\
-		catch_memory_errors = 0;				\
-		printf("  %-*s = *** Error reading field.\n",		\
-					DUMP_WIDTH, #field);		\
-	}								\
-	catch_memory_errors = 0;					\
-} while (0)
-
-#define DUMP_FIELD(obj, format, field)	\
-	DUMP_VALUE(format, field, obj->field)
-
-static void dump_spu_fields(struct spu *spu)
-{
-	printf("Dumping spu fields at address %p:\n", spu);
-
-	DUMP_FIELD(spu, "0x%x", number);
-	DUMP_FIELD(spu, "%s", name);
-	DUMP_FIELD(spu, "0x%lx", local_store_phys);
-	DUMP_FIELD(spu, "0x%p", local_store);
-	DUMP_FIELD(spu, "0x%lx", ls_size);
-	DUMP_FIELD(spu, "0x%x", node);
-	DUMP_FIELD(spu, "0x%lx", flags);
-	DUMP_FIELD(spu, "%llu", class_0_pending);
-	DUMP_FIELD(spu, "0x%llx", class_0_dar);
-	DUMP_FIELD(spu, "0x%llx", class_1_dar);
-	DUMP_FIELD(spu, "0x%llx", class_1_dsisr);
-	DUMP_FIELD(spu, "0x%x", irqs[0]);
-	DUMP_FIELD(spu, "0x%x", irqs[1]);
-	DUMP_FIELD(spu, "0x%x", irqs[2]);
-	DUMP_FIELD(spu, "0x%x", slb_replace);
-	DUMP_FIELD(spu, "%d", pid);
-	DUMP_FIELD(spu, "0x%p", mm);
-	DUMP_FIELD(spu, "0x%p", ctx);
-	DUMP_FIELD(spu, "0x%p", rq);
-	DUMP_FIELD(spu, "0x%llx", timestamp);
-	DUMP_FIELD(spu, "0x%lx", problem_phys);
-	DUMP_FIELD(spu, "0x%p", problem);
-	DUMP_VALUE("0x%x", problem->spu_runcntl_RW,
-			in_be32(&spu->problem->spu_runcntl_RW));
-	DUMP_VALUE("0x%x", problem->spu_status_R,
-			in_be32(&spu->problem->spu_status_R));
-	DUMP_VALUE("0x%x", problem->spu_npc_RW,
-			in_be32(&spu->problem->spu_npc_RW));
-	DUMP_FIELD(spu, "0x%p", priv2);
-	DUMP_FIELD(spu, "0x%p", pdata);
-}
-
-static int spu_inst_dump(unsigned long adr, long count, int praddr)
-{
-	return generic_inst_dump(adr, count, praddr, print_insn_spu);
-}
-
-static void dump_spu_ls(unsigned long num, int subcmd)
-{
-	unsigned long offset, addr, ls_addr;
-
-	if (setjmp(bus_error_jmp) == 0) {
-		catch_memory_errors = 1;
-		sync();
-		ls_addr = (unsigned long)spu_info[num].spu->local_store;
-		sync();
-		__delay(200);
-	} else {
-		catch_memory_errors = 0;
-		printf("*** Error: accessing spu info for spu %ld\n", num);
-		return;
-	}
-	catch_memory_errors = 0;
-
-	if (scanhex(&offset))
-		addr = ls_addr + offset;
-	else
-		addr = spu_info[num].dump_addr;
-
-	if (addr >= ls_addr + LS_SIZE) {
-		printf("*** Error: address outside of local store\n");
-		return;
-	}
-
-	switch (subcmd) {
-	case 'i':
-		addr += spu_inst_dump(addr, 16, 1);
-		last_cmd = "sdi\n";
-		break;
-	default:
-		prdump(addr, 64);
-		addr += 64;
-		last_cmd = "sd\n";
-		break;
-	}
-
-	spu_info[num].dump_addr = addr;
-}
-
-static int do_spu_cmd(void)
-{
-	static unsigned long num = 0;
-	int cmd, subcmd = 0;
-
-	cmd = inchar();
-	switch (cmd) {
-	case 's':
-		stop_spus();
-		break;
-	case 'r':
-		restart_spus();
-		break;
-	case 'd':
-		subcmd = inchar();
-		if (isxdigit(subcmd) || subcmd == '\n')
-			termch = subcmd;
-		fallthrough;
-	case 'f':
-		scanhex(&num);
-		if (num >= XMON_NUM_SPUS || !spu_info[num].spu) {
-			printf("*** Error: invalid spu number\n");
-			return 0;
-		}
-
-		switch (cmd) {
-		case 'f':
-			dump_spu_fields(spu_info[num].spu);
-			break;
-		default:
-			dump_spu_ls(num, subcmd);
-			break;
-		}
-
-		break;
-	default:
-		return -1;
-	}
-
-	return 0;
-}
-#else /* ! CONFIG_SPU_BASE */
-static int do_spu_cmd(void)
-{
-	return -1;
-}
-#endif
diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild
index 2c585f7a0b6e..126fb738fc44 100644
--- a/arch/riscv/Kbuild
+++ b/arch/riscv/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 obj-y += kernel/ mm/ net/
-obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
 obj-$(CONFIG_CRYPTO) += crypto/
 obj-y += errata/
 obj-$(CONFIG_KVM) += kvm/
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7612c52e9b1e..bbec87b79309 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -25,6 +25,8 @@ config RISCV
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_CRC32 if RISCV_ISA_ZBC
+	select ARCH_HAS_CRC64 if 64BIT && RISCV_ISA_ZBC
+	select ARCH_HAS_CRC_T10DIF if RISCV_ISA_ZBC
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEBUG_VM_PGTABLE
@@ -43,6 +45,7 @@ config RISCV
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PREPARE_SYNC_CORE_CMD
+	select ARCH_HAS_PTDUMP if MMU
 	select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU
@@ -53,7 +56,7 @@ config RISCV
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN
-	select ARCH_HAS_VDSO_TIME_DATA
+	select ARCH_HAS_VDSO_ARCH_DATA if GENERIC_VDSO_DATA_STORE
 	select ARCH_KEEP_MEMBLOCK if ACPI
 	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if 64BIT && MMU
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
@@ -62,6 +65,7 @@ config RISCV
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
+	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
 	# LLD >= 14: https://github.com/llvm/llvm-project/issues/50505
 	select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000
@@ -111,11 +115,12 @@ config RISCV
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_LIB_DEVMEM_IS_ALLOWED
+	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_PCI_IOMAP
-	select GENERIC_PTDUMP if MMU
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL if MMU && 64BIT
+	select GENERIC_VDSO_DATA_STORE if MMU
 	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HARDIRQS_SW_RESEND
 	select HAS_IOPORT if MMU
@@ -149,7 +154,7 @@ config RISCV
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_GRAPH_FUNC
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 	select HAVE_EBPF_JIT if MMU
@@ -201,6 +206,7 @@ config RISCV
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_ECAM if (ACPI && PCI)
 	select PCI_MSI if PCI
+	select RELOCATABLE if !MMU && !PHYS_RAM_BASE_FIXED
 	select RISCV_ALTERNATIVE if !XIP_KERNEL
 	select RISCV_APLIC
 	select RISCV_IMSIC
@@ -288,13 +294,6 @@ config MMU
 	  Select if you want MMU-based virtualised addressing space
 	  support by paged memory management. If unsure, say 'Y'.
 
-config PAGE_OFFSET
-	hex
-	default 0x80000000 if !MMU && RISCV_M_MODE
-	default 0x80200000 if !MMU
-	default 0xc0000000 if 32BIT
-	default 0xff60000000000000 if 64BIT
-
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN_GENERIC
@@ -566,7 +565,8 @@ config RISCV_ISA_C
 	help
 	  Adds "C" to the ISA subsets that the toolchain is allowed to emit
 	  when building Linux, which results in compressed instructions in the
-	  Linux binary.
+	  Linux binary. This option produces a kernel that will not run on
+	  systems that do not support compressed instructions.
 
 	  If you don't know what to do here, say Y.
 
@@ -587,8 +587,8 @@ config RISCV_ISA_SVNAPOT
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
-	  Allow kernel to detect the Svnapot ISA-extension dynamically at boot
-	  time and enable its usage.
+	  Enable support for the Svnapot ISA-extension when it is detected
+	  at boot.
 
 	  The Svnapot extension is used to mark contiguous PTEs as a range
 	  of contiguous virtual-to-physical translations for a naturally
@@ -606,9 +606,8 @@ config RISCV_ISA_SVPBMT
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
-	   Adds support to dynamically detect the presence of the Svpbmt
-	   ISA-extension (Supervisor-mode: page-based memory types) and
-	   enable its usage.
+	   Add support for the Svpbmt ISA-extension (Supervisor-mode:
+	   page-based memory types) in the kernel when it is detected at boot.
 
 	   The memory type for a page contains a combination of attributes
 	   that indicate the cacheability, idempotency, and ordering
@@ -627,14 +626,15 @@ config TOOLCHAIN_HAS_V
 	depends on AS_HAS_OPTION_ARCH
 
 config RISCV_ISA_V
-	bool "VECTOR extension support"
+	bool "Vector extension support"
 	depends on TOOLCHAIN_HAS_V
 	depends on FPU
 	select DYNAMIC_SIGFRAME
 	default y
 	help
-	  Say N here if you want to disable all vector related procedure
-	  in the kernel.
+	  Add support for the Vector extension when it is detected at boot.
+	  When this option is disabled, neither the kernel nor userspace may
+	  use vector procedures.
 
 	  If you don't know what to do here, say Y.
 
@@ -733,6 +733,14 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO
 	def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb)
 	depends on AS_HAS_OPTION_ARCH
 
+config TOOLCHAIN_HAS_ZBA
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zba)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zba)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900
+	depends on AS_HAS_OPTION_ARCH
+
 config RISCV_ISA_ZBA
 	bool "Zba extension support for bit manipulation instructions"
 	default y
@@ -747,12 +755,12 @@ config RISCV_ISA_ZBA
 
 config RISCV_ISA_ZBB
 	bool "Zbb extension support for bit manipulation instructions"
-	depends on TOOLCHAIN_HAS_ZBB
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
-	   Adds support to dynamically detect the presence of the ZBB
-	   extension (basic bit manipulation) and enable its usage.
+	   Add support for enabling optimisations in the kernel when the
+	   Zbb extension is detected at boot. Some optimisations may
+	   additionally depend on toolchain support for Zbb.
 
 	   The Zbb extension provides instructions to accelerate a number
 	   of bit-specific operations (count bit population, sign extending,
@@ -783,6 +791,28 @@ config RISCV_ISA_ZBC
 
 	   If you don't know what to do here, say Y.
 
+config TOOLCHAIN_HAS_ZBKB
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbkb)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbkb)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZBKB
+	bool "Zbkb extension support for bit manipulation instructions"
+	depends on TOOLCHAIN_HAS_ZBKB
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the ZBKB
+	   extension (bit manipulation for cryptography) and enable its usage.
+
+	   The Zbkb extension provides instructions to accelerate a number
+	   of common cryptography operations (pack, zip, etc).
+
+	   If you don't know what to do here, say Y.
+
 config RISCV_ISA_ZICBOM
 	bool "Zicbom extension support for non-coherent DMA operation"
 	depends on MMU
@@ -791,9 +821,9 @@ config RISCV_ISA_ZICBOM
 	select RISCV_DMA_NONCOHERENT
 	select DMA_DIRECT_REMAP
 	help
-	   Adds support to dynamically detect the presence of the ZICBOM
-	   extension (Cache Block Management Operations) and enable its
-	   usage.
+	   Add support for the Zicbom extension (Cache Block Management
+	   Operations) and enable its use in the kernel when it is detected
+	   at boot.
 
 	   The Zicbom extension can be used to handle for example
 	   non-coherent DMA support on devices that need it.
@@ -806,7 +836,7 @@ config RISCV_ISA_ZICBOZ
 	default y
 	help
 	   Enable the use of the Zicboz extension (cbo.zero instruction)
-	   when available.
+	   in the kernel when it is detected at boot.
 
 	   The Zicboz extension is used for faster zeroing of memory.
 
@@ -844,8 +874,9 @@ config FPU
 	bool "FPU support"
 	default y
 	help
-	  Say N here if you want to disable all floating-point related procedure
-	  in the kernel.
+	  Add support for floating point operations when an FPU is detected at
+	  boot. When this option is disabled, neither the kernel nor userspace
+	  may use the floating point unit.
 
 	  If you don't know what to do here, say Y.
 
@@ -1075,8 +1106,9 @@ config PARAVIRT_TIME_ACCOUNTING
 
 config RELOCATABLE
 	bool "Build a relocatable kernel"
-	depends on MMU && 64BIT && !XIP_KERNEL
+	depends on !XIP_KERNEL
 	select MODULE_SECTIONS if MODULES
+	select ARCH_VMLINUX_NEEDS_RELOCS
 	help
           This builds a kernel as a Position Independent Executable (PIE),
           which retains all relocation metadata required to relocate the
@@ -1269,13 +1301,14 @@ config RISCV_ISA_FALLBACK
 config BUILTIN_DTB
 	bool "Built-in device tree"
 	depends on OF && NONPORTABLE
+	select GENERIC_BUILTIN_DTB
 	help
 	  Build a device tree into the Linux image.
 	  This option should be selected if no bootloader is being used.
 	  If unsure, say N.
 
 
-config BUILTIN_DTB_SOURCE
+config BUILTIN_DTB_NAME
 	string "Built-in device tree source"
 	depends on BUILTIN_DTB
 	help
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 1916cf7ba450..8b503e54fa1b 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -26,6 +26,7 @@ config ARCH_SOPHGO
 
 config ARCH_SPACEMIT
 	bool "SpacemiT SoCs"
+	select PINCTRL
 	help
 	  This enables support for SpacemiT SoC platform hardware.
 
@@ -58,7 +59,6 @@ config ARCH_THEAD
 
 config ARCH_VIRT
 	bool "QEMU Virt Machine"
-	select CLINT_TIMER if RISCV_M_MODE
 	select POWER_RESET
 	select POWER_RESET_SYSCON
 	select POWER_RESET_SYSCON_POWEROFF
@@ -78,7 +78,6 @@ config ARCH_CANAAN
 config SOC_CANAAN_K210
 	bool "Canaan Kendryte K210 SoC"
 	depends on !MMU && ARCH_CANAAN
-	select CLINT_TIMER if RISCV_M_MODE
 	select ARCH_HAS_RESET_CONTROLLER
 	select PINCTRL
 	select COMMON_CLK
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 13fbc0f94238..539d2aef5cab 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -8,7 +8,7 @@
 
 LDFLAGS_vmlinux := -z norelro
 ifeq ($(CONFIG_RELOCATABLE),y)
-	LDFLAGS_vmlinux += -shared -Bsymbolic -z notext --emit-relocs
+	LDFLAGS_vmlinux += -shared -Bsymbolic -z notext
 	KBUILD_CFLAGS += -fPIE
 endif
 ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
@@ -98,7 +98,6 @@ KBUILD_AFLAGS += -march=$(riscv-march-y)
 CC_FLAGS_FPU  := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/')
 
 KBUILD_CFLAGS += -mno-save-restore
-KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET)
 
 ifeq ($(CONFIG_CMODEL_MEDLOW),y)
 	KBUILD_CFLAGS += -mcmodel=medlow
diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink
index 6b0580949b6a..0e4cf8ad2f14 100644
--- a/arch/riscv/Makefile.postlink
+++ b/arch/riscv/Makefile.postlink
@@ -10,26 +10,17 @@ __archpost:
 
 -include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
-include $(srctree)/scripts/Makefile.lib
 
 quiet_cmd_relocs_check = CHKREL  $@
 cmd_relocs_check = 							\
 	$(CONFIG_SHELL) $(srctree)/arch/riscv/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 
-ifdef CONFIG_RELOCATABLE
-quiet_cmd_cp_vmlinux_relocs = CPREL   vmlinux.relocs
-cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs
-
-endif
-
 # `@true` prevents complaint when there is nothing to be done
 
-vmlinux: FORCE
+vmlinux vmlinux.unstripped: FORCE
 	@true
 ifdef CONFIG_RELOCATABLE
 	$(call if_changed,relocs_check)
-	$(call if_changed,cp_vmlinux_relocs)
-	$(call if_changed,strip_relocs)
 endif
 
 clean:
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
index b25d524ce5eb..bfc3d0b75b9b 100644
--- a/arch/riscv/boot/Makefile
+++ b/arch/riscv/boot/Makefile
@@ -32,10 +32,7 @@ $(obj)/xipImage: vmlinux FORCE
 endif
 
 ifdef CONFIG_RELOCATABLE
-vmlinux.relocs: vmlinux
-	@ (! [ -f vmlinux.relocs ] && echo "vmlinux.relocs can't be found, please remove vmlinux and try again") || true
-
-$(obj)/Image: vmlinux.relocs FORCE
+$(obj)/Image: vmlinux.unstripped FORCE
 else
 $(obj)/Image: vmlinux FORCE
 endif
diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile
index bff887d38abe..64a898da9aee 100644
--- a/arch/riscv/boot/dts/Makefile
+++ b/arch/riscv/boot/dts/Makefile
@@ -8,5 +8,3 @@ subdir-y += sophgo
 subdir-y += spacemit
 subdir-y += starfive
 subdir-y += thead
-
-obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi
index 1069134f2e12..a6dda55a2d1d 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi
@@ -32,8 +32,9 @@
 		#interrupt-cells = <0x1>;
 		#size-cells = <0x2>;
 		device_type = "pci";
-		reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
-		reg-names = "cfg", "apb";
+		reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>,
+		      <0x0 0x4300a000 0x0 0x2000>;
+		reg-names = "cfg", "bridge", "ctrl";
 		bus-range = <0x0 0x7f>;
 		interrupt-parent = <&plic>;
 		interrupts = <119>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi
index 8230f06ddf48..36a9860f31da 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi
@@ -20,8 +20,9 @@
 		#interrupt-cells = <0x1>;
 		#size-cells = <0x2>;
 		device_type = "pci";
-		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
-		reg-names = "cfg", "apb";
+		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>,
+		      <0x0 0x4300a000 0x0 0x2000>;
+		reg-names = "cfg", "bridge", "ctrl";
 		bus-range = <0x0 0x7f>;
 		interrupt-parent = <&plic>;
 		interrupts = <119>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi
index 9a56de7b91d6..a57dca891965 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi
@@ -20,8 +20,9 @@
 		#interrupt-cells = <0x1>;
 		#size-cells = <0x2>;
 		device_type = "pci";
-		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>;
-		reg-names = "cfg", "apb";
+		reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>,
+		      <0x0 0x4300a000 0x0 0x2000>;
+		reg-names = "cfg", "bridge", "ctrl";
 		bus-range = <0x0 0x7f>;
 		interrupt-parent = <&plic>;
 		interrupts = <119>;
diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
index c18822ec849f..58cd546392e0 100644
--- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi
@@ -341,7 +341,7 @@
 					   1024 1024 1024 1024>;
 			snps,priority = <0 1 2 3 4 5 6 7>;
 			snps,dma-masters = <2>;
-			snps,data-width = <4>;
+			snps,data-width = <2>;
 			status = "disabled";
 		};
 
diff --git a/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts
index be596d01ff8d..34645a5f6038 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts
+++ b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts
@@ -73,6 +73,13 @@
 };
 
 / {
+	pwmfan: pwm-fan {
+		compatible = "pwm-fan";
+		cooling-levels = <103 128 179 230 255>;
+		pwms = <&pwm 0 40000 0>;
+		#cooling-cells = <2>;
+	};
+
 	thermal-zones {
 		soc-thermal {
 			polling-delay-passive = <1000>;
@@ -104,6 +111,28 @@
 					type = "hot";
 				};
 			};
+
+			cooling-maps {
+				map0 {
+					trip = <&soc_active1>;
+					cooling-device = <&pwmfan 0 1>;
+				};
+
+				map1 {
+					trip = <&soc_active2>;
+					cooling-device = <&pwmfan 1 2>;
+				};
+
+				map2 {
+					trip = <&soc_active3>;
+					cooling-device = <&pwmfan 2 3>;
+				};
+
+				map3 {
+					trip = <&soc_hot>;
+					cooling-device = <&pwmfan 3 4>;
+				};
+			};
 		};
 
 		board-thermal {
@@ -118,6 +147,13 @@
 					type = "active";
 				};
 			};
+
+			cooling-maps {
+				map4 {
+					trip = <&board_active>;
+					cooling-device = <&pwmfan 3 4>;
+				};
+			};
 		};
 	};
 };
diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
index e62ac51ac55a..aa8b7fcc125d 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi
+++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
@@ -165,6 +165,15 @@
 			};
 		};
 
+		pwm: pwm@703000c000 {
+			compatible = "sophgo,sg2042-pwm";
+			reg = <0x70 0x3000c000 0x0 0x20>;
+			#pwm-cells = <3>;
+			clocks = <&clkgen GATE_CLK_APB_PWM>;
+			clock-names = "apb";
+			resets = <&rstgen RST_PWM>;
+		};
+
 		pllclk: clock-controller@70300100c0 {
 			compatible = "sophgo,sg2042-pll";
 			reg = <0x70 0x300100c0 0x0 0x40>;
@@ -173,6 +182,16 @@
 			#clock-cells = <1>;
 		};
 
+		msi: msi-controller@7030010304 {
+			compatible = "sophgo,sg2042-msi";
+			reg = <0x70 0x30010304 0x0 0x4>,
+			      <0x70 0x30010300 0x0 0x4>;
+			reg-names = "clr", "doorbell";
+			msi-controller;
+			#msi-cells = <0>;
+			msi-ranges = <&intc 64 IRQ_TYPE_LEVEL_HIGH 32>;
+		};
+
 		rpgate: clock-controller@7030010368 {
 			compatible = "sophgo,sg2042-rpgate";
 			reg = <0x70 0x30010368 0x0 0x98>;
diff --git a/arch/riscv/boot/dts/spacemit/Makefile b/arch/riscv/boot/dts/spacemit/Makefile
index ac617319a574..92e13ce1c16d 100644
--- a/arch/riscv/boot/dts/spacemit/Makefile
+++ b/arch/riscv/boot/dts/spacemit/Makefile
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_ARCH_SPACEMIT) += k1-bananapi-f3.dtb
+dtb-$(CONFIG_ARCH_SPACEMIT) += k1-milkv-jupiter.dtb
diff --git a/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts
new file mode 100644
index 000000000000..448319214104
--- /dev/null
+++ b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2024 Yangyu Chen <cyy@cyyself.name>
+ * Copyright (C) 2025 Javier Martinez Canillas <javierm@redhat.com>
+ */
+
+#include "k1.dtsi"
+#include "k1-pinctrl.dtsi"
+
+/ {
+	model = "Milk-V Jupiter (K1)";
+	compatible = "milkv,jupiter", "spacemit,k1";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0";
+	};
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_2_cfg>;
+	status = "okay";
+};
diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
index 48fb5091b817..c2f70f5e2918 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
@@ -233,7 +233,7 @@
 				regulator-always-on;
 				regulator-min-microvolt = <500000>;
 				regulator-max-microvolt = <1540000>;
-				regulator-name = "vdd-cpu";
+				regulator-name = "vdd_cpu";
 			};
 
 			emmc_vdd: aldo4 {
@@ -350,12 +350,6 @@
 &spi0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi0_pins>;
-
-	spi_dev0: spi@0 {
-		compatible = "rohm,dh2228fv";
-		reg = <0>;
-		spi-max-frequency = <10000000>;
-	};
 };
 
 &syscrg {
diff --git a/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts
index 30b0715196b6..8d9ce8b69a71 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts
+++ b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts
@@ -11,6 +11,40 @@
 	compatible = "deepcomputing,fml13v01", "starfive,jh7110";
 };
 
+&pcie1 {
+	perst-gpios = <&sysgpio 21 GPIO_ACTIVE_LOW>;
+	phys = <&pciephy1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie1_pins>;
+	status = "okay";
+};
+
+&sysgpio {
+	pcie1_pins: pcie1-0 {
+		clkreq-pins {
+			pinmux = <GPIOMUX(29, GPOUT_LOW,
+					      GPOEN_DISABLE,
+					      GPI_NONE)>;
+			bias-pull-down;
+			drive-strength = <2>;
+			input-enable;
+			input-schmitt-disable;
+			slew-rate = <0>;
+		};
+
+		wake-pins {
+			pinmux = <GPIOMUX(28, GPOUT_HIGH,
+					      GPOEN_DISABLE,
+					      GPI_NONE)>;
+			bias-pull-up;
+			drive-strength = <2>;
+			input-enable;
+			input-schmitt-disable;
+			slew-rate = <0>;
+		};
+	};
+};
+
 &usb0 {
 	dr_mode = "host";
 	status = "okay";
diff --git a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts
index b764d4d92fd9..31e825be2065 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts
+++ b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts
@@ -100,3 +100,8 @@
 	pinctrl-0 = <&usb0_pins>;
 	status = "okay";
 };
+
+&usb_cdns3 {
+	phys = <&usbphy0>, <&pciephy0>;
+	phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy";
+};
diff --git a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
index 256de17f5261..ae49c908e7fb 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
+++ b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
@@ -89,7 +89,7 @@
 #define GPOUT_SYS_SDIO1_DATA1			59
 #define GPOUT_SYS_SDIO1_DATA2			60
 #define GPOUT_SYS_SDIO1_DATA3			61
-#define GPOUT_SYS_SDIO1_DATA4			63
+#define GPOUT_SYS_SDIO1_DATA4			62
 #define GPOUT_SYS_SDIO1_DATA5			63
 #define GPOUT_SYS_SDIO1_DATA6			64
 #define GPOUT_SYS_SDIO1_DATA7			65
diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi
index 0d8339357bad..0ba74ef04679 100644
--- a/arch/riscv/boot/dts/starfive/jh7110.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi
@@ -611,6 +611,8 @@
 		pciephy0: phy@10210000 {
 			compatible = "starfive,jh7110-pcie-phy";
 			reg = <0x0 0x10210000 0x0 0x10000>;
+			starfive,sys-syscon = <&sys_syscon 0x18>;
+			starfive,stg-syscon = <&stg_syscon 0x148 0x1f4>;
 			#phy-cells = <0>;
 		};
 
@@ -1022,7 +1024,6 @@
 			snps,force_thresh_dma_mode;
 			snps,axi-config = <&stmmac_axi_setup>;
 			snps,tso;
-			snps,en-tx-lpi-clockgating;
 			snps,txpbl = <16>;
 			snps,rxpbl = <16>;
 			starfive,syscon = <&aon_syscon 0xc 0x12>;
@@ -1053,7 +1054,6 @@
 			snps,force_thresh_dma_mode;
 			snps,axi-config = <&stmmac_axi_setup>;
 			snps,tso;
-			snps,en-tx-lpi-clockgating;
 			snps,txpbl = <16>;
 			snps,rxpbl = <16>;
 			starfive,syscon = <&sys_syscon 0x90 0x2>;
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 0f7dcbe3c45b..3c8e16d71e17 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -26,7 +26,6 @@ CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
 CONFIG_ARCH_MICROCHIP=y
-CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_SIFIVE=y
 CONFIG_ARCH_SOPHGO=y
 CONFIG_ARCH_SPACEMIT=y
@@ -202,7 +201,6 @@ CONFIG_USB=y
 CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_PLATFORM=y
-# CONFIG_USB_XHCI_RCAR is not set
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
index 87ff5a1233af..ee18d1e333f2 100644
--- a/arch/riscv/configs/nommu_k210_defconfig
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -35,7 +35,7 @@ CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_BUILTIN_DTB=y
-CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic"
+CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic"
 # CONFIG_SECCOMP is not set
 # CONFIG_STACKPROTECTOR is not set
 # CONFIG_GCC_PLUGINS is not set
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
index 95cbd574f291..e770d81b738e 100644
--- a/arch/riscv/configs/nommu_k210_sdcard_defconfig
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -27,7 +27,7 @@ CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_BUILTIN_DTB=y
-CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic"
+CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic"
 # CONFIG_SECCOMP is not set
 # CONFIG_STACKPROTECTOR is not set
 # CONFIG_GCC_PLUGINS is not set
diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig
index ad58dad9a580..cd9b776602f8 100644
--- a/arch/riscv/crypto/Kconfig
+++ b/arch/riscv/crypto/Kconfig
@@ -18,17 +18,6 @@ config CRYPTO_AES_RISCV64
 	  - Zvkb vector crypto extension (CTR)
 	  - Zvkg vector crypto extension (XTS)
 
-config CRYPTO_CHACHA_RISCV64
-	tristate "Ciphers: ChaCha"
-	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_CHACHA_GENERIC
-	help
-	  Length-preserving ciphers: ChaCha20 stream cipher algorithm
-
-	  Architecture: riscv64 using:
-	  - Zvkb vector crypto extension
-
 config CRYPTO_GHASH_RISCV64
 	tristate "Hash functions: GHASH"
 	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
@@ -39,17 +28,6 @@ config CRYPTO_GHASH_RISCV64
 	  Architecture: riscv64 using:
 	  - Zvkg vector crypto extension
 
-config CRYPTO_SHA256_RISCV64
-	tristate "Hash functions: SHA-224 and SHA-256"
-	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
-	select CRYPTO_SHA256
-	help
-	  SHA-224 and SHA-256 secure hash algorithm (FIPS 180)
-
-	  Architecture: riscv64 using:
-	  - Zvknha or Zvknhb vector crypto extensions
-	  - Zvkb vector crypto extension
-
 config CRYPTO_SHA512_RISCV64
 	tristate "Hash functions: SHA-384 and SHA-512"
 	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
@@ -65,7 +43,7 @@ config CRYPTO_SM3_RISCV64
 	tristate "Hash functions: SM3 (ShangMi 3)"
 	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
 	select CRYPTO_HASH
-	select CRYPTO_SM3
+	select CRYPTO_LIB_SM3
 	help
 	  SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
 
diff --git a/arch/riscv/crypto/Makefile b/arch/riscv/crypto/Makefile
index 247c7bc7288c..e10e8257734e 100644
--- a/arch/riscv/crypto/Makefile
+++ b/arch/riscv/crypto/Makefile
@@ -4,15 +4,9 @@ obj-$(CONFIG_CRYPTO_AES_RISCV64) += aes-riscv64.o
 aes-riscv64-y := aes-riscv64-glue.o aes-riscv64-zvkned.o \
 		 aes-riscv64-zvkned-zvbb-zvkg.o aes-riscv64-zvkned-zvkb.o
 
-obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o
-chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o
-
 obj-$(CONFIG_CRYPTO_GHASH_RISCV64) += ghash-riscv64.o
 ghash-riscv64-y := ghash-riscv64-glue.o ghash-riscv64-zvkg.o
 
-obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o
-sha256-riscv64-y := sha256-riscv64-glue.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o
-
 obj-$(CONFIG_CRYPTO_SHA512_RISCV64) += sha512-riscv64.o
 sha512-riscv64-y := sha512-riscv64-glue.o sha512-riscv64-zvknhb-zvkb.o
 
diff --git a/arch/riscv/crypto/chacha-riscv64-glue.c b/arch/riscv/crypto/chacha-riscv64-glue.c
deleted file mode 100644
index 10b46f36375a..000000000000
--- a/arch/riscv/crypto/chacha-riscv64-glue.c
+++ /dev/null
@@ -1,101 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ChaCha20 using the RISC-V vector crypto extensions
- *
- * Copyright (C) 2023 SiFive, Inc.
- * Author: Jerry Shih <jerry.shih@sifive.com>
- */
-
-#include <asm/simd.h>
-#include <asm/vector.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/linkage.h>
-#include <linux/module.h>
-
-asmlinkage void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out,
-			      size_t len, const u32 iv[4]);
-
-static int riscv64_chacha20_crypt(struct skcipher_request *req)
-{
-	u32 iv[CHACHA_IV_SIZE / sizeof(u32)];
-	u8 block_buffer[CHACHA_BLOCK_SIZE];
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	const struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	unsigned int tail_bytes;
-	int err;
-
-	iv[0] = get_unaligned_le32(req->iv);
-	iv[1] = get_unaligned_le32(req->iv + 4);
-	iv[2] = get_unaligned_le32(req->iv + 8);
-	iv[3] = get_unaligned_le32(req->iv + 12);
-
-	err = skcipher_walk_virt(&walk, req, false);
-	while (walk.nbytes) {
-		nbytes = walk.nbytes & ~(CHACHA_BLOCK_SIZE - 1);
-		tail_bytes = walk.nbytes & (CHACHA_BLOCK_SIZE - 1);
-		kernel_vector_begin();
-		if (nbytes) {
-			chacha20_zvkb(ctx->key, walk.src.virt.addr,
-				      walk.dst.virt.addr, nbytes, iv);
-			iv[0] += nbytes / CHACHA_BLOCK_SIZE;
-		}
-		if (walk.nbytes == walk.total && tail_bytes > 0) {
-			memcpy(block_buffer, walk.src.virt.addr + nbytes,
-			       tail_bytes);
-			chacha20_zvkb(ctx->key, block_buffer, block_buffer,
-				      CHACHA_BLOCK_SIZE, iv);
-			memcpy(walk.dst.virt.addr + nbytes, block_buffer,
-			       tail_bytes);
-			tail_bytes = 0;
-		}
-		kernel_vector_end();
-
-		err = skcipher_walk_done(&walk, tail_bytes);
-	}
-
-	return err;
-}
-
-static struct skcipher_alg riscv64_chacha_alg = {
-	.setkey = chacha20_setkey,
-	.encrypt = riscv64_chacha20_crypt,
-	.decrypt = riscv64_chacha20_crypt,
-	.min_keysize = CHACHA_KEY_SIZE,
-	.max_keysize = CHACHA_KEY_SIZE,
-	.ivsize = CHACHA_IV_SIZE,
-	.chunksize = CHACHA_BLOCK_SIZE,
-	.walksize = 4 * CHACHA_BLOCK_SIZE,
-	.base = {
-		.cra_blocksize = 1,
-		.cra_ctxsize = sizeof(struct chacha_ctx),
-		.cra_priority = 300,
-		.cra_name = "chacha20",
-		.cra_driver_name = "chacha20-riscv64-zvkb",
-		.cra_module = THIS_MODULE,
-	},
-};
-
-static int __init riscv64_chacha_mod_init(void)
-{
-	if (riscv_isa_extension_available(NULL, ZVKB) &&
-	    riscv_vector_vlen() >= 128)
-		return crypto_register_skcipher(&riscv64_chacha_alg);
-
-	return -ENODEV;
-}
-
-static void __exit riscv64_chacha_mod_exit(void)
-{
-	crypto_unregister_skcipher(&riscv64_chacha_alg);
-}
-
-module_init(riscv64_chacha_mod_init);
-module_exit(riscv64_chacha_mod_exit);
-
-MODULE_DESCRIPTION("ChaCha20 (RISC-V accelerated)");
-MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("chacha20");
diff --git a/arch/riscv/crypto/ghash-riscv64-glue.c b/arch/riscv/crypto/ghash-riscv64-glue.c
index 312e7891fd0a..d86073d25387 100644
--- a/arch/riscv/crypto/ghash-riscv64-glue.c
+++ b/arch/riscv/crypto/ghash-riscv64-glue.c
@@ -11,11 +11,16 @@
 
 #include <asm/simd.h>
 #include <asm/vector.h>
+#include <crypto/b128ops.h>
+#include <crypto/gf128mul.h>
 #include <crypto/ghash.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <linux/linkage.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
 
 asmlinkage void ghash_zvkg(be128 *accumulator, const be128 *key, const u8 *data,
 			   size_t len);
@@ -26,8 +31,6 @@ struct riscv64_ghash_tfm_ctx {
 
 struct riscv64_ghash_desc_ctx {
 	be128 accumulator;
-	u8 buffer[GHASH_BLOCK_SIZE];
-	u32 bytes;
 };
 
 static int riscv64_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
@@ -78,50 +81,24 @@ static int riscv64_ghash_update(struct shash_desc *desc, const u8 *src,
 {
 	const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	unsigned int len;
-
-	if (dctx->bytes) {
-		if (dctx->bytes + srclen < GHASH_BLOCK_SIZE) {
-			memcpy(dctx->buffer + dctx->bytes, src, srclen);
-			dctx->bytes += srclen;
-			return 0;
-		}
-		memcpy(dctx->buffer + dctx->bytes, src,
-		       GHASH_BLOCK_SIZE - dctx->bytes);
-		riscv64_ghash_blocks(tctx, dctx, dctx->buffer,
-				     GHASH_BLOCK_SIZE);
-		src += GHASH_BLOCK_SIZE - dctx->bytes;
-		srclen -= GHASH_BLOCK_SIZE - dctx->bytes;
-		dctx->bytes = 0;
-	}
-
-	len = round_down(srclen, GHASH_BLOCK_SIZE);
-	if (len) {
-		riscv64_ghash_blocks(tctx, dctx, src, len);
-		src += len;
-		srclen -= len;
-	}
 
-	if (srclen) {
-		memcpy(dctx->buffer, src, srclen);
-		dctx->bytes = srclen;
-	}
-
-	return 0;
+	riscv64_ghash_blocks(tctx, dctx, src,
+			     round_down(srclen, GHASH_BLOCK_SIZE));
+	return srclen - round_down(srclen, GHASH_BLOCK_SIZE);
 }
 
-static int riscv64_ghash_final(struct shash_desc *desc, u8 *out)
+static int riscv64_ghash_finup(struct shash_desc *desc, const u8 *src,
+			       unsigned int len, u8 *out)
 {
 	const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	int i;
 
-	if (dctx->bytes) {
-		for (i = dctx->bytes; i < GHASH_BLOCK_SIZE; i++)
-			dctx->buffer[i] = 0;
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
 
-		riscv64_ghash_blocks(tctx, dctx, dctx->buffer,
-				     GHASH_BLOCK_SIZE);
+		memcpy(buf, src, len);
+		riscv64_ghash_blocks(tctx, dctx, buf, GHASH_BLOCK_SIZE);
+		memzero_explicit(buf, sizeof(buf));
 	}
 
 	memcpy(out, &dctx->accumulator, GHASH_DIGEST_SIZE);
@@ -131,7 +108,7 @@ static int riscv64_ghash_final(struct shash_desc *desc, u8 *out)
 static struct shash_alg riscv64_ghash_alg = {
 	.init = riscv64_ghash_init,
 	.update = riscv64_ghash_update,
-	.final = riscv64_ghash_final,
+	.finup = riscv64_ghash_finup,
 	.setkey = riscv64_ghash_setkey,
 	.descsize = sizeof(struct riscv64_ghash_desc_ctx),
 	.digestsize = GHASH_DIGEST_SIZE,
@@ -139,6 +116,7 @@ static struct shash_alg riscv64_ghash_alg = {
 		.cra_blocksize = GHASH_BLOCK_SIZE,
 		.cra_ctxsize = sizeof(struct riscv64_ghash_tfm_ctx),
 		.cra_priority = 300,
+		.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_name = "ghash",
 		.cra_driver_name = "ghash-riscv64-zvkg",
 		.cra_module = THIS_MODULE,
diff --git a/arch/riscv/crypto/sha256-riscv64-glue.c b/arch/riscv/crypto/sha256-riscv64-glue.c
deleted file mode 100644
index 71e051e40a64..000000000000
--- a/arch/riscv/crypto/sha256-riscv64-glue.c
+++ /dev/null
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SHA-256 and SHA-224 using the RISC-V vector crypto extensions
- *
- * Copyright (C) 2022 VRULL GmbH
- * Author: Heiko Stuebner <heiko.stuebner@vrull.eu>
- *
- * Copyright (C) 2023 SiFive, Inc.
- * Author: Jerry Shih <jerry.shih@sifive.com>
- */
-
-#include <asm/simd.h>
-#include <asm/vector.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha256_base.h>
-#include <linux/linkage.h>
-#include <linux/module.h>
-
-/*
- * Note: the asm function only uses the 'state' field of struct sha256_state.
- * It is assumed to be the first field.
- */
-asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb(
-	struct sha256_state *state, const u8 *data, int num_blocks);
-
-static int riscv64_sha256_update(struct shash_desc *desc, const u8 *data,
-				 unsigned int len)
-{
-	/*
-	 * Ensure struct sha256_state begins directly with the SHA-256
-	 * 256-bit internal state, as this is what the asm function expects.
-	 */
-	BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
-
-	if (crypto_simd_usable()) {
-		kernel_vector_begin();
-		sha256_base_do_update(desc, data, len,
-				      sha256_transform_zvknha_or_zvknhb_zvkb);
-		kernel_vector_end();
-	} else {
-		crypto_sha256_update(desc, data, len);
-	}
-	return 0;
-}
-
-static int riscv64_sha256_finup(struct shash_desc *desc, const u8 *data,
-				unsigned int len, u8 *out)
-{
-	if (crypto_simd_usable()) {
-		kernel_vector_begin();
-		if (len)
-			sha256_base_do_update(
-				desc, data, len,
-				sha256_transform_zvknha_or_zvknhb_zvkb);
-		sha256_base_do_finalize(
-			desc, sha256_transform_zvknha_or_zvknhb_zvkb);
-		kernel_vector_end();
-
-		return sha256_base_finish(desc, out);
-	}
-
-	return crypto_sha256_finup(desc, data, len, out);
-}
-
-static int riscv64_sha256_final(struct shash_desc *desc, u8 *out)
-{
-	return riscv64_sha256_finup(desc, NULL, 0, out);
-}
-
-static int riscv64_sha256_digest(struct shash_desc *desc, const u8 *data,
-				 unsigned int len, u8 *out)
-{
-	return sha256_base_init(desc) ?:
-	       riscv64_sha256_finup(desc, data, len, out);
-}
-
-static struct shash_alg riscv64_sha256_algs[] = {
-	{
-		.init = sha256_base_init,
-		.update = riscv64_sha256_update,
-		.final = riscv64_sha256_final,
-		.finup = riscv64_sha256_finup,
-		.digest = riscv64_sha256_digest,
-		.descsize = sizeof(struct sha256_state),
-		.digestsize = SHA256_DIGEST_SIZE,
-		.base = {
-			.cra_blocksize = SHA256_BLOCK_SIZE,
-			.cra_priority = 300,
-			.cra_name = "sha256",
-			.cra_driver_name = "sha256-riscv64-zvknha_or_zvknhb-zvkb",
-			.cra_module = THIS_MODULE,
-		},
-	}, {
-		.init = sha224_base_init,
-		.update = riscv64_sha256_update,
-		.final = riscv64_sha256_final,
-		.finup = riscv64_sha256_finup,
-		.descsize = sizeof(struct sha256_state),
-		.digestsize = SHA224_DIGEST_SIZE,
-		.base = {
-			.cra_blocksize = SHA224_BLOCK_SIZE,
-			.cra_priority = 300,
-			.cra_name = "sha224",
-			.cra_driver_name = "sha224-riscv64-zvknha_or_zvknhb-zvkb",
-			.cra_module = THIS_MODULE,
-		},
-	},
-};
-
-static int __init riscv64_sha256_mod_init(void)
-{
-	/* Both zvknha and zvknhb provide the SHA-256 instructions. */
-	if ((riscv_isa_extension_available(NULL, ZVKNHA) ||
-	     riscv_isa_extension_available(NULL, ZVKNHB)) &&
-	    riscv_isa_extension_available(NULL, ZVKB) &&
-	    riscv_vector_vlen() >= 128)
-		return crypto_register_shashes(riscv64_sha256_algs,
-					       ARRAY_SIZE(riscv64_sha256_algs));
-
-	return -ENODEV;
-}
-
-static void __exit riscv64_sha256_mod_exit(void)
-{
-	crypto_unregister_shashes(riscv64_sha256_algs,
-				  ARRAY_SIZE(riscv64_sha256_algs));
-}
-
-module_init(riscv64_sha256_mod_init);
-module_exit(riscv64_sha256_mod_exit);
-
-MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)");
-MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha224");
diff --git a/arch/riscv/crypto/sha512-riscv64-glue.c b/arch/riscv/crypto/sha512-riscv64-glue.c
index 43b56a08aeb5..4634fca78ae2 100644
--- a/arch/riscv/crypto/sha512-riscv64-glue.c
+++ b/arch/riscv/crypto/sha512-riscv64-glue.c
@@ -14,7 +14,7 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
 #include <crypto/sha512_base.h>
-#include <linux/linkage.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
 /*
@@ -24,8 +24,8 @@
 asmlinkage void sha512_transform_zvknhb_zvkb(
 	struct sha512_state *state, const u8 *data, int num_blocks);
 
-static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data,
-				 unsigned int len)
+static void sha512_block(struct sha512_state *state, const u8 *data,
+			 int num_blocks)
 {
 	/*
 	 * Ensure struct sha512_state begins directly with the SHA-512
@@ -35,35 +35,24 @@ static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data,
 
 	if (crypto_simd_usable()) {
 		kernel_vector_begin();
-		sha512_base_do_update(desc, data, len,
-				      sha512_transform_zvknhb_zvkb);
+		sha512_transform_zvknhb_zvkb(state, data, num_blocks);
 		kernel_vector_end();
 	} else {
-		crypto_sha512_update(desc, data, len);
+		sha512_generic_block_fn(state, data, num_blocks);
 	}
-	return 0;
 }
 
-static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data,
-				unsigned int len, u8 *out)
+static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data,
+				 unsigned int len)
 {
-	if (crypto_simd_usable()) {
-		kernel_vector_begin();
-		if (len)
-			sha512_base_do_update(desc, data, len,
-					      sha512_transform_zvknhb_zvkb);
-		sha512_base_do_finalize(desc, sha512_transform_zvknhb_zvkb);
-		kernel_vector_end();
-
-		return sha512_base_finish(desc, out);
-	}
-
-	return crypto_sha512_finup(desc, data, len, out);
+	return sha512_base_do_update_blocks(desc, data, len, sha512_block);
 }
 
-static int riscv64_sha512_final(struct shash_desc *desc, u8 *out)
+static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data,
+				unsigned int len, u8 *out)
 {
-	return riscv64_sha512_finup(desc, NULL, 0, out);
+	sha512_base_do_finup(desc, data, len, sha512_block);
+	return sha512_base_finish(desc, out);
 }
 
 static int riscv64_sha512_digest(struct shash_desc *desc, const u8 *data,
@@ -77,14 +66,15 @@ static struct shash_alg riscv64_sha512_algs[] = {
 	{
 		.init = sha512_base_init,
 		.update = riscv64_sha512_update,
-		.final = riscv64_sha512_final,
 		.finup = riscv64_sha512_finup,
 		.digest = riscv64_sha512_digest,
-		.descsize = sizeof(struct sha512_state),
+		.descsize = SHA512_STATE_SIZE,
 		.digestsize = SHA512_DIGEST_SIZE,
 		.base = {
 			.cra_blocksize = SHA512_BLOCK_SIZE,
 			.cra_priority = 300,
+			.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				     CRYPTO_AHASH_ALG_FINUP_MAX,
 			.cra_name = "sha512",
 			.cra_driver_name = "sha512-riscv64-zvknhb-zvkb",
 			.cra_module = THIS_MODULE,
@@ -92,13 +82,14 @@ static struct shash_alg riscv64_sha512_algs[] = {
 	}, {
 		.init = sha384_base_init,
 		.update = riscv64_sha512_update,
-		.final = riscv64_sha512_final,
 		.finup = riscv64_sha512_finup,
-		.descsize = sizeof(struct sha512_state),
+		.descsize = SHA512_STATE_SIZE,
 		.digestsize = SHA384_DIGEST_SIZE,
 		.base = {
 			.cra_blocksize = SHA384_BLOCK_SIZE,
 			.cra_priority = 300,
+			.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+				     CRYPTO_AHASH_ALG_FINUP_MAX,
 			.cra_name = "sha384",
 			.cra_driver_name = "sha384-riscv64-zvknhb-zvkb",
 			.cra_module = THIS_MODULE,
diff --git a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S
index 3a9ae210f915..89f4a10d12dd 100644
--- a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S
+++ b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S
@@ -43,7 +43,7 @@
 // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknhb')
 // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb')
 
-#include <linux/cfi_types.h>
+#include <linux/linkage.h>
 
 .text
 .option arch, +zvknhb, +zvkb
@@ -95,7 +95,7 @@
 
 // void sha512_transform_zvknhb_zvkb(u64 state[8], const u8 *data,
 //				     int num_blocks);
-SYM_TYPED_FUNC_START(sha512_transform_zvknhb_zvkb)
+SYM_FUNC_START(sha512_transform_zvknhb_zvkb)
 
 	// Setup mask for the vmerge to replace the first word (idx==0) in
 	// message scheduling.  There are 4 words, so an 8-bit mask suffices.
diff --git a/arch/riscv/crypto/sm3-riscv64-glue.c b/arch/riscv/crypto/sm3-riscv64-glue.c
index e1737a970c7c..abdfe4a63a27 100644
--- a/arch/riscv/crypto/sm3-riscv64-glue.c
+++ b/arch/riscv/crypto/sm3-riscv64-glue.c
@@ -13,8 +13,9 @@
 #include <asm/vector.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
+#include <crypto/sm3.h>
 #include <crypto/sm3_base.h>
-#include <linux/linkage.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 
 /*
@@ -24,8 +25,8 @@
 asmlinkage void sm3_transform_zvksh_zvkb(
 	struct sm3_state *state, const u8 *data, int num_blocks);
 
-static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data,
-			      unsigned int len)
+static void sm3_block(struct sm3_state *state, const u8 *data,
+		      int num_blocks)
 {
 	/*
 	 * Ensure struct sm3_state begins directly with the SM3
@@ -35,52 +36,36 @@ static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data,
 
 	if (crypto_simd_usable()) {
 		kernel_vector_begin();
-		sm3_base_do_update(desc, data, len, sm3_transform_zvksh_zvkb);
+		sm3_transform_zvksh_zvkb(state, data, num_blocks);
 		kernel_vector_end();
 	} else {
-		sm3_update(shash_desc_ctx(desc), data, len);
+		sm3_block_generic(state, data, num_blocks);
 	}
-	return 0;
 }
 
-static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *out)
+static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
 {
-	struct sm3_state *ctx;
-
-	if (crypto_simd_usable()) {
-		kernel_vector_begin();
-		if (len)
-			sm3_base_do_update(desc, data, len,
-					   sm3_transform_zvksh_zvkb);
-		sm3_base_do_finalize(desc, sm3_transform_zvksh_zvkb);
-		kernel_vector_end();
-
-		return sm3_base_finish(desc, out);
-	}
-
-	ctx = shash_desc_ctx(desc);
-	if (len)
-		sm3_update(ctx, data, len);
-	sm3_final(ctx, out);
-
-	return 0;
+	return sm3_base_do_update_blocks(desc, data, len, sm3_block);
 }
 
-static int riscv64_sm3_final(struct shash_desc *desc, u8 *out)
+static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
 {
-	return riscv64_sm3_finup(desc, NULL, 0, out);
+	sm3_base_do_finup(desc, data, len, sm3_block);
+	return sm3_base_finish(desc, out);
 }
 
 static struct shash_alg riscv64_sm3_alg = {
 	.init = sm3_base_init,
 	.update = riscv64_sm3_update,
-	.final = riscv64_sm3_final,
 	.finup = riscv64_sm3_finup,
-	.descsize = sizeof(struct sm3_state),
+	.descsize = SM3_STATE_SIZE,
 	.digestsize = SM3_DIGEST_SIZE,
 	.base = {
 		.cra_blocksize = SM3_BLOCK_SIZE,
+		.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+			     CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_priority = 300,
 		.cra_name = "sm3",
 		.cra_driver_name = "sm3-riscv64-zvksh-zvkb",
diff --git a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S
index a2b65d961c04..4fe754846f65 100644
--- a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S
+++ b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S
@@ -43,7 +43,7 @@
 // - RISC-V Vector SM3 Secure Hash extension ('Zvksh')
 // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb')
 
-#include <linux/cfi_types.h>
+#include <linux/linkage.h>
 
 .text
 .option arch, +zvksh, +zvkb
@@ -81,7 +81,7 @@
 .endm
 
 // void sm3_transform_zvksh_zvkb(u32 state[8], const u8 *data, int num_blocks);
-SYM_TYPED_FUNC_START(sm3_transform_zvksh_zvkb)
+SYM_FUNC_START(sm3_transform_zvksh_zvkb)
 
 	// Load the state and endian-swap each 32-bit word.
 	vsetivli	zero, 8, e32, m2, ta, ma
diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile
index f0da9d7b39c3..bc6c77ba837d 100644
--- a/arch/riscv/errata/Makefile
+++ b/arch/riscv/errata/Makefile
@@ -1,5 +1,9 @@
 ifdef CONFIG_RELOCATABLE
-KBUILD_CFLAGS += -fno-pie
+# We can't use PIC/PIE when handling early-boot errata parsing, as the kernel
+# doesn't have a GOT setup at that point.  So instead just use medany: it's
+# usually position-independent, so it should be good enough for the errata
+# handling.
+KBUILD_CFLAGS += -fno-pie -mcmodel=medany
 endif
 
 ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 721ec275ce57..231d777d936c 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -115,24 +115,19 @@
 	\old_c
 .endm
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
-
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG(old_c, ...)		ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG_2(old_c, ...)		ALTERNATIVE_CFG old_c
 
 #else /* !__ASSEMBLY__ */
 
-#define __ALTERNATIVE_CFG(old_c)	\
-	old_c "\n"
+#define __ALTERNATIVE_CFG(old_c, ...)		old_c "\n"
+#define __ALTERNATIVE_CFG_2(old_c, ...)		old_c "\n"
 
-#define _ALTERNATIVE_CFG(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#endif /* __ASSEMBLY__ */
 
-#define _ALTERNATIVE_CFG_2(old_c, ...)	\
-	__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG(old_c, ...)		__ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG_2(old_c, ...)		__ALTERNATIVE_CFG_2(old_c)
 
-#endif /* __ASSEMBLY__ */
 #endif /* CONFIG_RISCV_ALTERNATIVE */
 
 /*
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index 613769b9cdc9..0e7cdbbec8ef 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -19,7 +19,7 @@
 
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
-#ifdef CONFIG_RISCV_ISA_ZBB
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
 	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
@@ -50,7 +50,7 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 #if BITS_PER_LONG == 64
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
-# ifdef CONFIG_RISCV_ISA_ZBB
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
 	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
@@ -64,7 +64,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
 	return w;
 
 legacy:
-# endif
+#endif
 	return __sw_hweight64(w);
 }
 #else /* BITS_PER_LONG == 64 */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index cd627ec289f1..bfc8ea5f9319 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -52,6 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
+asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs);
+asmlinkage void ret_from_fork_user(struct pt_regs *regs);
 asmlinkage void handle_bad_stack(struct pt_regs *regs);
 asmlinkage void do_page_fault(struct pt_regs *regs);
 asmlinkage void do_irq(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 776354895b81..a8a2af6dfe9d 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -27,6 +27,7 @@
 #define REG_ASM		__REG_SEL(.dword, .word)
 #define SZREG		__REG_SEL(8, 4)
 #define LGREG		__REG_SEL(3, 2)
+#define SRLI		__REG_SEL(srliw, srli)
 
 #if __SIZEOF_POINTER__ == 8
 #ifdef __ASSEMBLY__
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index c6bd3d8354a9..d59310f74c2b 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -15,7 +15,7 @@
 #include <asm/barrier.h>
 #include <asm/bitsperlong.h>
 
-#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE)
+#if !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE)
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
@@ -175,7 +175,7 @@ legacy:
 	 variable_fls(x_);					\
 })
 
-#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */
+#endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/fls64.h>
@@ -226,7 +226,7 @@ legacy:
  * @nr: Bit to set
  * @addr: Address to count from
  *
- * This operation may be reordered on other architectures than x86.
+ * This is an atomic fully-ordered operation (implied full memory barrier).
  */
 static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr)
 {
@@ -238,7 +238,7 @@ static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long
  * @nr: Bit to clear
  * @addr: Address to count from
  *
- * This operation can be reordered on other architectures other than x86.
+ * This is an atomic fully-ordered operation (implied full memory barrier).
  */
 static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f91bfa3..b59ffeb668d6 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page)
 	flush_dcache_folio(page_folio(page));
 }
 
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
 #define flush_icache_user_page(vma, pg, addr, len)	\
 do {							\
 	if (vma->vm_flags & VM_EXEC)			\
@@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	flush_icache_all();
+}
+
 extern unsigned int riscv_cbom_block_size;
 extern unsigned int riscv_cboz_block_size;
 void riscv_init_cbo_blocksizes(void);
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index 88e6f1499e88..da378856f1d5 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -49,8 +49,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	 * ZBB only saves three instructions on 32-bit and five on 64-bit so not
 	 * worth checking if supported without Alternatives.
 	 */
-	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
-	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
 		unsigned long fold_temp;
 
 		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4cadc56220fe..2ec119eb147b 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -231,7 +231,7 @@
 		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
 			       sc_prepend, sc_append,			\
 			       cas_prepend, cas_append,			\
-			       __ret, __ptr, (long), __old, __new);	\
+			       __ret, __ptr, (long)(int)(long), __old, __new);	\
 		break;							\
 	case 8:								\
 		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
@@ -365,16 +365,48 @@ static __always_inline void __cmpwait(volatile void *ptr,
 {
 	unsigned long tmp;
 
+	u32 *__ptr32b;
+	ulong __s, __val, __mask;
+
 	asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop",
 			     0, RISCV_ISA_EXT_ZAWRS, 1)
 		 : : : : no_zawrs);
 
 	switch (size) {
 	case 1:
-		fallthrough;
+		__ptr32b = (u32 *)((ulong)(ptr) & ~0x3);
+		__s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE;
+		__val = val << __s;
+		__mask = 0xff << __s;
+
+		asm volatile(
+		"	lr.w	%0, %1\n"
+		"	and	%0, %0, %3\n"
+		"	xor	%0, %0, %2\n"
+		"	bnez	%0, 1f\n"
+			ZAWRS_WRS_NTO "\n"
+		"1:"
+		: "=&r" (tmp), "+A" (*(__ptr32b))
+		: "r" (__val), "r" (__mask)
+		: "memory");
+		break;
 	case 2:
-		/* RISC-V doesn't have lr instructions on byte and half-word. */
-		goto no_zawrs;
+		__ptr32b = (u32 *)((ulong)(ptr) & ~0x3);
+		__s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE;
+		__val = val << __s;
+		__mask = 0xffff << __s;
+
+		asm volatile(
+		"	lr.w	%0, %1\n"
+		"	and	%0, %0, %3\n"
+		"	xor	%0, %0, %2\n"
+		"	bnez	%0, 1f\n"
+			ZAWRS_WRS_NTO "\n"
+		"1:"
+		: "=&r" (tmp), "+A" (*(__ptr32b))
+		: "r" (__val), "r" (__mask)
+		: "memory");
+		break;
 	case 4:
 		asm volatile(
 		"	lr.w	%0, %1\n"
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 569140d6e639..f56b409361fb 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -56,6 +56,9 @@ void __init riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
 	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
 			    ARRAY_SIZE(_bundled_exts), NULL)
+#define __RISCV_ISA_EXT_BUNDLE_VALIDATE(_name, _bundled_exts, _validate) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
+			    ARRAY_SIZE(_bundled_exts), _validate)
 
 /* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
 #define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
@@ -63,7 +66,7 @@ void __init riscv_user_isa_enable(void);
 #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
 	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
 
-bool check_unaligned_access_emulated_all_cpus(void);
+bool __init check_unaligned_access_emulated_all_cpus(void);
 #if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
 void check_unaligned_access_emulated(struct work_struct *work __always_unused);
 void unaligned_emulation_finish(void);
@@ -76,7 +79,7 @@ static inline bool unaligned_ctl_available(void)
 }
 #endif
 
-bool check_vector_unaligned_access_emulated_all_cpus(void);
+bool __init check_vector_unaligned_access_emulated_all_cpus(void);
 #if defined(CONFIG_RISCV_VECTOR_MISALIGNED)
 void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused);
 DECLARE_PER_CPU(long, vector_misaligned_access);
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index c4721ce44ca4..d627f63ee289 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -79,7 +79,6 @@ struct dyn_arch_ftrace {
 #define AUIPC_RA		(0x00000097)
 #define JALR_T0			(0x000282e7)
 #define AUIPC_T0		(0x00000297)
-#define NOP4			(0x00000013)
 
 #define to_jalr_t0(offset)						\
 	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
@@ -92,7 +91,7 @@ struct dyn_arch_ftrace {
 #define make_call_t0(caller, callee, call)				\
 do {									\
 	unsigned int offset =						\
-		(unsigned long) callee - (unsigned long) caller;	\
+		(unsigned long) (callee) - (unsigned long) (caller);	\
 	call[0] = to_auipc_t0(offset);					\
 	call[1] = to_jalr_t0(offset);					\
 } while (0)
@@ -108,7 +107,7 @@ do {									\
 #define make_call_ra(caller, callee, call)				\
 do {									\
 	unsigned int offset =						\
-		(unsigned long) callee - (unsigned long) caller;	\
+		(unsigned long) (callee) - (unsigned long) (caller);	\
 	call[0] = to_auipc_ra(offset);					\
 	call[1] = to_jalr_ra(offset);					\
 } while (0)
@@ -207,7 +206,7 @@ ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs)
 {
 	struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs);
 
-	memcpy(&regs->a0, afregs->args, sizeof(afregs->args));
+	memcpy(&regs->a_regs, afregs->args, sizeof(afregs->args));
 	regs->epc = afregs->epc;
 	regs->ra = afregs->ra;
 	regs->sp = afregs->sp;
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 72be100afa23..90c86b115e00 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
 		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
 	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
-	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
 	: "memory");
 	__disable_user_access();
 
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index faf3624d8057..446126497768 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 869da082252a..e3cbf203cdde 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -100,6 +100,11 @@
 #define RISCV_ISA_EXT_ZICCRSE		91
 #define RISCV_ISA_EXT_SVADE		92
 #define RISCV_ISA_EXT_SVADU		93
+#define RISCV_ISA_EXT_ZFBFMIN		94
+#define RISCV_ISA_EXT_ZVFBFMIN		95
+#define RISCV_ISA_EXT_ZVFBFWMA		96
+#define RISCV_ISA_EXT_ZAAMO		97
+#define RISCV_ISA_EXT_ZALRSC		98
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index dd624523981c..1f690fea0e03 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 11
+#define RISCV_HWPROBE_MAX_KEY 12
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index 9a913010cdd9..71060a2f838e 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -199,5 +199,8 @@
 #define RISCV_PAUSE	".4byte 0x100000f"
 #define ZAWRS_WRS_NTO	".4byte 0x00d00073"
 #define ZAWRS_WRS_STO	".4byte 0x01d00073"
+#define RISCV_NOP4	".4byte 0x00000013"
+
+#define RISCV_INSN_NOP4	_AC(0x00000013, U)
 
 #endif /* __ASM_INSN_DEF_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1c5c641075d2..a0e51840b9db 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -136,8 +136,8 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
 #include <asm-generic/io.h>
 
 #ifdef CONFIG_MMU
-#define arch_memremap_wb(addr, size)	\
-	((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL))
+#define arch_memremap_wb(addr, size, flags)	\
+	((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL)))
 #endif
 
 #endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 46677daf708b..cc11c4544cff 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,16 +19,9 @@
 
 #ifndef	__ASSEMBLY__
 
+void arch_kgdb_breakpoint(void);
 extern unsigned long kgdb_compiled_break;
 
-static inline void arch_kgdb_breakpoint(void)
-{
-	asm(".global kgdb_compiled_break\n"
-	    ".option norvc\n"
-	    "kgdb_compiled_break: ebreak\n"
-	    ".option rvc\n");
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #define DBG_REG_ZERO "zero"
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index cc33e35cd628..0e9c2fab6378 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -301,8 +301,6 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
 	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
 }
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 125f5ecd9565..572a141ddecd 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -24,21 +24,22 @@
  * When not using MMU this corresponds to the first free page in
  * physical memory (aligned on a page boundary).
  */
-#ifdef CONFIG_64BIT
 #ifdef CONFIG_MMU
-#define PAGE_OFFSET		kernel_map.page_offset
-#else
-#define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
-#endif
-/*
- * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so
- * define the PAGE_OFFSET value for SV48 and SV39.
- */
+#ifdef CONFIG_64BIT
+#define PAGE_OFFSET_L5		_AC(0xff60000000000000, UL)
 #define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
 #define PAGE_OFFSET_L3		_AC(0xffffffd600000000, UL)
+#ifdef CONFIG_XIP_KERNEL
+#define PAGE_OFFSET		PAGE_OFFSET_L3
 #else
-#define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#define PAGE_OFFSET		kernel_map.page_offset
+#endif /* CONFIG_XIP_KERNEL */
+#else
+#define PAGE_OFFSET		_AC(0xc0000000, UL)
 #endif /* CONFIG_64BIT */
+#else
+#define PAGE_OFFSET		((unsigned long)phys_ram_base)
+#endif /* CONFIG_MMU */
 
 #ifndef __ASSEMBLY__
 
@@ -95,14 +96,9 @@ typedef struct page *pgtable_t;
 #define MIN_MEMBLOCK_ADDR      0
 #endif
 
-#ifdef CONFIG_MMU
 #define ARCH_PFN_OFFSET		(PFN_DOWN((unsigned long)phys_ram_base))
-#else
-#define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
-#endif /* CONFIG_MMU */
 
 struct kernel_mapping {
-	unsigned long page_offset;
 	unsigned long virt_addr;
 	unsigned long virt_offset;
 	uintptr_t phys_addr;
@@ -116,6 +112,7 @@ struct kernel_mapping {
 	uintptr_t xiprom;
 	uintptr_t xiprom_sz;
 #else
+	unsigned long page_offset;
 	unsigned long va_kernel_pa_offset;
 #endif
 };
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index 3e2aebea6312..770ce18a7328 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -15,24 +15,6 @@
 #define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
-/*
- * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
- * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
- * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
- * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
- * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
- * for more details.
- */
-static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
-{
-	if (riscv_use_sbi_for_rfence()) {
-		tlb_remove_ptdesc(tlb, pt);
-	} else {
-		pagetable_dtor(pt);
-		tlb_remove_page_ptdesc(tlb, pt);
-	}
-}
-
 static inline void pmd_populate_kernel(struct mm_struct *mm,
 	pmd_t *pmd, pte_t *pte)
 {
@@ -108,14 +90,14 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				  unsigned long addr)
 {
 	if (pgtable_l4_enabled)
-		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
+		tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				  unsigned long addr)
 {
 	if (pgtable_l5_enabled)
-		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
+		tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
@@ -143,7 +125,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				  unsigned long addr)
 {
-	riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -151,7 +133,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
-	riscv_tlb_remove_ptdesc(tlb, page_ptdesc(pte));
+	tlb_remove_ptdesc(tlb, page_ptdesc(pte));
 }
 #endif /* CONFIG_MMU */
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 050fdc49b5ad..428e48e5f57d 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -12,7 +12,11 @@
 #include <asm/pgtable-bits.h>
 
 #ifndef CONFIG_MMU
-#define KERNEL_LINK_ADDR	PAGE_OFFSET
+#ifdef CONFIG_RELOCATABLE
+#define KERNEL_LINK_ADDR	UL(0)
+#else
+#define KERNEL_LINK_ADDR	_AC(CONFIG_PHYS_RAM_BASE, UL)
+#endif
 #define KERN_VIRT_SIZE		(UL(-1))
 #else
 
@@ -341,6 +345,14 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 
 #define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
 
+#define pte_pgprot pte_pgprot
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
 static inline int pte_present(pte_t pte)
 {
 	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
@@ -674,6 +686,11 @@ static inline pmd_t pte_pmd(pte_t pte)
 	return __pmd(pte_val(pte));
 }
 
+static inline pud_t pte_pud(pte_t pte)
+{
+	return __pud(pte_val(pte));
+}
+
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
 	return pmd;
@@ -699,6 +716,18 @@ static inline unsigned long pud_pfn(pud_t pud)
 	return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT);
 }
 
+#define pmd_pgprot pmd_pgprot
+static inline pgprot_t pmd_pgprot(pmd_t pmd)
+{
+	return pte_pgprot(pmd_pte(pmd));
+}
+
+#define pud_pgprot pud_pgprot
+static inline pgprot_t pud_pgprot(pud_t pud)
+{
+	return pte_pgprot(pud_pte(pud));
+}
+
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
 	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
@@ -768,6 +797,30 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
 }
 
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+static inline bool pmd_special(pmd_t pmd)
+{
+	return pte_special(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+	return pte_pmd(pte_mkspecial(pmd_pte(pmd)));
+}
+#endif
+
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+static inline bool pud_special(pud_t pud)
+{
+	return pte_special(pud_pte(pud));
+}
+
+static inline pud_t pud_mkspecial(pud_t pud)
+{
+	return pte_pud(pte_mkspecial(pud_pte(pud)));
+}
+#endif
+
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index b5b0adcc85c1..2910231977cb 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -23,14 +23,16 @@ struct pt_regs {
 	unsigned long t2;
 	unsigned long s0;
 	unsigned long s1;
-	unsigned long a0;
-	unsigned long a1;
-	unsigned long a2;
-	unsigned long a3;
-	unsigned long a4;
-	unsigned long a5;
-	unsigned long a6;
-	unsigned long a7;
+	struct_group(a_regs,
+		unsigned long a0;
+		unsigned long a1;
+		unsigned long a2;
+		unsigned long a3;
+		unsigned long a4;
+		unsigned long a5;
+		unsigned long a6;
+		unsigned long a7;
+	);
 	unsigned long s2;
 	unsigned long s3;
 	unsigned long s4;
diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
new file mode 100644
index 000000000000..451fd76b8811
--- /dev/null
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_RUNTIME_CONST_H
+#define _ASM_RISCV_RUNTIME_CONST_H
+
+#include <asm/asm.h>
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/insn-def.h>
+#include <linux/memory.h>
+#include <asm/text-patching.h>
+
+#include <linux/uaccess.h>
+
+#ifdef CONFIG_32BIT
+#define runtime_const_ptr(sym)					\
+({								\
+	typeof(sym) __ret;					\
+	asm_inline(".option push\n\t"				\
+		".option norvc\n\t"				\
+		"1:\t"						\
+		"lui	%[__ret],0x89abd\n\t"			\
+		"addi	%[__ret],%[__ret],-0x211\n\t"		\
+		".option pop\n\t"				\
+		".pushsection runtime_ptr_" #sym ",\"a\"\n\t"	\
+		".long 1b - .\n\t"				\
+		".popsection"					\
+		: [__ret] "=r" (__ret));			\
+	__ret;							\
+})
+#else
+/*
+ * Loading 64-bit constants into a register from immediates is a non-trivial
+ * task on riscv64. To get it somewhat performant, load 32 bits into two
+ * different registers and then combine the results.
+ *
+ * If the processor supports the Zbkb extension, we can combine the final
+ * "slli,slli,srli,add" into the single "pack" instruction. If the processor
+ * doesn't support Zbkb but does support the Zbb extension, we can
+ * combine the final "slli,srli,add" into one instruction "add.uw".
+ */
+#define RISCV_RUNTIME_CONST_64_PREAMBLE				\
+	".option push\n\t"					\
+	".option norvc\n\t"					\
+	"1:\t"							\
+	"lui	%[__ret],0x89abd\n\t"				\
+	"lui	%[__tmp],0x1234\n\t"				\
+	"addiw	%[__ret],%[__ret],-0x211\n\t"			\
+	"addiw	%[__tmp],%[__tmp],0x567\n\t"			\
+
+#define RISCV_RUNTIME_CONST_64_BASE				\
+	"slli	%[__tmp],%[__tmp],32\n\t"			\
+	"slli	%[__ret],%[__ret],32\n\t"			\
+	"srli	%[__ret],%[__ret],32\n\t"			\
+	"add	%[__ret],%[__ret],%[__tmp]\n\t"			\
+
+#define RISCV_RUNTIME_CONST_64_ZBA				\
+	".option push\n\t"					\
+	".option arch,+zba\n\t"					\
+	".option norvc\n\t"					\
+	"slli	%[__tmp],%[__tmp],32\n\t"			\
+	"add.uw %[__ret],%[__ret],%[__tmp]\n\t"			\
+	"nop\n\t"						\
+	"nop\n\t"						\
+	".option pop\n\t"					\
+
+#define RISCV_RUNTIME_CONST_64_ZBKB				\
+	".option push\n\t"					\
+	".option arch,+zbkb\n\t"				\
+	".option norvc\n\t"					\
+	"pack	%[__ret],%[__ret],%[__tmp]\n\t"			\
+	"nop\n\t"						\
+	"nop\n\t"						\
+	"nop\n\t"						\
+	".option pop\n\t"					\
+
+#define RISCV_RUNTIME_CONST_64_POSTAMBLE(sym)			\
+	".option pop\n\t"					\
+	".pushsection runtime_ptr_" #sym ",\"a\"\n\t"		\
+	".long 1b - .\n\t"					\
+	".popsection"						\
+
+#if defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA)	\
+	&& defined(CONFIG_RISCV_ISA_ZBKB)
+#define runtime_const_ptr(sym)						\
+({									\
+	typeof(sym) __ret, __tmp;					\
+	asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE			\
+		ALTERNATIVE_2(						\
+			RISCV_RUNTIME_CONST_64_BASE,			\
+			RISCV_RUNTIME_CONST_64_ZBA,			\
+			0, RISCV_ISA_EXT_ZBA, 1,			\
+			RISCV_RUNTIME_CONST_64_ZBKB,			\
+			0, RISCV_ISA_EXT_ZBKB, 1			\
+		)							\
+		RISCV_RUNTIME_CONST_64_POSTAMBLE(sym)			\
+		: [__ret] "=r" (__ret), [__tmp] "=r" (__tmp));		\
+	__ret;								\
+})
+#elif defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA)
+#define runtime_const_ptr(sym)						\
+({									\
+	typeof(sym) __ret, __tmp;					\
+	asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE			\
+		ALTERNATIVE(						\
+			RISCV_RUNTIME_CONST_64_BASE,			\
+			RISCV_RUNTIME_CONST_64_ZBA,			\
+			0, RISCV_ISA_EXT_ZBA, 1				\
+		)							\
+		RISCV_RUNTIME_CONST_64_POSTAMBLE(sym)			\
+		: [__ret] "=r" (__ret), [__tmp] "=r" (__tmp));		\
+	__ret;								\
+})
+#elif defined(CONFIG_RISCV_ISA_ZBKB)
+#define runtime_const_ptr(sym)						\
+({									\
+	typeof(sym) __ret, __tmp;					\
+	asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE			\
+		ALTERNATIVE(						\
+			RISCV_RUNTIME_CONST_64_BASE,			\
+			RISCV_RUNTIME_CONST_64_ZBKB,			\
+			0, RISCV_ISA_EXT_ZBKB, 1			\
+		)							\
+		RISCV_RUNTIME_CONST_64_POSTAMBLE(sym)			\
+		: [__ret] "=r" (__ret), [__tmp] "=r" (__tmp));		\
+	__ret;								\
+})
+#else
+#define runtime_const_ptr(sym)						\
+({									\
+	typeof(sym) __ret, __tmp;					\
+	asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE			\
+		RISCV_RUNTIME_CONST_64_BASE				\
+		RISCV_RUNTIME_CONST_64_POSTAMBLE(sym)			\
+		: [__ret] "=r" (__ret), [__tmp] "=r" (__tmp));		\
+	__ret;								\
+})
+#endif
+#endif
+
+#define runtime_const_shift_right_32(val, sym)			\
+({								\
+	u32 __ret;						\
+	asm_inline(".option push\n\t"				\
+		".option norvc\n\t"				\
+		"1:\t"						\
+		SRLI " %[__ret],%[__val],12\n\t"		\
+		".option pop\n\t"				\
+		".pushsection runtime_shift_" #sym ",\"a\"\n\t"	\
+		".long 1b - .\n\t"				\
+		".popsection"					\
+		: [__ret] "=r" (__ret)				\
+		: [__val] "r" (val));				\
+	__ret;							\
+})
+
+#define runtime_const_init(type, sym) do {			\
+	extern s32 __start_runtime_##type##_##sym[];		\
+	extern s32 __stop_runtime_##type##_##sym[];		\
+								\
+	runtime_const_fixup(__runtime_fixup_##type,		\
+			    (unsigned long)(sym),		\
+			    __start_runtime_##type##_##sym,	\
+			    __stop_runtime_##type##_##sym);	\
+} while (0)
+
+static inline void __runtime_fixup_caches(void *where, unsigned int insns)
+{
+	/* On riscv there are currently only cache-wide flushes so va is ignored. */
+	__always_unused uintptr_t va = (uintptr_t)where;
+
+	flush_icache_range(va, va + 4 * insns);
+}
+
+/*
+ * The 32-bit immediate is stored in a lui+addi pairing.
+ * lui holds the upper 20 bits of the immediate in the first 20 bits of the instruction.
+ * addi holds the lower 12 bits of the immediate in the first 12 bits of the instruction.
+ */
+static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, unsigned int val)
+{
+	unsigned int lower_immediate, upper_immediate;
+	u32 lui_insn, addi_insn, addi_insn_mask;
+	__le32 lui_res, addi_res;
+
+	/* Mask out upper 12 bit of addi */
+	addi_insn_mask = 0x000fffff;
+
+	lui_insn = (u32)le16_to_cpu(lui_parcel[0]) | (u32)le16_to_cpu(lui_parcel[1]) << 16;
+	addi_insn = (u32)le16_to_cpu(addi_parcel[0]) | (u32)le16_to_cpu(addi_parcel[1]) << 16;
+
+	lower_immediate = sign_extend32(val, 11);
+	upper_immediate = (val - lower_immediate);
+
+	if (upper_immediate & 0xfffff000) {
+		/* replace upper 20 bits of lui with upper immediate */
+		lui_insn &= 0x00000fff;
+		lui_insn |= upper_immediate & 0xfffff000;
+	} else {
+		/* replace lui with nop if immediate is small enough to fit in addi */
+		lui_insn = RISCV_INSN_NOP4;
+		/*
+		 * lui is being skipped, so do a load instead of an add. A load
+		 * is performed by adding with the x0 register. Setting rs to
+		 * zero with the following mask will accomplish this goal.
+		 */
+		addi_insn_mask &= 0x07fff;
+	}
+
+	if (lower_immediate & 0x00000fff) {
+		/* replace upper 12 bits of addi with lower 12 bits of val */
+		addi_insn &= addi_insn_mask;
+		addi_insn |= (lower_immediate & 0x00000fff) << 20;
+	} else {
+		/* replace addi with nop if lower_immediate is empty */
+		addi_insn = RISCV_INSN_NOP4;
+	}
+
+	addi_res = cpu_to_le32(addi_insn);
+	lui_res = cpu_to_le32(lui_insn);
+	mutex_lock(&text_mutex);
+	patch_insn_write(addi_parcel, &addi_res, sizeof(addi_res));
+	patch_insn_write(lui_parcel, &lui_res, sizeof(lui_res));
+	mutex_unlock(&text_mutex);
+}
+
+static inline void __runtime_fixup_ptr(void *where, unsigned long val)
+{
+#ifdef CONFIG_32BIT
+		__runtime_fixup_32(where, where + 4, val);
+		__runtime_fixup_caches(where, 2);
+#else
+		__runtime_fixup_32(where, where + 8, val);
+		__runtime_fixup_32(where + 4, where + 12, val >> 32);
+		__runtime_fixup_caches(where, 4);
+#endif
+}
+
+/*
+ * Replace the least significant 5 bits of the srli/srliw immediate that is
+ * located at bits 20-24
+ */
+static inline void __runtime_fixup_shift(void *where, unsigned long val)
+{
+	__le16 *parcel = where;
+	__le32 res;
+	u32 insn;
+
+	insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16;
+
+	insn &= 0xfe0fffff;
+	insn |= (val & 0b11111) << 20;
+
+	res = cpu_to_le32(insn);
+	mutex_lock(&text_mutex);
+	patch_text_nosync(where, &res, sizeof(insn));
+	mutex_unlock(&text_mutex);
+}
+
+static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
+				       unsigned long val, s32 *start, s32 *end)
+{
+	while (start < end) {
+		fn(*start + (void *)start, val);
+		start++;
+	}
+}
+
+#endif /* _ASM_RISCV_RUNTIME_CONST_H */
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 4ffb022b097f..dc5782b5fbad 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -18,6 +18,10 @@ struct suspend_context {
 	unsigned long ie;
 #ifdef CONFIG_MMU
 	unsigned long satp;
+	unsigned long stimecmp;
+#if __riscv_xlen < 64
+	unsigned long stimecmph;
+#endif
 #endif
 };
 
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 121fff429dce..eceabf59ae48 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -62,8 +62,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 	args[0] = regs->orig_a0;
-	args++;
-	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+	args[1] = regs->a1;
+	args[2] = regs->a2;
+	args[3] = regs->a3;
+	args[4] = regs->a4;
+	args[5] = regs->a5;
 }
 
 static inline int syscall_get_arch(struct task_struct *task)
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 72e559934952..ce0dd0fed764 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -60,8 +60,7 @@ void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 
 bool arch_tlbbatch_should_defer(struct mm_struct *mm);
 void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-			       struct mm_struct *mm,
-			       unsigned long uaddr);
+		struct mm_struct *mm, unsigned long start, unsigned long end);
 void arch_flush_tlb_batched_pending(struct mm_struct *mm);
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index f891478829a5..c130d8100232 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -14,7 +14,7 @@
  */
 #ifdef CONFIG_MMU
 
-#define __VVAR_PAGES    2
+#define __VDSO_PAGES    4
 
 #ifndef __ASSEMBLY__
 #include <generated/vdso-offsets.h>
diff --git a/arch/riscv/include/asm/vdso/time_data.h b/arch/riscv/include/asm/vdso/arch_data.h
index dfa65228999b..da57a3786f7a 100644
--- a/arch/riscv/include/asm/vdso/time_data.h
+++ b/arch/riscv/include/asm/vdso/arch_data.h
@@ -1,12 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __RISCV_ASM_VDSO_TIME_DATA_H
-#define __RISCV_ASM_VDSO_TIME_DATA_H
+#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H
+#define __RISCV_ASM_VDSO_ARCH_DATA_H
 
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <asm/hwprobe.h>
 
-struct arch_vdso_time_data {
+struct vdso_arch_data {
 	/* Stash static answers to the hwprobe queries when all CPUs are selected. */
 	__u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1];
 
@@ -14,4 +14,4 @@ struct arch_vdso_time_data {
 	__u8 homogeneous_cpus;
 };
 
-#endif /* __RISCV_ASM_VDSO_TIME_DATA_H */
+#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index ba3283cf7acc..29164f84f93c 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -69,7 +69,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 #endif /* CONFIG_GENERIC_TIME_VSYSCALL */
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	/*
 	 * The purpose of csr_read(CSR_TIME) is to trap the system into
@@ -79,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return csr_read(CSR_TIME);
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h
index e8a9c4b53c0c..1140b54b4bc8 100644
--- a/arch/riscv/include/asm/vdso/vsyscall.h
+++ b/arch/riscv/include/asm/vdso/vsyscall.h
@@ -6,15 +6,6 @@
 
 #include <vdso/datapage.h>
 
-extern struct vdso_data *vdso_data;
-
-static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-
-#define __arch_get_k_vdso_data __riscv_get_k_vdso_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index c3c1cc951cb9..3c2fce939673 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -73,6 +73,14 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZCMOP		(1ULL << 47)
 #define		RISCV_HWPROBE_EXT_ZAWRS		(1ULL << 48)
 #define		RISCV_HWPROBE_EXT_SUPM		(1ULL << 49)
+#define		RISCV_HWPROBE_EXT_ZICNTR	(1ULL << 50)
+#define		RISCV_HWPROBE_EXT_ZIHPM		(1ULL << 51)
+#define		RISCV_HWPROBE_EXT_ZFBFMIN	(1ULL << 52)
+#define		RISCV_HWPROBE_EXT_ZVFBFMIN	(1ULL << 53)
+#define		RISCV_HWPROBE_EXT_ZVFBFWMA	(1ULL << 54)
+#define		RISCV_HWPROBE_EXT_ZICBOM	(1ULL << 55)
+#define		RISCV_HWPROBE_EXT_ZAAMO		(1ULL << 56)
+#define		RISCV_HWPROBE_EXT_ZALRSC	(1ULL << 57)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -95,6 +103,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
 #define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0	11
+#define RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE	12
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index f06bc5efcd79..5f59fd226cc5 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -182,6 +182,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_SVVPTC,
 	KVM_RISCV_ISA_EXT_ZABHA,
 	KVM_RISCV_ISA_EXT_ZICCRSE,
+	KVM_RISCV_ISA_EXT_ZAAMO,
+	KVM_RISCV_ISA_EXT_ZALRSC,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 8d186bfced45..f7480c9c6f8d 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
-CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c
index 2fd29695a788..3f6d5a6789e8 100644
--- a/arch/riscv/kernel/acpi.c
+++ b/arch/riscv/kernel/acpi.c
@@ -305,7 +305,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		}
 	}
 
-	return ioremap_prot(phys, size, pgprot_val(prot));
+	return ioremap_prot(phys, size, prot);
 }
 
 #ifdef CONFIG_PCI
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index e89455a6a0e5..16490755304e 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -36,7 +36,6 @@ void asm_offsets(void)
 	OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
 
 	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
-	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
 	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 2d40736fc37c..26b085dbdd07 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -108,11 +108,11 @@ int populate_cache_leaves(unsigned int cpu)
 	if (!np)
 		return -ENOENT;
 
-	if (of_property_read_bool(np, "cache-size"))
+	if (of_property_present(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-	if (of_property_read_bool(np, "i-cache-size"))
+	if (of_property_present(np, "i-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-	if (of_property_read_bool(np, "d-cache-size"))
+	if (of_property_present(np, "d-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
@@ -125,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu)
 			break;
 		if (level <= levels)
 			break;
-		if (of_property_read_bool(np, "cache-size"))
+		if (of_property_present(np, "cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-		if (of_property_read_bool(np, "i-cache-size"))
+		if (of_property_present(np, "i-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-		if (of_property_read_bool(np, "d-cache-size"))
+		if (of_property_present(np, "d-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c6ba750536c3..2054f6c4b0ae 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -32,6 +32,7 @@
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
 static bool any_cpu_has_zicboz;
+static bool any_cpu_has_zicbom;
 
 unsigned long elf_hwcap __read_mostly;
 
@@ -53,9 +54,7 @@ u32 thead_vlenb_of;
  */
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
 {
-	if (!isa_bitmap)
-		return riscv_isa[0];
-	return isa_bitmap[0];
+	return !isa_bitmap ? riscv_isa[0] : isa_bitmap[0];
 }
 EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
 
@@ -76,10 +75,19 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned i
 	if (bit >= RISCV_ISA_EXT_MAX)
 		return false;
 
-	return test_bit(bit, bmap) ? true : false;
+	return test_bit(bit, bmap);
 }
 EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
 
+static int riscv_ext_f_depends(const struct riscv_isa_ext_data *data,
+			       const unsigned long *isa_bitmap)
+{
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_f))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
 static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data,
 				     const unsigned long *isa_bitmap)
 {
@@ -91,6 +99,8 @@ static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data,
 		pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n");
 		return -EINVAL;
 	}
+
+	any_cpu_has_zicbom = true;
 	return 0;
 }
 
@@ -109,6 +119,82 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static int riscv_ext_f_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	/*
+	 * Due to extension ordering, d is checked before f, so no deferral
+	 * is required.
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d)) {
+		pr_warn_once("This kernel does not support systems with F but not D\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int riscv_ext_d_validate(const struct riscv_isa_ext_data *data,
+				const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_x_validate(const struct riscv_isa_ext_data *data,
+				       const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_float_validate(const struct riscv_isa_ext_data *data,
+					   const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	if (!IS_ENABLED(CONFIG_FPU))
+		return -EINVAL;
+
+	/*
+	 * The kernel doesn't support systems that don't implement both of
+	 * F and D, so if any of the vector extensions that do floating point
+	 * are to be usable, both floating point extensions need to be usable.
+	 *
+	 * Since this function validates vector only, and v/Zve* are probed
+	 * after f/d, there's no need for a deferral here.
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int riscv_ext_vector_crypto_validate(const struct riscv_isa_ext_data *data,
+					    const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	/*
+	 * It isn't the kernel's job to check that the binding is correct, so
+	 * it should be enough to check that any of the vector extensions are
+	 * enabled, which in-turn means that vector is usable in this kernel
+	 */
+	if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32X))
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 static int riscv_ext_zca_depends(const struct riscv_isa_ext_data *data,
 				 const unsigned long *isa_bitmap)
 {
@@ -140,6 +226,28 @@ static int riscv_ext_zcf_validate(const struct riscv_isa_ext_data *data,
 	return -EPROBE_DEFER;
 }
 
+static int riscv_vector_f_validate(const struct riscv_isa_ext_data *data,
+				   const unsigned long *isa_bitmap)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
+		return -EINVAL;
+
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32F))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
+static int riscv_ext_zvfbfwma_validate(const struct riscv_isa_ext_data *data,
+				       const unsigned long *isa_bitmap)
+{
+	if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZFBFMIN) &&
+	    __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVFBFMIN))
+		return 0;
+
+	return -EPROBE_DEFER;
+}
+
 static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data,
 				    const unsigned long *isa_bitmap)
 {
@@ -150,6 +258,11 @@ static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static const unsigned int riscv_a_exts[] = {
+	RISCV_ISA_EXT_ZAAMO,
+	RISCV_ISA_EXT_ZALRSC,
+};
+
 static const unsigned int riscv_zk_bundled_exts[] = {
 	RISCV_ISA_EXT_ZBKB,
 	RISCV_ISA_EXT_ZBKC,
@@ -321,17 +434,15 @@ static const unsigned int riscv_c_exts[] = {
 const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i),
 	__RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m),
-	__RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a),
-	__RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f),
-	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
+	__RISCV_ISA_EXT_SUPERSET(a, RISCV_ISA_EXT_a, riscv_a_exts),
+	__RISCV_ISA_EXT_DATA_VALIDATE(f, RISCV_ISA_EXT_f, riscv_ext_f_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(d, RISCV_ISA_EXT_d, riscv_ext_d_validate),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_SUPERSET(c, RISCV_ISA_EXT_c, riscv_c_exts),
-	__RISCV_ISA_EXT_SUPERSET(v, RISCV_ISA_EXT_v, riscv_v_exts),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(v, RISCV_ISA_EXT_v, riscv_v_exts, riscv_ext_vector_float_validate),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
-	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts,
-					  riscv_ext_zicbom_validate),
-	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts,
-					  riscv_ext_zicboz_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, riscv_ext_zicbom_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, riscv_ext_zicboz_validate),
 	__RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
@@ -341,10 +452,13 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zimop, RISCV_ISA_EXT_ZIMOP),
+	__RISCV_ISA_EXT_DATA(zaamo, RISCV_ISA_EXT_ZAAMO),
 	__RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
 	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zalrsc, RISCV_ISA_EXT_ZALRSC),
 	__RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
 	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA),
@@ -370,29 +484,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
 	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
 	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
-	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
-	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
-	__RISCV_ISA_EXT_SUPERSET(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts),
-	__RISCV_ISA_EXT_DATA(zve32x, RISCV_ISA_EXT_ZVE32X),
-	__RISCV_ISA_EXT_SUPERSET(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts),
-	__RISCV_ISA_EXT_SUPERSET(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts),
-	__RISCV_ISA_EXT_SUPERSET(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvbc, RISCV_ISA_EXT_ZVBC, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zve32x, RISCV_ISA_EXT_ZVE32X, riscv_ext_vector_x_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts, riscv_ext_vector_float_validate),
+	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts, riscv_ext_vector_x_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, riscv_ext_zvfbfwma_validate),
 	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
 	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
-	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
-	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
-	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
-	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
-	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
-	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
-	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
-	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
-	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
-	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
-	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkb, RISCV_ISA_EXT_ZVKB, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkg, RISCV_ISA_EXT_ZVKG, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkn, riscv_zvkn_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvknc, riscv_zvknc_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkned, RISCV_ISA_EXT_ZVKNED, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkng, riscv_zvkng_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvknha, RISCV_ISA_EXT_ZVKNHA, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvknhb, RISCV_ISA_EXT_ZVKNHB, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvks, riscv_zvks_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksc, riscv_zvksc_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvksed, RISCV_ISA_EXT_ZVKSED, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvksh, RISCV_ISA_EXT_ZVKSH, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksg, riscv_zvksg_bundled_exts, riscv_ext_vector_crypto_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zvkt, RISCV_ISA_EXT_ZVKT, riscv_ext_vector_crypto_validate),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smmpm, RISCV_ISA_EXT_SMMPM),
 	__RISCV_ISA_EXT_SUPERSET(smnpm, RISCV_ISA_EXT_SMNPM, riscv_xlinuxenvcfg_exts),
@@ -479,7 +595,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa,
 			if (bit < RISCV_ISA_EXT_BASE)
 				*this_hwcap |= isa2hwcap[bit];
 		}
-	} while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa)));
+	} while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX));
 }
 
 static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap)
@@ -960,16 +1076,6 @@ void __init riscv_fill_hwcap(void)
 		riscv_v_setup_vsize();
 	}
 
-	if (elf_hwcap & COMPAT_HWCAP_ISA_V) {
-		/*
-		 * ISA string in device tree might have 'v' flag, but
-		 * CONFIG_RISCV_ISA_V is disabled in kernel.
-		 * Clear V flag in elf_hwcap if CONFIG_RISCV_ISA_V is disabled.
-		 */
-		if (!IS_ENABLED(CONFIG_RISCV_ISA_V))
-			elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
-	}
-
 	memset(print_str, 0, sizeof(print_str));
 	for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++)
 		if (riscv_isa[0] & BIT_MASK(i))
@@ -1001,6 +1107,11 @@ void __init riscv_user_isa_enable(void)
 		current->thread.envcfg |= ENVCFG_CBZE;
 	else if (any_cpu_has_zicboz)
 		pr_warn("Zicboz disabled as it is unavailable on some harts\n");
+
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOM))
+		current->thread.envcfg |= ENVCFG_CBCFE;
+	else if (any_cpu_has_zicbom)
+		pr_warn("Zicbom disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index 3c37661801f9..e783a72d051f 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -468,6 +468,9 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		case R_RISCV_ALIGN:
 		case R_RISCV_RELAX:
 			break;
+		case R_RISCV_64:
+			*(u64 *)loc = val;
+			break;
 		default:
 			pr_err("Unknown rela relocation: %d\n", r_type);
 			return -ENOEXEC;
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 33a5a9f2a0d4..0fb338000c6d 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -319,17 +319,21 @@ SYM_CODE_END(handle_kernel_stack_overflow)
 ASM_NOKPROBE(handle_kernel_stack_overflow)
 #endif
 
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_kernel_asm)
+	call schedule_tail
+	move a0, s1 /* fn_arg */
+	move a1, s0 /* fn */
+	move a2, sp /* pt_regs */
+	call ret_from_fork_kernel
+	j ret_from_exception
+SYM_CODE_END(ret_from_fork_kernel_asm)
+
+SYM_CODE_START(ret_from_fork_user_asm)
 	call schedule_tail
-	beqz s0, 1f	/* not from kernel thread */
-	/* Call fn(arg) */
-	move a0, s1
-	jalr s0
-1:
 	move a0, sp /* pt_regs */
-	call syscall_exit_to_user_mode
+	call ret_from_fork_user
 	j ret_from_exception
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_user_asm)
 
 #ifdef CONFIG_IRQ_STACKS
 /*
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 3524db5e4fa0..674dcdfae7a1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -36,7 +36,7 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 				     unsigned int *expected)
 {
 	unsigned int replaced[2];
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	/* we expect nops at the hook position */
 	if (!expected)
@@ -68,7 +68,7 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 				bool enable, bool ra)
 {
 	unsigned int call[2];
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	if (ra)
 		make_call_ra(hook_pos, target, call);
@@ -97,7 +97,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
-	unsigned int nops[2] = {NOP4, NOP4};
+	unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4};
 
 	if (patch_insn_write((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
index 654ed159c830..b4c1a6a3fbd2 100644
--- a/arch/riscv/kernel/jump_label.c
+++ b/arch/riscv/kernel/jump_label.c
@@ -11,8 +11,8 @@
 #include <asm/bug.h>
 #include <asm/cacheflush.h>
 #include <asm/text-patching.h>
+#include <asm/insn-def.h>
 
-#define RISCV_INSN_NOP 0x00000013U
 #define RISCV_INSN_JAL 0x0000006fU
 
 bool arch_jump_label_transform_queue(struct jump_entry *entry,
@@ -33,7 +33,7 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 			(((u32)offset & GENMASK(10,  1)) << (21 -  1)) |
 			(((u32)offset & GENMASK(20, 20)) << (31 - 20));
 	} else {
-		insn = RISCV_INSN_NOP;
+		insn = RISCV_INSN_NOP4;
 	}
 
 	if (early_boot_irqs_disabled) {
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index 2e0266ae6bd7..9f3db3503dab 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
 	regs->epc = pc;
 }
 
+noinline void arch_kgdb_breakpoint(void)
+{
+	asm(".global kgdb_compiled_break\n"
+	    "kgdb_compiled_break: ebreak\n");
+}
+
 void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer,
 				char *remcom_out_buffer)
 {
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 068168046e0e..da4a4000e57e 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -12,8 +12,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
 
-#define ABI_SIZE_ON_STACK	80
-
 	.text
 
 	.macro SAVE_ABI_STATE
@@ -28,12 +26,12 @@
 	 * register if a0 was not saved.
 	 */
 	.macro SAVE_RET_ABI_STATE
-	addi	sp, sp, -ABI_SIZE_ON_STACK
-	REG_S	ra, 1*SZREG(sp)
-	REG_S	s0, 8*SZREG(sp)
-	REG_S	a0, 10*SZREG(sp)
-	REG_S	a1, 11*SZREG(sp)
-	addi	s0, sp, ABI_SIZE_ON_STACK
+	addi	sp, sp, -FREGS_SIZE_ON_STACK
+	REG_S	ra, FREGS_RA(sp)
+	REG_S	s0, FREGS_S0(sp)
+	REG_S	a0, FREGS_A0(sp)
+	REG_S	a1, FREGS_A1(sp)
+	addi	s0, sp, FREGS_SIZE_ON_STACK
 	.endm
 
 	.macro RESTORE_ABI_STATE
@@ -43,11 +41,11 @@
 	.endm
 
 	.macro RESTORE_RET_ABI_STATE
-	REG_L	ra, 1*SZREG(sp)
-	REG_L	s0, 8*SZREG(sp)
-	REG_L	a0, 10*SZREG(sp)
-	REG_L	a1, 11*SZREG(sp)
-	addi	sp, sp, ABI_SIZE_ON_STACK
+	REG_L	ra, FREGS_RA(sp)
+	REG_L	s0, FREGS_S0(sp)
+	REG_L	a0, FREGS_A0(sp)
+	REG_L	a1, FREGS_A1(sp)
+	addi	sp, sp, FREGS_SIZE_ON_STACK
 	.endm
 
 SYM_TYPED_FUNC_START(ftrace_stub)
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index e264e59e596e..91d0b355ceef 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -73,16 +73,17 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int type, i;
-
-	for (i = 0; i < num; i++) {
-		type = ELF_RISCV_R_TYPE(relas[i].r_info);
-		if (type == R_RISCV_CALL_PLT) {
+	for (int i = 0; i < num; i++) {
+		switch (ELF_R_TYPE(relas[i].r_info)) {
+		case R_RISCV_CALL_PLT:
+		case R_RISCV_PLT32:
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
-		} else if (type == R_RISCV_GOT_HI20) {
+			break;
+		case R_RISCV_GOT_HI20:
 			if (!duplicate_rela(relas, i))
 				(*gots)++;
+			break;
 		}
 	}
 }
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 47d0ebeec93c..7f6147c18033 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me,
 		kfree(bucket_iter);
 	}
 
-	kfree(*relocation_hashtable);
+	kvfree(*relocation_hashtable);
 }
 
 static int add_relocation_to_accumulate(struct module *me, int type,
@@ -752,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations,
 
 	hashtable_size <<= should_double_size;
 
-	*relocation_hashtable = kmalloc_array(hashtable_size,
-					      sizeof(**relocation_hashtable),
-					      GFP_KERNEL);
+	/* Number of relocations may be large, so kvmalloc it */
+	*relocation_hashtable = kvmalloc_array(hashtable_size,
+					       sizeof(**relocation_hashtable),
+					       GFP_KERNEL);
 	if (!*relocation_hashtable)
 		return 0;
 
@@ -859,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 				}
 
 				j++;
-				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+				if (j == num_relocations)
 					j = 0;
 
 			} while (j_idx != j);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8beaf77..cc15f7ca6cc1 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 	/* Initialize the slot */
 	void *kaddr = kmap_atomic(page);
 	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+	unsigned long start = (unsigned long)dst;
 
 	memcpy(dst, src, len);
 
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
 	}
 
+	flush_icache_range(start, start + len);
 	kunmap_atomic(kaddr);
-
-	/*
-	 * We probably need flush_icache_user_page() but it needs vma.
-	 * This should work on most of architectures by default. If
-	 * architecture needs to do something different it can define
-	 * its own version of the function.
-	 */
-	flush_dcache_page(page);
 }
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 7c244de77180..bbf7ec6a75c0 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -17,7 +17,9 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/personality.h>
+#include <linux/entry-common.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/csr.h>
@@ -36,7 +38,8 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_fork_kernel_asm(void);
+extern asmlinkage void ret_from_fork_user_asm(void);
 
 void noinstr arch_cpu_idle(void)
 {
@@ -206,6 +209,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs)
+{
+	fn(fn_arg);
+
+	syscall_exit_to_user_mode(regs);
+}
+
+asmlinkage void ret_from_fork_user(struct pt_regs *regs)
+{
+	syscall_exit_to_user_mode(regs);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -228,6 +243,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 		p->thread.s[0] = (unsigned long)args->fn;
 		p->thread.s[1] = (unsigned long)args->fn_arg;
+		p->thread.ra = (unsigned long)ret_from_fork_kernel_asm;
 	} else {
 		*childregs = *(current_pt_regs());
 		/* Turn off status.VS */
@@ -237,12 +253,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		if (clone_flags & CLONE_SETTLS)
 			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
-		p->thread.s[0] = 0;
+		p->thread.ra = (unsigned long)ret_from_fork_user_asm;
 	}
 	p->thread.riscv_v_flags = 0;
 	if (has_vector() || has_xtheadvector())
 		riscv_v_thread_alloc(p);
-	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
@@ -275,6 +290,9 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 	unsigned long pmm;
 	u8 pmlen;
 
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return -EINVAL;
+
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
@@ -330,6 +348,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 	struct thread_info *ti = task_thread_info(task);
 	long ret = 0;
 
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+		return -EINVAL;
+
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f1793630fc51..f7c9a1caa83e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -66,6 +66,9 @@ static struct resource bss_res = { .name = "Kernel bss", };
 static struct resource elfcorehdr_res = { .name = "ELF Core hdr", };
 #endif
 
+static int num_standard_resources;
+static struct resource *standard_resources;
+
 static int __init add_resource(struct resource *parent,
 				struct resource *res)
 {
@@ -139,7 +142,7 @@ static void __init init_resources(void)
 	struct resource *res = NULL;
 	struct resource *mem_res = NULL;
 	size_t mem_res_sz = 0;
-	int num_resources = 0, res_idx = 0;
+	int num_resources = 0, res_idx = 0, non_resv_res = 0;
 	int ret = 0;
 
 	/* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
@@ -193,6 +196,7 @@ static void __init init_resources(void)
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
 		res = &mem_res[res_idx--];
+		non_resv_res++;
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";
@@ -210,6 +214,9 @@ static void __init init_resources(void)
 			goto error;
 	}
 
+	num_standard_resources = non_resv_res;
+	standard_resources = &mem_res[res_idx + 1];
+
 	/* Clean-up any unused pre-allocated resources */
 	if (res_idx >= 0)
 		memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
@@ -221,6 +228,33 @@ static void __init init_resources(void)
 	memblock_free(mem_res, mem_res_sz);
 }
 
+static int __init reserve_memblock_reserved_regions(void)
+{
+	u64 i, j;
+
+	for (i = 0; i < num_standard_resources; i++) {
+		struct resource *mem = &standard_resources[i];
+		phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+		if (!memblock_is_region_reserved(mem->start, mem_size))
+			continue;
+
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
+			resource_size_t start, end;
+
+			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+			end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+			if (start > mem->end || end < mem->start)
+				continue;
+
+			reserve_region_with_split(mem, start, end, "Reserved");
+		}
+	}
+
+	return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
 
 static void __init parse_dtb(void)
 {
@@ -235,11 +269,6 @@ static void __init parse_dtb(void)
 	} else {
 		pr_err("No DTB passed to the kernel\n");
 	}
-
-#ifdef CONFIG_CMDLINE_FORCE
-	strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-	pr_info("Forcing kernel command line to: %s\n", boot_command_line);
-#endif
 }
 
 #if defined(CONFIG_RISCV_COMBO_SPINLOCKS)
@@ -322,8 +351,8 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
-	init_rt_signal_env();
 	apply_boot_alternatives();
+	init_rt_signal_env();
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 94e905eea1de..08378fea3a11 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -215,12 +215,6 @@ static size_t get_rt_frame_size(bool cal_all)
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
-	/*
-	 * Preserved a __riscv_ctx_hdr for END signal context header if an
-	 * extension uses __riscv_extra_ext_header
-	 */
-	if (total_context_size)
-		total_context_size += sizeof(struct __riscv_ctx_hdr);
 
 	frame_size += total_context_size;
 
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index d58b5e751286..e650dec44817 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -48,6 +48,8 @@ EXPORT_SYMBOL_GPL(__cpuid_to_hartid_map);
 void __init smp_setup_processor_id(void)
 {
 	cpuid_to_hartid_map(0) = boot_cpu_hartid;
+
+	pr_info("Booting Linux on hartid %lu\n", boot_cpu_hartid);
 }
 
 static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index e36d20205bd7..601a321e0f17 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -231,6 +231,10 @@ asmlinkage __visible void smp_callin(void)
 	riscv_ipi_enable();
 
 	numa_add_cpu(curr_cpuid);
+
+	pr_debug("CPU%u: Booted secondary hartid %lu\n", curr_cpuid,
+		cpuid_to_hartid_map(curr_cpuid));
+
 	set_cpu_online(curr_cpuid, true);
 
 	/*
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index d4355c770c36..3fe9e6edef8f 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -74,7 +74,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 						   &frame->ra);
 			if (pc >= (unsigned long)handle_exception &&
 			    pc < (unsigned long)&ret_from_exception_end) {
-				if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))
+				if (unlikely(!fn(arg, pc)))
 					break;
 
 				pc = ((struct pt_regs *)sp)->epc;
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 9a8a0dc035b2..24b3f57d467f 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -30,6 +30,13 @@ void suspend_save_csrs(struct suspend_context *context)
 	 */
 
 #ifdef CONFIG_MMU
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) {
+		context->stimecmp = csr_read(CSR_STIMECMP);
+#if __riscv_xlen < 64
+		context->stimecmph = csr_read(CSR_STIMECMPH);
+#endif
+	}
+
 	context->satp = csr_read(CSR_SATP);
 #endif
 }
@@ -43,6 +50,13 @@ void suspend_restore_csrs(struct suspend_context *context)
 	csr_write(CSR_IE, context->ie);
 
 #ifdef CONFIG_MMU
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) {
+		csr_write(CSR_STIMECMP, context->stimecmp);
+#if __riscv_xlen < 64
+		csr_write(CSR_STIMECMPH, context->stimecmph);
+#endif
+	}
+
 	csr_write(CSR_SATP, context->satp);
 #endif
 }
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index bcd3b816306c..249aec8594a9 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -95,7 +95,9 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		 * regardless of the kernel's configuration, as no other checks, besides
 		 * presence in the hart_isa bitmap, are made.
 		 */
+		EXT_KEY(ZAAMO);
 		EXT_KEY(ZACAS);
+		EXT_KEY(ZALRSC);
 		EXT_KEY(ZAWRS);
 		EXT_KEY(ZBA);
 		EXT_KEY(ZBB);
@@ -107,10 +109,13 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 		EXT_KEY(ZCA);
 		EXT_KEY(ZCB);
 		EXT_KEY(ZCMOP);
+		EXT_KEY(ZICBOM);
 		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZICNTR);
 		EXT_KEY(ZICOND);
 		EXT_KEY(ZIHINTNTL);
 		EXT_KEY(ZIHINTPAUSE);
+		EXT_KEY(ZIHPM);
 		EXT_KEY(ZIMOP);
 		EXT_KEY(ZKND);
 		EXT_KEY(ZKNE);
@@ -132,6 +137,8 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZVE64D);
 			EXT_KEY(ZVE64F);
 			EXT_KEY(ZVE64X);
+			EXT_KEY(ZVFBFMIN);
+			EXT_KEY(ZVFBFWMA);
 			EXT_KEY(ZVFH);
 			EXT_KEY(ZVFHMIN);
 			EXT_KEY(ZVKB);
@@ -148,6 +155,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 			EXT_KEY(ZCD);
 			EXT_KEY(ZCF);
 			EXT_KEY(ZFA);
+			EXT_KEY(ZFBFMIN);
 			EXT_KEY(ZFH);
 			EXT_KEY(ZFHMIN);
 		}
@@ -161,7 +169,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	pair->value &= ~missing;
 }
 
-static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
 {
 	struct riscv_hwprobe pair;
 
@@ -279,6 +287,11 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
 			pair->value = riscv_cboz_block_size;
 		break;
+	case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM))
+			pair->value = riscv_cbom_block_size;
+		break;
 	case RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS:
 		pair->value = user_max_virt_addr();
 		break;
@@ -450,8 +463,7 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
 
 static int __init init_hwprobe_vdso_data(void)
 {
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_time_data *avd = &vd->arch_data;
+	struct vdso_arch_data *avd = vdso_k_arch_data;
 	u64 id_bitsmash = 0;
 	struct riscv_hwprobe pair;
 	int key;
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 8ff8e8b36524..9c83848797a7 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
 
-asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
+enum misaligned_access_type {
+	MISALIGNED_STORE,
+	MISALIGNED_LOAD,
+};
+static const struct {
+	const char *type_str;
+	int (*handler)(struct pt_regs *regs);
+} misaligned_handler[] = {
+	[MISALIGNED_STORE] = {
+		.type_str = "Oops - store (or AMO) address misaligned",
+		.handler = handle_misaligned_store,
+	},
+	[MISALIGNED_LOAD] = {
+		.type_str = "Oops - load address misaligned",
+		.handler = handle_misaligned_load,
+	},
+};
+
+static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type)
 {
+	irqentry_state_t state;
+
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
+		local_irq_enable();
+	} else {
+		state = irqentry_nmi_enter(regs);
+	}
 
-		if (handle_misaligned_load(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-			      "Oops - load address misaligned");
+	if (misaligned_handler[type].handler(regs))
+		do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+			      misaligned_handler[type].type_str);
 
+	if (user_mode(regs)) {
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
-		irqentry_state_t state = irqentry_nmi_enter(regs);
-
-		if (handle_misaligned_load(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-			      "Oops - load address misaligned");
-
 		irqentry_nmi_exit(regs, state);
 	}
 }
 
-asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		irqentry_enter_from_user_mode(regs);
-
-		if (handle_misaligned_store(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-				"Oops - store (or AMO) address misaligned");
-
-		irqentry_exit_to_user_mode(regs);
-	} else {
-		irqentry_state_t state = irqentry_nmi_enter(regs);
-
-		if (handle_misaligned_store(regs))
-			do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
-				"Oops - store (or AMO) address misaligned");
+	do_trap_misaligned(regs, MISALIGNED_LOAD);
+}
 
-		irqentry_nmi_exit(regs, state);
-	}
+asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+{
+	do_trap_misaligned(regs, MISALIGNED_STORE);
 }
+
 DO_ERROR_INFO(do_trap_store_fault,
 	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
 DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 7cc108aed74e..77c788660223 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -88,6 +88,13 @@
 #define INSN_MATCH_C_FSWSP		0xe002
 #define INSN_MASK_C_FSWSP		0xe003
 
+#define INSN_MATCH_C_LHU		0x8400
+#define INSN_MASK_C_LHU			0xfc43
+#define INSN_MATCH_C_LH			0x8440
+#define INSN_MASK_C_LH			0xfc43
+#define INSN_MATCH_C_SH			0x8c00
+#define INSN_MASK_C_SH			0xfc43
+
 #define INSN_LEN(insn)			((((insn) & 0x3) < 0x3) ? 2 : 4)
 
 #if defined(CONFIG_64BIT)
@@ -268,7 +275,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
 	int __ret;					\
 							\
 	if (user_mode(regs)) {				\
-		__ret = __get_user(insn, (type __user *) insn_addr); \
+		__ret = get_user(insn, (type __user *) insn_addr); \
 	} else {					\
 		insn = *(type *)insn_addr;		\
 		__ret = 0;				\
@@ -431,6 +438,13 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 		fp = 1;
 		len = 4;
 #endif
+	} else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) {
+		len = 2;
+		insn = RVC_RS2S(insn) << SH_RD;
+	} else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) {
+		len = 2;
+		shift = 8 * (sizeof(ulong) - len);
+		insn = RVC_RS2S(insn) << SH_RD;
 	} else {
 		regs->epc = epc;
 		return -1;
@@ -530,6 +544,9 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
 		len = 4;
 		val.data_ulong = GET_F32_RS2C(insn, regs);
 #endif
+	} else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) {
+		len = 2;
+		val.data_ulong = GET_RS2S(insn, regs);
 	} else {
 		regs->epc = epc;
 		return -1;
@@ -605,16 +622,10 @@ void check_vector_unaligned_access_emulated(struct work_struct *work __always_un
 	kernel_vector_end();
 }
 
-bool check_vector_unaligned_access_emulated_all_cpus(void)
+bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 {
 	int cpu;
 
-	if (!has_vector()) {
-		for_each_online_cpu(cpu)
-			per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
-		return false;
-	}
-
 	schedule_on_each_cpu(check_vector_unaligned_access_emulated);
 
 	for_each_online_cpu(cpu)
@@ -625,7 +636,7 @@ bool check_vector_unaligned_access_emulated_all_cpus(void)
 	return true;
 }
 #else
-bool check_vector_unaligned_access_emulated_all_cpus(void)
+bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 {
 	return false;
 }
@@ -659,7 +670,7 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused)
 	}
 }
 
-bool check_unaligned_access_emulated_all_cpus(void)
+bool __init check_unaligned_access_emulated_all_cpus(void)
 {
 	int cpu;
 
@@ -684,7 +695,7 @@ bool unaligned_ctl_available(void)
 	return unaligned_ctl;
 }
 #else
-bool check_unaligned_access_emulated_all_cpus(void)
+bool __init check_unaligned_access_emulated_all_cpus(void)
 {
 	return false;
 }
diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c
index 91f189cf1611..b8ba13819d05 100644
--- a/arch/riscv/kernel/unaligned_access_speed.c
+++ b/arch/riscv/kernel/unaligned_access_speed.c
@@ -24,8 +24,12 @@
 DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
 DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
-#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
+static long unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN;
+static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN;
+
 static cpumask_t fast_misaligned_access;
+
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
 static int check_unaligned_access(void *param)
 {
 	int cpu = smp_processor_id();
@@ -121,7 +125,7 @@ static int check_unaligned_access(void *param)
 	return 0;
 }
 
-static void check_unaligned_access_nonboot_cpu(void *param)
+static void __init check_unaligned_access_nonboot_cpu(void *param)
 {
 	unsigned int cpu = smp_processor_id();
 	struct page **pages = param;
@@ -130,6 +134,50 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static void __init check_unaligned_access_speed_all_cpus(void)
+{
+	unsigned int cpu;
+	unsigned int cpu_count = num_possible_cpus();
+	struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL);
+
+	if (!bufs) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return;
+	}
+
+	/*
+	 * Allocate separate buffers for each CPU so there's no fighting over
+	 * cache lines.
+	 */
+	for_each_cpu(cpu, cpu_online_mask) {
+		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!bufs[cpu]) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			goto out;
+		}
+	}
+
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
+
+out:
+	for_each_cpu(cpu, cpu_online_mask) {
+		if (bufs[cpu])
+			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
+	}
+
+	kfree(bufs);
+}
+#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
+static void __init check_unaligned_access_speed_all_cpus(void)
+{
+}
+#endif
+
 DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
 
 static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
@@ -175,7 +223,7 @@ static void set_unaligned_access_static_branches(void)
 	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
 }
 
-static int lock_and_set_unaligned_access_static_branch(void)
+static int __init lock_and_set_unaligned_access_static_branch(void)
 {
 	cpus_read_lock();
 	set_unaligned_access_static_branches();
@@ -188,21 +236,29 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
 
 static int riscv_online_cpu(unsigned int cpu)
 {
-	static struct page *buf;
-
 	/* We are already set since the last check */
-	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN)
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		goto exit;
+	} else if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
 		goto exit;
-
-	check_unaligned_access_emulated(NULL);
-	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
-	if (!buf) {
-		pr_warn("Allocation failure, not measuring misaligned performance\n");
-		return -ENOMEM;
 	}
 
-	check_unaligned_access(buf);
-	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS
+	{
+		static struct page *buf;
+
+		check_unaligned_access_emulated(NULL);
+		buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!buf) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			return -ENOMEM;
+		}
+
+		check_unaligned_access(buf);
+		__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+	}
+#endif
 
 exit:
 	set_unaligned_access_static_branches();
@@ -217,59 +273,6 @@ static int riscv_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-/* Measure unaligned access speed on all CPUs present at boot in parallel. */
-static int check_unaligned_access_speed_all_cpus(void)
-{
-	unsigned int cpu;
-	unsigned int cpu_count = num_possible_cpus();
-	struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL);
-
-	if (!bufs) {
-		pr_warn("Allocation failure, not measuring misaligned performance\n");
-		return 0;
-	}
-
-	/*
-	 * Allocate separate buffers for each CPU so there's no fighting over
-	 * cache lines.
-	 */
-	for_each_cpu(cpu, cpu_online_mask) {
-		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
-		if (!bufs[cpu]) {
-			pr_warn("Allocation failure, not measuring misaligned performance\n");
-			goto out;
-		}
-	}
-
-	/* Check everybody except 0, who stays behind to tend jiffies. */
-	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
-
-	/* Check core 0. */
-	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
-
-	/*
-	 * Setup hotplug callbacks for any new CPUs that come online or go
-	 * offline.
-	 */
-	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu, riscv_offline_cpu);
-
-out:
-	for_each_cpu(cpu, cpu_online_mask) {
-		if (bufs[cpu])
-			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
-	}
-
-	kfree(bufs);
-	return 0;
-}
-#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */
-static int check_unaligned_access_speed_all_cpus(void)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
 static void check_vector_unaligned_access(struct work_struct *work __always_unused)
 {
@@ -349,7 +352,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus
 		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n",
 			cpu);
 
-		return;
+		goto free;
 	}
 
 	if (word_cycles < byte_cycles)
@@ -363,57 +366,119 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus
 		(speed ==  RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow");
 
 	per_cpu(vector_misaligned_access, cpu) = speed;
+
+free:
+	__free_pages(page, MISALIGNED_BUFFER_ORDER);
+}
+
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	schedule_on_each_cpu(check_vector_unaligned_access);
+
+	return 0;
+}
+#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
+static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+{
+	return 0;
 }
+#endif
 
 static int riscv_online_cpu_vec(unsigned int cpu)
 {
-	if (!has_vector())
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
 		return 0;
+	}
 
-	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED)
+#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS
+	if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN)
 		return 0;
 
 	check_vector_unaligned_access_emulated(NULL);
 	check_vector_unaligned_access(NULL);
+#endif
+
 	return 0;
 }
 
-/* Measure unaligned access speed on all CPUs present at boot in parallel. */
-static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
-{
-	schedule_on_each_cpu(check_vector_unaligned_access);
+static const char * const speed_str[] __initconst = { NULL, NULL, "slow", "fast", "unsupported" };
 
-	/*
-	 * Setup hotplug callbacks for any new CPUs that come online or go
-	 * offline.
-	 */
-	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu_vec, NULL);
+static int __init set_unaligned_scalar_speed_param(char *str)
+{
+	if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_FAST]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED]))
+		unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED;
+	else
+		return -EINVAL;
 
-	return 0;
+	return 1;
 }
-#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */
-static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
+__setup("unaligned_scalar_speed=", set_unaligned_scalar_speed_param);
+
+static int __init set_unaligned_vector_speed_param(char *str)
 {
-	return 0;
+	if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_FAST]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST;
+	else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED]))
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
+	else
+		return -EINVAL;
+
+	return 1;
 }
-#endif
+__setup("unaligned_vector_speed=", set_unaligned_vector_speed_param);
 
-static int check_unaligned_access_all_cpus(void)
+static int __init check_unaligned_access_all_cpus(void)
 {
-	bool all_cpus_emulated, all_cpus_vec_unsupported;
+	int cpu;
+
+	if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) {
+		pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n",
+			speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param);
+		for_each_online_cpu(cpu)
+			per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param;
+	} else if (!check_unaligned_access_emulated_all_cpus()) {
+		check_unaligned_access_speed_all_cpus();
+	}
+
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		if (!has_vector() &&
+		    unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) {
+			pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n",
+				speed_str[unaligned_vector_speed_param]);
+		} else {
+			pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n",
+				speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param);
+		}
+	}
 
-	all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
-	all_cpus_vec_unsupported = check_vector_unaligned_access_emulated_all_cpus();
+	if (!has_vector())
+		unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED;
 
-	if (!all_cpus_vec_unsupported &&
-	    IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
+	if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) {
+		for_each_online_cpu(cpu)
+			per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
+	} else if (!check_vector_unaligned_access_emulated_all_cpus() &&
+		   IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
 		kthread_run(vec_check_unaligned_access_speed_all_cpus,
 			    NULL, "vec_check_unaligned_access_speed_all_cpus");
 	}
 
-	if (!all_cpus_emulated)
-		return check_unaligned_access_speed_all_cpus();
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu, riscv_offline_cpu);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu_vec, NULL);
 
 	return 0;
 }
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 3ca3ae4277e1..cc2895d1fbc2 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -13,20 +13,11 @@
 #include <linux/err.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 #include <vdso/vsyscall.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
-#define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
+#define VVAR_SIZE  (VDSO_NR_PAGES << PAGE_SHIFT)
 
 struct __vdso_info {
 	const char *name;
@@ -79,78 +70,6 @@ static void __init __vdso_init(struct __vdso_info *vdso_info)
 	vdso_info->cm->pages = vdso_pagelist;
 }
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-static const struct vm_special_mapping rv_vvar_map;
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a task
- * changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &rv_vvar_map))
-			zap_vma_pages(vma);
-	}
-
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long pfn;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		if (timens_page)
-			pfn = page_to_pfn(timens_page);
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_special_mapping rv_vvar_map = {
-	.name   = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping rv_vdso_map __ro_after_init = {
 	.name   = "[vdso]",
 	.mremap = vdso_mremap,
@@ -196,7 +115,7 @@ static int __setup_additional_pages(struct mm_struct *mm,
 	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
 	void *ret;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 
 	vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
@@ -208,8 +127,7 @@ static int __setup_additional_pages(struct mm_struct *mm,
 		goto up_fail;
 	}
 
-	ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
-		(VM_READ | VM_MAYREAD | VM_PFNMAP), &rv_vvar_map);
+	ret = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(ret))
 		goto up_fail;
 
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9a1b555e8733..ad73607abc28 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -2,7 +2,7 @@
 # Copied from arch/tile/kernel/vdso/Makefile
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 # Symbols present in the vdso
 vdso-syms  = rt_sigreturn
 ifdef CONFIG_64BIT
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index a158c029344f..2ddeba6c68dd 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -16,8 +16,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
 				 size_t cpusetsize, unsigned long *cpus,
 				 unsigned int flags)
 {
-	const struct vdso_data *vd = __arch_get_vdso_data();
-	const struct arch_vdso_time_data *avd = &vd->arch_data;
+	const struct vdso_arch_data *avd = &vdso_u_arch_data;
 	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
@@ -51,8 +50,7 @@ static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
 			       size_t cpusetsize, unsigned long *cpus,
 			       unsigned int flags)
 {
-	const struct vdso_data *vd = __arch_get_vdso_data();
-	const struct arch_vdso_time_data *avd = &vd->arch_data;
+	const struct vdso_arch_data *avd = &vdso_u_arch_data;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 	unsigned char *c = (unsigned char *)cpus;
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index cbe2a179331d..8e86965a8aae 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -4,15 +4,14 @@
  */
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_ARCH(riscv)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S
index d16f19f1b3b6..7ce4de6f6e69 100644
--- a/arch/riscv/kernel/vec-copy-unaligned.S
+++ b/arch/riscv/kernel/vec-copy-unaligned.S
@@ -11,7 +11,7 @@
 
 #define WORD_SEW CONCATENATE(e, WORD_EEW)
 #define VEC_L CONCATENATE(vle, WORD_EEW).v
-#define VEC_S CONCATENATE(vle, WORD_EEW).v
+#define VEC_S CONCATENATE(vse, WORD_EEW).v
 
 /* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using word loads and stores. */
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
index a31ff84740eb..9feb7f67a0a3 100644
--- a/arch/riscv/kernel/vendor_extensions.c
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -61,6 +61,6 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig
 	if (bit >= RISCV_ISA_VENDOR_EXT_MAX)
 		return false;
 
-	return test_bit(bit, bmap->isa) ? true : false;
+	return test_bit(bit, bmap->isa);
 }
 EXPORT_SYMBOL_GPL(__riscv_isa_vendor_extension_available);
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 002ca58dd998..61bd5ba6680a 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -97,6 +97,9 @@ SECTIONS
 	{
 		EXIT_DATA
 	}
+
+	RUNTIME_CONST_VARIABLES
+
 	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	.rel.dyn : {
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index a8085cd8215e..29ef9c2133a9 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
 
 	if (imsic->vsfile_cpu >= 0) {
 		writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE);
-		kvm_vcpu_kick(vcpu);
 	} else {
 		eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)];
 		set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip);
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index 1fa8be5ee509..4b24705dc63a 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -172,8 +172,8 @@ module_init(riscv_kvm_init);
 
 static void __exit riscv_kvm_exit(void)
 {
-	kvm_riscv_teardown();
-
 	kvm_exit();
+
+	kvm_riscv_teardown();
 }
 module_exit(riscv_kvm_exit);
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 60d684c76c58..02635bac91f1 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
 	spin_unlock(&vcpu->arch.reset_cntx_lock);
 
+	memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+
 	kvm_riscv_vcpu_fp_reset(vcpu);
 
 	kvm_riscv_vcpu_vector_reset(vcpu);
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f6d27b59c641..2e1b646f0d61 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,8 +47,10 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVNAPOT),
 	KVM_ISA_EXT_ARR(SVPBMT),
 	KVM_ISA_EXT_ARR(SVVPTC),
+	KVM_ISA_EXT_ARR(ZAAMO),
 	KVM_ISA_EXT_ARR(ZABHA),
 	KVM_ISA_EXT_ARR(ZACAS),
+	KVM_ISA_EXT_ARR(ZALRSC),
 	KVM_ISA_EXT_ARR(ZAWRS),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
@@ -149,8 +151,10 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_SVVPTC:
+	case KVM_RISCV_ISA_EXT_ZAAMO:
 	case KVM_RISCV_ISA_EXT_ZABHA:
 	case KVM_RISCV_ISA_EXT_ZACAS:
+	case KVM_RISCV_ISA_EXT_ZALRSC:
 	case KVM_RISCV_ISA_EXT_ZAWRS:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
@@ -203,7 +207,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVADE:
 		/*
 		 * The henvcfg.ADUE is read-only zero if menvcfg.ADUE is zero.
-		 * Svade is not allowed to disable when the platform use Svade.
+		 * Svade can't be disabled unless we support Svadu.
 		 */
 		return arch_has_hw_pte_young();
 	default:
diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index 2707a51b082c..78ac3216a54d 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -666,6 +666,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba
 		.type = etype,
 		.size = sizeof(struct perf_event_attr),
 		.pinned = true,
+		.disabled = true,
 		/*
 		 * It should never reach here if the platform doesn't support the sscofpmf
 		 * extension as mode filtering won't work without it.
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index dce667f4b6ab..3070bb31745d 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_sbi.h>
 
@@ -79,12 +80,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
 	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
 	if (!target_vcpu)
 		return SBI_ERR_INVALID_PARAM;
-	if (!kvm_riscv_vcpu_stopped(target_vcpu))
-		return SBI_HSM_STATE_STARTED;
-	else if (vcpu->stat.generic.blocking)
+	if (kvm_riscv_vcpu_stopped(target_vcpu))
+		return SBI_HSM_STATE_STOPPED;
+	else if (target_vcpu->stat.generic.blocking)
 		return SBI_HSM_STATE_SUSPENDED;
 	else
-		return SBI_HSM_STATE_STOPPED;
+		return SBI_HSM_STATE_STARTED;
 }
 
 static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
@@ -109,7 +110,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		}
 		return 0;
 	case SBI_EXT_HSM_HART_SUSPEND:
-		switch (cp->a0) {
+		switch (lower_32_bits(cp->a0)) {
 		case SBI_HSM_SUSPEND_RET_DEFAULT:
 			kvm_riscv_vcpu_wfi(vcpu);
 			break;
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9c2ab3dfa93a..5fbf3f94f1e8 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u64 next_cycle;
 
 	if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
 	unsigned long hbase = cp->a1;
+	unsigned long hart_bit = 0, sentmask = 0;
 
 	if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
 				continue;
-			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+			hart_bit = tmp->vcpu_id - hbase;
+			if (hart_bit >= __riscv_xlen)
+				goto done;
+			if (!(hmask & (1UL << hart_bit)))
 				continue;
 		}
 		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
 		if (ret < 0)
 			break;
+		sentmask |= 1UL << hart_bit;
 		kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
 	}
 
+done:
+	if (hbase != -1UL && (hmask ^ sentmask))
+		retdata->err_val = SBI_ERR_INVALID_PARAM;
+
 	return ret;
 }
 
diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index 5d55e08791fa..bc0ebba89003 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
@@ -19,7 +20,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	switch (funcid) {
 	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
-		if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
 			retdata->err_val = SBI_ERR_INVALID_PARAM;
 			return 0;
 		}
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 96e7a4e463f7..ff672fa71fcc 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -248,18 +248,19 @@ int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu)
 	if (t->init_done)
 		return -EINVAL;
 
-	hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	t->init_done = true;
 	t->next_set = false;
 
 	/* Enable sstc for every vcpu if available in hardware */
 	if (riscv_isa_extension_available(NULL, SSTC)) {
 		t->sstc_enabled = true;
-		t->hrt.function = kvm_riscv_vcpu_vstimer_expired;
+		hrtimer_setup(&t->hrt, kvm_riscv_vcpu_vstimer_expired, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 		t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp;
 	} else {
 		t->sstc_enabled = false;
-		t->hrt.function = kvm_riscv_vcpu_hrtimer_expired;
+		hrtimer_setup(&t->hrt, kvm_riscv_vcpu_hrtimer_expired, CLOCK_MONOTONIC,
+			      HRTIMER_MODE_REL);
 		t->timer_next_event = kvm_riscv_vcpu_update_hrtimer;
 	}
 
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 79368a895fee..0baec92d2f55 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+obj-y			+= crypto/
 lib-y			+= delay.o
 lib-y			+= memcpy.o
 lib-y			+= memset.o
@@ -16,6 +17,11 @@ lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_RISCV_ISA_ZICBOZ)	+= clear_page.o
 obj-$(CONFIG_CRC32_ARCH)	+= crc32-riscv.o
+crc32-riscv-y := crc32.o crc32_msb.o crc32_lsb.o
+obj-$(CONFIG_CRC64_ARCH) += crc64-riscv.o
+crc64-riscv-y := crc64.o crc64_msb.o crc64_lsb.o
+obj-$(CONFIG_CRC_T10DIF_ARCH)	+= crc-t10dif-riscv.o
+crc-t10dif-riscv-y := crc-t10dif.o crc16_msb.o
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
 lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o
diff --git a/arch/riscv/lib/crc-clmul-consts.h b/arch/riscv/lib/crc-clmul-consts.h
new file mode 100644
index 000000000000..8d73449235ef
--- /dev/null
+++ b/arch/riscv/lib/crc-clmul-consts.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CRC constants generated by:
+ *
+ *	./scripts/gen-crc-consts.py riscv_clmul crc16_msb_0x8bb7,crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5
+ *
+ * Do not edit manually.
+ */
+
+struct crc_clmul_consts {
+	unsigned long fold_across_2_longs_const_hi;
+	unsigned long fold_across_2_longs_const_lo;
+	unsigned long barrett_reduction_const_1;
+	unsigned long barrett_reduction_const_2;
+};
+
+/*
+ * Constants generated for most-significant-bit-first CRC-16 using
+ * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ */
+static const struct crc_clmul_consts crc16_msb_0x8bb7_consts __maybe_unused = {
+#ifdef CONFIG_64BIT
+	.fold_across_2_longs_const_hi = 0x0000000000001faa, /* x^192 mod G */
+	.fold_across_2_longs_const_lo = 0x000000000000a010, /* x^128 mod G */
+	.barrett_reduction_const_1 = 0xfb2d2bfc0e99d245, /* floor(x^79 / G) */
+	.barrett_reduction_const_2 = 0x0000000000008bb7, /* G - x^16 */
+#else
+	.fold_across_2_longs_const_hi = 0x00005890, /* x^96 mod G */
+	.fold_across_2_longs_const_lo = 0x0000f249, /* x^64 mod G */
+	.barrett_reduction_const_1 = 0xfb2d2bfc, /* floor(x^47 / G) */
+	.barrett_reduction_const_2 = 0x00008bb7, /* G - x^16 */
+#endif
+};
+
+/*
+ * Constants generated for most-significant-bit-first CRC-32 using
+ * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 +
+ *        x^5 + x^4 + x^2 + x^1 + x^0
+ */
+static const struct crc_clmul_consts crc32_msb_0x04c11db7_consts __maybe_unused = {
+#ifdef CONFIG_64BIT
+	.fold_across_2_longs_const_hi = 0x00000000c5b9cd4c, /* x^192 mod G */
+	.fold_across_2_longs_const_lo = 0x00000000e8a45605, /* x^128 mod G */
+	.barrett_reduction_const_1 = 0x826880efa40da72d, /* floor(x^95 / G) */
+	.barrett_reduction_const_2 = 0x0000000004c11db7, /* G - x^32 */
+#else
+	.fold_across_2_longs_const_hi = 0xf200aa66, /* x^96 mod G */
+	.fold_across_2_longs_const_lo = 0x490d678d, /* x^64 mod G */
+	.barrett_reduction_const_1 = 0x826880ef, /* floor(x^63 / G) */
+	.barrett_reduction_const_2 = 0x04c11db7, /* G - x^32 */
+#endif
+};
+
+/*
+ * Constants generated for least-significant-bit-first CRC-32 using
+ * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 +
+ *        x^5 + x^4 + x^2 + x^1 + x^0
+ */
+static const struct crc_clmul_consts crc32_lsb_0xedb88320_consts __maybe_unused = {
+#ifdef CONFIG_64BIT
+	.fold_across_2_longs_const_hi = 0x65673b4600000000, /* x^191 mod G */
+	.fold_across_2_longs_const_lo = 0x9ba54c6f00000000, /* x^127 mod G */
+	.barrett_reduction_const_1 = 0xb4e5b025f7011641, /* floor(x^95 / G) */
+	.barrett_reduction_const_2 = 0x00000000edb88320, /* (G - x^32) * x^32 */
+#else
+	.fold_across_2_longs_const_hi = 0xccaa009e, /* x^95 mod G */
+	.fold_across_2_longs_const_lo = 0xb8bc6765, /* x^63 mod G */
+	.barrett_reduction_const_1 = 0xf7011641, /* floor(x^63 / G) */
+	.barrett_reduction_const_2 = 0xedb88320, /* (G - x^32) * x^0 */
+#endif
+};
+
+/*
+ * Constants generated for least-significant-bit-first CRC-32 using
+ * G(x) = x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 + x^18 +
+ *        x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0
+ */
+static const struct crc_clmul_consts crc32_lsb_0x82f63b78_consts __maybe_unused = {
+#ifdef CONFIG_64BIT
+	.fold_across_2_longs_const_hi = 0x3743f7bd00000000, /* x^191 mod G */
+	.fold_across_2_longs_const_lo = 0x3171d43000000000, /* x^127 mod G */
+	.barrett_reduction_const_1 = 0x4869ec38dea713f1, /* floor(x^95 / G) */
+	.barrett_reduction_const_2 = 0x0000000082f63b78, /* (G - x^32) * x^32 */
+#else
+	.fold_across_2_longs_const_hi = 0x493c7d27, /* x^95 mod G */
+	.fold_across_2_longs_const_lo = 0xdd45aab8, /* x^63 mod G */
+	.barrett_reduction_const_1 = 0xdea713f1, /* floor(x^63 / G) */
+	.barrett_reduction_const_2 = 0x82f63b78, /* (G - x^32) * x^0 */
+#endif
+};
+
+/*
+ * Constants generated for most-significant-bit-first CRC-64 using
+ * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ *        x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ *        x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ *        x^7 + x^4 + x^1 + x^0
+ */
+#ifdef CONFIG_64BIT
+static const struct crc_clmul_consts crc64_msb_0x42f0e1eba9ea3693_consts __maybe_unused = {
+	.fold_across_2_longs_const_hi = 0x4eb938a7d257740e, /* x^192 mod G */
+	.fold_across_2_longs_const_lo = 0x05f5c3c7eb52fab6, /* x^128 mod G */
+	.barrett_reduction_const_1 = 0xabc694e836627c39, /* floor(x^127 / G) */
+	.barrett_reduction_const_2 = 0x42f0e1eba9ea3693, /* G - x^64 */
+};
+#endif
+
+/*
+ * Constants generated for least-significant-bit-first CRC-64 using
+ * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 +
+ *        x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 +
+ *        x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 +
+ *        x^4 + x^3 + x^0
+ */
+#ifdef CONFIG_64BIT
+static const struct crc_clmul_consts crc64_lsb_0x9a6c9329ac4bc9b5_consts __maybe_unused = {
+	.fold_across_2_longs_const_hi = 0xeadc41fd2ba3d420, /* x^191 mod G */
+	.fold_across_2_longs_const_lo = 0x21e9761e252621ac, /* x^127 mod G */
+	.barrett_reduction_const_1 = 0x27ecfa329aef9f77, /* floor(x^127 / G) */
+	.barrett_reduction_const_2 = 0x9a6c9329ac4bc9b5, /* (G - x^64) * x^0 */
+};
+#endif
diff --git a/arch/riscv/lib/crc-clmul-template.h b/arch/riscv/lib/crc-clmul-template.h
new file mode 100644
index 000000000000..77187e7f1762
--- /dev/null
+++ b/arch/riscv/lib/crc-clmul-template.h
@@ -0,0 +1,265 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright 2025 Google LLC */
+
+/*
+ * This file is a "template" that generates a CRC function optimized using the
+ * RISC-V Zbc (scalar carryless multiplication) extension.  The includer of this
+ * file must define the following parameters to specify the type of CRC:
+ *
+ *	crc_t: the data type of the CRC, e.g. u32 for a 32-bit CRC
+ *	LSB_CRC: 0 for a msb (most-significant-bit) first CRC, i.e. natural
+ *		 mapping between bits and polynomial coefficients
+ *	         1 for a lsb (least-significant-bit) first CRC, i.e. reflected
+ *	         mapping between bits and polynomial coefficients
+ */
+
+#include <asm/byteorder.h>
+#include <linux/minmax.h>
+
+#define CRC_BITS	(8 * sizeof(crc_t))	/* a.k.a. 'n' */
+
+static inline unsigned long clmul(unsigned long a, unsigned long b)
+{
+	unsigned long res;
+
+	asm(".option push\n"
+	    ".option arch,+zbc\n"
+	    "clmul %0, %1, %2\n"
+	    ".option pop\n"
+	    : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+static inline unsigned long clmulh(unsigned long a, unsigned long b)
+{
+	unsigned long res;
+
+	asm(".option push\n"
+	    ".option arch,+zbc\n"
+	    "clmulh %0, %1, %2\n"
+	    ".option pop\n"
+	    : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+static inline unsigned long clmulr(unsigned long a, unsigned long b)
+{
+	unsigned long res;
+
+	asm(".option push\n"
+	    ".option arch,+zbc\n"
+	    "clmulr %0, %1, %2\n"
+	    ".option pop\n"
+	    : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/*
+ * crc_load_long() loads one "unsigned long" of aligned data bytes, producing a
+ * polynomial whose bit order matches the CRC's bit order.
+ */
+#ifdef CONFIG_64BIT
+#  if LSB_CRC
+#    define crc_load_long(x)	le64_to_cpup(x)
+#  else
+#    define crc_load_long(x)	be64_to_cpup(x)
+#  endif
+#else
+#  if LSB_CRC
+#    define crc_load_long(x)	le32_to_cpup(x)
+#  else
+#    define crc_load_long(x)	be32_to_cpup(x)
+#  endif
+#endif
+
+/* XOR @crc into the end of @msgpoly that represents the high-order terms. */
+static inline unsigned long
+crc_clmul_prep(crc_t crc, unsigned long msgpoly)
+{
+#if LSB_CRC
+	return msgpoly ^ crc;
+#else
+	return msgpoly ^ ((unsigned long)crc << (BITS_PER_LONG - CRC_BITS));
+#endif
+}
+
+/*
+ * Multiply the long-sized @msgpoly by x^n (a.k.a. x^CRC_BITS) and reduce it
+ * modulo the generator polynomial G.  This gives the CRC of @msgpoly.
+ */
+static inline crc_t
+crc_clmul_long(unsigned long msgpoly, const struct crc_clmul_consts *consts)
+{
+	unsigned long tmp;
+
+	/*
+	 * First step of Barrett reduction with integrated multiplication by
+	 * x^n: calculate floor((msgpoly * x^n) / G).  This is the value by
+	 * which G needs to be multiplied to cancel out the x^n and higher terms
+	 * of msgpoly * x^n.  Do it using the following formula:
+	 *
+	 * msb-first:
+	 *    floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G)) / x^(BITS_PER_LONG-1))
+	 * lsb-first:
+	 *    floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G) * x) / x^BITS_PER_LONG)
+	 *
+	 * barrett_reduction_const_1 contains floor(x^(BITS_PER_LONG-1+n) / G),
+	 * which fits a long exactly.  Using any lower power of x there would
+	 * not carry enough precision through the calculation, while using any
+	 * higher power of x would require extra instructions to handle a wider
+	 * multiplication.  In the msb-first case, using this power of x results
+	 * in needing a floored division by x^(BITS_PER_LONG-1), which matches
+	 * what clmulr produces.  In the lsb-first case, a factor of x gets
+	 * implicitly introduced by each carryless multiplication (shown as
+	 * '* x' above), and the floored division instead needs to be by
+	 * x^BITS_PER_LONG which matches what clmul produces.
+	 */
+#if LSB_CRC
+	tmp = clmul(msgpoly, consts->barrett_reduction_const_1);
+#else
+	tmp = clmulr(msgpoly, consts->barrett_reduction_const_1);
+#endif
+
+	/*
+	 * Second step of Barrett reduction:
+	 *
+	 *    crc := (msgpoly * x^n) + (G * floor((msgpoly * x^n) / G))
+	 *
+	 * This reduces (msgpoly * x^n) modulo G by adding the appropriate
+	 * multiple of G to it.  The result uses only the x^0..x^(n-1) terms.
+	 * HOWEVER, since the unreduced value (msgpoly * x^n) is zero in those
+	 * terms in the first place, it is more efficient to do the equivalent:
+	 *
+	 *    crc := ((G - x^n) * floor((msgpoly * x^n) / G)) mod x^n
+	 *
+	 * In the lsb-first case further modify it to the following which avoids
+	 * a shift, as the crc ends up in the physically low n bits from clmulr:
+	 *
+	 *    product := ((G - x^n) * x^(BITS_PER_LONG - n)) * floor((msgpoly * x^n) / G) * x
+	 *    crc := floor(product / x^(BITS_PER_LONG + 1 - n)) mod x^n
+	 *
+	 * barrett_reduction_const_2 contains the constant multiplier (G - x^n)
+	 * or (G - x^n) * x^(BITS_PER_LONG - n) from the formulas above.  The
+	 * cast of the result to crc_t is essential, as it applies the mod x^n!
+	 */
+#if LSB_CRC
+	return clmulr(tmp, consts->barrett_reduction_const_2);
+#else
+	return clmul(tmp, consts->barrett_reduction_const_2);
+#endif
+}
+
+/* Update @crc with the data from @msgpoly. */
+static inline crc_t
+crc_clmul_update_long(crc_t crc, unsigned long msgpoly,
+		      const struct crc_clmul_consts *consts)
+{
+	return crc_clmul_long(crc_clmul_prep(crc, msgpoly), consts);
+}
+
+/* Update @crc with 1 <= @len < sizeof(unsigned long) bytes of data. */
+static inline crc_t
+crc_clmul_update_partial(crc_t crc, const u8 *p, size_t len,
+			 const struct crc_clmul_consts *consts)
+{
+	unsigned long msgpoly;
+	size_t i;
+
+#if LSB_CRC
+	msgpoly = (unsigned long)p[0] << (BITS_PER_LONG - 8);
+	for (i = 1; i < len; i++)
+		msgpoly = (msgpoly >> 8) ^ ((unsigned long)p[i] << (BITS_PER_LONG - 8));
+#else
+	msgpoly = p[0];
+	for (i = 1; i < len; i++)
+		msgpoly = (msgpoly << 8) ^ p[i];
+#endif
+
+	if (len >= sizeof(crc_t)) {
+	#if LSB_CRC
+		msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len);
+	#else
+		msgpoly ^= (unsigned long)crc << (8*len - CRC_BITS);
+	#endif
+		return crc_clmul_long(msgpoly, consts);
+	}
+#if LSB_CRC
+	msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len);
+	return crc_clmul_long(msgpoly, consts) ^ (crc >> (8*len));
+#else
+	msgpoly ^= crc >> (CRC_BITS - 8*len);
+	return crc_clmul_long(msgpoly, consts) ^ (crc << (8*len));
+#endif
+}
+
+static inline crc_t
+crc_clmul(crc_t crc, const void *p, size_t len,
+	  const struct crc_clmul_consts *consts)
+{
+	size_t align;
+
+	/* This implementation assumes that the CRC fits in an unsigned long. */
+	BUILD_BUG_ON(sizeof(crc_t) > sizeof(unsigned long));
+
+	/* If the buffer is not long-aligned, align it. */
+	align = (unsigned long)p % sizeof(unsigned long);
+	if (align && len) {
+		align = min(sizeof(unsigned long) - align, len);
+		crc = crc_clmul_update_partial(crc, p, align, consts);
+		p += align;
+		len -= align;
+	}
+
+	if (len >= 4 * sizeof(unsigned long)) {
+		unsigned long m0, m1;
+
+		m0 = crc_clmul_prep(crc, crc_load_long(p));
+		m1 = crc_load_long(p + sizeof(unsigned long));
+		p += 2 * sizeof(unsigned long);
+		len -= 2 * sizeof(unsigned long);
+		/*
+		 * Main loop.  Each iteration starts with a message polynomial
+		 * (x^BITS_PER_LONG)*m0 + m1, then logically extends it by two
+		 * more longs of data to form x^(3*BITS_PER_LONG)*m0 +
+		 * x^(2*BITS_PER_LONG)*m1 + x^BITS_PER_LONG*m2 + m3, then
+		 * "folds" that back into a congruent (modulo G) value that uses
+		 * just m0 and m1 again.  This is done by multiplying m0 by the
+		 * precomputed constant (x^(3*BITS_PER_LONG) mod G) and m1 by
+		 * the precomputed constant (x^(2*BITS_PER_LONG) mod G), then
+		 * adding the results to m2 and m3 as appropriate.  Each such
+		 * multiplication produces a result twice the length of a long,
+		 * which in RISC-V is two instructions clmul and clmulh.
+		 *
+		 * This could be changed to fold across more than 2 longs at a
+		 * time if there is a CPU that can take advantage of it.
+		 */
+		do {
+			unsigned long p0, p1, p2, p3;
+
+			p0 = clmulh(m0, consts->fold_across_2_longs_const_hi);
+			p1 = clmul(m0, consts->fold_across_2_longs_const_hi);
+			p2 = clmulh(m1, consts->fold_across_2_longs_const_lo);
+			p3 = clmul(m1, consts->fold_across_2_longs_const_lo);
+			m0 = (LSB_CRC ? p1 ^ p3 : p0 ^ p2) ^ crc_load_long(p);
+			m1 = (LSB_CRC ? p0 ^ p2 : p1 ^ p3) ^
+			     crc_load_long(p + sizeof(unsigned long));
+
+			p += 2 * sizeof(unsigned long);
+			len -= 2 * sizeof(unsigned long);
+		} while (len >= 2 * sizeof(unsigned long));
+
+		crc = crc_clmul_long(m0, consts);
+		crc = crc_clmul_update_long(crc, m1, consts);
+	}
+
+	while (len >= sizeof(unsigned long)) {
+		crc = crc_clmul_update_long(crc, crc_load_long(p), consts);
+		p += sizeof(unsigned long);
+		len -= sizeof(unsigned long);
+	}
+
+	if (len)
+		crc = crc_clmul_update_partial(crc, p, len, consts);
+
+	return crc;
+}
diff --git a/arch/riscv/lib/crc-clmul.h b/arch/riscv/lib/crc-clmul.h
new file mode 100644
index 000000000000..dd1736245815
--- /dev/null
+++ b/arch/riscv/lib/crc-clmul.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright 2025 Google LLC */
+
+#ifndef _RISCV_CRC_CLMUL_H
+#define _RISCV_CRC_CLMUL_H
+
+#include <linux/types.h>
+#include "crc-clmul-consts.h"
+
+u16 crc16_msb_clmul(u16 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts);
+u32 crc32_msb_clmul(u32 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts);
+u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts);
+#ifdef CONFIG_64BIT
+u64 crc64_msb_clmul(u64 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts);
+u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts);
+#endif
+
+#endif /* _RISCV_CRC_CLMUL_H */
diff --git a/arch/riscv/lib/crc-t10dif.c b/arch/riscv/lib/crc-t10dif.c
new file mode 100644
index 000000000000..e6b0051ccd86
--- /dev/null
+++ b/arch/riscv/lib/crc-t10dif.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized CRC-T10DIF function
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+#include <linux/crc-t10dif.h>
+#include <linux/module.h>
+
+#include "crc-clmul.h"
+
+u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc16_msb_clmul(crc, p, len, &crc16_msb_0x8bb7_consts);
+	return crc_t10dif_generic(crc, p, len);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+MODULE_DESCRIPTION("RISC-V optimized CRC-T10DIF function");
+MODULE_LICENSE("GPL");
diff --git a/arch/riscv/lib/crc16_msb.c b/arch/riscv/lib/crc16_msb.c
new file mode 100644
index 000000000000..554d295e95f5
--- /dev/null
+++ b/arch/riscv/lib/crc16_msb.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized most-significant-bit-first CRC16
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "crc-clmul.h"
+
+typedef u16 crc_t;
+#define LSB_CRC 0
+#include "crc-clmul-template.h"
+
+u16 crc16_msb_clmul(u16 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts)
+{
+	return crc_clmul(crc, p, len, consts);
+}
diff --git a/arch/riscv/lib/crc32-riscv.c b/arch/riscv/lib/crc32-riscv.c
deleted file mode 100644
index 53d56ab422c7..000000000000
--- a/arch/riscv/lib/crc32-riscv.c
+++ /dev/null
@@ -1,311 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Accelerated CRC32 implementation with Zbc extension.
- *
- * Copyright (C) 2024 Intel Corporation
- */
-
-#include <asm/hwcap.h>
-#include <asm/alternative-macros.h>
-#include <asm/byteorder.h>
-
-#include <linux/types.h>
-#include <linux/minmax.h>
-#include <linux/crc32poly.h>
-#include <linux/crc32.h>
-#include <linux/byteorder/generic.h>
-#include <linux/module.h>
-
-/*
- * Refer to https://www.corsix.org/content/barrett-reduction-polynomials for
- * better understanding of how this math works.
- *
- * let "+" denotes polynomial add (XOR)
- * let "-" denotes polynomial sub (XOR)
- * let "*" denotes polynomial multiplication
- * let "/" denotes polynomial floor division
- * let "S" denotes source data, XLEN bit wide
- * let "P" denotes CRC32 polynomial
- * let "T" denotes 2^(XLEN+32)
- * let "QT" denotes quotient of T/P, with the bit for 2^XLEN being implicit
- *
- * crc32(S, P)
- * => S * (2^32) - S * (2^32) / P * P
- * => lowest 32 bits of: S * (2^32) / P * P
- * => lowest 32 bits of: S * (2^32) * (T / P) / T * P
- * => lowest 32 bits of: S * (2^32) * quotient / T * P
- * => lowest 32 bits of: S * quotient / 2^XLEN * P
- * => lowest 32 bits of: (clmul_high_part(S, QT) + S) * P
- * => clmul_low_part(clmul_high_part(S, QT) + S, P)
- *
- * In terms of below implementations, the BE case is more intuitive, since the
- * higher order bit sits at more significant position.
- */
-
-#if __riscv_xlen == 64
-/* Slide by XLEN bits per iteration */
-# define STEP_ORDER 3
-
-/* Each below polynomial quotient has an implicit bit for 2^XLEN */
-
-/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in LE format */
-# define CRC32_POLY_QT_LE	0x5a72d812fb808b20
-
-/* Polynomial quotient of (2^(XLEN+32))/CRC32C_POLY, in LE format */
-# define CRC32C_POLY_QT_LE	0xa434f61c6f5389f8
-
-/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in BE format, it should be
- * the same as the bit-reversed version of CRC32_POLY_QT_LE
- */
-# define CRC32_POLY_QT_BE	0x04d101df481b4e5a
-
-static inline u64 crc32_le_prep(u32 crc, unsigned long const *ptr)
-{
-	return (u64)crc ^ (__force u64)__cpu_to_le64(*ptr);
-}
-
-static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt)
-{
-	u32 crc;
-
-	/* We don't have a "clmulrh" insn, so use clmul + slli instead. */
-	asm volatile (".option push\n"
-		      ".option arch,+zbc\n"
-		      "clmul	%0, %1, %2\n"
-		      "slli	%0, %0, 1\n"
-		      "xor	%0, %0, %1\n"
-		      "clmulr	%0, %0, %3\n"
-		      "srli	%0, %0, 32\n"
-		      ".option pop\n"
-		      : "=&r" (crc)
-		      : "r" (s),
-			"r" (poly_qt),
-			"r" ((u64)poly << 32)
-		      :);
-	return crc;
-}
-
-static inline u64 crc32_be_prep(u32 crc, unsigned long const *ptr)
-{
-	return ((u64)crc << 32) ^ (__force u64)__cpu_to_be64(*ptr);
-}
-
-#elif __riscv_xlen == 32
-# define STEP_ORDER 2
-/* Each quotient should match the upper half of its analog in RV64 */
-# define CRC32_POLY_QT_LE	0xfb808b20
-# define CRC32C_POLY_QT_LE	0x6f5389f8
-# define CRC32_POLY_QT_BE	0x04d101df
-
-static inline u32 crc32_le_prep(u32 crc, unsigned long const *ptr)
-{
-	return crc ^ (__force u32)__cpu_to_le32(*ptr);
-}
-
-static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt)
-{
-	u32 crc;
-
-	/* We don't have a "clmulrh" insn, so use clmul + slli instead. */
-	asm volatile (".option push\n"
-		      ".option arch,+zbc\n"
-		      "clmul	%0, %1, %2\n"
-		      "slli	%0, %0, 1\n"
-		      "xor	%0, %0, %1\n"
-		      "clmulr	%0, %0, %3\n"
-		      ".option pop\n"
-		      : "=&r" (crc)
-		      : "r" (s),
-			"r" (poly_qt),
-			"r" (poly)
-		      :);
-	return crc;
-}
-
-static inline u32 crc32_be_prep(u32 crc, unsigned long const *ptr)
-{
-	return crc ^ (__force u32)__cpu_to_be32(*ptr);
-}
-
-#else
-# error "Unexpected __riscv_xlen"
-#endif
-
-static inline u32 crc32_be_zbc(unsigned long s)
-{
-	u32 crc;
-
-	asm volatile (".option push\n"
-		      ".option arch,+zbc\n"
-		      "clmulh	%0, %1, %2\n"
-		      "xor	%0, %0, %1\n"
-		      "clmul	%0, %0, %3\n"
-		      ".option pop\n"
-		      : "=&r" (crc)
-		      : "r" (s),
-			"r" (CRC32_POLY_QT_BE),
-			"r" (CRC32_POLY_BE)
-		      :);
-	return crc;
-}
-
-#define STEP		(1 << STEP_ORDER)
-#define OFFSET_MASK	(STEP - 1)
-
-typedef u32 (*fallback)(u32 crc, unsigned char const *p, size_t len);
-
-static inline u32 crc32_le_unaligned(u32 crc, unsigned char const *p,
-				     size_t len, u32 poly,
-				     unsigned long poly_qt)
-{
-	size_t bits = len * 8;
-	unsigned long s = 0;
-	u32 crc_low = 0;
-
-	for (int i = 0; i < len; i++)
-		s = ((unsigned long)*p++ << (__riscv_xlen - 8)) | (s >> 8);
-
-	s ^= (unsigned long)crc << (__riscv_xlen - bits);
-	if (__riscv_xlen == 32 || len < sizeof(u32))
-		crc_low = crc >> bits;
-
-	crc = crc32_le_zbc(s, poly, poly_qt);
-	crc ^= crc_low;
-
-	return crc;
-}
-
-static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
-					  size_t len, u32 poly,
-					  unsigned long poly_qt,
-					  fallback crc_fb)
-{
-	size_t offset, head_len, tail_len;
-	unsigned long const *p_ul;
-	unsigned long s;
-
-	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
-			     RISCV_ISA_EXT_ZBC, 1)
-		 : : : : legacy);
-
-	/* Handle the unaligned head. */
-	offset = (unsigned long)p & OFFSET_MASK;
-	if (offset && len) {
-		head_len = min(STEP - offset, len);
-		crc = crc32_le_unaligned(crc, p, head_len, poly, poly_qt);
-		p += head_len;
-		len -= head_len;
-	}
-
-	tail_len = len & OFFSET_MASK;
-	len = len >> STEP_ORDER;
-	p_ul = (unsigned long const *)p;
-
-	for (int i = 0; i < len; i++) {
-		s = crc32_le_prep(crc, p_ul);
-		crc = crc32_le_zbc(s, poly, poly_qt);
-		p_ul++;
-	}
-
-	/* Handle the tail bytes. */
-	p = (unsigned char const *)p_ul;
-	if (tail_len)
-		crc = crc32_le_unaligned(crc, p, tail_len, poly, poly_qt);
-
-	return crc;
-
-legacy:
-	return crc_fb(crc, p, len);
-}
-
-u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, CRC32_POLY_LE, CRC32_POLY_QT_LE,
-				crc32_le_base);
-}
-EXPORT_SYMBOL(crc32_le_arch);
-
-u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, CRC32C_POLY_LE,
-				CRC32C_POLY_QT_LE, crc32c_le_base);
-}
-EXPORT_SYMBOL(crc32c_le_arch);
-
-static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p,
-				     size_t len)
-{
-	size_t bits = len * 8;
-	unsigned long s = 0;
-	u32 crc_low = 0;
-
-	s = 0;
-	for (int i = 0; i < len; i++)
-		s = *p++ | (s << 8);
-
-	if (__riscv_xlen == 32 || len < sizeof(u32)) {
-		s ^= crc >> (32 - bits);
-		crc_low = crc << bits;
-	} else {
-		s ^= (unsigned long)crc << (bits - 32);
-	}
-
-	crc = crc32_be_zbc(s);
-	crc ^= crc_low;
-
-	return crc;
-}
-
-u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len)
-{
-	size_t offset, head_len, tail_len;
-	unsigned long const *p_ul;
-	unsigned long s;
-
-	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
-			     RISCV_ISA_EXT_ZBC, 1)
-		 : : : : legacy);
-
-	/* Handle the unaligned head. */
-	offset = (unsigned long)p & OFFSET_MASK;
-	if (offset && len) {
-		head_len = min(STEP - offset, len);
-		crc = crc32_be_unaligned(crc, p, head_len);
-		p += head_len;
-		len -= head_len;
-	}
-
-	tail_len = len & OFFSET_MASK;
-	len = len >> STEP_ORDER;
-	p_ul = (unsigned long const *)p;
-
-	for (int i = 0; i < len; i++) {
-		s = crc32_be_prep(crc, p_ul);
-		crc = crc32_be_zbc(s);
-		p_ul++;
-	}
-
-	/* Handle the tail bytes. */
-	p = (unsigned char const *)p_ul;
-	if (tail_len)
-		crc = crc32_be_unaligned(crc, p, tail_len);
-
-	return crc;
-
-legacy:
-	return crc32_be_base(crc, p, len);
-}
-EXPORT_SYMBOL(crc32_be_arch);
-
-u32 crc32_optimizations(void)
-{
-	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
-		return CRC32_LE_OPTIMIZATION |
-		       CRC32_BE_OPTIMIZATION |
-		       CRC32C_OPTIMIZATION;
-	return 0;
-}
-EXPORT_SYMBOL(crc32_optimizations);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension");
diff --git a/arch/riscv/lib/crc32.c b/arch/riscv/lib/crc32.c
new file mode 100644
index 000000000000..a3188b7d9c40
--- /dev/null
+++ b/arch/riscv/lib/crc32.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized CRC32 functions
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+#include <linux/crc32.h>
+#include <linux/module.h>
+
+#include "crc-clmul.h"
+
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc32_lsb_clmul(crc, p, len,
+				       &crc32_lsb_0xedb88320_consts);
+	return crc32_le_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le_arch);
+
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc32_msb_clmul(crc, p, len,
+				       &crc32_msb_0x04c11db7_consts);
+	return crc32_be_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be_arch);
+
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc32_lsb_clmul(crc, p, len,
+				       &crc32_lsb_0x82f63b78_consts);
+	return crc32c_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32c_arch);
+
+u32 crc32_optimizations(void)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return CRC32_LE_OPTIMIZATION |
+		       CRC32_BE_OPTIMIZATION |
+		       CRC32C_OPTIMIZATION;
+	return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_DESCRIPTION("RISC-V optimized CRC32 functions");
+MODULE_LICENSE("GPL");
diff --git a/arch/riscv/lib/crc32_lsb.c b/arch/riscv/lib/crc32_lsb.c
new file mode 100644
index 000000000000..72fd67e7470c
--- /dev/null
+++ b/arch/riscv/lib/crc32_lsb.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized least-significant-bit-first CRC32
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "crc-clmul.h"
+
+typedef u32 crc_t;
+#define LSB_CRC 1
+#include "crc-clmul-template.h"
+
+u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts)
+{
+	return crc_clmul(crc, p, len, consts);
+}
diff --git a/arch/riscv/lib/crc32_msb.c b/arch/riscv/lib/crc32_msb.c
new file mode 100644
index 000000000000..fdbeaccc369f
--- /dev/null
+++ b/arch/riscv/lib/crc32_msb.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized most-significant-bit-first CRC32
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "crc-clmul.h"
+
+typedef u32 crc_t;
+#define LSB_CRC 0
+#include "crc-clmul-template.h"
+
+u32 crc32_msb_clmul(u32 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts)
+{
+	return crc_clmul(crc, p, len, consts);
+}
diff --git a/arch/riscv/lib/crc64.c b/arch/riscv/lib/crc64.c
new file mode 100644
index 000000000000..f0015a27836a
--- /dev/null
+++ b/arch/riscv/lib/crc64.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized CRC64 functions
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+#include <linux/crc64.h>
+#include <linux/module.h>
+
+#include "crc-clmul.h"
+
+u64 crc64_be_arch(u64 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc64_msb_clmul(crc, p, len,
+				       &crc64_msb_0x42f0e1eba9ea3693_consts);
+	return crc64_be_generic(crc, p, len);
+}
+EXPORT_SYMBOL(crc64_be_arch);
+
+u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len)
+{
+	if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC))
+		return crc64_lsb_clmul(crc, p, len,
+				       &crc64_lsb_0x9a6c9329ac4bc9b5_consts);
+	return crc64_nvme_generic(crc, p, len);
+}
+EXPORT_SYMBOL(crc64_nvme_arch);
+
+MODULE_DESCRIPTION("RISC-V optimized CRC64 functions");
+MODULE_LICENSE("GPL");
diff --git a/arch/riscv/lib/crc64_lsb.c b/arch/riscv/lib/crc64_lsb.c
new file mode 100644
index 000000000000..c5371bb85d90
--- /dev/null
+++ b/arch/riscv/lib/crc64_lsb.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized least-significant-bit-first CRC64
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "crc-clmul.h"
+
+typedef u64 crc_t;
+#define LSB_CRC 1
+#include "crc-clmul-template.h"
+
+u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts)
+{
+	return crc_clmul(crc, p, len, consts);
+}
diff --git a/arch/riscv/lib/crc64_msb.c b/arch/riscv/lib/crc64_msb.c
new file mode 100644
index 000000000000..1925d1dbe225
--- /dev/null
+++ b/arch/riscv/lib/crc64_msb.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RISC-V optimized most-significant-bit-first CRC64
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include "crc-clmul.h"
+
+typedef u64 crc_t;
+#define LSB_CRC 0
+#include "crc-clmul-template.h"
+
+u64 crc64_msb_clmul(u64 crc, const void *p, size_t len,
+		    const struct crc_clmul_consts *consts)
+{
+	return crc_clmul(crc, p, len, consts);
+}
diff --git a/arch/riscv/lib/crypto/Kconfig b/arch/riscv/lib/crypto/Kconfig
new file mode 100644
index 000000000000..47c99ea97ce2
--- /dev/null
+++ b/arch/riscv/lib/crypto/Kconfig
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA_RISCV64
+	tristate
+	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+
+config CRYPTO_SHA256_RISCV64
+	tristate
+	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD
+	select CRYPTO_LIB_SHA256_GENERIC
diff --git a/arch/riscv/lib/crypto/Makefile b/arch/riscv/lib/crypto/Makefile
new file mode 100644
index 000000000000..b7cb877a2c07
--- /dev/null
+++ b/arch/riscv/lib/crypto/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o
+chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o
+
+obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o
+sha256-riscv64-y := sha256.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o
diff --git a/arch/riscv/lib/crypto/chacha-riscv64-glue.c b/arch/riscv/lib/crypto/chacha-riscv64-glue.c
new file mode 100644
index 000000000000..8c3f11d79be3
--- /dev/null
+++ b/arch/riscv/lib/crypto/chacha-riscv64-glue.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ChaCha stream cipher (RISC-V optimized)
+ *
+ * Copyright (C) 2023 SiFive, Inc.
+ * Author: Jerry Shih <jerry.shih@sifive.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/vector.h>
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/linkage.h>
+#include <linux/module.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_zvkb);
+
+asmlinkage void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out,
+			    size_t nblocks, int nrounds);
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	hchacha_block_generic(state, out, nrounds);
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	u8 block_buffer[CHACHA_BLOCK_SIZE];
+	unsigned int full_blocks = bytes / CHACHA_BLOCK_SIZE;
+	unsigned int tail_bytes = bytes % CHACHA_BLOCK_SIZE;
+
+	if (!static_branch_likely(&use_zvkb) || !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	kernel_vector_begin();
+	if (full_blocks) {
+		chacha_zvkb(state, src, dst, full_blocks, nrounds);
+		src += full_blocks * CHACHA_BLOCK_SIZE;
+		dst += full_blocks * CHACHA_BLOCK_SIZE;
+	}
+	if (tail_bytes) {
+		memcpy(block_buffer, src, tail_bytes);
+		chacha_zvkb(state, block_buffer, block_buffer, 1, nrounds);
+		memcpy(dst, block_buffer, tail_bytes);
+	}
+	kernel_vector_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return static_key_enabled(&use_zvkb);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init riscv64_chacha_mod_init(void)
+{
+	if (riscv_isa_extension_available(NULL, ZVKB) &&
+	    riscv_vector_vlen() >= 128)
+		static_branch_enable(&use_zvkb);
+	return 0;
+}
+subsys_initcall(riscv64_chacha_mod_init);
+
+static void __exit riscv64_chacha_mod_exit(void)
+{
+}
+module_exit(riscv64_chacha_mod_exit);
+
+MODULE_DESCRIPTION("ChaCha stream cipher (RISC-V optimized)");
+MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>");
+MODULE_LICENSE("GPL");
diff --git a/arch/riscv/crypto/chacha-riscv64-zvkb.S b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S
index bf057737ac69..b777d0b4e379 100644
--- a/arch/riscv/crypto/chacha-riscv64-zvkb.S
+++ b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S
@@ -46,11 +46,11 @@
 .text
 .option arch, +zvkb
 
-#define KEYP		a0
+#define STATEP		a0
 #define INP		a1
 #define OUTP		a2
-#define LEN		a3
-#define IVP		a4
+#define NBLOCKS		a3
+#define NROUNDS		a4
 
 #define CONSTS0		a5
 #define CONSTS1		a6
@@ -59,7 +59,7 @@
 #define TMP		t1
 #define VL		t2
 #define STRIDE		t3
-#define NROUNDS		t4
+#define ROUND_CTR	t4
 #define KEY0		s0
 #define KEY1		s1
 #define KEY2		s2
@@ -132,14 +132,16 @@
 	vror.vi		\b3, \b3, 32 - 7
 .endm
 
-// void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out, size_t len,
-//		      const u32 iv[4]);
+// void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out,
+//		    size_t nblocks, int nrounds);
 //
-// |len| must be nonzero and a multiple of 64 (CHACHA_BLOCK_SIZE).
-// The counter is treated as 32-bit, following the RFC7539 convention.
-SYM_FUNC_START(chacha20_zvkb)
-	srli		LEN, LEN, 6	// Bytes to blocks
-
+// |nblocks| is the number of 64-byte blocks to process, and must be nonzero.
+//
+// |state| gives the ChaCha state matrix, including the 32-bit counter in
+// state->x[12] following the RFC7539 convention; note that this differs from
+// the original Salsa20 paper which uses a 64-bit counter in state->x[12..13].
+// The updated 32-bit counter is written back to state->x[12] before returning.
+SYM_FUNC_START(chacha_zvkb)
 	addi		sp, sp, -96
 	sd		s0, 0(sp)
 	sd		s1, 8(sp)
@@ -157,26 +159,26 @@ SYM_FUNC_START(chacha20_zvkb)
 	li		STRIDE, 64
 
 	// Set up the initial state matrix in scalar registers.
-	li		CONSTS0, 0x61707865	// "expa" little endian
-	li		CONSTS1, 0x3320646e	// "nd 3" little endian
-	li		CONSTS2, 0x79622d32	// "2-by" little endian
-	li		CONSTS3, 0x6b206574	// "te k" little endian
-	lw		KEY0, 0(KEYP)
-	lw		KEY1, 4(KEYP)
-	lw		KEY2, 8(KEYP)
-	lw		KEY3, 12(KEYP)
-	lw		KEY4, 16(KEYP)
-	lw		KEY5, 20(KEYP)
-	lw		KEY6, 24(KEYP)
-	lw		KEY7, 28(KEYP)
-	lw		COUNTER, 0(IVP)
-	lw		NONCE0, 4(IVP)
-	lw		NONCE1, 8(IVP)
-	lw		NONCE2, 12(IVP)
+	lw		CONSTS0, 0(STATEP)
+	lw		CONSTS1, 4(STATEP)
+	lw		CONSTS2, 8(STATEP)
+	lw		CONSTS3, 12(STATEP)
+	lw		KEY0, 16(STATEP)
+	lw		KEY1, 20(STATEP)
+	lw		KEY2, 24(STATEP)
+	lw		KEY3, 28(STATEP)
+	lw		KEY4, 32(STATEP)
+	lw		KEY5, 36(STATEP)
+	lw		KEY6, 40(STATEP)
+	lw		KEY7, 44(STATEP)
+	lw		COUNTER, 48(STATEP)
+	lw		NONCE0, 52(STATEP)
+	lw		NONCE1, 56(STATEP)
+	lw		NONCE2, 60(STATEP)
 
 .Lblock_loop:
 	// Set vl to the number of blocks to process in this iteration.
-	vsetvli		VL, LEN, e32, m1, ta, ma
+	vsetvli		VL, NBLOCKS, e32, m1, ta, ma
 
 	// Set up the initial state matrix for the next VL blocks in v0-v15.
 	// v{i} holds the i'th 32-bit word of the state matrix for all blocks.
@@ -203,16 +205,16 @@ SYM_FUNC_START(chacha20_zvkb)
 	// v{16+i} holds the i'th 32-bit word for all blocks.
 	vlsseg8e32.v	v16, (INP), STRIDE
 
-	li		NROUNDS, 20
+	mv		ROUND_CTR, NROUNDS
 .Lnext_doubleround:
-	addi		NROUNDS, NROUNDS, -2
+	addi		ROUND_CTR, ROUND_CTR, -2
 	// column round
 	chacha_round	v0, v4, v8, v12, v1, v5, v9, v13, \
 			v2, v6, v10, v14, v3, v7, v11, v15
 	// diagonal round
 	chacha_round	v0, v5, v10, v15, v1, v6, v11, v12, \
 			v2, v7, v8, v13, v3, v4, v9, v14
-	bnez		NROUNDS, .Lnext_doubleround
+	bnez		ROUND_CTR, .Lnext_doubleround
 
 	// Load the second half of the input data for each block into v24-v31.
 	// v{24+i} holds the {8+i}'th 32-bit word for all blocks.
@@ -271,12 +273,13 @@ SYM_FUNC_START(chacha20_zvkb)
 	// Update the counter, the remaining number of blocks, and the input and
 	// output pointers according to the number of blocks processed (VL).
 	add		COUNTER, COUNTER, VL
-	sub		LEN, LEN, VL
+	sub		NBLOCKS, NBLOCKS, VL
 	slli		TMP, VL, 6
 	add		OUTP, OUTP, TMP
 	add		INP, INP, TMP
-	bnez		LEN, .Lblock_loop
+	bnez		NBLOCKS, .Lblock_loop
 
+	sw		COUNTER, 48(STATEP)
 	ld		s0, 0(sp)
 	ld		s1, 8(sp)
 	ld		s2, 16(sp)
@@ -291,4 +294,4 @@ SYM_FUNC_START(chacha20_zvkb)
 	ld		s11, 88(sp)
 	addi		sp, sp, 96
 	ret
-SYM_FUNC_END(chacha20_zvkb)
+SYM_FUNC_END(chacha_zvkb)
diff --git a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S
index 8ebcc17de4dc..fad501ad0617 100644
--- a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S
+++ b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S
@@ -43,7 +43,7 @@
 // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknha' or 'Zvknhb')
 // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb')
 
-#include <linux/cfi_types.h>
+#include <linux/linkage.h>
 
 .text
 .option arch, +zvknha, +zvkb
@@ -106,9 +106,9 @@
 	sha256_4rounds	\last, \k3, W3, W0, W1, W2
 .endm
 
-// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[8], const u8 *data,
-//					       int num_blocks);
-SYM_TYPED_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb)
+// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[SHA256_STATE_WORDS],
+//					       const u8 *data, size_t nblocks);
+SYM_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb)
 
 	// Load the round constants into K0-K15.
 	vsetivli	zero, 4, e32, m1, ta, ma
diff --git a/arch/riscv/lib/crypto/sha256.c b/arch/riscv/lib/crypto/sha256.c
new file mode 100644
index 000000000000..71808397dff4
--- /dev/null
+++ b/arch/riscv/lib/crypto/sha256.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 (RISC-V accelerated)
+ *
+ * Copyright (C) 2022 VRULL GmbH
+ * Author: Heiko Stuebner <heiko.stuebner@vrull.eu>
+ *
+ * Copyright (C) 2023 SiFive, Inc.
+ * Author: Jerry Shih <jerry.shih@sifive.com>
+ */
+
+#include <asm/vector.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb(
+	u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_extensions);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_extensions)) {
+		kernel_vector_begin();
+		sha256_transform_zvknha_or_zvknhb_zvkb(state, data, nblocks);
+		kernel_vector_end();
+	} else {
+		sha256_blocks_generic(state, data, nblocks);
+	}
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_extensions);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init riscv64_sha256_mod_init(void)
+{
+	/* Both zvknha and zvknhb provide the SHA-256 instructions. */
+	if ((riscv_isa_extension_available(NULL, ZVKNHA) ||
+	     riscv_isa_extension_available(NULL, ZVKNHB)) &&
+	    riscv_isa_extension_available(NULL, ZVKB) &&
+	    riscv_vector_vlen() >= 128)
+		static_branch_enable(&have_extensions);
+	return 0;
+}
+subsys_initcall(riscv64_sha256_mod_init);
+
+static void __exit riscv64_sha256_mod_exit(void)
+{
+}
+module_exit(riscv64_sha256_mod_exit);
+
+MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)");
+MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>");
+MODULE_LICENSE("GPL");
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index 7fb12c59e571..9408f50ca59a 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -40,12 +40,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	uproto = (__force unsigned int)htonl(proto);
 	sum += uproto;
 
-	/*
-	 * Zbb support saves 4 instructions, so not worth checking without
-	 * alternatives if supported
-	 */
-	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
-	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
 		unsigned long fold_temp;
 
 		/*
@@ -157,12 +152,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 	csum = do_csum_common(ptr, end, data);
 
 #ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT
-	/*
-	 * Zbb support saves 6 instructions, so not worth checking without
-	 * alternatives if supported
-	 */
-	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
-	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
 		unsigned long fold_temp;
 
 		/*
@@ -244,12 +234,7 @@ do_csum_no_alignment(const unsigned char *buff, int len)
 	end = (const unsigned long *)(buff + len);
 	csum = do_csum_common(ptr, end, data);
 
-	/*
-	 * Zbb support saves 6 instructions, so not worth checking without
-	 * alternatives if supported
-	 */
-	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
-	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
 		unsigned long fold_temp;
 
 		/*
diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S
index 57a5c0066231..65027e742af1 100644
--- a/arch/riscv/lib/strcmp.S
+++ b/arch/riscv/lib/strcmp.S
@@ -8,7 +8,8 @@
 /* int strcmp(const char *cs, const char *ct) */
 SYM_FUNC_START(strcmp)
 
-	ALTERNATIVE("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB)
+	__ALTERNATIVE_CFG("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB,
+		IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB))
 
 	/*
 	 * Returns
@@ -43,7 +44,7 @@ SYM_FUNC_START(strcmp)
  * The code was published as part of the bitmanip manual
  * in Appendix A.
  */
-#ifdef CONFIG_RISCV_ISA_ZBB
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
 strcmp_zbb:
 
 .option push
diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S
index 962983b73251..eb4d2b7ed22b 100644
--- a/arch/riscv/lib/strlen.S
+++ b/arch/riscv/lib/strlen.S
@@ -8,7 +8,8 @@
 /* int strlen(const char *s) */
 SYM_FUNC_START(strlen)
 
-	ALTERNATIVE("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB)
+	__ALTERNATIVE_CFG("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB,
+		IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB))
 
 	/*
 	 * Returns
@@ -33,7 +34,7 @@ SYM_FUNC_START(strlen)
 /*
  * Variant of strlen using the ZBB extension if available
  */
-#ifdef CONFIG_RISCV_ISA_ZBB
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
 strlen_zbb:
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S
index 7b2d0ff9ed6c..062000c468c8 100644
--- a/arch/riscv/lib/strncmp.S
+++ b/arch/riscv/lib/strncmp.S
@@ -8,7 +8,8 @@
 /* int strncmp(const char *cs, const char *ct, size_t count) */
 SYM_FUNC_START(strncmp)
 
-	ALTERNATIVE("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB)
+	__ALTERNATIVE_CFG("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB,
+		IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB))
 
 	/*
 	 * Returns
@@ -46,7 +47,7 @@ SYM_FUNC_START(strncmp)
 /*
  * Variant of strncmp using the ZBB extension if available
  */
-#ifdef CONFIG_RISCV_ISA_ZBB
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
 strncmp_zbb:
 
 .option push
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index cbe4d775ef56..b916a68d324a 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -19,7 +19,7 @@ obj-y += context.o
 obj-y += pmem.o
 
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
+obj-$(CONFIG_PTDUMP) += ptdump.o
 obj-$(CONFIG_KASAN)   += kasan_init.o
 
 ifdef CONFIG_KASAN
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 4abe3de23225..55c20ad1f744 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -158,7 +158,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 	 *
 	 * - We get a zero back from the cmpxchg and end up waiting on the
 	 *   lock. Taking the lock synchronises with the rollover and so
-	 *   we are forced to see the updated verion.
+	 *   we are forced to see the updated version.
 	 *
 	 * - We get a valid context back from the cmpxchg then we continue
 	 *   using old ASID because __flush_context() would have marked ASID
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 42314f093922..375dd96bb4a0 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -148,22 +148,25 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
-			      unsigned long pte_num)
+			      unsigned long ncontig)
 {
-	pte_t orig_pte = ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) {
-		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
-
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += PAGE_SIZE;
+		tmp_pte = ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -212,6 +215,26 @@ static void clear_flush(struct mm_struct *mm,
 	flush_tlb_range(&vma, saddr, addr);
 }
 
+static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize)
+{
+	unsigned long hugepage_shift;
+
+	if (sz >= PGDIR_SIZE)
+		hugepage_shift = PGDIR_SHIFT;
+	else if (sz >= P4D_SIZE)
+		hugepage_shift = P4D_SHIFT;
+	else if (sz >= PUD_SIZE)
+		hugepage_shift = PUD_SHIFT;
+	else if (sz >= PMD_SIZE)
+		hugepage_shift = PMD_SHIFT;
+	else
+		hugepage_shift = PAGE_SHIFT;
+
+	*pgsize = 1 << hugepage_shift;
+
+	return sz >> hugepage_shift;
+}
+
 /*
  * When dealing with NAPOT mappings, the privileged specification indicates that
  * "if an update needs to be made, the OS generally should first mark all of the
@@ -226,22 +249,10 @@ void set_huge_pte_at(struct mm_struct *mm,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift, pgsize;
+	size_t pgsize;
 	int i, pte_num;
 
-	if (sz >= PGDIR_SIZE)
-		hugepage_shift = PGDIR_SHIFT;
-	else if (sz >= P4D_SIZE)
-		hugepage_shift = P4D_SHIFT;
-	else if (sz >= PUD_SIZE)
-		hugepage_shift = PUD_SHIFT;
-	else if (sz >= PMD_SIZE)
-		hugepage_shift = PMD_SHIFT;
-	else
-		hugepage_shift = PAGE_SHIFT;
-
-	pte_num = sz >> hugepage_shift;
-	pgsize = 1 << hugepage_shift;
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
@@ -293,15 +304,16 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
+	size_t pgsize;
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
 
 	if (!pte_napot(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
 
-	pte_num = napot_pte_num(napot_cont_order(orig_pte));
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	return get_clear_contig(mm, addr, ptep, pte_num);
 }
@@ -351,6 +363,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
+	size_t pgsize;
 	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
@@ -359,8 +372,9 @@ void huge_pte_clear(struct mm_struct *mm,
 		return;
 	}
 
-	pte_num = napot_pte_num(napot_cont_order(pte));
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	for (i = 0; i < pte_num; i++, addr += pgsize, ptep++)
 		pte_clear(mm, addr, ptep);
 }
 
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 15b2eda4c364..ab475ec6ca42 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -20,15 +20,13 @@
 #include <linux/dma-map-ops.h>
 #include <linux/crash_dump.h>
 #include <linux/hugetlb.h>
-#ifdef CONFIG_RELOCATABLE
-#include <linux/elf.h>
-#endif
 #include <linux/kfence.h>
 #include <linux/execmem.h>
 
 #include <asm/fixmap.h>
 #include <asm/io.h>
 #include <asm/kasan.h>
+#include <asm/module.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
@@ -171,7 +169,7 @@ static void __init print_vm_layout(void)
 static void print_vm_layout(void) { }
 #endif /* CONFIG_DEBUG_VM */
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
 #ifdef CONFIG_FLATMEM
@@ -192,7 +190,6 @@ void __init mem_init(void)
 	}
 
 	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
-	memblock_free_all();
 
 	print_vm_layout();
 }
@@ -295,10 +292,8 @@ static void __init setup_bootmem(void)
 	phys_ram_end = memblock_end_of_DRAM();
 	min_low_pfn = PFN_UP(phys_ram_base);
 	max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
-	high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
 
 	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
-	set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
 
 	reserve_initrd_mem();
 
@@ -323,6 +318,44 @@ static void __init setup_bootmem(void)
 		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
 }
 
+#ifdef CONFIG_RELOCATABLE
+extern unsigned long __rela_dyn_start, __rela_dyn_end;
+
+static void __init relocate_kernel(void)
+{
+	Elf_Rela *rela = (Elf_Rela *)&__rela_dyn_start;
+	/*
+	 * This holds the offset between the linked virtual address and the
+	 * relocated virtual address.
+	 */
+	uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR;
+	/*
+	 * This holds the offset between kernel linked virtual address and
+	 * physical address.
+	 */
+	uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr;
+
+	for ( ; rela < (Elf_Rela *)&__rela_dyn_end; rela++) {
+		Elf_Addr addr = (rela->r_offset - va_kernel_link_pa_offset);
+		Elf_Addr relocated_addr = rela->r_addend;
+
+		if (rela->r_info != R_RISCV_RELATIVE)
+			continue;
+
+		/*
+		 * Make sure to not relocate vdso symbols like rt_sigreturn
+		 * which are linked from the address 0 in vmlinux since
+		 * vdso symbol addresses are actually used as an offset from
+		 * mm->context.vdso in VDSO_OFFSET macro.
+		 */
+		if (relocated_addr >= KERNEL_LINK_ADDR)
+			relocated_addr += reloc_offset;
+
+		*(Elf_Addr *)addr = relocated_addr;
+	}
+}
+#endif /* CONFIG_RELOCATABLE */
+
 #ifdef CONFIG_MMU
 struct pt_alloc_ops pt_ops __meminitdata;
 
@@ -823,6 +856,8 @@ static __init void set_satp_mode(uintptr_t dtb_pa)
 	uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
 	u64 satp_mode_cmdline = __pi_set_satp_mode_from_cmdline(dtb_pa);
 
+	kernel_map.page_offset = PAGE_OFFSET_L5;
+
 	if (satp_mode_cmdline == SATP_MODE_57) {
 		disable_pgtable_l5();
 	} else if (satp_mode_cmdline == SATP_MODE_48) {
@@ -893,44 +928,6 @@ retry:
 #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
 #endif
 
-#ifdef CONFIG_RELOCATABLE
-extern unsigned long __rela_dyn_start, __rela_dyn_end;
-
-static void __init relocate_kernel(void)
-{
-	Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start;
-	/*
-	 * This holds the offset between the linked virtual address and the
-	 * relocated virtual address.
-	 */
-	uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR;
-	/*
-	 * This holds the offset between kernel linked virtual address and
-	 * physical address.
-	 */
-	uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr;
-
-	for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) {
-		Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset);
-		Elf64_Addr relocated_addr = rela->r_addend;
-
-		if (rela->r_info != R_RISCV_RELATIVE)
-			continue;
-
-		/*
-		 * Make sure to not relocate vdso symbols like rt_sigreturn
-		 * which are linked from the address 0 in vmlinux since
-		 * vdso symbol addresses are actually used as an offset from
-		 * mm->context.vdso in VDSO_OFFSET macro.
-		 */
-		if (relocated_addr >= KERNEL_LINK_ADDR)
-			relocated_addr += reloc_offset;
-
-		*(Elf64_Addr *)addr = relocated_addr;
-	}
-}
-#endif /* CONFIG_RELOCATABLE */
-
 #ifdef CONFIG_XIP_KERNEL
 static void __init create_kernel_page_table(pgd_t *pgdir,
 					    __always_unused bool early)
@@ -1108,11 +1105,6 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset;
 
 #ifdef CONFIG_XIP_KERNEL
-#ifdef CONFIG_64BIT
-	kernel_map.page_offset = PAGE_OFFSET_L3;
-#else
-	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
-#endif
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
 	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
@@ -1127,7 +1119,6 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	kernel_map.va_kernel_xip_data_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr
 						+ (uintptr_t)&_sdata - (uintptr_t)&_start;
 #else
-	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 	kernel_map.phys_addr = (uintptr_t)(&_start);
 	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
@@ -1174,7 +1165,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	 * makes the kernel cross over a PUD_SIZE boundary, raise a bug
 	 * since a part of the kernel would not get mapped.
 	 */
-	BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size);
+	if (IS_ENABLED(CONFIG_64BIT))
+		BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size);
 	relocate_kernel();
 #endif
 
@@ -1378,6 +1370,12 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
 	dtb_early_va = (void *)dtb_pa;
 	dtb_early_pa = dtb_pa;
+
+#ifdef CONFIG_RELOCATABLE
+	kernel_map.virt_addr = (uintptr_t)_start;
+	kernel_map.phys_addr = (uintptr_t)_start;
+	relocate_kernel();
+#endif
 }
 
 static inline void setup_vm_final(void)
@@ -1396,21 +1394,19 @@ static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 void __init paging_init(void)
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
index 18706f457da7..559d291fac5c 100644
--- a/arch/riscv/mm/physaddr.c
+++ b/arch/riscv/mm/physaddr.c
@@ -12,7 +12,7 @@ phys_addr_t __virt_to_phys(unsigned long x)
 	 * Boundary checking aginst the kernel linear mapping space.
 	 */
 	WARN(!is_linear_mapping(x) && !is_kernel_mapping(x),
-	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     "virt_to_phys used for non-linear address: %p (%pS)\n",
 	     (void *)x, (void *)x);
 
 	return __va_to_pa_nodebug(x);
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 9b6e86ce3867..f9e27ba1df99 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -4,6 +4,7 @@
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
+#include <linux/mmu_notifier.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
@@ -78,10 +79,17 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+	return mm ? cntx2asid(atomic_long_read(&mm->context.id)) : FLUSH_TLB_NO_ASID;
+}
+
+static void __flush_tlb_range(struct mm_struct *mm,
+			      const struct cpumask *cmask,
 			      unsigned long start, unsigned long size,
 			      unsigned long stride)
 {
+	unsigned long asid = get_mm_asid(mm);
 	unsigned int cpu;
 
 	if (cpumask_empty(cmask))
@@ -105,30 +113,26 @@ static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
 	}
 
 	put_cpu();
-}
 
-static inline unsigned long get_mm_asid(struct mm_struct *mm)
-{
-	return cntx2asid(atomic_long_read(&mm->context.id));
+	if (mm)
+		mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, start + size);
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
-			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	__flush_tlb_range(mm, mm_cpumask(mm), 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 }
 
 void flush_tlb_mm_range(struct mm_struct *mm,
 			unsigned long start, unsigned long end,
 			unsigned int page_size)
 {
-	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
-			  start, end - start, page_size);
+	__flush_tlb_range(mm, mm_cpumask(mm), start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
-	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
 			  addr, PAGE_SIZE, PAGE_SIZE);
 }
 
@@ -161,13 +165,13 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		}
 	}
 
-	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
 			  start, end - start, stride_size);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	__flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
+	__flush_tlb_range(NULL, cpu_online_mask,
 			  start, end - start, PAGE_SIZE);
 }
 
@@ -175,7 +179,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
 {
-	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
 			  start, end - start, PMD_SIZE);
 }
 #endif
@@ -186,10 +190,10 @@ bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 }
 
 void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-			       struct mm_struct *mm,
-			       unsigned long uaddr)
+		struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 void arch_flush_tlb_batched_pending(struct mm_struct *mm)
@@ -199,7 +203,7 @@ void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
-			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	__flush_tlb_range(NULL, &batch->cpumask,
+			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
 	cpumask_clear(&batch->cpumask);
 }
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
index 0e6ca6d5ae4b..c5db2f072c34 100644
--- a/arch/riscv/purgatory/entry.S
+++ b/arch/riscv/purgatory/entry.S
@@ -12,6 +12,7 @@
 
 .text
 
+.align	2
 SYM_CODE_START(purgatory_start)
 
 	lla	sp, .Lstack
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9c9ec08d78c7..0c16dc443e2f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -41,9 +41,6 @@ config AUDIT_ARCH
 config NO_IOPORT_MAP
 	def_bool y
 
-config PCI_QUIRKS
-	def_bool n
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
@@ -73,7 +70,6 @@ config S390
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT
 	select ALTERNATE_USER_ADDRESS_SPACE
 	select ARCH_32BIT_USTAT_F_TINODE
-	select ARCH_BINFMT_ELF_STATE
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
@@ -96,6 +92,7 @@ config S390
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_PREEMPT_LAZY
+	select ARCH_HAS_PTDUMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME
 	select ARCH_HAS_SET_DIRECT_MAP
@@ -140,6 +137,7 @@ config S390
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && CC_IS_CLANG
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_USE_BUILTIN_BSWAP
@@ -148,6 +146,7 @@ config S390
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_KERNEL_PMD_MKWRITE
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
@@ -163,9 +162,9 @@ config S390
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
-	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GENERIC_IOREMAP if PCI
 	select HAVE_ALIGNED_STRUCT_PAGE
@@ -185,6 +184,7 @@ config S390
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_VMAP_STACK
 	select HAVE_ASM_MODVERSIONS
+	select HAVE_BUILDTIME_MCOUNT_SORT
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
@@ -241,6 +241,7 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_VIRT_CPU_ACCOUNTING_IDLE
+	select HOTPLUG_SMT
 	select IOMMU_HELPER		if PCI
 	select IOMMU_SUPPORT		if PCI
 	select KASAN_VMALLOC if KASAN
@@ -258,6 +259,7 @@ config S390
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
 	select PCI_MSI_ARCH_FALLBACKS	if PCI_MSI
+	select PCI_QUIRKS		if PCI
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
@@ -331,6 +333,10 @@ config HAVE_MARCH_Z16_FEATURES
 	def_bool n
 	select HAVE_MARCH_Z15_FEATURES
 
+config HAVE_MARCH_Z17_FEATURES
+	def_bool n
+	select HAVE_MARCH_Z16_FEATURES
+
 choice
 	prompt "Processor type"
 	default MARCH_Z196
@@ -396,6 +402,14 @@ config MARCH_Z16
 	  Select this to enable optimizations for IBM z16 (3931 and
 	  3932 series).
 
+config MARCH_Z17
+	bool "IBM z17"
+	select HAVE_MARCH_Z17_FEATURES
+	depends on $(cc-option,-march=z17)
+	help
+	  Select this to enable optimizations for IBM z17 (9175 and
+	  9176 series).
+
 endchoice
 
 config MARCH_Z10_TUNE
@@ -419,6 +433,9 @@ config MARCH_Z15_TUNE
 config MARCH_Z16_TUNE
 	def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT
 
+config MARCH_Z17_TUNE
+	def_bool TUNE_Z17 || MARCH_Z17 && TUNE_DEFAULT
+
 choice
 	prompt "Tune code generation"
 	default TUNE_DEFAULT
@@ -463,6 +480,10 @@ config TUNE_Z16
 	bool "IBM z16"
 	depends on $(cc-option,-mtune=z16)
 
+config TUNE_Z17
+	bool "IBM z17"
+	depends on $(cc-option,-mtune=z17)
+
 endchoice
 
 config 64BIT
@@ -630,6 +651,7 @@ endchoice
 
 config RELOCATABLE
 	def_bool y
+	select ARCH_VMLINUX_NEEDS_RELOCS
 	help
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded at an arbitrary address.
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index c4300ea4abf8..7955d7eee7d8 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -13,6 +13,16 @@ config DEBUG_ENTRY
 
 	  If unsure, say N.
 
+config STRICT_MM_TYPECHECKS
+	bool "Strict Memory Management Type Checks"
+	depends on DEBUG_KERNEL
+	help
+	  Enable strict type checking for memory management types like pte_t
+	  and pmd_t. This generates slightly worse code and should be used
+	  for debug builds.
+
+	  If unsure, say N.
+
 config CIO_INJECT
 	bool "CIO Inject interfaces"
 	depends on DEBUG_KERNEL && DEBUG_FS
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 5fae311203c2..7679bc16b692 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -15,7 +15,7 @@ KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
 KBUILD_CFLAGS	+= -fPIC
-LDFLAGS_vmlinux	:= -no-pie --emit-relocs --discard-none
+LDFLAGS_vmlinux	:= $(call ld-option,-no-pie)
 extra_tools	:= relocs
 aflags_dwarf	:= -Wa,-gdwarf-2
 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
@@ -48,6 +48,7 @@ mflags-$(CONFIG_MARCH_Z13)    := -march=z13
 mflags-$(CONFIG_MARCH_Z14)    := -march=z14
 mflags-$(CONFIG_MARCH_Z15)    := -march=z15
 mflags-$(CONFIG_MARCH_Z16)    := -march=z16
+mflags-$(CONFIG_MARCH_Z17)    := -march=z17
 
 export CC_FLAGS_MARCH := $(mflags-y)
 
@@ -61,6 +62,7 @@ cflags-$(CONFIG_MARCH_Z13_TUNE)		+= -mtune=z13
 cflags-$(CONFIG_MARCH_Z14_TUNE)		+= -mtune=z14
 cflags-$(CONFIG_MARCH_Z15_TUNE)		+= -mtune=z15
 cflags-$(CONFIG_MARCH_Z16_TUNE)		+= -mtune=z16
+cflags-$(CONFIG_MARCH_Z17_TUNE)		+= -mtune=z17
 
 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 
diff --git a/arch/s390/Makefile.postlink b/arch/s390/Makefile.postlink
index 1ae5478cd6ac..c2b737500a91 100644
--- a/arch/s390/Makefile.postlink
+++ b/arch/s390/Makefile.postlink
@@ -11,7 +11,6 @@ __archpost:
 
 -include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
-include $(srctree)/scripts/Makefile.lib
 
 CMD_RELOCS=arch/s390/tools/relocs
 OUT_RELOCS = arch/s390/boot
@@ -20,9 +19,8 @@ quiet_cmd_relocs = RELOCS  $(OUT_RELOCS)/relocs.S
 	mkdir -p $(OUT_RELOCS); \
 	$(CMD_RELOCS) $@ > $(OUT_RELOCS)/relocs.S
 
-vmlinux: FORCE
+vmlinux.unstripped: FORCE
 	$(call cmd,relocs)
-	$(call cmd,strip_relocs)
 
 clean:
 	@rm -f $(OUT_RELOCS)/relocs.S
diff --git a/arch/s390/boot/.gitignore b/arch/s390/boot/.gitignore
index f5ef099e2fd3..af2a6a7bc028 100644
--- a/arch/s390/boot/.gitignore
+++ b/arch/s390/boot/.gitignore
@@ -5,4 +5,5 @@ relocs.S
 section_cmp.*
 vmlinux
 vmlinux.lds
+vmlinux.map
 vmlinux.syms
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 8bc1308ac892..bee49626be4b 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -26,7 +26,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
 obj-y	:= head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o
 obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o relocs.o alternative.o
+obj-y	+= version.o pgm_check.o ctype.o ipl_data.o relocs.o alternative.o
 obj-y	+= uv.o printk.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 obj-y	+= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
diff --git a/arch/s390/boot/alternative.c b/arch/s390/boot/alternative.c
index abc08d2c873d..19ea7934b918 100644
--- a/arch/s390/boot/alternative.c
+++ b/arch/s390/boot/alternative.c
@@ -1,3 +1,138 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt)	"alt: " fmt
+#include "boot.h"
+
+#define a_debug		boot_debug
 
 #include "../kernel/alternative.c"
+
+static void alt_debug_all(int type)
+{
+	int i;
+
+	switch (type) {
+	case ALT_TYPE_FACILITY:
+		for (i = 0; i < ARRAY_SIZE(alt_debug.facilities); i++)
+			alt_debug.facilities[i] = -1UL;
+		break;
+	case ALT_TYPE_FEATURE:
+		for (i = 0; i < ARRAY_SIZE(alt_debug.mfeatures); i++)
+			alt_debug.mfeatures[i] = -1UL;
+		break;
+	case ALT_TYPE_SPEC:
+		alt_debug.spec = 1;
+		break;
+	}
+}
+
+static void alt_debug_modify(int type, unsigned int nr, bool clear)
+{
+	switch (type) {
+	case ALT_TYPE_FACILITY:
+		if (clear)
+			__clear_facility(nr, alt_debug.facilities);
+		else
+			__set_facility(nr, alt_debug.facilities);
+		break;
+	case ALT_TYPE_FEATURE:
+		if (clear)
+			__clear_machine_feature(nr, alt_debug.mfeatures);
+		else
+			__set_machine_feature(nr, alt_debug.mfeatures);
+		break;
+	}
+}
+
+static char *alt_debug_parse(int type, char *str)
+{
+	unsigned long val, endval;
+	char *endp;
+	bool clear;
+	int i;
+
+	if (*str == ':') {
+		str++;
+	} else {
+		alt_debug_all(type);
+		return str;
+	}
+	clear = false;
+	if (*str == '!') {
+		alt_debug_all(type);
+		clear = true;
+		str++;
+	}
+	while (*str) {
+		val = simple_strtoull(str, &endp, 0);
+		if (str == endp)
+			break;
+		str = endp;
+		if (*str == '-') {
+			str++;
+			endval = simple_strtoull(str, &endp, 0);
+			if (str == endp)
+				break;
+			str = endp;
+			while (val <= endval) {
+				alt_debug_modify(type, val, clear);
+				val++;
+			}
+		} else {
+			alt_debug_modify(type, val, clear);
+		}
+		if (*str != ',')
+			break;
+		str++;
+	}
+	return str;
+}
+
+/*
+ * Use debug-alternative command line parameter for debugging:
+ * "debug-alternative"
+ *  -> print debug message for every single alternative
+ *
+ * "debug-alternative=0;2"
+ * -> print debug message for all alternatives with type 0 and 2
+ *
+ * "debug-alternative=0:0-7"
+ * -> print debug message for all alternatives with type 0 and with
+ *    facility numbers within the range of 0-7
+ *    (if type 0 is ALT_TYPE_FACILITY)
+ *
+ * "debug-alternative=0:!8;1"
+ * -> print debug message for all alternatives with type 0, for all
+ *    facility number, except facility 8, and in addition print all
+ *    alternatives with type 1
+ */
+void alt_debug_setup(char *str)
+{
+	unsigned long type;
+	char *endp;
+	int i;
+
+	if (!str) {
+		alt_debug_all(ALT_TYPE_FACILITY);
+		alt_debug_all(ALT_TYPE_FEATURE);
+		alt_debug_all(ALT_TYPE_SPEC);
+		return;
+	}
+	while (*str) {
+		type = simple_strtoull(str, &endp, 0);
+		if (str == endp)
+			break;
+		str = endp;
+		switch (type) {
+		case ALT_TYPE_FACILITY:
+		case ALT_TYPE_FEATURE:
+			str = alt_debug_parse(type, str);
+			break;
+		case ALT_TYPE_SPEC:
+			alt_debug_all(ALT_TYPE_SPEC);
+			break;
+		}
+		if (*str != ';')
+			break;
+		str++;
+	}
+}
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 69f261566a64..e045cae6e80a 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -11,11 +11,6 @@
 #include <linux/printk.h>
 #include <asm/physmem_info.h>
 
-struct machine_info {
-	unsigned char has_edat1 : 1;
-	unsigned char has_edat2 : 1;
-};
-
 struct vmlinux_info {
 	unsigned long entry;
 	unsigned long image_size;	/* does not include .bss */
@@ -69,7 +64,8 @@ void parse_boot_command_line(void);
 void verify_facilities(void);
 void print_missing_facilities(void);
 void sclp_early_setup_buffer(void);
-void print_pgm_check_info(void);
+void alt_debug_setup(char *str);
+void do_pgm_check(struct pt_regs *regs);
 unsigned long randomize_within_range(unsigned long size, unsigned long align,
 				     unsigned long min, unsigned long max);
 void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit);
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 0a47b16f6412..0b511d5c030b 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -254,8 +254,9 @@ SYM_CODE_START_LOCAL(startup_normal)
 	xc	0xf00(256),0xf00
 	larl	%r13,.Lctl
 	lctlg	%c0,%c15,0(%r13)	# load control registers
-	stcke	__LC_BOOT_CLOCK
-	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
+	larl	%r13,tod_clock_base
+	stcke	0(%r13)
+	mvc	__LC_LAST_UPDATE_CLOCK(8),1(%r13)
 	larl	%r13,6f
 	spt	0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),0(%r13)
@@ -292,12 +293,6 @@ SYM_CODE_END(startup_normal)
 
 #include "head_kdump.S"
 
-#
-# This program check is active immediately after kernel start
-# and until early_pgm_check_handler is set in kernel/early.c
-# It simply saves general/control registers and psw in
-# the save area and does disabled wait with a faulty address.
-#
 SYM_CODE_START_LOCAL(startup_pgm_check_handler)
 	stmg	%r8,%r15,__LC_SAVE_AREA
 	la	%r8,4095
@@ -311,8 +306,18 @@ SYM_CODE_START_LOCAL(startup_pgm_check_handler)
 	oi	__LC_RETURN_PSW+1,0x2	# set wait state bit
 	larl	%r9,.Lold_psw_disabled_wait
 	stg	%r9,__LC_PGM_NEW_PSW+8
-	larl	%r15,_dump_info_stack_end-STACK_FRAME_OVERHEAD
-	brasl	%r14,print_pgm_check_info
+	larl	%r15,_dump_info_stack_end-(STACK_FRAME_OVERHEAD+__PT_SIZE)
+	la	%r2,STACK_FRAME_OVERHEAD(%r15)
+	mvc	__PT_PSW(16,%r2),__LC_PSW_SAVE_AREA-4095(%r8)
+	mvc	__PT_R0(128,%r2),__LC_GPREGS_SAVE_AREA-4095(%r8)
+	mvc	__PT_LAST_BREAK(8,%r2),__LC_PGM_LAST_BREAK
+	mvc	__PT_INT_CODE(4,%r2),__LC_PGM_INT_CODE
+	brasl	%r14,do_pgm_check
+	larl	%r9,startup_pgm_check_handler
+	stg	%r9,__LC_PGM_NEW_PSW+8
+	mvc	__LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
+	lmg	%r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
+	lpswe	__LC_RETURN_PSW
 .Lold_psw_disabled_wait:
 	la	%r8,4095
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index d3731f2983b7..f584d7da29cb 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -5,6 +5,7 @@
 #include <linux/pgtable.h>
 #include <asm/abs_lowcore.h>
 #include <asm/page-states.h>
+#include <asm/machine.h>
 #include <asm/ebcdic.h>
 #include <asm/sclp.h>
 #include <asm/sections.h>
@@ -34,29 +35,14 @@ int vmalloc_size_set;
 
 static inline int __diag308(unsigned long subcode, void *addr)
 {
-	unsigned long reg1, reg2;
-	union register_pair r1;
-	psw_t old;
-
-	r1.even = (unsigned long) addr;
-	r1.odd	= 0;
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
+	union register_pair r1 = { .even = (unsigned long)addr, .odd = 0 };
+
+	asm_inline volatile(
 		"	diag	%[r1],%[subcode],0x308\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
-		: [r1] "+&d" (r1.pair),
-		  [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  "+Q" (get_lowcore()->program_new_psw),
-		  "=Q" (old)
-		: [subcode] "d" (subcode),
-		  [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw)
+		"0:\n"
+		EX_TABLE(0b, 0b)
+		: [r1] "+d" (r1.pair)
+		: [subcode] "d" (subcode)
 		: "cc", "memory");
 	return r1.odd;
 }
@@ -193,7 +179,7 @@ void setup_boot_command_line(void)
 	if (has_ebcdic_char(parmarea.command_line))
 		EBCASC(parmarea.command_line, COMMAND_LINE_SIZE);
 	/* copy arch command line */
-	strcpy(early_command_line, strim(parmarea.command_line));
+	strscpy(early_command_line, strim(parmarea.command_line));
 
 	/* append IPL PARM data to the boot command line */
 	if (!is_prot_virt_guest() && ipl_block_valid)
@@ -267,7 +253,8 @@ void parse_boot_command_line(void)
 	int rc;
 
 	__kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
-	args = strcpy(command_line_buf, early_command_line);
+	strscpy(command_line_buf, early_command_line);
+	args = command_line_buf;
 	while (*args) {
 		args = next_arg(args, &param, &val);
 
@@ -295,6 +282,9 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "facilities") && val)
 			modify_fac_list(val);
 
+		if (!strcmp(param, "debug-alternative"))
+			alt_debug_setup(val);
+
 		if (!strcmp(param, "nokaslr"))
 			__kaslr_enabled = 0;
 
@@ -312,7 +302,7 @@ void parse_boot_command_line(void)
 		}
 #endif
 		if (!strcmp(param, "relocate_lowcore") && test_facility(193))
-			relocate_lowcore = 1;
+			set_machine_feature(MFEATURE_LOWCORE);
 		if (!strcmp(param, "earlyprintk"))
 			boot_earlyprintk = true;
 		if (!strcmp(param, "debug"))
@@ -320,7 +310,7 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "bootdebug")) {
 			bootdebug = true;
 			if (val)
-				strncpy(bootdebug_filter, val, sizeof(bootdebug_filter) - 1);
+				strscpy(bootdebug_filter, val);
 		}
 		if (!strcmp(param, "quiet"))
 			boot_console_loglevel = CONSOLE_LOGLEVEL_QUIET;
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check.c
index 633f11600aab..fa621fa5bc02 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check.c
@@ -32,26 +32,49 @@ void print_stacktrace(unsigned long sp)
 	}
 }
 
-void print_pgm_check_info(void)
+extern struct exception_table_entry __start___ex_table[];
+extern struct exception_table_entry __stop___ex_table[];
+
+static inline unsigned long extable_insn(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->insn + x->insn;
+}
+
+static bool ex_handler(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	for (ex = __start___ex_table; ex < __stop___ex_table; ex++) {
+		if (extable_insn(ex) != regs->psw.addr)
+			continue;
+		if (ex->type != EX_TYPE_FIXUP)
+			return false;
+		regs->psw.addr = extable_fixup(ex);
+		return true;
+	}
+	return false;
+}
+
+void do_pgm_check(struct pt_regs *regs)
 {
-	unsigned long *gpregs = (unsigned long *)get_lowcore()->gpregs_save_area;
-	struct psw_bits *psw = &psw_bits(get_lowcore()->psw_save_area);
+	struct psw_bits *psw = &psw_bits(regs->psw);
+	unsigned long *gpregs = regs->gprs;
 
+	if (ex_handler(regs))
+		return;
 	if (bootdebug)
 		boot_rb_dump();
 	boot_emerg("Linux version %s\n", kernel_version);
 	if (!is_prot_virt_guest() && early_command_line[0])
 		boot_emerg("Kernel command line: %s\n", early_command_line);
 	boot_emerg("Kernel fault: interruption code %04x ilc:%d\n",
-		   get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1);
+		   regs->int_code & 0xffff, regs->int_code >> 17);
 	if (kaslr_enabled()) {
 		boot_emerg("Kernel random base: %lx\n", __kaslr_offset);
 		boot_emerg("Kernel random base phys: %lx\n", __kaslr_offset_phys);
 	}
 	boot_emerg("PSW : %016lx %016lx (%pS)\n",
-		   get_lowcore()->psw_save_area.mask,
-		   get_lowcore()->psw_save_area.addr,
-		   (void *)get_lowcore()->psw_save_area.addr);
+		   regs->psw.mask, regs->psw.addr, (void *)regs->psw.addr);
 	boot_emerg("      R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n",
 		   psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck,
 		   psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, psw->eaba);
@@ -59,8 +82,11 @@ void print_pgm_check_info(void)
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]);
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]);
 	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]);
-	print_stacktrace(get_lowcore()->gpregs_save_area[15]);
+	print_stacktrace(gpregs[15]);
 	boot_emerg("Last Breaking-Event-Address:\n");
-	boot_emerg(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break,
-		   (void *)get_lowcore()->pgm_last_break);
+	boot_emerg(" [<%016lx>] %pS\n", regs->last_break, (void *)regs->last_break);
+	/* Convert to disabled wait PSW */
+	psw->io = 0;
+	psw->ext = 0;
+	psw->wait = 1;
 }
diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c
index aa096ef68e8c..45e3d057cfaa 100644
--- a/arch/s390/boot/physmem_info.c
+++ b/arch/s390/boot/physmem_info.c
@@ -59,36 +59,22 @@ void add_physmem_online_range(u64 start, u64 end)
 
 static int __diag260(unsigned long rx1, unsigned long rx2)
 {
-	unsigned long reg1, reg2, ry;
 	union register_pair rx;
 	int cc, exception;
-	psw_t old;
+	unsigned long ry;
 
 	rx.even = rx1;
 	rx.odd	= rx2;
 	ry = 0x10; /* storage configuration */
 	exception = 1;
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
+	asm_inline volatile(
 		"	diag	%[rx],%[ry],0x260\n"
-		"	lhi	%[exc],0\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
+		"0:	lhi	%[exc],0\n"
+		"1:\n"
 		CC_IPM(cc)
-		: CC_OUT(cc, cc),
-		  [exc] "+d" (exception),
-		  [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  [ry] "+&d" (ry),
-		  "+Q" (get_lowcore()->program_new_psw),
-		  "=Q" (old)
-		: [rx] "d" (rx.pair),
-		  [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw)
+		EX_TABLE(0b, 1b)
+		: CC_OUT(cc, cc), [exc] "+d" (exception), [ry] "+d" (ry)
+		: [rx] "d" (rx.pair)
 		: CC_CLOBBER_LIST("memory"));
 	cc = exception ? -1 : CC_TRANSFORM(cc);
 	return cc == 0 ? ry : -1;
@@ -118,29 +104,15 @@ static int diag260(void)
 static int diag500_storage_limit(unsigned long *max_physmem_end)
 {
 	unsigned long storage_limit;
-	unsigned long reg1, reg2;
-	psw_t old;
-
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
-		"	lghi	1,%[subcode]\n"
-		"	lghi	2,0\n"
-		"	diag	2,4,0x500\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
-		"	lgr	%[slimit],2\n"
-		: [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  [slimit] "=d" (storage_limit),
-		  "=Q" (get_lowcore()->program_new_psw),
-		  "=Q" (old)
-		: [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw),
-		  [subcode] "i" (DIAG500_SC_STOR_LIMIT)
+
+	asm_inline volatile(
+		"	lghi	%%r1,%[subcode]\n"
+		"	lghi	%%r2,0\n"
+		"	diag	%%r2,%%r4,0x500\n"
+		"0:	lgr	%[slimit],%%r2\n"
+		EX_TABLE(0b, 0b)
+		: [slimit] "=d" (storage_limit)
+		: [subcode] "i" (DIAG500_SC_STOR_LIMIT)
 		: "memory", "1", "2");
 	if (!storage_limit)
 		return -EINVAL;
@@ -151,31 +123,17 @@ static int diag500_storage_limit(unsigned long *max_physmem_end)
 
 static int tprot(unsigned long addr)
 {
-	unsigned long reg1, reg2;
 	int cc, exception;
-	psw_t old;
 
 	exception = 1;
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
+	asm_inline volatile(
 		"	tprot	0(%[addr]),0\n"
-		"	lhi	%[exc],0\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
+		"0:	lhi	%[exc],0\n"
+		"1:\n"
 		CC_IPM(cc)
-		: CC_OUT(cc, cc),
-		  [exc] "+d" (exception),
-		  [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  "=Q" (get_lowcore()->program_new_psw.addr),
-		  "=Q" (old)
-		: [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw),
-		  [addr] "a" (addr)
+		EX_TABLE(0b, 1b)
+		: CC_OUT(cc, cc), [exc] "+d" (exception)
+		: [addr] "a" (addr)
 		: CC_CLOBBER_LIST("memory"));
 	cc = exception ? -EFAULT : CC_TRANSFORM(cc);
 	return cc;
diff --git a/arch/s390/boot/printk.c b/arch/s390/boot/printk.c
index b4c66fa667d5..4bb6bc95704e 100644
--- a/arch/s390/boot/printk.c
+++ b/arch/s390/boot/printk.c
@@ -8,6 +8,7 @@
 #include <asm/sections.h>
 #include <asm/lowcore.h>
 #include <asm/setup.h>
+#include <asm/timex.h>
 #include <asm/sclp.h>
 #include <asm/uv.h>
 #include "boot.h"
@@ -28,7 +29,8 @@ static void boot_rb_add(const char *str, size_t len)
 	/* store strings separated by '\0' */
 	if (len + 1 > avail)
 		boot_rb_off = 0;
-	strcpy(boot_rb + boot_rb_off, str);
+	avail = sizeof(boot_rb) - boot_rb_off - 1;
+	strscpy(boot_rb + boot_rb_off, str, avail);
 	boot_rb_off += len + 1;
 }
 
@@ -157,10 +159,10 @@ static noinline char *strsym(char *buf, void *ip)
 
 	p = findsym((unsigned long)ip, &off, &len);
 	if (p) {
-		strncpy(buf, p, MAX_SYMLEN);
+		strscpy(buf, p, MAX_SYMLEN);
 		/* reserve 15 bytes for offset/len in symbol+0x1234/0x1234 */
 		p = buf + strnlen(buf, MAX_SYMLEN - 15);
-		strcpy(p, "+0x");
+		strscpy(p, "+0x", MAX_SYMLEN - (p - buf));
 		as_hex(p + 3, off, 0);
 		strcat(p, "/0x");
 		as_hex(p + strlen(p), len, 0);
@@ -199,8 +201,7 @@ static void boot_console_earlyprintk(const char *buf)
 static char *add_timestamp(char *buf)
 {
 #ifdef CONFIG_PRINTK_TIME
-	union tod_clock *boot_clock = (union tod_clock *)&get_lowcore()->boot_clock;
-	unsigned long ns = tod_to_ns(get_tod_clock() - boot_clock->tod);
+	unsigned long ns = tod_to_ns(__get_tod_clock_monotonic());
 	char ts[MAX_NUMLEN];
 
 	*buf++ = '[';
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 9276e0576d0a..da8337e63a3e 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -6,9 +6,13 @@
 #include <asm/boot_data.h>
 #include <asm/extmem.h>
 #include <asm/sections.h>
+#include <asm/diag288.h>
 #include <asm/maccess.h>
+#include <asm/machine.h>
+#include <asm/sysinfo.h>
 #include <asm/cpu_mf.h>
 #include <asm/setup.h>
+#include <asm/timex.h>
 #include <asm/kasan.h>
 #include <asm/kexec.h>
 #include <asm/sclp.h>
@@ -34,13 +38,12 @@ unsigned long __bootdata_preserved(max_mappable);
 unsigned long __bootdata_preserved(page_noexec_mask);
 unsigned long __bootdata_preserved(segment_noexec_mask);
 unsigned long __bootdata_preserved(region_noexec_mask);
-int __bootdata_preserved(relocate_lowcore);
+union tod_clock __bootdata_preserved(tod_clock_base);
+u64 __bootdata_preserved(clock_comparator_max) = -1UL;
 
 u64 __bootdata_preserved(stfle_fac_list[16]);
 struct oldmem_data __bootdata_preserved(oldmem_data);
 
-struct machine_info machine;
-
 void error(char *x)
 {
 	boot_emerg("%s\n", x);
@@ -48,50 +51,115 @@ void error(char *x)
 	disabled_wait();
 }
 
+static char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+
+static void detect_machine_type(void)
+{
+	struct sysinfo_3_2_2 *vmms = (struct sysinfo_3_2_2 *)&sysinfo_page;
+
+	/* Check current-configuration-level */
+	if (stsi(NULL, 0, 0, 0) <= 2) {
+		set_machine_feature(MFEATURE_LPAR);
+		return;
+	}
+	/* Get virtual-machine cpu information. */
+	if (stsi(vmms, 3, 2, 2) || !vmms->count)
+		return;
+	/* Detect known hypervisors */
+	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
+		set_machine_feature(MFEATURE_KVM);
+	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
+		set_machine_feature(MFEATURE_VM);
+}
+
+static void detect_diag288(void)
+{
+	/* "BEGIN" in EBCDIC character set */
+	static const char cmd[] = "\xc2\xc5\xc7\xc9\xd5";
+	unsigned long action, len;
+
+	action = machine_is_vm() ? (unsigned long)cmd : LPARWDT_RESTART;
+	len = machine_is_vm() ? sizeof(cmd) : 0;
+	if (__diag288(WDT_FUNC_INIT, MIN_INTERVAL, action, len))
+		return;
+	__diag288(WDT_FUNC_CANCEL, 0, 0, 0);
+	set_machine_feature(MFEATURE_DIAG288);
+}
+
+static void detect_diag9c(void)
+{
+	unsigned int cpu;
+	int rc = 1;
+
+	cpu = stap();
+	asm_inline volatile(
+		"	diag	%[cpu],%%r0,0x9c\n"
+		"0:	lhi	%[rc],0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [rc] "+d" (rc)
+		: [cpu] "d" (cpu)
+		: "cc", "memory");
+	if (!rc)
+		set_machine_feature(MFEATURE_DIAG9C);
+}
+
+static void reset_tod_clock(void)
+{
+	union tod_clock clk;
+
+	if (store_tod_clock_ext_cc(&clk) == 0)
+		return;
+	/* TOD clock not running. Set the clock to Unix Epoch. */
+	if (set_tod_clock(TOD_UNIX_EPOCH) || store_tod_clock_ext_cc(&clk))
+		disabled_wait();
+	memset(&tod_clock_base, 0, sizeof(tod_clock_base));
+	tod_clock_base.tod = TOD_UNIX_EPOCH;
+	get_lowcore()->last_update_clock = TOD_UNIX_EPOCH;
+}
+
 static void detect_facilities(void)
 {
-	if (test_facility(8)) {
-		machine.has_edat1 = 1;
+	if (cpu_has_edat1())
 		local_ctl_set_bit(0, CR0_EDAT_BIT);
-	}
-	if (test_facility(78))
-		machine.has_edat2 = 1;
 	page_noexec_mask = -1UL;
 	segment_noexec_mask = -1UL;
 	region_noexec_mask = -1UL;
-	if (!test_facility(130)) {
+	if (!cpu_has_nx()) {
 		page_noexec_mask &= ~_PAGE_NOEXEC;
 		segment_noexec_mask &= ~_SEGMENT_ENTRY_NOEXEC;
 		region_noexec_mask &= ~_REGION_ENTRY_NOEXEC;
 	}
+	if (IS_ENABLED(CONFIG_PCI) && test_facility(153))
+		set_machine_feature(MFEATURE_PCI_MIO);
+	reset_tod_clock();
+	if (test_facility(139) && (tod_clock_base.tod >> 63)) {
+		/* Enable signed clock comparator comparisons */
+		set_machine_feature(MFEATURE_SCC);
+		clock_comparator_max = -1UL >> 1;
+		local_ctl_set_bit(0, CR0_CLOCK_COMPARATOR_SIGN_BIT);
+	}
+	if (test_facility(50) && test_facility(73)) {
+		set_machine_feature(MFEATURE_TX);
+		local_ctl_set_bit(0, CR0_TRANSACTIONAL_EXECUTION_BIT);
+	}
+	if (cpu_has_vx())
+		local_ctl_set_bit(0, CR0_VECTOR_BIT);
 }
 
 static int cmma_test_essa(void)
 {
-	unsigned long reg1, reg2, tmp = 0;
+	unsigned long tmp = 0;
 	int rc = 1;
-	psw_t old;
 
 	/* Test ESSA_GET_STATE */
-	asm volatile(
-		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
-		"	epsw	%[reg1],%[reg2]\n"
-		"	st	%[reg1],0(%[psw_pgm])\n"
-		"	st	%[reg2],4(%[psw_pgm])\n"
-		"	larl	%[reg1],1f\n"
-		"	stg	%[reg1],8(%[psw_pgm])\n"
+	asm_inline volatile(
 		"	.insn	rrf,0xb9ab0000,%[tmp],%[tmp],%[cmd],0\n"
-		"	la	%[rc],0\n"
-		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
-		: [reg1] "=&d" (reg1),
-		  [reg2] "=&a" (reg2),
-		  [rc] "+&d" (rc),
-		  [tmp] "+&d" (tmp),
-		  "+Q" (get_lowcore()->program_new_psw),
-		  "=Q" (old)
-		: [psw_old] "a" (&old),
-		  [psw_pgm] "a" (&get_lowcore()->program_new_psw),
-		  [cmd] "i" (ESSA_GET_STATE)
+		"0:	lhi	%[rc],0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [rc] "+d" (rc), [tmp] "+d" (tmp)
+		: [cmd] "i" (ESSA_GET_STATE)
 		: "cc", "memory");
 	return rc;
 }
@@ -462,7 +530,12 @@ void startup_kernel(void)
 
 	read_ipl_report();
 	sclp_early_read_info();
+	sclp_early_detect_machine_features();
 	detect_facilities();
+	detect_diag9c();
+	detect_machine_type();
+	/* detect_diag288() needs machine type */
+	detect_diag288();
 	cmma_init();
 	sanitize_prot_virt_host();
 	max_physmem_end = detect_max_physmem_end();
diff --git a/arch/s390/boot/string.c b/arch/s390/boot/string.c
index f6b9b1df48a8..bd68161434a6 100644
--- a/arch/s390/boot/string.c
+++ b/arch/s390/boot/string.c
@@ -29,6 +29,18 @@ int strncmp(const char *cs, const char *ct, size_t count)
 	return 0;
 }
 
+ssize_t sized_strscpy(char *dst, const char *src, size_t count)
+{
+	size_t len;
+
+	if (count == 0)
+		return -E2BIG;
+	len = strnlen(src, count - 1);
+	memcpy(dst, src, len);
+	dst[len] = '\0';
+	return src[len] ? -E2BIG : len;
+}
+
 void *memset64(uint64_t *s, uint64_t v, size_t count)
 {
 	uint64_t *xs = s;
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index cfca94a8eac4..1d073acd05a7 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #define boot_fmt(fmt) "vmem: " fmt
+#include <linux/cpufeature.h>
 #include <linux/sched/task.h>
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
@@ -10,6 +11,7 @@
 #include <asm/ctlreg.h>
 #include <asm/physmem_info.h>
 #include <asm/maccess.h>
+#include <asm/machine.h>
 #include <asm/abs_lowcore.h>
 #include "decompressor.h"
 #include "boot.h"
@@ -314,7 +316,7 @@ static unsigned long try_get_large_pud_pa(pud_t *pu_dir, unsigned long addr, uns
 {
 	unsigned long pa, size = end - addr;
 
-	if (!machine.has_edat2 || !large_page_mapping_allowed(mode) ||
+	if (!cpu_has_edat2() || !large_page_mapping_allowed(mode) ||
 	    !IS_ALIGNED(addr, PUD_SIZE) || (size < PUD_SIZE))
 		return INVALID_PHYS_ADDR;
 
@@ -330,7 +332,7 @@ static unsigned long try_get_large_pmd_pa(pmd_t *pm_dir, unsigned long addr, uns
 {
 	unsigned long pa, size = end - addr;
 
-	if (!machine.has_edat1 || !large_page_mapping_allowed(mode) ||
+	if (!cpu_has_edat1() || !large_page_mapping_allowed(mode) ||
 	    !IS_ALIGNED(addr, PMD_SIZE) || (size < PMD_SIZE))
 		return INVALID_PHYS_ADDR;
 
@@ -516,7 +518,7 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
 	__arch_set_page_dat((void *)swapper_pg_dir, 1UL << CRST_ALLOC_ORDER);
 	__arch_set_page_dat((void *)invalid_pg_dir, 1UL << CRST_ALLOC_ORDER);
 
-	if (relocate_lowcore)
+	if (machine_has_relocated_lowcore())
 		lowcore_address = LOWCORE_ALT_ADDRESS;
 
 	/*
diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index 66670212a361..50988022f9ea 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -40,6 +40,7 @@ SECTIONS
 		*(.rodata.*)
 		_erodata = . ;
 	}
+	EXCEPTION_TABLE(16)
 	.got : {
 		*(.got)
 	}
@@ -165,7 +166,6 @@ SECTIONS
 	/DISCARD/ : {
 		COMMON_DISCARDS
 		*(.eh_frame)
-		*(__ex_table)
 		*(*__ksymtab*)
 		*(___kcrctab*)
 	}
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 80bdfbae6e5b..8ecad727497e 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -38,7 +38,6 @@ CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
@@ -92,7 +91,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
-CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLAB_BUCKETS=y
 CONFIG_SLUB_STATS=y
@@ -395,6 +393,9 @@ CONFIG_CLS_U32_MARK=y
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -405,6 +406,9 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GATE=m
 CONFIG_NET_TC_SKB_EXT=y
 CONFIG_DNS_RESOLVER=y
@@ -628,8 +632,16 @@ CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_MEM=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -654,7 +666,6 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=y
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -724,11 +735,10 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_HARDENED_USERCOPY=y
-CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_LOCKDOWN_LSM=y
@@ -741,12 +751,14 @@ CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_HARDENED_USERCOPY=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_SELFTESTS=y
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECDSA=m
@@ -756,7 +768,6 @@ CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
@@ -795,13 +806,11 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA3_256_S390=m
 CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_HMAC_S390=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
@@ -812,12 +821,9 @@ CONFIG_PKEY_UV=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
 CONFIG_CORDIC=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
-CONFIG_CRC4=m
-CONFIG_CRC7=m
-CONFIG_CRC8=m
 CONFIG_RANDOM32_SELFTEST=y
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
@@ -888,12 +894,14 @@ CONFIG_USER_EVENTS=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_FTRACE_STARTUP_TEST=y
 # CONFIG_EVENT_TRACE_STARTUP_TEST is not set
+CONFIG_FTRACE_SORT_STARTUP_TEST=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_SAMPLE_FTRACE_DIRECT=m
 CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m
 CONFIG_SAMPLE_FTRACE_OPS=m
 CONFIG_DEBUG_ENTRY=y
+CONFIG_STRICT_MM_TYPECHECKS=y
 CONFIG_CIO_INJECT=y
 CONFIG_KUNIT=m
 CONFIG_KUNIT_DEBUGFS=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 449a0e996b96..c13a77765162 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -36,7 +36,6 @@ CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
 CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
@@ -86,7 +85,6 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
-CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLAB_BUCKETS=y
 # CONFIG_COMPAT_BRK is not set
@@ -385,6 +383,9 @@ CONFIG_CLS_U32_MARK=y
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NET_EMATCH=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -395,6 +396,9 @@ CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GATE=m
 CONFIG_NET_TC_SKB_EXT=y
 CONFIG_DNS_RESOLVER=y
@@ -618,8 +622,16 @@ CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_MEM=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VDPA=m
+CONFIG_VDPA_SIM=m
+CONFIG_VDPA_SIM_NET=m
+CONFIG_VDPA_SIM_BLOCK=m
+CONFIG_VDPA_USER=m
+CONFIG_MLX5_VDPA_NET=m
+CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+CONFIG_VHOST_VDPA=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -641,7 +653,6 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=m
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
-CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -711,6 +722,7 @@ CONFIG_NLS_UTF8=m
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
@@ -729,10 +741,10 @@ CONFIG_IMA_APPRAISE=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_SELFTESTS=y
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECDSA=m
@@ -742,7 +754,6 @@ CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
@@ -782,13 +793,11 @@ CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA3_256_S390=m
 CONFIG_CRYPTO_SHA3_512_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_HMAC_S390=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
@@ -799,13 +808,10 @@ CONFIG_PKEY_UV=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_SYSTEM_BLACKLIST_KEYRING=y
+CONFIG_CRYPTO_KRB5=m
+CONFIG_CRYPTO_KRB5_SELFTESTS=y
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
-CONFIG_CRYPTO_LIB_CURVE25519=m
-CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
-CONFIG_CRC4=m
-CONFIG_CRC7=m
-CONFIG_CRC8=m
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
diff --git a/arch/s390/configs/mmtypes.config b/arch/s390/configs/mmtypes.config
new file mode 100644
index 000000000000..fe32b442d789
--- /dev/null
+++ b/arch/s390/configs/mmtypes.config
@@ -0,0 +1,2 @@
+# Help: Enable strict memory management typechecks
+CONFIG_STRICT_MM_TYPECHECKS=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 853b2326a171..8163c1702720 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -70,7 +70,6 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_DEBUG_FS=y
 CONFIG_PANIC_ON_OOPS=y
-# CONFIG_SCHED_DEBUG is not set
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 # CONFIG_RCU_TRACE is not set
 # CONFIG_FTRACE is not set
diff --git a/arch/s390/crypto/Kconfig b/arch/s390/crypto/Kconfig
index b760232537f1..e2c27588b21a 100644
--- a/arch/s390/crypto/Kconfig
+++ b/arch/s390/crypto/Kconfig
@@ -4,7 +4,6 @@ menu "Accelerated Cryptographic Algorithms for CPU (s390)"
 
 config CRYPTO_SHA512_S390
 	tristate "Hash functions: SHA-384 and SHA-512"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  SHA-384 and SHA-512 secure hash algorithms (FIPS 180)
@@ -15,7 +14,6 @@ config CRYPTO_SHA512_S390
 
 config CRYPTO_SHA1_S390
 	tristate "Hash functions: SHA-1"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  SHA-1 secure hash algorithm (FIPS 180)
@@ -24,20 +22,8 @@ config CRYPTO_SHA1_S390
 
 	  It is available as of z990.
 
-config CRYPTO_SHA256_S390
-	tristate "Hash functions: SHA-224 and SHA-256"
-	depends on S390
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: s390
-
-	  It is available as of z9.
-
 config CRYPTO_SHA3_256_S390
 	tristate "Hash functions: SHA3-224 and SHA3-256"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  SHA3-224 and SHA3-256 secure hash algorithms (FIPS 202)
@@ -48,7 +34,6 @@ config CRYPTO_SHA3_256_S390
 
 config CRYPTO_SHA3_512_S390
 	tristate "Hash functions: SHA3-384 and SHA3-512"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  SHA3-384 and SHA3-512 secure hash algorithms (FIPS 202)
@@ -59,7 +44,6 @@ config CRYPTO_SHA3_512_S390
 
 config CRYPTO_GHASH_S390
 	tristate "Hash functions: GHASH"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  GCM GHASH hash function (NIST SP800-38D)
@@ -70,7 +54,6 @@ config CRYPTO_GHASH_S390
 
 config CRYPTO_AES_S390
 	tristate "Ciphers: AES, modes: ECB, CBC, CTR, XTS, GCM"
-	depends on S390
 	select CRYPTO_ALGAPI
 	select CRYPTO_SKCIPHER
 	help
@@ -92,7 +75,6 @@ config CRYPTO_AES_S390
 
 config CRYPTO_DES_S390
 	tristate "Ciphers: DES and Triple DES EDE, modes: ECB, CBC, CTR"
-	depends on S390
 	select CRYPTO_ALGAPI
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
@@ -107,22 +89,8 @@ config CRYPTO_DES_S390
 	  As of z990 the ECB and CBC mode are hardware accelerated.
 	  As of z196 the CTR mode is hardware accelerated.
 
-config CRYPTO_CHACHA_S390
-	tristate "Ciphers: ChaCha20"
-	depends on S390
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_CHACHA_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving cipher: ChaCha20 stream cipher (RFC 7539)
-
-	  Architecture: s390
-
-	  It is available as of z13.
-
 config CRYPTO_HMAC_S390
 	tristate "Keyed-hash message authentication code: HMAC"
-	depends on S390
 	select CRYPTO_HASH
 	help
 	  s390 specific HMAC hardware support for SHA224, SHA256, SHA384 and
diff --git a/arch/s390/crypto/Makefile b/arch/s390/crypto/Makefile
index 14dafadbcbed..21757d86cd49 100644
--- a/arch/s390/crypto/Makefile
+++ b/arch/s390/crypto/Makefile
@@ -4,17 +4,13 @@
 #
 
 obj-$(CONFIG_CRYPTO_SHA1_S390) += sha1_s390.o sha_common.o
-obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_SHA512_S390) += sha512_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_SHA3_256_S390) += sha3_256_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_SHA3_512_S390) += sha3_512_s390.o sha_common.o
 obj-$(CONFIG_CRYPTO_DES_S390) += des_s390.o
 obj-$(CONFIG_CRYPTO_AES_S390) += aes_s390.o
 obj-$(CONFIG_CRYPTO_PAES_S390) += paes_s390.o
-obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o
 obj-$(CONFIG_S390_PRNG) += prng.o
 obj-$(CONFIG_CRYPTO_GHASH_S390) += ghash_s390.o
 obj-$(CONFIG_CRYPTO_HMAC_S390) += hmac_s390.o
 obj-y += arch_random.o
-
-chacha_s390-y := chacha-glue.o chacha-s390.o
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 9c46b1b630b1..5d36f4020dfa 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -66,7 +66,6 @@ struct s390_xts_ctx {
 struct gcm_sg_walk {
 	struct scatter_walk walk;
 	unsigned int walk_bytes;
-	u8 *walk_ptr;
 	unsigned int walk_bytes_remain;
 	u8 buf[AES_BLOCK_SIZE];
 	unsigned int buf_bytes;
@@ -787,29 +786,20 @@ static void gcm_walk_start(struct gcm_sg_walk *gw, struct scatterlist *sg,
 
 static inline unsigned int _gcm_sg_clamp_and_map(struct gcm_sg_walk *gw)
 {
-	struct scatterlist *nextsg;
-
-	gw->walk_bytes = scatterwalk_clamp(&gw->walk, gw->walk_bytes_remain);
-	while (!gw->walk_bytes) {
-		nextsg = sg_next(gw->walk.sg);
-		if (!nextsg)
-			return 0;
-		scatterwalk_start(&gw->walk, nextsg);
-		gw->walk_bytes = scatterwalk_clamp(&gw->walk,
-						   gw->walk_bytes_remain);
-	}
-	gw->walk_ptr = scatterwalk_map(&gw->walk);
+	if (gw->walk_bytes_remain == 0)
+		return 0;
+	gw->walk_bytes = scatterwalk_next(&gw->walk, gw->walk_bytes_remain);
 	return gw->walk_bytes;
 }
 
 static inline void _gcm_sg_unmap_and_advance(struct gcm_sg_walk *gw,
-					     unsigned int nbytes)
+					     unsigned int nbytes, bool out)
 {
 	gw->walk_bytes_remain -= nbytes;
-	scatterwalk_unmap(gw->walk_ptr);
-	scatterwalk_advance(&gw->walk, nbytes);
-	scatterwalk_done(&gw->walk, 0, gw->walk_bytes_remain);
-	gw->walk_ptr = NULL;
+	if (out)
+		scatterwalk_done_dst(&gw->walk, nbytes);
+	else
+		scatterwalk_done_src(&gw->walk, nbytes);
 }
 
 static int gcm_in_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
@@ -835,16 +825,16 @@ static int gcm_in_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
 	}
 
 	if (!gw->buf_bytes && gw->walk_bytes >= minbytesneeded) {
-		gw->ptr = gw->walk_ptr;
+		gw->ptr = gw->walk.addr;
 		gw->nbytes = gw->walk_bytes;
 		goto out;
 	}
 
 	while (1) {
 		n = min(gw->walk_bytes, AES_BLOCK_SIZE - gw->buf_bytes);
-		memcpy(gw->buf + gw->buf_bytes, gw->walk_ptr, n);
+		memcpy(gw->buf + gw->buf_bytes, gw->walk.addr, n);
 		gw->buf_bytes += n;
-		_gcm_sg_unmap_and_advance(gw, n);
+		_gcm_sg_unmap_and_advance(gw, n, false);
 		if (gw->buf_bytes >= minbytesneeded) {
 			gw->ptr = gw->buf;
 			gw->nbytes = gw->buf_bytes;
@@ -876,13 +866,12 @@ static int gcm_out_walk_go(struct gcm_sg_walk *gw, unsigned int minbytesneeded)
 	}
 
 	if (gw->walk_bytes >= minbytesneeded) {
-		gw->ptr = gw->walk_ptr;
+		gw->ptr = gw->walk.addr;
 		gw->nbytes = gw->walk_bytes;
 		goto out;
 	}
 
-	scatterwalk_unmap(gw->walk_ptr);
-	gw->walk_ptr = NULL;
+	scatterwalk_unmap(&gw->walk);
 
 	gw->ptr = gw->buf;
 	gw->nbytes = sizeof(gw->buf);
@@ -904,7 +893,7 @@ static int gcm_in_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
 		} else
 			gw->buf_bytes = 0;
 	} else
-		_gcm_sg_unmap_and_advance(gw, bytesdone);
+		_gcm_sg_unmap_and_advance(gw, bytesdone, false);
 
 	return bytesdone;
 }
@@ -921,11 +910,11 @@ static int gcm_out_walk_done(struct gcm_sg_walk *gw, unsigned int bytesdone)
 			if (!_gcm_sg_clamp_and_map(gw))
 				return i;
 			n = min(gw->walk_bytes, bytesdone - i);
-			memcpy(gw->walk_ptr, gw->buf + i, n);
-			_gcm_sg_unmap_and_advance(gw, n);
+			memcpy(gw->walk.addr, gw->buf + i, n);
+			_gcm_sg_unmap_and_advance(gw, n, true);
 		}
 	} else
-		_gcm_sg_unmap_and_advance(gw, bytesdone);
+		_gcm_sg_unmap_and_advance(gw, bytesdone, true);
 
 	return bytesdone;
 }
diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c
deleted file mode 100644
index f8b0c52e77a4..000000000000
--- a/arch/s390/crypto/chacha-glue.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * s390 ChaCha stream cipher.
- *
- * Copyright IBM Corp. 2021
- */
-
-#define KMSG_COMPONENT "chacha_s390"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/algapi.h>
-#include <linux/cpufeature.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <asm/fpu.h>
-#include "chacha-s390.h"
-
-static void chacha20_crypt_s390(u32 *state, u8 *dst, const u8 *src,
-				unsigned int nbytes, const u32 *key,
-				u32 *counter)
-{
-	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
-
-	kernel_fpu_begin(&vxstate, KERNEL_VXR);
-	chacha20_vx(dst, src, nbytes, key, counter);
-	kernel_fpu_end(&vxstate, KERNEL_VXR);
-
-	*counter += round_up(nbytes, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
-}
-
-static int chacha20_s390(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	u32 state[CHACHA_STATE_WORDS] __aligned(16);
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	int rc;
-
-	rc = skcipher_walk_virt(&walk, req, false);
-	chacha_init_generic(state, ctx->key, req->iv);
-
-	while (walk.nbytes > 0) {
-		nbytes = walk.nbytes;
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		if (nbytes <= CHACHA_BLOCK_SIZE) {
-			chacha_crypt_generic(state, walk.dst.virt.addr,
-					     walk.src.virt.addr, nbytes,
-					     ctx->nrounds);
-		} else {
-			chacha20_crypt_s390(state, walk.dst.virt.addr,
-					    walk.src.virt.addr, nbytes,
-					    &state[4], &state[12]);
-		}
-		rc = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-	return rc;
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
-	/* TODO: implement hchacha_block_arch() in assembly */
-	hchacha_block_generic(state, stream, nrounds);
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src,
-		       unsigned int bytes, int nrounds)
-{
-	/* s390 chacha20 implementation has 20 rounds hard-coded,
-	 * it cannot handle a block of data or less, but otherwise
-	 * it can handle data of arbitrary size
-	 */
-	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !cpu_has_vx())
-		chacha_crypt_generic(state, dst, src, bytes, nrounds);
-	else
-		chacha20_crypt_s390(state, dst, src, bytes,
-				    &state[4], &state[12]);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static struct skcipher_alg chacha_algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-s390",
-		.base.cra_priority	= 900,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha20_s390,
-		.decrypt		= chacha20_s390,
-	}
-};
-
-static int __init chacha_mod_init(void)
-{
-	return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
-		crypto_register_skciphers(chacha_algs, ARRAY_SIZE(chacha_algs)) : 0;
-}
-
-static void __exit chacha_mod_fini(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER))
-		crypto_unregister_skciphers(chacha_algs, ARRAY_SIZE(chacha_algs));
-}
-
-module_cpu_feature_match(S390_CPU_FEATURE_VXRS, chacha_mod_init);
-module_exit(chacha_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha20 stream cipher");
-MODULE_LICENSE("GPL v2");
-
-MODULE_ALIAS_CRYPTO("chacha20");
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 0800a2a5799f..dcbcee37cb63 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -8,29 +8,28 @@
  * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
+#include <asm/cpacf.h>
+#include <crypto/ghash.h>
 #include <crypto/internal/hash.h>
-#include <linux/module.h>
 #include <linux/cpufeature.h>
-#include <asm/cpacf.h>
-
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
-struct ghash_ctx {
+struct s390_ghash_ctx {
 	u8 key[GHASH_BLOCK_SIZE];
 };
 
-struct ghash_desc_ctx {
+struct s390_ghash_desc_ctx {
 	u8 icv[GHASH_BLOCK_SIZE];
 	u8 key[GHASH_BLOCK_SIZE];
-	u8 buffer[GHASH_BLOCK_SIZE];
-	u32 bytes;
 };
 
 static int ghash_init(struct shash_desc *desc)
 {
-	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	struct s390_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	struct s390_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
 	memset(dctx, 0, sizeof(*dctx));
 	memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
@@ -41,7 +40,7 @@ static int ghash_init(struct shash_desc *desc)
 static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	struct s390_ghash_ctx *ctx = crypto_shash_ctx(tfm);
 
 	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
@@ -54,80 +53,71 @@ static int ghash_setkey(struct crypto_shash *tfm,
 static int ghash_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
-	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct s390_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 	unsigned int n;
-	u8 *buf = dctx->buffer;
-
-	if (dctx->bytes) {
-		u8 *pos = buf + (GHASH_BLOCK_SIZE - dctx->bytes);
 
-		n = min(srclen, dctx->bytes);
-		dctx->bytes -= n;
-		srclen -= n;
-
-		memcpy(pos, src, n);
-		src += n;
+	n = srclen & ~(GHASH_BLOCK_SIZE - 1);
+	cpacf_kimd(CPACF_KIMD_GHASH, dctx, src, n);
+	return srclen - n;
+}
 
-		if (!dctx->bytes) {
-			cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf,
-				   GHASH_BLOCK_SIZE);
-		}
-	}
+static void ghash_flush(struct s390_ghash_desc_ctx *dctx, const u8 *src,
+			unsigned int len)
+{
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
 
-	n = srclen & ~(GHASH_BLOCK_SIZE - 1);
-	if (n) {
-		cpacf_kimd(CPACF_KIMD_GHASH, dctx, src, n);
-		src += n;
-		srclen -= n;
+		memcpy(buf, src, len);
+		cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
+		memzero_explicit(buf, sizeof(buf));
 	}
+}
 
-	if (srclen) {
-		dctx->bytes = GHASH_BLOCK_SIZE - srclen;
-		memcpy(buf, src, srclen);
-	}
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *dst)
+{
+	struct s390_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
+	ghash_flush(dctx, src, len);
+	memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
 	return 0;
 }
 
-static int ghash_flush(struct ghash_desc_ctx *dctx)
+static int ghash_export(struct shash_desc *desc, void *out)
 {
-	u8 *buf = dctx->buffer;
-
-	if (dctx->bytes) {
-		u8 *pos = buf + (GHASH_BLOCK_SIZE - dctx->bytes);
-
-		memset(pos, 0, dctx->bytes);
-		cpacf_kimd(CPACF_KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
-		dctx->bytes = 0;
-	}
+	struct s390_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
+	memcpy(out, dctx->icv, GHASH_DIGEST_SIZE);
 	return 0;
 }
 
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_import(struct shash_desc *desc, const void *in)
 {
-	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	int ret;
+	struct s390_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	struct s390_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	ret = ghash_flush(dctx);
-	if (!ret)
-		memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
-	return ret;
+	memcpy(dctx->icv, in, GHASH_DIGEST_SIZE);
+	memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
+	return 0;
 }
 
 static struct shash_alg ghash_alg = {
 	.digestsize	= GHASH_DIGEST_SIZE,
 	.init		= ghash_init,
 	.update		= ghash_update,
-	.final		= ghash_final,
+	.finup		= ghash_finup,
 	.setkey		= ghash_setkey,
-	.descsize	= sizeof(struct ghash_desc_ctx),
+	.export		= ghash_export,
+	.import		= ghash_import,
+	.statesize	= sizeof(struct ghash_desc_ctx),
+	.descsize	= sizeof(struct s390_ghash_desc_ctx),
 	.base		= {
 		.cra_name		= "ghash",
 		.cra_driver_name	= "ghash-s390",
 		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct ghash_ctx),
+		.cra_ctxsize		= sizeof(struct s390_ghash_ctx),
 		.cra_module		= THIS_MODULE,
 	},
 };
diff --git a/arch/s390/crypto/hmac_s390.c b/arch/s390/crypto/hmac_s390.c
index bba9a818dfdc..93a1098d9f8d 100644
--- a/arch/s390/crypto/hmac_s390.c
+++ b/arch/s390/crypto/hmac_s390.c
@@ -9,10 +9,14 @@
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
 
 #include <asm/cpacf.h>
-#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
+#include <crypto/hmac.h>
+#include <crypto/sha2.h>
 #include <linux/cpufeature.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
 
 /*
  * KMAC param block layout for sha2 function codes:
@@ -71,32 +75,31 @@ union s390_kmac_gr0 {
 struct s390_kmac_sha2_ctx {
 	u8 param[MAX_DIGEST_SIZE + MAX_IMBL_SIZE + MAX_BLOCK_SIZE];
 	union s390_kmac_gr0 gr0;
-	u8 buf[MAX_BLOCK_SIZE];
-	unsigned int buflen;
+	u64 buflen[2];
 };
 
 /*
  * kmac_sha2_set_imbl - sets the input message bit-length based on the blocksize
  */
-static inline void kmac_sha2_set_imbl(u8 *param, unsigned int buflen,
-				      unsigned int blocksize)
+static inline void kmac_sha2_set_imbl(u8 *param, u64 buflen_lo,
+				      u64 buflen_hi, unsigned int blocksize)
 {
 	u8 *imbl = param + SHA2_IMBL_OFFSET(blocksize);
 
 	switch (blocksize) {
 	case SHA256_BLOCK_SIZE:
-		*(u64 *)imbl = (u64)buflen * BITS_PER_BYTE;
+		*(u64 *)imbl = buflen_lo * BITS_PER_BYTE;
 		break;
 	case SHA512_BLOCK_SIZE:
-		*(u128 *)imbl = (u128)buflen * BITS_PER_BYTE;
+		*(u128 *)imbl = (((u128)buflen_hi << 64) + buflen_lo) << 3;
 		break;
 	default:
 		break;
 	}
 }
 
-static int hash_key(const u8 *in, unsigned int inlen,
-		    u8 *digest, unsigned int digestsize)
+static int hash_data(const u8 *in, unsigned int inlen,
+		     u8 *digest, unsigned int digestsize, bool final)
 {
 	unsigned long func;
 	union {
@@ -123,19 +126,23 @@ static int hash_key(const u8 *in, unsigned int inlen,
 
 	switch (digestsize) {
 	case SHA224_DIGEST_SIZE:
-		func = CPACF_KLMD_SHA_256;
+		func = final ? CPACF_KLMD_SHA_256 : CPACF_KIMD_SHA_256;
 		PARAM_INIT(256, 224, inlen * 8);
+		if (!final)
+			digestsize = SHA256_DIGEST_SIZE;
 		break;
 	case SHA256_DIGEST_SIZE:
-		func = CPACF_KLMD_SHA_256;
+		func = final ? CPACF_KLMD_SHA_256 : CPACF_KIMD_SHA_256;
 		PARAM_INIT(256, 256, inlen * 8);
 		break;
 	case SHA384_DIGEST_SIZE:
-		func = CPACF_KLMD_SHA_512;
+		func = final ? CPACF_KLMD_SHA_512 : CPACF_KIMD_SHA_512;
 		PARAM_INIT(512, 384, inlen * 8);
+		if (!final)
+			digestsize = SHA512_DIGEST_SIZE;
 		break;
 	case SHA512_DIGEST_SIZE:
-		func = CPACF_KLMD_SHA_512;
+		func = final ? CPACF_KLMD_SHA_512 : CPACF_KIMD_SHA_512;
 		PARAM_INIT(512, 512, inlen * 8);
 		break;
 	default:
@@ -151,6 +158,12 @@ static int hash_key(const u8 *in, unsigned int inlen,
 	return 0;
 }
 
+static int hash_key(const u8 *in, unsigned int inlen,
+		    u8 *digest, unsigned int digestsize)
+{
+	return hash_data(in, inlen, digest, digestsize, true);
+}
+
 static int s390_hmac_sha2_setkey(struct crypto_shash *tfm,
 				 const u8 *key, unsigned int keylen)
 {
@@ -176,7 +189,8 @@ static int s390_hmac_sha2_init(struct shash_desc *desc)
 	memcpy(ctx->param + SHA2_KEY_OFFSET(bs),
 	       tfm_ctx->key, bs);
 
-	ctx->buflen = 0;
+	ctx->buflen[0] = 0;
+	ctx->buflen[1] = 0;
 	ctx->gr0.reg = 0;
 	switch (crypto_shash_digestsize(desc->tfm)) {
 	case SHA224_DIGEST_SIZE:
@@ -203,48 +217,31 @@ static int s390_hmac_sha2_update(struct shash_desc *desc,
 {
 	struct s390_kmac_sha2_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bs = crypto_shash_blocksize(desc->tfm);
-	unsigned int offset, n;
-
-	/* check current buffer */
-	offset = ctx->buflen % bs;
-	ctx->buflen += len;
-	if (offset + len < bs)
-		goto store;
-
-	/* process one stored block */
-	if (offset) {
-		n = bs - offset;
-		memcpy(ctx->buf + offset, data, n);
-		ctx->gr0.iimp = 1;
-		_cpacf_kmac(&ctx->gr0.reg, ctx->param, ctx->buf, bs);
-		data += n;
-		len -= n;
-		offset = 0;
-	}
-	/* process as many blocks as possible */
-	if (len >= bs) {
-		n = (len / bs) * bs;
-		ctx->gr0.iimp = 1;
-		_cpacf_kmac(&ctx->gr0.reg, ctx->param, data, n);
-		data += n;
-		len -= n;
-	}
-store:
-	/* store incomplete block in buffer */
-	if (len)
-		memcpy(ctx->buf + offset, data, len);
+	unsigned int n = round_down(len, bs);
 
-	return 0;
+	ctx->buflen[0] += n;
+	if (ctx->buflen[0] < n)
+		ctx->buflen[1]++;
+
+	/* process as many blocks as possible */
+	ctx->gr0.iimp = 1;
+	_cpacf_kmac(&ctx->gr0.reg, ctx->param, data, n);
+	return len - n;
 }
 
-static int s390_hmac_sha2_final(struct shash_desc *desc, u8 *out)
+static int s390_hmac_sha2_finup(struct shash_desc *desc, const u8 *src,
+				unsigned int len, u8 *out)
 {
 	struct s390_kmac_sha2_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bs = crypto_shash_blocksize(desc->tfm);
 
+	ctx->buflen[0] += len;
+	if (ctx->buflen[0] < len)
+		ctx->buflen[1]++;
+
 	ctx->gr0.iimp = 0;
-	kmac_sha2_set_imbl(ctx->param, ctx->buflen, bs);
-	_cpacf_kmac(&ctx->gr0.reg, ctx->param, ctx->buf, ctx->buflen % bs);
+	kmac_sha2_set_imbl(ctx->param, ctx->buflen[0], ctx->buflen[1], bs);
+	_cpacf_kmac(&ctx->gr0.reg, ctx->param, src, len);
 	memcpy(out, ctx->param, crypto_shash_digestsize(desc->tfm));
 
 	return 0;
@@ -262,7 +259,7 @@ static int s390_hmac_sha2_digest(struct shash_desc *desc,
 		return rc;
 
 	ctx->gr0.iimp = 0;
-	kmac_sha2_set_imbl(ctx->param, len,
+	kmac_sha2_set_imbl(ctx->param, len, 0,
 			   crypto_shash_blocksize(desc->tfm));
 	_cpacf_kmac(&ctx->gr0.reg, ctx->param, data, len);
 	memcpy(out, ctx->param, ds);
@@ -270,22 +267,89 @@ static int s390_hmac_sha2_digest(struct shash_desc *desc,
 	return 0;
 }
 
-#define S390_HMAC_SHA2_ALG(x) {						\
+static int s390_hmac_export_zero(struct shash_desc *desc, void *out)
+{
+	struct crypto_shash *tfm = desc->tfm;
+	u8 ipad[SHA512_BLOCK_SIZE];
+	struct s390_hmac_ctx *ctx;
+	unsigned int bs;
+	int err, i;
+
+	ctx = crypto_shash_ctx(tfm);
+	bs = crypto_shash_blocksize(tfm);
+	for (i = 0; i < bs; i++)
+		ipad[i] = ctx->key[i] ^ HMAC_IPAD_VALUE;
+
+	err = hash_data(ipad, bs, out, crypto_shash_digestsize(tfm), false);
+	memzero_explicit(ipad, sizeof(ipad));
+	return err;
+}
+
+static int s390_hmac_export(struct shash_desc *desc, void *out)
+{
+	struct s390_kmac_sha2_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int bs = crypto_shash_blocksize(desc->tfm);
+	unsigned int ds = bs / 2;
+	union {
+		u8 *u8;
+		u64 *u64;
+	} p = { .u8 = out };
+	int err = 0;
+
+	if (!ctx->gr0.ikp)
+		err = s390_hmac_export_zero(desc, out);
+	else
+		memcpy(p.u8, ctx->param, ds);
+	p.u8 += ds;
+	put_unaligned(ctx->buflen[0], p.u64++);
+	if (ds == SHA512_DIGEST_SIZE)
+		put_unaligned(ctx->buflen[1], p.u64);
+	return err;
+}
+
+static int s390_hmac_import(struct shash_desc *desc, const void *in)
+{
+	struct s390_kmac_sha2_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int bs = crypto_shash_blocksize(desc->tfm);
+	unsigned int ds = bs / 2;
+	union {
+		const u8 *u8;
+		const u64 *u64;
+	} p = { .u8 = in };
+	int err;
+
+	err = s390_hmac_sha2_init(desc);
+	memcpy(ctx->param, p.u8, ds);
+	p.u8 += ds;
+	ctx->buflen[0] = get_unaligned(p.u64++);
+	if (ds == SHA512_DIGEST_SIZE)
+		ctx->buflen[1] = get_unaligned(p.u64);
+	if (ctx->buflen[0] | ctx->buflen[1])
+		ctx->gr0.ikp = 1;
+	return err;
+}
+
+#define S390_HMAC_SHA2_ALG(x, ss) {					\
 	.fc = CPACF_KMAC_HMAC_SHA_##x,					\
 	.alg = {							\
 		.init = s390_hmac_sha2_init,				\
 		.update = s390_hmac_sha2_update,			\
-		.final = s390_hmac_sha2_final,				\
+		.finup = s390_hmac_sha2_finup,				\
 		.digest = s390_hmac_sha2_digest,			\
 		.setkey = s390_hmac_sha2_setkey,			\
+		.export = s390_hmac_export,				\
+		.import = s390_hmac_import,				\
 		.descsize = sizeof(struct s390_kmac_sha2_ctx),		\
 		.halg = {						\
+			.statesize = ss,				\
 			.digestsize = SHA##x##_DIGEST_SIZE,		\
 			.base = {					\
 				.cra_name = "hmac(sha" #x ")",		\
 				.cra_driver_name = "hmac_s390_sha" #x,	\
 				.cra_blocksize = SHA##x##_BLOCK_SIZE,	\
 				.cra_priority = 400,			\
+				.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | \
+					     CRYPTO_AHASH_ALG_FINUP_MAX, \
 				.cra_ctxsize = sizeof(struct s390_hmac_ctx), \
 				.cra_module = THIS_MODULE,		\
 			},						\
@@ -298,10 +362,10 @@ static struct s390_hmac_alg {
 	unsigned int fc;
 	struct shash_alg alg;
 } s390_hmac_algs[] = {
-	S390_HMAC_SHA2_ALG(224),
-	S390_HMAC_SHA2_ALG(256),
-	S390_HMAC_SHA2_ALG(384),
-	S390_HMAC_SHA2_ALG(512),
+	S390_HMAC_SHA2_ALG(224, sizeof(struct crypto_sha256_state)),
+	S390_HMAC_SHA2_ALG(256, sizeof(struct crypto_sha256_state)),
+	S390_HMAC_SHA2_ALG(384, SHA512_STATE_SIZE),
+	S390_HMAC_SHA2_ALG(512, SHA512_STATE_SIZE),
 };
 
 static __always_inline void _s390_hmac_algs_unregister(void)
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 511093713a6f..8a340c16acb4 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -5,7 +5,7 @@
  * s390 implementation of the AES Cipher Algorithm with protected keys.
  *
  * s390 Version:
- *   Copyright IBM Corp. 2017, 2023
+ *   Copyright IBM Corp. 2017, 2025
  *   Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *		Harald Freudenberger <freude@de.ibm.com>
  */
@@ -13,16 +13,18 @@
 #define KMSG_COMPONENT "paes_s390"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
-#include <crypto/aes.h>
-#include <crypto/algapi.h>
-#include <linux/bug.h>
-#include <linux/err.h>
-#include <linux/module.h>
+#include <linux/atomic.h>
 #include <linux/cpufeature.h>
+#include <linux/delay.h>
+#include <linux/err.h>
 #include <linux/init.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
-#include <linux/delay.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/engine.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/xts.h>
 #include <asm/cpacf.h>
@@ -44,23 +46,61 @@ static DEFINE_MUTEX(ctrblk_lock);
 
 static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
 
+static struct crypto_engine *paes_crypto_engine;
+#define MAX_QLEN 10
+
+/*
+ * protected key specific stuff
+ */
+
 struct paes_protkey {
 	u32 type;
 	u32 len;
 	u8 protkey[PXTS_256_PROTKEY_SIZE];
 };
 
-struct key_blob {
-	/*
-	 * Small keys will be stored in the keybuf. Larger keys are
-	 * stored in extra allocated memory. In both cases does
-	 * key point to the memory where the key is stored.
-	 * The code distinguishes by checking keylen against
-	 * sizeof(keybuf). See the two following helper functions.
-	 */
-	u8 *key;
-	u8 keybuf[128];
+#define PK_STATE_NO_KEY		     0
+#define PK_STATE_CONVERT_IN_PROGRESS 1
+#define PK_STATE_VALID		     2
+
+struct s390_paes_ctx {
+	/* source key material used to derive a protected key from */
+	u8 keybuf[PAES_MAX_KEYSIZE];
+	unsigned int keylen;
+
+	/* cpacf function code to use with this protected key type */
+	long fc;
+
+	/* nr of requests enqueued via crypto engine which use this tfm ctx */
+	atomic_t via_engine_ctr;
+
+	/* spinlock to atomic read/update all the following fields */
+	spinlock_t pk_lock;
+
+	/* see PK_STATE* defines above, < 0 holds convert failure rc  */
+	int pk_state;
+	/* if state is valid, pk holds the protected key */
+	struct paes_protkey pk;
+};
+
+struct s390_pxts_ctx {
+	/* source key material used to derive a protected key from */
+	u8 keybuf[2 * PAES_MAX_KEYSIZE];
 	unsigned int keylen;
+
+	/* cpacf function code to use with this protected key type */
+	long fc;
+
+	/* nr of requests enqueued via crypto engine which use this tfm ctx */
+	atomic_t via_engine_ctr;
+
+	/* spinlock to atomic read/update all the following fields */
+	spinlock_t pk_lock;
+
+	/* see PK_STATE* defines above, < 0 holds convert failure rc  */
+	int pk_state;
+	/* if state is valid, pk[] hold(s) the protected key(s) */
+	struct paes_protkey pk[2];
 };
 
 /*
@@ -89,214 +129,370 @@ static inline u32 make_clrkey_token(const u8 *ck, size_t cklen, u8 *dest)
 	return sizeof(*token) + cklen;
 }
 
-static inline int _key_to_kb(struct key_blob *kb,
-			     const u8 *key,
-			     unsigned int keylen)
+/*
+ * paes_ctx_setkey() - Set key value into context, maybe construct
+ * a clear key token digestible by pkey from a clear key value.
+ */
+static inline int paes_ctx_setkey(struct s390_paes_ctx *ctx,
+				  const u8 *key, unsigned int keylen)
 {
+	if (keylen > sizeof(ctx->keybuf))
+		return -EINVAL;
+
 	switch (keylen) {
 	case 16:
 	case 24:
 	case 32:
 		/* clear key value, prepare pkey clear key token in keybuf */
-		memset(kb->keybuf, 0, sizeof(kb->keybuf));
-		kb->keylen = make_clrkey_token(key, keylen, kb->keybuf);
-		kb->key = kb->keybuf;
+		memset(ctx->keybuf, 0, sizeof(ctx->keybuf));
+		ctx->keylen = make_clrkey_token(key, keylen, ctx->keybuf);
 		break;
 	default:
 		/* other key material, let pkey handle this */
-		if (keylen <= sizeof(kb->keybuf))
-			kb->key = kb->keybuf;
-		else {
-			kb->key = kmalloc(keylen, GFP_KERNEL);
-			if (!kb->key)
-				return -ENOMEM;
-		}
-		memcpy(kb->key, key, keylen);
-		kb->keylen = keylen;
+		memcpy(ctx->keybuf, key, keylen);
+		ctx->keylen = keylen;
 		break;
 	}
 
 	return 0;
 }
 
-static inline int _xts_key_to_kb(struct key_blob *kb,
-				 const u8 *key,
-				 unsigned int keylen)
+/*
+ * pxts_ctx_setkey() - Set key value into context, maybe construct
+ * a clear key token digestible by pkey from a clear key value.
+ */
+static inline int pxts_ctx_setkey(struct s390_pxts_ctx *ctx,
+				  const u8 *key, unsigned int keylen)
 {
 	size_t cklen = keylen / 2;
 
-	memset(kb->keybuf, 0, sizeof(kb->keybuf));
+	if (keylen > sizeof(ctx->keybuf))
+		return -EINVAL;
 
 	switch (keylen) {
 	case 32:
 	case 64:
 		/* clear key value, prepare pkey clear key tokens in keybuf */
-		kb->key = kb->keybuf;
-		kb->keylen  = make_clrkey_token(key, cklen, kb->key);
-		kb->keylen += make_clrkey_token(key + cklen, cklen,
-						kb->key + kb->keylen);
+		memset(ctx->keybuf, 0, sizeof(ctx->keybuf));
+		ctx->keylen = make_clrkey_token(key, cklen, ctx->keybuf);
+		ctx->keylen += make_clrkey_token(key + cklen, cklen,
+						 ctx->keybuf + ctx->keylen);
 		break;
 	default:
 		/* other key material, let pkey handle this */
-		if (keylen <= sizeof(kb->keybuf)) {
-			kb->key = kb->keybuf;
-		} else {
-			kb->key = kmalloc(keylen, GFP_KERNEL);
-			if (!kb->key)
-				return -ENOMEM;
-		}
-		memcpy(kb->key, key, keylen);
-		kb->keylen = keylen;
+		memcpy(ctx->keybuf, key, keylen);
+		ctx->keylen = keylen;
 		break;
 	}
 
 	return 0;
 }
 
-static inline void _free_kb_keybuf(struct key_blob *kb)
+/*
+ * Convert the raw key material into a protected key via PKEY api.
+ * This function may sleep - don't call in non-sleeping context.
+ */
+static inline int convert_key(const u8 *key, unsigned int keylen,
+			      struct paes_protkey *pk)
 {
-	if (kb->key && kb->key != kb->keybuf
-	    && kb->keylen > sizeof(kb->keybuf)) {
-		kfree_sensitive(kb->key);
-		kb->key = NULL;
+	int rc, i;
+
+	pk->len = sizeof(pk->protkey);
+
+	/*
+	 * In case of a busy card retry with increasing delay
+	 * of 200, 400, 800 and 1600 ms - in total 3 s.
+	 */
+	for (rc = -EIO, i = 0; rc && i < 5; i++) {
+		if (rc == -EBUSY && msleep_interruptible((1 << i) * 100)) {
+			rc = -EINTR;
+			goto out;
+		}
+		rc = pkey_key2protkey(key, keylen,
+				      pk->protkey, &pk->len, &pk->type,
+				      PKEY_XFLAG_NOMEMALLOC);
 	}
-	memzero_explicit(kb->keybuf, sizeof(kb->keybuf));
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-struct s390_paes_ctx {
-	struct key_blob kb;
+/*
+ * (Re-)Convert the raw key material from the ctx into a protected key
+ * via convert_key() function. Update the pk_state, pk_type, pk_len
+ * and the protected key in the tfm context.
+ * Please note this function may be invoked concurrently with the very
+ * same tfm context. The pk_lock spinlock in the context ensures an
+ * atomic update of the pk and the pk state but does not guarantee any
+ * order of update. So a fresh converted valid protected key may get
+ * updated with an 'old' expired key value. As the cpacf instructions
+ * detect this, refuse to operate with an invalid key and the calling
+ * code triggers a (re-)conversion this does no harm. This may lead to
+ * unnecessary additional conversion but never to invalid data on en-
+ * or decrypt operations.
+ */
+static int paes_convert_key(struct s390_paes_ctx *ctx)
+{
 	struct paes_protkey pk;
-	spinlock_t pk_lock;
-	unsigned long fc;
-};
+	int rc;
 
-struct s390_pxts_ctx {
-	struct key_blob kb;
-	struct paes_protkey pk[2];
-	spinlock_t pk_lock;
-	unsigned long fc;
-};
+	spin_lock_bh(&ctx->pk_lock);
+	ctx->pk_state = PK_STATE_CONVERT_IN_PROGRESS;
+	spin_unlock_bh(&ctx->pk_lock);
 
-static inline int __paes_keyblob2pkey(const u8 *key, unsigned int keylen,
-				      struct paes_protkey *pk)
-{
-	int i, rc = -EIO;
+	rc = convert_key(ctx->keybuf, ctx->keylen, &pk);
 
-	/* try three times in case of busy card */
-	for (i = 0; rc && i < 3; i++) {
-		if (rc == -EBUSY && in_task()) {
-			if (msleep_interruptible(1000))
-				return -EINTR;
-		}
-		rc = pkey_key2protkey(key, keylen, pk->protkey, &pk->len,
-				      &pk->type);
+	/* update context */
+	spin_lock_bh(&ctx->pk_lock);
+	if (rc) {
+		ctx->pk_state = rc;
+	} else {
+		ctx->pk_state = PK_STATE_VALID;
+		ctx->pk = pk;
 	}
+	spin_unlock_bh(&ctx->pk_lock);
 
+	memzero_explicit(&pk, sizeof(pk));
+	pr_debug("rc=%d\n", rc);
 	return rc;
 }
 
-static inline int __paes_convert_key(struct s390_paes_ctx *ctx)
+/*
+ * (Re-)Convert the raw xts key material from the ctx into a
+ * protected key via convert_key() function. Update the pk_state,
+ * pk_type, pk_len and the protected key in the tfm context.
+ * See also comments on function paes_convert_key.
+ */
+static int pxts_convert_key(struct s390_pxts_ctx *ctx)
 {
-	struct paes_protkey pk;
+	struct paes_protkey pk0, pk1;
+	size_t split_keylen;
 	int rc;
 
-	pk.len = sizeof(pk.protkey);
-	rc = __paes_keyblob2pkey(ctx->kb.key, ctx->kb.keylen, &pk);
+	spin_lock_bh(&ctx->pk_lock);
+	ctx->pk_state = PK_STATE_CONVERT_IN_PROGRESS;
+	spin_unlock_bh(&ctx->pk_lock);
+
+	rc = convert_key(ctx->keybuf, ctx->keylen, &pk0);
 	if (rc)
-		return rc;
+		goto out;
+
+	switch (pk0.type) {
+	case PKEY_KEYTYPE_AES_128:
+	case PKEY_KEYTYPE_AES_256:
+		/* second keytoken required */
+		if (ctx->keylen % 2) {
+			rc = -EINVAL;
+			goto out;
+		}
+		split_keylen = ctx->keylen / 2;
+		rc = convert_key(ctx->keybuf + split_keylen,
+				 split_keylen, &pk1);
+		if (rc)
+			goto out;
+		if (pk0.type != pk1.type) {
+			rc = -EINVAL;
+			goto out;
+		}
+		break;
+	case PKEY_KEYTYPE_AES_XTS_128:
+	case PKEY_KEYTYPE_AES_XTS_256:
+		/* single key */
+		pk1.type = 0;
+		break;
+	default:
+		/* unsupported protected keytype */
+		rc = -EINVAL;
+		goto out;
+	}
 
+out:
+	/* update context */
 	spin_lock_bh(&ctx->pk_lock);
-	memcpy(&ctx->pk, &pk, sizeof(pk));
+	if (rc) {
+		ctx->pk_state = rc;
+	} else {
+		ctx->pk_state = PK_STATE_VALID;
+		ctx->pk[0] = pk0;
+		ctx->pk[1] = pk1;
+	}
 	spin_unlock_bh(&ctx->pk_lock);
 
-	return 0;
+	memzero_explicit(&pk0, sizeof(pk0));
+	memzero_explicit(&pk1, sizeof(pk1));
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static int ecb_paes_init(struct crypto_skcipher *tfm)
-{
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+/*
+ * PAES ECB implementation
+ */
 
-	ctx->kb.key = NULL;
-	spin_lock_init(&ctx->pk_lock);
+struct ecb_param {
+	u8 key[PAES_256_PROTKEY_SIZE];
+} __packed;
 
-	return 0;
-}
+struct s390_pecb_req_ctx {
+	unsigned long modifier;
+	struct skcipher_walk walk;
+	bool param_init_done;
+	struct ecb_param param;
+};
 
-static void ecb_paes_exit(struct crypto_skcipher *tfm)
+static int ecb_paes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			   unsigned int key_len)
 {
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	_free_kb_keybuf(&ctx->kb);
-}
-
-static inline int __ecb_paes_set_key(struct s390_paes_ctx *ctx)
-{
-	unsigned long fc;
+	long fc;
 	int rc;
 
-	rc = __paes_convert_key(ctx);
+	/* set raw key into context */
+	rc = paes_ctx_setkey(ctx, in_key, key_len);
 	if (rc)
-		return rc;
+		goto out;
 
-	/* Pick the correct function code based on the protected key type */
-	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KM_PAES_128 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KM_PAES_192 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KM_PAES_256 : 0;
+	/* convert key into protected key */
+	rc = paes_convert_key(ctx);
+	if (rc)
+		goto out;
 
-	/* Check if the function code is available */
+	/* Pick the correct function code based on the protected key type */
+	switch (ctx->pk.type) {
+	case PKEY_KEYTYPE_AES_128:
+		fc = CPACF_KM_PAES_128;
+		break;
+	case PKEY_KEYTYPE_AES_192:
+		fc = CPACF_KM_PAES_192;
+		break;
+	case PKEY_KEYTYPE_AES_256:
+		fc = CPACF_KM_PAES_256;
+		break;
+	default:
+		fc = 0;
+		break;
+	}
 	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
 
-	return ctx->fc ? 0 : -EINVAL;
+	rc = fc ? 0 : -EINVAL;
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static int ecb_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
-			    unsigned int key_len)
+static int ecb_paes_do_crypt(struct s390_paes_ctx *ctx,
+			     struct s390_pecb_req_ctx *req_ctx,
+			     bool maysleep)
 {
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int rc;
-
-	_free_kb_keybuf(&ctx->kb);
-	rc = _key_to_kb(&ctx->kb, in_key, key_len);
+	struct ecb_param *param = &req_ctx->param;
+	struct skcipher_walk *walk = &req_ctx->walk;
+	unsigned int nbytes, n, k;
+	int pk_state, rc = 0;
+
+	if (!req_ctx->param_init_done) {
+		/* fetch and check protected key state */
+		spin_lock_bh(&ctx->pk_lock);
+		pk_state = ctx->pk_state;
+		switch (pk_state) {
+		case PK_STATE_NO_KEY:
+			rc = -ENOKEY;
+			break;
+		case PK_STATE_CONVERT_IN_PROGRESS:
+			rc = -EKEYEXPIRED;
+			break;
+		case PK_STATE_VALID:
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			req_ctx->param_init_done = true;
+			break;
+		default:
+			rc = pk_state < 0 ? pk_state : -EIO;
+			break;
+		}
+		spin_unlock_bh(&ctx->pk_lock);
+	}
 	if (rc)
-		return rc;
+		goto out;
 
-	return __ecb_paes_set_key(ctx);
+	/*
+	 * Note that in case of partial processing or failure the walk
+	 * is NOT unmapped here. So a follow up task may reuse the walk
+	 * or in case of unrecoverable failure needs to unmap it.
+	 */
+	while ((nbytes = walk->nbytes) != 0) {
+		/* only use complete blocks */
+		n = nbytes & ~(AES_BLOCK_SIZE - 1);
+		k = cpacf_km(ctx->fc | req_ctx->modifier, param,
+			     walk->dst.virt.addr, walk->src.virt.addr, n);
+		if (k)
+			rc = skcipher_walk_done(walk, nbytes - k);
+		if (k < n) {
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = paes_convert_key(ctx);
+			if (rc)
+				goto out;
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			spin_unlock_bh(&ctx->pk_lock);
+		}
+	}
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
 static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
+	struct s390_pecb_req_ctx *req_ctx = skcipher_request_ctx(req);
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct {
-		u8 key[PAES_256_PROTKEY_SIZE];
-	} param;
-	struct skcipher_walk walk;
-	unsigned int nbytes, n, k;
+	struct skcipher_walk *walk = &req_ctx->walk;
 	int rc;
 
-	rc = skcipher_walk_virt(&walk, req, false);
+	/*
+	 * Attempt synchronous encryption first. If it fails, schedule the request
+	 * asynchronously via the crypto engine. To preserve execution order,
+	 * once a request is queued to the engine, further requests using the same
+	 * tfm will also be routed through the engine.
+	 */
+
+	rc = skcipher_walk_virt(walk, req, false);
 	if (rc)
-		return rc;
+		goto out;
 
-	spin_lock_bh(&ctx->pk_lock);
-	memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-	spin_unlock_bh(&ctx->pk_lock);
+	req_ctx->modifier = modifier;
+	req_ctx->param_init_done = false;
 
-	while ((nbytes = walk.nbytes) != 0) {
-		/* only use complete blocks */
-		n = nbytes & ~(AES_BLOCK_SIZE - 1);
-		k = cpacf_km(ctx->fc | modifier, &param,
-			     walk.dst.virt.addr, walk.src.virt.addr, n);
-		if (k)
-			rc = skcipher_walk_done(&walk, nbytes - k);
-		if (k < n) {
-			if (__paes_convert_key(ctx))
-				return skcipher_walk_done(&walk, -EIO);
-			spin_lock_bh(&ctx->pk_lock);
-			memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-			spin_unlock_bh(&ctx->pk_lock);
-		}
+	/* Try synchronous operation if no active engine usage */
+	if (!atomic_read(&ctx->via_engine_ctr)) {
+		rc = ecb_paes_do_crypt(ctx, req_ctx, false);
+		if (rc == 0)
+			goto out;
+	}
+
+	/*
+	 * If sync operation failed or key expired or there are already
+	 * requests enqueued via engine, fallback to async. Mark tfm as
+	 * using engine to serialize requests.
+	 */
+	if (rc == 0 || rc == -EKEYEXPIRED) {
+		atomic_inc(&ctx->via_engine_ctr);
+		rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req);
+		if (rc != -EINPROGRESS)
+			atomic_dec(&ctx->via_engine_ctr);
 	}
+
+	if (rc != -EINPROGRESS)
+		skcipher_walk_done(walk, rc);
+
+out:
+	if (rc != -EINPROGRESS)
+		memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("rc=%d\n", rc);
 	return rc;
 }
 
@@ -310,112 +506,256 @@ static int ecb_paes_decrypt(struct skcipher_request *req)
 	return ecb_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct skcipher_alg ecb_paes_alg = {
-	.base.cra_name		=	"ecb(paes)",
-	.base.cra_driver_name	=	"ecb-paes-s390",
-	.base.cra_priority	=	401,	/* combo: aes + ecb + 1 */
-	.base.cra_blocksize	=	AES_BLOCK_SIZE,
-	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
-	.base.cra_module	=	THIS_MODULE,
-	.base.cra_list		=	LIST_HEAD_INIT(ecb_paes_alg.base.cra_list),
-	.init			=	ecb_paes_init,
-	.exit			=	ecb_paes_exit,
-	.min_keysize		=	PAES_MIN_KEYSIZE,
-	.max_keysize		=	PAES_MAX_KEYSIZE,
-	.setkey			=	ecb_paes_set_key,
-	.encrypt		=	ecb_paes_encrypt,
-	.decrypt		=	ecb_paes_decrypt,
-};
-
-static int cbc_paes_init(struct crypto_skcipher *tfm)
+static int ecb_paes_init(struct crypto_skcipher *tfm)
 {
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	ctx->kb.key = NULL;
+	memset(ctx, 0, sizeof(*ctx));
 	spin_lock_init(&ctx->pk_lock);
 
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct s390_pecb_req_ctx));
+
 	return 0;
 }
 
-static void cbc_paes_exit(struct crypto_skcipher *tfm)
+static void ecb_paes_exit(struct crypto_skcipher *tfm)
 {
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	_free_kb_keybuf(&ctx->kb);
+	memzero_explicit(ctx, sizeof(*ctx));
 }
 
-static inline int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
+static int ecb_paes_do_one_request(struct crypto_engine *engine, void *areq)
 {
-	unsigned long fc;
+	struct skcipher_request *req = skcipher_request_cast(areq);
+	struct s390_pecb_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
 	int rc;
 
-	rc = __paes_convert_key(ctx);
-	if (rc)
-		return rc;
+	/* walk has already been prepared */
+
+	rc = ecb_paes_do_crypt(ctx, req_ctx, true);
+	if (rc == -EKEYEXPIRED) {
+		/*
+		 * Protected key expired, conversion is in process.
+		 * Trigger a re-schedule of this request by returning
+		 * -ENOSPC ("hardware queue is full") to the crypto engine.
+		 * To avoid immediately re-invocation of this callback,
+		 * tell the scheduler to voluntarily give up the CPU here.
+		 */
+		cond_resched();
+		pr_debug("rescheduling request\n");
+		return -ENOSPC;
+	} else if (rc) {
+		skcipher_walk_done(walk, rc);
+	}
 
-	/* Pick the correct function code based on the protected key type */
-	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KMC_PAES_128 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KMC_PAES_192 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KMC_PAES_256 : 0;
+	memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("request complete with rc=%d\n", rc);
+	local_bh_disable();
+	atomic_dec(&ctx->via_engine_ctr);
+	crypto_finalize_skcipher_request(engine, req, rc);
+	local_bh_enable();
+	return rc;
+}
 
-	/* Check if the function code is available */
-	ctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0;
+static struct skcipher_engine_alg ecb_paes_alg = {
+	.base = {
+		.base.cra_name	      = "ecb(paes)",
+		.base.cra_driver_name = "ecb-paes-s390",
+		.base.cra_priority    = 401,	/* combo: aes + ecb + 1 */
+		.base.cra_blocksize   = AES_BLOCK_SIZE,
+		.base.cra_ctxsize     = sizeof(struct s390_paes_ctx),
+		.base.cra_module      = THIS_MODULE,
+		.base.cra_list	      = LIST_HEAD_INIT(ecb_paes_alg.base.base.cra_list),
+		.init		      = ecb_paes_init,
+		.exit		      = ecb_paes_exit,
+		.min_keysize	      = PAES_MIN_KEYSIZE,
+		.max_keysize	      = PAES_MAX_KEYSIZE,
+		.setkey		      = ecb_paes_setkey,
+		.encrypt	      = ecb_paes_encrypt,
+		.decrypt	      = ecb_paes_decrypt,
+	},
+	.op = {
+		.do_one_request	      = ecb_paes_do_one_request,
+	},
+};
 
-	return ctx->fc ? 0 : -EINVAL;
-}
+/*
+ * PAES CBC implementation
+ */
+
+struct cbc_param {
+	u8 iv[AES_BLOCK_SIZE];
+	u8 key[PAES_256_PROTKEY_SIZE];
+} __packed;
+
+struct s390_pcbc_req_ctx {
+	unsigned long modifier;
+	struct skcipher_walk walk;
+	bool param_init_done;
+	struct cbc_param param;
+};
 
-static int cbc_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
-			    unsigned int key_len)
+static int cbc_paes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			   unsigned int key_len)
 {
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	long fc;
 	int rc;
 
-	_free_kb_keybuf(&ctx->kb);
-	rc = _key_to_kb(&ctx->kb, in_key, key_len);
+	/* set raw key into context */
+	rc = paes_ctx_setkey(ctx, in_key, key_len);
 	if (rc)
-		return rc;
+		goto out;
 
-	return __cbc_paes_set_key(ctx);
+	/* convert raw key into protected key */
+	rc = paes_convert_key(ctx);
+	if (rc)
+		goto out;
+
+	/* Pick the correct function code based on the protected key type */
+	switch (ctx->pk.type) {
+	case PKEY_KEYTYPE_AES_128:
+		fc = CPACF_KMC_PAES_128;
+		break;
+	case PKEY_KEYTYPE_AES_192:
+		fc = CPACF_KMC_PAES_192;
+		break;
+	case PKEY_KEYTYPE_AES_256:
+		fc = CPACF_KMC_PAES_256;
+		break;
+	default:
+		fc = 0;
+		break;
+	}
+	ctx->fc = (fc && cpacf_test_func(&kmc_functions, fc)) ? fc : 0;
+
+	rc = fc ? 0 : -EINVAL;
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier)
+static int cbc_paes_do_crypt(struct s390_paes_ctx *ctx,
+			     struct s390_pcbc_req_ctx *req_ctx,
+			     bool maysleep)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct {
-		u8 iv[AES_BLOCK_SIZE];
-		u8 key[PAES_256_PROTKEY_SIZE];
-	} param;
-	struct skcipher_walk walk;
+	struct cbc_param *param = &req_ctx->param;
+	struct skcipher_walk *walk = &req_ctx->walk;
 	unsigned int nbytes, n, k;
-	int rc;
-
-	rc = skcipher_walk_virt(&walk, req, false);
+	int pk_state, rc = 0;
+
+	if (!req_ctx->param_init_done) {
+		/* fetch and check protected key state */
+		spin_lock_bh(&ctx->pk_lock);
+		pk_state = ctx->pk_state;
+		switch (pk_state) {
+		case PK_STATE_NO_KEY:
+			rc = -ENOKEY;
+			break;
+		case PK_STATE_CONVERT_IN_PROGRESS:
+			rc = -EKEYEXPIRED;
+			break;
+		case PK_STATE_VALID:
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			req_ctx->param_init_done = true;
+			break;
+		default:
+			rc = pk_state < 0 ? pk_state : -EIO;
+			break;
+		}
+		spin_unlock_bh(&ctx->pk_lock);
+	}
 	if (rc)
-		return rc;
+		goto out;
 
-	memcpy(param.iv, walk.iv, AES_BLOCK_SIZE);
-	spin_lock_bh(&ctx->pk_lock);
-	memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-	spin_unlock_bh(&ctx->pk_lock);
+	memcpy(param->iv, walk->iv, AES_BLOCK_SIZE);
 
-	while ((nbytes = walk.nbytes) != 0) {
+	/*
+	 * Note that in case of partial processing or failure the walk
+	 * is NOT unmapped here. So a follow up task may reuse the walk
+	 * or in case of unrecoverable failure needs to unmap it.
+	 */
+	while ((nbytes = walk->nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
-		k = cpacf_kmc(ctx->fc | modifier, &param,
-			      walk.dst.virt.addr, walk.src.virt.addr, n);
+		k = cpacf_kmc(ctx->fc | req_ctx->modifier, param,
+			      walk->dst.virt.addr, walk->src.virt.addr, n);
 		if (k) {
-			memcpy(walk.iv, param.iv, AES_BLOCK_SIZE);
-			rc = skcipher_walk_done(&walk, nbytes - k);
+			memcpy(walk->iv, param->iv, AES_BLOCK_SIZE);
+			rc = skcipher_walk_done(walk, nbytes - k);
 		}
 		if (k < n) {
-			if (__paes_convert_key(ctx))
-				return skcipher_walk_done(&walk, -EIO);
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = paes_convert_key(ctx);
+			if (rc)
+				goto out;
 			spin_lock_bh(&ctx->pk_lock);
-			memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
 			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
+}
+
+static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier)
+{
+	struct s390_pcbc_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
+	int rc;
+
+	/*
+	 * Attempt synchronous encryption first. If it fails, schedule the request
+	 * asynchronously via the crypto engine. To preserve execution order,
+	 * once a request is queued to the engine, further requests using the same
+	 * tfm will also be routed through the engine.
+	 */
+
+	rc = skcipher_walk_virt(walk, req, false);
+	if (rc)
+		goto out;
+
+	req_ctx->modifier = modifier;
+	req_ctx->param_init_done = false;
+
+	/* Try synchronous operation if no active engine usage */
+	if (!atomic_read(&ctx->via_engine_ctr)) {
+		rc = cbc_paes_do_crypt(ctx, req_ctx, false);
+		if (rc == 0)
+			goto out;
+	}
+
+	/*
+	 * If sync operation failed or key expired or there are already
+	 * requests enqueued via engine, fallback to async. Mark tfm as
+	 * using engine to serialize requests.
+	 */
+	if (rc == 0 || rc == -EKEYEXPIRED) {
+		atomic_inc(&ctx->via_engine_ctr);
+		rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req);
+		if (rc != -EINPROGRESS)
+			atomic_dec(&ctx->via_engine_ctr);
+	}
+
+	if (rc != -EINPROGRESS)
+		skcipher_walk_done(walk, rc);
+
+out:
+	if (rc != -EINPROGRESS)
+		memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("rc=%d\n", rc);
 	return rc;
 }
 
@@ -429,496 +769,882 @@ static int cbc_paes_decrypt(struct skcipher_request *req)
 	return cbc_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static struct skcipher_alg cbc_paes_alg = {
-	.base.cra_name		=	"cbc(paes)",
-	.base.cra_driver_name	=	"cbc-paes-s390",
-	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
-	.base.cra_blocksize	=	AES_BLOCK_SIZE,
-	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
-	.base.cra_module	=	THIS_MODULE,
-	.base.cra_list		=	LIST_HEAD_INIT(cbc_paes_alg.base.cra_list),
-	.init			=	cbc_paes_init,
-	.exit			=	cbc_paes_exit,
-	.min_keysize		=	PAES_MIN_KEYSIZE,
-	.max_keysize		=	PAES_MAX_KEYSIZE,
-	.ivsize			=	AES_BLOCK_SIZE,
-	.setkey			=	cbc_paes_set_key,
-	.encrypt		=	cbc_paes_encrypt,
-	.decrypt		=	cbc_paes_decrypt,
-};
-
-static int xts_paes_init(struct crypto_skcipher *tfm)
+static int cbc_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	ctx->kb.key = NULL;
+	memset(ctx, 0, sizeof(*ctx));
 	spin_lock_init(&ctx->pk_lock);
 
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct s390_pcbc_req_ctx));
+
 	return 0;
 }
 
-static void xts_paes_exit(struct crypto_skcipher *tfm)
+static void cbc_paes_exit(struct crypto_skcipher *tfm)
 {
-	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	_free_kb_keybuf(&ctx->kb);
+	memzero_explicit(ctx, sizeof(*ctx));
 }
 
-static inline int __xts_paes_convert_key(struct s390_pxts_ctx *ctx)
+static int cbc_paes_do_one_request(struct crypto_engine *engine, void *areq)
 {
-	struct paes_protkey pk0, pk1;
-	size_t split_keylen;
+	struct skcipher_request *req = skcipher_request_cast(areq);
+	struct s390_pcbc_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
 	int rc;
 
-	pk0.len = sizeof(pk0.protkey);
-	pk1.len = sizeof(pk1.protkey);
-
-	rc = __paes_keyblob2pkey(ctx->kb.key, ctx->kb.keylen, &pk0);
-	if (rc)
-		return rc;
+	/* walk has already been prepared */
+
+	rc = cbc_paes_do_crypt(ctx, req_ctx, true);
+	if (rc == -EKEYEXPIRED) {
+		/*
+		 * Protected key expired, conversion is in process.
+		 * Trigger a re-schedule of this request by returning
+		 * -ENOSPC ("hardware queue is full") to the crypto engine.
+		 * To avoid immediately re-invocation of this callback,
+		 * tell the scheduler to voluntarily give up the CPU here.
+		 */
+		cond_resched();
+		pr_debug("rescheduling request\n");
+		return -ENOSPC;
+	} else if (rc) {
+		skcipher_walk_done(walk, rc);
+	}
 
-	switch (pk0.type) {
-	case PKEY_KEYTYPE_AES_128:
-	case PKEY_KEYTYPE_AES_256:
-		/* second keytoken required */
-		if (ctx->kb.keylen % 2)
-			return -EINVAL;
-		split_keylen = ctx->kb.keylen / 2;
+	memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("request complete with rc=%d\n", rc);
+	local_bh_disable();
+	atomic_dec(&ctx->via_engine_ctr);
+	crypto_finalize_skcipher_request(engine, req, rc);
+	local_bh_enable();
+	return rc;
+}
 
-		rc = __paes_keyblob2pkey(ctx->kb.key + split_keylen,
-					 split_keylen, &pk1);
-		if (rc)
-			return rc;
+static struct skcipher_engine_alg cbc_paes_alg = {
+	.base = {
+		.base.cra_name	      = "cbc(paes)",
+		.base.cra_driver_name = "cbc-paes-s390",
+		.base.cra_priority    = 402,	/* cbc-paes-s390 + 1 */
+		.base.cra_blocksize   = AES_BLOCK_SIZE,
+		.base.cra_ctxsize     = sizeof(struct s390_paes_ctx),
+		.base.cra_module      = THIS_MODULE,
+		.base.cra_list	      = LIST_HEAD_INIT(cbc_paes_alg.base.base.cra_list),
+		.init		      = cbc_paes_init,
+		.exit		      = cbc_paes_exit,
+		.min_keysize	      = PAES_MIN_KEYSIZE,
+		.max_keysize	      = PAES_MAX_KEYSIZE,
+		.ivsize		      = AES_BLOCK_SIZE,
+		.setkey		      = cbc_paes_setkey,
+		.encrypt	      = cbc_paes_encrypt,
+		.decrypt	      = cbc_paes_decrypt,
+	},
+	.op = {
+		.do_one_request	      = cbc_paes_do_one_request,
+	},
+};
 
-		if (pk0.type != pk1.type)
-			return -EINVAL;
-		break;
-	case PKEY_KEYTYPE_AES_XTS_128:
-	case PKEY_KEYTYPE_AES_XTS_256:
-		/* single key */
-		pk1.type = 0;
-		break;
-	default:
-		/* unsupported protected keytype */
-		return -EINVAL;
-	}
+/*
+ * PAES CTR implementation
+ */
 
-	spin_lock_bh(&ctx->pk_lock);
-	ctx->pk[0] = pk0;
-	ctx->pk[1] = pk1;
-	spin_unlock_bh(&ctx->pk_lock);
+struct ctr_param {
+	u8 key[PAES_256_PROTKEY_SIZE];
+} __packed;
 
-	return 0;
-}
+struct s390_pctr_req_ctx {
+	unsigned long modifier;
+	struct skcipher_walk walk;
+	bool param_init_done;
+	struct ctr_param param;
+};
 
-static inline int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
+static int ctr_paes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			   unsigned int key_len)
 {
-	unsigned long fc;
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	long fc;
 	int rc;
 
-	rc = __xts_paes_convert_key(ctx);
+	/* set raw key into context */
+	rc = paes_ctx_setkey(ctx, in_key, key_len);
 	if (rc)
-		return rc;
+		goto out;
+
+	/* convert raw key into protected key */
+	rc = paes_convert_key(ctx);
+	if (rc)
+		goto out;
 
 	/* Pick the correct function code based on the protected key type */
-	switch (ctx->pk[0].type) {
+	switch (ctx->pk.type) {
 	case PKEY_KEYTYPE_AES_128:
-		fc = CPACF_KM_PXTS_128;
-		break;
-	case PKEY_KEYTYPE_AES_256:
-		fc = CPACF_KM_PXTS_256;
+		fc = CPACF_KMCTR_PAES_128;
 		break;
-	case PKEY_KEYTYPE_AES_XTS_128:
-		fc = CPACF_KM_PXTS_128_FULL;
+	case PKEY_KEYTYPE_AES_192:
+		fc = CPACF_KMCTR_PAES_192;
 		break;
-	case PKEY_KEYTYPE_AES_XTS_256:
-		fc = CPACF_KM_PXTS_256_FULL;
+	case PKEY_KEYTYPE_AES_256:
+		fc = CPACF_KMCTR_PAES_256;
 		break;
 	default:
 		fc = 0;
 		break;
 	}
+	ctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0;
 
-	/* Check if the function code is available */
-	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+	rc = fc ? 0 : -EINVAL;
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
+}
+
+static inline unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	memcpy(ctrptr, iv, AES_BLOCK_SIZE);
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = (n / AES_BLOCK_SIZE) - 1; i > 0; i--) {
+		memcpy(ctrptr + AES_BLOCK_SIZE, ctrptr, AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + AES_BLOCK_SIZE, AES_BLOCK_SIZE);
+		ctrptr += AES_BLOCK_SIZE;
+	}
+	return n;
+}
+
+static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx,
+			     struct s390_pctr_req_ctx *req_ctx,
+			     bool maysleep)
+{
+	struct ctr_param *param = &req_ctx->param;
+	struct skcipher_walk *walk = &req_ctx->walk;
+	u8 buf[AES_BLOCK_SIZE], *ctrptr;
+	unsigned int nbytes, n, k;
+	int pk_state, locked, rc = 0;
+
+	if (!req_ctx->param_init_done) {
+		/* fetch and check protected key state */
+		spin_lock_bh(&ctx->pk_lock);
+		pk_state = ctx->pk_state;
+		switch (pk_state) {
+		case PK_STATE_NO_KEY:
+			rc = -ENOKEY;
+			break;
+		case PK_STATE_CONVERT_IN_PROGRESS:
+			rc = -EKEYEXPIRED;
+			break;
+		case PK_STATE_VALID:
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			req_ctx->param_init_done = true;
+			break;
+		default:
+			rc = pk_state < 0 ? pk_state : -EIO;
+			break;
+		}
+		spin_unlock_bh(&ctx->pk_lock);
+	}
+	if (rc)
+		goto out;
+
+	locked = mutex_trylock(&ctrblk_lock);
+
+	/*
+	 * Note that in case of partial processing or failure the walk
+	 * is NOT unmapped here. So a follow up task may reuse the walk
+	 * or in case of unrecoverable failure needs to unmap it.
+	 */
+	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
+		n = AES_BLOCK_SIZE;
+		if (nbytes >= 2 * AES_BLOCK_SIZE && locked)
+			n = __ctrblk_init(ctrblk, walk->iv, nbytes);
+		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv;
+		k = cpacf_kmctr(ctx->fc, param, walk->dst.virt.addr,
+				walk->src.virt.addr, n, ctrptr);
+		if (k) {
+			if (ctrptr == ctrblk)
+				memcpy(walk->iv, ctrptr + k - AES_BLOCK_SIZE,
+				       AES_BLOCK_SIZE);
+			crypto_inc(walk->iv, AES_BLOCK_SIZE);
+			rc = skcipher_walk_done(walk, nbytes - k);
+		}
+		if (k < n) {
+			if (!maysleep) {
+				if (locked)
+					mutex_unlock(&ctrblk_lock);
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = paes_convert_key(ctx);
+			if (rc) {
+				if (locked)
+					mutex_unlock(&ctrblk_lock);
+				goto out;
+			}
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			spin_unlock_bh(&ctx->pk_lock);
+		}
+	}
+	if (locked)
+		mutex_unlock(&ctrblk_lock);
+
+	/* final block may be < AES_BLOCK_SIZE, copy only nbytes */
+	if (nbytes) {
+		memset(buf, 0, AES_BLOCK_SIZE);
+		memcpy(buf, walk->src.virt.addr, nbytes);
+		while (1) {
+			if (cpacf_kmctr(ctx->fc, param, buf,
+					buf, AES_BLOCK_SIZE,
+					walk->iv) == AES_BLOCK_SIZE)
+				break;
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = paes_convert_key(ctx);
+			if (rc)
+				goto out;
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param->key, ctx->pk.protkey, sizeof(param->key));
+			spin_unlock_bh(&ctx->pk_lock);
+		}
+		memcpy(walk->dst.virt.addr, buf, nbytes);
+		crypto_inc(walk->iv, AES_BLOCK_SIZE);
+		rc = skcipher_walk_done(walk, 0);
+	}
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
+}
+
+static int ctr_paes_crypt(struct skcipher_request *req)
+{
+	struct s390_pctr_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
+	int rc;
+
+	/*
+	 * Attempt synchronous encryption first. If it fails, schedule the request
+	 * asynchronously via the crypto engine. To preserve execution order,
+	 * once a request is queued to the engine, further requests using the same
+	 * tfm will also be routed through the engine.
+	 */
+
+	rc = skcipher_walk_virt(walk, req, false);
+	if (rc)
+		goto out;
+
+	req_ctx->param_init_done = false;
+
+	/* Try synchronous operation if no active engine usage */
+	if (!atomic_read(&ctx->via_engine_ctr)) {
+		rc = ctr_paes_do_crypt(ctx, req_ctx, false);
+		if (rc == 0)
+			goto out;
+	}
+
+	/*
+	 * If sync operation failed or key expired or there are already
+	 * requests enqueued via engine, fallback to async. Mark tfm as
+	 * using engine to serialize requests.
+	 */
+	if (rc == 0 || rc == -EKEYEXPIRED) {
+		atomic_inc(&ctx->via_engine_ctr);
+		rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req);
+		if (rc != -EINPROGRESS)
+			atomic_dec(&ctx->via_engine_ctr);
+	}
+
+	if (rc != -EINPROGRESS)
+		skcipher_walk_done(walk, rc);
+
+out:
+	if (rc != -EINPROGRESS)
+		memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("rc=%d\n", rc);
+	return rc;
+}
+
+static int ctr_paes_init(struct crypto_skcipher *tfm)
+{
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	memset(ctx, 0, sizeof(*ctx));
+	spin_lock_init(&ctx->pk_lock);
+
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct s390_pctr_req_ctx));
+
+	return 0;
+}
+
+static void ctr_paes_exit(struct crypto_skcipher *tfm)
+{
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	memzero_explicit(ctx, sizeof(*ctx));
+}
+
+static int ctr_paes_do_one_request(struct crypto_engine *engine, void *areq)
+{
+	struct skcipher_request *req = skcipher_request_cast(areq);
+	struct s390_pctr_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
+	int rc;
 
-	return ctx->fc ? 0 : -EINVAL;
+	/* walk has already been prepared */
+
+	rc = ctr_paes_do_crypt(ctx, req_ctx, true);
+	if (rc == -EKEYEXPIRED) {
+		/*
+		 * Protected key expired, conversion is in process.
+		 * Trigger a re-schedule of this request by returning
+		 * -ENOSPC ("hardware queue is full") to the crypto engine.
+		 * To avoid immediately re-invocation of this callback,
+		 * tell the scheduler to voluntarily give up the CPU here.
+		 */
+		cond_resched();
+		pr_debug("rescheduling request\n");
+		return -ENOSPC;
+	} else if (rc) {
+		skcipher_walk_done(walk, rc);
+	}
+
+	memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("request complete with rc=%d\n", rc);
+	local_bh_disable();
+	atomic_dec(&ctx->via_engine_ctr);
+	crypto_finalize_skcipher_request(engine, req, rc);
+	local_bh_enable();
+	return rc;
 }
 
-static int xts_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
-			    unsigned int in_keylen)
+static struct skcipher_engine_alg ctr_paes_alg = {
+	.base = {
+		.base.cra_name	      =	"ctr(paes)",
+		.base.cra_driver_name =	"ctr-paes-s390",
+		.base.cra_priority    =	402,	/* ecb-paes-s390 + 1 */
+		.base.cra_blocksize   =	1,
+		.base.cra_ctxsize     =	sizeof(struct s390_paes_ctx),
+		.base.cra_module      =	THIS_MODULE,
+		.base.cra_list	      =	LIST_HEAD_INIT(ctr_paes_alg.base.base.cra_list),
+		.init		      =	ctr_paes_init,
+		.exit		      =	ctr_paes_exit,
+		.min_keysize	      =	PAES_MIN_KEYSIZE,
+		.max_keysize	      =	PAES_MAX_KEYSIZE,
+		.ivsize		      =	AES_BLOCK_SIZE,
+		.setkey		      =	ctr_paes_setkey,
+		.encrypt	      =	ctr_paes_crypt,
+		.decrypt	      =	ctr_paes_crypt,
+		.chunksize	      =	AES_BLOCK_SIZE,
+	},
+	.op = {
+		.do_one_request	      = ctr_paes_do_one_request,
+	},
+};
+
+/*
+ * PAES XTS implementation
+ */
+
+struct xts_full_km_param {
+	u8 key[64];
+	u8 tweak[16];
+	u8 nap[16];
+	u8 wkvp[32];
+} __packed;
+
+struct xts_km_param {
+	u8 key[PAES_256_PROTKEY_SIZE];
+	u8 init[16];
+} __packed;
+
+struct xts_pcc_param {
+	u8 key[PAES_256_PROTKEY_SIZE];
+	u8 tweak[16];
+	u8 block[16];
+	u8 bit[16];
+	u8 xts[16];
+} __packed;
+
+struct s390_pxts_req_ctx {
+	unsigned long modifier;
+	struct skcipher_walk walk;
+	bool param_init_done;
+	union {
+		struct xts_full_km_param full_km_param;
+		struct xts_km_param km_param;
+	} param;
+};
+
+static int xts_paes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			   unsigned int in_keylen)
 {
 	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 	u8 ckey[2 * AES_MAX_KEY_SIZE];
 	unsigned int ckey_len;
+	long fc;
 	int rc;
 
 	if ((in_keylen == 32 || in_keylen == 64) &&
 	    xts_verify_key(tfm, in_key, in_keylen))
 		return -EINVAL;
 
-	_free_kb_keybuf(&ctx->kb);
-	rc = _xts_key_to_kb(&ctx->kb, in_key, in_keylen);
+	/* set raw key into context */
+	rc = pxts_ctx_setkey(ctx, in_key, in_keylen);
 	if (rc)
-		return rc;
+		goto out;
 
-	rc = __xts_paes_set_key(ctx);
+	/* convert raw key(s) into protected key(s) */
+	rc = pxts_convert_key(ctx);
 	if (rc)
-		return rc;
+		goto out;
 
 	/*
-	 * It is not possible on a single protected key (e.g. full AES-XTS) to
-	 * check, if k1 and k2 are the same.
-	 */
-	if (ctx->pk[0].type == PKEY_KEYTYPE_AES_XTS_128 ||
-	    ctx->pk[0].type == PKEY_KEYTYPE_AES_XTS_256)
-		return 0;
-	/*
 	 * xts_verify_key verifies the key length is not odd and makes
 	 * sure that the two keys are not the same. This can be done
-	 * on the two protected keys as well
+	 * on the two protected keys as well - but not for full xts keys.
 	 */
-	ckey_len = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ?
-		AES_KEYSIZE_128 : AES_KEYSIZE_256;
-	memcpy(ckey, ctx->pk[0].protkey, ckey_len);
-	memcpy(ckey + ckey_len, ctx->pk[1].protkey, ckey_len);
-	return xts_verify_key(tfm, ckey, 2*ckey_len);
+	if (ctx->pk[0].type == PKEY_KEYTYPE_AES_128 ||
+	    ctx->pk[0].type == PKEY_KEYTYPE_AES_256) {
+		ckey_len = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ?
+			AES_KEYSIZE_128 : AES_KEYSIZE_256;
+		memcpy(ckey, ctx->pk[0].protkey, ckey_len);
+		memcpy(ckey + ckey_len, ctx->pk[1].protkey, ckey_len);
+		rc = xts_verify_key(tfm, ckey, 2 * ckey_len);
+		memzero_explicit(ckey, sizeof(ckey));
+		if (rc)
+			goto out;
+	}
+
+	/* Pick the correct function code based on the protected key type */
+	switch (ctx->pk[0].type) {
+	case PKEY_KEYTYPE_AES_128:
+		fc = CPACF_KM_PXTS_128;
+		break;
+	case PKEY_KEYTYPE_AES_256:
+		fc = CPACF_KM_PXTS_256;
+		break;
+	case PKEY_KEYTYPE_AES_XTS_128:
+		fc = CPACF_KM_PXTS_128_FULL;
+		break;
+	case PKEY_KEYTYPE_AES_XTS_256:
+		fc = CPACF_KM_PXTS_256_FULL;
+		break;
+	default:
+		fc = 0;
+		break;
+	}
+	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+
+	rc = fc ? 0 : -EINVAL;
+
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static int paes_xts_crypt_full(struct skcipher_request *req,
-			       unsigned long modifier)
+static int xts_paes_do_crypt_fullkey(struct s390_pxts_ctx *ctx,
+				     struct s390_pxts_req_ctx *req_ctx,
+				     bool maysleep)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct xts_full_km_param *param = &req_ctx->param.full_km_param;
+	struct skcipher_walk *walk = &req_ctx->walk;
 	unsigned int keylen, offset, nbytes, n, k;
-	struct {
-		u8 key[64];
-		u8 tweak[16];
-		u8 nap[16];
-		u8 wkvp[32];
-	} fxts_param = {
-		.nap = {0},
-	};
-	struct skcipher_walk walk;
-	int rc;
+	int rc = 0;
 
-	rc = skcipher_walk_virt(&walk, req, false);
-	if (rc)
-		return rc;
+	/*
+	 * The calling function xts_paes_do_crypt() ensures the
+	 * protected key state is always PK_STATE_VALID when this
+	 * function is invoked.
+	 */
 
 	keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_XTS_128) ? 32 : 64;
 	offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_XTS_128) ? 32 : 0;
 
-	spin_lock_bh(&ctx->pk_lock);
-	memcpy(fxts_param.key + offset, ctx->pk[0].protkey, keylen);
-	memcpy(fxts_param.wkvp, ctx->pk[0].protkey + keylen,
-	       sizeof(fxts_param.wkvp));
-	spin_unlock_bh(&ctx->pk_lock);
-	memcpy(fxts_param.tweak, walk.iv, sizeof(fxts_param.tweak));
-	fxts_param.nap[0] = 0x01; /* initial alpha power (1, little-endian) */
+	if (!req_ctx->param_init_done) {
+		memset(param, 0, sizeof(*param));
+		spin_lock_bh(&ctx->pk_lock);
+		memcpy(param->key + offset, ctx->pk[0].protkey, keylen);
+		memcpy(param->wkvp, ctx->pk[0].protkey + keylen, sizeof(param->wkvp));
+		spin_unlock_bh(&ctx->pk_lock);
+		memcpy(param->tweak, walk->iv, sizeof(param->tweak));
+		param->nap[0] = 0x01; /* initial alpha power (1, little-endian) */
+		req_ctx->param_init_done = true;
+	}
 
-	while ((nbytes = walk.nbytes) != 0) {
+	/*
+	 * Note that in case of partial processing or failure the walk
+	 * is NOT unmapped here. So a follow up task may reuse the walk
+	 * or in case of unrecoverable failure needs to unmap it.
+	 */
+	while ((nbytes = walk->nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
-		k = cpacf_km(ctx->fc | modifier, fxts_param.key + offset,
-			     walk.dst.virt.addr, walk.src.virt.addr, n);
+		k = cpacf_km(ctx->fc | req_ctx->modifier, param->key + offset,
+			     walk->dst.virt.addr, walk->src.virt.addr, n);
 		if (k)
-			rc = skcipher_walk_done(&walk, nbytes - k);
+			rc = skcipher_walk_done(walk, nbytes - k);
 		if (k < n) {
-			if (__xts_paes_convert_key(ctx))
-				return skcipher_walk_done(&walk, -EIO);
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = pxts_convert_key(ctx);
+			if (rc)
+				goto out;
 			spin_lock_bh(&ctx->pk_lock);
-			memcpy(fxts_param.key + offset, ctx->pk[0].protkey,
-			       keylen);
-			memcpy(fxts_param.wkvp, ctx->pk[0].protkey + keylen,
-			       sizeof(fxts_param.wkvp));
+			memcpy(param->key + offset, ctx->pk[0].protkey, keylen);
+			memcpy(param->wkvp, ctx->pk[0].protkey + keylen, sizeof(param->wkvp));
 			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
 
+out:
+	pr_debug("rc=%d\n", rc);
 	return rc;
 }
 
-static int paes_xts_crypt(struct skcipher_request *req, unsigned long modifier)
+static inline int __xts_2keys_prep_param(struct s390_pxts_ctx *ctx,
+					 struct xts_km_param *param,
+					 struct skcipher_walk *walk,
+					 unsigned int keylen,
+					 unsigned int offset, bool maysleep)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct xts_pcc_param pcc_param;
+	unsigned long cc = 1;
+	int rc = 0;
+
+	while (cc) {
+		memset(&pcc_param, 0, sizeof(pcc_param));
+		memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+		spin_lock_bh(&ctx->pk_lock);
+		memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen);
+		memcpy(param->key + offset, ctx->pk[0].protkey, keylen);
+		spin_unlock_bh(&ctx->pk_lock);
+		cc = cpacf_pcc(ctx->fc, pcc_param.key + offset);
+		if (cc) {
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				break;
+			}
+			rc = pxts_convert_key(ctx);
+			if (rc)
+				break;
+			continue;
+		}
+		memcpy(param->init, pcc_param.xts, 16);
+	}
+
+	memzero_explicit(pcc_param.key, sizeof(pcc_param.key));
+	return rc;
+}
+
+static int xts_paes_do_crypt_2keys(struct s390_pxts_ctx *ctx,
+				   struct s390_pxts_req_ctx *req_ctx,
+				   bool maysleep)
+{
+	struct xts_km_param *param = &req_ctx->param.km_param;
+	struct skcipher_walk *walk = &req_ctx->walk;
 	unsigned int keylen, offset, nbytes, n, k;
-	struct {
-		u8 key[PAES_256_PROTKEY_SIZE];
-		u8 tweak[16];
-		u8 block[16];
-		u8 bit[16];
-		u8 xts[16];
-	} pcc_param;
-	struct {
-		u8 key[PAES_256_PROTKEY_SIZE];
-		u8 init[16];
-	} xts_param;
-	struct skcipher_walk walk;
-	int rc;
+	int rc = 0;
 
-	rc = skcipher_walk_virt(&walk, req, false);
-	if (rc)
-		return rc;
+	/*
+	 * The calling function xts_paes_do_crypt() ensures the
+	 * protected key state is always PK_STATE_VALID when this
+	 * function is invoked.
+	 */
 
 	keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 48 : 64;
 	offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 16 : 0;
 
-	memset(&pcc_param, 0, sizeof(pcc_param));
-	memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak));
-	spin_lock_bh(&ctx->pk_lock);
-	memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen);
-	memcpy(xts_param.key + offset, ctx->pk[0].protkey, keylen);
-	spin_unlock_bh(&ctx->pk_lock);
-	cpacf_pcc(ctx->fc, pcc_param.key + offset);
-	memcpy(xts_param.init, pcc_param.xts, 16);
+	if (!req_ctx->param_init_done) {
+		rc = __xts_2keys_prep_param(ctx, param, walk,
+					    keylen, offset, maysleep);
+		if (rc)
+			goto out;
+		req_ctx->param_init_done = true;
+	}
 
-	while ((nbytes = walk.nbytes) != 0) {
+	/*
+	 * Note that in case of partial processing or failure the walk
+	 * is NOT unmapped here. So a follow up task may reuse the walk
+	 * or in case of unrecoverable failure needs to unmap it.
+	 */
+	while ((nbytes = walk->nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
-		k = cpacf_km(ctx->fc | modifier, xts_param.key + offset,
-			     walk.dst.virt.addr, walk.src.virt.addr, n);
+		k = cpacf_km(ctx->fc | req_ctx->modifier, param->key + offset,
+			     walk->dst.virt.addr, walk->src.virt.addr, n);
 		if (k)
-			rc = skcipher_walk_done(&walk, nbytes - k);
+			rc = skcipher_walk_done(walk, nbytes - k);
 		if (k < n) {
-			if (__xts_paes_convert_key(ctx))
-				return skcipher_walk_done(&walk, -EIO);
+			if (!maysleep) {
+				rc = -EKEYEXPIRED;
+				goto out;
+			}
+			rc = pxts_convert_key(ctx);
+			if (rc)
+				goto out;
 			spin_lock_bh(&ctx->pk_lock);
-			memcpy(xts_param.key + offset,
-			       ctx->pk[0].protkey, keylen);
+			memcpy(param->key + offset, ctx->pk[0].protkey, keylen);
 			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
 
+out:
+	pr_debug("rc=%d\n", rc);
 	return rc;
 }
 
-static inline int xts_paes_crypt(struct skcipher_request *req, unsigned long modifier)
+static int xts_paes_do_crypt(struct s390_pxts_ctx *ctx,
+			     struct s390_pxts_req_ctx *req_ctx,
+			     bool maysleep)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int pk_state, rc = 0;
+
+	/* fetch and check protected key state */
+	spin_lock_bh(&ctx->pk_lock);
+	pk_state = ctx->pk_state;
+	switch (pk_state) {
+	case PK_STATE_NO_KEY:
+		rc = -ENOKEY;
+		break;
+	case PK_STATE_CONVERT_IN_PROGRESS:
+		rc = -EKEYEXPIRED;
+		break;
+	case PK_STATE_VALID:
+		break;
+	default:
+		rc = pk_state < 0 ? pk_state : -EIO;
+		break;
+	}
+	spin_unlock_bh(&ctx->pk_lock);
+	if (rc)
+		goto out;
 
+	/* Call the 'real' crypt function based on the xts prot key type. */
 	switch (ctx->fc) {
 	case CPACF_KM_PXTS_128:
 	case CPACF_KM_PXTS_256:
-		return paes_xts_crypt(req, modifier);
+		rc = xts_paes_do_crypt_2keys(ctx, req_ctx, maysleep);
+		break;
 	case CPACF_KM_PXTS_128_FULL:
 	case CPACF_KM_PXTS_256_FULL:
-		return paes_xts_crypt_full(req, modifier);
+		rc = xts_paes_do_crypt_fullkey(ctx, req_ctx, maysleep);
+		break;
 	default:
-		return -EINVAL;
+		rc = -EINVAL;
 	}
-}
 
-static int xts_paes_encrypt(struct skcipher_request *req)
-{
-	return xts_paes_crypt(req, 0);
+out:
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static int xts_paes_decrypt(struct skcipher_request *req)
+static inline int xts_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 {
-	return xts_paes_crypt(req, CPACF_DECRYPT);
-}
+	struct s390_pxts_req_ctx *req_ctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
+	int rc;
 
-static struct skcipher_alg xts_paes_alg = {
-	.base.cra_name		=	"xts(paes)",
-	.base.cra_driver_name	=	"xts-paes-s390",
-	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
-	.base.cra_blocksize	=	AES_BLOCK_SIZE,
-	.base.cra_ctxsize	=	sizeof(struct s390_pxts_ctx),
-	.base.cra_module	=	THIS_MODULE,
-	.base.cra_list		=	LIST_HEAD_INIT(xts_paes_alg.base.cra_list),
-	.init			=	xts_paes_init,
-	.exit			=	xts_paes_exit,
-	.min_keysize		=	2 * PAES_MIN_KEYSIZE,
-	.max_keysize		=	2 * PAES_MAX_KEYSIZE,
-	.ivsize			=	AES_BLOCK_SIZE,
-	.setkey			=	xts_paes_set_key,
-	.encrypt		=	xts_paes_encrypt,
-	.decrypt		=	xts_paes_decrypt,
-};
+	/*
+	 * Attempt synchronous encryption first. If it fails, schedule the request
+	 * asynchronously via the crypto engine. To preserve execution order,
+	 * once a request is queued to the engine, further requests using the same
+	 * tfm will also be routed through the engine.
+	 */
 
-static int ctr_paes_init(struct crypto_skcipher *tfm)
-{
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	rc = skcipher_walk_virt(walk, req, false);
+	if (rc)
+		goto out;
 
-	ctx->kb.key = NULL;
-	spin_lock_init(&ctx->pk_lock);
+	req_ctx->modifier = modifier;
+	req_ctx->param_init_done = false;
 
-	return 0;
-}
+	/* Try synchronous operation if no active engine usage */
+	if (!atomic_read(&ctx->via_engine_ctr)) {
+		rc = xts_paes_do_crypt(ctx, req_ctx, false);
+		if (rc == 0)
+			goto out;
+	}
 
-static void ctr_paes_exit(struct crypto_skcipher *tfm)
-{
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	/*
+	 * If sync operation failed or key expired or there are already
+	 * requests enqueued via engine, fallback to async. Mark tfm as
+	 * using engine to serialize requests.
+	 */
+	if (rc == 0 || rc == -EKEYEXPIRED) {
+		atomic_inc(&ctx->via_engine_ctr);
+		rc = crypto_transfer_skcipher_request_to_engine(paes_crypto_engine, req);
+		if (rc != -EINPROGRESS)
+			atomic_dec(&ctx->via_engine_ctr);
+	}
+
+	if (rc != -EINPROGRESS)
+		skcipher_walk_done(walk, rc);
 
-	_free_kb_keybuf(&ctx->kb);
+out:
+	if (rc != -EINPROGRESS)
+		memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("rc=%d\n", rc);
+	return rc;
 }
 
-static inline int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
+static int xts_paes_encrypt(struct skcipher_request *req)
 {
-	unsigned long fc;
-	int rc;
-
-	rc = __paes_convert_key(ctx);
-	if (rc)
-		return rc;
-
-	/* Pick the correct function code based on the protected key type */
-	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KMCTR_PAES_128 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KMCTR_PAES_192 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ?
-		CPACF_KMCTR_PAES_256 : 0;
-
-	/* Check if the function code is available */
-	ctx->fc = (fc && cpacf_test_func(&kmctr_functions, fc)) ? fc : 0;
+	return xts_paes_crypt(req, 0);
+}
 
-	return ctx->fc ? 0 : -EINVAL;
+static int xts_paes_decrypt(struct skcipher_request *req)
+{
+	return xts_paes_crypt(req, CPACF_DECRYPT);
 }
 
-static int ctr_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
-			    unsigned int key_len)
+static int xts_paes_init(struct crypto_skcipher *tfm)
 {
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int rc;
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	_free_kb_keybuf(&ctx->kb);
-	rc = _key_to_kb(&ctx->kb, in_key, key_len);
-	if (rc)
-		return rc;
+	memset(ctx, 0, sizeof(*ctx));
+	spin_lock_init(&ctx->pk_lock);
 
-	return __ctr_paes_set_key(ctx);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct s390_pxts_req_ctx));
+
+	return 0;
 }
 
-static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes)
+static void xts_paes_exit(struct crypto_skcipher *tfm)
 {
-	unsigned int i, n;
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	/* only use complete blocks, max. PAGE_SIZE */
-	memcpy(ctrptr, iv, AES_BLOCK_SIZE);
-	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
-	for (i = (n / AES_BLOCK_SIZE) - 1; i > 0; i--) {
-		memcpy(ctrptr + AES_BLOCK_SIZE, ctrptr, AES_BLOCK_SIZE);
-		crypto_inc(ctrptr + AES_BLOCK_SIZE, AES_BLOCK_SIZE);
-		ctrptr += AES_BLOCK_SIZE;
-	}
-	return n;
+	memzero_explicit(ctx, sizeof(*ctx));
 }
 
-static int ctr_paes_crypt(struct skcipher_request *req)
+static int xts_paes_do_one_request(struct crypto_engine *engine, void *areq)
 {
+	struct skcipher_request *req = skcipher_request_cast(areq);
+	struct s390_pxts_req_ctx *req_ctx = skcipher_request_ctx(req);
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	u8 buf[AES_BLOCK_SIZE], *ctrptr;
-	struct {
-		u8 key[PAES_256_PROTKEY_SIZE];
-	} param;
-	struct skcipher_walk walk;
-	unsigned int nbytes, n, k;
-	int rc, locked;
-
-	rc = skcipher_walk_virt(&walk, req, false);
-	if (rc)
-		return rc;
-
-	spin_lock_bh(&ctx->pk_lock);
-	memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-	spin_unlock_bh(&ctx->pk_lock);
-
-	locked = mutex_trylock(&ctrblk_lock);
+	struct s390_pxts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk *walk = &req_ctx->walk;
+	int rc;
 
-	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-		n = AES_BLOCK_SIZE;
-		if (nbytes >= 2*AES_BLOCK_SIZE && locked)
-			n = __ctrblk_init(ctrblk, walk.iv, nbytes);
-		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv;
-		k = cpacf_kmctr(ctx->fc, &param, walk.dst.virt.addr,
-				walk.src.virt.addr, n, ctrptr);
-		if (k) {
-			if (ctrptr == ctrblk)
-				memcpy(walk.iv, ctrptr + k - AES_BLOCK_SIZE,
-				       AES_BLOCK_SIZE);
-			crypto_inc(walk.iv, AES_BLOCK_SIZE);
-			rc = skcipher_walk_done(&walk, nbytes - k);
-		}
-		if (k < n) {
-			if (__paes_convert_key(ctx)) {
-				if (locked)
-					mutex_unlock(&ctrblk_lock);
-				return skcipher_walk_done(&walk, -EIO);
-			}
-			spin_lock_bh(&ctx->pk_lock);
-			memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-			spin_unlock_bh(&ctx->pk_lock);
-		}
-	}
-	if (locked)
-		mutex_unlock(&ctrblk_lock);
-	/*
-	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
-	 */
-	if (nbytes) {
-		memset(buf, 0, AES_BLOCK_SIZE);
-		memcpy(buf, walk.src.virt.addr, nbytes);
-		while (1) {
-			if (cpacf_kmctr(ctx->fc, &param, buf,
-					buf, AES_BLOCK_SIZE,
-					walk.iv) == AES_BLOCK_SIZE)
-				break;
-			if (__paes_convert_key(ctx))
-				return skcipher_walk_done(&walk, -EIO);
-			spin_lock_bh(&ctx->pk_lock);
-			memcpy(param.key, ctx->pk.protkey, PAES_256_PROTKEY_SIZE);
-			spin_unlock_bh(&ctx->pk_lock);
-		}
-		memcpy(walk.dst.virt.addr, buf, nbytes);
-		crypto_inc(walk.iv, AES_BLOCK_SIZE);
-		rc = skcipher_walk_done(&walk, nbytes);
+	/* walk has already been prepared */
+
+	rc = xts_paes_do_crypt(ctx, req_ctx, true);
+	if (rc == -EKEYEXPIRED) {
+		/*
+		 * Protected key expired, conversion is in process.
+		 * Trigger a re-schedule of this request by returning
+		 * -ENOSPC ("hardware queue is full") to the crypto engine.
+		 * To avoid immediately re-invocation of this callback,
+		 * tell the scheduler to voluntarily give up the CPU here.
+		 */
+		cond_resched();
+		pr_debug("rescheduling request\n");
+		return -ENOSPC;
+	} else if (rc) {
+		skcipher_walk_done(walk, rc);
 	}
 
+	memzero_explicit(&req_ctx->param, sizeof(req_ctx->param));
+	pr_debug("request complete with rc=%d\n", rc);
+	local_bh_disable();
+	atomic_dec(&ctx->via_engine_ctr);
+	crypto_finalize_skcipher_request(engine, req, rc);
+	local_bh_enable();
 	return rc;
 }
 
-static struct skcipher_alg ctr_paes_alg = {
-	.base.cra_name		=	"ctr(paes)",
-	.base.cra_driver_name	=	"ctr-paes-s390",
-	.base.cra_priority	=	402,	/* ecb-paes-s390 + 1 */
-	.base.cra_blocksize	=	1,
-	.base.cra_ctxsize	=	sizeof(struct s390_paes_ctx),
-	.base.cra_module	=	THIS_MODULE,
-	.base.cra_list		=	LIST_HEAD_INIT(ctr_paes_alg.base.cra_list),
-	.init			=	ctr_paes_init,
-	.exit			=	ctr_paes_exit,
-	.min_keysize		=	PAES_MIN_KEYSIZE,
-	.max_keysize		=	PAES_MAX_KEYSIZE,
-	.ivsize			=	AES_BLOCK_SIZE,
-	.setkey			=	ctr_paes_set_key,
-	.encrypt		=	ctr_paes_crypt,
-	.decrypt		=	ctr_paes_crypt,
-	.chunksize		=	AES_BLOCK_SIZE,
+static struct skcipher_engine_alg xts_paes_alg = {
+	.base = {
+		.base.cra_name	      =	"xts(paes)",
+		.base.cra_driver_name =	"xts-paes-s390",
+		.base.cra_priority    =	402,	/* ecb-paes-s390 + 1 */
+		.base.cra_blocksize   =	AES_BLOCK_SIZE,
+		.base.cra_ctxsize     =	sizeof(struct s390_pxts_ctx),
+		.base.cra_module      =	THIS_MODULE,
+		.base.cra_list	      =	LIST_HEAD_INIT(xts_paes_alg.base.base.cra_list),
+		.init		      =	xts_paes_init,
+		.exit		      =	xts_paes_exit,
+		.min_keysize	      =	2 * PAES_MIN_KEYSIZE,
+		.max_keysize	      =	2 * PAES_MAX_KEYSIZE,
+		.ivsize		      =	AES_BLOCK_SIZE,
+		.setkey		      =	xts_paes_setkey,
+		.encrypt	      =	xts_paes_encrypt,
+		.decrypt	      =	xts_paes_decrypt,
+	},
+	.op = {
+		.do_one_request	      = xts_paes_do_one_request,
+	},
 };
 
-static inline void __crypto_unregister_skcipher(struct skcipher_alg *alg)
+/*
+ * alg register, unregister, module init, exit
+ */
+
+static struct miscdevice paes_dev = {
+	.name	= "paes",
+	.minor	= MISC_DYNAMIC_MINOR,
+};
+
+static inline void __crypto_unregister_skcipher(struct skcipher_engine_alg *alg)
 {
-	if (!list_empty(&alg->base.cra_list))
-		crypto_unregister_skcipher(alg);
+	if (!list_empty(&alg->base.base.cra_list))
+		crypto_engine_unregister_skcipher(alg);
 }
 
 static void paes_s390_fini(void)
 {
+	if (paes_crypto_engine) {
+		crypto_engine_stop(paes_crypto_engine);
+		crypto_engine_exit(paes_crypto_engine);
+	}
 	__crypto_unregister_skcipher(&ctr_paes_alg);
 	__crypto_unregister_skcipher(&xts_paes_alg);
 	__crypto_unregister_skcipher(&cbc_paes_alg);
 	__crypto_unregister_skcipher(&ecb_paes_alg);
 	if (ctrblk)
-		free_page((unsigned long) ctrblk);
+		free_page((unsigned long)ctrblk);
+	misc_deregister(&paes_dev);
 }
 
 static int __init paes_s390_init(void)
 {
 	int rc;
 
+	/* register a simple paes pseudo misc device */
+	rc = misc_register(&paes_dev);
+	if (rc)
+		return rc;
+
+	/* with this pseudo devie alloc and start a crypto engine */
+	paes_crypto_engine =
+		crypto_engine_alloc_init_and_set(paes_dev.this_device,
+						 true, NULL, false, MAX_QLEN);
+	if (!paes_crypto_engine) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
+	rc = crypto_engine_start(paes_crypto_engine);
+	if (rc) {
+		crypto_engine_exit(paes_crypto_engine);
+		paes_crypto_engine = NULL;
+		goto out_err;
+	}
+
 	/* Query available functions for KM, KMC and KMCTR */
 	cpacf_query(CPACF_KM, &km_functions);
 	cpacf_query(CPACF_KMC, &kmc_functions);
@@ -927,40 +1653,45 @@ static int __init paes_s390_init(void)
 	if (cpacf_test_func(&km_functions, CPACF_KM_PAES_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PAES_192) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PAES_256)) {
-		rc = crypto_register_skcipher(&ecb_paes_alg);
+		rc = crypto_engine_register_skcipher(&ecb_paes_alg);
 		if (rc)
 			goto out_err;
+		pr_debug("%s registered\n", ecb_paes_alg.base.base.cra_driver_name);
 	}
 
 	if (cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
 	    cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256)) {
-		rc = crypto_register_skcipher(&cbc_paes_alg);
+		rc = crypto_engine_register_skcipher(&cbc_paes_alg);
 		if (rc)
 			goto out_err;
+		pr_debug("%s registered\n", cbc_paes_alg.base.base.cra_driver_name);
 	}
 
 	if (cpacf_test_func(&km_functions, CPACF_KM_PXTS_128) ||
 	    cpacf_test_func(&km_functions, CPACF_KM_PXTS_256)) {
-		rc = crypto_register_skcipher(&xts_paes_alg);
+		rc = crypto_engine_register_skcipher(&xts_paes_alg);
 		if (rc)
 			goto out_err;
+		pr_debug("%s registered\n", xts_paes_alg.base.base.cra_driver_name);
 	}
 
 	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_128) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_192) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_256)) {
-		ctrblk = (u8 *) __get_free_page(GFP_KERNEL);
+		ctrblk = (u8 *)__get_free_page(GFP_KERNEL);
 		if (!ctrblk) {
 			rc = -ENOMEM;
 			goto out_err;
 		}
-		rc = crypto_register_skcipher(&ctr_paes_alg);
+		rc = crypto_engine_register_skcipher(&ctr_paes_alg);
 		if (rc)
 			goto out_err;
+		pr_debug("%s registered\n", ctr_paes_alg.base.base.cra_driver_name);
 	}
 
 	return 0;
+
 out_err:
 	paes_s390_fini();
 	return rc;
diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h
index 2bb22db54c31..d757ccbce2b4 100644
--- a/arch/s390/crypto/sha.h
+++ b/arch/s390/crypto/sha.h
@@ -10,27 +10,33 @@
 #ifndef _CRYPTO_ARCH_S390_SHA_H
 #define _CRYPTO_ARCH_S390_SHA_H
 
-#include <linux/crypto.h>
-#include <crypto/sha1.h>
 #include <crypto/sha2.h>
 #include <crypto/sha3.h>
+#include <linux/types.h>
 
 /* must be big enough for the largest SHA variant */
-#define SHA3_STATE_SIZE			200
 #define CPACF_MAX_PARMBLOCK_SIZE	SHA3_STATE_SIZE
 #define SHA_MAX_BLOCK_SIZE		SHA3_224_BLOCK_SIZE
+#define S390_SHA_CTX_SIZE		sizeof(struct s390_sha_ctx)
 
 struct s390_sha_ctx {
 	u64 count;		/* message length in bytes */
-	u32 state[CPACF_MAX_PARMBLOCK_SIZE / sizeof(u32)];
-	u8 buf[SHA_MAX_BLOCK_SIZE];
+	union {
+		u32 state[CPACF_MAX_PARMBLOCK_SIZE / sizeof(u32)];
+		struct {
+			u64 state[SHA512_DIGEST_SIZE / sizeof(u64)];
+			u64 count_hi;
+		} sha512;
+	};
 	int func;		/* KIMD function to use */
-	int first_message_part;
+	bool first_message_part;
 };
 
 struct shash_desc;
 
-int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len);
-int s390_sha_final(struct shash_desc *desc, u8 *out);
+int s390_sha_update_blocks(struct shash_desc *desc, const u8 *data,
+			   unsigned int len);
+int s390_sha_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+		   u8 *out);
 
 #endif
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index bc3a22704e09..d229cbd2ba22 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -18,12 +18,12 @@
  *   Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
  *   Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  */
+#include <asm/cpacf.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
 #include <crypto/sha1.h>
-#include <asm/cpacf.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 #include "sha.h"
 
@@ -49,7 +49,6 @@ static int s390_sha1_export(struct shash_desc *desc, void *out)
 
 	octx->count = sctx->count;
 	memcpy(octx->state, sctx->state, sizeof(octx->state));
-	memcpy(octx->buffer, sctx->buf, sizeof(octx->buffer));
 	return 0;
 }
 
@@ -60,7 +59,6 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in)
 
 	sctx->count = ictx->count;
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
-	memcpy(sctx->buf, ictx->buffer, sizeof(ictx->buffer));
 	sctx->func = CPACF_KIMD_SHA_1;
 	return 0;
 }
@@ -68,16 +66,18 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in)
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	s390_sha1_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	s390_sha1_export,
 	.import		=	s390_sha1_import,
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha1_state),
+	.descsize	=	S390_SHA_CTX_SIZE,
+	.statesize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-s390",
 		.cra_priority	=	300,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
deleted file mode 100644
index 6f1ccdf93d3e..000000000000
--- a/arch/s390/crypto/sha256_s390.c
+++ /dev/null
@@ -1,143 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Cryptographic API.
- *
- * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm.
- *
- * s390 Version:
- *   Copyright IBM Corp. 2005, 2011
- *   Author(s): Jan Glauber (jang@de.ibm.com)
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
-#include <crypto/sha2.h>
-#include <asm/cpacf.h>
-
-#include "sha.h"
-
-static int s390_sha256_init(struct shash_desc *desc)
-{
-	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA256_H0;
-	sctx->state[1] = SHA256_H1;
-	sctx->state[2] = SHA256_H2;
-	sctx->state[3] = SHA256_H3;
-	sctx->state[4] = SHA256_H4;
-	sctx->state[5] = SHA256_H5;
-	sctx->state[6] = SHA256_H6;
-	sctx->state[7] = SHA256_H7;
-	sctx->count = 0;
-	sctx->func = CPACF_KIMD_SHA_256;
-
-	return 0;
-}
-
-static int sha256_export(struct shash_desc *desc, void *out)
-{
-	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-	struct sha256_state *octx = out;
-
-	octx->count = sctx->count;
-	memcpy(octx->state, sctx->state, sizeof(octx->state));
-	memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
-	return 0;
-}
-
-static int sha256_import(struct shash_desc *desc, const void *in)
-{
-	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-	const struct sha256_state *ictx = in;
-
-	sctx->count = ictx->count;
-	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
-	sctx->func = CPACF_KIMD_SHA_256;
-	return 0;
-}
-
-static struct shash_alg sha256_alg = {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	s390_sha256_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
-	.export		=	sha256_export,
-	.import		=	sha256_import,
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"sha256-s390",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static int s390_sha224_init(struct shash_desc *desc)
-{
-	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA224_H0;
-	sctx->state[1] = SHA224_H1;
-	sctx->state[2] = SHA224_H2;
-	sctx->state[3] = SHA224_H3;
-	sctx->state[4] = SHA224_H4;
-	sctx->state[5] = SHA224_H5;
-	sctx->state[6] = SHA224_H6;
-	sctx->state[7] = SHA224_H7;
-	sctx->count = 0;
-	sctx->func = CPACF_KIMD_SHA_256;
-
-	return 0;
-}
-
-static struct shash_alg sha224_alg = {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	s390_sha224_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
-	.export		=	sha256_export,
-	.import		=	sha256_import,
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"sha224-s390",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static int __init sha256_s390_init(void)
-{
-	int ret;
-
-	if (!cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_256))
-		return -ENODEV;
-	ret = crypto_register_shash(&sha256_alg);
-	if (ret < 0)
-		goto out;
-	ret = crypto_register_shash(&sha224_alg);
-	if (ret < 0)
-		crypto_unregister_shash(&sha256_alg);
-out:
-	return ret;
-}
-
-static void __exit sha256_s390_fini(void)
-{
-	crypto_unregister_shash(&sha224_alg);
-	crypto_unregister_shash(&sha256_alg);
-}
-
-module_cpu_feature_match(S390_CPU_FEATURE_MSA, sha256_s390_init);
-module_exit(sha256_s390_fini);
-
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha3_256_s390.c b/arch/s390/crypto/sha3_256_s390.c
index a84ef692f572..4a7731ac6bcd 100644
--- a/arch/s390/crypto/sha3_256_s390.c
+++ b/arch/s390/crypto/sha3_256_s390.c
@@ -8,12 +8,14 @@
  *   Copyright IBM Corp. 2019
  *   Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com)
  */
+#include <asm/cpacf.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
 #include <crypto/sha3.h>
-#include <asm/cpacf.h>
+#include <linux/cpufeature.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
 #include "sha.h"
 
@@ -21,11 +23,11 @@ static int sha3_256_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 
-	if (!test_facility(86)) /* msa 12 */
+	sctx->first_message_part = test_facility(86);
+	if (!sctx->first_message_part)
 		memset(sctx->state, 0, sizeof(sctx->state));
 	sctx->count = 0;
 	sctx->func = CPACF_KIMD_SHA3_256;
-	sctx->first_message_part = 1;
 
 	return 0;
 }
@@ -35,11 +37,11 @@ static int sha3_256_export(struct shash_desc *desc, void *out)
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	struct sha3_state *octx = out;
 
-	octx->rsiz = sctx->count;
+	if (sctx->first_message_part) {
+		memset(sctx->state, 0, sizeof(sctx->state));
+		sctx->first_message_part = 0;
+	}
 	memcpy(octx->st, sctx->state, sizeof(octx->st));
-	memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
-	octx->partial = sctx->first_message_part;
-
 	return 0;
 }
 
@@ -48,10 +50,9 @@ static int sha3_256_import(struct shash_desc *desc, const void *in)
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	const struct sha3_state *ictx = in;
 
-	sctx->count = ictx->rsiz;
+	sctx->count = 0;
 	memcpy(sctx->state, ictx->st, sizeof(ictx->st));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
-	sctx->first_message_part = ictx->partial;
+	sctx->first_message_part = 0;
 	sctx->func = CPACF_KIMD_SHA3_256;
 
 	return 0;
@@ -60,30 +61,26 @@ static int sha3_256_import(struct shash_desc *desc, const void *in)
 static int sha3_224_import(struct shash_desc *desc, const void *in)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-	const struct sha3_state *ictx = in;
 
-	sctx->count = ictx->rsiz;
-	memcpy(sctx->state, ictx->st, sizeof(ictx->st));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
-	sctx->first_message_part = ictx->partial;
+	sha3_256_import(desc, in);
 	sctx->func = CPACF_KIMD_SHA3_224;
-
 	return 0;
 }
 
 static struct shash_alg sha3_256_alg = {
 	.digestsize	=	SHA3_256_DIGEST_SIZE,	   /* = 32 */
 	.init		=	sha3_256_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha3_256_export,
 	.import		=	sha3_256_import,
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha3_state),
+	.descsize	=	S390_SHA_CTX_SIZE,
+	.statesize	=	SHA3_STATE_SIZE,
 	.base		=	{
 		.cra_name	 =	"sha3-256",
 		.cra_driver_name =	"sha3-256-s390",
 		.cra_priority	 =	300,
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	SHA3_256_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -93,28 +90,25 @@ static int sha3_224_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 
-	if (!test_facility(86)) /* msa 12 */
-		memset(sctx->state, 0, sizeof(sctx->state));
-	sctx->count = 0;
+	sha3_256_init(desc);
 	sctx->func = CPACF_KIMD_SHA3_224;
-	sctx->first_message_part = 1;
-
 	return 0;
 }
 
 static struct shash_alg sha3_224_alg = {
 	.digestsize	=	SHA3_224_DIGEST_SIZE,
 	.init		=	sha3_224_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha3_256_export, /* same as for 256 */
 	.import		=	sha3_224_import, /* function code different! */
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha3_state),
+	.descsize	=	S390_SHA_CTX_SIZE,
+	.statesize	=	SHA3_STATE_SIZE,
 	.base		=	{
 		.cra_name	 =	"sha3-224",
 		.cra_driver_name =	"sha3-224-s390",
 		.cra_priority	 =	300,
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	SHA3_224_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/sha3_512_s390.c b/arch/s390/crypto/sha3_512_s390.c
index 07528fc98ff7..018f02fff444 100644
--- a/arch/s390/crypto/sha3_512_s390.c
+++ b/arch/s390/crypto/sha3_512_s390.c
@@ -7,12 +7,14 @@
  * Copyright IBM Corp. 2019
  * Author(s): Joerg Schmidbauer (jschmidb@de.ibm.com)
  */
+#include <asm/cpacf.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
 #include <crypto/sha3.h>
-#include <asm/cpacf.h>
+#include <linux/cpufeature.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
 #include "sha.h"
 
@@ -20,11 +22,11 @@ static int sha3_512_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 
-	if (!test_facility(86)) /* msa 12 */
+	sctx->first_message_part = test_facility(86);
+	if (!sctx->first_message_part)
 		memset(sctx->state, 0, sizeof(sctx->state));
 	sctx->count = 0;
 	sctx->func = CPACF_KIMD_SHA3_512;
-	sctx->first_message_part = 1;
 
 	return 0;
 }
@@ -34,13 +36,12 @@ static int sha3_512_export(struct shash_desc *desc, void *out)
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	struct sha3_state *octx = out;
 
-	octx->rsiz = sctx->count;
-	octx->rsizw = sctx->count >> 32;
 
+	if (sctx->first_message_part) {
+		memset(sctx->state, 0, sizeof(sctx->state));
+		sctx->first_message_part = 0;
+	}
 	memcpy(octx->st, sctx->state, sizeof(octx->st));
-	memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
-	octx->partial = sctx->first_message_part;
-
 	return 0;
 }
 
@@ -49,13 +50,9 @@ static int sha3_512_import(struct shash_desc *desc, const void *in)
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	const struct sha3_state *ictx = in;
 
-	if (unlikely(ictx->rsizw))
-		return -ERANGE;
-	sctx->count = ictx->rsiz;
-
+	sctx->count = 0;
 	memcpy(sctx->state, ictx->st, sizeof(ictx->st));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
-	sctx->first_message_part = ictx->partial;
+	sctx->first_message_part = 0;
 	sctx->func = CPACF_KIMD_SHA3_512;
 
 	return 0;
@@ -64,33 +61,26 @@ static int sha3_512_import(struct shash_desc *desc, const void *in)
 static int sha3_384_import(struct shash_desc *desc, const void *in)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
-	const struct sha3_state *ictx = in;
 
-	if (unlikely(ictx->rsizw))
-		return -ERANGE;
-	sctx->count = ictx->rsiz;
-
-	memcpy(sctx->state, ictx->st, sizeof(ictx->st));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
-	sctx->first_message_part = ictx->partial;
+	sha3_512_import(desc, in);
 	sctx->func = CPACF_KIMD_SHA3_384;
-
 	return 0;
 }
 
 static struct shash_alg sha3_512_alg = {
 	.digestsize	=	SHA3_512_DIGEST_SIZE,
 	.init		=	sha3_512_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha3_512_export,
 	.import		=	sha3_512_import,
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha3_state),
+	.descsize	=	S390_SHA_CTX_SIZE,
+	.statesize	=	SHA3_STATE_SIZE,
 	.base		=	{
 		.cra_name	 =	"sha3-512",
 		.cra_driver_name =	"sha3-512-s390",
 		.cra_priority	 =	300,
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	SHA3_512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -102,28 +92,25 @@ static int sha3_384_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 
-	if (!test_facility(86)) /* msa 12 */
-		memset(sctx->state, 0, sizeof(sctx->state));
-	sctx->count = 0;
+	sha3_512_init(desc);
 	sctx->func = CPACF_KIMD_SHA3_384;
-	sctx->first_message_part = 1;
-
 	return 0;
 }
 
 static struct shash_alg sha3_384_alg = {
 	.digestsize	=	SHA3_384_DIGEST_SIZE,
 	.init		=	sha3_384_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha3_512_export, /* same as for 512 */
 	.import		=	sha3_384_import, /* function code different! */
-	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha3_state),
+	.descsize	=	S390_SHA_CTX_SIZE,
+	.statesize	=	SHA3_STATE_SIZE,
 	.base		=	{
 		.cra_name	 =	"sha3-384",
 		.cra_driver_name =	"sha3-384-s390",
 		.cra_priority	 =	300,
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	SHA3_384_BLOCK_SIZE,
 		.cra_ctxsize	 =	sizeof(struct s390_sha_ctx),
 		.cra_module	 =	THIS_MODULE,
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 04f11c407763..33711a29618c 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -7,14 +7,13 @@
  * Copyright IBM Corp. 2007
  * Author(s): Jan Glauber (jang@de.ibm.com)
  */
+#include <asm/cpacf.h>
 #include <crypto/internal/hash.h>
 #include <crypto/sha2.h>
+#include <linux/cpufeature.h>
 #include <linux/errno.h>
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/cpufeature.h>
-#include <asm/cpacf.h>
 
 #include "sha.h"
 
@@ -22,15 +21,16 @@ static int sha512_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 
-	*(__u64 *)&ctx->state[0] = SHA512_H0;
-	*(__u64 *)&ctx->state[2] = SHA512_H1;
-	*(__u64 *)&ctx->state[4] = SHA512_H2;
-	*(__u64 *)&ctx->state[6] = SHA512_H3;
-	*(__u64 *)&ctx->state[8] = SHA512_H4;
-	*(__u64 *)&ctx->state[10] = SHA512_H5;
-	*(__u64 *)&ctx->state[12] = SHA512_H6;
-	*(__u64 *)&ctx->state[14] = SHA512_H7;
+	ctx->sha512.state[0] = SHA512_H0;
+	ctx->sha512.state[1] = SHA512_H1;
+	ctx->sha512.state[2] = SHA512_H2;
+	ctx->sha512.state[3] = SHA512_H3;
+	ctx->sha512.state[4] = SHA512_H4;
+	ctx->sha512.state[5] = SHA512_H5;
+	ctx->sha512.state[6] = SHA512_H6;
+	ctx->sha512.state[7] = SHA512_H7;
 	ctx->count = 0;
+	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
 
 	return 0;
@@ -42,9 +42,8 @@ static int sha512_export(struct shash_desc *desc, void *out)
 	struct sha512_state *octx = out;
 
 	octx->count[0] = sctx->count;
-	octx->count[1] = 0;
+	octx->count[1] = sctx->sha512.count_hi;
 	memcpy(octx->state, sctx->state, sizeof(octx->state));
-	memcpy(octx->buf, sctx->buf, sizeof(octx->buf));
 	return 0;
 }
 
@@ -53,12 +52,10 @@ static int sha512_import(struct shash_desc *desc, const void *in)
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	const struct sha512_state *ictx = in;
 
-	if (unlikely(ictx->count[1]))
-		return -ERANGE;
 	sctx->count = ictx->count[0];
+	sctx->sha512.count_hi = ictx->count[1];
 
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
-	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
 	sctx->func = CPACF_KIMD_SHA_512;
 	return 0;
 }
@@ -66,16 +63,18 @@ static int sha512_import(struct shash_desc *desc, const void *in)
 static struct shash_alg sha512_alg = {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha512_export,
 	.import		=	sha512_import,
 	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha512_state),
+	.statesize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"sha512-s390",
 		.cra_priority	=	300,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -87,15 +86,16 @@ static int sha384_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 
-	*(__u64 *)&ctx->state[0] = SHA384_H0;
-	*(__u64 *)&ctx->state[2] = SHA384_H1;
-	*(__u64 *)&ctx->state[4] = SHA384_H2;
-	*(__u64 *)&ctx->state[6] = SHA384_H3;
-	*(__u64 *)&ctx->state[8] = SHA384_H4;
-	*(__u64 *)&ctx->state[10] = SHA384_H5;
-	*(__u64 *)&ctx->state[12] = SHA384_H6;
-	*(__u64 *)&ctx->state[14] = SHA384_H7;
+	ctx->sha512.state[0] = SHA384_H0;
+	ctx->sha512.state[1] = SHA384_H1;
+	ctx->sha512.state[2] = SHA384_H2;
+	ctx->sha512.state[3] = SHA384_H3;
+	ctx->sha512.state[4] = SHA384_H4;
+	ctx->sha512.state[5] = SHA384_H5;
+	ctx->sha512.state[6] = SHA384_H6;
+	ctx->sha512.state[7] = SHA384_H7;
 	ctx->count = 0;
+	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
 
 	return 0;
@@ -104,17 +104,19 @@ static int sha384_init(struct shash_desc *desc)
 static struct shash_alg sha384_alg = {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_init,
-	.update		=	s390_sha_update,
-	.final		=	s390_sha_final,
+	.update		=	s390_sha_update_blocks,
+	.finup		=	s390_sha_finup,
 	.export		=	sha512_export,
 	.import		=	sha512_import,
 	.descsize	=	sizeof(struct s390_sha_ctx),
-	.statesize	=	sizeof(struct sha512_state),
+	.statesize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"sha384-s390",
 		.cra_priority	=	300,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_ctxsize	=	sizeof(struct s390_sha_ctx),
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index 961d7d522af1..b5e2c365ea05 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -13,50 +13,33 @@
 #include <asm/cpacf.h>
 #include "sha.h"
 
-int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len)
+int s390_sha_update_blocks(struct shash_desc *desc, const u8 *data,
+			   unsigned int len)
 {
-	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
-	unsigned int index, n;
+	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int n;
 	int fc;
 
-	/* how much is already in the buffer? */
-	index = ctx->count % bsize;
-	ctx->count += len;
-
-	if ((index + len) < bsize)
-		goto store;
-
 	fc = ctx->func;
 	if (ctx->first_message_part)
-		fc |= test_facility(86) ? CPACF_KIMD_NIP : 0;
-
-	/* process one stored block */
-	if (index) {
-		memcpy(ctx->buf + index, data, bsize - index);
-		cpacf_kimd(fc, ctx->state, ctx->buf, bsize);
-		ctx->first_message_part = 0;
-		fc &= ~CPACF_KIMD_NIP;
-		data += bsize - index;
-		len -= bsize - index;
-		index = 0;
-	}
+		fc |= CPACF_KIMD_NIP;
 
 	/* process as many blocks as possible */
-	if (len >= bsize) {
-		n = (len / bsize) * bsize;
-		cpacf_kimd(fc, ctx->state, data, n);
-		ctx->first_message_part = 0;
-		data += n;
-		len -= n;
+	n = (len / bsize) * bsize;
+	ctx->count += n;
+	switch (ctx->func) {
+	case CPACF_KLMD_SHA_512:
+	case CPACF_KLMD_SHA3_384:
+		if (ctx->count < n)
+			ctx->sha512.count_hi++;
+		break;
 	}
-store:
-	if (len)
-		memcpy(ctx->buf + index , data, len);
-
-	return 0;
+	cpacf_kimd(fc, ctx->state, data, n);
+	ctx->first_message_part = 0;
+	return len - n;
 }
-EXPORT_SYMBOL_GPL(s390_sha_update);
+EXPORT_SYMBOL_GPL(s390_sha_update_blocks);
 
 static int s390_crypto_shash_parmsize(int func)
 {
@@ -77,15 +60,15 @@ static int s390_crypto_shash_parmsize(int func)
 	}
 }
 
-int s390_sha_final(struct shash_desc *desc, u8 *out)
+int s390_sha_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+		   u8 *out)
 {
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
-	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
-	u64 bits;
-	unsigned int n;
 	int mbl_offset, fc;
+	u64 bits;
+
+	ctx->count += len;
 
-	n = ctx->count % bsize;
 	bits = ctx->count * 8;
 	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
@@ -95,17 +78,16 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
-	case CPACF_KLMD_SHA_1:
-	case CPACF_KLMD_SHA_256:
-		memcpy(ctx->state + mbl_offset, &bits, sizeof(bits));
-		break;
 	case CPACF_KLMD_SHA_512:
-		/*
-		 * the SHA512 parmblock has a 128-bit mbl field, clear
-		 * high-order u64 field, copy bits to low-order u64 field
-		 */
-		memset(ctx->state + mbl_offset, 0x00, sizeof(bits));
+		/* The SHA512 parmblock has a 128-bit mbl field. */
+		if (ctx->count < len)
+			ctx->sha512.count_hi++;
+		ctx->sha512.count_hi <<= 3;
+		ctx->sha512.count_hi |= ctx->count >> 61;
 		mbl_offset += sizeof(u64) / sizeof(u32);
+		fallthrough;
+	case CPACF_KLMD_SHA_1:
+	case CPACF_KLMD_SHA_256:
 		memcpy(ctx->state + mbl_offset, &bits, sizeof(bits));
 		break;
 	case CPACF_KLMD_SHA3_224:
@@ -121,16 +103,14 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	fc |= test_facility(86) ? CPACF_KLMD_DUFOP : 0;
 	if (ctx->first_message_part)
 		fc |= CPACF_KLMD_NIP;
-	cpacf_klmd(fc, ctx->state, ctx->buf, n);
+	cpacf_klmd(fc, ctx->state, src, len);
 
 	/* copy digest to out */
 	memcpy(out, ctx->state, crypto_shash_digestsize(desc->tfm));
-	/* wipe context */
-	memset(ctx, 0, sizeof *ctx);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(s390_sha_final);
+EXPORT_SYMBOL_GPL(s390_sha_finup);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("s390 SHA cipher common functions");
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index 4131f0daa5ea..61220e717af0 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -9,6 +9,7 @@
 
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/hypfs.h>
 #include "hypfs.h"
@@ -107,7 +108,7 @@ static struct hypfs_dbfs_file dbfs_file_0c = {
  */
 int __init hypfs_diag0c_init(void)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 0;
 	hypfs_dbfs_create_file(&dbfs_file_0c);
 	return 0;
@@ -118,7 +119,7 @@ int __init hypfs_diag0c_init(void)
  */
 void hypfs_diag0c_exit(void)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return;
 	hypfs_dbfs_remove_file(&dbfs_file_0c);
 }
diff --git a/arch/s390/hypfs/hypfs_diag_fs.c b/arch/s390/hypfs/hypfs_diag_fs.c
index 00a6d370a280..ede951dc0085 100644
--- a/arch/s390/hypfs/hypfs_diag_fs.c
+++ b/arch/s390/hypfs/hypfs_diag_fs.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include "hypfs_diag.h"
@@ -208,6 +209,8 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 	snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_get_info_type(),
 							    cpu_info));
 	cpu_dir = hypfs_mkdir(cpus_dir, buffer);
+	if (IS_ERR(cpu_dir))
+		return PTR_ERR(cpu_dir);
 	rc = hypfs_create_u64(cpu_dir, "mgmtime",
 			      cpu_info__acc_time(diag204_get_info_type(), cpu_info) -
 			      cpu_info__lp_time(diag204_get_info_type(), cpu_info));
@@ -382,7 +385,7 @@ static void diag224_delete_name_table(void)
 
 int __init __hypfs_diag_fs_init(void)
 {
-	if (MACHINE_IS_LPAR)
+	if (machine_is_lpar())
 		return diag224_get_name_table();
 	return 0;
 }
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 3db40ad853e0..4db2895e4da3 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <asm/extable.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include <asm/timex.h>
@@ -121,7 +122,7 @@ static struct hypfs_dbfs_file dbfs_file_2fc = {
 
 int hypfs_vm_init(void)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 0;
 	if (diag2fc(0, all_guests, NULL) > 0)
 		diag2fc_guest_query = all_guests;
@@ -135,7 +136,7 @@ int hypfs_vm_init(void)
 
 void hypfs_vm_exit(void)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return;
 	hypfs_dbfs_remove_file(&dbfs_file_2fc);
 }
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index d428635abf08..96409573c75d 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -24,6 +24,7 @@
 #include <linux/kobject.h>
 #include <linux/seq_file.h>
 #include <linux/uio.h>
+#include <asm/machine.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
@@ -184,7 +185,7 @@ static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 	}
 	hypfs_delete_tree(sb->s_root);
-	if (MACHINE_IS_VM)
+	if (machine_is_vm())
 		rc = hypfs_vm_create_files(sb->s_root);
 	else
 		rc = hypfs_diag_create_files(sb->s_root);
@@ -273,7 +274,7 @@ static int hypfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_root = root_dentry = d_make_root(root_inode);
 	if (!root_dentry)
 		return -ENOMEM;
-	if (MACHINE_IS_VM)
+	if (machine_is_vm())
 		rc = hypfs_vm_create_files(root_dentry);
 	else
 		rc = hypfs_diag_create_files(root_dentry);
@@ -341,7 +342,7 @@ static struct dentry *hypfs_create_file(struct dentry *parent, const char *name,
 	struct inode *inode;
 
 	inode_lock(d_inode(parent));
-	dentry = lookup_one_len(name, parent, strlen(name));
+	dentry = lookup_noperm(&QSTR(name), parent);
 	if (IS_ERR(dentry)) {
 		dentry = ERR_PTR(-ENOMEM);
 		goto fail;
diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h
index 004d17ea05cf..317c07c09ae4 100644
--- a/arch/s390/include/asm/abs_lowcore.h
+++ b/arch/s390/include/asm/abs_lowcore.h
@@ -25,11 +25,4 @@ static inline void put_abs_lowcore(struct lowcore *lc)
 	put_cpu();
 }
 
-extern int relocate_lowcore;
-
-static inline int have_relocated_lowcore(void)
-{
-	return relocate_lowcore;
-}
-
 #endif /* _ASM_S390_ABS_LOWCORE_H */
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index 73e781b56bfe..c7bf60a541e9 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -32,8 +32,8 @@
 #define ALT_CTX_ALL		(ALT_CTX_EARLY | ALT_CTX_LATE)
 
 #define ALT_TYPE_FACILITY	0
-#define ALT_TYPE_SPEC		1
-#define ALT_TYPE_LOWCORE	2
+#define ALT_TYPE_FEATURE	1
+#define ALT_TYPE_SPEC		2
 
 #define ALT_DATA_SHIFT		0
 #define ALT_TYPE_SHIFT		20
@@ -43,13 +43,14 @@
 					 ALT_TYPE_FACILITY << ALT_TYPE_SHIFT	| \
 					 (facility) << ALT_DATA_SHIFT)
 
+#define ALT_FEATURE(feature)		(ALT_CTX_EARLY << ALT_CTX_SHIFT		| \
+					 ALT_TYPE_FEATURE << ALT_TYPE_SHIFT	| \
+					 (feature) << ALT_DATA_SHIFT)
+
 #define ALT_SPEC(facility)		(ALT_CTX_LATE << ALT_CTX_SHIFT		| \
 					 ALT_TYPE_SPEC << ALT_TYPE_SHIFT	| \
 					 (facility) << ALT_DATA_SHIFT)
 
-#define ALT_LOWCORE			(ALT_CTX_EARLY << ALT_CTX_SHIFT		| \
-					 ALT_TYPE_LOWCORE << ALT_TYPE_SHIFT)
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h
index a92ebbc7aa7a..99b2902c10fd 100644
--- a/arch/s390/include/asm/appldata.h
+++ b/arch/s390/include/asm/appldata.h
@@ -9,6 +9,7 @@
 #define _ASM_S390_APPLDATA_H
 
 #include <linux/io.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 
 #define APPLDATA_START_INTERVAL_REC	0x80
@@ -48,7 +49,7 @@ static inline int appldata_asm(struct appldata_parameter_list *parm_list,
 {
 	int ry;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return -EOPNOTSUPP;
 	parm_list->diag = 0xdc;
 	parm_list->function = fn;
diff --git a/arch/s390/include/asm/asce.h b/arch/s390/include/asm/asce.h
new file mode 100644
index 000000000000..f6dfaaba735a
--- /dev/null
+++ b/arch/s390/include/asm/asce.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_S390_ASCE_H
+#define _ASM_S390_ASCE_H
+
+#include <linux/thread_info.h>
+#include <linux/irqflags.h>
+#include <asm/lowcore.h>
+#include <asm/ctlreg.h>
+
+static inline bool enable_sacf_uaccess(void)
+{
+	unsigned long flags;
+
+	if (test_thread_flag(TIF_ASCE_PRIMARY))
+		return true;
+	local_irq_save(flags);
+	local_ctl_load(1, &get_lowcore()->kernel_asce);
+	set_thread_flag(TIF_ASCE_PRIMARY);
+	local_irq_restore(flags);
+	return false;
+}
+
+static inline void disable_sacf_uaccess(bool previous)
+{
+	unsigned long flags;
+
+	if (previous)
+		return;
+	local_irq_save(flags);
+	local_ctl_load(1, &get_lowcore()->user_asce);
+	clear_thread_flag(TIF_ASCE_PRIMARY);
+	local_irq_restore(flags);
+}
+
+#endif /* _ASM_S390_ASCE_H */
diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h
index 2e829c16fd8a..d23ea0c94e4e 100644
--- a/arch/s390/include/asm/asm-extable.h
+++ b/arch/s390/include/asm/asm-extable.h
@@ -14,6 +14,8 @@
 #define EX_TYPE_UA_LOAD_REGPAIR	6
 #define EX_TYPE_ZEROPAD		7
 #define EX_TYPE_FPC		8
+#define EX_TYPE_UA_MVCOS_TO	9
+#define EX_TYPE_UA_MVCOS_FROM	10
 
 #define EX_DATA_REG_ERR_SHIFT	0
 #define EX_DATA_REG_ERR		GENMASK(3, 0)
@@ -84,4 +86,10 @@
 #define EX_TABLE_FPC(_fault, _target)					\
 	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FPC, __stringify(%%r0), __stringify(%%r0), 0)
 
+#define EX_TABLE_UA_MVCOS_TO(_fault, _target)				\
+	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_MVCOS_TO, __stringify(%%r0), __stringify(%%r0), 0)
+
+#define EX_TABLE_UA_MVCOS_FROM(_fault, _target)				\
+	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_MVCOS_FROM, __stringify(%%r0), __stringify(%%r0), 0)
+
 #endif /* __ASM_EXTABLE_H */
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index 585678bbcd7a..21c26d842832 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -163,10 +163,10 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
 
 #undef __ATOMIC64_OPS
 
-#define __atomic_add_const(val, ptr)		__atomic_add(val, ptr)
-#define __atomic_add_const_barrier(val, ptr)	__atomic_add(val, ptr)
-#define __atomic64_add_const(val, ptr)		__atomic64_add(val, ptr)
-#define __atomic64_add_const_barrier(val, ptr)	__atomic64_add(val, ptr)
+#define __atomic_add_const(val, ptr)		((void)__atomic_add(val, ptr))
+#define __atomic_add_const_barrier(val, ptr)	((void)__atomic_add(val, ptr))
+#define __atomic64_add_const(val, ptr)		((void)__atomic64_add(val, ptr))
+#define __atomic64_add_const_barrier(val, ptr)	((void)__atomic64_add(val, ptr))
 
 #endif /* MARCH_HAS_Z196_FEATURES */
 
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index 59ab1192e2d5..54cb97603ec0 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -649,18 +649,30 @@ static inline void cpacf_trng(u8 *ucbuf, unsigned long ucbuf_len,
  *		 instruction
  * @func: the function code passed to PCC; see CPACF_KM_xxx defines
  * @param: address of parameter block; see POP for details on each func
+ *
+ * Returns the condition code, this is
+ * 0 - cc code 0 (normal completion)
+ * 1 - cc code 1 (protected key wkvp mismatch or src operand out of range)
+ * 2 - cc code 2 (something invalid, scalar multiply infinity, ...)
+ * Condition code 3 (partial completion) is handled within the asm code
+ * and never returned.
  */
-static inline void cpacf_pcc(unsigned long func, void *param)
+static inline int cpacf_pcc(unsigned long func, void *param)
 {
+	int cc;
+
 	asm volatile(
 		"	lgr	0,%[fc]\n"
 		"	lgr	1,%[pba]\n"
 		"0:	.insn	rre,%[opc] << 16,0,0\n" /* PCC opcode */
 		"	brc	1,0b\n" /* handle partial completion */
-		:
+		CC_IPM(cc)
+		: CC_OUT(cc, cc)
 		: [fc] "d" (func), [pba] "d" ((unsigned long)param),
 		  [opc] "i" (CPACF_PCC)
-		: "cc", "memory", "0", "1");
+		: CC_CLOBBER_LIST("memory", "0", "1"));
+
+	return CC_TRANSFORM(cc);
 }
 
 /**
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index e1a279e0d6a6..1798fbd59068 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -171,7 +171,7 @@ static inline int qctri(struct cpumf_ctr_info *info)
 {
 	int rc = -EINVAL;
 
-	asm volatile (
+	asm_inline volatile (
 		"0:	qctri	%1\n"
 		"1:	lhi	%0,0\n"
 		"2:\n"
@@ -185,7 +185,7 @@ static inline int lcctl(u64 ctl)
 {
 	int cc;
 
-	asm volatile (
+	asm_inline volatile (
 		"	lcctl	%[ctl]\n"
 		CC_IPM(cc)
 		: CC_OUT(cc, cc)
@@ -200,7 +200,7 @@ static inline int __ecctr(u64 ctr, u64 *content)
 	u64 _content;
 	int cc;
 
-	asm volatile (
+	asm_inline volatile (
 		"	ecctr	%[_content],%[ctr]\n"
 		CC_IPM(cc)
 		: CC_OUT(cc, cc), [_content] "=d" (_content)
diff --git a/arch/s390/include/asm/cpufeature.h b/arch/s390/include/asm/cpufeature.h
index 931204613753..6c6a99660e78 100644
--- a/arch/s390/include/asm/cpufeature.h
+++ b/arch/s390/include/asm/cpufeature.h
@@ -9,10 +9,13 @@
 #ifndef __ASM_S390_CPUFEATURE_H
 #define __ASM_S390_CPUFEATURE_H
 
+#include <asm/facility.h>
+
 enum {
 	S390_CPU_FEATURE_MSA,
 	S390_CPU_FEATURE_VXRS,
 	S390_CPU_FEATURE_UV,
+	S390_CPU_FEATURE_D288,
 	MAX_CPU_FEATURES
 };
 
@@ -20,4 +23,16 @@ enum {
 
 int cpu_have_feature(unsigned int nr);
 
+#define cpu_has_bear()		test_facility(193)
+#define cpu_has_edat1()		test_facility(8)
+#define cpu_has_edat2()		test_facility(78)
+#define cpu_has_gs()		test_facility(133)
+#define cpu_has_idte()		test_facility(3)
+#define cpu_has_nx()		test_facility(130)
+#define cpu_has_rdp()		test_facility(194)
+#define cpu_has_seq_insn()	test_facility(85)
+#define cpu_has_tlb_lc()	test_facility(51)
+#define cpu_has_topology()	test_facility(11)
+#define cpu_has_vx()		test_facility(129)
+
 #endif /* __ASM_S390_CPUFEATURE_H */
diff --git a/arch/s390/include/asm/current.h b/arch/s390/include/asm/current.h
index d03a922c641e..f9529f7cf62c 100644
--- a/arch/s390/include/asm/current.h
+++ b/arch/s390/include/asm/current.h
@@ -11,9 +11,25 @@
 #define _S390_CURRENT_H
 
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 
 struct task_struct;
 
-#define current ((struct task_struct *const)get_lowcore()->current_task)
+static __always_inline struct task_struct *get_current(void)
+{
+	unsigned long ptr, lc_current;
+
+	lc_current = offsetof(struct lowcore, current_task);
+	asm_inline(
+		ALTERNATIVE("	lg	%[ptr],%[offzero](%%r0)\n",
+			    "	lg	%[ptr],%[offalt](%%r0)\n",
+			    ALT_FEATURE(MFEATURE_LOWCORE))
+		: [ptr] "=d" (ptr)
+		: [offzero] "i" (lc_current),
+		  [offalt] "i" (lc_current + LOWCORE_ALT_ADDRESS));
+	return (struct task_struct *)ptr;
+}
+
+#define current get_current()
 
 #endif /* !(_S390_CURRENT_H) */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 5790630e31f0..8db8db3b1018 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -66,7 +66,7 @@ static inline void diag10_range(unsigned long start_pfn, unsigned long num_pfn)
 	end_addr = pfn_to_phys(start_pfn + num_pfn - 1);
 
 	diag_stat_inc(DIAG_STAT_X010);
-	asm volatile(
+	asm_inline volatile(
 		"0:	diag	%0,%1,0x10\n"
 		"1:	nopr	%%r7\n"
 		EX_TABLE(0b, 1b)
diff --git a/arch/s390/include/asm/diag288.h b/arch/s390/include/asm/diag288.h
new file mode 100644
index 000000000000..5e1b43cea9d6
--- /dev/null
+++ b/arch/s390/include/asm/diag288.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_S390_DIAG288_H
+#define _ASM_S390_DIAG288_H
+
+#include <asm/asm-extable.h>
+#include <asm/types.h>
+
+#define MIN_INTERVAL 15	    /* Minimal time supported by diag288 */
+#define MAX_INTERVAL 3600   /* One hour should be enough - pure estimation */
+
+#define WDT_DEFAULT_TIMEOUT 30
+
+/* Function codes - init, change, cancel */
+#define WDT_FUNC_INIT 0
+#define WDT_FUNC_CHANGE 1
+#define WDT_FUNC_CANCEL 2
+#define WDT_FUNC_CONCEAL 0x80000000
+
+/* Action codes for LPAR watchdog */
+#define LPARWDT_RESTART 0
+
+static inline int __diag288(unsigned int func, unsigned int timeout,
+			    unsigned long action, unsigned int len)
+{
+	union register_pair r1 = { .even = func, .odd = timeout, };
+	union register_pair r3 = { .even = action, .odd = len, };
+	int rc = -EINVAL;
+
+	asm volatile(
+		"	diag	%[r1],%[r3],0x288\n"
+		"0:	lhi	%[rc],0\n"
+		"1:"
+		EX_TABLE(0b, 1b)
+		: [rc] "+d" (rc)
+		: [r1] "d" (r1.pair), [r3] "d" (r3.pair)
+		: "cc", "memory");
+	return rc;
+}
+
+#endif /* _ASM_S390_DIAG288_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 8f2c23cc52b6..a03df312081e 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -158,9 +158,6 @@ enum {
 #define ELF_DATA	ELFDATA2MSB
 #define ELF_ARCH	EM_S390
 
-/* s390 specific phdr types */
-#define PT_S390_PGSTE	0x70000000
-
 /*
  * ELF register definitions..
  */
@@ -191,35 +188,6 @@ typedef s390_compat_regs compat_elf_gregset_t;
 	 && (x)->e_ident[EI_CLASS] == ELF_CLASS)
 #define compat_start_thread	start_thread31
 
-struct arch_elf_state {
-	int rc;
-};
-
-#define INIT_ARCH_ELF_STATE { .rc = 0 }
-
-#define arch_check_elf(ehdr, interp, interp_ehdr, state) (0)
-#ifdef CONFIG_PGSTE
-#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state)	\
-({								\
-	struct arch_elf_state *_state = state;			\
-	if ((phdr)->p_type == PT_S390_PGSTE &&			\
-	    !page_table_allocate_pgste &&			\
-	    !test_thread_flag(TIF_PGSTE) &&			\
-	    !current->mm->context.alloc_pgste) {		\
-		set_thread_flag(TIF_PGSTE);			\
-		set_pt_regs_flag(task_pt_regs(current),		\
-				 PIF_EXECVE_PGSTE_RESTART);	\
-		_state->rc = -EAGAIN;				\
-	}							\
-	_state->rc;						\
-})
-#else
-#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state)	\
-({								\
-	(state)->rc;						\
-})
-#endif
-
 /* For SVR4/S390 the function pointer to be registered with `atexit` is
    passed in R14. */
 #define ELF_PLAT_INIT(_r, load_addr) \
diff --git a/arch/s390/include/asm/fpu.h b/arch/s390/include/asm/fpu.h
index c84cb33913e2..960c6c67ad6c 100644
--- a/arch/s390/include/asm/fpu.h
+++ b/arch/s390/include/asm/fpu.h
@@ -44,6 +44,7 @@
 #ifndef _ASM_S390_FPU_H
 #define _ASM_S390_FPU_H
 
+#include <linux/cpufeature.h>
 #include <linux/processor.h>
 #include <linux/preempt.h>
 #include <linux/string.h>
@@ -51,12 +52,6 @@
 #include <asm/sigcontext.h>
 #include <asm/fpu-types.h>
 #include <asm/fpu-insn.h>
-#include <asm/facility.h>
-
-static inline bool cpu_has_vx(void)
-{
-	return likely(test_facility(129));
-}
 
 enum {
 	KERNEL_FPC_BIT = 0,
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index f5781794356b..942f21c39697 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -13,9 +13,11 @@
 static uaccess_kmsan_or_inline int						\
 __futex_atomic_##name(int oparg, int *old, u32 __user *uaddr)			\
 {										\
+	bool sacf_flag;								\
 	int rc, new;								\
 										\
 	instrument_copy_from_user_before(old, uaddr, sizeof(*old));		\
+	sacf_flag = enable_sacf_uaccess();					\
 	asm_inline volatile(							\
 		"	sacf	256\n"						\
 		"0:	l	%[old],%[uaddr]\n"				\
@@ -32,6 +34,7 @@ __futex_atomic_##name(int oparg, int *old, u32 __user *uaddr)			\
 		  [new] "=&d" (new), [uaddr] "+Q" (*uaddr)			\
 		: [oparg] "d" (oparg)						\
 		: "cc");							\
+	disable_sacf_uaccess(sacf_flag);					\
 	if (!rc)								\
 		instrument_copy_from_user_after(old, uaddr, sizeof(*old), 0);	\
 	return rc;								\
@@ -75,9 +78,11 @@ int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 static uaccess_kmsan_or_inline
 int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval)
 {
+	bool sacf_flag;
 	int rc;
 
 	instrument_copy_from_user_before(uval, uaddr, sizeof(*uval));
+	sacf_flag = enable_sacf_uaccess();
 	asm_inline volatile(
 		"	sacf	256\n"
 		"0:	cs	%[old],%[new],%[uaddr]\n"
@@ -88,6 +93,7 @@ int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32
 		: [rc] "=d" (rc), [old] "+d" (oldval), [uaddr] "+Q" (*uaddr)
 		: [new] "d" (newval)
 		: "cc", "memory");
+	disable_sacf_uaccess(sacf_flag);
 	*uval = oldval;
 	instrument_copy_from_user_after(uval, uaddr, sizeof(*uval), 0);
 	return rc;
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 4e73ef46d4b2..9f2814d0e1e9 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -139,7 +139,6 @@ int s390_replace_asce(struct gmap *gmap);
 void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
 int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
 			    unsigned long end, bool interruptible);
-int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split);
 unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
 
 /**
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f82..931fcc413598 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -9,12 +9,13 @@
 #ifndef _ASM_S390_HUGETLB_H
 #define _ASM_S390_HUGETLB_H
 
+#include <linux/cpufeature.h>
 #include <linux/pgtable.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <asm/page.h>
 
-#define hugepages_supported()			(MACHINE_HAS_EDAT1)
+#define hugepages_supported()	cpu_has_edat1()
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -25,8 +26,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +57,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +68,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +78,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index fc9933a743d6..faddb9aef3b8 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -33,9 +33,7 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL)
 
 #define ioremap_wc(addr, size)  \
-	ioremap_prot((addr), (size), pgprot_val(pgprot_writecombine(PAGE_KERNEL)))
-#define ioremap_wt(addr, size)  \
-	ioremap_prot((addr), (size), pgprot_val(pgprot_writethrough(PAGE_KERNEL)))
+	ioremap_prot((addr), (size), pgprot_writecombine(PAGE_KERNEL))
 
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index d9e705f4a697..bde6a496df5f 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -54,7 +54,6 @@ enum interruption_class {
 	IRQIO_C70,
 	IRQIO_TAP,
 	IRQIO_VMR,
-	IRQIO_LCS,
 	IRQIO_CTC,
 	IRQIO_ADM,
 	IRQIO_CSC,
diff --git a/arch/s390/include/asm/kfence.h b/arch/s390/include/asm/kfence.h
index e47fd8cbe701..e95e35eb8a3f 100644
--- a/arch/s390/include/asm/kfence.h
+++ b/arch/s390/include/asm/kfence.h
@@ -12,27 +12,16 @@ void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static __always_inline bool arch_kfence_init_pool(void)
 {
-	return true;
-}
-
-#define arch_kfence_test_address(addr) ((addr) & PAGE_MASK)
-
-/*
- * Do not split kfence pool to 4k mapping with arch_kfence_init_pool(),
- * but earlier where page table allocations still happen with memblock.
- * Reason is that arch_kfence_init_pool() gets called when the system
- * is still in a limbo state - disabling and enabling bottom halves is
- * not yet allowed, but that is what our page_table_alloc() would do.
- */
-static __always_inline void kfence_split_mapping(void)
-{
 #ifdef CONFIG_KFENCE
 	unsigned long pool_pages = KFENCE_POOL_SIZE >> PAGE_SHIFT;
 
 	set_memory_4k((unsigned long)__kfence_pool, pool_pages);
 #endif
+	return true;
 }
 
+#define arch_kfence_test_address(addr) ((addr) & PAGE_MASK)
+
 static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	__kernel_map_pages(virt_to_page((void *)addr), 1, !protect);
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 9a367866cab0..cb89e54ada25 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -20,14 +20,13 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/mmu_notifier.h>
+#include <asm/kvm_host_types.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
 #include <asm/fpu.h>
 #include <asm/isc.h>
 #include <asm/guarded_storage.h>
 
-#define KVM_S390_BSCA_CPU_SLOTS 64
-#define KVM_S390_ESCA_CPU_SLOTS 248
 #define KVM_MAX_VCPUS 255
 
 #define KVM_INTERNAL_MEM_SLOTS 1
@@ -51,342 +50,6 @@
 #define KVM_REQ_REFRESH_GUEST_PREFIX	\
 	KVM_ARCH_REQ_FLAGS(6, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
-#define SIGP_CTRL_C		0x80
-#define SIGP_CTRL_SCN_MASK	0x3f
-
-union bsca_sigp_ctrl {
-	__u8 value;
-	struct {
-		__u8 c : 1;
-		__u8 r : 1;
-		__u8 scn : 6;
-	};
-};
-
-union esca_sigp_ctrl {
-	__u16 value;
-	struct {
-		__u8 c : 1;
-		__u8 reserved: 7;
-		__u8 scn;
-	};
-};
-
-struct esca_entry {
-	union esca_sigp_ctrl sigp_ctrl;
-	__u16   reserved1[3];
-	__u64   sda;
-	__u64   reserved2[6];
-};
-
-struct bsca_entry {
-	__u8	reserved0;
-	union bsca_sigp_ctrl	sigp_ctrl;
-	__u16	reserved[3];
-	__u64	sda;
-	__u64	reserved2[2];
-};
-
-union ipte_control {
-	unsigned long val;
-	struct {
-		unsigned long k  : 1;
-		unsigned long kh : 31;
-		unsigned long kg : 32;
-	};
-};
-
-/*
- * Utility is defined as two bytes but having it four bytes wide
- * generates more efficient code. Since the following bytes are
- * reserved this makes no functional difference.
- */
-union sca_utility {
-	__u32 val;
-	struct {
-		__u32 mtcr : 1;
-		__u32	   : 31;
-	};
-};
-
-struct bsca_block {
-	union ipte_control ipte_control;
-	__u64	reserved[5];
-	__u64	mcn;
-	union sca_utility utility;
-	__u8	reserved2[4];
-	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
-};
-
-struct esca_block {
-	union ipte_control ipte_control;
-	__u64   reserved1[6];
-	union sca_utility utility;
-	__u8	reserved2[4];
-	__u64   mcn[4];
-	__u64   reserved3[20];
-	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
-};
-
-/*
- * This struct is used to store some machine check info from lowcore
- * for machine checks that happen while the guest is running.
- * This info in host's lowcore might be overwritten by a second machine
- * check from host when host is in the machine check's high-level handling.
- * The size is 24 bytes.
- */
-struct mcck_volatile_info {
-	__u64 mcic;
-	__u64 failing_storage_address;
-	__u32 ext_damage_code;
-	__u32 reserved;
-};
-
-#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \
-			  CR0_MEASUREMENT_ALERT_SUBMASK)
-#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \
-			   CR14_EXTERNAL_DAMAGE_SUBMASK)
-
-#define SIDAD_SIZE_MASK		0xff
-#define sida_addr(sie_block) phys_to_virt((sie_block)->sidad & PAGE_MASK)
-#define sida_size(sie_block) \
-	((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE)
-
-#define CPUSTAT_STOPPED    0x80000000
-#define CPUSTAT_WAIT       0x10000000
-#define CPUSTAT_ECALL_PEND 0x08000000
-#define CPUSTAT_STOP_INT   0x04000000
-#define CPUSTAT_IO_INT     0x02000000
-#define CPUSTAT_EXT_INT    0x01000000
-#define CPUSTAT_RUNNING    0x00800000
-#define CPUSTAT_RETAINED   0x00400000
-#define CPUSTAT_TIMING_SUB 0x00020000
-#define CPUSTAT_SIE_SUB    0x00010000
-#define CPUSTAT_RRF        0x00008000
-#define CPUSTAT_SLSV       0x00004000
-#define CPUSTAT_SLSR       0x00002000
-#define CPUSTAT_ZARCH      0x00000800
-#define CPUSTAT_MCDS       0x00000100
-#define CPUSTAT_KSS        0x00000200
-#define CPUSTAT_SM         0x00000080
-#define CPUSTAT_IBS        0x00000040
-#define CPUSTAT_GED2       0x00000010
-#define CPUSTAT_G          0x00000008
-#define CPUSTAT_GED        0x00000004
-#define CPUSTAT_J          0x00000002
-#define CPUSTAT_P          0x00000001
-
-struct kvm_s390_sie_block {
-	atomic_t cpuflags;		/* 0x0000 */
-	__u32 : 1;			/* 0x0004 */
-	__u32 prefix : 18;
-	__u32 : 1;
-	__u32 ibc : 12;
-	__u8	reserved08[4];		/* 0x0008 */
-#define PROG_IN_SIE (1<<0)
-	__u32	prog0c;			/* 0x000c */
-	union {
-		__u8	reserved10[16];		/* 0x0010 */
-		struct {
-			__u64	pv_handle_cpu;
-			__u64	pv_handle_config;
-		};
-	};
-#define PROG_BLOCK_SIE	(1<<0)
-#define PROG_REQUEST	(1<<1)
-	atomic_t prog20;		/* 0x0020 */
-	__u8	reserved24[4];		/* 0x0024 */
-	__u64	cputm;			/* 0x0028 */
-	__u64	ckc;			/* 0x0030 */
-	__u64	epoch;			/* 0x0038 */
-	__u32	svcc;			/* 0x0040 */
-#define LCTL_CR0	0x8000
-#define LCTL_CR6	0x0200
-#define LCTL_CR9	0x0040
-#define LCTL_CR10	0x0020
-#define LCTL_CR11	0x0010
-#define LCTL_CR14	0x0002
-	__u16   lctl;			/* 0x0044 */
-	__s16	icpua;			/* 0x0046 */
-#define ICTL_OPEREXC	0x80000000
-#define ICTL_PINT	0x20000000
-#define ICTL_LPSW	0x00400000
-#define ICTL_STCTL	0x00040000
-#define ICTL_ISKE	0x00004000
-#define ICTL_SSKE	0x00002000
-#define ICTL_RRBE	0x00001000
-#define ICTL_TPROT	0x00000200
-	__u32	ictl;			/* 0x0048 */
-#define ECA_CEI		0x80000000
-#define ECA_IB		0x40000000
-#define ECA_SIGPI	0x10000000
-#define ECA_MVPGI	0x01000000
-#define ECA_AIV		0x00200000
-#define ECA_VX		0x00020000
-#define ECA_PROTEXCI	0x00002000
-#define ECA_APIE	0x00000008
-#define ECA_SII		0x00000001
-	__u32	eca;			/* 0x004c */
-#define ICPT_INST	0x04
-#define ICPT_PROGI	0x08
-#define ICPT_INSTPROGI	0x0C
-#define ICPT_EXTREQ	0x10
-#define ICPT_EXTINT	0x14
-#define ICPT_IOREQ	0x18
-#define ICPT_WAIT	0x1c
-#define ICPT_VALIDITY	0x20
-#define ICPT_STOP	0x28
-#define ICPT_OPEREXC	0x2C
-#define ICPT_PARTEXEC	0x38
-#define ICPT_IOINST	0x40
-#define ICPT_KSS	0x5c
-#define ICPT_MCHKREQ	0x60
-#define ICPT_INT_ENABLE	0x64
-#define ICPT_PV_INSTR	0x68
-#define ICPT_PV_NOTIFY	0x6c
-#define ICPT_PV_PREF	0x70
-	__u8	icptcode;		/* 0x0050 */
-	__u8	icptstatus;		/* 0x0051 */
-	__u16	ihcpu;			/* 0x0052 */
-	__u8	reserved54;		/* 0x0054 */
-#define IICTL_CODE_NONE		 0x00
-#define IICTL_CODE_MCHK		 0x01
-#define IICTL_CODE_EXT		 0x02
-#define IICTL_CODE_IO		 0x03
-#define IICTL_CODE_RESTART	 0x04
-#define IICTL_CODE_SPECIFICATION 0x10
-#define IICTL_CODE_OPERAND	 0x11
-	__u8	iictl;			/* 0x0055 */
-	__u16	ipa;			/* 0x0056 */
-	__u32	ipb;			/* 0x0058 */
-	__u32	scaoh;			/* 0x005c */
-#define FPF_BPBC 	0x20
-	__u8	fpf;			/* 0x0060 */
-#define ECB_GS		0x40
-#define ECB_TE		0x10
-#define ECB_SPECI	0x08
-#define ECB_SRSI	0x04
-#define ECB_HOSTPROTINT	0x02
-#define ECB_PTF		0x01
-	__u8	ecb;			/* 0x0061 */
-#define ECB2_CMMA	0x80
-#define ECB2_IEP	0x20
-#define ECB2_PFMFI	0x08
-#define ECB2_ESCA	0x04
-#define ECB2_ZPCI_LSI	0x02
-	__u8    ecb2;                   /* 0x0062 */
-#define ECB3_AISI	0x20
-#define ECB3_AISII	0x10
-#define ECB3_DEA 0x08
-#define ECB3_AES 0x04
-#define ECB3_RI  0x01
-	__u8    ecb3;			/* 0x0063 */
-#define ESCA_SCAOL_MASK ~0x3fU
-	__u32	scaol;			/* 0x0064 */
-	__u8	sdf;			/* 0x0068 */
-	__u8    epdx;			/* 0x0069 */
-	__u8	cpnc;			/* 0x006a */
-	__u8	reserved6b;		/* 0x006b */
-	__u32	todpr;			/* 0x006c */
-#define GISA_FORMAT1 0x00000001
-	__u32	gd;			/* 0x0070 */
-	__u8	reserved74[12];		/* 0x0074 */
-	__u64	mso;			/* 0x0080 */
-	__u64	msl;			/* 0x0088 */
-	psw_t	gpsw;			/* 0x0090 */
-	__u64	gg14;			/* 0x00a0 */
-	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[8];		/* 0x00b0 */
-#define HPID_KVM	0x4
-#define HPID_VSIE	0x5
-	__u8	hpid;			/* 0x00b8 */
-	__u8	reservedb9[7];		/* 0x00b9 */
-	union {
-		struct {
-			__u32	eiparams;	/* 0x00c0 */
-			__u16	extcpuaddr;	/* 0x00c4 */
-			__u16	eic;		/* 0x00c6 */
-		};
-		__u64	mcic;			/* 0x00c0 */
-	} __packed;
-	__u32	reservedc8;		/* 0x00c8 */
-	union {
-		struct {
-			__u16	pgmilc;		/* 0x00cc */
-			__u16	iprcc;		/* 0x00ce */
-		};
-		__u32	edc;			/* 0x00cc */
-	} __packed;
-	union {
-		struct {
-			__u32	dxc;		/* 0x00d0 */
-			__u16	mcn;		/* 0x00d4 */
-			__u8	perc;		/* 0x00d6 */
-			__u8	peratmid;	/* 0x00d7 */
-		};
-		__u64	faddr;			/* 0x00d0 */
-	} __packed;
-	__u64	peraddr;		/* 0x00d8 */
-	__u8	eai;			/* 0x00e0 */
-	__u8	peraid;			/* 0x00e1 */
-	__u8	oai;			/* 0x00e2 */
-	__u8	armid;			/* 0x00e3 */
-	__u8	reservede4[4];		/* 0x00e4 */
-	union {
-		__u64	tecmc;		/* 0x00e8 */
-		struct {
-			__u16	subchannel_id;	/* 0x00e8 */
-			__u16	subchannel_nr;	/* 0x00ea */
-			__u32	io_int_parm;	/* 0x00ec */
-			__u32	io_int_word;	/* 0x00f0 */
-		};
-	} __packed;
-	__u8	reservedf4[8];		/* 0x00f4 */
-#define CRYCB_FORMAT_MASK 0x00000003
-#define CRYCB_FORMAT0 0x00000000
-#define CRYCB_FORMAT1 0x00000001
-#define CRYCB_FORMAT2 0x00000003
-	__u32	crycbd;			/* 0x00fc */
-	__u64	gcr[16];		/* 0x0100 */
-	union {
-		__u64	gbea;		/* 0x0180 */
-		__u64	sidad;
-	};
-	__u8    reserved188[8];		/* 0x0188 */
-	__u64   sdnxo;			/* 0x0190 */
-	__u8    reserved198[8];		/* 0x0198 */
-	__u32	fac;			/* 0x01a0 */
-	__u8	reserved1a4[20];	/* 0x01a4 */
-	__u64	cbrlo;			/* 0x01b8 */
-	__u8	reserved1c0[8];		/* 0x01c0 */
-#define ECD_HOSTREGMGMT	0x20000000
-#define ECD_MEF		0x08000000
-#define ECD_ETOKENF	0x02000000
-#define ECD_ECC		0x00200000
-#define ECD_HMAC	0x00004000
-	__u32	ecd;			/* 0x01c8 */
-	__u8	reserved1cc[18];	/* 0x01cc */
-	__u64	pp;			/* 0x01de */
-	__u8	reserved1e6[2];		/* 0x01e6 */
-	__u64	itdba;			/* 0x01e8 */
-	__u64   riccbd;			/* 0x01f0 */
-	__u64	gvrd;			/* 0x01f8 */
-} __packed __aligned(512);
-
-struct kvm_s390_itdb {
-	__u8	data[256];
-};
-
-struct sie_page {
-	struct kvm_s390_sie_block sie_block;
-	struct mcck_volatile_info mcck_info;	/* 0x0200 */
-	__u8 reserved218[360];		/* 0x0218 */
-	__u64 pv_grregs[16];		/* 0x0380 */
-	__u8 reserved400[512];		/* 0x0400 */
-	struct kvm_s390_itdb itdb;	/* 0x0600 */
-	__u8 reserved700[2304];		/* 0x0700 */
-};
-
 struct kvm_vcpu_stat {
 	struct kvm_vcpu_stat_generic generic;
 	u64 exit_userspace;
@@ -1056,7 +719,6 @@ bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu);
 extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc);
 extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 					 struct kvm_memory_slot *slot) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
diff --git a/arch/s390/include/asm/kvm_host_types.h b/arch/s390/include/asm/kvm_host_types.h
new file mode 100644
index 000000000000..1394d3fb648f
--- /dev/null
+++ b/arch/s390/include/asm/kvm_host_types.h
@@ -0,0 +1,348 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_KVM_HOST_TYPES_H
+#define _ASM_KVM_HOST_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/types.h>
+
+#define KVM_S390_BSCA_CPU_SLOTS 64
+#define KVM_S390_ESCA_CPU_SLOTS 248
+
+#define SIGP_CTRL_C		0x80
+#define SIGP_CTRL_SCN_MASK	0x3f
+
+union bsca_sigp_ctrl {
+	__u8 value;
+	struct {
+		__u8 c : 1;
+		__u8 r : 1;
+		__u8 scn : 6;
+	};
+};
+
+union esca_sigp_ctrl {
+	__u16 value;
+	struct {
+		__u8 c : 1;
+		__u8 reserved: 7;
+		__u8 scn;
+	};
+};
+
+struct esca_entry {
+	union esca_sigp_ctrl sigp_ctrl;
+	__u16	reserved1[3];
+	__u64	sda;
+	__u64	reserved2[6];
+};
+
+struct bsca_entry {
+	__u8	reserved0;
+	union bsca_sigp_ctrl	sigp_ctrl;
+	__u16	reserved[3];
+	__u64	sda;
+	__u64	reserved2[2];
+};
+
+union ipte_control {
+	unsigned long val;
+	struct {
+		unsigned long k  : 1;
+		unsigned long kh : 31;
+		unsigned long kg : 32;
+	};
+};
+
+/*
+ * Utility is defined as two bytes but having it four bytes wide
+ * generates more efficient code. Since the following bytes are
+ * reserved this makes no functional difference.
+ */
+union sca_utility {
+	__u32 val;
+	struct {
+		__u32 mtcr : 1;
+		__u32	   : 31;
+	};
+};
+
+struct bsca_block {
+	union ipte_control ipte_control;
+	__u64	reserved[5];
+	__u64	mcn;
+	union sca_utility utility;
+	__u8	reserved2[4];
+	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
+};
+
+struct esca_block {
+	union ipte_control ipte_control;
+	__u64	reserved1[6];
+	union sca_utility utility;
+	__u8	reserved2[4];
+	__u64	mcn[4];
+	__u64	reserved3[20];
+	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
+};
+
+/*
+ * This struct is used to store some machine check info from lowcore
+ * for machine checks that happen while the guest is running.
+ * This info in host's lowcore might be overwritten by a second machine
+ * check from host when host is in the machine check's high-level handling.
+ * The size is 24 bytes.
+ */
+struct mcck_volatile_info {
+	__u64 mcic;
+	__u64 failing_storage_address;
+	__u32 ext_damage_code;
+	__u32 reserved;
+};
+
+#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \
+			  CR0_MEASUREMENT_ALERT_SUBMASK)
+#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \
+			   CR14_EXTERNAL_DAMAGE_SUBMASK)
+
+#define SIDAD_SIZE_MASK		0xff
+#define sida_addr(sie_block) phys_to_virt((sie_block)->sidad & PAGE_MASK)
+#define sida_size(sie_block) \
+	((((sie_block)->sidad & SIDAD_SIZE_MASK) + 1) * PAGE_SIZE)
+
+#define CPUSTAT_STOPPED    0x80000000
+#define CPUSTAT_WAIT	   0x10000000
+#define CPUSTAT_ECALL_PEND 0x08000000
+#define CPUSTAT_STOP_INT   0x04000000
+#define CPUSTAT_IO_INT	   0x02000000
+#define CPUSTAT_EXT_INT    0x01000000
+#define CPUSTAT_RUNNING    0x00800000
+#define CPUSTAT_RETAINED   0x00400000
+#define CPUSTAT_TIMING_SUB 0x00020000
+#define CPUSTAT_SIE_SUB    0x00010000
+#define CPUSTAT_RRF	   0x00008000
+#define CPUSTAT_SLSV	   0x00004000
+#define CPUSTAT_SLSR	   0x00002000
+#define CPUSTAT_ZARCH	   0x00000800
+#define CPUSTAT_MCDS	   0x00000100
+#define CPUSTAT_KSS	   0x00000200
+#define CPUSTAT_SM	   0x00000080
+#define CPUSTAT_IBS	   0x00000040
+#define CPUSTAT_GED2	   0x00000010
+#define CPUSTAT_G	   0x00000008
+#define CPUSTAT_GED	   0x00000004
+#define CPUSTAT_J	   0x00000002
+#define CPUSTAT_P	   0x00000001
+
+struct kvm_s390_sie_block {
+	atomic_t cpuflags;		/* 0x0000 */
+	__u32 : 1;			/* 0x0004 */
+	__u32 prefix : 18;
+	__u32 : 1;
+	__u32 ibc : 12;
+	__u8	reserved08[4];		/* 0x0008 */
+#define PROG_IN_SIE (1<<0)
+	__u32	prog0c;			/* 0x000c */
+	union {
+		__u8	reserved10[16];		/* 0x0010 */
+		struct {
+			__u64	pv_handle_cpu;
+			__u64	pv_handle_config;
+		};
+	};
+#define PROG_BLOCK_SIE	(1<<0)
+#define PROG_REQUEST	(1<<1)
+	atomic_t prog20;		/* 0x0020 */
+	__u8	reserved24[4];		/* 0x0024 */
+	__u64	cputm;			/* 0x0028 */
+	__u64	ckc;			/* 0x0030 */
+	__u64	epoch;			/* 0x0038 */
+	__u32	svcc;			/* 0x0040 */
+#define LCTL_CR0	0x8000
+#define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
+#define LCTL_CR14	0x0002
+	__u16	lctl;			/* 0x0044 */
+	__s16	icpua;			/* 0x0046 */
+#define ICTL_OPEREXC	0x80000000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
+#define ICTL_TPROT	0x00000200
+	__u32	ictl;			/* 0x0048 */
+#define ECA_CEI		0x80000000
+#define ECA_IB		0x40000000
+#define ECA_SIGPI	0x10000000
+#define ECA_MVPGI	0x01000000
+#define ECA_AIV		0x00200000
+#define ECA_VX		0x00020000
+#define ECA_PROTEXCI	0x00002000
+#define ECA_APIE	0x00000008
+#define ECA_SII		0x00000001
+	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_EXTREQ	0x10
+#define ICPT_EXTINT	0x14
+#define ICPT_IOREQ	0x18
+#define ICPT_WAIT	0x1c
+#define ICPT_VALIDITY	0x20
+#define ICPT_STOP	0x28
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
+#define ICPT_KSS	0x5c
+#define ICPT_MCHKREQ	0x60
+#define ICPT_INT_ENABLE	0x64
+#define ICPT_PV_INSTR	0x68
+#define ICPT_PV_NOTIFY	0x6c
+#define ICPT_PV_PREF	0x70
+	__u8	icptcode;		/* 0x0050 */
+	__u8	icptstatus;		/* 0x0051 */
+	__u16	ihcpu;			/* 0x0052 */
+	__u8	reserved54;		/* 0x0054 */
+#define IICTL_CODE_NONE		 0x00
+#define IICTL_CODE_MCHK		 0x01
+#define IICTL_CODE_EXT		 0x02
+#define IICTL_CODE_IO		 0x03
+#define IICTL_CODE_RESTART	 0x04
+#define IICTL_CODE_SPECIFICATION 0x10
+#define IICTL_CODE_OPERAND	 0x11
+	__u8	iictl;			/* 0x0055 */
+	__u16	ipa;			/* 0x0056 */
+	__u32	ipb;			/* 0x0058 */
+	__u32	scaoh;			/* 0x005c */
+#define FPF_BPBC	0x20
+	__u8	fpf;			/* 0x0060 */
+#define ECB_GS		0x40
+#define ECB_TE		0x10
+#define ECB_SPECI	0x08
+#define ECB_SRSI	0x04
+#define ECB_HOSTPROTINT	0x02
+#define ECB_PTF		0x01
+	__u8	ecb;			/* 0x0061 */
+#define ECB2_CMMA	0x80
+#define ECB2_IEP	0x20
+#define ECB2_PFMFI	0x08
+#define ECB2_ESCA	0x04
+#define ECB2_ZPCI_LSI	0x02
+	__u8	ecb2;			/* 0x0062 */
+#define ECB3_AISI	0x20
+#define ECB3_AISII	0x10
+#define ECB3_DEA 0x08
+#define ECB3_AES 0x04
+#define ECB3_RI  0x01
+	__u8	ecb3;			/* 0x0063 */
+#define ESCA_SCAOL_MASK ~0x3fU
+	__u32	scaol;			/* 0x0064 */
+	__u8	sdf;			/* 0x0068 */
+	__u8	epdx;			/* 0x0069 */
+	__u8	cpnc;			/* 0x006a */
+	__u8	reserved6b;		/* 0x006b */
+	__u32	todpr;			/* 0x006c */
+#define GISA_FORMAT1 0x00000001
+	__u32	gd;			/* 0x0070 */
+	__u8	reserved74[12];		/* 0x0074 */
+	__u64	mso;			/* 0x0080 */
+	__u64	msl;			/* 0x0088 */
+	psw_t	gpsw;			/* 0x0090 */
+	__u64	gg14;			/* 0x00a0 */
+	__u64	gg15;			/* 0x00a8 */
+	__u8	reservedb0[8];		/* 0x00b0 */
+#define HPID_KVM	0x4
+#define HPID_VSIE	0x5
+	__u8	hpid;			/* 0x00b8 */
+	__u8	reservedb9[7];		/* 0x00b9 */
+	union {
+		struct {
+			__u32	eiparams;	/* 0x00c0 */
+			__u16	extcpuaddr;	/* 0x00c4 */
+			__u16	eic;		/* 0x00c6 */
+		};
+		__u64	mcic;			/* 0x00c0 */
+	} __packed;
+	__u32	reservedc8;		/* 0x00c8 */
+	union {
+		struct {
+			__u16	pgmilc;		/* 0x00cc */
+			__u16	iprcc;		/* 0x00ce */
+		};
+		__u32	edc;			/* 0x00cc */
+	} __packed;
+	union {
+		struct {
+			__u32	dxc;		/* 0x00d0 */
+			__u16	mcn;		/* 0x00d4 */
+			__u8	perc;		/* 0x00d6 */
+			__u8	peratmid;	/* 0x00d7 */
+		};
+		__u64	faddr;			/* 0x00d0 */
+	} __packed;
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	union {
+		__u64	tecmc;		/* 0x00e8 */
+		struct {
+			__u16	subchannel_id;	/* 0x00e8 */
+			__u16	subchannel_nr;	/* 0x00ea */
+			__u32	io_int_parm;	/* 0x00ec */
+			__u32	io_int_word;	/* 0x00f0 */
+		};
+	} __packed;
+	__u8	reservedf4[8];		/* 0x00f4 */
+#define CRYCB_FORMAT_MASK 0x00000003
+#define CRYCB_FORMAT0 0x00000000
+#define CRYCB_FORMAT1 0x00000001
+#define CRYCB_FORMAT2 0x00000003
+	__u32	crycbd;			/* 0x00fc */
+	__u64	gcr[16];		/* 0x0100 */
+	union {
+		__u64	gbea;		/* 0x0180 */
+		__u64	sidad;
+	};
+	__u8	reserved188[8];		/* 0x0188 */
+	__u64	sdnxo;			/* 0x0190 */
+	__u8	reserved198[8];		/* 0x0198 */
+	__u32	fac;			/* 0x01a0 */
+	__u8	reserved1a4[20];	/* 0x01a4 */
+	__u64	cbrlo;			/* 0x01b8 */
+	__u8	reserved1c0[8];		/* 0x01c0 */
+#define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
+#define ECD_ETOKENF	0x02000000
+#define ECD_ECC		0x00200000
+#define ECD_HMAC	0x00004000
+	__u32	ecd;			/* 0x01c8 */
+	__u8	reserved1cc[18];	/* 0x01cc */
+	__u64	pp;			/* 0x01de */
+	__u8	reserved1e6[2];		/* 0x01e6 */
+	__u64	itdba;			/* 0x01e8 */
+	__u64	riccbd;			/* 0x01f0 */
+	__u64	gvrd;			/* 0x01f8 */
+} __packed __aligned(512);
+
+struct kvm_s390_itdb {
+	__u8	data[256];
+};
+
+struct sie_page {
+	struct kvm_s390_sie_block sie_block;
+	struct mcck_volatile_info mcck_info;	/* 0x0200 */
+	__u8 reserved218[360];		/* 0x0218 */
+	__u64 pv_grregs[16];		/* 0x0380 */
+	__u8 reserved400[512];		/* 0x0400 */
+	struct kvm_s390_itdb itdb;	/* 0x0600 */
+	__u8 reserved700[2304];		/* 0x0700 */
+};
+
+#endif /* _ASM_KVM_HOST_TYPES_H */
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 42a092fa1029..e99e9c87b1ce 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -10,6 +10,7 @@
 #define _ASM_S390_LOWCORE_H
 
 #include <linux/types.h>
+#include <asm/machine.h>
 #include <asm/ptrace.h>
 #include <asm/ctlreg.h>
 #include <asm/cpu.h>
@@ -126,7 +127,7 @@ struct lowcore {
 	__u64	int_clock;			/* 0x0318 */
 	__u8	pad_0x0320[0x0328-0x0320];	/* 0x0320 */
 	__u64	clock_comparator;		/* 0x0328 */
-	__u64	boot_clock[2];			/* 0x0330 */
+	__u8	pad_0x0330[0x0340-0x0330];	/* 0x0330 */
 
 	/* Current process. */
 	__u64	current_task;			/* 0x0340 */
@@ -163,9 +164,7 @@ struct lowcore {
 	__u32	spinlock_index;			/* 0x03b0 */
 	__u8	pad_0x03b4[0x03b8-0x03b4];	/* 0x03b4 */
 	__u64	percpu_offset;			/* 0x03b8 */
-	__u8	pad_0x03c0[0x03c8-0x03c0];	/* 0x03c0 */
-	__u64	machine_flags;			/* 0x03c8 */
-	__u8	pad_0x03d0[0x0400-0x03d0];	/* 0x03d0 */
+	__u8	pad_0x03c0[0x0400-0x03c0];	/* 0x03c0 */
 
 	__u32	return_lpswe;			/* 0x0400 */
 	__u32	return_mcck_lpswe;		/* 0x0404 */
@@ -222,9 +221,12 @@ static __always_inline struct lowcore *get_lowcore(void)
 
 	if (__is_defined(__DECOMPRESSOR))
 		return NULL;
-	asm(ALTERNATIVE("llilh %[lc],0", "llilh %[lc],%[alt]", ALT_LOWCORE)
-	    : [lc] "=d" (lc)
-	    : [alt] "i" (LOWCORE_ALT_ADDRESS >> 16));
+	asm_inline(
+		ALTERNATIVE("	lghi	%[lc],0",
+			    "	llilh	%[lc],%[alt]",
+			    ALT_FEATURE(MFEATURE_LOWCORE))
+		: [lc] "=d" (lc)
+		: [alt] "i" (LOWCORE_ALT_ADDRESS >> 16));
 	return lc;
 }
 
@@ -238,15 +240,15 @@ static inline void set_prefix(__u32 address)
 #else /* __ASSEMBLY__ */
 
 .macro GET_LC reg
-	ALTERNATIVE "llilh	\reg,0",					\
+	ALTERNATIVE "lghi	\reg,0",					\
 		__stringify(llilh	\reg, LOWCORE_ALT_ADDRESS >> 16),	\
-		ALT_LOWCORE
+		ALT_FEATURE(MFEATURE_LOWCORE)
 .endm
 
 .macro STMG_LC start, end, savearea
 	ALTERNATIVE "stmg	\start, \end, \savearea",				\
 		__stringify(stmg	\start, \end, LOWCORE_ALT_ADDRESS + \savearea),	\
-		ALT_LOWCORE
+		ALT_FEATURE(MFEATURE_LOWCORE)
 .endm
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/machine.h b/arch/s390/include/asm/machine.h
new file mode 100644
index 000000000000..8abe5afdbfc4
--- /dev/null
+++ b/arch/s390/include/asm/machine.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 2024
+ */
+
+#ifndef __ASM_S390_MACHINE_H
+#define __ASM_S390_MACHINE_H
+
+#include <linux/const.h>
+
+#define MFEATURE_LOWCORE	0
+#define MFEATURE_PCI_MIO	1
+#define MFEATURE_SCC		2
+#define MFEATURE_TLB_GUEST	3
+#define MFEATURE_TX		4
+#define MFEATURE_ESOP		5
+#define MFEATURE_DIAG9C		6
+#define MFEATURE_VM		7
+#define MFEATURE_KVM		8
+#define MFEATURE_LPAR		9
+#define MFEATURE_DIAG288	10
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitops.h>
+#include <asm/alternative.h>
+
+extern unsigned long machine_features[1];
+
+#define MAX_MFEATURE_BIT (sizeof(machine_features) * BITS_PER_BYTE)
+
+static inline void __set_machine_feature(unsigned int nr, unsigned long *mfeatures)
+{
+	if (nr >= MAX_MFEATURE_BIT)
+		return;
+	__set_bit(nr, mfeatures);
+}
+
+static inline void set_machine_feature(unsigned int nr)
+{
+	__set_machine_feature(nr, machine_features);
+}
+
+static inline void __clear_machine_feature(unsigned int nr, unsigned long *mfeatures)
+{
+	if (nr >= MAX_MFEATURE_BIT)
+		return;
+	__clear_bit(nr, mfeatures);
+}
+
+static inline void clear_machine_feature(unsigned int nr)
+{
+	__clear_machine_feature(nr, machine_features);
+}
+
+static bool __test_machine_feature(unsigned int nr, unsigned long *mfeatures)
+{
+	if (nr >= MAX_MFEATURE_BIT)
+		return false;
+	return test_bit(nr, mfeatures);
+}
+
+static bool test_machine_feature(unsigned int nr)
+{
+	return __test_machine_feature(nr, machine_features);
+}
+
+static __always_inline bool __test_machine_feature_constant(unsigned int nr)
+{
+	asm goto(
+		ALTERNATIVE("brcl 15,%l[l_no]", "brcl 0,0", ALT_FEATURE(%[nr]))
+		:
+		: [nr] "i" (nr)
+		:
+		: l_no);
+	return true;
+l_no:
+	return false;
+}
+
+#define DEFINE_MACHINE_HAS_FEATURE(name, feature)				\
+static __always_inline bool machine_has_##name(void)				\
+{										\
+	if (!__is_defined(__DECOMPRESSOR) && __builtin_constant_p(feature))	\
+		return __test_machine_feature_constant(feature);		\
+	return test_machine_feature(feature);					\
+}
+
+DEFINE_MACHINE_HAS_FEATURE(relocated_lowcore, MFEATURE_LOWCORE)
+DEFINE_MACHINE_HAS_FEATURE(scc, MFEATURE_SCC)
+DEFINE_MACHINE_HAS_FEATURE(tlb_guest, MFEATURE_TLB_GUEST)
+DEFINE_MACHINE_HAS_FEATURE(tx, MFEATURE_TX)
+DEFINE_MACHINE_HAS_FEATURE(esop, MFEATURE_ESOP)
+DEFINE_MACHINE_HAS_FEATURE(diag9c, MFEATURE_DIAG9C)
+DEFINE_MACHINE_HAS_FEATURE(vm, MFEATURE_VM)
+DEFINE_MACHINE_HAS_FEATURE(kvm, MFEATURE_KVM)
+DEFINE_MACHINE_HAS_FEATURE(lpar, MFEATURE_LPAR)
+
+#define machine_is_vm	machine_has_vm
+#define machine_is_kvm	machine_has_kvm
+#define machine_is_lpar	machine_has_lpar
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_S390_MACHINE_H */
diff --git a/arch/s390/include/asm/march.h b/arch/s390/include/asm/march.h
index fd9eef3be44c..11a71bd14954 100644
--- a/arch/s390/include/asm/march.h
+++ b/arch/s390/include/asm/march.h
@@ -33,6 +33,10 @@
 #define MARCH_HAS_Z16_FEATURES 1
 #endif
 
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+#define MARCH_HAS_Z17_FEATURES 1
+#endif
+
 #endif /* __DECOMPRESSOR */
 
 #endif /* __ASM_S390_MARCH_H */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 4c2dc7abc285..f07e49b419ab 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -22,10 +22,7 @@ typedef struct {
 	 * The following bitfields need a down_write on the mm
 	 * semaphore when they are written to. As they are only
 	 * written once, they can be read without a lock.
-	 *
-	 * The mmu context allocates 4K page tables.
 	 */
-	unsigned int alloc_pgste:1;
 	/* The mmu context uses extended page tables. */
 	unsigned int has_pgste:1;
 	/* The mmu context uses storage keys. */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d56eb0a1f37b..d9b8501bc93d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -13,6 +13,7 @@
 #include <linux/mm_types.h>
 #include <asm/tlbflush.h>
 #include <asm/ctlreg.h>
+#include <asm/asce.h>
 #include <asm-generic/mm_hooks.h>
 
 #define init_new_context init_new_context
@@ -29,9 +30,6 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.gmap_asce = 0;
 	mm->context.flush_mm = 0;
 #ifdef CONFIG_PGSTE
-	mm->context.alloc_pgste = page_table_allocate_pgste ||
-		test_thread_flag(TIF_PGSTE) ||
-		(current->mm && current->mm->context.alloc_pgste);
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
@@ -80,7 +78,8 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *
 	else
 		get_lowcore()->user_asce.val = next->context.asce;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	/* Clear previous user-ASCE from CR7 */
+	/* Clear previous user-ASCE from CR1 and CR7 */
+	local_ctl_load(1, &s390_invalid_asce);
 	local_ctl_load(7, &s390_invalid_asce);
 	if (prev != next)
 		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
@@ -102,6 +101,7 @@ static inline void finish_arch_post_lock_switch(void)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
+	unsigned long flags;
 
 	if (mm) {
 		preempt_disable();
@@ -111,15 +111,25 @@ static inline void finish_arch_post_lock_switch(void)
 		__tlb_flush_mm_lazy(mm);
 		preempt_enable();
 	}
+	local_irq_save(flags);
+	if (test_thread_flag(TIF_ASCE_PRIMARY))
+		local_ctl_load(1, &get_lowcore()->kernel_asce);
+	else
+		local_ctl_load(1, &get_lowcore()->user_asce);
 	local_ctl_load(7, &get_lowcore()->user_asce);
+	local_irq_restore(flags);
 }
 
 #define activate_mm activate_mm
 static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
-	switch_mm(prev, next, current);
+	switch_mm_irqs_off(prev, next, current);
 	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+	if (test_thread_flag(TIF_ASCE_PRIMARY))
+		local_ctl_load(1, &get_lowcore()->kernel_asce);
+	else
+		local_ctl_load(1, &get_lowcore()->user_asce);
 	local_ctl_load(7, &get_lowcore()->user_asce);
 }
 
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 1ff145f7b52b..4e5dbabdf202 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -71,9 +71,11 @@ static inline void copy_page(void *to, void *from)
 #define vma_alloc_zeroed_movable_folio(vma, vaddr) \
 	vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr)
 
-/*
- * These are used to make use of C type-checking..
- */
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
+#define STRICT_MM_TYPECHECKS
+#endif
+
+#ifdef STRICT_MM_TYPECHECKS
 
 typedef struct { unsigned long pgprot; } pgprot_t;
 typedef struct { unsigned long pgste; } pgste_t;
@@ -82,43 +84,48 @@ typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pud; } pud_t;
 typedef struct { unsigned long p4d; } p4d_t;
 typedef struct { unsigned long pgd; } pgd_t;
-typedef pte_t *pgtable_t;
 
-#define pgprot_val(x)	((x).pgprot)
-#define pgste_val(x)	((x).pgste)
-
-static inline unsigned long pte_val(pte_t pte)
-{
-	return pte.pte;
+#define DEFINE_PGVAL_FUNC(name)						\
+static __always_inline unsigned long name ## _val(name ## _t name)	\
+{									\
+	return name.name;						\
 }
 
-static inline unsigned long pmd_val(pmd_t pmd)
-{
-	return pmd.pmd;
-}
+#else /* STRICT_MM_TYPECHECKS */
 
-static inline unsigned long pud_val(pud_t pud)
-{
-	return pud.pud;
-}
+typedef unsigned long pgprot_t;
+typedef unsigned long pgste_t;
+typedef unsigned long pte_t;
+typedef unsigned long pmd_t;
+typedef unsigned long pud_t;
+typedef unsigned long p4d_t;
+typedef unsigned long pgd_t;
 
-static inline unsigned long p4d_val(p4d_t p4d)
-{
-	return p4d.p4d;
+#define DEFINE_PGVAL_FUNC(name)						\
+static __always_inline unsigned long name ## _val(name ## _t name)	\
+{									\
+	return name;							\
 }
 
-static inline unsigned long pgd_val(pgd_t pgd)
-{
-	return pgd.pgd;
-}
+#endif /* STRICT_MM_TYPECHECKS */
+
+DEFINE_PGVAL_FUNC(pgprot)
+DEFINE_PGVAL_FUNC(pgste)
+DEFINE_PGVAL_FUNC(pte)
+DEFINE_PGVAL_FUNC(pmd)
+DEFINE_PGVAL_FUNC(pud)
+DEFINE_PGVAL_FUNC(p4d)
+DEFINE_PGVAL_FUNC(pgd)
+
+typedef pte_t *pgtable_t;
 
+#define __pgprot(x)	((pgprot_t) { (x) } )
 #define __pgste(x)	((pgste_t) { (x) } )
 #define __pte(x)        ((pte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
 #define __pud(x)	((pud_t) { (x) } )
 #define __p4d(x)	((p4d_t) { (x) } )
 #define __pgd(x)        ((pgd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
 
 static inline void page_set_storage_key(unsigned long addr,
 					unsigned char skey, int mapped)
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 474e1f8d1d3c..41f900f693d9 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -11,6 +11,9 @@
 #include <asm/pci_insn.h>
 #include <asm/sclp.h>
 
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE	1
+#define arch_can_pci_mmap_wc()		1
+
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 
@@ -144,7 +147,7 @@ struct zpci_dev {
 	u8		util_str_avail	: 1;
 	u8		irqs_registered	: 1;
 	u8		tid_avail	: 1;
-	u8		reserved	: 1;
+	u8		rtr_avail	: 1; /* Relaxed translation allowed */
 	unsigned int	devfn;		/* DEVFN part of the RID*/
 
 	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
@@ -217,6 +220,7 @@ extern struct airq_iv *zpci_aif_sbv;
 struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
 int zpci_add_device(struct zpci_dev *zdev);
 int zpci_enable_device(struct zpci_dev *);
+int zpci_reenable_device(struct zpci_dev *zdev);
 int zpci_disable_device(struct zpci_dev *);
 int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh);
 int zpci_deconfigure_device(struct zpci_dev *zdev);
@@ -245,6 +249,7 @@ void update_uid_checking(bool new);
 /* IOMMU Interface */
 int zpci_init_iommu(struct zpci_dev *zdev);
 void zpci_destroy_iommu(struct zpci_dev *zdev);
+int zpci_iommu_register_ioat(struct zpci_dev *zdev, u8 *status);
 
 #ifdef CONFIG_PCI
 static inline bool zpci_use_mio(struct zpci_dev *zdev)
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index 3fff2f7095c8..7ebff39c84b3 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -156,7 +156,9 @@ struct clp_rsp_query_pci_grp {
 	u16			:  4;
 	u16 noi			: 12;	/* number of interrupts */
 	u8 version;
-	u8			:  6;
+	u8			:  2;
+	u8 rtr			:  1;	/* Relaxed translation requirement */
+	u8			:  3;
 	u8 frame		:  1;
 	u8 refresh		:  1;	/* TLB refresh mode */
 	u16			:  3;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index b19b6ed2ab53..005497ffebda 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -26,7 +26,6 @@ unsigned long *page_table_alloc(struct mm_struct *);
 struct ptdesc *page_table_alloc_pgste(struct mm_struct *mm);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_pgste(struct ptdesc *ptdesc);
-extern int page_table_allocate_pgste;
 
 static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 3ca5af4cfe43..f8a6b54986ec 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -14,6 +14,7 @@
 
 #include <linux/sched.h>
 #include <linux/mm_types.h>
+#include <linux/cpufeature.h>
 #include <linux/page-flags.h>
 #include <linux/radix-tree.h>
 #include <linux/atomic.h>
@@ -583,13 +584,14 @@ static inline int mm_is_protected(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int mm_alloc_pgste(struct mm_struct *mm)
+static inline pgste_t clear_pgste_bit(pgste_t pgste, unsigned long mask)
 {
-#ifdef CONFIG_PGSTE
-	if (unlikely(mm->context.alloc_pgste))
-		return 1;
-#endif
-	return 0;
+	return __pgste(pgste_val(pgste) & ~mask);
+}
+
+static inline pgste_t set_pgste_bit(pgste_t pgste, unsigned long mask)
+{
+	return __pgste(pgste_val(pgste) | mask);
 }
 
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
@@ -1339,7 +1341,7 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
 	 * PTE does not have _PAGE_PROTECT set, to avoid unnecessary overhead.
 	 * A local RDP can be used to do the flush.
 	 */
-	if (MACHINE_HAS_RDP && !(pte_val(*ptep) & _PAGE_PROTECT))
+	if (cpu_has_rdp() && !(pte_val(*ptep) & _PAGE_PROTECT))
 		__ptep_rdp(address, ptep, 0, 0, 1);
 }
 #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault
@@ -1354,7 +1356,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 {
 	if (pte_same(*ptep, entry))
 		return 0;
-	if (MACHINE_HAS_RDP && !mm_has_pgste(vma->vm_mm) && pte_allow_rdp(*ptep, entry))
+	if (cpu_has_rdp() && !mm_has_pgste(vma->vm_mm) && pte_allow_rdp(*ptep, entry))
 		ptep_reset_dat_prot(vma->vm_mm, addr, ptep, entry);
 	else
 		ptep_xchg_direct(vma->vm_mm, addr, ptep, entry);
@@ -1402,9 +1404,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 #define pgprot_writecombine	pgprot_writecombine
 pgprot_t pgprot_writecombine(pgprot_t prot);
 
-#define pgprot_writethrough	pgprot_writethrough
-pgprot_t pgprot_writethrough(pgprot_t prot);
-
 #define PFN_PTE_SHIFT		PAGE_SHIFT
 
 /*
@@ -1890,7 +1889,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 #define has_transparent_hugepage has_transparent_hugepage
 static inline int has_transparent_hugepage(void)
 {
-	return MACHINE_HAS_EDAT1 ? 1 : 0;
+	return cpu_has_edat1() ? 1 : 0;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
diff --git a/arch/s390/include/asm/pkey.h b/arch/s390/include/asm/pkey.h
index 5dca1a46a9f6..b7b59faf16f4 100644
--- a/arch/s390/include/asm/pkey.h
+++ b/arch/s390/include/asm/pkey.h
@@ -20,9 +20,22 @@
  * @param key pointer to a buffer containing the key blob
  * @param keylen size of the key blob in bytes
  * @param protkey pointer to buffer receiving the protected key
+ * @param xflags additional execution flags (see PKEY_XFLAG_* definitions below)
+ *	  As of now the only supported flag is PKEY_XFLAG_NOMEMALLOC.
  * @return 0 on success, negative errno value on failure
  */
 int pkey_key2protkey(const u8 *key, u32 keylen,
-		     u8 *protkey, u32 *protkeylen, u32 *protkeytype);
+		     u8 *protkey, u32 *protkeylen, u32 *protkeytype,
+		     u32 xflags);
+
+/*
+ * If this flag is given in the xflags parameter, the pkey implementation
+ * is not allowed to allocate memory but instead should fall back to use
+ * preallocated memory or simple fail with -ENOMEM.
+ * This flag is for protected key derive within a cipher or similar
+ * which must not allocate memory which would cause io operations - see
+ * also the CRYPTO_ALG_ALLOCATES_MEMORY flag in crypto.h.
+ */
+#define PKEY_XFLAG_NOMEMALLOC 0x0001
 
 #endif /* _KAPI_PKEY_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 4f8d5592c298..6c8063cb8fe7 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -31,6 +31,7 @@
 #include <linux/cpumask.h>
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
+#include <linux/bitops.h>
 #include <asm/fpu-types.h>
 #include <asm/cpu.h>
 #include <asm/page.h>
@@ -62,33 +63,27 @@ static __always_inline struct pcpu *this_pcpu(void)
 
 static __always_inline void set_cpu_flag(int flag)
 {
-	this_pcpu()->flags |= (1UL << flag);
+	set_bit(flag, &this_pcpu()->flags);
 }
 
 static __always_inline void clear_cpu_flag(int flag)
 {
-	this_pcpu()->flags &= ~(1UL << flag);
+	clear_bit(flag, &this_pcpu()->flags);
 }
 
 static __always_inline bool test_cpu_flag(int flag)
 {
-	return this_pcpu()->flags & (1UL << flag);
+	return test_bit(flag, &this_pcpu()->flags);
 }
 
 static __always_inline bool test_and_set_cpu_flag(int flag)
 {
-	if (test_cpu_flag(flag))
-		return true;
-	set_cpu_flag(flag);
-	return false;
+	return test_and_set_bit(flag, &this_pcpu()->flags);
 }
 
 static __always_inline bool test_and_clear_cpu_flag(int flag)
 {
-	if (!test_cpu_flag(flag))
-		return false;
-	clear_cpu_flag(flag);
-	return true;
+	return test_and_clear_bit(flag, &this_pcpu()->flags);
 }
 
 /*
@@ -97,7 +92,7 @@ static __always_inline bool test_and_clear_cpu_flag(int flag)
  */
 static __always_inline bool test_cpu_flag_of(int flag, int cpu)
 {
-	return per_cpu(pcpu_devices, cpu).flags & (1UL << flag);
+	return test_bit(flag, &per_cpu(pcpu_devices, cpu).flags);
 }
 
 #define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
@@ -416,7 +411,11 @@ static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 
 static __always_inline void bpon(void)
 {
-	asm volatile(ALTERNATIVE("nop", ".insn	rrf,0xb2e80000,0,0,13,0", ALT_SPEC(82)));
+	asm_inline volatile(
+		ALTERNATIVE("	nop\n",
+			    "	.insn	rrf,0xb2e80000,0,0,13,0\n",
+			    ALT_SPEC(82))
+		);
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 788bc4467445..62c0ab4a4b9d 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -9,16 +9,15 @@
 
 #include <linux/bits.h>
 #include <uapi/asm/ptrace.h>
+#include <asm/thread_info.h>
 #include <asm/tpi.h>
 
 #define PIF_SYSCALL			0	/* inside a system call */
-#define PIF_EXECVE_PGSTE_RESTART	1	/* restart execve for PGSTE binaries */
 #define PIF_SYSCALL_RET_SET		2	/* return value was set via ptrace */
 #define PIF_GUEST_FAULT			3	/* indicates program check in sie64a */
 #define PIF_FTRACE_FULL_REGS		4	/* all register contents valid (ftrace) */
 
 #define _PIF_SYSCALL			BIT(PIF_SYSCALL)
-#define _PIF_EXECVE_PGSTE_RESTART	BIT(PIF_EXECVE_PGSTE_RESTART)
 #define _PIF_SYSCALL_RET_SET		BIT(PIF_SYSCALL_RET_SET)
 #define _PIF_GUEST_FAULT		BIT(PIF_GUEST_FAULT)
 #define _PIF_FTRACE_FULL_REGS		BIT(PIF_FTRACE_FULL_REGS)
@@ -128,7 +127,6 @@ struct pt_regs {
 		struct tpi_info tpi_info;
 	};
 	unsigned long flags;
-	unsigned long cr1;
 	unsigned long last_break;
 };
 
@@ -231,8 +229,44 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
 
 int regs_query_register_offset(const char *name);
 const char *regs_query_register_name(unsigned int offset);
-unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset);
-unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
+
+static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->gprs[15];
+}
+
+static __always_inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return 0;
+	return regs->gprs[offset];
+}
+
+static __always_inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	unsigned long ksp = kernel_stack_pointer(regs);
+
+	return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:pt_regs which contains kernel stack pointer.
+ * @n:stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long addr;
+
+	addr = kernel_stack_pointer(regs) + n * sizeof(long);
+	if (!regs_within_kernel_stack(regs, addr))
+		return 0;
+	return READ_ONCE_NOCHECK(addr);
+}
 
 /**
  * regs_get_kernel_argument() - get Nth function argument in kernel
@@ -253,11 +287,6 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
 	return regs_get_kernel_stack_nth(regs, argoffset + n);
 }
 
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
-{
-	return regs->gprs[15];
-}
-
 static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 {
 	regs->gprs[2] = rc;
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 18f37dff03c9..1e62919bacf4 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -168,6 +168,7 @@ int sclp_early_read_storage_info(void);
 int sclp_early_get_core_info(struct sclp_core_info *info);
 void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
 void sclp_early_detect(void);
+void sclp_early_detect_machine_features(void);
 void sclp_early_printk(const char *s);
 void __sclp_early_printk(const char *s, unsigned int len);
 void sclp_emergency_printk(const char *s);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 70b920b32827..031e881b4d88 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -13,28 +13,6 @@
 #define PARMAREA		0x10400
 
 #define COMMAND_LINE_SIZE CONFIG_COMMAND_LINE_SIZE
-/*
- * Machine features detected in early.c
- */
-
-#define MACHINE_FLAG_VM		BIT(0)
-#define MACHINE_FLAG_KVM	BIT(1)
-#define MACHINE_FLAG_LPAR	BIT(2)
-#define MACHINE_FLAG_DIAG9C	BIT(3)
-#define MACHINE_FLAG_ESOP	BIT(4)
-#define MACHINE_FLAG_IDTE	BIT(5)
-#define MACHINE_FLAG_EDAT1	BIT(7)
-#define MACHINE_FLAG_EDAT2	BIT(8)
-#define MACHINE_FLAG_TOPOLOGY	BIT(10)
-#define MACHINE_FLAG_TE		BIT(11)
-#define MACHINE_FLAG_TLB_LC	BIT(12)
-#define MACHINE_FLAG_TLB_GUEST	BIT(14)
-#define MACHINE_FLAG_NX		BIT(15)
-#define MACHINE_FLAG_GS		BIT(16)
-#define MACHINE_FLAG_SCC	BIT(17)
-#define MACHINE_FLAG_PCI_MIO	BIT(18)
-#define MACHINE_FLAG_RDP	BIT(19)
-#define MACHINE_FLAG_SEQ_INSN	BIT(20)
 
 #define LPP_MAGIC		BIT(31)
 #define LPP_PID_MASK		_AC(0xffffffff, UL)
@@ -78,26 +56,6 @@ extern unsigned long max_mappable;
 /* The Write Back bit position in the physaddr is given by the SLPC PCI */
 extern unsigned long mio_wb_bit_mask;
 
-#define MACHINE_IS_VM		(get_lowcore()->machine_flags & MACHINE_FLAG_VM)
-#define MACHINE_IS_KVM		(get_lowcore()->machine_flags & MACHINE_FLAG_KVM)
-#define MACHINE_IS_LPAR		(get_lowcore()->machine_flags & MACHINE_FLAG_LPAR)
-
-#define MACHINE_HAS_DIAG9C	(get_lowcore()->machine_flags & MACHINE_FLAG_DIAG9C)
-#define MACHINE_HAS_ESOP	(get_lowcore()->machine_flags & MACHINE_FLAG_ESOP)
-#define MACHINE_HAS_IDTE	(get_lowcore()->machine_flags & MACHINE_FLAG_IDTE)
-#define MACHINE_HAS_EDAT1	(get_lowcore()->machine_flags & MACHINE_FLAG_EDAT1)
-#define MACHINE_HAS_EDAT2	(get_lowcore()->machine_flags & MACHINE_FLAG_EDAT2)
-#define MACHINE_HAS_TOPOLOGY	(get_lowcore()->machine_flags & MACHINE_FLAG_TOPOLOGY)
-#define MACHINE_HAS_TE		(get_lowcore()->machine_flags & MACHINE_FLAG_TE)
-#define MACHINE_HAS_TLB_LC	(get_lowcore()->machine_flags & MACHINE_FLAG_TLB_LC)
-#define MACHINE_HAS_TLB_GUEST	(get_lowcore()->machine_flags & MACHINE_FLAG_TLB_GUEST)
-#define MACHINE_HAS_NX		(get_lowcore()->machine_flags & MACHINE_FLAG_NX)
-#define MACHINE_HAS_GS		(get_lowcore()->machine_flags & MACHINE_FLAG_GS)
-#define MACHINE_HAS_SCC		(get_lowcore()->machine_flags & MACHINE_FLAG_SCC)
-#define MACHINE_HAS_PCI_MIO	(get_lowcore()->machine_flags & MACHINE_FLAG_PCI_MIO)
-#define MACHINE_HAS_RDP		(get_lowcore()->machine_flags & MACHINE_FLAG_RDP)
-#define MACHINE_HAS_SEQ_INSN	(get_lowcore()->machine_flags & MACHINE_FLAG_SEQ_INSN)
-
 /*
  * Console mode. Override with conmode=
  */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 7feca96c48c6..03f4d01664f8 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -7,11 +7,29 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
-#include <asm/sigp.h>
-#include <asm/lowcore.h>
 #include <asm/processor.h>
+#include <asm/lowcore.h>
+#include <asm/machine.h>
+#include <asm/sigp.h>
+
+static __always_inline unsigned int raw_smp_processor_id(void)
+{
+	unsigned long lc_cpu_nr;
+	unsigned int cpu;
+
+	BUILD_BUG_ON(sizeof_field(struct lowcore, cpu_nr) != sizeof(cpu));
+	lc_cpu_nr = offsetof(struct lowcore, cpu_nr);
+	asm_inline(
+		ALTERNATIVE("   ly      %[cpu],%[offzero](%%r0)\n",
+			    "   ly      %[cpu],%[offalt](%%r0)\n",
+			    ALT_FEATURE(MFEATURE_LOWCORE))
+		: [cpu] "=d" (cpu)
+		: [offzero] "i" (lc_cpu_nr),
+		  [offalt] "i" (lc_cpu_nr + LOWCORE_ALT_ADDRESS),
+		  "m" (((struct lowcore *)0)->cpu_nr));
+	return cpu;
+}
 
-#define raw_smp_processor_id()	(get_lowcore()->cpu_nr)
 #define arch_scale_cpu_capacity smp_cpu_get_capacity
 
 extern struct mutex smp_cpu_state_mutex;
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index f87dd0a84855..f9935db9fd76 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -16,7 +16,23 @@
 #include <asm/processor.h>
 #include <asm/alternative.h>
 
-#define SPINLOCK_LOCKVAL (get_lowcore()->spinlock_lockval)
+static __always_inline unsigned int spinlock_lockval(void)
+{
+	unsigned long lc_lockval;
+	unsigned int lockval;
+
+	BUILD_BUG_ON(sizeof_field(struct lowcore, spinlock_lockval) != sizeof(lockval));
+	lc_lockval = offsetof(struct lowcore, spinlock_lockval);
+	asm_inline(
+		ALTERNATIVE("   ly      %[lockval],%[offzero](%%r0)\n",
+			    "   ly      %[lockval],%[offalt](%%r0)\n",
+			    ALT_FEATURE(MFEATURE_LOWCORE))
+		: [lockval] "=d" (lockval)
+		: [offzero] "i" (lc_lockval),
+		  [offalt] "i" (lc_lockval + LOWCORE_ALT_ADDRESS),
+		  "m" (((struct lowcore *)0)->spinlock_lockval));
+	return lockval;
+}
 
 extern int spin_retry;
 
@@ -60,7 +76,7 @@ static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 	int old = 0;
 
 	barrier();
-	return likely(arch_try_cmpxchg(&lp->lock, &old, SPINLOCK_LOCKVAL));
+	return likely(arch_try_cmpxchg(&lp->lock, &old, spinlock_lockval()));
 }
 
 static inline void arch_spin_lock(arch_spinlock_t *lp)
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index 2ab868cbae6c..f8f68f4ef255 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -26,11 +26,9 @@ void *memmove(void *dest, const void *src, size_t n);
 #define __HAVE_ARCH_MEMSCAN	/* inline & arch function */
 #define __HAVE_ARCH_STRCAT	/* inline & arch function */
 #define __HAVE_ARCH_STRCMP	/* arch function */
-#define __HAVE_ARCH_STRCPY	/* inline & arch function */
 #define __HAVE_ARCH_STRLCAT	/* arch function */
 #define __HAVE_ARCH_STRLEN	/* inline & arch function */
 #define __HAVE_ARCH_STRNCAT	/* arch function */
-#define __HAVE_ARCH_STRNCPY	/* arch function */
 #define __HAVE_ARCH_STRNLEN	/* inline & arch function */
 #define __HAVE_ARCH_STRSTR	/* arch function */
 #define __HAVE_ARCH_MEMSET16	/* arch function */
@@ -42,7 +40,6 @@ int memcmp(const void *s1, const void *s2, size_t n);
 int strcmp(const char *s1, const char *s2);
 size_t strlcat(char *dest, const char *src, size_t n);
 char *strncat(char *dest, const char *src, size_t n);
-char *strncpy(char *dest, const char *src, size_t n);
 char *strstr(const char *s1, const char *s2);
 #endif /* !defined(CONFIG_KASAN) && !defined(CONFIG_KMSAN) */
 
@@ -155,22 +152,6 @@ static inline char *strcat(char *dst, const char *src)
 }
 #endif
 
-#ifdef __HAVE_ARCH_STRCPY
-static inline char *strcpy(char *dst, const char *src)
-{
-	char *ret = dst;
-
-	asm volatile(
-		"	lghi	0,0\n"
-		"0:	mvst	%[dst],%[src]\n"
-		"	jo	0b"
-		: [dst] "+&a" (dst), [src] "+&a" (src)
-		:
-		: "cc", "memory", "0");
-	return ret;
-}
-#endif
-
 #if defined(__HAVE_ARCH_STRLEN) || (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__))
 static inline size_t __no_sanitize_prefix_strfunc(strlen)(const char *s)
 {
@@ -208,7 +189,6 @@ static inline size_t strnlen(const char * s, size_t n)
 void *memchr(const void * s, int c, size_t n);
 void *memscan(void *s, int c, size_t n);
 char *strcat(char *dst, const char *src);
-char *strcpy(char *dst, const char *src);
 size_t strlen(const char *s);
 size_t strnlen(const char * s, size_t n);
 #endif /* !IN_ARCH_STRING_C */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 27e3d804b311..0213ec800b57 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -65,15 +65,13 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 	unsigned long mask = -1UL;
-	unsigned int n = 6;
 
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_31BIT))
 		mask = 0xffffffff;
 #endif
-	while (n-- > 0)
-		if (n > 0)
-			args[n] = regs->gprs[2 + n] & mask;
+	for (int i = 1; i < 6; i++)
+		args[i] = regs->gprs[2 + i] & mask;
 
 	args[0] = regs->orig_gpr2 & mask;
 }
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index edca5a751df4..9088c5267f35 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -11,8 +11,34 @@
 #ifndef __ASM_S390_SYSINFO_H
 #define __ASM_S390_SYSINFO_H
 
-#include <asm/bitsperlong.h>
 #include <linux/uuid.h>
+#include <asm/bitsperlong.h>
+#include <asm/asm.h>
+
+/*
+ * stsi - store system information
+ *
+ * Returns the current configuration level if function code 0 was specified.
+ * Otherwise returns 0 on success or a negative value on error.
+ */
+static inline int stsi(void *sysinfo, int fc, int sel1, int sel2)
+{
+	int r0 = (fc << 28) | sel1;
+	int cc;
+
+	asm volatile(
+		"	lr	%%r0,%[r0]\n"
+		"	lr	%%r1,%[r1]\n"
+		"	stsi	%[sysinfo]\n"
+		"	lr	%[r0],%%r0\n"
+		CC_IPM(cc)
+		: CC_OUT(cc, cc), [r0] "+d" (r0), [sysinfo] "=Q" (*(char *)sysinfo)
+		: [r1] "d" (sel2)
+		: CC_CLOBBER_LIST("0", "1", "memory"));
+	if (cc == 3)
+		return -EOPNOTSUPP;
+	return fc ? 0 : (unsigned int)r0 >> 28;
+}
 
 struct sysinfo_1_1_1 {
 	unsigned char p:1;
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index c33f7144d1b9..391eb04d26d8 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -9,9 +9,7 @@
 #define _ASM_THREAD_INFO_H
 
 #include <linux/bits.h>
-#ifndef ASM_OFFSETS_C
-#include <asm/asm-offsets.h>
-#endif
+#include <vdso/page.h>
 
 /*
  * General size of kernel stacks
@@ -27,8 +25,6 @@
 #define STACK_INIT_OFFSET (THREAD_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
 
 #ifndef __ASSEMBLY__
-#include <asm/lowcore.h>
-#include <asm/page.h>
 
 /*
  * low level task data that entry.S needs immediate access to
@@ -67,7 +63,7 @@ void arch_setup_new_exec(void);
 #define TIF_NEED_RESCHED_LAZY	3	/* lazy rescheduling needed */
 #define TIF_UPROBE		4	/* breakpointed or single-stepping */
 #define TIF_PATCH_PENDING	5	/* pending live patching update */
-#define TIF_PGSTE		6	/* New mm's will use 4K page tables */
+#define TIF_ASCE_PRIMARY	6	/* primary asce is kernel asce */
 #define TIF_NOTIFY_SIGNAL	7	/* signal notifications exist */
 #define TIF_GUARDED_STORAGE	8	/* load guarded storage control block */
 #define TIF_ISOLATE_BP_GUEST	9	/* Run KVM guests with isolated BP */
@@ -89,7 +85,7 @@ void arch_setup_new_exec(void);
 #define _TIF_NEED_RESCHED_LAZY	BIT(TIF_NEED_RESCHED_LAZY)
 #define _TIF_UPROBE		BIT(TIF_UPROBE)
 #define _TIF_PATCH_PENDING	BIT(TIF_PATCH_PENDING)
-#define _TIF_PGSTE		BIT(TIF_PGSTE)
+#define _TIF_ASCE_PRIMARY	BIT(TIF_ASCE_PRIMARY)
 #define _TIF_NOTIFY_SIGNAL	BIT(TIF_NOTIFY_SIGNAL)
 #define _TIF_GUARDED_STORAGE	BIT(TIF_GUARDED_STORAGE)
 #define _TIF_ISOLATE_BP_GUEST	BIT(TIF_ISOLATE_BP_GUEST)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index a9460bd6555b..bed8d0b5a282 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -13,6 +13,7 @@
 #include <linux/preempt.h>
 #include <linux/time64.h>
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 #include <asm/asm.h>
 
 /* The value of the TOD clock for 1.1.1970. */
@@ -267,7 +268,7 @@ static __always_inline u128 eitod_to_ns(u128 todval)
  */
 static inline int tod_after(unsigned long a, unsigned long b)
 {
-	if (MACHINE_HAS_SCC)
+	if (machine_has_scc())
 		return (long) a > (long) b;
 	return a > b;
 }
@@ -281,7 +282,7 @@ static inline int tod_after(unsigned long a, unsigned long b)
  */
 static inline int tod_after_eq(unsigned long a, unsigned long b)
 {
-	if (MACHINE_HAS_SCC)
+	if (machine_has_scc())
 		return (long) a >= (long) b;
 	return a >= b;
 }
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 72655fd2d867..f20601995bb0 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -84,7 +84,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
 	tlb->cleared_pmds = 1;
-	if (mm_alloc_pgste(tlb->mm))
+	if (mm_has_pgste(tlb->mm))
 		gmap_unlink(tlb->mm, (unsigned long *)pte, address);
 	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pte));
 }
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 9dfd46dd03c6..75491baa2197 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -2,9 +2,11 @@
 #ifndef _S390_TLBFLUSH_H
 #define _S390_TLBFLUSH_H
 
+#include <linux/cpufeature.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
+#include <asm/machine.h>
 
 /*
  * Flush all TLB entries on the local CPU.
@@ -22,7 +24,7 @@ static inline void __tlb_flush_idte(unsigned long asce)
 	unsigned long opt;
 
 	opt = IDTE_PTOA;
-	if (MACHINE_HAS_TLB_GUEST)
+	if (machine_has_tlb_guest())
 		opt |= IDTE_GUEST_ASCE;
 	/* Global TLB flush for the mm */
 	asm volatile("idte 0,%1,%0" : : "a" (opt), "a" (asce) : "cc");
@@ -52,7 +54,7 @@ static inline void __tlb_flush_mm(struct mm_struct *mm)
 	cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
 	barrier();
 	gmap_asce = READ_ONCE(mm->context.gmap_asce);
-	if (MACHINE_HAS_IDTE && gmap_asce != -1UL) {
+	if (cpu_has_idte() && gmap_asce != -1UL) {
 		if (gmap_asce)
 			__tlb_flush_idte(gmap_asce);
 		__tlb_flush_idte(mm->context.asce);
@@ -66,7 +68,7 @@ static inline void __tlb_flush_mm(struct mm_struct *mm)
 
 static inline void __tlb_flush_kernel(void)
 {
-	if (MACHINE_HAS_IDTE)
+	if (cpu_has_idte())
 		__tlb_flush_idte(init_mm.context.asce);
 	else
 		__tlb_flush_global();
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index cef06bffad80..44110847342a 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -61,6 +61,12 @@ static inline void topology_expect_change(void) { }
 
 #endif /* CONFIG_SCHED_TOPOLOGY */
 
+static inline bool topology_is_primary_thread(unsigned int cpu)
+{
+	return smp_get_base_cpu(cpu) == cpu;
+}
+#define topology_is_primary_thread topology_is_primary_thread
+
 #define POLARIZATION_UNKNOWN	(-1)
 #define POLARIZATION_HRZ	(0)
 #define POLARIZATION_VL		(1)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index f5920163ee97..a43fc88c0050 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -13,125 +13,80 @@
 /*
  * User space memory access functions
  */
+#include <linux/pgtable.h>
 #include <asm/asm-extable.h>
 #include <asm/processor.h>
 #include <asm/extable.h>
 #include <asm/facility.h>
 #include <asm-generic/access_ok.h>
+#include <asm/asce.h>
 #include <linux/instrumented.h>
 
 void debug_user_asce(int exit);
 
-union oac {
-	unsigned int val;
-	struct {
-		struct {
-			unsigned short key : 4;
-			unsigned short	   : 4;
-			unsigned short as  : 2;
-			unsigned short	   : 4;
-			unsigned short k   : 1;
-			unsigned short a   : 1;
-		} oac1;
-		struct {
-			unsigned short key : 4;
-			unsigned short	   : 4;
-			unsigned short as  : 2;
-			unsigned short	   : 4;
-			unsigned short k   : 1;
-			unsigned short a   : 1;
-		} oac2;
-	};
-};
-
-static __always_inline __must_check unsigned long
-raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key)
-{
-	unsigned long rem;
-	union oac spec = {
-		.oac2.key = key,
-		.oac2.as = PSW_BITS_AS_SECONDARY,
-		.oac2.k = 1,
-		.oac2.a = 1,
-	};
-
-	asm_inline volatile(
-		"	lr	%%r0,%[spec]\n"
-		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
-		"1:	jz	5f\n"
-		"	algr	%[size],%[val]\n"
-		"	slgr	%[from],%[val]\n"
-		"	slgr	%[to],%[val]\n"
-		"	j	0b\n"
-		"2:	la	%[rem],4095(%[from])\n" /* rem = from + 4095 */
-		"	nr	%[rem],%[val]\n"	/* rem = (from + 4095) & -4096 */
-		"	slgr	%[rem],%[from]\n"
-		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
-		"	jnh	6f\n"
-		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
-		"4:	slgr	%[size],%[rem]\n"
-		"	j	6f\n"
-		"5:	lghi	%[size],0\n"
-		"6:\n"
-		EX_TABLE(0b, 2b)
-		EX_TABLE(1b, 2b)
-		EX_TABLE(3b, 6b)
-		EX_TABLE(4b, 6b)
-		: [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem)
-		: [val] "a" (-4096UL), [spec] "d" (spec.val)
-		: "cc", "memory", "0");
-	return size;
-}
+#ifdef CONFIG_KMSAN
+#define uaccess_kmsan_or_inline noinline __maybe_unused __no_sanitize_memory
+#else
+#define uaccess_kmsan_or_inline __always_inline
+#endif
 
-static __always_inline __must_check unsigned long
-raw_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	return raw_copy_from_user_key(to, from, n, 0);
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
 
-static __always_inline __must_check unsigned long
-raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key)
+static uaccess_kmsan_or_inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long rem;
-	union oac spec = {
-		.oac1.key = key,
-		.oac1.as = PSW_BITS_AS_SECONDARY,
-		.oac1.k = 1,
-		.oac1.a = 1,
-	};
-
-	asm_inline volatile(
-		"	lr	%%r0,%[spec]\n"
-		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
-		"1:	jz	5f\n"
-		"	algr	%[size],%[val]\n"
-		"	slgr	%[to],%[val]\n"
-		"	slgr	%[from],%[val]\n"
-		"	j	0b\n"
-		"2:	la	%[rem],4095(%[to])\n"	/* rem = to + 4095 */
-		"	nr	%[rem],%[val]\n"	/* rem = (to + 4095) & -4096 */
-		"	slgr	%[rem],%[to]\n"
-		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
-		"	jnh	6f\n"
-		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
-		"4:	slgr	%[size],%[rem]\n"
-		"	j	6f\n"
-		"5:	lghi	%[size],0\n"
-		"6:\n"
-		EX_TABLE(0b, 2b)
-		EX_TABLE(1b, 2b)
-		EX_TABLE(3b, 6b)
-		EX_TABLE(4b, 6b)
-		: [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem)
-		: [val] "a" (-4096UL), [spec] "d" (spec.val)
-		: "cc", "memory", "0");
-	return size;
+	unsigned long osize;
+	int cc;
+
+	while (1) {
+		osize = size;
+		asm_inline volatile(
+			"	lhi	%%r0,%[spec]\n"
+			"0:	mvcos	%[to],%[from],%[size]\n"
+			"1:	nopr	%%r7\n"
+			CC_IPM(cc)
+			EX_TABLE_UA_MVCOS_FROM(0b, 0b)
+			EX_TABLE_UA_MVCOS_FROM(1b, 0b)
+			: CC_OUT(cc, cc), [size] "+d" (size), [to] "=Q" (*(char *)to)
+			: [spec] "I" (0x81), [from] "Q" (*(const char __user *)from)
+			: CC_CLOBBER_LIST("memory", "0"));
+		if (__builtin_constant_p(osize) && osize <= 4096)
+			return osize - size;
+		if (likely(CC_TRANSFORM(cc) == 0))
+			return osize - size;
+		size -= 4096;
+		to += 4096;
+		from += 4096;
+	}
 }
 
-static __always_inline __must_check unsigned long
-raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+static uaccess_kmsan_or_inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long size)
 {
-	return raw_copy_to_user_key(to, from, n, 0);
+	unsigned long osize;
+	int cc;
+
+	while (1) {
+		osize = size;
+		asm_inline volatile(
+			"	llilh	%%r0,%[spec]\n"
+			"0:	mvcos	%[to],%[from],%[size]\n"
+			"1:	nopr	%%r7\n"
+			CC_IPM(cc)
+			EX_TABLE_UA_MVCOS_TO(0b, 0b)
+			EX_TABLE_UA_MVCOS_TO(1b, 0b)
+			: CC_OUT(cc, cc), [size] "+d" (size), [to] "=Q" (*(char __user *)to)
+			: [spec] "I" (0x81), [from] "Q" (*(const char *)from)
+			: CC_CLOBBER_LIST("memory", "0"));
+		if (__builtin_constant_p(osize) && osize <= 4096)
+			return osize - size;
+		if (likely(CC_TRANSFORM(cc) == 0))
+			return osize - size;
+		size -= 4096;
+		to += 4096;
+		from += 4096;
+	}
 }
 
 unsigned long __must_check
@@ -158,12 +113,6 @@ copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned lo
 
 int __noreturn __put_user_bad(void);
 
-#ifdef CONFIG_KMSAN
-#define uaccess_kmsan_or_inline noinline __maybe_unused __no_sanitize_memory
-#else
-#define uaccess_kmsan_or_inline __always_inline
-#endif
-
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
 #define DEFINE_PUT_USER_NOINSTR(type)					\
@@ -199,7 +148,7 @@ __put_user_##type##_noinstr(unsigned type __user *to,			\
 {									\
 	int rc;								\
 									\
-	asm volatile(							\
+	asm_inline volatile(						\
 		"	llilh	%%r0,%[spec]\n"				\
 		"0:	mvcos	%[to],%[from],%[size]\n"		\
 		"1:	lhi	%[rc],0\n"				\
@@ -315,7 +264,7 @@ __get_user_##type##_noinstr(unsigned type *to,				\
 {									\
 	int rc;								\
 									\
-	asm volatile(							\
+	asm_inline volatile(						\
 		"	lhi	%%r0,%[spec]\n"				\
 		"0:	mvcos	%[to],%[from],%[size]\n"		\
 		"1:	lhi	%[rc],0\n"				\
@@ -415,12 +364,34 @@ long __must_check strncpy_from_user(char *dst, const char __user *src, long coun
 
 long __must_check strnlen_user(const char __user *src, long count);
 
-/*
- * Zero Userspace
- */
-unsigned long __must_check __clear_user(void __user *to, unsigned long size);
+static uaccess_kmsan_or_inline __must_check unsigned long
+__clear_user(void __user *to, unsigned long size)
+{
+	unsigned long osize;
+	int cc;
+
+	while (1) {
+		osize = size;
+		asm_inline volatile(
+			"	llilh	%%r0,%[spec]\n"
+			"0:	mvcos	%[to],%[from],%[size]\n"
+			"1:	nopr	%%r7\n"
+			CC_IPM(cc)
+			EX_TABLE_UA_MVCOS_TO(0b, 0b)
+			EX_TABLE_UA_MVCOS_TO(1b, 0b)
+			: CC_OUT(cc, cc), [size] "+d" (size), [to] "=Q" (*(char __user *)to)
+			: [spec] "I" (0x81), [from] "Q" (*(const char *)empty_zero_page)
+			: CC_CLOBBER_LIST("memory", "0"));
+		if (__builtin_constant_p(osize) && osize <= 4096)
+			return osize - size;
+		if (CC_TRANSFORM(cc) == 0)
+			return osize - size;
+		size -= 4096;
+		to += 4096;
+	}
+}
 
-static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
+static __always_inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	might_fault();
 	return __clear_user(to, n);
@@ -508,6 +479,7 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 					      __uint128_t old, __uint128_t new,
 					      unsigned long key, int size)
 {
+	bool sacf_flag;
 	int rc = 0;
 
 	switch (size) {
@@ -520,7 +492,8 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 		_old = ((unsigned int)old & 0xff) << shift;
 		_new = ((unsigned int)new & 0xff) << shift;
 		mask = ~(0xff << shift);
-		asm volatile(
+		sacf_flag = enable_sacf_uaccess();
+		asm_inline volatile(
 			"	spka	0(%[key])\n"
 			"	sacf	256\n"
 			"	llill	%[count],%[max_loops]\n"
@@ -554,6 +527,7 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 			  [default_key] "J" (PAGE_DEFAULT_KEY),
 			  [max_loops] "J" (CMPXCHG_USER_KEY_MAX_LOOPS)
 			: "memory", "cc");
+		disable_sacf_uaccess(sacf_flag);
 		*(unsigned char *)uval = prev >> shift;
 		if (!count)
 			rc = -EAGAIN;
@@ -568,7 +542,8 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 		_old = ((unsigned int)old & 0xffff) << shift;
 		_new = ((unsigned int)new & 0xffff) << shift;
 		mask = ~(0xffff << shift);
-		asm volatile(
+		sacf_flag = enable_sacf_uaccess();
+		asm_inline volatile(
 			"	spka	0(%[key])\n"
 			"	sacf	256\n"
 			"	llill	%[count],%[max_loops]\n"
@@ -602,6 +577,7 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 			  [default_key] "J" (PAGE_DEFAULT_KEY),
 			  [max_loops] "J" (CMPXCHG_USER_KEY_MAX_LOOPS)
 			: "memory", "cc");
+		disable_sacf_uaccess(sacf_flag);
 		*(unsigned short *)uval = prev >> shift;
 		if (!count)
 			rc = -EAGAIN;
@@ -610,7 +586,8 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 	case 4:	{
 		unsigned int prev = old;
 
-		asm volatile(
+		sacf_flag = enable_sacf_uaccess();
+		asm_inline volatile(
 			"	spka	0(%[key])\n"
 			"	sacf	256\n"
 			"0:	cs	%[prev],%[new],%[address]\n"
@@ -625,13 +602,15 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 			  [key] "a" (key << 4),
 			  [default_key] "J" (PAGE_DEFAULT_KEY)
 			: "memory", "cc");
+		disable_sacf_uaccess(sacf_flag);
 		*(unsigned int *)uval = prev;
 		return rc;
 	}
 	case 8: {
 		unsigned long prev = old;
 
-		asm volatile(
+		sacf_flag = enable_sacf_uaccess();
+		asm_inline volatile(
 			"	spka	0(%[key])\n"
 			"	sacf	256\n"
 			"0:	csg	%[prev],%[new],%[address]\n"
@@ -646,13 +625,15 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 			  [key] "a" (key << 4),
 			  [default_key] "J" (PAGE_DEFAULT_KEY)
 			: "memory", "cc");
+		disable_sacf_uaccess(sacf_flag);
 		*(unsigned long *)uval = prev;
 		return rc;
 	}
 	case 16: {
 		__uint128_t prev = old;
 
-		asm volatile(
+		sacf_flag = enable_sacf_uaccess();
+		asm_inline volatile(
 			"	spka	0(%[key])\n"
 			"	sacf	256\n"
 			"0:	cdsg	%[prev],%[new],%[address]\n"
@@ -667,6 +648,7 @@ static __always_inline int __cmpxchg_user_key(unsigned long address, void *uval,
 			  [key] "a" (key << 4),
 			  [default_key] "J" (PAGE_DEFAULT_KEY)
 			: "memory", "cc");
+		disable_sacf_uaccess(sacf_flag);
 		*(__uint128_t *)uval = prev;
 		return rc;
 	}
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index b11f5b6d0bd1..b008402ec9aa 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -616,8 +616,9 @@ static inline int uv_remove_shared(unsigned long addr)
 	return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
 }
 
-int uv_get_secret_metadata(const u8 secret_id[UV_SECRET_ID_LEN],
-			   struct uv_secret_list_item_hdr *secret);
+int uv_find_secret(const u8 secret_id[UV_SECRET_ID_LEN],
+		   struct uv_secret_list *list,
+		   struct uv_secret_list_item_hdr *secret);
 int uv_retrieve_secret(u16 secret_idx, u8 *buf, size_t buf_size);
 
 extern int prot_virt_host;
@@ -631,7 +632,7 @@ int uv_pin_shared(unsigned long paddr);
 int uv_destroy_folio(struct folio *folio);
 int uv_destroy_pte(pte_t pte);
 int uv_convert_from_secure_pte(pte_t pte);
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb);
 int uv_convert_from_secure(unsigned long paddr);
 int uv_convert_from_secure_folio(struct folio *folio);
 
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 92c73e4d97a9..420a073fdde5 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -6,13 +6,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern struct vdso_data *vdso_data;
-
 int vdso_getcpu_init(void);
 
 #endif /* __ASSEMBLY__ */
 
-#define __VVAR_PAGES	2
+#define __VDSO_PAGES	4
 
 #define VDSO_VERSION_STRING	LINUX_2.6.29
 
diff --git a/arch/s390/include/asm/vdso/getrandom.h b/arch/s390/include/asm/vdso/getrandom.h
index 36355af7160b..f8713ce39bb2 100644
--- a/arch/s390/include/asm/vdso/getrandom.h
+++ b/arch/s390/include/asm/vdso/getrandom.h
@@ -23,18 +23,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 	return syscall3(__NR_getrandom, (long)buffer, (long)len, (long)flags);
 }
 
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	/*
-	 * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace
-	 * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_
-	 * PAGE_OFFSET points to the real VVAR page.
-	 */
-	if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
-	return &_vdso_rng_data;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h
index 7937765ccfa5..fb4564308e9d 100644
--- a/arch/s390/include/asm/vdso/gettimeofday.h
+++ b/arch/s390/include/asm/vdso/gettimeofday.h
@@ -14,12 +14,7 @@
 #include <linux/compiler.h>
 
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return _vdso_data;
-}
-
-static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd)
+static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_time_data *vd)
 {
 	u64 adj, now;
 
@@ -49,12 +44,4 @@ long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts)
 	return syscall2(__NR_clock_getres, (long)clkid, (long)ts);
 }
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return _timens_data;
-}
-#endif
-
 #endif
diff --git a/arch/s390/include/asm/vdso/vsyscall.h b/arch/s390/include/asm/vdso/vsyscall.h
index 3eb576ecd3bd..d346ebe51301 100644
--- a/arch/s390/include/asm/vdso/vsyscall.h
+++ b/arch/s390/include/asm/vdso/vsyscall.h
@@ -2,32 +2,12 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET	768
-
 #ifndef __ASSEMBLY__
 
 #include <linux/hrtimer.h>
 #include <vdso/datapage.h>
 #include <asm/vdso.h>
 
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES
-};
-
-static __always_inline struct vdso_data *__s390_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __s390_get_k_vdso_data
-
-static __always_inline struct vdso_rng_data *__s390_get_k_vdso_rnd_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __s390_get_k_vdso_rnd_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/s390/include/asm/word-at-a-time.h b/arch/s390/include/asm/word-at-a-time.h
index 203acd6e431b..eaa19dee7699 100644
--- a/arch/s390/include/asm/word-at-a-time.h
+++ b/arch/s390/include/asm/word-at-a-time.h
@@ -52,7 +52,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
 	unsigned long data;
 
-	asm volatile(
+	asm_inline volatile(
 		"0:	lg	%[data],0(%[addr])\n"
 		"1:	nopr	%%r7\n"
 		EX_TABLE_ZEROPAD(0b, 1b, %[data], %[addr])
diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c
index 88f0b91d7a73..6252b7d115dd 100644
--- a/arch/s390/kernel/abs_lowcore.c
+++ b/arch/s390/kernel/abs_lowcore.c
@@ -5,7 +5,6 @@
 #include <asm/sections.h>
 
 unsigned long __bootdata_preserved(__abs_lowcore);
-int __bootdata_preserved(relocate_lowcore);
 
 int abs_lowcore_map(int cpu, struct lowcore *lc, bool alloc)
 {
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 8d5d0de35de0..90c0e6408992 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -1,41 +1,90 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#ifndef pr_fmt
+#define pr_fmt(fmt)	"alt: " fmt
+#endif
+
 #include <linux/uaccess.h>
+#include <linux/printk.h>
 #include <asm/nospec-branch.h>
 #include <asm/abs_lowcore.h>
 #include <asm/alternative.h>
 #include <asm/facility.h>
+#include <asm/sections.h>
+#include <asm/machine.h>
+
+#ifndef a_debug
+#define a_debug		pr_debug
+#endif
+
+#ifndef __kernel_va
+#define __kernel_va(x)	(void *)(x)
+#endif
+
+unsigned long __bootdata_preserved(machine_features[1]);
+
+struct alt_debug {
+	unsigned long facilities[MAX_FACILITY_BIT / BITS_PER_LONG];
+	unsigned long mfeatures[MAX_MFEATURE_BIT / BITS_PER_LONG];
+	int spec;
+};
+
+static struct alt_debug __bootdata_preserved(alt_debug);
+
+static void alternative_dump(u8 *old, u8 *new, unsigned int len, unsigned int type, unsigned int data)
+{
+	char oinsn[33], ninsn[33];
+	unsigned long kptr;
+	unsigned int pos;
+
+	for (pos = 0; pos < len && 2 * pos < sizeof(oinsn) - 3; pos++)
+		hex_byte_pack(&oinsn[2 * pos], old[pos]);
+	oinsn[2 * pos] = 0;
+	for (pos = 0; pos < len && 2 * pos < sizeof(ninsn) - 3; pos++)
+		hex_byte_pack(&ninsn[2 * pos], new[pos]);
+	ninsn[2 * pos] = 0;
+	kptr = (unsigned long)__kernel_va(old);
+	a_debug("[%d/%3d] %016lx: %s -> %s\n", type, data, kptr, oinsn, ninsn);
+}
 
 void __apply_alternatives(struct alt_instr *start, struct alt_instr *end, unsigned int ctx)
 {
-	u8 *instr, *replacement;
+	struct alt_debug *d;
 	struct alt_instr *a;
-	bool replace;
+	bool debug, replace;
+	u8 *old, *new;
 
 	/*
 	 * The scan order should be from start to end. A later scanned
 	 * alternative code can overwrite previously scanned alternative code.
 	 */
+	d = &alt_debug;
 	for (a = start; a < end; a++) {
 		if (!(a->ctx & ctx))
 			continue;
 		switch (a->type) {
 		case ALT_TYPE_FACILITY:
 			replace = test_facility(a->data);
+			debug = __test_facility(a->data, d->facilities);
+			break;
+		case ALT_TYPE_FEATURE:
+			replace = test_machine_feature(a->data);
+			debug = __test_machine_feature(a->data, d->mfeatures);
 			break;
 		case ALT_TYPE_SPEC:
 			replace = nobp_enabled();
-			break;
-		case ALT_TYPE_LOWCORE:
-			replace = have_relocated_lowcore();
+			debug = d->spec;
 			break;
 		default:
 			replace = false;
+			debug = false;
 		}
 		if (!replace)
 			continue;
-		instr = (u8 *)&a->instr_offset + a->instr_offset;
-		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		s390_kernel_write(instr, replacement, a->instrlen);
+		old = (u8 *)&a->instr_offset + a->instr_offset;
+		new = (u8 *)&a->repl_offset + a->repl_offset;
+		if (debug)
+			alternative_dump(old, new, a->instrlen, a->type, a->data);
+		s390_kernel_write(old, new, a->instrlen);
 	}
 }
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 36709112ae7a..95ecad9c7d7d 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -5,15 +5,14 @@
  * and format the required data.
  */
 
-#define ASM_OFFSETS_C
-
 #include <linux/kbuild.h>
-#include <linux/kvm_host.h>
 #include <linux/sched.h>
 #include <linux/purgatory.h>
 #include <linux/pgtable.h>
-#include <linux/ftrace.h>
+#include <linux/ftrace_regs.h>
+#include <asm/kvm_host_types.h>
 #include <asm/stacktrace.h>
+#include <asm/ptrace.h>
 
 int main(void)
 {
@@ -49,8 +48,8 @@ int main(void)
 	OFFSET(__PT_R14, pt_regs, gprs[14]);
 	OFFSET(__PT_R15, pt_regs, gprs[15]);
 	OFFSET(__PT_ORIG_GPR2, pt_regs, orig_gpr2);
+	OFFSET(__PT_INT_CODE, pt_regs, int_code);
 	OFFSET(__PT_FLAGS, pt_regs, flags);
-	OFFSET(__PT_CR1, pt_regs, cr1);
 	OFFSET(__PT_LAST_BREAK, pt_regs, last_break);
 	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
 	BLANK();
@@ -76,7 +75,8 @@ int main(void)
 	OFFSET(__LC_EXT_CPU_ADDR, lowcore, ext_cpu_addr);
 	OFFSET(__LC_EXT_INT_CODE, lowcore, ext_int_code);
 	OFFSET(__LC_PGM_ILC, lowcore, pgm_ilc);
-	OFFSET(__LC_PGM_INT_CODE, lowcore, pgm_code);
+	OFFSET(__LC_PGM_CODE, lowcore, pgm_code);
+	OFFSET(__LC_PGM_INT_CODE, lowcore, pgm_int_code);
 	OFFSET(__LC_DATA_EXC_CODE, lowcore, data_exc_code);
 	OFFSET(__LC_MON_CLASS_NR, lowcore, mon_class_num);
 	OFFSET(__LC_PER_CODE, lowcore, per_code);
@@ -122,7 +122,6 @@ int main(void)
 	OFFSET(__LC_LAST_UPDATE_TIMER, lowcore, last_update_timer);
 	OFFSET(__LC_LAST_UPDATE_CLOCK, lowcore, last_update_clock);
 	OFFSET(__LC_INT_CLOCK, lowcore, int_clock);
-	OFFSET(__LC_BOOT_CLOCK, lowcore, boot_clock);
 	OFFSET(__LC_CURRENT, lowcore, current_task);
 	OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
 	OFFSET(__LC_ASYNC_STACK, lowcore, async_stack);
diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c
index bf983513dd33..c217a5e64094 100644
--- a/arch/s390/kernel/cert_store.c
+++ b/arch/s390/kernel/cert_store.c
@@ -138,7 +138,7 @@ static void cert_store_key_describe(const struct key *key, struct seq_file *m)
 	 * First 64 bytes of the key description is key name in EBCDIC CP 500.
 	 * Convert it to ASCII for displaying in /proc/keys.
 	 */
-	strscpy(ascii, key->description, sizeof(ascii));
+	strscpy(ascii, key->description);
 	EBCASC_500(ascii, VC_NAME_LEN_BYTES);
 	seq_puts(m, ascii);
 
@@ -235,7 +235,7 @@ static int __diag320(unsigned long subcode, void *addr)
 {
 	union register_pair rp = { .even = (unsigned long)addr, };
 
-	asm volatile(
+	asm_inline volatile(
 		"	diag	%[rp],%[subcode],0x320\n"
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
diff --git a/arch/s390/kernel/cpufeature.c b/arch/s390/kernel/cpufeature.c
index 1b2ae42a0c15..76210f001028 100644
--- a/arch/s390/kernel/cpufeature.c
+++ b/arch/s390/kernel/cpufeature.c
@@ -5,11 +5,13 @@
 
 #include <linux/cpufeature.h>
 #include <linux/bug.h>
+#include <asm/machine.h>
 #include <asm/elf.h>
 
 enum {
 	TYPE_HWCAP,
 	TYPE_FACILITY,
+	TYPE_MACHINE,
 };
 
 struct s390_cpu_feature {
@@ -21,6 +23,7 @@ static struct s390_cpu_feature s390_cpu_features[MAX_CPU_FEATURES] = {
 	[S390_CPU_FEATURE_MSA]	= {.type = TYPE_HWCAP, .num = HWCAP_NR_MSA},
 	[S390_CPU_FEATURE_VXRS]	= {.type = TYPE_HWCAP, .num = HWCAP_NR_VXRS},
 	[S390_CPU_FEATURE_UV]	= {.type = TYPE_FACILITY, .num = 158},
+	[S390_CPU_FEATURE_D288]	= {.type = TYPE_MACHINE, .num = MFEATURE_DIAG288},
 };
 
 /*
@@ -38,6 +41,8 @@ int cpu_have_feature(unsigned int num)
 		return !!(elf_hwcap & BIT(feature->num));
 	case TYPE_FACILITY:
 		return test_facility(feature->num);
+	case TYPE_MACHINE:
+		return test_machine_feature(feature->num);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 276cb4c1e11b..adb164223f8c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -246,15 +246,6 @@ bool is_kdump_kernel(void)
 }
 EXPORT_SYMBOL_GPL(is_kdump_kernel);
 
-static const char *nt_name(Elf64_Word type)
-{
-	const char *name = "LINUX";
-
-	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
-		name = KEXEC_CORE_NOTE_NAME;
-	return name;
-}
-
 /*
  * Initialize ELF note
  */
@@ -279,10 +270,8 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
 	return PTR_ADD(buf, len);
 }
 
-static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
-{
-	return nt_init_name(buf, type, desc, d_len, nt_name(type));
-}
+#define nt_init(buf, type, desc) \
+	nt_init_name(buf, NT_ ## type, &(desc), sizeof(desc), NN_ ## type)
 
 /*
  * Calculate the size of ELF note
@@ -298,10 +287,7 @@ static size_t nt_size_name(int d_len, const char *name)
 	return size;
 }
 
-static inline size_t nt_size(Elf64_Word type, int d_len)
-{
-	return nt_size_name(d_len, nt_name(type));
-}
+#define nt_size(type, desc) nt_size_name(sizeof(desc), NN_ ## type)
 
 /*
  * Fill ELF notes for one CPU with save area registers
@@ -322,18 +308,16 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 	memcpy(&nt_fpregset.fpc, &sa->fpc, sizeof(sa->fpc));
 	memcpy(&nt_fpregset.fprs, &sa->fprs, sizeof(sa->fprs));
 	/* Create ELF notes for the CPU */
-	ptr = nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus));
-	ptr = nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset));
-	ptr = nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer));
-	ptr = nt_init(ptr, NT_S390_TODCMP, &sa->todcmp, sizeof(sa->todcmp));
-	ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg));
-	ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs));
-	ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix));
+	ptr = nt_init(ptr, PRSTATUS, nt_prstatus);
+	ptr = nt_init(ptr, PRFPREG, nt_fpregset);
+	ptr = nt_init(ptr, S390_TIMER, sa->timer);
+	ptr = nt_init(ptr, S390_TODCMP, sa->todcmp);
+	ptr = nt_init(ptr, S390_TODPREG, sa->todpreg);
+	ptr = nt_init(ptr, S390_CTRS, sa->ctrs);
+	ptr = nt_init(ptr, S390_PREFIX, sa->prefix);
 	if (cpu_has_vx()) {
-		ptr = nt_init(ptr, NT_S390_VXRS_HIGH,
-			      &sa->vxrs_high, sizeof(sa->vxrs_high));
-		ptr = nt_init(ptr, NT_S390_VXRS_LOW,
-			      &sa->vxrs_low, sizeof(sa->vxrs_low));
+		ptr = nt_init(ptr, S390_VXRS_HIGH, sa->vxrs_high);
+		ptr = nt_init(ptr, S390_VXRS_LOW, sa->vxrs_low);
 	}
 	return ptr;
 }
@@ -346,16 +330,16 @@ static size_t get_cpu_elf_notes_size(void)
 	struct save_area *sa = NULL;
 	size_t size;
 
-	size =	nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
-	size +=  nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
-	size +=  nt_size(NT_S390_TIMER, sizeof(sa->timer));
-	size +=  nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
-	size +=  nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
-	size +=  nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
-	size +=  nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+	size =	nt_size(PRSTATUS, struct elf_prstatus);
+	size += nt_size(PRFPREG, elf_fpregset_t);
+	size += nt_size(S390_TIMER, sa->timer);
+	size += nt_size(S390_TODCMP, sa->todcmp);
+	size += nt_size(S390_TODPREG, sa->todpreg);
+	size += nt_size(S390_CTRS, sa->ctrs);
+	size += nt_size(S390_PREFIX, sa->prefix);
 	if (cpu_has_vx()) {
-		size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
-		size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+		size += nt_size(S390_VXRS_HIGH, sa->vxrs_high);
+		size += nt_size(S390_VXRS_LOW, sa->vxrs_low);
 	}
 
 	return size;
@@ -370,8 +354,8 @@ static void *nt_prpsinfo(void *ptr)
 
 	memset(&prpsinfo, 0, sizeof(prpsinfo));
 	prpsinfo.pr_sname = 'R';
-	strcpy(prpsinfo.pr_fname, "vmlinux");
-	return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo));
+	strscpy(prpsinfo.pr_fname, "vmlinux");
+	return nt_init(ptr, PRPSINFO, prpsinfo);
 }
 
 /*
@@ -610,7 +594,7 @@ static size_t get_elfcorehdr_size(int phdr_count)
 	/* PT_NOTES */
 	size += sizeof(Elf64_Phdr);
 	/* nt_prpsinfo */
-	size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+	size += nt_size(PRPSINFO, struct elf_prpsinfo);
 	/* regsets */
 	size += get_cpu_cnt() * get_cpu_elf_notes_size();
 	/* nt_vmcoreinfo */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index ce038e9205f7..2a41be2f7925 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -251,7 +251,7 @@ static debug_info_t *debug_info_alloc(const char *name, int pages_per_area,
 	rc->level	   = level;
 	rc->buf_size	   = buf_size;
 	rc->entry_size	   = sizeof(debug_entry_t) + buf_size;
-	strscpy(rc->name, name, sizeof(rc->name));
+	strscpy(rc->name, name);
 	memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
 	memset(rc->debugfs_entries, 0, DEBUG_MAX_VIEWS * sizeof(struct dentry *));
 	refcount_set(&(rc->ref_count), 0);
diff --git a/arch/s390/kernel/diag/diag.c b/arch/s390/kernel/diag/diag.c
index e15b8dee3228..56b862ba9be8 100644
--- a/arch/s390/kernel/diag/diag.c
+++ b/arch/s390/kernel/diag/diag.c
@@ -195,7 +195,7 @@ static inline int __diag204(unsigned long *subcode, unsigned long size, void *ad
 {
 	union register_pair rp = { .even = *subcode, .odd = size };
 
-	asm volatile(
+	asm_inline volatile(
 		"	diag	%[addr],%[rp],0x204\n"
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
@@ -286,7 +286,7 @@ int diag224(void *ptr)
 	int rc = -EOPNOTSUPP;
 
 	diag_stat_inc(DIAG_STAT_X224);
-	asm volatile("\n"
+	asm_inline volatile("\n"
 		"	diag	%[type],%[addr],0x224\n"
 		"0:	lhi	%[rc],0\n"
 		"1:\n"
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 1ecd0580561f..dd410962ecbe 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
+#include <asm/asm-offsets.h>
 #include <asm/processor.h>
 #include <asm/debug.h>
 #include <asm/dis.h>
@@ -198,13 +199,8 @@ void __noreturn die(struct pt_regs *regs, const char *str)
 	console_verbose();
 	spin_lock_irq(&die_lock);
 	bust_spinlocks(1);
-	printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
+	printk("%s: %04x ilc:%d [#%d]", str, regs->int_code & 0xffff,
 	       regs->int_code >> 17, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	pr_cont("PREEMPT ");
-#elif defined(CONFIG_PREEMPT_RT)
-	pr_cont("PREEMPT_RT ");
-#endif
 	pr_cont("SMP ");
 	if (debug_pagealloc_enabled())
 		pr_cont("DEBUG_PAGEALLOC");
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2fa25164df7d..54cf0923050f 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -8,6 +8,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/sched/debug.h>
+#include <linux/cpufeature.h>
 #include <linux/compiler.h>
 #include <linux/init.h>
 #include <linux/errno.h>
@@ -21,6 +22,8 @@
 #include <asm/asm-extable.h>
 #include <linux/memblock.h>
 #include <asm/access-regs.h>
+#include <asm/asm-offsets.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include <asm/fpu.h>
@@ -36,12 +39,14 @@
 #include <asm/boot_data.h>
 #include "entry.h"
 
-#define decompressor_handled_param(param)			\
-static int __init ignore_decompressor_param_##param(char *s)	\
+#define __decompressor_handled_param(func, param)		\
+static int __init ignore_decompressor_param_##func(char *s)	\
 {								\
 	return 0;						\
 }								\
-early_param(#param, ignore_decompressor_param_##param)
+early_param(#param, ignore_decompressor_param_##func)
+
+#define decompressor_handled_param(param) __decompressor_handled_param(param, param)
 
 decompressor_handled_param(mem);
 decompressor_handled_param(vmalloc);
@@ -51,6 +56,7 @@ decompressor_handled_param(nokaslr);
 decompressor_handled_param(cmma);
 decompressor_handled_param(relocate_lowcore);
 decompressor_handled_param(bootdebug);
+__decompressor_handled_param(debug_alternative, debug-alternative);
 #if IS_ENABLED(CONFIG_KVM)
 decompressor_handled_param(prot_virt);
 #endif
@@ -63,21 +69,6 @@ static void __init kasan_early_init(void)
 #endif
 }
 
-static void __init reset_tod_clock(void)
-{
-	union tod_clock clk;
-
-	if (store_tod_clock_ext_cc(&clk) == 0)
-		return;
-	/* TOD clock not running. Set the clock to Unix Epoch. */
-	if (set_tod_clock(TOD_UNIX_EPOCH) || store_tod_clock_ext_cc(&clk))
-		disabled_wait();
-
-	memset(&tod_clock_base, 0, sizeof(tod_clock_base));
-	tod_clock_base.tod = TOD_UNIX_EPOCH;
-	get_lowcore()->last_update_clock = TOD_UNIX_EPOCH;
-}
-
 /*
  * Initialize storage key for kernel pages
  */
@@ -96,26 +87,6 @@ static noinline __init void init_kernel_storage_key(void)
 
 static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE);
 
-static noinline __init void detect_machine_type(void)
-{
-	struct sysinfo_3_2_2 *vmms = (struct sysinfo_3_2_2 *)&sysinfo_page;
-
-	/* Check current-configuration-level */
-	if (stsi(NULL, 0, 0, 0) <= 2) {
-		get_lowcore()->machine_flags |= MACHINE_FLAG_LPAR;
-		return;
-	}
-	/* Get virtual-machine cpu information. */
-	if (stsi(vmms, 3, 2, 2) || !vmms->count)
-		return;
-
-	/* Detect known hypervisors */
-	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_KVM;
-	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_VM;
-}
-
 /* Remove leading, trailing and double whitespace. */
 static inline void strim_all(char *str)
 {
@@ -156,9 +127,9 @@ static noinline __init void setup_arch_string(void)
 		strim_all(hvstr);
 	} else {
 		sprintf(hvstr, "%s",
-			MACHINE_IS_LPAR ? "LPAR" :
-			MACHINE_IS_VM ? "z/VM" :
-			MACHINE_IS_KVM ? "KVM" : "unknown");
+			machine_is_lpar() ? "LPAR" :
+			machine_is_vm() ? "z/VM" :
+			machine_is_kvm() ? "KVM" : "unknown");
 	}
 	dump_stack_set_arch_desc("%s (%s)", mstr, hvstr);
 }
@@ -167,9 +138,8 @@ static __init void setup_topology(void)
 {
 	int max_mnest;
 
-	if (!test_facility(11))
+	if (!cpu_has_topology())
 		return;
-	get_lowcore()->machine_flags |= MACHINE_FLAG_TOPOLOGY;
 	for (max_mnest = 6; max_mnest > 1; max_mnest--) {
 		if (stsi(&sysinfo_page, 15, 1, max_mnest) == 0)
 			break;
@@ -218,65 +188,10 @@ static noinline __init void setup_lowcore_early(void)
 	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
 }
 
-static __init void detect_diag9c(void)
-{
-	unsigned int cpu_address;
-	int rc;
-
-	cpu_address = stap();
-	diag_stat_inc(DIAG_STAT_X09C);
-	asm volatile(
-		"	diag	%2,0,0x9c\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc");
-	if (!rc)
-		get_lowcore()->machine_flags |= MACHINE_FLAG_DIAG9C;
-}
-
-static __init void detect_machine_facilities(void)
-{
-	if (test_facility(8)) {
-		get_lowcore()->machine_flags |= MACHINE_FLAG_EDAT1;
-		system_ctl_set_bit(0, CR0_EDAT_BIT);
-	}
-	if (test_facility(78))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_EDAT2;
-	if (test_facility(3))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_IDTE;
-	if (test_facility(50) && test_facility(73)) {
-		get_lowcore()->machine_flags |= MACHINE_FLAG_TE;
-		system_ctl_set_bit(0, CR0_TRANSACTIONAL_EXECUTION_BIT);
-	}
-	if (test_facility(51))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_TLB_LC;
-	if (test_facility(129))
-		system_ctl_set_bit(0, CR0_VECTOR_BIT);
-	if (test_facility(130))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_NX;
-	if (test_facility(133))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_GS;
-	if (test_facility(139) && (tod_clock_base.tod >> 63)) {
-		/* Enabled signed clock comparator comparisons */
-		get_lowcore()->machine_flags |= MACHINE_FLAG_SCC;
-		clock_comparator_max = -1ULL >> 1;
-		system_ctl_set_bit(0, CR0_CLOCK_COMPARATOR_SIGN_BIT);
-	}
-	if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) {
-		get_lowcore()->machine_flags |= MACHINE_FLAG_PCI_MIO;
-		/* the control bit is set during PCI initialization */
-	}
-	if (test_facility(194))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_RDP;
-	if (test_facility(85))
-		get_lowcore()->machine_flags |= MACHINE_FLAG_SEQ_INSN;
-}
-
 static inline void save_vector_registers(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	if (test_facility(129))
+	if (cpu_has_vx())
 		save_vx_regs(boot_cpu_vector_save_area);
 #endif
 }
@@ -308,17 +223,13 @@ static void __init sort_amode31_extable(void)
 void __init startup_init(void)
 {
 	kasan_early_init();
-	reset_tod_clock();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
 	sort_amode31_extable();
 	setup_lowcore_early();
-	detect_machine_type();
 	setup_arch_string();
 	setup_boot_command_line();
-	detect_diag9c();
-	detect_machine_facilities();
 	save_vector_registers();
 	setup_topology();
 	sclp_early_detect();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 4cc3408c4dac..0f00f4b06d51 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -29,6 +29,7 @@
 #include <asm/nmi.h>
 #include <asm/nospec-insn.h>
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 
 _LPP_OFFSET	= __LC_LPP
 
@@ -44,7 +45,7 @@ _LPP_OFFSET	= __LC_LPP
 	ALTERNATIVE_2 "b \lpswe;nopr", \
 		".insn siy,0xeb0000000071,\address,0", ALT_FACILITY(193),		\
 		__stringify(.insn siy,0xeb0000000071,LOWCORE_ALT_ADDRESS+\address,0),	\
-		ALT_LOWCORE
+		ALT_FEATURE(MFEATURE_LOWCORE)
 	.endm
 
 	.macro MBEAR reg, lowcore
@@ -67,7 +68,7 @@ _LPP_OFFSET	= __LC_LPP
 	clg	%r14,__LC_RESTART_STACK(\lowcore)
 	je	\oklabel
 	la	%r14,\savearea(\lowcore)
-	j	stack_overflow
+	j	stack_invalid
 	.endm
 
 	/*
@@ -115,7 +116,7 @@ _LPP_OFFSET	= __LC_LPP
 	.macro SIEEXIT sie_control,lowcore
 	lg	%r9,\sie_control			# get control block pointer
 	ni	__SIE_PROG0C+3(%r9),0xfe		# no longer in SIE
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE(\lowcore)	# load primary asce
+	lctlg	%c1,%c1,__LC_USER_ASCE(\lowcore)	# load primary asce
 	lg	%r9,__LC_CURRENT(\lowcore)
 	mvi	__TI_sie(%r9),0
 	larl	%r9,sie_exit			# skip forward to sie_exit
@@ -207,7 +208,7 @@ SYM_FUNC_START(__sie64a)
 	lg	%r14,__SF_SIE_CONTROL(%r15)	# get control block pointer
 	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
 	GET_LC	%r14
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r14)	# load primary asce
+	lctlg	%c1,%c1,__LC_USER_ASCE(%r14)	# load primary asce
 	lg	%r14,__LC_CURRENT(%r14)
 	mvi	__TI_sie(%r14),0
 SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL)
@@ -239,7 +240,6 @@ SYM_CODE_START(system_call)
 	lghi	%r14,0
 .Lsysc_per:
 	STBEAR	__LC_LAST_BREAK(%r13)
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
 	lg	%r15,__LC_KERNEL_STACK(%r13)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	stmg	%r0,%r7,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
@@ -260,7 +260,6 @@ SYM_CODE_START(system_call)
 	lgr	%r3,%r14
 	brasl	%r14,__do_syscall
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	mvc	__LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
 	BPON
 	LBEAR	STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
@@ -277,7 +276,6 @@ SYM_CODE_START(ret_from_fork)
 	brasl	%r14,__ret_from_fork
 	STACKLEAK_ERASE
 	GET_LC	%r13
-	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	mvc	__LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
 	BPON
 	LBEAR	STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
@@ -298,10 +296,7 @@ SYM_CODE_START(pgm_check_handler)
 	lmg	%r8,%r9,__LC_PGM_OLD_PSW(%r13)
 	xgr	%r10,%r10
 	tmhh	%r8,0x0001		# coming from user space?
-	jno	.Lpgm_skip_asce
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
-	j	3f			# -> fault in user space
-.Lpgm_skip_asce:
+	jo	3f			# -> fault in user space
 #if IS_ENABLED(CONFIG_KVM)
 	lg	%r11,__LC_CURRENT(%r13)
 	tm	__TI_sie(%r11),0xff
@@ -315,7 +310,7 @@ SYM_CODE_START(pgm_check_handler)
 	tm	__LC_PGM_ILC+3(%r13),0x80	# check for per exception
 	jnz	.Lpgm_svcper		# -> single stepped svc
 2:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	# CHECK_VMAP_STACK branches to stack_overflow or 4f
+	# CHECK_VMAP_STACK branches to stack_invalid or 4f
 	CHECK_VMAP_STACK __LC_SAVE_AREA,%r13,4f
 3:	lg	%r15,__LC_KERNEL_STACK(%r13)
 4:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
@@ -339,7 +334,6 @@ SYM_CODE_START(pgm_check_handler)
 	tmhh	%r8,0x0001		# returning to user space?
 	jno	.Lpgm_exit_kernel
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	BPON
 	stpt	__LC_EXIT_TIMER(%r13)
 .Lpgm_exit_kernel:
@@ -383,8 +377,7 @@ SYM_CODE_START(\name)
 #endif
 0:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	2f
-1:	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
-	lg	%r15,__LC_KERNEL_STACK(%r13)
+1:	lg	%r15,__LC_KERNEL_STACK(%r13)
 2:	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
@@ -407,7 +400,6 @@ SYM_CODE_START(\name)
 	tmhh	%r8,0x0001		# returning to user ?
 	jno	2f
 	STACKLEAK_ERASE
-	lctlg	%c1,%c1,__LC_USER_ASCE(%r13)
 	BPON
 	stpt	__LC_EXIT_TIMER(%r13)
 2:	LBEAR	__PT_LAST_BREAK(%r11)
@@ -467,7 +459,7 @@ SYM_CODE_START(mcck_int_handler)
 	clgrjl	%r9,%r14, 4f
 	larl	%r14,.Lsie_leave
 	clgrjhe	%r9,%r14, 4f
-	lg	%r10,__LC_PCPU
+	lg	%r10,__LC_PCPU(%r13)
 	oi	__PCPU_FLAGS+7(%r10), _CIF_MCCK_GUEST
 4:	BPENTER	__SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
 	SIEEXIT __SF_SIE_CONTROL(%r15),%r13
@@ -475,8 +467,6 @@ SYM_CODE_START(mcck_int_handler)
 .Lmcck_user:
 	lg	%r15,__LC_MCCK_STACK(%r13)
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
-	stctg	%c1,%c1,__PT_CR1(%r11)
-	lctlg	%c1,%c1,__LC_KERNEL_ASCE(%r13)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lay	%r14,__LC_GPREGS_SAVE_AREA(%r13)
 	mvc	__PT_R0(128,%r11),0(%r14)
@@ -494,7 +484,6 @@ SYM_CODE_START(mcck_int_handler)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,s390_do_machine_check
-	lctlg	%c1,%c1,__PT_CR1(%r11)
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_MCCK_PSW(16,%r13),__PT_PSW(%r11) # move return PSW
 	tm	__LC_RETURN_MCCK_PSW+1(%r13),0x01 # returning to user ?
@@ -590,22 +579,23 @@ SYM_CODE_END(early_pgm_check_handler)
 	.section .kprobes.text, "ax"
 
 /*
- * The synchronous or the asynchronous stack overflowed. We are dead.
+ * The synchronous or the asynchronous stack pointer is invalid. We are dead.
  * No need to properly save the registers, we are going to panic anyway.
  * Setup a pt_regs so that show_trace can provide a good call trace.
  */
-SYM_CODE_START(stack_overflow)
+SYM_CODE_START(stack_invalid)
 	GET_LC	%r15
 	lg	%r15,__LC_NODAT_STACK(%r15) # change to panic stack
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	mvc	__PT_R8(64,%r11),0(%r14)
-	stg	%r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
+	GET_LC	%r2
+	mvc	__PT_ORIG_GPR2(8,%r11),__LC_PGM_LAST_BREAK(%r2)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
-	jg	kernel_stack_overflow
-SYM_CODE_END(stack_overflow)
+	jg	kernel_stack_invalid
+SYM_CODE_END(stack_invalid)
 
 	.section .data, "aw"
 	.balign	4
@@ -621,7 +611,7 @@ SYM_DATA_END(daton_psw)
 	.balign	8
 #define SYSCALL(esame,emu)	.quad __s390x_ ## esame
 SYM_DATA_START(sys_call_table)
-#include "asm/syscall_table.h"
+#include <asm/syscall_table.h>
 SYM_DATA_END(sys_call_table)
 #undef SYSCALL
 
@@ -629,7 +619,7 @@ SYM_DATA_END(sys_call_table)
 
 #define SYSCALL(esame,emu)	.quad __s390_ ## emu
 SYM_DATA_START(sys_call_table_emu)
-#include "asm/syscall_table.h"
+#include <asm/syscall_table.h>
 SYM_DATA_END(sys_call_table_emu)
 #undef SYSCALL
 #endif
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index a1f28879c87e..dd55cc6bbc28 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -31,7 +31,7 @@ void do_secure_storage_access(struct pt_regs *regs);
 void do_non_secure_storage_access(struct pt_regs *regs);
 void do_secure_storage_violation(struct pt_regs *regs);
 void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
-void kernel_stack_overflow(struct pt_regs * regs);
+void kernel_stack_invalid(struct pt_regs *regs);
 void handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 		     struct pt_regs *regs);
 
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 63ba6306632e..e94bb98f5231 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/kmsan-checks.h>
+#include <linux/cpufeature.h>
 #include <linux/kprobes.h>
 #include <linux/execmem.h>
 #include <trace/syscall.h>
@@ -69,7 +70,7 @@ static const char *ftrace_shared_hotpatch_trampoline(const char **end)
 
 bool ftrace_need_init_nop(void)
 {
-	return !MACHINE_HAS_SEQ_INSN;
+	return !cpu_has_seq_insn();
 }
 
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
@@ -189,7 +190,7 @@ static int ftrace_modify_trampoline_call(struct dyn_ftrace *rec,
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
-	if (MACHINE_HAS_SEQ_INSN)
+	if (cpu_has_seq_insn())
 		return ftrace_patch_branch_insn(rec->ip, old_addr, addr);
 	else
 		return ftrace_modify_trampoline_call(rec, old_addr, addr);
@@ -213,8 +214,8 @@ static int ftrace_patch_branch_mask(void *addr, u16 expected, bool enable)
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
-	/* Expect brcl 0xf,... for the !MACHINE_HAS_SEQ_INSN case */
-	if (MACHINE_HAS_SEQ_INSN)
+	/* Expect brcl 0xf,... for the !cpu_has_seq_insn() case */
+	if (cpu_has_seq_insn())
 		return ftrace_patch_branch_insn(rec->ip, addr, 0);
 	else
 		return ftrace_patch_branch_mask((void *)rec->ip, 0xc0f4, false);
@@ -234,7 +235,7 @@ static int ftrace_make_trampoline_call(struct dyn_ftrace *rec, unsigned long add
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	if (MACHINE_HAS_SEQ_INSN)
+	if (cpu_has_seq_insn())
 		return ftrace_patch_branch_insn(rec->ip, 0, addr);
 	else
 		return ftrace_make_trampoline_call(rec, addr);
@@ -266,12 +267,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+	unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
-	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+	if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
 		*parent = (unsigned long)&return_to_handler;
 }
 
diff --git a/arch/s390/kernel/guarded_storage.c b/arch/s390/kernel/guarded_storage.c
index 0b68168d9566..cf26d7a37425 100644
--- a/arch/s390/kernel/guarded_storage.c
+++ b/arch/s390/kernel/guarded_storage.c
@@ -4,6 +4,7 @@
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
+#include <linux/cpufeature.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/signal.h>
@@ -109,7 +110,7 @@ static int gs_broadcast(void)
 SYSCALL_DEFINE2(s390_guarded_storage, int, command,
 		struct gs_cb __user *, gs_cb)
 {
-	if (!MACHINE_HAS_GS)
+	if (!cpu_has_gs())
 		return -EOPNOTSUPP;
 	switch (command) {
 	case GS_ENABLE:
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 396034b2fe67..7edb9ded199c 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -18,12 +18,10 @@
 
 __HEAD
 SYM_CODE_START(startup_continue)
-	larl	%r1,tod_clock_base
-	GET_LC	%r2
-	mvc	0(16,%r1),__LC_BOOT_CLOCK(%r2)
 #
 # Setup stack
 #
+	GET_LC	%r2
 	larl	%r14,init_task
 	stg	%r14,__LC_CURRENT(%r2)
 	larl	%r15,init_thread_union+STACK_INIT_OFFSET
diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c
index 7857a7e8e56c..e7b66d046e8d 100644
--- a/arch/s390/kernel/hiperdispatch.c
+++ b/arch/s390/kernel/hiperdispatch.c
@@ -45,6 +45,7 @@
  * therefore delaying the throughput loss caused by using SMP threads.
  */
 
+#include <linux/cpufeature.h>
 #include <linux/cpumask.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
@@ -87,7 +88,7 @@ static DECLARE_DELAYED_WORK(hd_capacity_work, hd_capacity_work_fn);
 
 static int hd_set_hiperdispatch_mode(int enable)
 {
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		enable = 0;
 	if (hd_enabled == enable)
 		return 0;
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 69be2309cde0..ff15f91affde 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -22,6 +22,7 @@
 #include <linux/debug_locks.h>
 #include <linux/vmalloc.h>
 #include <asm/asm-extable.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/ipl.h>
 #include <asm/smp.h>
@@ -185,7 +186,7 @@ static inline int __diag308(unsigned long subcode, unsigned long addr)
 
 	r1.even = addr;
 	r1.odd	= 0;
-	asm volatile(
+	asm_inline volatile(
 		"	diag	%[r1],%[subcode],0x308\n"
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b,0b)
@@ -269,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj,	\
 {									\
 	if (len >= sizeof(_value))					\
 		return -E2BIG;						\
-	len = strscpy(_value, buf, sizeof(_value));			\
+	len = strscpy(_value, buf);					\
 	if ((ssize_t)len < 0)						\
 		return len;						\
 	strim(_value);							\
@@ -685,7 +686,7 @@ static int __init ipl_init(void)
 		goto out;
 	switch (ipl_info.type) {
 	case IPL_TYPE_CCW:
-		if (MACHINE_IS_VM)
+		if (machine_is_vm())
 			rc = sysfs_create_group(&ipl_kset->kobj,
 						&ipl_ccw_attr_group_vm);
 		else
@@ -1272,7 +1273,7 @@ static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
 	ipb->ccw.flags = IPL_PB0_FLAG_LOADPARM;
 
 	/* VM PARM */
-	if (MACHINE_IS_VM && ipl_block_valid &&
+	if (machine_is_vm() && ipl_block_valid &&
 	    (ipl_block.ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP)) {
 
 		ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
@@ -1286,7 +1287,7 @@ static int __init reipl_nss_init(void)
 {
 	int rc;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 0;
 
 	reipl_block_nss = (void *) get_zeroed_page(GFP_KERNEL);
@@ -1311,8 +1312,8 @@ static int __init reipl_ccw_init(void)
 		return -ENOMEM;
 
 	rc = sysfs_create_group(&reipl_kset->kobj,
-				MACHINE_IS_VM ? &reipl_ccw_attr_group_vm
-					      : &reipl_ccw_attr_group_lpar);
+				machine_is_vm() ? &reipl_ccw_attr_group_vm
+						: &reipl_ccw_attr_group_lpar);
 	if (rc)
 		return rc;
 
@@ -1987,7 +1988,7 @@ static void vmcmd_run(struct shutdown_trigger *trigger)
 
 static int vmcmd_init(void)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return -EOPNOTSUPP;
 	vmcmd_kset = kset_create_and_add("vmcmd", NULL, firmware_kobj);
 	if (!vmcmd_kset)
@@ -2248,26 +2249,28 @@ static int __init s390_ipl_init(void)
 
 __initcall(s390_ipl_init);
 
-static void __init strncpy_skip_quote(char *dst, char *src, int n)
+static void __init strscpy_skip_quote(char *dst, char *src, int n)
 {
 	int sx, dx;
 
-	dx = 0;
-	for (sx = 0; src[sx] != 0; sx++) {
+	if (!n)
+		return;
+	for (sx = 0, dx = 0; src[sx]; sx++) {
 		if (src[sx] == '"')
 			continue;
-		dst[dx++] = src[sx];
-		if (dx >= n)
+		dst[dx] = src[sx];
+		if (dx + 1 == n)
 			break;
+		dx++;
 	}
+	dst[dx] = '\0';
 }
 
 static int __init vmcmd_on_reboot_setup(char *str)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 1;
-	strncpy_skip_quote(vmcmd_on_reboot, str, VMCMD_MAX_SIZE);
-	vmcmd_on_reboot[VMCMD_MAX_SIZE] = 0;
+	strscpy_skip_quote(vmcmd_on_reboot, str, sizeof(vmcmd_on_reboot));
 	on_reboot_trigger.action = &vmcmd_action;
 	return 1;
 }
@@ -2275,10 +2278,9 @@ __setup("vmreboot=", vmcmd_on_reboot_setup);
 
 static int __init vmcmd_on_panic_setup(char *str)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 1;
-	strncpy_skip_quote(vmcmd_on_panic, str, VMCMD_MAX_SIZE);
-	vmcmd_on_panic[VMCMD_MAX_SIZE] = 0;
+	strscpy_skip_quote(vmcmd_on_panic, str, sizeof(vmcmd_on_panic));
 	on_panic_trigger.action = &vmcmd_action;
 	return 1;
 }
@@ -2286,10 +2288,9 @@ __setup("vmpanic=", vmcmd_on_panic_setup);
 
 static int __init vmcmd_on_halt_setup(char *str)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 1;
-	strncpy_skip_quote(vmcmd_on_halt, str, VMCMD_MAX_SIZE);
-	vmcmd_on_halt[VMCMD_MAX_SIZE] = 0;
+	strscpy_skip_quote(vmcmd_on_halt, str, sizeof(vmcmd_on_halt));
 	on_halt_trigger.action = &vmcmd_action;
 	return 1;
 }
@@ -2297,10 +2298,9 @@ __setup("vmhalt=", vmcmd_on_halt_setup);
 
 static int __init vmcmd_on_poff_setup(char *str)
 {
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return 1;
-	strncpy_skip_quote(vmcmd_on_poff, str, VMCMD_MAX_SIZE);
-	vmcmd_on_poff[VMCMD_MAX_SIZE] = 0;
+	strscpy_skip_quote(vmcmd_on_poff, str, sizeof(vmcmd_on_poff));
 	on_poff_trigger.action = &vmcmd_action;
 	return 1;
 }
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index ef7be599e1f7..bdf9c7cb5685 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/kernel_stat.h>
+#include <linux/cpufeature.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
@@ -25,6 +26,7 @@
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
 #include <asm/stacktrace.h>
@@ -84,7 +86,6 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
 	{.irq = IRQIO_TAP,  .name = "TAP", .desc = "[I/O] Tape"},
 	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
-	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
 	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
 	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
@@ -149,7 +150,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	if (user_mode(regs)) {
 		update_timer_sys();
-		if (static_branch_likely(&cpu_has_bear))
+		if (cpu_has_bear())
 			current->thread.last_break = regs->last_break;
 	}
 
@@ -164,7 +165,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			do_irq_async(regs, THIN_INTERRUPT);
 		else
 			do_irq_async(regs, IO_INTERRUPT);
-	} while (MACHINE_IS_LPAR && irq_pending(regs));
+	} while (machine_is_lpar() && irq_pending(regs));
 
 	irq_exit_rcu();
 
@@ -185,7 +186,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 
 	if (user_mode(regs)) {
 		update_timer_sys();
-		if (static_branch_likely(&cpu_has_bear))
+		if (cpu_has_bear())
 			current->thread.last_break = regs->last_break;
 	}
 
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 8b80ea57125f..c450120b4474 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -13,6 +13,7 @@
 #include <linux/ptrace.h>
 #include <linux/preempt.h>
 #include <linux/stop_machine.h>
+#include <linux/cpufeature.h>
 #include <linux/kdebug.h>
 #include <linux/uaccess.h>
 #include <linux/extable.h>
@@ -153,7 +154,7 @@ void arch_arm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
 
-	if (MACHINE_HAS_SEQ_INSN) {
+	if (cpu_has_seq_insn()) {
 		swap_instruction(&args);
 		text_poke_sync();
 	} else {
@@ -166,7 +167,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
 
-	if (MACHINE_HAS_SEQ_INSN) {
+	if (cpu_has_seq_insn()) {
 		swap_instruction(&args);
 		text_poke_sync();
 	} else {
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 8f681ccfb83a..baeb3dcfc1c8 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -13,7 +13,9 @@
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
 #include <linux/debug_locks.h>
+#include <linux/cpufeature.h>
 #include <asm/guarded_storage.h>
+#include <asm/machine.h>
 #include <asm/pfault.h>
 #include <asm/cio.h>
 #include <asm/fpu.h>
@@ -94,7 +96,7 @@ static noinline void __machine_kdump(void *image)
 	mcesa = __va(get_lowcore()->mcesad & MCESA_ORIGIN_MASK);
 	if (cpu_has_vx())
 		save_vx_regs((__vector128 *) mcesa->vector_save_area);
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		local_ctl_store(2, &cr2_old.reg);
 		cr2_new = cr2_old;
 		cr2_new.gse = 1;
@@ -178,7 +180,7 @@ void arch_kexec_unprotect_crashkres(void)
 static int machine_kexec_prepare_kdump(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	if (MACHINE_IS_VM)
+	if (machine_is_vm())
 		diag10_range(PFN_DOWN(crashk_res.start),
 			     PFN_DOWN(crashk_res.end - crashk_res.start + 1));
 	return 0;
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index fbd218b6fc8e..3da371c144eb 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/kernel_stat.h>
+#include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/entry-common.h>
@@ -45,7 +46,7 @@ static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
 
 static inline int nmi_needs_mcesa(void)
 {
-	return cpu_has_vx() || MACHINE_HAS_GS;
+	return cpu_has_vx() || cpu_has_gs();
 }
 
 /*
@@ -61,7 +62,7 @@ void __init nmi_alloc_mcesa_early(u64 *mcesad)
 	if (!nmi_needs_mcesa())
 		return;
 	*mcesad = __pa(&boot_mcesa);
-	if (MACHINE_HAS_GS)
+	if (cpu_has_gs())
 		*mcesad |= ilog2(MCESA_MAX_SIZE);
 }
 
@@ -73,14 +74,14 @@ int nmi_alloc_mcesa(u64 *mcesad)
 	*mcesad = 0;
 	if (!nmi_needs_mcesa())
 		return 0;
-	size = MACHINE_HAS_GS ? MCESA_MAX_SIZE : MCESA_MIN_SIZE;
+	size = cpu_has_gs() ? MCESA_MAX_SIZE : MCESA_MIN_SIZE;
 	origin = kmalloc(size, GFP_KERNEL);
 	if (!origin)
 		return -ENOMEM;
 	/* The pointer is stored with mcesa_bits ORed in */
 	kmemleak_not_leak(origin);
 	*mcesad = __pa(origin);
-	if (MACHINE_HAS_GS)
+	if (cpu_has_gs())
 		*mcesad |= ilog2(MCESA_MAX_SIZE);
 	return 0;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 33205dd410e4..6a262e198e35 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -442,7 +442,7 @@ static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset)
 			ctrset_size = 48;
 		else if (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5)
 			ctrset_size = 128;
-		else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7)
+		else if (cpumf_ctr_info.csvn >= 6 && cpumf_ctr_info.csvn <= 8)
 			ctrset_size = 160;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
@@ -858,18 +858,13 @@ static int cpumf_pmu_event_type(struct perf_event *event)
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
 	unsigned int type = event->attr.type;
-	int err;
+	int err = -ENOENT;
 
 	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
 		err = __hw_perf_event_init(event, type);
 	else if (event->pmu->type == type)
 		/* Registered as unknown PMU */
 		err = __hw_perf_event_init(event, cpumf_pmu_event_type(event));
-	else
-		return -ENOENT;
-
-	if (unlikely(err) && event->destroy)
-		event->destroy(event);
 
 	return err;
 }
@@ -985,8 +980,6 @@ static int cfdiag_push_sample(struct perf_event *event,
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);
-	if (overflow)
-		event->pmu->stop(event, 0);
 
 	perf_event_update_userpage(event);
 	return overflow;
@@ -1819,8 +1812,6 @@ static int cfdiag_event_init(struct perf_event *event)
 	event->destroy = hw_perf_event_destroy;
 
 	err = cfdiag_event_init2(event);
-	if (unlikely(err))
-		event->destroy(event);
 out:
 	return err;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index e4a6bfc91080..7ace1f9e4ccf 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -237,7 +237,6 @@ CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
 CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
 CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-
 CPUMF_EVENT_ATTR(cf_z15, L1D_RO_EXCL_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z15, DTLB2_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z15, DTLB2_MISSES, 0x0082);
@@ -291,8 +290,8 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_NO_SPECIAL, 0x00f4);
 CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x0108);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x0109);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 CPUMF_EVENT_ATTR(cf_z16, L1D_RO_EXCL_WRITES, 0x0080);
@@ -365,6 +364,83 @@ CPUMF_EVENT_ATTR(cf_z16, NNPA_WAIT_LOCK, 0x010d);
 CPUMF_EVENT_ATTR(cf_z16, NNPA_HOLD_LOCK, 0x010e);
 CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
+CPUMF_EVENT_ATTR(cf_z17, L1D_RO_EXCL_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z17, CRSTE_1MB_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_GPAGE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_MISSES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_PTE_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_CRSTE_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_ENGINES_BUSY, 0x008b);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TEND, 0x008c);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TEND, 0x008d);
+CPUMF_EVENT_ATTR(cf_z17, L1C_TLB2_MISSES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ, 0x0091);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_IV, 0x0092);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_CHIP_HIT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_DRAWER_HIT, 0x0094);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP, 0x0095);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_CHIP_HIT, 0x0097);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT, 0x0098);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE, 0x0099);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER, 0x009a);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER, 0x009b);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_MEMORY, 0x009c);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE_MEMORY, 0x009d);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER_MEMORY, 0x009e);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER_MEMORY, 0x009f);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT, 0x00a1);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT, 0x00a2);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_IV, 0x00a3);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT, 0x00a4);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT, 0x00a5);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_IV, 0x00a6);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT, 0x00a7);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT, 0x00a8);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ, 0x00a9);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_IV, 0x00aa);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_CHIP_HIT, 0x00ab);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_DRAWER_HIT, 0x00ac);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP, 0x00ad);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_IV, 0x00ae);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_CHIP_HIT, 0x00af);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT, 0x00b0);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_MODULE, 0x00b1);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_DRAWER, 0x00b2);
+CPUMF_EVENT_ATTR(cf_z17, ICW_OFF_DRAWER, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_SAMETHRD, 0x00ca);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_DIFFTHRD, 0x00cb);
+CPUMF_EVENT_ATTR(cf_z17, INST_SAMETHRD, 0x00cc);
+CPUMF_EVENT_ATTR(cf_z17, INST_DIFFTHRD, 0x00cd);
+CPUMF_EVENT_ATTR(cf_z17, WRONG_BRANCH_PREDICTION, 0x00ce);
+CPUMF_EVENT_ATTR(cf_z17, VX_BCD_EXECUTION_SLOTS, 0x00e1);
+CPUMF_EVENT_ATTR(cf_z17, DECIMAL_INSTRUCTIONS, 0x00e2);
+CPUMF_EVENT_ATTR(cf_z17, LAST_HOST_TRANSLATIONS, 0x00e8);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TABORT, 0x00f4);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_NO_SPECIAL, 0x00f5);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_SPECIAL, 0x00f6);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_ACCESS, 0x00f8);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CYCLES, 0x00fd);
+CPUMF_EVENT_ATTR(cf_z17, SORTL, 0x0100);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CC, 0x0109);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CCFINISH, 0x010a);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INVOCATIONS, 0x010b);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPLETIONS, 0x010c);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_WAIT_LOCK, 0x010d);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_HOLD_LOCK, 0x010e);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_ONCHIP, 0x0110);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_OFFCHIP, 0x0111);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_DIFF, 0x0112);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_4K_PREFETCH, 0x0114);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPL_LOCK, 0x0115);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK, 0x0116);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO, 0x0117);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
 static struct attribute *cpumcf_fvn1_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_fvn1, CPU_CYCLES),
@@ -414,7 +490,7 @@ static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
-static struct attribute *cpumcf_svn_67_pmu_event_attr[] __initdata = {
+static struct attribute *cpumcf_svn_678_pmu_event_attr[] __initdata = {
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
 	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
@@ -779,6 +855,87 @@ static struct attribute *cpumcf_z16_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
+static struct attribute *cpumcf_z17_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z17, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, CRSTE_1MB_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, DTLB2_GPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, ITLB2_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, ITLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z17, TLB2_ENGINES_BUSY),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TEND),
+	CPUMF_EVENT_PTR(cf_z17, TX_NC_TEND),
+	CPUMF_EVENT_PTR(cf_z17, L1C_TLB2_MISSES),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_IV),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_REQ_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_IV),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER_MEMORY),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_IV),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_IV),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_REQ_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_IV),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_CHIP_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_MODULE),
+	CPUMF_EVENT_PTR(cf_z17, ICW_ON_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, ICW_OFF_DRAWER),
+	CPUMF_EVENT_PTR(cf_z17, CYCLES_SAMETHRD),
+	CPUMF_EVENT_PTR(cf_z17, CYCLES_DIFFTHRD),
+	CPUMF_EVENT_PTR(cf_z17, INST_SAMETHRD),
+	CPUMF_EVENT_PTR(cf_z17, INST_DIFFTHRD),
+	CPUMF_EVENT_PTR(cf_z17, WRONG_BRANCH_PREDICTION),
+	CPUMF_EVENT_PTR(cf_z17, VX_BCD_EXECUTION_SLOTS),
+	CPUMF_EVENT_PTR(cf_z17, DECIMAL_INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf_z17, LAST_HOST_TRANSLATIONS),
+	CPUMF_EVENT_PTR(cf_z17, TX_NC_TABORT),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_NO_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_SPECIAL),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_ACCESS),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CYCLES),
+	CPUMF_EVENT_PTR(cf_z17, SORTL),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CC),
+	CPUMF_EVENT_PTR(cf_z17, DFLT_CCFINISH),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INVOCATIONS),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_COMPLETIONS),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_WAIT_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_HOLD_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_ONCHIP),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_OFFCHIP),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_INST_DIFF),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_4K_PREFETCH),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_COMPL_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK),
+	CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO),
+	CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
+	CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
+	NULL,
+};
+
 /* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
 
 static struct attribute_group cpumcf_pmu_events_group = {
@@ -859,7 +1016,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	if (ci.csvn >= 1 && ci.csvn <= 5)
 		csvn = cpumcf_svn_12345_pmu_event_attr;
 	else if (ci.csvn >= 6)
-		csvn = cpumcf_svn_67_pmu_event_attr;
+		csvn = cpumcf_svn_678_pmu_event_attr;
 
 	/* Determine model-specific counter set(s) */
 	get_cpu_id(&cpu_id);
@@ -892,6 +1049,10 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	case 0x3932:
 		model = cpumcf_z16_pmu_event_attr;
 		break;
+	case 0x9175:
+	case 0x9176:
+		model = cpumcf_z17_pmu_event_attr;
+		break;
 	default:
 		model = none;
 		break;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 5f60248cb468..91469401f2c9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -885,9 +885,6 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 		event->attr.exclude_idle = 0;
 
 	err = __hw_perf_event_init(event);
-	if (unlikely(err))
-		if (event->destroy)
-			event->destroy(event);
 	return err;
 }
 
@@ -1075,10 +1072,7 @@ static int perf_push_sample(struct perf_event *event,
 	overflow = 0;
 	if (perf_event_exclude(event, &regs, sde_regs))
 		goto out;
-	if (perf_event_overflow(event, &data, &regs)) {
-		overflow = 1;
-		event->pmu->stop(event, 0);
-	}
+	overflow = perf_event_overflow(event, &data, &regs);
 	perf_event_update_userpage(event);
 out:
 	return overflow;
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 10725f5a6f0f..63875270941b 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -518,7 +518,8 @@ static void paicrypt_have_samples(void)
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event CRYPTO_ALL is allowed.
  */
-static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				struct task_struct *task, bool sched_in)
 {
 	/* We started with a clean page on event installation. So read out
 	 * results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index a8f0bad99cf0..fd14d5ebccbc 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -542,7 +542,8 @@ static void paiext_have_samples(void)
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event NNPA_ALL is allowed.
  */
-static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			      struct task_struct *task, bool sched_in)
 {
 	/* We started with a clean page on event installation. So read out
 	 * results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5ce9a795a0fe..11f70c1e2797 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -8,6 +8,7 @@
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
 #include <linux/stop_machine.h>
+#include <linux/cpufeature.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/random.h>
@@ -19,6 +20,7 @@
 #include <linux/cpu.h>
 #include <linux/smp.h>
 #include <asm/text-patching.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/facility.h>
 #include <asm/elf.h>
@@ -72,7 +74,7 @@ void notrace stop_machine_yield(const struct cpumask *cpumask)
 	this_cpu = smp_processor_id();
 	if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
 		__this_cpu_write(cpu_relax_retry, 0);
-		cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+		cpu = cpumask_next_wrap(this_cpu, cpumask);
 		if (cpu >= nr_cpu_ids)
 			return;
 		if (arch_vcpu_is_preempted(cpu))
@@ -209,14 +211,14 @@ static int __init setup_hwcaps(void)
 		elf_hwcap |= HWCAP_DFP;
 
 	/* huge page support */
-	if (MACHINE_HAS_EDAT1)
+	if (cpu_has_edat1())
 		elf_hwcap |= HWCAP_HPAGE;
 
 	/* 64-bit register support for 31-bit processes */
 	elf_hwcap |= HWCAP_HIGH_GPRS;
 
 	/* transactional execution */
-	if (MACHINE_HAS_TE)
+	if (machine_has_tx())
 		elf_hwcap |= HWCAP_TE;
 
 	/* vector */
@@ -244,10 +246,10 @@ static int __init setup_hwcaps(void)
 		elf_hwcap |= HWCAP_NNPA;
 
 	/* guarded storage */
-	if (MACHINE_HAS_GS)
+	if (cpu_has_gs())
 		elf_hwcap |= HWCAP_GS;
 
-	if (MACHINE_HAS_PCI_MIO)
+	if (test_machine_feature(MFEATURE_PCI_MIO))
 		elf_hwcap |= HWCAP_PCI_MIO;
 
 	/* virtualization support */
@@ -266,31 +268,35 @@ static int __init setup_elf_platform(void)
 	add_device_randomness(&cpu_id, sizeof(cpu_id));
 	switch (cpu_id.machine) {
 	default:	/* Use "z10" as default. */
-		strcpy(elf_platform, "z10");
+		strscpy(elf_platform, "z10");
 		break;
 	case 0x2817:
 	case 0x2818:
-		strcpy(elf_platform, "z196");
+		strscpy(elf_platform, "z196");
 		break;
 	case 0x2827:
 	case 0x2828:
-		strcpy(elf_platform, "zEC12");
+		strscpy(elf_platform, "zEC12");
 		break;
 	case 0x2964:
 	case 0x2965:
-		strcpy(elf_platform, "z13");
+		strscpy(elf_platform, "z13");
 		break;
 	case 0x3906:
 	case 0x3907:
-		strcpy(elf_platform, "z14");
+		strscpy(elf_platform, "z14");
 		break;
 	case 0x8561:
 	case 0x8562:
-		strcpy(elf_platform, "z15");
+		strscpy(elf_platform, "z15");
 		break;
 	case 0x3931:
 	case 0x3932:
-		strcpy(elf_platform, "z16");
+		strscpy(elf_platform, "z16");
+		break;
+	case 0x9175:
+	case 0x9176:
+		strscpy(elf_platform, "z17");
 		break;
 	}
 	return 0;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 1cfed8b710b8..e1240f6b29fa 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -7,10 +7,10 @@
  *               Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
-#include "asm/ptrace.h"
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/cpufeature.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
@@ -31,6 +31,9 @@
 #include <asm/unistd.h>
 #include <asm/runtime_instr.h>
 #include <asm/facility.h>
+#include <asm/machine.h>
+#include <asm/ptrace.h>
+#include <asm/rwonce.h>
 #include <asm/fpu.h>
 
 #include "entry.h"
@@ -60,7 +63,7 @@ void update_cr_regs(struct task_struct *task)
 	cr0_new = cr0_old;
 	cr2_new = cr2_old;
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE) {
+	if (machine_has_tx()) {
 		/* Set or clear transaction execution TXC bit 8. */
 		cr0_new.tcx = 1;
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
@@ -75,7 +78,7 @@ void update_cr_regs(struct task_struct *task)
 		}
 	}
 	/* Take care of enable/disable of guarded storage. */
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		cr2_new.gse = 0;
 		if (task->thread.gs_cb)
 			cr2_new.gse = 1;
@@ -470,18 +473,18 @@ long arch_ptrace(struct task_struct *child, long request,
 	case PTRACE_GET_LAST_BREAK:
 		return put_user(child->thread.last_break, (unsigned long __user *)data);
 	case PTRACE_ENABLE_TE:
-		if (!MACHINE_HAS_TE)
+		if (!machine_has_tx())
 			return -EIO;
 		child->thread.per_flags &= ~PER_FLAG_NO_TE;
 		return 0;
 	case PTRACE_DISABLE_TE:
-		if (!MACHINE_HAS_TE)
+		if (!machine_has_tx())
 			return -EIO;
 		child->thread.per_flags |= PER_FLAG_NO_TE;
 		child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND;
 		return 0;
 	case PTRACE_TE_ABORT_RAND:
-		if (!MACHINE_HAS_TE || (child->thread.per_flags & PER_FLAG_NO_TE))
+		if (!machine_has_tx() || (child->thread.per_flags & PER_FLAG_NO_TE))
 			return -EIO;
 		switch (data) {
 		case 0UL:
@@ -1033,7 +1036,7 @@ static int s390_gs_cb_get(struct task_struct *target,
 {
 	struct gs_cb *data = target->thread.gs_cb;
 
-	if (!MACHINE_HAS_GS)
+	if (!cpu_has_gs())
 		return -ENODEV;
 	if (!data)
 		return -ENODATA;
@@ -1050,7 +1053,7 @@ static int s390_gs_cb_set(struct task_struct *target,
 	struct gs_cb gs_cb = { }, *data = NULL;
 	int rc;
 
-	if (!MACHINE_HAS_GS)
+	if (!cpu_has_gs())
 		return -ENODEV;
 	if (!target->thread.gs_cb) {
 		data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -1087,7 +1090,7 @@ static int s390_gs_bc_get(struct task_struct *target,
 {
 	struct gs_cb *data = target->thread.gs_bc_cb;
 
-	if (!MACHINE_HAS_GS)
+	if (!cpu_has_gs())
 		return -ENODEV;
 	if (!data)
 		return -ENODATA;
@@ -1101,7 +1104,7 @@ static int s390_gs_bc_set(struct task_struct *target,
 {
 	struct gs_cb *data = target->thread.gs_bc_cb;
 
-	if (!MACHINE_HAS_GS)
+	if (!cpu_has_gs())
 		return -ENODEV;
 	if (!data) {
 		data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -1521,13 +1524,6 @@ static const char *gpr_names[NUM_GPRS] = {
 	"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
 };
 
-unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
-{
-	if (offset >= NUM_GPRS)
-		return 0;
-	return regs->gprs[offset];
-}
-
 int regs_query_register_offset(const char *name)
 {
 	unsigned long offset;
@@ -1547,29 +1543,3 @@ const char *regs_query_register_name(unsigned int offset)
 		return NULL;
 	return gpr_names[offset];
 }
-
-static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
-{
-	unsigned long ksp = kernel_stack_pointer(regs);
-
-	return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
-}
-
-/**
- * regs_get_kernel_stack_nth() - get Nth entry of the stack
- * @regs:pt_regs which contains kernel stack pointer.
- * @n:stack entry number.
- *
- * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
- * this returns 0.
- */
-unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
-{
-	unsigned long addr;
-
-	addr = kernel_stack_pointer(regs) + n * sizeof(long);
-	if (!regs_within_kernel_stack(regs, addr))
-		return 0;
-	return *(unsigned long *)addr;
-}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d78bcfe707b5..f244c5560e7f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -54,6 +54,7 @@
 
 #include <asm/archrandom.h>
 #include <asm/boot_data.h>
+#include <asm/machine.h>
 #include <asm/ipl.h>
 #include <asm/facility.h>
 #include <asm/smp.h>
@@ -180,8 +181,6 @@ unsigned long __bootdata_preserved(MODULES_END);
 struct lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
 
-DEFINE_STATIC_KEY_FALSE(cpu_has_bear);
-
 /*
  * The Write Back bit position in the physaddr is given by the SLPC PCI.
  * Leaving the mask zero always uses write through which is safe
@@ -251,7 +250,7 @@ static void __init conmode_default(void)
 	char query_buffer[1024];
 	char *ptr;
 
-        if (MACHINE_IS_VM) {
+	if (machine_is_vm()) {
 		cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL);
 		console_devno = simple_strtoul(query_buffer + 5, NULL, 16);
 		ptr = strstr(query_buffer, "SUBCHANNEL =");
@@ -289,7 +288,7 @@ static void __init conmode_default(void)
 			SET_CONSOLE_SCLP;
 #endif
 		}
-	} else if (MACHINE_IS_KVM) {
+	} else if (machine_is_kvm()) {
 		if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
 			SET_CONSOLE_VT220;
 		else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
@@ -415,7 +414,6 @@ static void __init setup_lowcore(void)
 	lc->clock_comparator = clock_comparator_max;
 	lc->current_task = (unsigned long)&init_task;
 	lc->lpp = LPP_MAGIC;
-	lc->machine_flags = get_lowcore()->machine_flags;
 	lc->preempt_count = get_lowcore()->preempt_count;
 	nmi_alloc_mcesa_early(&lc->mcesad);
 	lc->sys_enter_timer = get_lowcore()->sys_enter_timer;
@@ -652,7 +650,7 @@ static void __init reserve_crashkernel(void)
 		return;
 	}
 
-	if (!oldmem_data.start && MACHINE_IS_VM)
+	if (!oldmem_data.start && machine_is_vm())
 		diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
@@ -898,12 +896,12 @@ void __init setup_arch(char **cmdline_p)
         /*
          * print what head.S has found out about the machine
          */
-	if (MACHINE_IS_VM)
+	if (machine_is_vm())
 		pr_info("Linux is running as a z/VM "
 			"guest operating system in 64-bit mode\n");
-	else if (MACHINE_IS_KVM)
+	else if (machine_is_kvm())
 		pr_info("Linux is running under KVM in 64-bit mode\n");
-	else if (MACHINE_IS_LPAR)
+	else if (machine_is_lpar())
 		pr_info("Linux is running natively in 64-bit mode\n");
 	else
 		pr_info("Linux is running as a guest in 64-bit mode\n");
@@ -911,7 +909,7 @@ void __init setup_arch(char **cmdline_p)
 	if (!boot_earlyprintk)
 		boot_rb_foreach(print_rb_entry);
 
-	if (have_relocated_lowcore())
+	if (machine_has_relocated_lowcore())
 		pr_info("Lowcore relocated to 0x%px\n", get_lowcore());
 
 	log_component_list();
@@ -961,7 +959,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_uv();
 	dma_contiguous_reserve(ident_map_size);
 	vmcp_cma_reserve();
-	if (MACHINE_HAS_EDAT2)
+	if (cpu_has_edat2())
 		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
 
 	reserve_crashkernel();
@@ -981,10 +979,6 @@ void __init setup_arch(char **cmdline_p)
 	numa_setup();
 	smp_detect_cpus();
 	topology_init_early();
-
-	if (test_facility(193))
-		static_branch_enable(&cpu_has_bear);
-
 	setup_protection_map();
 	/*
 	 * Create kernel page tables.
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7b08399b0846..81f12bb77f62 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -18,6 +18,7 @@
 #define KMSG_COMPONENT "cpu"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/cpufeature.h>
 #include <linux/workqueue.h>
 #include <linux/memblock.h>
 #include <linux/export.h>
@@ -38,6 +39,7 @@
 #include <linux/kprobes.h>
 #include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
+#include <asm/machine.h>
 #include <asm/ctlreg.h>
 #include <asm/pfault.h>
 #include <asm/diag.h>
@@ -97,13 +99,6 @@ __vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
 static unsigned int smp_max_threads __initdata = -1U;
 cpumask_t cpu_setup_mask;
 
-static int __init early_nosmt(char *s)
-{
-	smp_max_threads = 1;
-	return 0;
-}
-early_param("nosmt", early_nosmt);
-
 static int __init early_smt(char *s)
 {
 	get_option(&s, &smp_max_threads);
@@ -263,13 +258,12 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = get_lowcore()->kernel_asce;
 	lc->user_asce = s390_invalid_asce;
-	lc->machine_flags = get_lowcore()->machine_flags;
 	lc->user_timer = lc->system_timer =
 		lc->steal_timer = lc->avg_steal_timer = 0;
 	abs_lc = get_abs_lowcore();
 	memcpy(lc->cregs_save_area, abs_lc->cregs_save_area, sizeof(lc->cregs_save_area));
 	put_abs_lowcore(abs_lc);
-	lc->cregs_save_area[1] = lc->kernel_asce;
+	lc->cregs_save_area[1] = lc->user_asce;
 	lc->cregs_save_area[7] = lc->user_asce;
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	arch_spin_lock_setup(cpu);
@@ -416,7 +410,7 @@ EXPORT_SYMBOL(arch_vcpu_is_preempted);
 
 void notrace smp_yield_cpu(int cpu)
 {
-	if (!MACHINE_HAS_DIAG9C)
+	if (!machine_has_diag9c())
 		return;
 	diag_stat_inc_norecursion(DIAG_STAT_X09C);
 	asm volatile("diag %0,0,0x9c"
@@ -561,10 +555,10 @@ int smp_store_status(int cpu)
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
 			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
-	if (!cpu_has_vx() && !MACHINE_HAS_GS)
+	if (!cpu_has_vx() && !cpu_has_gs())
 		return 0;
 	pa = lc->mcesad & MCESA_ORIGIN_MASK;
-	if (MACHINE_HAS_GS)
+	if (cpu_has_gs())
 		pa |= lc->mcesad & MCESA_LC_MASK;
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
 			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
@@ -807,6 +801,7 @@ void __init smp_detect_cpus(void)
 	mtid = boot_core_type ? sclp.mtid : sclp.mtid_cp;
 	mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
 	pcpu_set_smt(mtid);
+	cpu_smt_set_num_threads(smp_cpu_mtid + 1, smp_cpu_mtid + 1);
 
 	/* Print number of CPUs */
 	c_cpus = s_cpus = 0;
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 40edfde25f5b..b153a395f46d 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -9,6 +9,7 @@
 #include <linux/stacktrace.h>
 #include <linux/uaccess.h>
 #include <linux/compat.h>
+#include <asm/asm-offsets.h>
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 #include <asm/kprobes.h>
diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c
index 5ec28028315b..4fee74553ca2 100644
--- a/arch/s390/kernel/syscall.c
+++ b/arch/s390/kernel/syscall.c
@@ -12,6 +12,7 @@
  *  platform.
  */
 
+#include <linux/cpufeature.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -81,25 +82,35 @@ SYSCALL_DEFINE0(ni_syscall)
 	return -ENOSYS;
 }
 
-static void do_syscall(struct pt_regs *regs)
+void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
 {
 	unsigned long nr;
 
+	add_random_kstack_offset();
+	enter_from_user_mode(regs);
+	regs->psw = get_lowcore()->svc_old_psw;
+	regs->int_code = get_lowcore()->svc_int_code;
+	update_timer_sys();
+	if (cpu_has_bear())
+		current->thread.last_break = regs->last_break;
+	local_irq_enable();
+	regs->orig_gpr2 = regs->gprs[2];
+	if (unlikely(per_trap))
+		set_thread_flag(TIF_PER_TRAP);
+	regs->flags = 0;
+	set_pt_regs_flag(regs, PIF_SYSCALL);
 	nr = regs->int_code & 0xffff;
-	if (!nr) {
+	if (likely(!nr)) {
 		nr = regs->gprs[1] & 0xffff;
 		regs->int_code &= ~0xffffUL;
 		regs->int_code |= nr;
 	}
-
 	regs->gprs[2] = nr;
-
 	if (nr == __NR_restart_syscall && !(current->restart_block.arch_data & 1)) {
 		regs->psw.addr = current->restart_block.arch_data;
 		current->restart_block.arch_data = 1;
 	}
 	nr = syscall_enter_from_user_mode_work(regs, nr);
-
 	/*
 	 * In the s390 ptrace ABI, both the syscall number and the return value
 	 * use gpr2. However, userspace puts the syscall number either in the
@@ -107,37 +118,11 @@ static void do_syscall(struct pt_regs *regs)
 	 * work, the ptrace code sets PIF_SYSCALL_RET_SET, which is checked here
 	 * and if set, the syscall will be skipped.
 	 */
-
 	if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
 		goto out;
 	regs->gprs[2] = -ENOSYS;
-	if (likely(nr >= NR_syscalls))
-		goto out;
-	do {
+	if (likely(nr < NR_syscalls))
 		regs->gprs[2] = current->thread.sys_call_table[nr](regs);
-	} while (test_and_clear_pt_regs_flag(regs, PIF_EXECVE_PGSTE_RESTART));
 out:
-	syscall_exit_to_user_mode_work(regs);
-}
-
-void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
-{
-	add_random_kstack_offset();
-	enter_from_user_mode(regs);
-	regs->psw = get_lowcore()->svc_old_psw;
-	regs->int_code = get_lowcore()->svc_int_code;
-	update_timer_sys();
-	if (static_branch_likely(&cpu_has_bear))
-		current->thread.last_break = regs->last_break;
-
-	local_irq_enable();
-	regs->orig_gpr2 = regs->gprs[2];
-
-	if (per_trap)
-		set_thread_flag(TIF_PER_TRAP);
-
-	regs->flags = 0;
-	set_pt_regs_flag(regs, PIF_SYSCALL);
-	do_syscall(regs);
-	exit_to_user_mode();
+	syscall_exit_to_user_mode(regs);
 }
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index e9115b4d8b63..a4569b96ef06 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -469,3 +469,4 @@
 464  common	getxattrat		sys_getxattrat			sys_getxattrat
 465  common	listxattrat		sys_listxattrat			sys_listxattrat
 466  common	removexattrat		sys_removexattrat		sys_removexattrat
+467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 88055f58fbda..1ea84e942bd4 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -5,6 +5,7 @@
  *	       Martin Schwidefsky <schwidefsky@de.ibm.com>,
  */
 
+#include <linux/cpufeature.h>
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -15,54 +16,17 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <asm/asm-extable.h>
+#include <asm/machine.h>
 #include <asm/ebcdic.h>
 #include <asm/debug.h>
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/topology.h>
 #include <asm/fpu.h>
+#include <asm/asm.h>
 
 int topology_max_mnest;
 
-static inline int __stsi(void *sysinfo, int fc, int sel1, int sel2, int *lvl)
-{
-	int r0 = (fc << 28) | sel1;
-	int rc = 0;
-
-	asm volatile(
-		"	lr	0,%[r0]\n"
-		"	lr	1,%[r1]\n"
-		"	stsi	0(%[sysinfo])\n"
-		"0:	jz	2f\n"
-		"1:	lhi	%[rc],%[retval]\n"
-		"2:	lr	%[r0],0\n"
-		EX_TABLE(0b, 1b)
-		: [r0] "+d" (r0), [rc] "+d" (rc)
-		: [r1] "d" (sel2),
-		  [sysinfo] "a" (sysinfo),
-		  [retval] "K" (-EOPNOTSUPP)
-		: "cc", "0", "1", "memory");
-	*lvl = ((unsigned int) r0) >> 28;
-	return rc;
-}
-
-/*
- * stsi - store system information
- *
- * Returns the current configuration level if function code 0 was specified.
- * Otherwise returns 0 on success or a negative value on error.
- */
-int stsi(void *sysinfo, int fc, int sel1, int sel2)
-{
-	int lvl, rc;
-
-	rc = __stsi(sysinfo, fc, sel1, sel2, &lvl);
-	if (rc)
-		return rc;
-	return fc ? 0 : lvl;
-}
-EXPORT_SYMBOL(stsi);
-
 #ifdef CONFIG_PROC_FS
 
 static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
@@ -154,7 +118,7 @@ static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info)
 	int i;
 
 	seq_putc(m, '\n');
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		return;
 	if (stsi(info, 15, 1, topology_max_mnest))
 		return;
@@ -415,7 +379,7 @@ static struct service_level service_level_vm = {
 static __init int create_proc_service_level(void)
 {
 	proc_create_seq("service_levels", 0, NULL, &service_level_seq_ops);
-	if (MACHINE_IS_VM)
+	if (machine_is_vm())
 		register_service_level(&service_level_vm);
 	return 0;
 }
@@ -559,7 +523,7 @@ static __init int stsi_init_debugfs(void)
 		sf = &stsi_file[i];
 		debugfs_create_file(sf->name, 0400, stsi_root, NULL, sf->fops);
 	}
-	if (IS_ENABLED(CONFIG_SCHED_TOPOLOGY) && MACHINE_HAS_TOPOLOGY) {
+	if (IS_ENABLED(CONFIG_SCHED_TOPOLOGY) && cpu_has_topology()) {
 		char link_to[10];
 
 		sprintf(link_to, "15_1_%d", topology_mnest_limit());
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e9f47c3a6197..fed17d407a44 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -54,10 +54,10 @@
 #include <asm/cio.h>
 #include "entry.h"
 
-union tod_clock tod_clock_base __section(".data");
+union tod_clock __bootdata_preserved(tod_clock_base);
 EXPORT_SYMBOL_GPL(tod_clock_base);
 
-u64 clock_comparator_max = -1ULL;
+u64 __bootdata_preserved(clock_comparator_max);
 EXPORT_SYMBOL_GPL(clock_comparator_max);
 
 static DEFINE_PER_CPU(struct clock_event_device, comparators);
@@ -79,12 +79,10 @@ void __init time_early_init(void)
 {
 	struct ptff_qto qto;
 	struct ptff_qui qui;
-	int cs;
 
 	/* Initialize TOD steering parameters */
 	tod_steering_end = tod_clock_base.tod;
-	for (cs = 0; cs < CS_BASES; cs++)
-		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
 
 	if (!test_facility(28))
 		return;
@@ -373,7 +371,6 @@ static void clock_sync_global(long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
-	int cs;
 
 	/* Fixup the monotonic sched clock. */
 	tod_clock_base.eitod += delta;
@@ -389,10 +386,8 @@ static void clock_sync_global(long delta)
 		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
-	for (cs = 0; cs < CS_BASES; cs++) {
-		vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
-		vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
-	}
+	vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
+	vdso_k_time_data->arch_data.tod_steering_delta = tod_steering_delta;
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
@@ -685,7 +680,7 @@ static void stp_work_fn(struct work_struct *work)
 
 	if (!stp_online) {
 		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL);
-		del_timer_sync(&stp_timer);
+		timer_delete_sync(&stp_timer);
 		goto out_unlock;
 	}
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 211cc8382e4a..3df048e190b1 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -6,6 +6,7 @@
 #define KMSG_COMPONENT "cpu"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/cpufeature.h>
 #include <linux/workqueue.h>
 #include <linux/memblock.h>
 #include <linux/uaccess.h>
@@ -240,7 +241,7 @@ int topology_set_cpu_management(int fc)
 {
 	int cpu, rc;
 
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		return -EOPNOTSUPP;
 	if (fc)
 		rc = ptf(PTF_VERTICAL);
@@ -315,13 +316,13 @@ static int __arch_update_cpu_topology(void)
 	hd_status = 0;
 	rc = 0;
 	mutex_lock(&smp_cpu_state_mutex);
-	if (MACHINE_HAS_TOPOLOGY) {
+	if (cpu_has_topology()) {
 		rc = 1;
 		store_topology(info);
 		tl_to_masks(info);
 	}
 	update_cpu_masks();
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		topology_update_polarization_simple();
 	if (cpu_management == 1)
 		hd_status = hd_enable_hiperdispatch();
@@ -376,7 +377,7 @@ static void set_topology_timer(void)
 
 void topology_expect_change(void)
 {
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		return;
 	/* This is racy, but it doesn't matter since it is just a heuristic.
 	 * Worst case is that we poll in a higher frequency for a bit longer.
@@ -500,7 +501,7 @@ int topology_cpu_init(struct cpu *cpu)
 	int rc;
 
 	rc = sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
-	if (rc || !MACHINE_HAS_TOPOLOGY)
+	if (rc || !cpu_has_topology())
 		return rc;
 	rc = sysfs_create_group(&cpu->dev.kobj, &topology_extra_cpu_attr_group);
 	if (rc)
@@ -569,12 +570,12 @@ void __init topology_init_early(void)
 
 	set_sched_topology(s390_topology);
 	if (topology_mode == TOPOLOGY_MODE_UNINITIALIZED) {
-		if (MACHINE_HAS_TOPOLOGY)
+		if (cpu_has_topology())
 			topology_mode = TOPOLOGY_MODE_HW;
 		else
 			topology_mode = TOPOLOGY_MODE_SINGLE;
 	}
-	if (!MACHINE_HAS_TOPOLOGY)
+	if (!cpu_has_topology())
 		goto out;
 	tl_info = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	info = tl_info;
@@ -596,7 +597,7 @@ static inline int topology_get_mode(int enabled)
 {
 	if (!enabled)
 		return TOPOLOGY_MODE_SINGLE;
-	return MACHINE_HAS_TOPOLOGY ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
+	return cpu_has_topology() ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
 }
 
 static inline int topology_is_enabled(void)
@@ -686,7 +687,7 @@ static int __init topology_init(void)
 	int rc = 0;
 
 	timer_setup(&topology_timer, topology_timer_fn, TIMER_DEFERRABLE);
-	if (MACHINE_HAS_TOPOLOGY)
+	if (cpu_has_topology())
 		set_topology_timer();
 	else
 		topology_update_polarization_simple();
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 24fee11b030d..19687dab32f7 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -3,18 +3,13 @@
  *  S390 version
  *    Copyright IBM Corp. 1999, 2000
  *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- *               Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
+ *		 Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
  *
  *  Derived from "arch/i386/kernel/traps.c"
  *    Copyright (C) 1991, 1992 Linus Torvalds
  */
 
-/*
- * 'Traps.c' handles hardware traps and faults after we have saved some
- * state in 'asm.s'.
- */
-#include "asm/irqflags.h"
-#include "asm/ptrace.h"
+#include <linux/cpufeature.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/randomize_kstack.h>
@@ -29,6 +24,8 @@
 #include <linux/entry-common.h>
 #include <linux/kmsan.h>
 #include <asm/asm-extable.h>
+#include <asm/irqflags.h>
+#include <asm/ptrace.h>
 #include <asm/vtime.h>
 #include <asm/fpu.h>
 #include <asm/fault.h>
@@ -42,7 +39,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 		address = current->thread.trap_tdb.data[3];
 	else
 		address = regs->psw.addr;
-	return (void __user *) (address - (regs->int_code >> 16));
+	return (void __user *)(address - (regs->int_code >> 16));
 }
 
 #ifdef CONFIG_GENERIC_BUG
@@ -57,16 +54,15 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 	if (user_mode(regs)) {
 		force_sig_fault(si_signo, si_code, get_trap_ip(regs));
 		report_user_fault(regs, si_signo, 0);
-        } else {
+	} else {
 		if (!fixup_exception(regs))
 			die(regs, str);
-        }
+	}
 }
 
 static void do_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 {
-	if (notify_die(DIE_TRAP, str, regs, 0,
-		       regs->int_code, si_signo) == NOTIFY_STOP)
+	if (notify_die(DIE_TRAP, str, regs, 0, regs->int_code, si_signo) == NOTIFY_STOP)
 		return;
 	do_report_trap(regs, si_signo, si_code, str);
 }
@@ -78,8 +74,7 @@ void do_per_trap(struct pt_regs *regs)
 		return;
 	if (!current->ptrace)
 		return;
-	force_sig_fault(SIGTRAP, TRAP_HWBKPT,
-		(void __force __user *) current->thread.per_event.address);
+	force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __force __user *)current->thread.per_event.address);
 }
 NOKPROBE_SYMBOL(do_per_trap);
 
@@ -98,36 +93,25 @@ static void name(struct pt_regs *regs)		\
 	do_trap(regs, signr, sicode, str);	\
 }
 
-DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR,
-	      "addressing exception")
-DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN,
-	      "execute exception")
-DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV,
-	      "fixpoint divide exception")
-DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF,
-	      "fixpoint overflow exception")
-DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF,
-	      "HFP overflow exception")
-DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND,
-	      "HFP underflow exception")
-DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES,
-	      "HFP significance exception")
-DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV,
-	      "HFP divide exception")
-DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV,
-	      "HFP square root exception")
-DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN,
-	      "operand exception")
-DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC,
-	      "privileged operation")
-DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN,
-	      "special operation exception")
-DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN,
-	      "transaction constraint exception")
+DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR, "addressing exception")
+DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV, "fixpoint divide exception")
+DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN, "execute exception")
+DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV, "HFP divide exception")
+DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF, "HFP overflow exception")
+DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES, "HFP significance exception")
+DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV, "HFP square root exception")
+DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND, "HFP underflow exception")
+DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN, "operand exception")
+DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF, "fixpoint overflow exception")
+DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC, "privileged operation")
+DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN, "special operation exception")
+DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN, "specification exception");
+DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN, "transaction constraint exception")
 
 static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc)
 {
 	int si_code = 0;
+
 	/* FPC[2] is Data Exception Code */
 	if ((fpc & 0x00000300) == 0) {
 		/* bits 6 and 7 of DXC are 0 iff IEEE exception */
@@ -153,36 +137,35 @@ static void translation_specification_exception(struct pt_regs *regs)
 
 static void illegal_op(struct pt_regs *regs)
 {
-        __u8 opcode[6];
-	__u16 __user *location;
 	int is_uprobe_insn = 0;
+	u16 __user *location;
 	int signal = 0;
+	u16 opcode;
 
 	location = get_trap_ip(regs);
-
 	if (user_mode(regs)) {
-		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
+		if (get_user(opcode, location))
 			return;
-		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
+		if (opcode == S390_BREAKPOINT_U16) {
 			if (current->ptrace)
 				force_sig_fault(SIGTRAP, TRAP_BRKPT, location);
 			else
 				signal = SIGILL;
 #ifdef CONFIG_UPROBES
-		} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
+		} else if (opcode == UPROBE_SWBP_INSN) {
 			is_uprobe_insn = 1;
 #endif
-		} else
+		} else {
 			signal = SIGILL;
+		}
 	}
 	/*
-	 * We got either an illegal op in kernel mode, or user space trapped
+	 * This is either an illegal op in kernel mode, or user space trapped
 	 * on a uprobes illegal instruction. See if kprobes or uprobes picks
 	 * it up. If not, SIGILL.
 	 */
 	if (is_uprobe_insn || !user_mode(regs)) {
-		if (notify_die(DIE_BPT, "bpt", regs, 0,
-			       3, SIGTRAP) != NOTIFY_STOP)
+		if (notify_die(DIE_BPT, "bpt", regs, 0, 3, SIGTRAP) != NOTIFY_STOP)
 			signal = SIGILL;
 	}
 	if (signal)
@@ -190,18 +173,10 @@ static void illegal_op(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(illegal_op);
 
-DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
-	      "specification exception");
-
 static void vector_exception(struct pt_regs *regs)
 {
 	int si_code, vic;
 
-	if (!cpu_has_vx()) {
-		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
-		return;
-	}
-
 	/* get vector interrupt code from fpc */
 	save_user_fpu_regs();
 	vic = (current->thread.ufpu.fpc & 0xf00) >> 8;
@@ -249,7 +224,6 @@ static void monitor_event_exception(struct pt_regs *regs)
 {
 	if (user_mode(regs))
 		return;
-
 	switch (report_bug(regs->psw.addr - (regs->int_code >> 16), regs)) {
 	case BUG_TRAP_TYPE_NONE:
 		fixup_exception(regs);
@@ -262,7 +236,7 @@ static void monitor_event_exception(struct pt_regs *regs)
 	}
 }
 
-void kernel_stack_overflow(struct pt_regs *regs)
+void kernel_stack_invalid(struct pt_regs *regs)
 {
 	/*
 	 * Normally regs are unpoisoned by the generic entry code, but
@@ -270,12 +244,12 @@ void kernel_stack_overflow(struct pt_regs *regs)
 	 */
 	kmsan_unpoison_entry_regs(regs);
 	bust_spinlocks(1);
-	printk("Kernel stack overflow.\n");
+	pr_emerg("Kernel stack pointer invalid\n");
 	show_regs(regs);
 	bust_spinlocks(0);
-	panic("Corrupt kernel stack, can't continue.");
+	panic("Invalid kernel stack pointer, cannot continue");
 }
-NOKPROBE_SYMBOL(kernel_stack_overflow);
+NOKPROBE_SYMBOL(kernel_stack_invalid);
 
 static void __init test_monitor_call(void)
 {
@@ -283,12 +257,12 @@ static void __init test_monitor_call(void)
 
 	if (!IS_ENABLED(CONFIG_BUG))
 		return;
-	asm volatile(
+	asm_inline volatile(
 		"	mc	0,0\n"
-		"0:	xgr	%0,%0\n"
+		"0:	lhi	%[val],0\n"
 		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (val));
+		EX_TABLE(0b, 1b)
+		: [val] "+d" (val));
 	if (!val)
 		panic("Monitor call doesn't work!\n");
 }
@@ -323,7 +297,6 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 	teid.val = lc->trans_exc_code;
 	regs->int_code = lc->pgm_int_code;
 	regs->int_parm_long = teid.val;
-
 	/*
 	 * In case of a guest fault, short-circuit the fault handler and return.
 	 * This way the sie64a() function will return 0; fault address and
@@ -336,23 +309,19 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 		current->thread.gmap_int_code = regs->int_code & 0xffff;
 		return;
 	}
-
 	state = irqentry_enter(regs);
-
 	if (user_mode(regs)) {
 		update_timer_sys();
-		if (!static_branch_likely(&cpu_has_bear)) {
+		if (!cpu_has_bear()) {
 			if (regs->last_break < 4096)
 				regs->last_break = 1;
 		}
 		current->thread.last_break = regs->last_break;
 	}
-
 	if (lc->pgm_code & 0x0200) {
 		/* transaction abort */
 		current->thread.trap_tdb = lc->pgm_tdb;
 	}
-
 	if (lc->pgm_code & PGM_INT_CODE_PER) {
 		if (user_mode(regs)) {
 			struct per_event *ev = &current->thread.per_event;
@@ -368,11 +337,9 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
 			goto out;
 		}
 	}
-
 	if (!irqs_disabled_flags(regs->psw.mask))
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(regs->psw.mask & ~PSW_MASK_PER);
-
 	trapnr = regs->int_code & PGM_INT_CODE_MASK;
 	if (trapnr)
 		pgm_check_table[trapnr](regs);
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 9f05df2da2f7..4ab0b6b4866e 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -206,6 +206,39 @@ int uv_convert_from_secure_pte(pte_t pte)
 	return uv_convert_from_secure_folio(pfn_folio(pte_pfn(pte)));
 }
 
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+	/*
+	 * The misc feature indicates, among other things, that importing a
+	 * shared page from a different protected VM will automatically also
+	 * transfer its ownership.
+	 */
+	if (uv_has_feature(BIT_UV_FEAT_MISC))
+		return false;
+	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+		return false;
+	return atomic_read(&mm->context.protected_count) > 1;
+}
+
 /*
  * Calculate the expected ref_count for a folio that would otherwise have no
  * further pins. This was cribbed from similar functions in other places in
@@ -228,7 +261,7 @@ static int expected_folio_refs(struct folio *folio)
 }
 
 /**
- * make_folio_secure() - make a folio secure
+ * __make_folio_secure() - make a folio secure
  * @folio: the folio to make secure
  * @uvcb: the uvcb that describes the UVC to be used
  *
@@ -237,20 +270,18 @@ static int expected_folio_refs(struct folio *folio)
  *
  * Return: 0 on success;
  *         -EBUSY if the folio is in writeback or has too many references;
- *         -E2BIG if the folio is large;
  *         -EAGAIN if the UVC needs to be attempted again;
  *         -ENXIO if the address is not mapped;
  *         -EINVAL if the UVC failed for other reasons.
  *
  * Context: The caller must hold exactly one extra reference on the folio
- *          (it's the same logic as split_folio())
+ *          (it's the same logic as split_folio()), and the folio must be
+ *          locked.
  */
-int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+static int __make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 {
 	int expected, cc = 0;
 
-	if (folio_test_large(folio))
-		return -E2BIG;
 	if (folio_test_writeback(folio))
 		return -EBUSY;
 	expected = expected_folio_refs(folio) + 1;
@@ -277,7 +308,98 @@ int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 		return -EAGAIN;
 	return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
 }
-EXPORT_SYMBOL_GPL(make_folio_secure);
+
+static int make_folio_secure(struct mm_struct *mm, struct folio *folio, struct uv_cb_header *uvcb)
+{
+	int rc;
+
+	if (!folio_trylock(folio))
+		return -EAGAIN;
+	if (should_export_before_import(uvcb, mm))
+		uv_convert_from_secure(folio_to_phys(folio));
+	rc = __make_folio_secure(folio, uvcb);
+	folio_unlock(folio);
+
+	return rc;
+}
+
+/**
+ * s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split.
+ * @mm:    the mm containing the folio to work on
+ * @folio: the folio
+ * @split: whether to split a large folio
+ *
+ * Context: Must be called while holding an extra reference to the folio;
+ *          the mm lock should not be held.
+ * Return: 0 if the folio was split successfully;
+ *         -EAGAIN if the folio was not split successfully but another attempt
+ *                 can be made, or if @split was set to false;
+ *         -EINVAL in case of other errors. See split_folio().
+ */
+static int s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
+{
+	int rc;
+
+	lockdep_assert_not_held(&mm->mmap_lock);
+	folio_wait_writeback(folio);
+	lru_add_drain_all();
+	if (split) {
+		folio_lock(folio);
+		rc = split_folio(folio);
+		folio_unlock(folio);
+
+		if (rc != -EBUSY)
+			return rc;
+	}
+	return -EAGAIN;
+}
+
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb)
+{
+	struct vm_area_struct *vma;
+	struct folio_walk fw;
+	struct folio *folio;
+	int rc;
+
+	mmap_read_lock(mm);
+	vma = vma_lookup(mm, hva);
+	if (!vma) {
+		mmap_read_unlock(mm);
+		return -EFAULT;
+	}
+	folio = folio_walk_start(&fw, vma, hva, 0);
+	if (!folio) {
+		mmap_read_unlock(mm);
+		return -ENXIO;
+	}
+
+	folio_get(folio);
+	/*
+	 * Secure pages cannot be huge and userspace should not combine both.
+	 * In case userspace does it anyway this will result in an -EFAULT for
+	 * the unpack. The guest is thus never reaching secure mode.
+	 * If userspace plays dirty tricks and decides to map huge pages at a
+	 * later point in time, it will receive a segmentation fault or
+	 * KVM_RUN will return -EFAULT.
+	 */
+	if (folio_test_hugetlb(folio))
+		rc = -EFAULT;
+	else if (folio_test_large(folio))
+		rc = -E2BIG;
+	else if (!pte_write(fw.pte) || (pte_val(fw.pte) & _PAGE_INVALID))
+		rc = -ENXIO;
+	else
+		rc = make_folio_secure(mm, folio, uvcb);
+	folio_walk_end(&fw, vma);
+	mmap_read_unlock(mm);
+
+	if (rc == -E2BIG || rc == -EBUSY)
+		rc = s390_wiggle_split_folio(mm, folio, rc == -E2BIG);
+	folio_put(folio);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(make_hva_secure);
 
 /*
  * To be called with the folio locked or with an extra reference! This will
@@ -660,7 +782,12 @@ out_kobj:
 device_initcall(uv_sysfs_init);
 
 /*
- * Find the secret with the secret_id in the provided list.
+ * Locate a secret in the list by its id.
+ * @secret_id: search pattern.
+ * @list: ephemeral buffer space
+ * @secret: output data, containing the secret's metadata.
+ *
+ * Search for a secret with the given secret_id in the Ultravisor secret store.
  *
  * Context: might sleep.
  */
@@ -681,12 +808,15 @@ static int find_secret_in_page(const u8 secret_id[UV_SECRET_ID_LEN],
 
 /*
  * Do the actual search for `uv_get_secret_metadata`.
+ * @secret_id: search pattern.
+ * @list: ephemeral buffer space
+ * @secret: output data, containing the secret's metadata.
  *
  * Context: might sleep.
  */
-static int find_secret(const u8 secret_id[UV_SECRET_ID_LEN],
-		       struct uv_secret_list *list,
-		       struct uv_secret_list_item_hdr *secret)
+int uv_find_secret(const u8 secret_id[UV_SECRET_ID_LEN],
+		   struct uv_secret_list *list,
+		   struct uv_secret_list_item_hdr *secret)
 {
 	u16 start_idx = 0;
 	u16 list_rc;
@@ -708,36 +838,7 @@ static int find_secret(const u8 secret_id[UV_SECRET_ID_LEN],
 
 	return -ENOENT;
 }
-
-/**
- * uv_get_secret_metadata() - get secret metadata for a given secret id.
- * @secret_id: search pattern.
- * @secret: output data, containing the secret's metadata.
- *
- * Search for a secret with the given secret_id in the Ultravisor secret store.
- *
- * Context: might sleep.
- *
- * Return:
- * * %0:	- Found entry; secret->idx and secret->type are valid.
- * * %ENOENT	- No entry found.
- * * %ENODEV:	- Not supported: UV not available or command not available.
- * * %EIO:	- Other unexpected UV error.
- */
-int uv_get_secret_metadata(const u8 secret_id[UV_SECRET_ID_LEN],
-			   struct uv_secret_list_item_hdr *secret)
-{
-	struct uv_secret_list *buf;
-	int rc;
-
-	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	rc = find_secret(secret_id, buf, secret);
-	kfree(buf);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(uv_get_secret_metadata);
+EXPORT_SYMBOL_GPL(uv_find_secret);
 
 /**
  * uv_retrieve_secret() - get the secret value for the secret index.
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 598b512cde01..430feb1a5013 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -16,8 +16,8 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
-#include <linux/time_namespace.h>
 #include <linux/random.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 #include <asm/vdso/vsyscall.h>
 #include <asm/alternative.h>
@@ -26,85 +26,6 @@
 extern char vdso64_start[], vdso64_end[];
 extern char vdso32_start[], vdso32_end[];
 
-static struct vm_special_mapping vvar_mapping;
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-
-struct vdso_data *vdso_data = vdso_data_store.data;
-
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The VVAR page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will be re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (!vma_is_special_mapping(vma, &vvar_mapping))
-			continue;
-		zap_vma_pages(vma);
-		break;
-	}
-	mmap_read_unlock(mm);
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct page *timens_page = find_timens_vvar_page(vma);
-	unsigned long addr, pfn;
-	vm_fault_t err;
-
-	switch (vmf->pgoff) {
-	case VVAR_DATA_PAGE_OFFSET:
-		pfn = virt_to_pfn(vdso_data);
-		if (timens_page) {
-			/*
-			 * Fault in VVAR page too, since it will be accessed
-			 * to get clock data anyway.
-			 */
-			addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
-			err = vmf_insert_pfn(vma, addr, pfn);
-			if (unlikely(err & VM_FAULT_ERROR))
-				return err;
-			pfn = page_to_pfn(timens_page);
-		}
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
-		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		pfn = virt_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		       struct vm_area_struct *vma)
 {
@@ -112,11 +33,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-static struct vm_special_mapping vvar_mapping = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
-
 static struct vm_special_mapping vdso64_mapping = {
 	.name = "[vdso]",
 	.mremap = vdso_mremap,
@@ -142,7 +58,7 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 	struct vm_area_struct *vma;
 	int rc;
 
-	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+	BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
@@ -157,17 +73,14 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
 	rc = vvar_start;
 	if (IS_ERR_VALUE(vvar_start))
 		goto out;
-	vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
-				       &vvar_mapping);
+	vma = vdso_install_vvar_mapping(mm, vvar_start);
 	rc = PTR_ERR(vma);
 	if (IS_ERR(vma))
 		goto out;
-	vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE;
+	vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE;
 	/* VM_MAYWRITE for COW so gdb can set breakpoints */
 	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
-				       VM_READ|VM_EXEC|
+				       VM_READ|VM_EXEC|VM_SEALED_SYSMAP|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				       vdso_mapping);
 	if (IS_ERR(vma)) {
@@ -220,7 +133,7 @@ unsigned long vdso_text_size(void)
 
 unsigned long vdso_size(void)
 {
-	return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE;
+	return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE;
 }
 
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 2c5afb88d298..1e4ddd1a683f 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -2,7 +2,7 @@
 # List of files in the vdso
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 obj-vdso32 = vdso_user_wrapper-32.o note-32.o
 
 # Build rules
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
index c916c4f73f76..9630d58c2080 100644
--- a/arch/s390/kernel/vdso32/vdso32.lds.S
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -6,16 +6,15 @@
 
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
 OUTPUT_ARCH(s390:31-bit)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index ad206f2068d8..d8f0df742809 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -2,7 +2,7 @@
 # List of files in the vdso
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o
 obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o
 VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index ec42b7d9cb53..e4f6551ae898 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -7,17 +7,15 @@
 #include <asm/vdso/vsyscall.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <vdso/datapage.h>
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-	PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
-	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 02adf151d4de..6d8944d1b4a0 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -23,116 +23,25 @@
 #include "gmap.h"
 
 /**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
-{
-	/*
-	 * The misc feature indicates, among other things, that importing a
-	 * shared page from a different protected VM will automatically also
-	 * transfer its ownership.
-	 */
-	if (uv_has_feature(BIT_UV_FEAT_MISC))
-		return false;
-	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
-		return false;
-	return atomic_read(&mm->context.protected_count) > 1;
-}
-
-static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
-{
-	struct folio *folio = page_folio(page);
-	int rc;
-
-	/*
-	 * Secure pages cannot be huge and userspace should not combine both.
-	 * In case userspace does it anyway this will result in an -EFAULT for
-	 * the unpack. The guest is thus never reaching secure mode.
-	 * If userspace plays dirty tricks and decides to map huge pages at a
-	 * later point in time, it will receive a segmentation fault or
-	 * KVM_RUN will return -EFAULT.
-	 */
-	if (folio_test_hugetlb(folio))
-		return -EFAULT;
-	if (folio_test_large(folio)) {
-		mmap_read_unlock(gmap->mm);
-		rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
-		mmap_read_lock(gmap->mm);
-		if (rc)
-			return rc;
-		folio = page_folio(page);
-	}
-
-	if (!folio_trylock(folio))
-		return -EAGAIN;
-	if (should_export_before_import(uvcb, gmap->mm))
-		uv_convert_from_secure(folio_to_phys(folio));
-	rc = make_folio_secure(folio, uvcb);
-	folio_unlock(folio);
-
-	/*
-	 * In theory a race is possible and the folio might have become
-	 * large again before the folio_trylock() above. In that case, no
-	 * action is performed and -EAGAIN is returned; the callers will
-	 * have to try again later.
-	 * In most cases this implies running the VM again, getting the same
-	 * exception again, and make another attempt in this function.
-	 * This is expected to happen extremely rarely.
-	 */
-	if (rc == -E2BIG)
-		return -EAGAIN;
-	/* The folio has too many references, try to shake some off */
-	if (rc == -EBUSY) {
-		mmap_read_unlock(gmap->mm);
-		kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
-		mmap_read_lock(gmap->mm);
-		return -EAGAIN;
-	}
-
-	return rc;
-}
-
-/**
  * gmap_make_secure() - make one guest page secure
  * @gmap: the guest gmap
  * @gaddr: the guest address that needs to be made secure
  * @uvcb: the UVCB specifying which operation needs to be performed
  *
  * Context: needs to be called with kvm->srcu held.
- * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()).
+ * Return: 0 on success, < 0 in case of error.
  */
 int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
 {
 	struct kvm *kvm = gmap->private;
-	struct page *page;
-	int rc = 0;
+	unsigned long vmaddr;
 
 	lockdep_assert_held(&kvm->srcu);
 
-	page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
-	mmap_read_lock(gmap->mm);
-	if (page)
-		rc = __gmap_make_secure(gmap, page, uvcb);
-	kvm_release_page_clean(page);
-	mmap_read_unlock(gmap->mm);
-
-	return rc;
+	vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
+		return -EFAULT;
+	return make_hva_secure(gmap->mm, vmaddr, uvcb);
 }
 
 int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 610dd44a948b..a06a000f196c 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -95,7 +95,7 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_validity++;
 	trace_kvm_s390_intercept_validity(vcpu, viwhy);
-	KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
+	KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%p)", viwhy,
 		  current->pid, vcpu->kvm);
 
 	/* do not warn on invalid runtime instrumentation mode */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 07ff0e10cb7f..60c360c18690 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -10,6 +10,7 @@
 #define KMSG_COMPONENT "kvm-s390"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/cpufeature.h>
 #include <linux/interrupt.h>
 #include <linux/kvm_host.h>
 #include <linux/hrtimer.h>
@@ -577,7 +578,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	/* take care of lazy register loading */
 	kvm_s390_fpu_store(vcpu->run);
 	save_access_regs(vcpu->run->s.regs.acrs);
-	if (MACHINE_HAS_GS && vcpu->arch.gs_enabled)
+	if (cpu_has_gs() && vcpu->arch.gs_enabled)
 		save_gs_cb(current->thread.gs_cb);
 
 	/* Extended save area */
@@ -948,8 +949,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
 	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
 				 (u64 *) __LC_PGM_LAST_BREAK);
-	rc |= put_guest_lc(vcpu, pgm_info.code,
-			   (u16 *)__LC_PGM_INT_CODE);
+	rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_CODE);
 	rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
 			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
 	rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
@@ -3161,7 +3161,7 @@ void kvm_s390_gisa_clear(struct kvm *kvm)
 	if (!gi->origin)
 		return;
 	gisa_clear_ipm(gi->origin);
-	VM_EVENT(kvm, 3, "gisa 0x%pK cleared", gi->origin);
+	VM_EVENT(kvm, 3, "gisa 0x%p cleared", gi->origin);
 }
 
 void kvm_s390_gisa_init(struct kvm *kvm)
@@ -3174,11 +3174,10 @@ void kvm_s390_gisa_init(struct kvm *kvm)
 	gi->alert.mask = 0;
 	spin_lock_init(&gi->alert.ref_lock);
 	gi->expires = 50 * 1000; /* 50 usec */
-	hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	gi->timer.function = gisa_vcpu_kicker;
+	hrtimer_setup(&gi->timer, gisa_vcpu_kicker, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
 	gi->origin->next_alert = (u32)virt_to_phys(gi->origin);
-	VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin);
+	VM_EVENT(kvm, 3, "gisa 0x%p initialized", gi->origin);
 }
 
 void kvm_s390_gisa_enable(struct kvm *kvm)
@@ -3219,7 +3218,7 @@ void kvm_s390_gisa_destroy(struct kvm *kvm)
 		process_gib_alert_list();
 	hrtimer_cancel(&gi->timer);
 	gi->origin = NULL;
-	VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa);
+	VM_EVENT(kvm, 3, "gisa 0x%p destroyed", gisa);
 }
 
 void kvm_s390_gisa_disable(struct kvm *kvm)
@@ -3468,7 +3467,7 @@ int __init kvm_s390_gib_init(u8 nisc)
 		}
 	}
 
-	KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc);
+	KVM_EVENT(3, "gib 0x%p (nisc=%d) initialized", gib, gib->nisc);
 	goto out;
 
 out_unreg_gal:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ebecb96bacce..3f3175193fd7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -23,6 +23,7 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/cpufeature.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
@@ -36,6 +37,7 @@
 #include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 #include <asm/stp.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
@@ -443,13 +445,13 @@ static void __init kvm_s390_cpu_feat_init(void)
 	if (test_facility(201))	/* PFCR */
 		pfcr_query(&kvm_s390_available_subfunc.pfcr);
 
-	if (MACHINE_HAS_ESOP)
+	if (machine_has_esop())
 		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
 	/*
 	 * We need SIE support, ESOP (PROT_READ protection for gmap_shadow),
 	 * 64bit SCAO (SCA passthrough) and IDTE (for gmap_shadow unshadowing).
 	 */
-	if (!sclp.has_sief2 || !MACHINE_HAS_ESOP || !sclp.has_64bscao ||
+	if (!sclp.has_sief2 || !machine_has_esop() || !sclp.has_64bscao ||
 	    !test_facility(3) || !nested)
 		return;
 	allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
@@ -638,7 +640,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
-		r = MACHINE_HAS_ESOP;
+		r = machine_has_esop();
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = test_facility(129);
@@ -1020,7 +1022,7 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		}
 		mutex_unlock(&kvm->lock);
 		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
-		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+		VM_EVENT(kvm, 3, "New guest asce: 0x%p",
 			 (void *) kvm->arch.gmap->asce);
 		break;
 	}
@@ -3396,7 +3398,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* we emulate STHYI in kvm */
 	set_kvm_facility(kvm->arch.model.fac_mask, 74);
 	set_kvm_facility(kvm->arch.model.fac_list, 74);
-	if (MACHINE_HAS_TLB_GUEST) {
+	if (machine_has_tlb_guest()) {
 		set_kvm_facility(kvm->arch.model.fac_mask, 147);
 		set_kvm_facility(kvm->arch.model.fac_list, 147);
 	}
@@ -3464,7 +3466,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		kvm_s390_gisa_init(kvm);
 	INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup);
 	kvm->arch.pv.set_aside = NULL;
-	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
+	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -3527,7 +3529,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
 	kvm_s390_vsie_destroy(kvm);
-	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
+	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -3648,7 +3650,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
 
 	free_page((unsigned long)old_sca);
 
-	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+	VM_EVENT(kvm, 2, "Switched to ESCA (0x%p -> 0x%p)",
 		 old_sca, kvm->arch.sca);
 	return 0;
 }
@@ -3892,8 +3894,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
-	/* pgste_set_pte has special handling for !MACHINE_HAS_ESOP */
-	if (MACHINE_HAS_ESOP)
+	/* pgste_set_pte has special handling for !machine_has_esop() */
+	if (machine_has_esop())
 		vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT;
 	if (test_kvm_facility(vcpu->kvm, 9))
 		vcpu->arch.sie_block->ecb |= ECB_SRSI;
@@ -3943,8 +3945,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 		if (rc)
 			return rc;
 	}
-	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+	hrtimer_setup(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	vcpu->arch.sie_block->hpid = HPID_KVM;
 
@@ -4025,7 +4027,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 			goto out_free_sie_block;
 	}
 
-	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK",
+	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p",
 		 vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
 
@@ -4952,6 +4954,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 {
 	unsigned int flags = 0;
 	unsigned long gaddr;
+	int rc;
 
 	gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
 	if (kvm_s390_cur_gmap_fault_is_write())
@@ -4961,16 +4964,6 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	case 0:
 		vcpu->stat.exit_null++;
 		break;
-	case PGM_NON_SECURE_STORAGE_ACCESS:
-		kvm_s390_assert_primary_as(vcpu);
-		/*
-		 * This is normal operation; a page belonging to a protected
-		 * guest has not been imported yet. Try to import the page into
-		 * the protected guest.
-		 */
-		if (gmap_convert_to_secure(vcpu->arch.gmap, gaddr) == -EINVAL)
-			send_sig(SIGSEGV, current, 0);
-		break;
 	case PGM_SECURE_STORAGE_ACCESS:
 	case PGM_SECURE_STORAGE_VIOLATION:
 		kvm_s390_assert_primary_as(vcpu);
@@ -4995,6 +4988,20 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 			send_sig(SIGSEGV, current, 0);
 		}
 		break;
+	case PGM_NON_SECURE_STORAGE_ACCESS:
+		kvm_s390_assert_primary_as(vcpu);
+		/*
+		 * This is normal operation; a page belonging to a protected
+		 * guest has not been imported yet. Try to import the page into
+		 * the protected guest.
+		 */
+		rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr);
+		if (rc == -EINVAL)
+			send_sig(SIGSEGV, current, 0);
+		if (rc != -ENXIO)
+			break;
+		flags = FAULT_FLAG_WRITE;
+		fallthrough;
 	case PGM_PROTECTION:
 	case PGM_SEGMENT_TRANSLATION:
 	case PGM_PAGE_TRANSLATION:
@@ -5171,7 +5178,7 @@ static void sync_regs_fmt2(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
 	}
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		preempt_disable();
 		local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
 		if (current->thread.gs_cb) {
@@ -5237,7 +5244,7 @@ static void store_regs_fmt2(struct kvm_vcpu *vcpu)
 	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
 	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	kvm_run->s.regs.diag318 = vcpu->arch.diag318_info.val;
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		preempt_disable();
 		local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
 		if (vcpu->arch.gs_enabled)
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 9b9e7fdd5380..8c40154ff50f 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -433,7 +433,6 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
 static int kvm_s390_pci_register_kvm(void *opaque, struct kvm *kvm)
 {
 	struct zpci_dev *zdev = opaque;
-	u8 status;
 	int rc;
 
 	if (!zdev)
@@ -480,13 +479,7 @@ static int kvm_s390_pci_register_kvm(void *opaque, struct kvm *kvm)
 	 */
 	zdev->gisa = (u32)virt_to_phys(&kvm->arch.sie_page2->gisa);
 
-	rc = zpci_enable_device(zdev);
-	if (rc)
-		goto clear_gisa;
-
-	/* Re-register the IOMMU that was already created */
-	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-				virt_to_phys(zdev->dma_table), &status);
+	rc = zpci_reenable_device(zdev);
 	if (rc)
 		goto clear_gisa;
 
@@ -516,7 +509,6 @@ static void kvm_s390_pci_unregister_kvm(void *opaque)
 {
 	struct zpci_dev *zdev = opaque;
 	struct kvm *kvm;
-	u8 status;
 
 	if (!zdev)
 		return;
@@ -550,12 +542,7 @@ static void kvm_s390_pci_unregister_kvm(void *opaque)
 			goto out;
 	}
 
-	if (zpci_enable_device(zdev))
-		goto out;
-
-	/* Re-register the IOMMU that was already created */
-	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-			   virt_to_phys(zdev->dma_table), &status);
+	zpci_reenable_device(zdev);
 
 out:
 	spin_lock(&kvm->arch.kzdev_list_lock);
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 9ac92dbf680d..9e28f165c114 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -56,7 +56,7 @@ TRACE_EVENT(kvm_s390_create_vcpu,
 		    __entry->sie_block = sie_block;
 		    ),
 
-	    TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+	    TP_printk("create cpu %d at 0x%p, sie block at 0x%p",
 		      __entry->id, __entry->vcpu, __entry->sie_block)
 	);
 
@@ -255,7 +255,7 @@ TRACE_EVENT(kvm_s390_enable_css,
 		    __entry->kvm = kvm;
 		    ),
 
-	    TP_printk("enabling channel I/O support (kvm @ %pK)\n",
+	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
 		      __entry->kvm)
 	);
 
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 14bbfe50033c..cd35cdbfa871 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -3,6 +3,7 @@
 # Makefile for s390-specific library files..
 #
 
+obj-y += crypto/
 lib-y += delay.o string.o uaccess.o find.o spinlock.o tishift.o
 lib-y += csum-partial.o
 obj-y += mem.o xor.o
@@ -26,4 +27,4 @@ lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 obj-$(CONFIG_EXPOLINE_EXTERN) += expoline.o
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-s390.o
-crc32-s390-y := crc32-glue.o crc32le-vx.o crc32be-vx.o
+crc32-s390-y := crc32.o crc32le-vx.o crc32be-vx.o
diff --git a/arch/s390/lib/crc32-glue.c b/arch/s390/lib/crc32.c
index 137080e61f90..3c4b344417c1 100644
--- a/arch/s390/lib/crc32-glue.c
+++ b/arch/s390/lib/crc32.c
@@ -18,8 +18,6 @@
 #define VX_ALIGNMENT		16L
 #define VX_ALIGN_MASK		(VX_ALIGNMENT - 1)
 
-static DEFINE_STATIC_KEY_FALSE(have_vxrs);
-
 /*
  * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension
  *
@@ -34,8 +32,7 @@ static DEFINE_STATIC_KEY_FALSE(have_vxrs);
 		unsigned long prealign, aligned, remaining;		    \
 		DECLARE_KERNEL_FPU_ONSTACK16(vxstate);			    \
 									    \
-		if (datalen < VX_MIN_LEN + VX_ALIGN_MASK ||		    \
-		    !static_branch_likely(&have_vxrs))			    \
+		if (datalen < VX_MIN_LEN + VX_ALIGN_MASK || !cpu_has_vx())  \
 			return ___crc32_sw(crc, data, datalen);		    \
 									    \
 		if ((unsigned long)data & VX_ALIGN_MASK) {		    \
@@ -62,27 +59,15 @@ static DEFINE_STATIC_KEY_FALSE(have_vxrs);
 
 DEFINE_CRC32_VX(crc32_le_arch, crc32_le_vgfm_16, crc32_le_base)
 DEFINE_CRC32_VX(crc32_be_arch, crc32_be_vgfm_16, crc32_be_base)
-DEFINE_CRC32_VX(crc32c_le_arch, crc32c_le_vgfm_16, crc32c_le_base)
-
-static int __init crc32_s390_init(void)
-{
-	if (cpu_have_feature(S390_CPU_FEATURE_VXRS))
-		static_branch_enable(&have_vxrs);
-	return 0;
-}
-arch_initcall(crc32_s390_init);
-
-static void __exit crc32_s390_exit(void)
-{
-}
-module_exit(crc32_s390_exit);
+DEFINE_CRC32_VX(crc32c_arch, crc32c_le_vgfm_16, crc32c_base)
 
 u32 crc32_optimizations(void)
 {
-	if (static_key_enabled(&have_vxrs))
+	if (cpu_has_vx()) {
 		return CRC32_LE_OPTIMIZATION |
 		       CRC32_BE_OPTIMIZATION |
 		       CRC32C_OPTIMIZATION;
+	}
 	return 0;
 }
 EXPORT_SYMBOL(crc32_optimizations);
diff --git a/arch/s390/lib/crypto/Kconfig b/arch/s390/lib/crypto/Kconfig
new file mode 100644
index 000000000000..e3f855ef4393
--- /dev/null
+++ b/arch/s390/lib/crypto/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA_S390
+	tristate
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_SHA256_S390
+	tristate
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_LIB_SHA256_GENERIC
diff --git a/arch/s390/lib/crypto/Makefile b/arch/s390/lib/crypto/Makefile
new file mode 100644
index 000000000000..920197967f46
--- /dev/null
+++ b/arch/s390/lib/crypto/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o
+chacha_s390-y := chacha-glue.o chacha-s390.o
+
+obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256.o
diff --git a/arch/s390/lib/crypto/chacha-glue.c b/arch/s390/lib/crypto/chacha-glue.c
new file mode 100644
index 000000000000..f95ba3483bbc
--- /dev/null
+++ b/arch/s390/lib/crypto/chacha-glue.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ChaCha stream cipher (s390 optimized)
+ *
+ * Copyright IBM Corp. 2021
+ */
+
+#define KMSG_COMPONENT "chacha_s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <crypto/chacha.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <asm/fpu.h>
+#include "chacha-s390.h"
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	/* TODO: implement hchacha_block_arch() in assembly */
+	hchacha_block_generic(state, out, nrounds);
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	/* s390 chacha20 implementation has 20 rounds hard-coded,
+	 * it cannot handle a block of data or less, but otherwise
+	 * it can handle data of arbitrary size
+	 */
+	if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !cpu_has_vx()) {
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+	} else {
+		DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
+
+		kernel_fpu_begin(&vxstate, KERNEL_VXR);
+		chacha20_vx(dst, src, bytes, &state->x[4], &state->x[12]);
+		kernel_fpu_end(&vxstate, KERNEL_VXR);
+
+		state->x[12] += round_up(bytes, CHACHA_BLOCK_SIZE) /
+				CHACHA_BLOCK_SIZE;
+	}
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return cpu_has_vx();
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+MODULE_DESCRIPTION("ChaCha stream cipher (s390 optimized)");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/s390/crypto/chacha-s390.S b/arch/s390/lib/crypto/chacha-s390.S
index 63f3102678c0..63f3102678c0 100644
--- a/arch/s390/crypto/chacha-s390.S
+++ b/arch/s390/lib/crypto/chacha-s390.S
diff --git a/arch/s390/crypto/chacha-s390.h b/arch/s390/lib/crypto/chacha-s390.h
index 733744ce30f5..733744ce30f5 100644
--- a/arch/s390/crypto/chacha-s390.h
+++ b/arch/s390/lib/crypto/chacha-s390.h
diff --git a/arch/s390/lib/crypto/sha256.c b/arch/s390/lib/crypto/sha256.c
new file mode 100644
index 000000000000..7dfe120fafab
--- /dev/null
+++ b/arch/s390/lib/crypto/sha256.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized using the CP Assist for Cryptographic Functions (CPACF)
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/cpacf.h>
+#include <crypto/internal/sha2.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_cpacf_sha256);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_cpacf_sha256))
+		cpacf_kimd(CPACF_KIMD_SHA_256, state, data,
+			   nblocks * SHA256_BLOCK_SIZE);
+	else
+		sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_cpacf_sha256);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_s390_mod_init(void)
+{
+	if (cpu_have_feature(S390_CPU_FEATURE_MSA) &&
+	    cpacf_query_func(CPACF_KIMD, CPACF_KIMD_SHA_256))
+		static_branch_enable(&have_cpacf_sha256);
+	return 0;
+}
+subsys_initcall(sha256_s390_mod_init);
+
+static void __exit sha256_s390_mod_exit(void)
+{
+}
+module_exit(sha256_s390_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 using the CP Assist for Cryptographic Functions (CPACF)");
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index a81a01c44927..ad9da4038511 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -10,11 +10,13 @@
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
+#include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/percpu.h>
 #include <linux/io.h>
 #include <asm/alternative.h>
+#include <asm/machine.h>
 #include <asm/asm.h>
 
 int spin_retry = -1;
@@ -37,6 +39,23 @@ static int __init spin_retry_setup(char *str)
 }
 __setup("spin_retry=", spin_retry_setup);
 
+static const struct ctl_table s390_spin_sysctl_table[] = {
+	{
+		.procname	= "spin_retry",
+		.data		= &spin_retry,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+static int __init init_s390_spin_sysctls(void)
+{
+	register_sysctl_init("kernel", s390_spin_sysctl_table);
+	return 0;
+}
+arch_initcall(init_s390_spin_sysctls);
+
 struct spin_wait {
 	struct spin_wait *next, *prev;
 	int node_id;
@@ -141,7 +160,7 @@ static inline void arch_spin_lock_queued(arch_spinlock_t *lp)
 
 	ix = get_lowcore()->spinlock_index++;
 	barrier();
-	lockval = SPINLOCK_LOCKVAL;	/* cpu + 1 */
+	lockval = spinlock_lockval();	/* cpu + 1 */
 	node = this_cpu_ptr(&spin_wait[ix]);
 	node->prev = node->next = NULL;
 	node_id = node->node_id;
@@ -212,7 +231,7 @@ static inline void arch_spin_lock_queued(arch_spinlock_t *lp)
 		if (count-- >= 0)
 			continue;
 		count = spin_retry;
-		if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(owner - 1))
+		if (!machine_is_lpar() || arch_vcpu_is_preempted(owner - 1))
 			smp_yield_cpu(owner - 1);
 	}
 
@@ -232,7 +251,7 @@ static inline void arch_spin_lock_classic(arch_spinlock_t *lp)
 {
 	int lockval, old, new, owner, count;
 
-	lockval = SPINLOCK_LOCKVAL;	/* cpu + 1 */
+	lockval = spinlock_lockval();	/* cpu + 1 */
 
 	/* Pass the virtual CPU to the lock holder if it is not running */
 	owner = arch_spin_yield_target(READ_ONCE(lp->lock), NULL);
@@ -255,7 +274,7 @@ static inline void arch_spin_lock_classic(arch_spinlock_t *lp)
 		if (count-- >= 0)
 			continue;
 		count = spin_retry;
-		if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(owner - 1))
+		if (!machine_is_lpar() || arch_vcpu_is_preempted(owner - 1))
 			smp_yield_cpu(owner - 1);
 	}
 }
@@ -271,7 +290,7 @@ EXPORT_SYMBOL(arch_spin_lock_wait);
 
 int arch_spin_trylock_retry(arch_spinlock_t *lp)
 {
-	int cpu = SPINLOCK_LOCKVAL;
+	int cpu = spinlock_lockval();
 	int owner, count;
 
 	for (count = spin_retry; count > 0; count--) {
@@ -337,7 +356,7 @@ void arch_spin_relax(arch_spinlock_t *lp)
 	cpu = READ_ONCE(lp->lock) & _Q_LOCK_CPU_MASK;
 	if (!cpu)
 		return;
-	if (MACHINE_IS_LPAR && !arch_vcpu_is_preempted(cpu - 1))
+	if (machine_is_lpar() && !arch_vcpu_is_preempted(cpu - 1))
 		return;
 	smp_yield_cpu(cpu - 1);
 }
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index 373fa1f01937..099de76e8b1a 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -78,50 +78,6 @@ EXPORT_SYMBOL(strnlen);
 #endif
 
 /**
- * strcpy - Copy a %NUL terminated string
- * @dest: Where to copy the string to
- * @src: Where to copy the string from
- *
- * returns a pointer to @dest
- */
-#ifdef __HAVE_ARCH_STRCPY
-char *strcpy(char *dest, const char *src)
-{
-	char *ret = dest;
-
-	asm volatile(
-		"	lghi	0,0\n"
-		"0:	mvst	%[dest],%[src]\n"
-		"	jo	0b\n"
-		: [dest] "+&a" (dest), [src] "+&a" (src)
-		:
-		: "cc", "memory", "0");
-	return ret;
-}
-EXPORT_SYMBOL(strcpy);
-#endif
-
-/**
- * strncpy - Copy a length-limited, %NUL-terminated string
- * @dest: Where to copy the string to
- * @src: Where to copy the string from
- * @n: The maximum number of bytes to copy
- *
- * The result is not %NUL-terminated if the source exceeds
- * @n bytes.
- */
-#ifdef __HAVE_ARCH_STRNCPY
-char *strncpy(char *dest, const char *src, size_t n)
-{
-	size_t len = __strnend(src, n) - src;
-	memset(dest + len, 0, n - len);
-	memcpy(dest, src, len);
-	return dest;
-}
-EXPORT_SYMBOL(strncpy);
-#endif
-
-/**
  * strcat - Append one %NUL-terminated string to another
  * @dest: The string to be appended to
  * @src: The string to append to it
@@ -181,9 +137,6 @@ EXPORT_SYMBOL(strlcat);
  * @n: The maximum numbers of bytes to copy
  *
  * returns a pointer to @dest
- *
- * Note that in contrast to strncpy, strncat ensures the result is
- * terminated.
  */
 #ifdef __HAVE_ARCH_STRNCAT
 char *strncat(char *dest, const char *src, size_t n)
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index f977b7c37efc..fa7d98fa1320 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -17,20 +17,75 @@
 #ifdef CONFIG_DEBUG_ENTRY
 void debug_user_asce(int exit)
 {
+	struct lowcore *lc = get_lowcore();
 	struct ctlreg cr1, cr7;
 
 	local_ctl_store(1, &cr1);
 	local_ctl_store(7, &cr7);
-	if (cr1.val == get_lowcore()->kernel_asce.val && cr7.val == get_lowcore()->user_asce.val)
+	if (cr1.val == lc->user_asce.val && cr7.val == lc->user_asce.val)
 		return;
 	panic("incorrect ASCE on kernel %s\n"
 	      "cr1:    %016lx cr7:  %016lx\n"
 	      "kernel: %016lx user: %016lx\n",
 	      exit ? "exit" : "entry", cr1.val, cr7.val,
-	      get_lowcore()->kernel_asce.val, get_lowcore()->user_asce.val);
+	      lc->kernel_asce.val, lc->user_asce.val);
 }
 #endif /*CONFIG_DEBUG_ENTRY */
 
+union oac {
+	unsigned int val;
+	struct {
+		struct {
+			unsigned short key : 4;
+			unsigned short	   : 4;
+			unsigned short as  : 2;
+			unsigned short	   : 4;
+			unsigned short k   : 1;
+			unsigned short a   : 1;
+		} oac1;
+		struct {
+			unsigned short key : 4;
+			unsigned short	   : 4;
+			unsigned short as  : 2;
+			unsigned short	   : 4;
+			unsigned short k   : 1;
+			unsigned short a   : 1;
+		} oac2;
+	};
+};
+
+static uaccess_kmsan_or_inline __must_check unsigned long
+raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key)
+{
+	unsigned long osize;
+	union oac spec = {
+		.oac2.key = key,
+		.oac2.as = PSW_BITS_AS_SECONDARY,
+		.oac2.k = 1,
+		.oac2.a = 1,
+	};
+	int cc;
+
+	while (1) {
+		osize = size;
+		asm_inline volatile(
+			"	lr	%%r0,%[spec]\n"
+			"0:	mvcos	%[to],%[from],%[size]\n"
+			"1:	nopr	%%r7\n"
+			CC_IPM(cc)
+			EX_TABLE_UA_MVCOS_FROM(0b, 0b)
+			EX_TABLE_UA_MVCOS_FROM(1b, 0b)
+			: CC_OUT(cc, cc), [size] "+d" (size), [to] "=Q" (*(char *)to)
+			: [spec] "d" (spec.val), [from] "Q" (*(const char __user *)from)
+			: CC_CLOBBER_LIST("memory", "0"));
+		if (CC_TRANSFORM(cc) == 0)
+			return osize - size;
+		size -= 4096;
+		to += 4096;
+		from += 4096;
+	}
+}
+
 unsigned long _copy_from_user_key(void *to, const void __user *from,
 				  unsigned long n, unsigned long key)
 {
@@ -48,6 +103,38 @@ unsigned long _copy_from_user_key(void *to, const void __user *from,
 }
 EXPORT_SYMBOL(_copy_from_user_key);
 
+static uaccess_kmsan_or_inline __must_check unsigned long
+raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key)
+{
+	unsigned long osize;
+	union oac spec = {
+		.oac1.key = key,
+		.oac1.as = PSW_BITS_AS_SECONDARY,
+		.oac1.k = 1,
+		.oac1.a = 1,
+	};
+	int cc;
+
+	while (1) {
+		osize = size;
+		asm_inline volatile(
+			"	lr	%%r0,%[spec]\n"
+			"0:	mvcos	%[to],%[from],%[size]\n"
+			"1:	nopr	%%r7\n"
+			CC_IPM(cc)
+			EX_TABLE_UA_MVCOS_TO(0b, 0b)
+			EX_TABLE_UA_MVCOS_TO(1b, 0b)
+			: CC_OUT(cc, cc), [size] "+d" (size), [to] "=Q" (*(char __user *)to)
+			: [spec] "d" (spec.val), [from] "Q" (*(const char *)from)
+			: CC_CLOBBER_LIST("memory", "0"));
+		if (CC_TRANSFORM(cc) == 0)
+			return osize - size;
+		size -= 4096;
+		to += 4096;
+		from += 4096;
+	}
+}
+
 unsigned long _copy_to_user_key(void __user *to, const void *from,
 				unsigned long n, unsigned long key)
 {
@@ -58,39 +145,3 @@ unsigned long _copy_to_user_key(void __user *to, const void *from,
 	return raw_copy_to_user_key(to, from, n, key);
 }
 EXPORT_SYMBOL(_copy_to_user_key);
-
-unsigned long __clear_user(void __user *to, unsigned long size)
-{
-	unsigned long rem;
-	union oac spec = {
-		.oac1.as = PSW_BITS_AS_SECONDARY,
-		.oac1.a = 1,
-	};
-
-	asm volatile(
-		"	lr	0,%[spec]\n"
-		"0:	mvcos	0(%[to]),0(%[zeropg]),%[size]\n"
-		"1:	jz	5f\n"
-		"	algr	%[size],%[val]\n"
-		"	slgr	%[to],%[val]\n"
-		"	j	0b\n"
-		"2:	la	%[rem],4095(%[to])\n"	/* rem = to + 4095 */
-		"	nr	%[rem],%[val]\n"	/* rem = (to + 4095) & -4096 */
-		"	slgr	%[rem],%[to]\n"
-		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
-		"	jnh	6f\n"
-		"3:	mvcos	0(%[to]),0(%[zeropg]),%[rem]\n"
-		"4:	slgr	%[size],%[rem]\n"
-		"	j	6f\n"
-		"5:	slgr	%[size],%[size]\n"
-		"6:\n"
-		EX_TABLE(0b, 2b)
-		EX_TABLE(1b, 2b)
-		EX_TABLE(3b, 6b)
-		EX_TABLE(4b, 6b)
-		: [size] "+&a" (size), [to] "+&a" (to), [rem] "=&a" (rem)
-		: [val] "a" (-4096UL), [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val)
-		: "cc", "memory", "0");
-	return size;
-}
-EXPORT_SYMBOL(__clear_user);
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index f6c2db7a8669..9726b91fe7e4 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -9,6 +9,6 @@ obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o extable.o
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_PTDUMP_CORE)	+= dump_pagetables.o
+obj-$(CONFIG_PTDUMP)		+= dump_pagetables.o
 obj-$(CONFIG_PGSTE)		+= gmap.o
 obj-$(CONFIG_PFAULT)		+= pfault.o
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 39f44b6256e0..e2a6eb92420f 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -201,7 +201,7 @@ static void cmm_set_timer(void)
 {
 	if (cmm_timed_pages_target <= 0 || cmm_timeout_seconds <= 0) {
 		if (timer_pending(&cmm_timer))
-			del_timer(&cmm_timer);
+			timer_delete(&cmm_timer);
 		return;
 	}
 	mod_timer(&cmm_timer, jiffies + secs_to_jiffies(cmm_timeout_seconds));
@@ -424,7 +424,7 @@ out_smsg:
 #endif
 	unregister_sysctl_table(cmm_sysctl_header);
 out_sysctl:
-	del_timer_sync(&cmm_timer);
+	timer_delete_sync(&cmm_timer);
 	return rc;
 }
 module_init(cmm_init);
@@ -437,7 +437,7 @@ static void __exit cmm_exit(void)
 #endif
 	unregister_oom_notifier(&cmm_oom_nb);
 	kthread_stop(cmm_thread_ptr);
-	del_timer_sync(&cmm_timer);
+	timer_delete_sync(&cmm_timer);
 	cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list);
 	cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list);
 }
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index fa54f3bc0c8d..d3e943752fa0 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+
+#include <linux/cpufeature.h>
 #include <linux/set_memory.h>
 #include <linux/ptdump.h>
 #include <linux/seq_file.h>
@@ -82,7 +84,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 	 * in which case we have two lpswe instructions in lowcore that need
 	 * to be executable.
 	 */
-	if (addr == PAGE_SIZE && (nospec_uses_trampoline() || !static_key_enabled(&cpu_has_bear)))
+	if (addr == PAGE_SIZE && (nospec_uses_trampoline() || !cpu_has_bear()))
 		return;
 	WARN_ONCE(IS_ENABLED(CONFIG_DEBUG_WX),
 		  "s390/mm: Found insecure W+X mapping at address %pS\n",
@@ -167,7 +169,7 @@ bool ptdump_check_wx(void)
 		},
 	};
 
-	if (!MACHINE_HAS_NX)
+	if (!cpu_has_nx())
 		return true;
 	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 	if (st.wx_pages) {
@@ -176,7 +178,7 @@ bool ptdump_check_wx(void)
 		return false;
 	} else {
 		pr_info("Checked W+X mappings: passed, no %sW+X pages found\n",
-			(nospec_uses_trampoline() || !static_key_enabled(&cpu_has_bear)) ?
+			(nospec_uses_trampoline() || !cpu_has_bear()) ?
 			"unexpected " : "");
 
 		return true;
diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c
index a046be1715cf..7498e858c401 100644
--- a/arch/s390/mm/extable.c
+++ b/arch/s390/mm/extable.c
@@ -73,6 +73,49 @@ static bool ex_handler_fpc(const struct exception_table_entry *ex, struct pt_reg
 	return true;
 }
 
+struct insn_ssf {
+	u64	opc1 : 8;
+	u64	r3   : 4;
+	u64	opc2 : 4;
+	u64	b1   : 4;
+	u64	d1   : 12;
+	u64	b2   : 4;
+	u64	d2   : 12;
+} __packed;
+
+static bool ex_handler_ua_mvcos(const struct exception_table_entry *ex,
+				bool from, struct pt_regs *regs)
+{
+	unsigned long uaddr, remainder;
+	struct insn_ssf *insn;
+
+	/*
+	 * If the faulting user space access crossed a page boundary retry by
+	 * limiting the access to the first page (adjust length accordingly).
+	 * Then the mvcos instruction will either complete with condition code
+	 * zero, or generate another fault where the user space access did not
+	 * cross a page boundary.
+	 * If the faulting user space access did not cross a page boundary set
+	 * length to zero and retry. In this case no user space access will
+	 * happen, and the mvcos instruction will complete with condition code
+	 * zero.
+	 * In both cases the instruction will complete with condition code
+	 * zero (copying finished), and the register which contains the
+	 * length, indicates the number of bytes copied.
+	 */
+	regs->psw.addr = extable_fixup(ex);
+	insn = (struct insn_ssf *)regs->psw.addr;
+	if (from)
+		uaddr = regs->gprs[insn->b2] + insn->d2;
+	else
+		uaddr = regs->gprs[insn->b1] + insn->d1;
+	remainder = PAGE_SIZE - (uaddr & (PAGE_SIZE - 1));
+	if (regs->gprs[insn->r3] <= remainder)
+		remainder = 0;
+	regs->gprs[insn->r3] = remainder;
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -95,6 +138,10 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_zeropad(ex, regs);
 	case EX_TYPE_FPC:
 		return ex_handler_fpc(ex, regs);
+	case EX_TYPE_UA_MVCOS_TO:
+		return ex_handler_ua_mvcos(ex, false, regs);
+	case EX_TYPE_UA_MVCOS_FROM:
+		return ex_handler_ua_mvcos(ex, true, regs);
 	}
 	panic("invalid exception table entry");
 }
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 4692136c0af1..f7da53e212f5 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -21,6 +21,7 @@
 #include <linux/ioport.h>
 #include <linux/refcount.h>
 #include <linux/pgtable.h>
+#include <asm/machine.h>
 #include <asm/diag.h>
 #include <asm/page.h>
 #include <asm/ebcdic.h>
@@ -255,7 +256,7 @@ segment_type (char* name)
 	int rc;
 	struct dcss_segment seg;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return -ENOSYS;
 
 	dcss_mkname(name, seg.dcss_name);
@@ -418,7 +419,7 @@ segment_load (char *name, int do_nonshared, unsigned long *addr,
 	struct dcss_segment *seg;
 	int rc;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return -ENOSYS;
 
 	mutex_lock(&dcss_lock);
@@ -529,6 +530,14 @@ segment_modify_shared (char *name, int do_nonshared)
 	return rc;
 }
 
+static void __dcss_diag_purge_on_cpu_0(void *data)
+{
+	struct dcss_segment *seg = (struct dcss_segment *)data;
+	unsigned long dummy;
+
+	dcss_diag(&purgeseg_scode, seg->dcss_name, &dummy, &dummy);
+}
+
 /*
  * Decrease the use count of a DCSS segment and remove
  * it from the address space if nobody is using it
@@ -537,10 +546,9 @@ segment_modify_shared (char *name, int do_nonshared)
 void
 segment_unload(char *name)
 {
-	unsigned long dummy;
 	struct dcss_segment *seg;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return;
 
 	mutex_lock(&dcss_lock);
@@ -555,7 +563,14 @@ segment_unload(char *name)
 	kfree(seg->res);
 	vmem_remove_mapping(seg->start_addr, seg->end - seg->start_addr + 1);
 	list_del(&seg->list);
-	dcss_diag(&purgeseg_scode, seg->dcss_name, &dummy, &dummy);
+	/*
+	 * Workaround for z/VM issue, where calling the DCSS unload diag on
+	 * a non-IPL CPU would cause bogus sclp maximum memory detection on
+	 * next IPL.
+	 * IPL CPU 0 cannot be set offline, so the dcss_diag() call can
+	 * directly be scheduled to that CPU.
+	 */
+	smp_call_function_single(0, __dcss_diag_purge_on_cpu_0, seg, 1);
 	kfree(seg);
 out_unlock:
 	mutex_unlock(&dcss_lock);
@@ -572,7 +587,7 @@ segment_save(char *name)
 	char cmd2[80];
 	int i, response;
 
-	if (!MACHINE_IS_VM)
+	if (!machine_is_vm())
 		return;
 
 	mutex_lock(&dcss_lock);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 9b681f74dccc..da84ff6770de 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -11,11 +11,11 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/mmu_context.h>
+#include <linux/cpufeature.h>
 #include <linux/perf_event.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
-#include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -46,16 +46,6 @@
 #include <asm/uv.h>
 #include "../kernel/entry.h"
 
-static DEFINE_STATIC_KEY_FALSE(have_store_indication);
-
-static int __init fault_init(void)
-{
-	if (test_facility(75))
-		static_branch_enable(&have_store_indication);
-	return 0;
-}
-early_initcall(fault_init);
-
 /*
  * Find out which address space caused the exception.
  */
@@ -81,7 +71,7 @@ static __always_inline bool fault_is_write(struct pt_regs *regs)
 {
 	union teid teid = { .val = regs->int_parm_long };
 
-	if (static_branch_likely(&have_store_indication))
+	if (test_facility(75))
 		return teid.fsi == TEID_FSI_STORE;
 	return false;
 }
@@ -175,6 +165,23 @@ static void dump_fault_info(struct pt_regs *regs)
 
 int show_unhandled_signals = 1;
 
+static const struct ctl_table s390_fault_sysctl_table[] = {
+	{
+		.procname	= "userprocess_debug",
+		.data		= &show_unhandled_signals,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+static int __init init_s390_fault_sysctls(void)
+{
+	register_sysctl_init("kernel", s390_fault_sysctl_table);
+	return 0;
+}
+arch_initcall(init_s390_fault_sysctls);
+
 void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
 {
 	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
@@ -369,6 +376,7 @@ void do_protection_exception(struct pt_regs *regs)
 	if (unlikely(!teid.b61)) {
 		if (user_mode(regs)) {
 			/* Low-address protection in user mode: cannot happen */
+			dump_fault_info(regs);
 			die(regs, "Low-address protection");
 		}
 		/*
@@ -377,7 +385,7 @@ void do_protection_exception(struct pt_regs *regs)
 		 */
 		return handle_fault_error_nolock(regs, 0);
 	}
-	if (unlikely(MACHINE_HAS_NX && teid.b56)) {
+	if (unlikely(cpu_has_nx() && teid.b56)) {
 		regs->int_parm_long = (teid.addr * PAGE_SIZE) | (regs->psw.addr & PAGE_MASK);
 		return handle_fault_error_nolock(regs, SEGV_ACCERR);
 	}
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 94d927785800..a94bd4870c65 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -8,6 +8,7 @@
  *		 Janosch Frank <frankja@linux.vnet.ibm.com>
  */
 
+#include <linux/cpufeature.h>
 #include <linux/kernel.h>
 #include <linux/pagewalk.h>
 #include <linux/swap.h>
@@ -20,6 +21,7 @@
 #include <linux/pgtable.h>
 #include <asm/page-states.h>
 #include <asm/pgalloc.h>
+#include <asm/machine.h>
 #include <asm/gmap.h>
 #include <asm/page.h>
 #include <asm/tlb.h>
@@ -135,7 +137,7 @@ EXPORT_SYMBOL_GPL(gmap_create);
 
 static void gmap_flush_tlb(struct gmap *gmap)
 {
-	if (MACHINE_HAS_IDTE)
+	if (cpu_has_idte())
 		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
@@ -2025,10 +2027,10 @@ static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
 	gaddr &= HPAGE_MASK;
 	pmdp_notify_gmap(gmap, pmdp, gaddr);
 	new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_GMAP_IN));
-	if (MACHINE_HAS_TLB_GUEST)
+	if (machine_has_tlb_guest())
 		__pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
 			    IDTE_GLOBAL);
-	else if (MACHINE_HAS_IDTE)
+	else if (cpu_has_idte())
 		__pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
 	else
 		__pmdp_csp(pmdp);
@@ -2103,10 +2105,10 @@ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
 			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
 						   _SEGMENT_ENTRY_GMAP_UC |
 						   _SEGMENT_ENTRY));
-			if (MACHINE_HAS_TLB_GUEST)
+			if (machine_has_tlb_guest())
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_LOCAL);
-			else if (MACHINE_HAS_IDTE)
+			else if (cpu_has_idte())
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
 			*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		}
@@ -2136,10 +2138,10 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
 						   _SEGMENT_ENTRY_GMAP_UC |
 						   _SEGMENT_ENTRY));
-			if (MACHINE_HAS_TLB_GUEST)
+			if (machine_has_tlb_guest())
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_GLOBAL);
-			else if (MACHINE_HAS_IDTE)
+			else if (cpu_has_idte())
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
 			else
 				__pmdp_csp(pmdp);
@@ -2258,9 +2260,6 @@ int s390_enable_sie(void)
 	/* Do we have pgstes? if yes, we are done */
 	if (mm_has_pgste(mm))
 		return 0;
-	/* Fail if the page tables are 2K */
-	if (!mm_alloc_pgste(mm))
-		return -EINVAL;
 	mmap_write_lock(mm);
 	mm->context.has_pgste = 1;
 	/* split thp mappings and disable thp for future mappings */
@@ -2626,31 +2625,3 @@ int s390_replace_asce(struct gmap *gmap)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(s390_replace_asce);
-
-/**
- * kvm_s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split
- * @mm:    the mm containing the folio to work on
- * @folio: the folio
- * @split: whether to split a large folio
- *
- * Context: Must be called while holding an extra reference to the folio;
- *          the mm lock should not be held.
- */
-int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
-{
-	int rc;
-
-	lockdep_assert_not_held(&mm->mmap_lock);
-	folio_wait_writeback(folio);
-	lru_add_drain_all();
-	if (split) {
-		folio_lock(folio);
-		rc = split_folio(folio);
-		folio_unlock(folio);
-
-		if (rc != -EBUSY)
-			return rc;
-	}
-	return -EAGAIN;
-}
-EXPORT_SYMBOL_GPL(kvm_s390_wiggle_split_folio);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de..e88c02c9e642 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -9,12 +9,13 @@
 #define KMSG_COMPONENT "hugetlb"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
-#include <asm/pgalloc.h>
+#include <linux/cpufeature.h>
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/security.h>
+#include <asm/pgalloc.h>
 
 /*
  * If the bit selected by single-bit bitmask "a" is set within "x", move
@@ -188,8 +189,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
@@ -248,9 +249,9 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
-	if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
+	if (cpu_has_edat1() && size == PMD_SIZE)
 		return true;
-	else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE)
+	else if (cpu_has_edat2() && size == PUD_SIZE)
 		return true;
 	else
 		return false;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f2298f7a3f21..afa085e8186c 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -8,6 +8,7 @@
  *    Copyright (C) 1995  Linus Torvalds
  */
 
+#include <linux/cpufeature.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -73,8 +74,6 @@ static void __init setup_zero_pages(void)
 {
 	unsigned long total_pages = memblock_estimated_nr_free_pages();
 	unsigned int order;
-	struct page *page;
-	int i;
 
 	/* Latest machines require a mapping granularity of 512KB */
 	order = 7;
@@ -83,16 +82,7 @@ static void __init setup_zero_pages(void)
 	while (order > 2 && (total_pages >> 10) < (1UL << order))
 		order--;
 
-	empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!empty_zero_page)
-		panic("Out of memory in setup_zero_pages");
-
-	page = virt_to_page((void *) empty_zero_page);
-	split_page(page, order);
-	for (i = 1 << order; i > 0; i--) {
-		mark_page_reserved(page);
-		page++;
-	}
+	empty_zero_page = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE << order, PAGE_SIZE);
 
 	zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
@@ -117,7 +107,7 @@ void mark_rodata_ro(void)
 {
 	unsigned long size = __end_ro_after_init - __start_ro_after_init;
 
-	if (MACHINE_HAS_NX)
+	if (cpu_has_nx())
 		system_ctl_set_bit(0, CR0_INSTRUCTION_EXEC_PROTECTION_BIT);
 	__set_memory_ro(__start_ro_after_init, __end_ro_after_init);
 	pr_info("Write protected read-only-after-init data: %luk\n", size >> 10);
@@ -165,19 +155,13 @@ static void pv_init(void)
 	swiotlb_update_mem_attributes();
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
 
-	set_max_mapnr(max_low_pfn);
-        high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-
 	pv_init();
-	kfence_split_mapping();
 
-	/* this will put all low memory onto the freelists */
-	memblock_free_all();
 	setup_zero_pages();	/* Setup zeroed pages. */
 }
 
@@ -239,16 +223,13 @@ struct s390_cma_mem_data {
 static int s390_cma_check_range(struct cma *cma, void *data)
 {
 	struct s390_cma_mem_data *mem_data;
-	unsigned long start, end;
 
 	mem_data = data;
-	start = cma_get_base(cma);
-	end = start + cma_get_size(cma);
-	if (end < mem_data->start)
-		return 0;
-	if (start >= mem_data->end)
-		return 0;
-	return -EBUSY;
+
+	if (cma_intersects(cma, mem_data->start, mem_data->end))
+		return -EBUSY;
+
+	return 0;
 }
 
 static int s390_cma_mem_notifier(struct notifier_block *nb,
@@ -285,7 +266,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long size_pages = PFN_DOWN(size);
 	int rc;
 
-	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
+	if (WARN_ON_ONCE(pgprot_val(params->pgprot) != pgprot_val(PAGE_KERNEL)))
 		return -EINVAL;
 
 	VM_BUG_ON(!mhp_range_allowed(start, size, true));
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 76f376876e0d..40a526d28184 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -51,7 +51,6 @@ static inline unsigned long mmap_base(unsigned long rnd,
 {
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
-	unsigned long gap_min, gap_max;
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
@@ -61,13 +60,7 @@ static inline unsigned long mmap_base(unsigned long rnd,
 	 * Top of mmap area (just below the process stack).
 	 * Leave at least a ~128 MB hole.
 	 */
-	gap_min = SZ_128M;
-	gap_max = (STACK_TOP / 6) * 5;
-
-	if (gap < gap_min)
-		gap = gap_min;
-	else if (gap > gap_max)
-		gap = gap_max;
+	gap = clamp(gap, SZ_128M, (STACK_TOP / 6) * 5);
 
 	return PAGE_ALIGN(STACK_TOP - gap - rnd);
 }
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index eae97fb61712..348e759840e7 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -3,6 +3,7 @@
  * Copyright IBM Corp. 2011
  * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
  */
+#include <linux/cpufeature.h>
 #include <linux/hugetlb.h>
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
@@ -27,7 +28,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 	unsigned long boundary, size;
 
 	while (start < end) {
-		if (MACHINE_HAS_EDAT1) {
+		if (cpu_has_edat1()) {
 			/* set storage keys for a 1MB frame */
 			size = 1UL << 20;
 			boundary = (start + size) & ~(size - 1);
@@ -63,7 +64,7 @@ static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr,
 	unsigned long *table, mask;
 
 	mask = 0;
-	if (MACHINE_HAS_EDAT2) {
+	if (cpu_has_edat2()) {
 		switch (dtt) {
 		case CRDTE_DTT_REGION3:
 			mask = ~(PTRS_PER_PUD * sizeof(pud_t) - 1);
@@ -77,7 +78,7 @@ static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr,
 		}
 		table = (unsigned long *)((unsigned long)old & mask);
 		crdte(*old, new, table, dtt, addr, get_lowcore()->kernel_asce.val);
-	} else if (MACHINE_HAS_IDTE) {
+	} else if (cpu_has_idte()) {
 		cspg(old, *old, new);
 	} else {
 		csp((unsigned int *)old + 1, *old, new);
@@ -373,7 +374,7 @@ int __set_memory(unsigned long addr, unsigned long numpages, unsigned long flags
 	unsigned long end;
 	int rc;
 
-	if (!MACHINE_HAS_NX)
+	if (!cpu_has_nx())
 		flags &= ~(SET_MEMORY_NX | SET_MEMORY_X);
 	if (!flags)
 		return 0;
diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index 1aac13bb8f53..e6175d75e4b0 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -9,6 +9,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <asm/asm-extable.h>
+#include <asm/asm-offsets.h>
 #include <asm/pfault.h>
 #include <asm/diag.h>
 
@@ -56,7 +57,7 @@ int __pfault_init(void)
 	if (pfault_disable)
 		return rc;
 	diag_stat_inc(DIAG_STAT_X258);
-	asm volatile(
+	asm_inline volatile(
 		"	diag	%[refbk],%[rc],0x258\n"
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
@@ -78,7 +79,7 @@ void __pfault_fini(void)
 	if (pfault_disable)
 		return;
 	diag_stat_inc(DIAG_STAT_X258);
-	asm volatile(
+	asm_inline volatile(
 		"	diag	%[refbk],0,0x258\n"
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 30387a6e98ff..d177bea0bd73 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -16,31 +16,6 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-#ifdef CONFIG_PGSTE
-
-int page_table_allocate_pgste = 0;
-EXPORT_SYMBOL(page_table_allocate_pgste);
-
-static const struct ctl_table page_table_sysctl[] = {
-	{
-		.procname	= "allocate_pgste",
-		.data		= &page_table_allocate_pgste,
-		.maxlen		= sizeof(int),
-		.mode		= S_IRUGO | S_IWUSR,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-};
-
-static int __init page_table_register_sysctl(void)
-{
-	return register_sysctl("vm", page_table_sysctl) ? 0 : -ENOMEM;
-}
-__initcall(page_table_register_sysctl);
-
-#endif /* CONFIG_PGSTE */
-
 unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
 	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER);
@@ -63,11 +38,15 @@ void crst_table_free(struct mm_struct *mm, unsigned long *table)
 static void __crst_table_upgrade(void *arg)
 {
 	struct mm_struct *mm = arg;
+	struct ctlreg asce;
 
 	/* change all active ASCEs to avoid the creation of new TLBs */
 	if (current->active_mm == mm) {
-		get_lowcore()->user_asce.val = mm->context.asce;
-		local_ctl_load(7, &get_lowcore()->user_asce);
+		asce.val = mm->context.asce;
+		get_lowcore()->user_asce = asce;
+		local_ctl_load(7, &asce);
+		if (!test_thread_flag(TIF_ASCE_PRIMARY))
+			local_ctl_load(1, &asce);
 	}
 	__tlb_flush_local();
 }
@@ -77,6 +56,8 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 	unsigned long *pgd = NULL, *p4d = NULL, *__pgd;
 	unsigned long asce_limit = mm->context.asce_limit;
 
+	mmap_assert_write_locked(mm);
+
 	/* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
 	VM_BUG_ON(asce_limit < _REGION2_SIZE);
 
@@ -100,13 +81,6 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 
 	spin_lock_bh(&mm->page_table_lock);
 
-	/*
-	 * This routine gets called with mmap_lock lock held and there is
-	 * no reason to optimize for the case of otherwise. However, if
-	 * that would ever change, the below check will let us know.
-	 */
-	VM_BUG_ON(asce_limit != mm->context.asce_limit);
-
 	if (p4d) {
 		__pgd = (unsigned long *) mm->pgd;
 		p4d_populate(mm, (p4d_t *) p4d, (pud_t *) __pgd);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index f05e62e037c2..9901934284ec 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -4,6 +4,7 @@
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
+#include <linux/cpufeature.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -23,6 +24,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/page-states.h>
+#include <asm/machine.h>
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
@@ -34,22 +36,12 @@ pgprot_t pgprot_writecombine(pgprot_t prot)
 }
 EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
-pgprot_t pgprot_writethrough(pgprot_t prot)
-{
-	/*
-	 * mio_wb_bit_mask may be set on a different CPU, but it is only set
-	 * once at init and only read afterwards.
-	 */
-	return __pgprot(pgprot_val(prot) & ~mio_wb_bit_mask);
-}
-EXPORT_SYMBOL_GPL(pgprot_writethrough);
-
 static inline void ptep_ipte_local(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, int nodat)
 {
 	unsigned long opt, asce;
 
-	if (MACHINE_HAS_TLB_GUEST) {
+	if (machine_has_tlb_guest()) {
 		opt = 0;
 		asce = READ_ONCE(mm->context.gmap_asce);
 		if (asce == 0UL || nodat)
@@ -69,7 +61,7 @@ static inline void ptep_ipte_global(struct mm_struct *mm, unsigned long addr,
 {
 	unsigned long opt, asce;
 
-	if (MACHINE_HAS_TLB_GUEST) {
+	if (machine_has_tlb_guest()) {
 		opt = 0;
 		asce = READ_ONCE(mm->context.gmap_asce);
 		if (asce == 0UL || nodat)
@@ -94,7 +86,7 @@ static inline pte_t ptep_flush_direct(struct mm_struct *mm,
 	if (unlikely(pte_val(old) & _PAGE_INVALID))
 		return old;
 	atomic_inc(&mm->context.flush_count);
-	if (MACHINE_HAS_TLB_LC &&
+	if (cpu_has_tlb_lc() &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		ptep_ipte_local(mm, addr, ptep, nodat);
 	else
@@ -173,10 +165,10 @@ static inline pgste_t pgste_update_all(pte_t pte, pgste_t pgste,
 	skey = (unsigned long) page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 	/* Transfer page changed & referenced bit to guest bits in pgste */
-	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
+	pgste = set_pgste_bit(pgste, bits << 48); /* GR bit & GC bit */
 	/* Copy page access key and fetch protection bit to pgste */
-	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
-	pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
+	pgste = clear_pgste_bit(pgste, PGSTE_ACC_BITS | PGSTE_FP_BIT);
+	pgste = set_pgste_bit(pgste, (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56);
 #endif
 	return pgste;
 
@@ -210,7 +202,7 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 	if ((pte_val(entry) & _PAGE_PRESENT) &&
 	    (pte_val(entry) & _PAGE_WRITE) &&
 	    !(pte_val(entry) & _PAGE_INVALID)) {
-		if (!MACHINE_HAS_ESOP) {
+		if (!machine_has_esop()) {
 			/*
 			 * Without enhanced suppression-on-protection force
 			 * the dirty bit on for all writable ptes.
@@ -220,7 +212,7 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 		}
 		if (!(pte_val(entry) & _PAGE_PROTECT))
 			/* This pte allows write access, set user-dirty */
-			pgste_val(pgste) |= PGSTE_UC_BIT;
+			pgste = set_pgste_bit(pgste, PGSTE_UC_BIT);
 	}
 #endif
 	set_pte(ptep, entry);
@@ -236,7 +228,7 @@ static inline pgste_t pgste_pte_notify(struct mm_struct *mm,
 
 	bits = pgste_val(pgste) & (PGSTE_IN_BIT | PGSTE_VSIE_BIT);
 	if (bits) {
-		pgste_val(pgste) ^= bits;
+		pgste = __pgste(pgste_val(pgste) ^ bits);
 		ptep_notify(mm, addr, ptep, bits);
 	}
 #endif
@@ -374,7 +366,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 static inline void pmdp_idte_local(struct mm_struct *mm,
 				   unsigned long addr, pmd_t *pmdp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (machine_has_tlb_guest())
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_LOCAL);
 	else
@@ -386,12 +378,12 @@ static inline void pmdp_idte_local(struct mm_struct *mm,
 static inline void pmdp_idte_global(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	if (MACHINE_HAS_TLB_GUEST) {
+	if (machine_has_tlb_guest()) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
 		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
-	} else if (MACHINE_HAS_IDTE) {
+	} else if (cpu_has_idte()) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
 		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
@@ -411,7 +403,7 @@ static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
 		return old;
 	atomic_inc(&mm->context.flush_count);
-	if (MACHINE_HAS_TLB_LC &&
+	if (cpu_has_tlb_lc() &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		pmdp_idte_local(mm, addr, pmdp);
 	else
@@ -505,7 +497,7 @@ EXPORT_SYMBOL(pmdp_xchg_lazy);
 static inline void pudp_idte_local(struct mm_struct *mm,
 				   unsigned long addr, pud_t *pudp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (machine_has_tlb_guest())
 		__pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_LOCAL);
 	else
@@ -515,10 +507,10 @@ static inline void pudp_idte_local(struct mm_struct *mm,
 static inline void pudp_idte_global(struct mm_struct *mm,
 				    unsigned long addr, pud_t *pudp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (machine_has_tlb_guest())
 		__pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-	else if (MACHINE_HAS_IDTE)
+	else if (cpu_has_idte())
 		__pudp_idte(addr, pudp, 0, 0, IDTE_GLOBAL);
 	else
 		/*
@@ -537,7 +529,7 @@ static inline pud_t pudp_flush_direct(struct mm_struct *mm,
 	if (pud_val(old) & _REGION_ENTRY_INVALID)
 		return old;
 	atomic_inc(&mm->context.flush_count);
-	if (MACHINE_HAS_TLB_LC &&
+	if (cpu_has_tlb_lc() &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		pudp_idte_local(mm, addr, pudp);
 	else
@@ -609,7 +601,7 @@ void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	/* the mm_has_pgste() check is done in set_pte_at() */
 	preempt_disable();
 	pgste = pgste_get_lock(ptep);
-	pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
+	pgste = clear_pgste_bit(pgste, _PGSTE_GPS_ZERO);
 	pgste_set_key(ptep, pgste, entry, mm);
 	pgste = pgste_set_pte(ptep, pgste, entry);
 	pgste_set_unlock(ptep, pgste);
@@ -622,7 +614,7 @@ void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 
 	preempt_disable();
 	pgste = pgste_get_lock(ptep);
-	pgste_val(pgste) |= PGSTE_IN_BIT;
+	pgste = set_pgste_bit(pgste, PGSTE_IN_BIT);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }
@@ -667,7 +659,7 @@ int ptep_force_prot(struct mm_struct *mm, unsigned long addr,
 		entry = clear_pte_bit(entry, __pgprot(_PAGE_INVALID));
 		entry = set_pte_bit(entry, __pgprot(_PAGE_PROTECT));
 	}
-	pgste_val(pgste) |= bit;
+	pgste = set_pgste_bit(pgste, bit);
 	pgste = pgste_set_pte(ptep, pgste, entry);
 	pgste_set_unlock(ptep, pgste);
 	return 0;
@@ -687,7 +679,7 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 	if (!(pte_val(spte) & _PAGE_INVALID) &&
 	    !((pte_val(spte) & _PAGE_PROTECT) &&
 	      !(pte_val(pte) & _PAGE_PROTECT))) {
-		pgste_val(spgste) |= PGSTE_VSIE_BIT;
+		spgste = set_pgste_bit(spgste, PGSTE_VSIE_BIT);
 		tpgste = pgste_get_lock(tptep);
 		tpte = __pte((pte_val(spte) & PAGE_MASK) |
 			     (pte_val(pte) & _PAGE_PROTECT));
@@ -745,7 +737,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 		pte_clear(mm, addr, ptep);
 	}
 	if (reset)
-		pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
+		pgste = clear_pgste_bit(pgste, _PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }
@@ -758,8 +750,8 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	/* Clear storage key ACC and F, but set R/C */
 	preempt_disable();
 	pgste = pgste_get_lock(ptep);
-	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
-	pgste_val(pgste) |= PGSTE_GR_BIT | PGSTE_GC_BIT;
+	pgste = clear_pgste_bit(pgste, PGSTE_ACC_BITS | PGSTE_FP_BIT);
+	pgste = set_pgste_bit(pgste, PGSTE_GR_BIT | PGSTE_GC_BIT);
 	ptev = pte_val(*ptep);
 	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
 		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 0);
@@ -780,13 +772,13 @@ bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr,
 
 	pgste = pgste_get_lock(ptep);
 	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
-	pgste_val(pgste) &= ~PGSTE_UC_BIT;
+	pgste = clear_pgste_bit(pgste, PGSTE_UC_BIT);
 	pte = *ptep;
 	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
 		pgste = pgste_pte_notify(mm, addr, ptep, pgste);
 		nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
 		ptep_ipte_global(mm, addr, ptep, nodat);
-		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
+		if (machine_has_esop() || !(pte_val(pte) & _PAGE_WRITE))
 			pte = set_pte_bit(pte, __pgprot(_PAGE_PROTECT));
 		else
 			pte = set_pte_bit(pte, __pgprot(_PAGE_INVALID));
@@ -842,11 +834,11 @@ again:
 	if (!ptep)
 		goto again;
 	new = old = pgste_get_lock(ptep);
-	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
-			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
+	new = clear_pgste_bit(new, PGSTE_GR_BIT | PGSTE_GC_BIT |
+				   PGSTE_ACC_BITS | PGSTE_FP_BIT);
 	keyul = (unsigned long) key;
-	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
-	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
+	new = set_pgste_bit(new, (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48);
+	new = set_pgste_bit(new, (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56);
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
 		unsigned long bits, skey;
 
@@ -857,12 +849,12 @@ again:
 		/* Set storage key ACC and FP */
 		page_set_storage_key(paddr, skey, !nq);
 		/* Merge host changed & referenced into pgste  */
-		pgste_val(new) |= bits << 52;
+		new = set_pgste_bit(new, bits << 52);
 	}
 	/* changing the guest storage key is considered a change of the page */
 	if ((pgste_val(new) ^ pgste_val(old)) &
 	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
-		pgste_val(new) |= PGSTE_UC_BIT;
+		new = set_pgste_bit(new, PGSTE_UC_BIT);
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(ptep, ptl);
@@ -950,19 +942,19 @@ again:
 		goto again;
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
-	pgste_val(new) &= ~PGSTE_GR_BIT;
+	new = clear_pgste_bit(new, PGSTE_GR_BIT);
 
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
 		paddr = pte_val(*ptep) & PAGE_MASK;
 		cc = page_reset_referenced(paddr);
 		/* Merge real referenced bit into host-set */
-		pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
+		new = set_pgste_bit(new, ((unsigned long)cc << 53) & PGSTE_HR_BIT);
 	}
 	/* Reflect guest's logical view, not physical */
 	cc |= (pgste_val(old) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 49;
 	/* Changing the guest storage key is considered a change of the page */
 	if ((pgste_val(new) ^ pgste_val(old)) & PGSTE_GR_BIT)
-		pgste_val(new) |= PGSTE_UC_BIT;
+		new = set_pgste_bit(new, PGSTE_UC_BIT);
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(ptep, ptl);
@@ -1126,7 +1118,7 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 	if (res)
 		pgstev |= _PGSTE_GPS_ZERO;
 
-	pgste_val(pgste) = pgstev;
+	pgste = __pgste(pgstev);
 	pgste_set_unlock(ptep, pgste);
 	pte_unmap_unlock(ptep, ptl);
 	return res;
@@ -1159,8 +1151,8 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
 		return -EFAULT;
 	new = pgste_get_lock(ptep);
 
-	pgste_val(new) &= ~bits;
-	pgste_val(new) |= value & bits;
+	new = clear_pgste_bit(new, bits);
+	new = set_pgste_bit(new, value & bits);
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(ptep, ptl);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 8ead999e340b..448dd6ed1069 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/memory_hotplug.h>
+#include <linux/cpufeature.h>
 #include <linux/memblock.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
@@ -249,12 +250,12 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
 		} else if (pmd_none(*pmd)) {
 			if (IS_ALIGNED(addr, PMD_SIZE) &&
 			    IS_ALIGNED(next, PMD_SIZE) &&
-			    MACHINE_HAS_EDAT1 && direct &&
+			    cpu_has_edat1() && direct &&
 			    !debug_pagealloc_enabled()) {
 				set_pmd(pmd, __pmd(__pa(addr) | prot));
 				pages++;
 				continue;
-			} else if (!direct && MACHINE_HAS_EDAT1) {
+			} else if (!direct && cpu_has_edat1()) {
 				void *new_page;
 
 				/*
@@ -335,7 +336,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
 		} else if (pud_none(*pud)) {
 			if (IS_ALIGNED(addr, PUD_SIZE) &&
 			    IS_ALIGNED(next, PUD_SIZE) &&
-			    MACHINE_HAS_EDAT2 && direct &&
+			    cpu_has_edat2() && direct &&
 			    !debug_pagealloc_enabled()) {
 				set_pud(pud, __pud(__pa(addr) | prot));
 				pages++;
@@ -659,7 +660,7 @@ void __init vmem_map_init(void)
 	 * prefix page is used to return to the previous context with
 	 * an LPSWE instruction and therefore must be executable.
 	 */
-	if (!static_key_enabled(&cpu_has_bear))
+	if (!cpu_has_bear())
 		set_memory_x(0, 1);
 	if (debug_pagealloc_enabled())
 		__set_memory_4k(__va(0), absolute_pointer(__va(0)) + ident_map_size);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9d440a0b729e..0776dfde2dba 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2919,10 +2919,16 @@ bool bpf_jit_supports_arena(void)
 
 bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 {
-	/*
-	 * Currently the verifier uses this function only to check which
-	 * atomic stores to arena are supported, and they all are.
-	 */
+	if (!in_arena)
+		return true;
+	switch (insn->code) {
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (bpf_atomic_is_load_store(insn))
+			return false;
+	}
 	return true;
 }
 
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index df73c5182990..1810e0944a4e 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -5,6 +5,6 @@
 
 obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_clp.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
-			   pci_bus.o pci_kvm_hook.o pci_report.o
+			   pci_bus.o pci_kvm_hook.o pci_report.o pci_fixup.o
 obj-$(CONFIG_PCI_IOV)	+= pci_iov.o
 obj-$(CONFIG_SYSFS)	+= pci_sysfs.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 88f72745fa59..cd6676c2d602 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -31,6 +31,7 @@
 #include <linux/lockdep.h>
 #include <linux/list_sort.h>
 
+#include <asm/machine.h>
 #include <asm/isc.h>
 #include <asm/airq.h>
 #include <asm/facility.h>
@@ -44,6 +45,7 @@
 /* list of all detected zpci devices */
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
+static DEFINE_MUTEX(zpci_add_remove_lock);
 
 static DECLARE_BITMAP(zpci_domain, ZPCI_DOMAIN_BITMAP_SIZE);
 static DEFINE_SPINLOCK(zpci_domain_lock);
@@ -69,6 +71,15 @@ EXPORT_SYMBOL_GPL(zpci_aipb);
 struct airq_iv *zpci_aif_sbv;
 EXPORT_SYMBOL_GPL(zpci_aif_sbv);
 
+void zpci_zdev_put(struct zpci_dev *zdev)
+{
+	if (!zdev)
+		return;
+	mutex_lock(&zpci_add_remove_lock);
+	kref_put_lock(&zdev->kref, zpci_release_device, &zpci_list_lock);
+	mutex_unlock(&zpci_add_remove_lock);
+}
+
 struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
 	struct zpci_dev *tmp, *zdev = NULL;
@@ -124,14 +135,13 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 	struct zpci_fib fib = {0};
 	u8 cc;
 
-	WARN_ON_ONCE(iota & 0x3fff);
 	fib.pba = base;
 	/* Work around off by one in ISM virt device */
 	if (zdev->pft == PCI_FUNC_TYPE_ISM && limit > base)
 		fib.pal = limit + (1 << 12);
 	else
 		fib.pal = limit;
-	fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
+	fib.iota = iota;
 	fib.gd = zdev->gisa;
 	cc = zpci_mod_fc(req, &fib, status);
 	if (cc)
@@ -255,7 +265,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 }
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot)
+			   pgprot_t prot)
 {
 	/*
 	 * When PCI MIO instructions are unavailable the "physical" address
@@ -265,7 +275,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
 	if (!static_branch_unlikely(&have_mio))
 		return (void __iomem *)phys_addr;
 
-	return generic_ioremap_prot(phys_addr, size, __pgprot(prot));
+	return generic_ioremap_prot(phys_addr, size, prot);
 }
 EXPORT_SYMBOL(ioremap_prot);
 
@@ -690,6 +700,23 @@ int zpci_enable_device(struct zpci_dev *zdev)
 }
 EXPORT_SYMBOL_GPL(zpci_enable_device);
 
+int zpci_reenable_device(struct zpci_dev *zdev)
+{
+	u8 status;
+	int rc;
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		return rc;
+
+	rc = zpci_iommu_register_ioat(zdev, &status);
+	if (rc)
+		zpci_disable_device(zdev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(zpci_reenable_device);
+
 int zpci_disable_device(struct zpci_dev *zdev)
 {
 	u32 fh = zdev->fh;
@@ -739,7 +766,6 @@ EXPORT_SYMBOL_GPL(zpci_disable_device);
  */
 int zpci_hot_reset_device(struct zpci_dev *zdev)
 {
-	u8 status;
 	int rc;
 
 	lockdep_assert_held(&zdev->state_lock);
@@ -758,19 +784,9 @@ int zpci_hot_reset_device(struct zpci_dev *zdev)
 			return rc;
 	}
 
-	rc = zpci_enable_device(zdev);
-	if (rc)
-		return rc;
+	rc = zpci_reenable_device(zdev);
 
-	if (zdev->dma_table)
-		rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-					virt_to_phys(zdev->dma_table), &status);
-	if (rc) {
-		zpci_disable_device(zdev);
-		return rc;
-	}
-
-	return 0;
+	return rc;
 }
 
 /**
@@ -831,6 +847,7 @@ int zpci_add_device(struct zpci_dev *zdev)
 {
 	int rc;
 
+	mutex_lock(&zpci_add_remove_lock);
 	zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", zdev->fid, zdev->fh, zdev->state);
 	rc = zpci_init_iommu(zdev);
 	if (rc)
@@ -844,12 +861,14 @@ int zpci_add_device(struct zpci_dev *zdev)
 	spin_lock(&zpci_list_lock);
 	list_add_tail(&zdev->entry, &zpci_list);
 	spin_unlock(&zpci_list_lock);
+	mutex_unlock(&zpci_add_remove_lock);
 	return 0;
 
 error_destroy_iommu:
 	zpci_destroy_iommu(zdev);
 error:
 	zpci_dbg(0, "add fid:%x, rc:%d\n", zdev->fid, rc);
+	mutex_unlock(&zpci_add_remove_lock);
 	return rc;
 }
 
@@ -919,21 +938,20 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
  * @zdev: the zpci_dev that was reserved
  *
  * Handle the case that a given zPCI function was reserved by another system.
- * After a call to this function the zpci_dev can not be found via
- * get_zdev_by_fid() anymore but may still be accessible via existing
- * references though it will not be functional anymore.
  */
 void zpci_device_reserved(struct zpci_dev *zdev)
 {
-	/*
-	 * Remove device from zpci_list as it is going away. This also
-	 * makes sure we ignore subsequent zPCI events for this device.
-	 */
-	spin_lock(&zpci_list_lock);
-	list_del(&zdev->entry);
-	spin_unlock(&zpci_list_lock);
+	lockdep_assert_held(&zdev->state_lock);
+	/* We may declare the device reserved multiple times */
+	if (zdev->state == ZPCI_FN_STATE_RESERVED)
+		return;
 	zdev->state = ZPCI_FN_STATE_RESERVED;
 	zpci_dbg(3, "rsv fid:%x\n", zdev->fid);
+	/*
+	 * The underlying device is gone. Allow the zdev to be freed
+	 * as soon as all other references are gone by accounting for
+	 * the removal as a dropped reference.
+	 */
 	zpci_zdev_put(zdev);
 }
 
@@ -941,13 +959,14 @@ void zpci_release_device(struct kref *kref)
 {
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
 
+	lockdep_assert_held(&zpci_add_remove_lock);
 	WARN_ON(zdev->state != ZPCI_FN_STATE_RESERVED);
-
-	if (zdev->zbus->bus)
-		zpci_bus_remove_device(zdev, false);
-
-	if (zdev_enabled(zdev))
-		zpci_disable_device(zdev);
+	/*
+	 * We already hold zpci_list_lock thanks to kref_put_lock().
+	 * This makes sure no new reference can be taken from the list.
+	 */
+	list_del(&zdev->entry);
+	spin_unlock(&zpci_list_lock);
 
 	if (zdev->has_hp_slot)
 		zpci_exit_slot(zdev);
@@ -1073,7 +1092,7 @@ char * __init pcibios_setup(char *str)
 		return NULL;
 	}
 	if (!strcmp(str, "nomio")) {
-		get_lowcore()->machine_flags &= ~MACHINE_FLAG_PCI_MIO;
+		clear_machine_feature(MFEATURE_PCI_MIO);
 		return NULL;
 	}
 	if (!strcmp(str, "force_floating")) {
@@ -1148,7 +1167,7 @@ static int __init pci_base_init(void)
 		return 0;
 	}
 
-	if (MACHINE_HAS_PCI_MIO) {
+	if (test_machine_feature(MFEATURE_PCI_MIO)) {
 		static_branch_enable(&have_mio);
 		system_ctl_set_bit(2, CR2_MIO_ADDRESSING_BIT);
 	}
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 39a481ec4a40..81bdb54ad5e3 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/pci.h>
 #include <linux/printk.h>
+#include <linux/dma-direct.h>
 
 #include <asm/pci_clp.h>
 #include <asm/pci_dma.h>
@@ -283,10 +284,32 @@ static struct zpci_bus *zpci_bus_alloc(int topo, bool topo_is_tid)
 	return zbus;
 }
 
+static void pci_dma_range_setup(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	u64 aligned_end, size;
+	dma_addr_t dma_start;
+	int ret;
+
+	dma_start = PAGE_ALIGN(zdev->start_dma);
+	aligned_end = PAGE_ALIGN_DOWN(zdev->end_dma + 1);
+	if (aligned_end >= dma_start)
+		size = aligned_end - dma_start;
+	else
+		size = 0;
+	WARN_ON_ONCE(size == 0);
+
+	ret = dma_direct_set_offset(&pdev->dev, 0, dma_start, size);
+	if (ret)
+		pr_err("Failed to allocate DMA range map for %s\n", pci_name(pdev));
+}
+
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
 
+	pci_dma_range_setup(pdev);
+
 	/*
 	 * With pdev->no_vf_scan the common PCI probing code does not
 	 * perform PF/VF linking.
@@ -335,6 +358,9 @@ static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev
 {
 	struct pci_dev *pdev;
 
+	if (!zdev->vfn)
+		return false;
+
 	pdev = zpci_iov_find_parent_pf(zbus, zdev);
 	if (!pdev)
 		return true;
diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h
index e86a9419d233..ae3d7a9159bd 100644
--- a/arch/s390/pci/pci_bus.h
+++ b/arch/s390/pci/pci_bus.h
@@ -21,11 +21,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev);
 void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error);
 
 void zpci_release_device(struct kref *kref);
-static inline void zpci_zdev_put(struct zpci_dev *zdev)
-{
-	if (zdev)
-		kref_put(&zdev->kref, zpci_release_device);
-}
+
+void zpci_zdev_put(struct zpci_dev *zdev);
 
 static inline void zpci_zdev_get(struct zpci_dev *zdev)
 {
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 14bf7e8d06b7..241f7251c873 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -56,7 +56,7 @@ static inline int clp_get_ilp(unsigned long *ilp)
 	int cc, exception;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"	.insn	rrf,0xb9a00000,%[mask],%[cmd],8,0\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -79,7 +79,7 @@ static __always_inline int clp_req(void *data, unsigned int lps)
 	u64 ignored;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"	.insn	rrf,0xb9a00000,%[ign],%[req],0,%[lps]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -112,6 +112,7 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
 	zdev->version = response->version;
 	zdev->maxstbl = response->maxstbl;
 	zdev->dtsm = response->dtsm;
+	zdev->rtr_avail = response->rtr;
 
 	switch (response->version) {
 	case 1:
@@ -427,6 +428,8 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
 		return;
 	}
 	zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state);
+	if (IS_ERR(zdev))
+		return;
 	list_add_tail(&zdev->entry, scan_list);
 }
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 7bd7721c1239..2fbee3887d13 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -335,6 +335,22 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 	zdev->state = ZPCI_FN_STATE_STANDBY;
 }
 
+static void zpci_event_reappear(struct zpci_dev *zdev)
+{
+	lockdep_assert_held(&zdev->state_lock);
+	/*
+	 * The zdev is in the reserved state. This means that it was presumed to
+	 * go away but there are still undropped references. Now, the platform
+	 * announced its availability again. Bring back the lingering zdev
+	 * to standby. This is safe because we hold a temporary reference
+	 * now so that it won't go away. Account for the re-appearance of the
+	 * underlying device by incrementing the reference count.
+	 */
+	zdev->state = ZPCI_FN_STATE_STANDBY;
+	zpci_zdev_get(zdev);
+	zpci_dbg(1, "rea fid:%x, fh:%x\n", zdev->fid, zdev->fh);
+}
+
 static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
@@ -358,8 +374,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 				break;
 			}
 		} else {
+			if (zdev->state == ZPCI_FN_STATE_RESERVED)
+				zpci_event_reappear(zdev);
 			/* the configuration request may be stale */
-			if (zdev->state != ZPCI_FN_STATE_STANDBY)
+			else if (zdev->state != ZPCI_FN_STATE_STANDBY)
 				break;
 			zdev->state = ZPCI_FN_STATE_CONFIGURED;
 		}
@@ -375,6 +393,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 				break;
 			}
 		} else {
+			if (zdev->state == ZPCI_FN_STATE_RESERVED)
+				zpci_event_reappear(zdev);
 			zpci_update_fh(zdev, ccdf->fh);
 		}
 		break;
diff --git a/arch/s390/pci/pci_fixup.c b/arch/s390/pci/pci_fixup.c
new file mode 100644
index 000000000000..35688b645098
--- /dev/null
+++ b/arch/s390/pci/pci_fixup.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Exceptions for specific devices,
+ *
+ * Copyright IBM Corp. 2025
+ *
+ * Author(s):
+ *   Niklas Schnelle <schnelle@linux.ibm.com>
+ */
+#include <linux/pci.h>
+
+static void zpci_ism_bar_no_mmap(struct pci_dev *pdev)
+{
+	/*
+	 * ISM's BAR is special. Drivers written for ISM know
+	 * how to handle this but others need to be aware of their
+	 * special nature e.g. to prevent attempts to mmap() it.
+	 */
+	pdev->non_mappable_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM,
+			PCI_DEVICE_ID_IBM_ISM,
+			zpci_ism_bar_no_mmap);
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index f5a75ea7629a..eb978c8012be 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -160,7 +160,7 @@ static inline int ____pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 	u64 __data;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"	.insn	rre,0xb9d20000,%[data],%[req_off]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -229,7 +229,7 @@ static inline int __pcilg_mio(u64 *data, u64 ioaddr, u64 len, u8 *status)
 	u64 __data;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"       .insn   rre,0xb9d60000,%[data],%[ioaddr_len]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -267,7 +267,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
 	int cc, exception;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"	.insn	rre,0xb9d00000,%[data],%[req_off]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -321,7 +321,7 @@ static inline int __pcistg_mio(u64 data, u64 ioaddr, u64 len, u8 *status)
 	int cc, exception;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"       .insn   rre,0xb9d40000,%[data],%[ioaddr_len]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -356,7 +356,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
 	int cc, exception;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"	.insn	rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
@@ -410,7 +410,7 @@ static inline int __pcistb_mio(const u64 *data, u64 ioaddr, u64 len, u8 *status)
 	int cc, exception;
 
 	exception = 1;
-	asm volatile (
+	asm_inline volatile (
 		"       .insn   rsy,0xeb00000000d4,%[len],%[ioaddr],%[data]\n"
 		"0:	lhi	%[exc],0\n"
 		"1:\n"
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 46f99dc164ad..51e7a28af899 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -32,9 +32,11 @@ static inline int __pcistb_mio_inuser(
 		u64 len, u8 *status)
 {
 	int cc, exception;
+	bool sacf_flag;
 
 	exception = 1;
-	asm volatile (
+	sacf_flag = enable_sacf_uaccess();
+	asm_inline volatile (
 		"	sacf	256\n"
 		"0:	.insn	rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n"
 		"1:	lhi	%[exc],0\n"
@@ -44,6 +46,7 @@ static inline int __pcistb_mio_inuser(
 		: CC_OUT(cc, cc), [len] "+d" (len), [exc] "+d" (exception)
 		: [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src))
 		: CC_CLOBBER_LIST("memory"));
+	disable_sacf_uaccess(sacf_flag);
 	*status = len >> 24 & 0xff;
 	return exception ? -ENXIO : CC_TRANSFORM(cc);
 }
@@ -54,6 +57,7 @@ static inline int __pcistg_mio_inuser(
 {
 	union register_pair ioaddr_len = {.even = (u64 __force)ioaddr, .odd = ulen};
 	int cc, exception;
+	bool sacf_flag;
 	u64 val = 0;
 	u64 cnt = ulen;
 	u8 tmp;
@@ -64,7 +68,8 @@ static inline int __pcistg_mio_inuser(
 	 * address space. pcistg then uses the user mappings.
 	 */
 	exception = 1;
-	asm volatile (
+	sacf_flag = enable_sacf_uaccess();
+	asm_inline volatile (
 		"	sacf	256\n"
 		"0:	llgc	%[tmp],0(%[src])\n"
 		"4:	sllg	%[val],%[val],8\n"
@@ -81,6 +86,7 @@ static inline int __pcistg_mio_inuser(
 		  CC_OUT(cc, cc), [ioaddr_len] "+&d" (ioaddr_len.pair)
 		:
 		: CC_CLOBBER_LIST("memory"));
+	disable_sacf_uaccess(sacf_flag);
 	*status = ioaddr_len.odd >> 24 & 0xff;
 
 	cc = exception ? -ENXIO : CC_TRANSFORM(cc);
@@ -175,8 +181,12 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	args.address = mmio_addr;
 	args.vma = vma;
 	ret = follow_pfnmap_start(&args);
-	if (ret)
-		goto out_unlock_mmap;
+	if (ret) {
+		fixup_user_fault(current->mm, mmio_addr, FAULT_FLAG_WRITE, NULL);
+		ret = follow_pfnmap_start(&args);
+		if (ret)
+			goto out_unlock_mmap;
+	}
 
 	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));
@@ -200,6 +210,7 @@ static inline int __pcilg_mio_inuser(
 		u64 ulen, u8 *status)
 {
 	union register_pair ioaddr_len = {.even = (u64 __force)ioaddr, .odd = ulen};
+	bool sacf_flag;
 	u64 cnt = ulen;
 	int shift = ulen * 8;
 	int cc, exception;
@@ -211,7 +222,8 @@ static inline int __pcilg_mio_inuser(
 	 * user address @dst
 	 */
 	exception = 1;
-	asm volatile (
+	sacf_flag = enable_sacf_uaccess();
+	asm_inline volatile (
 		"	sacf	256\n"
 		"0:	.insn	rre,0xb9d60000,%[val],%[ioaddr_len]\n"
 		"1:	lhi	%[exc],0\n"
@@ -232,10 +244,10 @@ static inline int __pcilg_mio_inuser(
 		: [ioaddr_len] "+&d" (ioaddr_len.pair), [exc] "+d" (exception),
 		  CC_OUT(cc, cc), [val] "=d" (val),
 		  [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp),
-		  [shift] "+d" (shift)
+		  [shift] "+a" (shift)
 		:
 		: CC_CLOBBER_LIST("memory"));
-
+	disable_sacf_uaccess(sacf_flag);
 	cc = exception ? -ENXIO : CC_TRANSFORM(cc);
 	/* did we write everything to the user space buffer? */
 	if (!cc && cnt != 0)
@@ -315,14 +327,18 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		goto out_unlock_mmap;
 	ret = -EACCES;
-	if (!(vma->vm_flags & VM_WRITE))
+	if (!(vma->vm_flags & VM_READ))
 		goto out_unlock_mmap;
 
 	args.vma = vma;
 	args.address = mmio_addr;
 	ret = follow_pfnmap_start(&args);
-	if (ret)
-		goto out_unlock_mmap;
+	if (ret) {
+		fixup_user_fault(current->mm, mmio_addr, 0, NULL);
+		ret = follow_pfnmap_start(&args);
+		if (ret)
+			goto out_unlock_mmap;
+	}
 
 	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 2de1ea6c3a8c..0ecad08e1b1e 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -52,7 +52,6 @@ static DEVICE_ATTR_RO(mio_enabled);
 
 static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
 {
-	u8 status;
 	int ret;
 
 	pci_stop_and_remove_bus_device(pdev);
@@ -70,16 +69,8 @@ static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
 			return ret;
 	}
 
-	ret = zpci_enable_device(zdev);
-	if (ret)
-		return ret;
+	ret = zpci_reenable_device(zdev);
 
-	if (zdev->dma_table) {
-		ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-					 virt_to_phys(zdev->dma_table), &status);
-		if (ret)
-			zpci_disable_device(zdev);
-	}
 	return ret;
 }
 
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index 855f818deb98..d5c68ade71ab 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -54,6 +54,9 @@ static struct facility_def facility_defs[] = {
 #ifdef CONFIG_HAVE_MARCH_Z15_FEATURES
 			61, /* miscellaneous-instruction-extension 3 */
 #endif
+#ifdef CONFIG_HAVE_MARCH_Z17_FEATURES
+			84, /* miscellaneous-instruction-extension 4 */
+#endif
 			-1 /* END */
 		}
 	},
diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c
index 2c44b94f82fb..1b3f43c3ac46 100644
--- a/arch/sh/boards/mach-landisk/setup.c
+++ b/arch/sh/boards/mach-landisk/setup.c
@@ -58,7 +58,7 @@ static int __init landisk_devices_setup(void)
 	/* open I/O area window */
 	paddrbase = virt_to_phys((void *)PA_AREA5_IO);
 	prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16);
-	cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, pgprot_val(prot));
+	cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, prot);
 	if (!cf_ide_base) {
 		printk("allocate_cf_area : can't open CF I/O window!\n");
 		return -ENOMEM;
diff --git a/arch/sh/boards/mach-lboxre2/setup.c b/arch/sh/boards/mach-lboxre2/setup.c
index 20d01b430f2a..e95bde207adb 100644
--- a/arch/sh/boards/mach-lboxre2/setup.c
+++ b/arch/sh/boards/mach-lboxre2/setup.c
@@ -53,7 +53,7 @@ static int __init lboxre2_devices_setup(void)
 	paddrbase = virt_to_phys((void*)PA_AREA5_IO);
 	psize = PAGE_SIZE;
 	prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16);
-	cf0_io_base = (u32)ioremap_prot(paddrbase, psize, pgprot_val(prot));
+	cf0_io_base = (u32)ioremap_prot(paddrbase, psize, prot);
 	if (!cf0_io_base) {
 		printk(KERN_ERR "%s : can't open CF I/O window!\n" , __func__ );
 		return -ENOMEM;
diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c
index f9f3b14f70d5..730c01b225bd 100644
--- a/arch/sh/boards/mach-se/7343/irq.c
+++ b/arch/sh/boards/mach-se/7343/irq.c
@@ -47,8 +47,9 @@ static void __init se7343_domain_init(void)
 {
 	int i;
 
-	se7343_irq_domain = irq_domain_add_linear(NULL, SE7343_FPGA_IRQ_NR,
-						  &irq_domain_simple_ops, NULL);
+	se7343_irq_domain = irq_domain_create_linear(NULL, SE7343_FPGA_IRQ_NR,
+						     &irq_domain_simple_ops,
+						     NULL);
 	if (unlikely(!se7343_irq_domain)) {
 		printk("Failed to get IRQ domain\n");
 		return;
@@ -70,7 +71,7 @@ static void __init se7343_gc_init(void)
 	struct irq_chip_type *ct;
 	unsigned int irq_base;
 
-	irq_base = irq_linear_revmap(se7343_irq_domain, 0);
+	irq_base = irq_find_mapping(se7343_irq_domain, 0);
 
 	gc = irq_alloc_generic_chip(DRV_NAME, 1, irq_base, se7343_irq_regs,
 				    handle_level_irq);
diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c
index efa96edd47dc..49aa3a2b1b8f 100644
--- a/arch/sh/boards/mach-se/7722/irq.c
+++ b/arch/sh/boards/mach-se/7722/irq.c
@@ -46,7 +46,7 @@ static void __init se7722_domain_init(void)
 {
 	int i;
 
-	se7722_irq_domain = irq_domain_add_linear(NULL, SE7722_FPGA_IRQ_NR,
+	se7722_irq_domain = irq_domain_create_linear(NULL, SE7722_FPGA_IRQ_NR,
 						  &irq_domain_simple_ops, NULL);
 	if (unlikely(!se7722_irq_domain)) {
 		printk("Failed to get IRQ domain\n");
@@ -69,7 +69,7 @@ static void __init se7722_gc_init(void)
 	struct irq_chip_type *ct;
 	unsigned int irq_base;
 
-	irq_base = irq_linear_revmap(se7722_irq_domain, 0);
+	irq_base = irq_find_mapping(se7722_irq_domain, 0);
 
 	gc = irq_alloc_generic_chip(DRV_NAME, 1, irq_base, se7722_irq_regs,
 				    handle_level_irq);
diff --git a/arch/sh/boards/mach-sh03/setup.c b/arch/sh/boards/mach-sh03/setup.c
index 3901b6031ad5..5c9312f334d3 100644
--- a/arch/sh/boards/mach-sh03/setup.c
+++ b/arch/sh/boards/mach-sh03/setup.c
@@ -75,7 +75,7 @@ static int __init sh03_devices_setup(void)
 	/* open I/O area window */
 	paddrbase = virt_to_phys((void *)PA_AREA5_IO);
 	prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16);
-	cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, pgprot_val(prot));
+	cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, prot);
 	if (!cf_ide_base) {
 		printk("allocate_cf_area : can't open CF I/O window!\n");
 		return -ENOMEM;
diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c
index f82d3a6a844a..c13d51b29702 100644
--- a/arch/sh/boards/mach-x3proto/gpio.c
+++ b/arch/sh/boards/mach-x3proto/gpio.c
@@ -108,7 +108,7 @@ int __init x3proto_gpio_setup(void)
 	if (unlikely(ret))
 		goto err_gpio;
 
-	x3proto_irq_domain = irq_domain_add_linear(NULL, NR_BASEBOARD_GPIOS,
+	x3proto_irq_domain = irq_domain_create_linear(NULL, NR_BASEBOARD_GPIOS,
 						   &x3proto_gpio_irq_ops, NULL);
 	if (unlikely(!x3proto_irq_domain))
 		goto err_irq;
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index 4464a2ad42ed..b6f36c938f1d 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -99,4 +99,3 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_CBC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig
index ee1b36682155..e76694aace25 100644
--- a/arch/sh/configs/ecovec24_defconfig
+++ b/arch/sh/configs/ecovec24_defconfig
@@ -128,4 +128,3 @@ CONFIG_DEBUG_FS=y
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_CBC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/edosk7705_defconfig b/arch/sh/configs/edosk7705_defconfig
index 296ed768cbbb..ee3f6db7d8da 100644
--- a/arch/sh/configs/edosk7705_defconfig
+++ b/arch/sh/configs/edosk7705_defconfig
@@ -33,4 +33,3 @@ CONFIG_CMDLINE_FROM_BOOTLOADER=y
 # CONFIG_PROC_FS is not set
 # CONFIG_SYSFS is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index 67716a44463e..da176f100e00 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -110,4 +110,3 @@ CONFIG_NLS_UTF8=y
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index 77e3185f63e4..3582af15ad86 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -56,5 +56,3 @@ CONFIG_CRYPTO_PCBC=y
 CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/kfr2r09-romimage_defconfig b/arch/sh/configs/kfr2r09-romimage_defconfig
index 42bf34181a3e..88fbb65cb9f9 100644
--- a/arch/sh/configs/kfr2r09-romimage_defconfig
+++ b/arch/sh/configs/kfr2r09-romimage_defconfig
@@ -49,4 +49,3 @@ CONFIG_TMPFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index d871623955c5..924bb3233b0b 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -111,4 +111,3 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_932=y
 CONFIG_SH_STANDARD_BIOS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 6a234761bfd7..0307bb2be79f 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -58,4 +58,3 @@ CONFIG_ROMFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_SH_STANDARD_BIOS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/magicpanelr2_defconfig b/arch/sh/configs/magicpanelr2_defconfig
index 8d443749550e..93b9aa32dc7c 100644
--- a/arch/sh/configs/magicpanelr2_defconfig
+++ b/arch/sh/configs/magicpanelr2_defconfig
@@ -86,5 +86,3 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_KOBJECT=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_FRAME_POINTER=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC16=m
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index 2d1e65cad239..31dbd8888aaa 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -87,7 +87,5 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_DEBUG_FS=y
-CONFIG_CRYPTO_MANAGER=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index 6bd6c0ae85d7..f28b8c4181c2 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -105,4 +105,3 @@ CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index cde668569cc1..3a4239f20ff1 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -103,4 +103,3 @@ CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index c863a11c7592..69568cc40396 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -87,4 +87,3 @@ CONFIG_MINIX_FS=y
 CONFIG_NLS_CODEPAGE_932=y
 CONFIG_DEBUG_FS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index 7e4f710d46c7..ecb4bdb5bb58 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -92,4 +92,3 @@ CONFIG_MINIX_FS=y
 CONFIG_NLS_CODEPAGE_932=y
 CONFIG_DEBUG_FS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig
index cd24cf08210e..9870d16d9711 100644
--- a/arch/sh/configs/sdk7780_defconfig
+++ b/arch/sh/configs/sdk7780_defconfig
@@ -136,4 +136,3 @@ CONFIG_SH_STANDARD_BIOS=y
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 78e0e7be57ee..64f9308ee586 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -101,8 +101,3 @@ CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
-CONFIG_CRC_ITU_T=y
-CONFIG_CRC7=y
-CONFIG_LIBCRC32C=y
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index 20f07aee5bde..8770a72e6a63 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -57,7 +57,6 @@ CONFIG_NET_SCH_TBF=y
 CONFIG_NET_SCH_GRED=y
 CONFIG_NET_SCH_DSMARK=y
 CONFIG_NET_SCH_NETEM=y
-CONFIG_NET_CLS_TCINDEX=y
 CONFIG_NET_CLS_ROUTE4=y
 CONFIG_NET_CLS_FW=y
 CONFIG_MTD=y
@@ -97,4 +96,3 @@ CONFIG_FRAME_POINTER=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index 00862d3c030d..b15c6406a0e8 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -56,7 +56,6 @@ CONFIG_NET_SCH_TBF=y
 CONFIG_NET_SCH_GRED=y
 CONFIG_NET_SCH_DSMARK=y
 CONFIG_NET_SCH_NETEM=y
-CONFIG_NET_CLS_TCINDEX=y
 CONFIG_NET_CLS_ROUTE4=y
 CONFIG_NET_CLS_FW=y
 CONFIG_MTD=y
@@ -123,4 +122,3 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_FRAME_POINTER=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig
index 96521271758c..9501e69eb886 100644
--- a/arch/sh/configs/se7724_defconfig
+++ b/arch/sh/configs/se7724_defconfig
@@ -128,4 +128,3 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_CBC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 48f38ec236b6..4d75c92cac10 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -120,6 +120,5 @@ CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_SHA1=y
 CONFIG_CRYPTO_DEFLATE=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=y
diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig
index 977ae405a75e..cc6292b3235a 100644
--- a/arch/sh/configs/sh2007_defconfig
+++ b/arch/sh/configs/sh2007_defconfig
@@ -193,6 +193,3 @@ CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC16=y
-CONFIG_LIBCRC32C=y
diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig
index 99a5d0760532..5b151bb2bc43 100644
--- a/arch/sh/configs/sh7710voipgw_defconfig
+++ b/arch/sh/configs/sh7710voipgw_defconfig
@@ -27,7 +27,6 @@ CONFIG_NETFILTER=y
 CONFIG_NET_SCHED=y
 CONFIG_NET_SCH_CBQ=y
 CONFIG_NET_CLS_BASIC=y
-CONFIG_NET_CLS_TCINDEX=y
 CONFIG_NET_CLS_ROUTE4=y
 CONFIG_NET_CLS_U32=y
 CONFIG_MTD=y
diff --git a/arch/sh/configs/sh7724_generic_defconfig b/arch/sh/configs/sh7724_generic_defconfig
index 5440bd0ca4ed..e6298f22623a 100644
--- a/arch/sh/configs/sh7724_generic_defconfig
+++ b/arch/sh/configs/sh7724_generic_defconfig
@@ -39,4 +39,3 @@ CONFIG_UIO_PDRV_GENIRQ=y
 # CONFIG_SYSFS is not set
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index 57923c3296cc..b77b3313157e 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -112,4 +112,3 @@ CONFIG_NLS_UTF8=y
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/sh/configs/sh7770_generic_defconfig b/arch/sh/configs/sh7770_generic_defconfig
index 4338af8d02d0..2e2b46980b58 100644
--- a/arch/sh/configs/sh7770_generic_defconfig
+++ b/arch/sh/configs/sh7770_generic_defconfig
@@ -41,4 +41,3 @@ CONFIG_UIO_PDRV_GENIRQ=y
 # CONFIG_SYSFS is not set
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 99bc0e889287..f022ada363b5 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -119,7 +119,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -265,5 +264,3 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
-CONFIG_LIBCRC32C=m
diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c
index ab9e791070b4..5442475d132e 100644
--- a/arch/sh/drivers/pci/common.c
+++ b/arch/sh/drivers/pci/common.c
@@ -90,7 +90,7 @@ static void pcibios_enable_err(struct timer_list *t)
 {
 	struct pci_channel *hose = from_timer(hose, t, err_timer);
 
-	del_timer(&hose->err_timer);
+	timer_delete(&hose->err_timer);
 	printk(KERN_DEBUG "PCI: re-enabling error IRQ.\n");
 	enable_irq(hose->err_irq);
 }
@@ -99,7 +99,7 @@ static void pcibios_enable_serr(struct timer_list *t)
 {
 	struct pci_channel *hose = from_timer(hose, t, serr_timer);
 
-	del_timer(&hose->serr_timer);
+	timer_delete(&hose->serr_timer);
 	printk(KERN_DEBUG "PCI: re-enabling system error IRQ.\n");
 	enable_irq(hose->serr_irq);
 }
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index cf5eab840d57..6d282b253815 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -19,7 +19,6 @@
 #include <asm/machvec.h>
 #include <asm/page.h>
 #include <linux/pgtable.h>
-#include <asm-generic/iomap.h>
 
 #define __IO_PREFIX     generic
 #include <asm/io_generic.h>
@@ -100,7 +99,7 @@ pfx##writes##bwlq(volatile void __iomem *mem, const void *addr,		\
 	}								\
 }									\
 									\
-static inline void pfx##reads##bwlq(volatile void __iomem *mem,		\
+static inline void pfx##reads##bwlq(const volatile void __iomem *mem,	\
 				    void *addr, unsigned int count)	\
 {									\
 	volatile type *__addr = addr;					\
@@ -114,37 +113,18 @@ static inline void pfx##reads##bwlq(volatile void __iomem *mem,		\
 __BUILD_MEMORY_STRING(__raw_, b, u8)
 __BUILD_MEMORY_STRING(__raw_, w, u16)
 
-void __raw_writesl(void __iomem *addr, const void *data, int longlen);
-void __raw_readsl(const void __iomem *addr, void *data, int longlen);
+void __raw_writesl(void volatile __iomem *addr, const void *data, int longlen);
+void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
 
 __BUILD_MEMORY_STRING(__raw_, q, u64)
 
 #define ioport_map ioport_map
-#define ioport_unmap ioport_unmap
 #define pci_iounmap pci_iounmap
 
-#define ioread8 ioread8
-#define ioread16 ioread16
-#define ioread16be ioread16be
-#define ioread32 ioread32
-#define ioread32be ioread32be
-
-#define iowrite8 iowrite8
-#define iowrite16 iowrite16
-#define iowrite16be iowrite16be
-#define iowrite32 iowrite32
-#define iowrite32be iowrite32be
-
-#define ioread8_rep ioread8_rep
-#define ioread16_rep ioread16_rep
-#define ioread32_rep ioread32_rep
-
-#define iowrite8_rep iowrite8_rep
-#define iowrite16_rep iowrite16_rep
-#define iowrite32_rep iowrite32_rep
-
 #ifdef CONFIG_HAS_IOPORT_MAP
 
+extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+
 /*
  * Slowdown I/O port space accesses for antique hardware.
  */
@@ -299,7 +279,7 @@ unsigned long long poke_real_address_q(unsigned long long addr,
 #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_NOCACHE)
 
 #define ioremap_cache(addr, size)  \
-	ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
+	ioremap_prot((addr), (size), PAGE_KERNEL)
 #endif /* CONFIG_MMU */
 
 #include <asm-generic/io.h>
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 96d938fdf224..6fe7123d38fa 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -32,10 +32,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 	set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
 }
 
-#define __pte_free_tlb(tlb, pte, addr)				\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, addr)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index ba917008d63e..7b453592adaf 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -21,10 +21,7 @@ obj-y	:= head_32.o debugtraps.o dumpstack.o				\
 	   syscalls_32.o time.o topology.o traps.o			\
 	   traps_32.o unwinder.o
 
-ifndef CONFIG_GENERIC_IOMAP
-obj-y				+= iomap.o
 obj-$(CONFIG_HAS_IOPORT_MAP)	+= ioport.o
-endif
 
 obj-y				+= sys_sh32.o
 obj-y				+= cpu/
diff --git a/arch/sh/kernel/iomap.c b/arch/sh/kernel/iomap.c
deleted file mode 100644
index 0a0dff4e66de..000000000000
--- a/arch/sh/kernel/iomap.c
+++ /dev/null
@@ -1,162 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * arch/sh/kernel/iomap.c
- *
- * Copyright (C) 2000  Niibe Yutaka
- * Copyright (C) 2005 - 2007 Paul Mundt
- */
-#include <linux/module.h>
-#include <linux/io.h>
-
-unsigned int ioread8(const void __iomem *addr)
-{
-	return readb(addr);
-}
-EXPORT_SYMBOL(ioread8);
-
-unsigned int ioread16(const void __iomem *addr)
-{
-	return readw(addr);
-}
-EXPORT_SYMBOL(ioread16);
-
-unsigned int ioread16be(const void __iomem *addr)
-{
-	return be16_to_cpu(__raw_readw(addr));
-}
-EXPORT_SYMBOL(ioread16be);
-
-unsigned int ioread32(const void __iomem *addr)
-{
-	return readl(addr);
-}
-EXPORT_SYMBOL(ioread32);
-
-unsigned int ioread32be(const void __iomem *addr)
-{
-	return be32_to_cpu(__raw_readl(addr));
-}
-EXPORT_SYMBOL(ioread32be);
-
-void iowrite8(u8 val, void __iomem *addr)
-{
-	writeb(val, addr);
-}
-EXPORT_SYMBOL(iowrite8);
-
-void iowrite16(u16 val, void __iomem *addr)
-{
-	writew(val, addr);
-}
-EXPORT_SYMBOL(iowrite16);
-
-void iowrite16be(u16 val, void __iomem *addr)
-{
-	__raw_writew(cpu_to_be16(val), addr);
-}
-EXPORT_SYMBOL(iowrite16be);
-
-void iowrite32(u32 val, void __iomem *addr)
-{
-	writel(val, addr);
-}
-EXPORT_SYMBOL(iowrite32);
-
-void iowrite32be(u32 val, void __iomem *addr)
-{
-	__raw_writel(cpu_to_be32(val), addr);
-}
-EXPORT_SYMBOL(iowrite32be);
-
-/*
- * These are the "repeat MMIO read/write" functions.
- * Note the "__raw" accesses, since we don't want to
- * convert to CPU byte order. We write in "IO byte
- * order" (we also don't have IO barriers).
- */
-static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
-{
-	while (--count >= 0) {
-		u8 data = __raw_readb(addr);
-		*dst = data;
-		dst++;
-	}
-}
-
-static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
-{
-	while (--count >= 0) {
-		u16 data = __raw_readw(addr);
-		*dst = data;
-		dst++;
-	}
-}
-
-static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
-{
-	while (--count >= 0) {
-		u32 data = __raw_readl(addr);
-		*dst = data;
-		dst++;
-	}
-}
-
-static inline void mmio_outsb(void __iomem *addr, const u8 *src, int count)
-{
-	while (--count >= 0) {
-		__raw_writeb(*src, addr);
-		src++;
-	}
-}
-
-static inline void mmio_outsw(void __iomem *addr, const u16 *src, int count)
-{
-	while (--count >= 0) {
-		__raw_writew(*src, addr);
-		src++;
-	}
-}
-
-static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
-{
-	while (--count >= 0) {
-		__raw_writel(*src, addr);
-		src++;
-	}
-}
-
-void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
-{
-	mmio_insb(addr, dst, count);
-}
-EXPORT_SYMBOL(ioread8_rep);
-
-void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
-{
-	mmio_insw(addr, dst, count);
-}
-EXPORT_SYMBOL(ioread16_rep);
-
-void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
-{
-	mmio_insl(addr, dst, count);
-}
-EXPORT_SYMBOL(ioread32_rep);
-
-void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count)
-{
-	mmio_outsb(addr, src, count);
-}
-EXPORT_SYMBOL(iowrite8_rep);
-
-void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count)
-{
-	mmio_outsw(addr, src, count);
-}
-EXPORT_SYMBOL(iowrite16_rep);
-
-void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count)
-{
-	mmio_outsl(addr, src, count);
-}
-EXPORT_SYMBOL(iowrite32_rep);
diff --git a/arch/sh/kernel/ioport.c b/arch/sh/kernel/ioport.c
index c8aff8a20164..915a3dfd9f02 100644
--- a/arch/sh/kernel/ioport.c
+++ b/arch/sh/kernel/ioport.c
@@ -23,8 +23,3 @@ void __iomem *ioport_map(unsigned long port, unsigned int nr)
 	return (void __iomem *)(port + sh_io_port_base);
 }
 EXPORT_SYMBOL(ioport_map);
-
-void ioport_unmap(void __iomem *addr)
-{
-}
-EXPORT_SYMBOL(ioport_unmap);
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index c8cad33bf250..52a7652fcff6 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 9644fe187a3f..008c30289eaa 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -71,7 +71,20 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
-	BSS_SECTION(0, PAGE_SIZE, 4)
+	__bss_start = .;
+	SBSS(0)
+	. = ALIGN(PAGE_SIZE);
+	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+		BSS_FIRST_SECTIONS
+		. = ALIGN(PAGE_SIZE);
+		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
+		*(.dynbss)
+		*(BSS_MAIN)
+		*(COMMON)
+		. = ALIGN(8);
+	}
+	__bss_stop = .;
 	_end = . ;
 
 	STABS_DEBUG
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index add35c51e017..1563dcc55fd3 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/elf.h>
 #include <linux/sched.h>
+#include <linux/sysctl.h>
 #include <linux/err.h>
 
 /*
@@ -30,6 +31,18 @@ static int __init vdso_setup(char *s)
 }
 __setup("vdso=", vdso_setup);
 
+static const struct ctl_table vdso_table[] = {
+	{
+		.procname	= "vdso_enabled",
+		.data		= &vdso_enabled,
+		.maxlen		= sizeof(vdso_enabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
 /*
  * These symbols are defined by vsyscall.o to mark the bounds
  * of the ELF DSO images included therein.
@@ -58,6 +71,14 @@ int __init vsyscall_init(void)
 	return 0;
 }
 
+static int __init vm_sysctl_init(void)
+{
+       register_sysctl_init("vm", vdso_table);
+       return 0;
+}
+
+fs_initcall(vm_sysctl_init);
+
 /* Setup a VMA at program startup for the vsyscall page */
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
diff --git a/arch/sh/lib/io.c b/arch/sh/lib/io.c
index ebcf7c0a7335..dc6345e4c53b 100644
--- a/arch/sh/lib/io.c
+++ b/arch/sh/lib/io.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 
-void __raw_readsl(const void __iomem *addr, void *datap, int len)
+void __raw_readsl(const volatile void __iomem *addr, void *datap, int len)
 {
 	u32 *data;
 
@@ -60,7 +60,7 @@ void __raw_readsl(const void __iomem *addr, void *datap, int len)
 }
 EXPORT_SYMBOL(__raw_readsl);
 
-void __raw_writesl(void __iomem *addr, const void *data, int len)
+void __raw_writesl(volatile void __iomem *addr, const void *data, int len)
 {
 	if (likely(len != 0)) {
 		int tmp1;
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 289a2fecebef..99e302eeeec1 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -290,7 +290,6 @@ void __init paging_init(void)
 	 */
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	min_low_pfn = __MEMORY_START >> PAGE_SHIFT;
-	set_max_mapnr(max_low_pfn - min_low_pfn);
 
 	nodes_clear(node_online_map);
 
@@ -331,15 +330,6 @@ unsigned int mem_init_done = 0;
 
 void __init mem_init(void)
 {
-	pg_data_t *pgdat;
-
-	high_memory = NULL;
-	for_each_online_pgdat(pgdat)
-		high_memory = max_t(void *, high_memory,
-				    __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT));
-
-	memblock_free_all();
-
 	/* Set this up early, so we can take care of the zero page */
 	cpu_cache_init();
 
diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c
index 33d20f34560f..5bbde53fb32d 100644
--- a/arch/sh/mm/ioremap.c
+++ b/arch/sh/mm/ioremap.c
@@ -73,10 +73,9 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
 #endif /* CONFIG_29BIT */
 
 void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size,
-				 unsigned long prot)
+				 pgprot_t pgprot)
 {
 	void __iomem *mapped;
-	pgprot_t pgprot = __pgprot(prot);
 
 	mapped = __ioremap_trapped(phys_addr, size);
 	if (mapped)
diff --git a/arch/sparc/configs/sparc32_defconfig b/arch/sparc/configs/sparc32_defconfig
index 5010164de3e4..f6341b063b01 100644
--- a/arch/sparc/configs/sparc32_defconfig
+++ b/arch/sparc/configs/sparc32_defconfig
@@ -94,4 +94,3 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_LIBCRC32C=m
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 0bb0d4da5227..7a7c4dec2925 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -205,7 +205,7 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_UPROBE_EVENTS=y
 CONFIG_KEYS=y
 CONFIG_CRYPTO_NULL=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
@@ -229,8 +229,6 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
-CONFIG_LIBCRC32C=m
 CONFIG_VCC=m
 CONFIG_PATA_CMD64X=y
 CONFIG_IP_PNP=y
diff --git a/arch/sparc/crypto/Kconfig b/arch/sparc/crypto/Kconfig
index e858597de89d..a6ba319c42dc 100644
--- a/arch/sparc/crypto/Kconfig
+++ b/arch/sparc/crypto/Kconfig
@@ -36,16 +36,6 @@ config CRYPTO_SHA1_SPARC64
 
 	  Architecture: sparc64
 
-config CRYPTO_SHA256_SPARC64
-	tristate "Hash functions: SHA-224 and SHA-256"
-	depends on SPARC64
-	select CRYPTO_SHA256
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: sparc64 using crypto instructions, when available
-
 config CRYPTO_SHA512_SPARC64
 	tristate "Hash functions: SHA-384 and SHA-512"
 	depends on SPARC64
diff --git a/arch/sparc/crypto/Makefile b/arch/sparc/crypto/Makefile
index a2d7fca40cb4..701c39edb0d7 100644
--- a/arch/sparc/crypto/Makefile
+++ b/arch/sparc/crypto/Makefile
@@ -4,7 +4,6 @@
 #
 
 obj-$(CONFIG_CRYPTO_SHA1_SPARC64) += sha1-sparc64.o
-obj-$(CONFIG_CRYPTO_SHA256_SPARC64) += sha256-sparc64.o
 obj-$(CONFIG_CRYPTO_SHA512_SPARC64) += sha512-sparc64.o
 obj-$(CONFIG_CRYPTO_MD5_SPARC64) += md5-sparc64.o
 
@@ -13,7 +12,6 @@ obj-$(CONFIG_CRYPTO_DES_SPARC64) += des-sparc64.o
 obj-$(CONFIG_CRYPTO_CAMELLIA_SPARC64) += camellia-sparc64.o
 
 sha1-sparc64-y := sha1_asm.o sha1_glue.o
-sha256-sparc64-y := sha256_asm.o sha256_glue.o
 sha512-sparc64-y := sha512_asm.o sha512_glue.o
 md5-sparc64-y := md5_asm.o md5_glue.o
 
diff --git a/arch/sparc/crypto/aes_asm.S b/arch/sparc/crypto/aes_asm.S
index 155cefb98520..f291174a72a1 100644
--- a/arch/sparc/crypto/aes_asm.S
+++ b/arch/sparc/crypto/aes_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 #define ENCRYPT_TWO_ROUNDS(KEY_BASE, I0, I1, T0, T1) \
 	AES_EROUND01(KEY_BASE +  0, I0, I1, T0) \
 	AES_EROUND23(KEY_BASE +  2, I0, I1, T1) \
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index e3d2138ff9e2..359f22643b05 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -27,11 +27,10 @@
 #include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
+#include <asm/opcodes.h>
 #include <asm/pstate.h>
 #include <asm/elf.h>
 
-#include "opcodes.h"
-
 struct aes_ops {
 	void (*encrypt)(const u64 *key, const u32 *input, u32 *output);
 	void (*decrypt)(const u64 *key, const u32 *input, u32 *output);
@@ -321,7 +320,7 @@ static void ctr_crypt_final(const struct crypto_sparc64_aes_ctx *ctx,
 {
 	u8 *ctrblk = walk->iv;
 	u64 keystream[AES_BLOCK_SIZE / sizeof(u64)];
-	u8 *src = walk->src.virt.addr;
+	const u8 *src = walk->src.virt.addr;
 	u8 *dst = walk->dst.virt.addr;
 	unsigned int nbytes = walk->nbytes;
 
diff --git a/arch/sparc/crypto/camellia_asm.S b/arch/sparc/crypto/camellia_asm.S
index dcdc9193fcd7..8471b346ef54 100644
--- a/arch/sparc/crypto/camellia_asm.S
+++ b/arch/sparc/crypto/camellia_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 #define CAMELLIA_6ROUNDS(KEY_BASE, I0, I1) \
 	CAMELLIA_F(KEY_BASE +  0, I1, I0, I1) \
 	CAMELLIA_F(KEY_BASE +  2, I0, I1, I0) \
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index aaa9714378e6..e7a1e1c42b99 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -15,11 +15,10 @@
 #include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
+#include <asm/opcodes.h>
 #include <asm/pstate.h>
 #include <asm/elf.h>
 
-#include "opcodes.h"
-
 #define CAMELLIA_MIN_KEY_SIZE        16
 #define CAMELLIA_MAX_KEY_SIZE        32
 #define CAMELLIA_BLOCK_SIZE          16
diff --git a/arch/sparc/crypto/des_asm.S b/arch/sparc/crypto/des_asm.S
index 7157468a679d..d534446cbef9 100644
--- a/arch/sparc/crypto/des_asm.S
+++ b/arch/sparc/crypto/des_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 	.align	32
 ENTRY(des_sparc64_key_expand)
 	/* %o0=input_key, %o1=output_key */
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index a499102bf706..e50ec4cd57cd 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -16,11 +16,10 @@
 #include <crypto/internal/skcipher.h>
 
 #include <asm/fpumacro.h>
+#include <asm/opcodes.h>
 #include <asm/pstate.h>
 #include <asm/elf.h>
 
-#include "opcodes.h"
-
 struct des_sparc64_ctx {
 	u64 encrypt_expkey[DES_EXPKEY_WORDS / 2];
 	u64 decrypt_expkey[DES_EXPKEY_WORDS / 2];
diff --git a/arch/sparc/crypto/md5_asm.S b/arch/sparc/crypto/md5_asm.S
index 7a6637455f37..60b544e4d205 100644
--- a/arch/sparc/crypto/md5_asm.S
+++ b/arch/sparc/crypto/md5_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 ENTRY(md5_sparc64_transform)
 	/* %o0 = digest, %o1 = data, %o2 = rounds */
 	VISEntryHalf
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 511db98d590a..b3615f0cdf62 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -14,121 +14,104 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <asm/elf.h>
+#include <asm/opcodes.h>
+#include <asm/pstate.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/md5.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
-#include <asm/pstate.h>
-#include <asm/elf.h>
-
-#include "opcodes.h"
+struct sparc_md5_state {
+	__le32 hash[MD5_HASH_WORDS];
+	u64 byte_count;
+};
 
-asmlinkage void md5_sparc64_transform(u32 *digest, const char *data,
+asmlinkage void md5_sparc64_transform(__le32 *digest, const char *data,
 				      unsigned int rounds);
 
 static int md5_sparc64_init(struct shash_desc *desc)
 {
-	struct md5_state *mctx = shash_desc_ctx(desc);
+	struct sparc_md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = MD5_H0;
-	mctx->hash[1] = MD5_H1;
-	mctx->hash[2] = MD5_H2;
-	mctx->hash[3] = MD5_H3;
-	le32_to_cpu_array(mctx->hash, 4);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
 }
 
-static void __md5_sparc64_update(struct md5_state *sctx, const u8 *data,
-				 unsigned int len, unsigned int partial)
-{
-	unsigned int done = 0;
-
-	sctx->byte_count += len;
-	if (partial) {
-		done = MD5_HMAC_BLOCK_SIZE - partial;
-		memcpy((u8 *)sctx->block + partial, data, done);
-		md5_sparc64_transform(sctx->hash, (u8 *)sctx->block, 1);
-	}
-	if (len - done >= MD5_HMAC_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / MD5_HMAC_BLOCK_SIZE;
-
-		md5_sparc64_transform(sctx->hash, data + done, rounds);
-		done += rounds * MD5_HMAC_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->block, data + done, len - done);
-}
-
 static int md5_sparc64_update(struct shash_desc *desc, const u8 *data,
 			      unsigned int len)
 {
-	struct md5_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->byte_count % MD5_HMAC_BLOCK_SIZE;
-
-	/* Handle the fast case right here */
-	if (partial + len < MD5_HMAC_BLOCK_SIZE) {
-		sctx->byte_count += len;
-		memcpy((u8 *)sctx->block + partial, data, len);
-	} else
-		__md5_sparc64_update(sctx, data, len, partial);
+	struct sparc_md5_state *sctx = shash_desc_ctx(desc);
 
-	return 0;
+	sctx->byte_count += round_down(len, MD5_HMAC_BLOCK_SIZE);
+	md5_sparc64_transform(sctx->hash, data, len / MD5_HMAC_BLOCK_SIZE);
+	return len - round_down(len, MD5_HMAC_BLOCK_SIZE);
 }
 
 /* Add padding and return the message digest. */
-static int md5_sparc64_final(struct shash_desc *desc, u8 *out)
+static int md5_sparc64_finup(struct shash_desc *desc, const u8 *src,
+			     unsigned int offset, u8 *out)
 {
-	struct md5_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	u32 *dst = (u32 *)out;
-	__le64 bits;
-	static const u8 padding[MD5_HMAC_BLOCK_SIZE] = { 0x80, };
-
-	bits = cpu_to_le64(sctx->byte_count << 3);
-
-	/* Pad out to 56 mod 64 and append length */
-	index = sctx->byte_count % MD5_HMAC_BLOCK_SIZE;
-	padlen = (index < 56) ? (56 - index) : ((MD5_HMAC_BLOCK_SIZE+56) - index);
-
-	/* We need to fill a whole block for __md5_sparc64_update() */
-	if (padlen <= 56) {
-		sctx->byte_count += padlen;
-		memcpy((u8 *)sctx->block + index, padding, padlen);
-	} else {
-		__md5_sparc64_update(sctx, padding, padlen, index);
-	}
-	__md5_sparc64_update(sctx, (const u8 *)&bits, sizeof(bits), 56);
+	struct sparc_md5_state *sctx = shash_desc_ctx(desc);
+	__le64 block[MD5_BLOCK_WORDS] = {};
+	u8 *p = memcpy(block, src, offset);
+	__le32 *dst = (__le32 *)out;
+	__le64 *pbits;
+	int i;
+
+	src = p;
+	p += offset;
+	*p++ = 0x80;
+	sctx->byte_count += offset;
+	pbits = &block[(MD5_BLOCK_WORDS / (offset > 55 ? 1 : 2)) - 1];
+	*pbits = cpu_to_le64(sctx->byte_count << 3);
+	md5_sparc64_transform(sctx->hash, src, (pbits - block + 1) / 8);
+	memzero_explicit(block, sizeof(block));
 
 	/* Store state in digest */
 	for (i = 0; i < MD5_HASH_WORDS; i++)
 		dst[i] = sctx->hash[i];
 
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
 	return 0;
 }
 
 static int md5_sparc64_export(struct shash_desc *desc, void *out)
 {
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
+	struct sparc_md5_state *sctx = shash_desc_ctx(desc);
+	union {
+		u8 *u8;
+		u32 *u32;
+		u64 *u64;
+	} p = { .u8 = out };
+	int i;
 
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		put_unaligned(le32_to_cpu(sctx->hash[i]), p.u32++);
+	put_unaligned(sctx->byte_count, p.u64);
 	return 0;
 }
 
 static int md5_sparc64_import(struct shash_desc *desc, const void *in)
 {
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
+	struct sparc_md5_state *sctx = shash_desc_ctx(desc);
+	union {
+		const u8 *u8;
+		const u32 *u32;
+		const u64 *u64;
+	} p = { .u8 = in };
+	int i;
 
+	for (i = 0; i < MD5_HASH_WORDS; i++)
+		sctx->hash[i] = cpu_to_le32(get_unaligned(p.u32++));
+	sctx->byte_count = get_unaligned(p.u64);
 	return 0;
 }
 
@@ -136,15 +119,16 @@ static struct shash_alg alg = {
 	.digestsize	=	MD5_DIGEST_SIZE,
 	.init		=	md5_sparc64_init,
 	.update		=	md5_sparc64_update,
-	.final		=	md5_sparc64_final,
+	.finup		=	md5_sparc64_finup,
 	.export		=	md5_sparc64_export,
 	.import		=	md5_sparc64_import,
-	.descsize	=	sizeof(struct md5_state),
-	.statesize	=	sizeof(struct md5_state),
+	.descsize	=	sizeof(struct sparc_md5_state),
+	.statesize	=	sizeof(struct sparc_md5_state),
 	.base		=	{
 		.cra_name	=	"md5",
 		.cra_driver_name=	"md5-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/sparc/crypto/sha1_asm.S b/arch/sparc/crypto/sha1_asm.S
index 7d8bf354f0e7..00b46bac1b08 100644
--- a/arch/sparc/crypto/sha1_asm.S
+++ b/arch/sparc/crypto/sha1_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 ENTRY(sha1_sparc64_transform)
 	/* %o0 = digest, %o1 = data, %o2 = rounds */
 	VISEntryHalf
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 06b7becfcb21..ef19d5023b1b 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -11,124 +11,44 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <asm/elf.h>
+#include <asm/opcodes.h>
+#include <asm/pstate.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
-#include <asm/pstate.h>
-#include <asm/elf.h>
-
-#include "opcodes.h"
-
-asmlinkage void sha1_sparc64_transform(u32 *digest, const char *data,
-				       unsigned int rounds);
-
-static void __sha1_sparc64_update(struct sha1_state *sctx, const u8 *data,
-				  unsigned int len, unsigned int partial)
-{
-	unsigned int done = 0;
-
-	sctx->count += len;
-	if (partial) {
-		done = SHA1_BLOCK_SIZE - partial;
-		memcpy(sctx->buffer + partial, data, done);
-		sha1_sparc64_transform(sctx->state, sctx->buffer, 1);
-	}
-	if (len - done >= SHA1_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
-
-		sha1_sparc64_transform(sctx->state, data + done, rounds);
-		done += rounds * SHA1_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buffer, data + done, len - done);
-}
+asmlinkage void sha1_sparc64_transform(struct sha1_state *digest,
+				       const u8 *data, int rounds);
 
 static int sha1_sparc64_update(struct shash_desc *desc, const u8 *data,
 			       unsigned int len)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA1_BLOCK_SIZE) {
-		sctx->count += len;
-		memcpy(sctx->buffer + partial, data, len);
-	} else
-		__sha1_sparc64_update(sctx, data, len, partial);
-
-	return 0;
+	return sha1_base_do_update_blocks(desc, data, len,
+					  sha1_sparc64_transform);
 }
 
 /* Add padding and return the message digest. */
-static int sha1_sparc64_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be32 *dst = (__be32 *)out;
-	__be64 bits;
-	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
-
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64 and append length */
-	index = sctx->count % SHA1_BLOCK_SIZE;
-	padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index);
-
-	/* We need to fill a whole block for __sha1_sparc64_update() */
-	if (padlen <= 56) {
-		sctx->count += padlen;
-		memcpy(sctx->buffer + index, padding, padlen);
-	} else {
-		__sha1_sparc64_update(sctx, padding, padlen, index);
-	}
-	__sha1_sparc64_update(sctx, (const u8 *)&bits, sizeof(bits), 56);
-
-	/* Store state in digest */
-	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha1_sparc64_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha1_sparc64_import(struct shash_desc *desc, const void *in)
+static int sha1_sparc64_finup(struct shash_desc *desc, const u8 *src,
+			      unsigned int len, u8 *out)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-
-	return 0;
+	sha1_base_do_finup(desc, src, len, sha1_sparc64_transform);
+	return sha1_base_finish(desc, out);
 }
 
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_sparc64_update,
-	.final		=	sha1_sparc64_final,
-	.export		=	sha1_sparc64_export,
-	.import		=	sha1_sparc64_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
+	.finup		=	sha1_sparc64_finup,
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
deleted file mode 100644
index 285561a1cde5..000000000000
--- a/arch/sparc/crypto/sha256_glue.c
+++ /dev/null
@@ -1,210 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Glue code for SHA256 hashing optimized for sparc64 crypto opcodes.
- *
- * This is based largely upon crypto/sha256_generic.c
- *
- * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
- * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
- * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
- * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-
-#include <asm/pstate.h>
-#include <asm/elf.h>
-
-#include "opcodes.h"
-
-asmlinkage void sha256_sparc64_transform(u32 *digest, const char *data,
-					 unsigned int rounds);
-
-static void __sha256_sparc64_update(struct sha256_state *sctx, const u8 *data,
-				    unsigned int len, unsigned int partial)
-{
-	unsigned int done = 0;
-
-	sctx->count += len;
-	if (partial) {
-		done = SHA256_BLOCK_SIZE - partial;
-		memcpy(sctx->buf + partial, data, done);
-		sha256_sparc64_transform(sctx->state, sctx->buf, 1);
-	}
-	if (len - done >= SHA256_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;
-
-		sha256_sparc64_transform(sctx->state, data + done, rounds);
-		done += rounds * SHA256_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buf, data + done, len - done);
-}
-
-static int sha256_sparc64_update(struct shash_desc *desc, const u8 *data,
-				 unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA256_BLOCK_SIZE) {
-		sctx->count += len;
-		memcpy(sctx->buf + partial, data, len);
-	} else
-		__sha256_sparc64_update(sctx, data, len, partial);
-
-	return 0;
-}
-
-static int sha256_sparc64_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be32 *dst = (__be32 *)out;
-	__be64 bits;
-	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
-
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64 and append length */
-	index = sctx->count % SHA256_BLOCK_SIZE;
-	padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56) - index);
-
-	/* We need to fill a whole block for __sha256_sparc64_update() */
-	if (padlen <= 56) {
-		sctx->count += padlen;
-		memcpy(sctx->buf + index, padding, padlen);
-	} else {
-		__sha256_sparc64_update(sctx, padding, padlen, index);
-	}
-	__sha256_sparc64_update(sctx, (const u8 *)&bits, sizeof(bits), 56);
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha224_sparc64_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA256_DIGEST_SIZE];
-
-	sha256_sparc64_final(desc, D);
-
-	memcpy(hash, D, SHA224_DIGEST_SIZE);
-	memzero_explicit(D, SHA256_DIGEST_SIZE);
-
-	return 0;
-}
-
-static int sha256_sparc64_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int sha256_sparc64_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg sha256_alg = {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	sha256_sparc64_update,
-	.final		=	sha256_sparc64_final,
-	.export		=	sha256_sparc64_export,
-	.import		=	sha256_sparc64_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"sha256-sparc64",
-		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static struct shash_alg sha224_alg = {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	sha256_sparc64_update,
-	.final		=	sha224_sparc64_final,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"sha224-sparc64",
-		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static bool __init sparc64_has_sha256_opcode(void)
-{
-	unsigned long cfr;
-
-	if (!(sparc64_elf_hwcap & HWCAP_SPARC_CRYPTO))
-		return false;
-
-	__asm__ __volatile__("rd %%asr26, %0" : "=r" (cfr));
-	if (!(cfr & CFR_SHA256))
-		return false;
-
-	return true;
-}
-
-static int __init sha256_sparc64_mod_init(void)
-{
-	if (sparc64_has_sha256_opcode()) {
-		int ret = crypto_register_shash(&sha224_alg);
-		if (ret < 0)
-			return ret;
-
-		ret = crypto_register_shash(&sha256_alg);
-		if (ret < 0) {
-			crypto_unregister_shash(&sha224_alg);
-			return ret;
-		}
-
-		pr_info("Using sparc64 sha256 opcode optimized SHA-256/SHA-224 implementation\n");
-		return 0;
-	}
-	pr_info("sparc64 sha256 opcode not available.\n");
-	return -ENODEV;
-}
-
-static void __exit sha256_sparc64_mod_fini(void)
-{
-	crypto_unregister_shash(&sha224_alg);
-	crypto_unregister_shash(&sha256_alg);
-}
-
-module_init(sha256_sparc64_mod_init);
-module_exit(sha256_sparc64_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated");
-
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha256");
-
-#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha512_asm.S b/arch/sparc/crypto/sha512_asm.S
index b2f6e6728802..9932b4fe1b59 100644
--- a/arch/sparc/crypto/sha512_asm.S
+++ b/arch/sparc/crypto/sha512_asm.S
@@ -1,9 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 ENTRY(sha512_sparc64_transform)
 	/* %o0 = digest, %o1 = data, %o2 = rounds */
 	VISEntry
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index d66efa4ec59a..47b9277b6877 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -10,115 +10,42 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <asm/elf.h>
+#include <asm/opcodes.h>
+#include <asm/pstate.h>
 #include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-
-#include <asm/pstate.h>
-#include <asm/elf.h>
-
-#include "opcodes.h"
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 asmlinkage void sha512_sparc64_transform(u64 *digest, const char *data,
 					 unsigned int rounds);
 
-static void __sha512_sparc64_update(struct sha512_state *sctx, const u8 *data,
-				    unsigned int len, unsigned int partial)
+static void sha512_block(struct sha512_state *sctx, const u8 *src, int blocks)
 {
-	unsigned int done = 0;
-
-	if ((sctx->count[0] += len) < len)
-		sctx->count[1]++;
-	if (partial) {
-		done = SHA512_BLOCK_SIZE - partial;
-		memcpy(sctx->buf + partial, data, done);
-		sha512_sparc64_transform(sctx->state, sctx->buf, 1);
-	}
-	if (len - done >= SHA512_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
-
-		sha512_sparc64_transform(sctx->state, data + done, rounds);
-		done += rounds * SHA512_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buf, data + done, len - done);
+	sha512_sparc64_transform(sctx->state, src, blocks);
 }
 
 static int sha512_sparc64_update(struct shash_desc *desc, const u8 *data,
 				 unsigned int len)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA512_BLOCK_SIZE) {
-		if ((sctx->count[0] += len) < len)
-			sctx->count[1]++;
-		memcpy(sctx->buf + partial, data, len);
-	} else
-		__sha512_sparc64_update(sctx, data, len, partial);
-
-	return 0;
+	return sha512_base_do_update_blocks(desc, data, len, sha512_block);
 }
 
-static int sha512_sparc64_final(struct shash_desc *desc, u8 *out)
+static int sha512_sparc64_finup(struct shash_desc *desc, const u8 *src,
+				unsigned int len, u8 *out)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be64 *dst = (__be64 *)out;
-	__be64 bits[2];
-	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
-
-	/* Save number of bits */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128 and append length */
-	index = sctx->count[0] % SHA512_BLOCK_SIZE;
-	padlen = (index < 112) ? (112 - index) : ((SHA512_BLOCK_SIZE+112) - index);
-
-	/* We need to fill a whole block for __sha512_sparc64_update() */
-	if (padlen <= 112) {
-		if ((sctx->count[0] += padlen) < padlen)
-			sctx->count[1]++;
-		memcpy(sctx->buf + index, padding, padlen);
-	} else {
-		__sha512_sparc64_update(sctx, padding, padlen, index);
-	}
-	__sha512_sparc64_update(sctx, (const u8 *)&bits, sizeof(bits), 112);
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha384_sparc64_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[64];
-
-	sha512_sparc64_final(desc, D);
-
-	memcpy(hash, D, 48);
-	memzero_explicit(D, 64);
-
-	return 0;
+	sha512_base_do_finup(desc, src, len, sha512_block);
+	return sha512_base_finish(desc, out);
 }
 
 static struct shash_alg sha512 = {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	sha512_sparc64_update,
-	.final		=	sha512_sparc64_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	sha512_sparc64_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"sha512-sparc64",
@@ -132,8 +59,8 @@ static struct shash_alg sha384 = {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	sha512_sparc64_update,
-	.final		=	sha384_sparc64_final,
-	.descsize	=	sizeof(struct sha512_state),
+	.finup		=	sha512_sparc64_finup,
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"sha384-sparc64",
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c714ca6a05aa..e7a9cdd498dc 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/crypto/opcodes.h b/arch/sparc/include/asm/opcodes.h
index 417b6a10a337..ebfda6eb49b2 100644
--- a/arch/sparc/crypto/opcodes.h
+++ b/arch/sparc/include/asm/opcodes.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _OPCODES_H
-#define _OPCODES_H
+#ifndef _SPARC_ASM_OPCODES_H
+#define _SPARC_ASM_OPCODES_H
 
 #define SPARC_CR_OPCODE_PRIORITY	300
 
@@ -97,4 +97,4 @@
 #define MOVXTOD_G7_F62		\
 	.word	0xbfb02307;
 
-#endif /* _OPCODES_H */
+#endif /* _SPARC_ASM_OPCODES_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 2b7f358762c1..dc28f2c4eee3 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -936,7 +936,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 		pte_t *ptep, pte_t pte, unsigned int nr)
 {
-	arch_enter_lazy_mmu_mode();
 	for (;;) {
 		__set_pte_at(mm, addr, ptep, pte, 0);
 		if (--nr == 0)
@@ -945,7 +944,6 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 		pte_val(pte) += PAGE_SIZE;
 		addr += PAGE_SIZE;
 	}
-	arch_leave_lazy_mmu_mode();
 }
 #define set_ptes set_ptes
 
diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c
index ab657b359789..f4fb82b019bb 100644
--- a/arch/sparc/kernel/led.c
+++ b/arch/sparc/kernel/led.c
@@ -84,7 +84,7 @@ static ssize_t led_proc_write(struct file *file, const char __user *buffer,
 	/* before we change anything we want to stop any running timers,
 	 * otherwise calls such as on will have no persistent effect
 	 */
-	del_timer_sync(&led_blink_timer);
+	timer_delete_sync(&led_blink_timer);
 
 	if (!strcmp(buf, "on")) {
 		auxio_set_led(AUXIO_LED_ON);
@@ -134,7 +134,7 @@ static int __init led_init(void)
 static void __exit led_exit(void)
 {
 	remove_proc_entry("led", NULL);
-	del_timer_sync(&led_blink_timer);
+	timer_delete_sync(&led_blink_timer);
 }
 
 module_init(led_init);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index f02a283a8e8f..cae4d33002a5 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1668,8 +1668,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		if (!sparc_perf_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, &data, regs))
-			sparc_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	finish_clock = sched_clock();
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 727f99d333b3..83e45eb6c095 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -512,3 +512,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 5724d0f356eb..5cf9781d68b4 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -4,6 +4,7 @@
 
 asflags-y := -ansi -DST_DIV0=0x02
 
+obj-y                 += crypto/
 lib-$(CONFIG_SPARC32) += ashrdi3.o
 lib-$(CONFIG_SPARC32) += memcpy.o memset.o
 lib-y                 += strlen.o
@@ -54,4 +55,4 @@ obj-$(CONFIG_SPARC64) += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
 obj-$(CONFIG_CRC32_ARCH) += crc32-sparc.o
-crc32-sparc-y := crc32_glue.o crc32c_asm.o
+crc32-sparc-y := crc32.o crc32c_asm.o
diff --git a/arch/sparc/lib/crc32_glue.c b/arch/sparc/lib/crc32.c
index 41076d2b1fd2..40d4720a42a1 100644
--- a/arch/sparc/lib/crc32_glue.c
+++ b/arch/sparc/lib/crc32.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Glue code for CRC32C optimized for sparc64 crypto opcodes.
+/* CRC32c (Castagnoli), sparc64 crc32c opcode accelerated
  *
  * This is based largely upon arch/x86/crypto/crc32c-intel.c
  *
@@ -17,7 +17,7 @@
 #include <asm/pstate.h>
 #include <asm/elf.h>
 
-static DEFINE_STATIC_KEY_FALSE(have_crc32c_opcode);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32c_opcode);
 
 u32 crc32_le_arch(u32 crc, const u8 *data, size_t len)
 {
@@ -27,17 +27,17 @@ EXPORT_SYMBOL(crc32_le_arch);
 
 void crc32c_sparc64(u32 *crcp, const u64 *data, size_t len);
 
-u32 crc32c_le_arch(u32 crc, const u8 *data, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *data, size_t len)
 {
 	size_t n = -(uintptr_t)data & 7;
 
 	if (!static_branch_likely(&have_crc32c_opcode))
-		return crc32c_le_base(crc, data, len);
+		return crc32c_base(crc, data, len);
 
 	if (n) {
 		/* Data isn't 8-byte aligned.  Align it. */
 		n = min(n, len);
-		crc = crc32c_le_base(crc, data, n);
+		crc = crc32c_base(crc, data, n);
 		data += n;
 		len -= n;
 	}
@@ -48,10 +48,10 @@ u32 crc32c_le_arch(u32 crc, const u8 *data, size_t len)
 		len -= n;
 	}
 	if (len)
-		crc = crc32c_le_base(crc, data, len);
+		crc = crc32c_base(crc, data, len);
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *data, size_t len)
 {
@@ -74,7 +74,7 @@ static int __init crc32_sparc_init(void)
 	pr_info("Using sparc64 crc32c opcode optimized CRC32C implementation\n");
 	return 0;
 }
-arch_initcall(crc32_sparc_init);
+subsys_initcall(crc32_sparc_init);
 
 static void __exit crc32_sparc_exit(void)
 {
diff --git a/arch/sparc/lib/crc32c_asm.S b/arch/sparc/lib/crc32c_asm.S
index ee454fa6aed6..4db873850f44 100644
--- a/arch/sparc/lib/crc32c_asm.S
+++ b/arch/sparc/lib/crc32c_asm.S
@@ -1,10 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 
-#include "../crypto/opcodes.h"
-
 ENTRY(crc32c_sparc64)
 	/* %o0=crc32p, %o1=data_ptr, %o2=len */
 	VISEntryHalf
diff --git a/arch/sparc/lib/crypto/Kconfig b/arch/sparc/lib/crypto/Kconfig
new file mode 100644
index 000000000000..e5c3e4d3dba6
--- /dev/null
+++ b/arch/sparc/lib/crypto/Kconfig
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_SHA256_SPARC64
+	tristate
+	depends on SPARC64
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_LIB_SHA256_GENERIC
diff --git a/arch/sparc/lib/crypto/Makefile b/arch/sparc/lib/crypto/Makefile
new file mode 100644
index 000000000000..75ee244ad6f7
--- /dev/null
+++ b/arch/sparc/lib/crypto/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_SHA256_SPARC64) += sha256-sparc64.o
+sha256-sparc64-y := sha256.o sha256_asm.o
diff --git a/arch/sparc/lib/crypto/sha256.c b/arch/sparc/lib/crypto/sha256.c
new file mode 100644
index 000000000000..8bdec2db08b3
--- /dev/null
+++ b/arch/sparc/lib/crypto/sha256.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SHA-256 accelerated using the sparc64 sha256 opcodes
+ *
+ * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
+ * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <asm/elf.h>
+#include <asm/opcodes.h>
+#include <asm/pstate.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha256_opcodes);
+
+asmlinkage void sha256_sparc64_transform(u32 state[SHA256_STATE_WORDS],
+					 const u8 *data, size_t nblocks);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_sha256_opcodes))
+		sha256_sparc64_transform(state, data, nblocks);
+	else
+		sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_sha256_opcodes);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_sparc64_mod_init(void)
+{
+	unsigned long cfr;
+
+	if (!(sparc64_elf_hwcap & HWCAP_SPARC_CRYPTO))
+		return 0;
+
+	__asm__ __volatile__("rd %%asr26, %0" : "=r" (cfr));
+	if (!(cfr & CFR_SHA256))
+		return 0;
+
+	static_branch_enable(&have_sha256_opcodes);
+	pr_info("Using sparc64 sha256 opcode optimized SHA-256/SHA-224 implementation\n");
+	return 0;
+}
+subsys_initcall(sha256_sparc64_mod_init);
+
+static void __exit sha256_sparc64_mod_exit(void)
+{
+}
+module_exit(sha256_sparc64_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 accelerated using the sparc64 sha256 opcodes");
diff --git a/arch/sparc/crypto/sha256_asm.S b/arch/sparc/lib/crypto/sha256_asm.S
index 0b39ec7d7ca2..ddcdd3daf31e 100644
--- a/arch/sparc/crypto/sha256_asm.S
+++ b/arch/sparc/lib/crypto/sha256_asm.S
@@ -1,11 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
+#include <asm/opcodes.h>
 #include <asm/visasm.h>
 
-#include "opcodes.h"
-
 ENTRY(sha256_sparc64_transform)
-	/* %o0 = digest, %o1 = data, %o2 = rounds */
+	/* %o0 = state, %o1 = data, %o2 = nblocks */
 	VISEntryHalf
 	ld	[%o0 + 0x00], %f0
 	ld	[%o0 + 0x04], %f1
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index eee601a0d2cf..80504148d8a5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index d96a14ffceeb..fdc93dd12c3e 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -232,19 +232,7 @@ static void __init taint_real_pages(void)
 	}
 }
 
-static void map_high_region(unsigned long start_pfn, unsigned long end_pfn)
-{
-	unsigned long tmp;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	printk("mapping high region %08lx - %08lx\n", start_pfn, end_pfn);
-#endif
-
-	for (tmp = start_pfn; tmp < end_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
-}
-
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	int i;
 
@@ -274,23 +262,6 @@ void __init mem_init(void)
 	memset(sparc_valid_addr_bitmap, 0, i << 2);
 
 	taint_real_pages();
-
-	max_mapnr = last_valid_pfn - pfn_base;
-	high_memory = __va(max_low_pfn << PAGE_SHIFT);
-	memblock_free_all();
-
-	for (i = 0; sp_banks[i].num_bytes != 0; i++) {
-		unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT;
-		unsigned long end_pfn = (sp_banks[i].base_addr + sp_banks[i].num_bytes) >> PAGE_SHIFT;
-
-		if (end_pfn <= highstart_pfn)
-			continue;
-
-		if (start_pfn < highstart_pfn)
-			start_pfn = highstart_pfn;
-
-		map_high_region(start_pfn, end_pfn);
-	}
 }
 
 void sparc_flush_page_to_ram(struct page *page)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 05882bca5b73..760818950464 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2505,10 +2505,6 @@ static void __init register_page_bootmem_info(void)
 }
 void __init mem_init(void)
 {
-	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
-
-	memblock_free_all();
-
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
 	 * might set fields in deferred struct pages that have not yet been
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 8648a50afe88..a35ddcca5e76 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -52,8 +52,10 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
+	struct tlb_batch *tb;
 
+	preempt_disable();
+	tb = this_cpu_ptr(&tlb_batch);
 	tb->active = 1;
 }
 
@@ -64,6 +66,7 @@ void arch_leave_lazy_mmu_mode(void)
 	if (tb->tlb_nr)
 		flush_tlb_pending();
 	tb->active = 0;
+	preempt_enable();
 }
 
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index 50ec2978cda5..fdc4a8f5a49c 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -22,7 +22,7 @@ targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 --no-undefined \
+VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 \
 			-z max-page-size=8192
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
@@ -101,7 +101,6 @@ $(obj)/vdso32.so.dbg: FORCE \
 quiet_cmd_vdso = VDSO    $@
       cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
-		sh $(src)/checkundef.sh '$(OBJDUMP)' '$@'
+		       -T $(filter %.lds,$^) $(filter %.o,$^)
 
-VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic
+VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic --no-undefined
diff --git a/arch/sparc/vdso/checkundef.sh b/arch/sparc/vdso/checkundef.sh
deleted file mode 100644
index 2d85876ffc32..000000000000
--- a/arch/sparc/vdso/checkundef.sh
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-objdump="$1"
-file="$2"
-$objdump -t "$file" | grep '*UUND*' | grep -v '#scratch' > /dev/null 2>&1
-if [ $? -eq 1 ]; then
-    exit 0
-else
-    echo "$file: undefined symbols found" >&2
-    exit 1
-fi
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 18051b1cfce0..79509c7f39de 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -12,6 +12,7 @@ config UML
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_STRNCPY_FROM_USER
 	select ARCH_HAS_STRNLEN_USER
+	select ARCH_HAS_STRICT_KERNEL_RWX
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_KASAN if X86_64
 	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 1d36a613aad8..9ed792e565c9 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -154,5 +154,6 @@ MRPROPER_FILES += $(HOST_DIR)/include/generated
 archclean:
 	@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
 		-o -name '*.gcov' \) -type f -print | xargs rm -f
+	$(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) clean
 
 export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING DEV_NULL_PATH
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
index ede40a160c5e..9cb196070614 100644
--- a/arch/um/drivers/Kconfig
+++ b/arch/um/drivers/Kconfig
@@ -345,16 +345,20 @@ config UML_RTC
 	  by providing a fake RTC clock that causes a wakeup at the right
 	  time.
 
-config UML_PCI_OVER_VIRTIO
-	bool "Enable PCI over VIRTIO device simulation"
-	# in theory, just VIRTIO is enough, but that causes recursion
-	depends on VIRTIO_UML
+config UML_PCI
+	bool
 	select FORCE_PCI
 	select UML_IOMEM_EMULATION
 	select UML_DMA_EMULATION
 	select PCI_MSI
 	select PCI_LOCKLESS_CONFIG
 
+config UML_PCI_OVER_VIRTIO
+	bool "Enable PCI over VIRTIO device simulation"
+	# in theory, just VIRTIO is enough, but that causes recursion
+	depends on VIRTIO_UML
+	select UML_PCI
+
 config UML_PCI_OVER_VIRTIO_DEVICE_ID
 	int "set the virtio device ID for PCI emulation"
 	default -1
diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index 57882e6bc215..0a5820343ad3 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -60,7 +60,8 @@ obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o
 obj-$(CONFIG_UML_RANDOM) += random.o
 obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
 obj-$(CONFIG_UML_RTC) += rtc.o
-obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virt-pci.o
+obj-$(CONFIG_UML_PCI) += virt-pci.o
+obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virtio_pcidev.o
 
 # pcap_user.o must be added explicitly.
 USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o vde_user.o vector_user.o
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index da985e0dc69a..ca08c91f47a3 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -79,7 +79,7 @@ static int __init rng_init (void)
 	if (err < 0)
 		goto err_out_cleanup_hw;
 
-	sigio_broken(random_fd);
+	sigio_broken();
 	hwrng.name = RNG_MODULE_NAME;
 	hwrng.read = rng_dev_read;
 
diff --git a/arch/um/drivers/rtc_user.c b/arch/um/drivers/rtc_user.c
index 7c3cec4c68cf..51e79f3148cd 100644
--- a/arch/um/drivers/rtc_user.c
+++ b/arch/um/drivers/rtc_user.c
@@ -39,7 +39,7 @@ int uml_rtc_start(bool timetravel)
 		}
 
 		/* apparently timerfd won't send SIGIO, use workaround */
-		sigio_broken(uml_rtc_irq_fds[0]);
+		sigio_broken();
 		err = add_sigio_fd(uml_rtc_irq_fds[0]);
 		if (err < 0) {
 			close(uml_rtc_irq_fds[0]);
diff --git a/arch/um/drivers/ubd.h b/arch/um/drivers/ubd.h
index f016fe15499f..2985c14661f4 100644
--- a/arch/um/drivers/ubd.h
+++ b/arch/um/drivers/ubd.h
@@ -7,8 +7,10 @@
 #ifndef __UM_UBD_USER_H
 #define __UM_UBD_USER_H
 
-extern int start_io_thread(unsigned long sp, int *fds_out);
-extern int io_thread(void *arg);
+#include <os.h>
+
+int start_io_thread(struct os_helper_thread **td_out, int *fd_out);
+void *io_thread(void *arg);
 extern int kernel_fd;
 
 extern int ubd_read_poll(int timeout);
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 0b1e61f72fb3..4de6613e7468 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -474,12 +474,12 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 }
 
 /* Only changed by ubd_init, which is an initcall. */
-static int io_pid = -1;
+static struct os_helper_thread *io_td;
 
 static void kill_io_thread(void)
 {
-	if(io_pid != -1)
-		os_kill_process(io_pid, 1);
+	if (io_td)
+		os_kill_helper_thread(io_td);
 }
 
 __uml_exitcall(kill_io_thread);
@@ -1104,8 +1104,8 @@ static int __init ubd_init(void)
 
 late_initcall(ubd_init);
 
-static int __init ubd_driver_init(void){
-	unsigned long stack;
+static int __init ubd_driver_init(void)
+{
 	int err;
 
 	/* Set by CONFIG_BLK_DEV_UBD_SYNC or ubd=sync.*/
@@ -1114,13 +1114,11 @@ static int __init ubd_driver_init(void){
 		/* Letting ubd=sync be like using ubd#s= instead of ubd#= is
 		 * enough. So use anyway the io thread. */
 	}
-	stack = alloc_stack(0, 0);
-	io_pid = start_io_thread(stack + PAGE_SIZE, &thread_fd);
-	if(io_pid < 0){
+	err = start_io_thread(&io_td, &thread_fd);
+	if (err < 0) {
 		printk(KERN_ERR
 		       "ubd : Failed to start I/O thread (errno = %d) - "
-		       "falling back to synchronous I/O\n", -io_pid);
-		io_pid = -1;
+		       "falling back to synchronous I/O\n", -err);
 		return 0;
 	}
 	err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr,
@@ -1496,12 +1494,11 @@ int kernel_fd = -1;
 /* Only changed by the io thread. XXX: currently unused. */
 static int io_count;
 
-int io_thread(void *arg)
+void *io_thread(void *arg)
 {
 	int n, count, written, res;
 
-	os_set_pdeathsig();
-	os_fix_helper_signals();
+	os_fix_helper_thread_signals();
 
 	while(1){
 		n = bulk_req_safe_read(
@@ -1543,5 +1540,5 @@ int io_thread(void *arg)
 		} while (written < n);
 	}
 
-	return 0;
+	return NULL;
 }
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index b4f8b8e60564..c5e6545f6fcf 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -25,9 +25,9 @@
 
 static struct pollfd kernel_pollfd;
 
-int start_io_thread(unsigned long sp, int *fd_out)
+int start_io_thread(struct os_helper_thread **td_out, int *fd_out)
 {
-	int pid, fds[2], err;
+	int fds[2], err;
 
 	err = os_pipe(fds, 1, 1);
 	if(err < 0){
@@ -47,14 +47,14 @@ int start_io_thread(unsigned long sp, int *fd_out)
 		goto out_close;
 	}
 
-	pid = clone(io_thread, (void *) sp, CLONE_FILES | CLONE_VM, NULL);
-	if(pid < 0){
-		err = -errno;
-		printk("start_io_thread - clone failed : errno = %d\n", errno);
+	err = os_run_helper_thread(td_out, io_thread, NULL);
+	if (err < 0) {
+		printk("%s - failed to run helper thread, err = %d\n",
+		       __func__, -err);
 		goto out_close;
 	}
 
-	return(pid);
+	return 0;
 
  out_close:
 	os_close_file(fds[0]);
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 85b129e2b70b..b97bb52dd562 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1112,7 +1112,7 @@ static int vector_net_close(struct net_device *dev)
 	struct vector_private *vp = netdev_priv(dev);
 
 	netif_stop_queue(dev);
-	del_timer(&vp->tl);
+	timer_delete(&vp->tl);
 
 	vp->opened = false;
 
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index dd5580f975cc..b83b5a765d4e 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -5,52 +5,19 @@
  */
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
 #include <linux/logic_iomem.h>
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
-#include <linux/virtio_pcidev.h>
-#include <linux/virtio-uml.h>
-#include <linux/delay.h>
 #include <linux/msi.h>
 #include <linux/unaligned.h>
 #include <irq_kern.h>
 
+#include "virt-pci.h"
+
 #define MAX_DEVICES 8
 #define MAX_MSI_VECTORS 32
 #define CFG_SPACE_SIZE 4096
 
-/* for MSI-X we have a 32-bit payload */
-#define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32))
-#define NUM_IRQ_MSGS	10
-
-struct um_pci_message_buffer {
-	struct virtio_pcidev_msg hdr;
-	u8 data[8];
-};
-
-struct um_pci_device {
-	struct virtio_device *vdev;
-
-	/* for now just standard BARs */
-	u8 resptr[PCI_STD_NUM_BARS];
-
-	struct virtqueue *cmd_vq, *irq_vq;
-
-#define UM_PCI_WRITE_BUFS	20
-	struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1];
-	void *extra_ptrs[UM_PCI_WRITE_BUFS + 1];
-	DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS);
-
-#define UM_PCI_STAT_WAITING	0
-	unsigned long status;
-
-	int irq;
-
-	bool platform;
-};
-
 struct um_pci_device_reg {
 	struct um_pci_device *dev;
 	void __iomem *iomem;
@@ -65,179 +32,15 @@ static struct irq_domain *um_pci_inner_domain;
 static struct irq_domain *um_pci_msi_domain;
 static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)];
 
-static unsigned int um_pci_max_delay_us = 40000;
-module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644);
-
-static int um_pci_get_buf(struct um_pci_device *dev, bool *posted)
-{
-	int i;
-
-	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
-		if (!test_and_set_bit(i, dev->used_bufs))
-			return i;
-	}
-
-	*posted = false;
-	return UM_PCI_WRITE_BUFS;
-}
-
-static void um_pci_free_buf(struct um_pci_device *dev, void *buf)
-{
-	int i;
-
-	if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) {
-		kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]);
-		dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL;
-		return;
-	}
-
-	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
-		if (buf == &dev->bufs[i]) {
-			kfree(dev->extra_ptrs[i]);
-			dev->extra_ptrs[i] = NULL;
-			WARN_ON(!test_and_clear_bit(i, dev->used_bufs));
-			return;
-		}
-	}
-
-	WARN_ON(1);
-}
-
-static int um_pci_send_cmd(struct um_pci_device *dev,
-			   struct virtio_pcidev_msg *cmd,
-			   unsigned int cmd_size,
-			   const void *extra, unsigned int extra_size,
-			   void *out, unsigned int out_size)
-{
-	struct scatterlist out_sg, extra_sg, in_sg;
-	struct scatterlist *sgs_list[] = {
-		[0] = &out_sg,
-		[1] = extra ? &extra_sg : &in_sg,
-		[2] = extra ? &in_sg : NULL,
-	};
-	struct um_pci_message_buffer *buf;
-	int delay_count = 0;
-	bool bounce_out;
-	int ret, len;
-	int buf_idx;
-	bool posted;
-
-	if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf)))
-		return -EINVAL;
-
-	switch (cmd->op) {
-	case VIRTIO_PCIDEV_OP_CFG_WRITE:
-	case VIRTIO_PCIDEV_OP_MMIO_WRITE:
-	case VIRTIO_PCIDEV_OP_MMIO_MEMSET:
-		/* in PCI, writes are posted, so don't wait */
-		posted = !out;
-		WARN_ON(!posted);
-		break;
-	default:
-		posted = false;
-		break;
-	}
-
-	bounce_out = !posted && cmd_size <= sizeof(*cmd) &&
-		     out && out_size <= sizeof(buf->data);
-
-	buf_idx = um_pci_get_buf(dev, &posted);
-	buf = &dev->bufs[buf_idx];
-	memcpy(buf, cmd, cmd_size);
-
-	if (posted && extra && extra_size > sizeof(buf) - cmd_size) {
-		dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size,
-						   GFP_ATOMIC);
-
-		if (!dev->extra_ptrs[buf_idx]) {
-			um_pci_free_buf(dev, buf);
-			return -ENOMEM;
-		}
-		extra = dev->extra_ptrs[buf_idx];
-	} else if (extra && extra_size <= sizeof(buf) - cmd_size) {
-		memcpy((u8 *)buf + cmd_size, extra, extra_size);
-		cmd_size += extra_size;
-		extra_size = 0;
-		extra = NULL;
-		cmd = (void *)buf;
-	} else {
-		cmd = (void *)buf;
-	}
-
-	sg_init_one(&out_sg, cmd, cmd_size);
-	if (extra)
-		sg_init_one(&extra_sg, extra, extra_size);
-	/* allow stack for small buffers */
-	if (bounce_out)
-		sg_init_one(&in_sg, buf->data, out_size);
-	else if (out)
-		sg_init_one(&in_sg, out, out_size);
-
-	/* add to internal virtio queue */
-	ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list,
-				extra ? 2 : 1,
-				out ? 1 : 0,
-				cmd, GFP_ATOMIC);
-	if (ret) {
-		um_pci_free_buf(dev, buf);
-		return ret;
-	}
-
-	if (posted) {
-		virtqueue_kick(dev->cmd_vq);
-		return 0;
-	}
-
-	/* kick and poll for getting a response on the queue */
-	set_bit(UM_PCI_STAT_WAITING, &dev->status);
-	virtqueue_kick(dev->cmd_vq);
-	ret = 0;
-
-	while (1) {
-		void *completed = virtqueue_get_buf(dev->cmd_vq, &len);
-
-		if (completed == buf)
-			break;
-
-		if (completed)
-			um_pci_free_buf(dev, completed);
-
-		if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) ||
-			      ++delay_count > um_pci_max_delay_us,
-			      "um virt-pci delay: %d", delay_count)) {
-			ret = -EIO;
-			break;
-		}
-		udelay(1);
-	}
-	clear_bit(UM_PCI_STAT_WAITING, &dev->status);
-
-	if (bounce_out)
-		memcpy(out, buf->data, out_size);
-
-	um_pci_free_buf(dev, buf);
-
-	return ret;
-}
-
 static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 					  int size)
 {
 	struct um_pci_device_reg *reg = priv;
 	struct um_pci_device *dev = reg->dev;
-	struct virtio_pcidev_msg hdr = {
-		.op = VIRTIO_PCIDEV_OP_CFG_READ,
-		.size = size,
-		.addr = offset,
-	};
-	/* max 8, we might not use it all */
-	u8 data[8];
 
 	if (!dev)
 		return ULONG_MAX;
 
-	memset(data, 0xff, sizeof(data));
-
 	switch (size) {
 	case 1:
 	case 2:
@@ -251,23 +54,7 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 		return ULONG_MAX;
 	}
 
-	if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size))
-		return ULONG_MAX;
-
-	switch (size) {
-	case 1:
-		return data[0];
-	case 2:
-		return le16_to_cpup((void *)data);
-	case 4:
-		return le32_to_cpup((void *)data);
-#ifdef CONFIG_64BIT
-	case 8:
-		return le64_to_cpup((void *)data);
-#endif
-	default:
-		return ULONG_MAX;
-	}
+	return dev->ops->cfgspace_read(dev, offset, size);
 }
 
 static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size,
@@ -275,42 +62,24 @@ static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size,
 {
 	struct um_pci_device_reg *reg = priv;
 	struct um_pci_device *dev = reg->dev;
-	struct {
-		struct virtio_pcidev_msg hdr;
-		/* maximum size - we may only use parts of it */
-		u8 data[8];
-	} msg = {
-		.hdr = {
-			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
-			.size = size,
-			.addr = offset,
-		},
-	};
 
 	if (!dev)
 		return;
 
 	switch (size) {
 	case 1:
-		msg.data[0] = (u8)val;
-		break;
 	case 2:
-		put_unaligned_le16(val, (void *)msg.data);
-		break;
 	case 4:
-		put_unaligned_le32(val, (void *)msg.data);
-		break;
 #ifdef CONFIG_64BIT
 	case 8:
-		put_unaligned_le64(val, (void *)msg.data);
-		break;
 #endif
+		break;
 	default:
 		WARN(1, "invalid config space write size %d\n", size);
 		return;
 	}
 
-	WARN_ON(um_pci_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0));
+	dev->ops->cfgspace_write(dev, offset, size, val);
 }
 
 static const struct logic_iomem_ops um_pci_device_cfgspace_ops = {
@@ -318,30 +87,14 @@ static const struct logic_iomem_ops um_pci_device_cfgspace_ops = {
 	.write = um_pci_cfgspace_write,
 };
 
-static void um_pci_bar_copy_from(void *priv, void *buffer,
-				 unsigned int offset, int size)
+static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
+				     int size)
 {
 	u8 *resptr = priv;
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct virtio_pcidev_msg hdr = {
-		.op = VIRTIO_PCIDEV_OP_MMIO_READ,
-		.bar = *resptr,
-		.size = size,
-		.addr = offset,
-	};
-
-	memset(buffer, 0xff, size);
-
-	um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, buffer, size);
-}
-
-static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
-				     int size)
-{
-	/* 8 is maximum size - we may only use parts of it */
-	u8 data[8];
+	u8 bar = *resptr;
 
 	switch (size) {
 	case 1:
@@ -352,72 +105,60 @@ static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
 #endif
 		break;
 	default:
-		WARN(1, "invalid config space read size %d\n", size);
+		WARN(1, "invalid bar read size %d\n", size);
 		return ULONG_MAX;
 	}
 
-	um_pci_bar_copy_from(priv, data, offset, size);
+	return dev->ops->bar_read(dev, bar, offset, size);
+}
+
+static void um_pci_bar_write(void *priv, unsigned int offset, int size,
+			     unsigned long val)
+{
+	u8 *resptr = priv;
+	struct um_pci_device *dev = container_of(resptr - *resptr,
+						 struct um_pci_device,
+						 resptr[0]);
+	u8 bar = *resptr;
 
 	switch (size) {
 	case 1:
-		return data[0];
 	case 2:
-		return le16_to_cpup((void *)data);
 	case 4:
-		return le32_to_cpup((void *)data);
 #ifdef CONFIG_64BIT
 	case 8:
-		return le64_to_cpup((void *)data);
 #endif
+		break;
 	default:
-		return ULONG_MAX;
+		WARN(1, "invalid bar write size %d\n", size);
+		return;
 	}
+
+	dev->ops->bar_write(dev, bar, offset, size, val);
 }
 
-static void um_pci_bar_copy_to(void *priv, unsigned int offset,
-			       const void *buffer, int size)
+static void um_pci_bar_copy_from(void *priv, void *buffer,
+				 unsigned int offset, int size)
 {
 	u8 *resptr = priv;
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct virtio_pcidev_msg hdr = {
-		.op = VIRTIO_PCIDEV_OP_MMIO_WRITE,
-		.bar = *resptr,
-		.size = size,
-		.addr = offset,
-	};
+	u8 bar = *resptr;
 
-	um_pci_send_cmd(dev, &hdr, sizeof(hdr), buffer, size, NULL, 0);
+	dev->ops->bar_copy_from(dev, bar, buffer, offset, size);
 }
 
-static void um_pci_bar_write(void *priv, unsigned int offset, int size,
-			     unsigned long val)
+static void um_pci_bar_copy_to(void *priv, unsigned int offset,
+			       const void *buffer, int size)
 {
-	/* maximum size - we may only use parts of it */
-	u8 data[8];
-
-	switch (size) {
-	case 1:
-		data[0] = (u8)val;
-		break;
-	case 2:
-		put_unaligned_le16(val, (void *)data);
-		break;
-	case 4:
-		put_unaligned_le32(val, (void *)data);
-		break;
-#ifdef CONFIG_64BIT
-	case 8:
-		put_unaligned_le64(val, (void *)data);
-		break;
-#endif
-	default:
-		WARN(1, "invalid config space write size %d\n", size);
-		return;
-	}
+	u8 *resptr = priv;
+	struct um_pci_device *dev = container_of(resptr - *resptr,
+						 struct um_pci_device,
+						 resptr[0]);
+	u8 bar = *resptr;
 
-	um_pci_bar_copy_to(priv, offset, data, size);
+	dev->ops->bar_copy_to(dev, bar, offset, buffer, size);
 }
 
 static void um_pci_bar_set(void *priv, unsigned int offset, u8 value, int size)
@@ -426,20 +167,9 @@ static void um_pci_bar_set(void *priv, unsigned int offset, u8 value, int size)
 	struct um_pci_device *dev = container_of(resptr - *resptr,
 						 struct um_pci_device,
 						 resptr[0]);
-	struct {
-		struct virtio_pcidev_msg hdr;
-		u8 data;
-	} msg = {
-		.hdr = {
-			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
-			.bar = *resptr,
-			.size = size,
-			.addr = offset,
-		},
-		.data = value,
-	};
+	u8 bar = *resptr;
 
-	um_pci_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0);
+	dev->ops->bar_set(dev, bar, offset, value, size);
 }
 
 static const struct logic_iomem_ops um_pci_device_bar_ops = {
@@ -486,76 +216,6 @@ static void um_pci_rescan(void)
 	pci_unlock_rescan_remove();
 }
 
-static void um_pci_irq_vq_addbuf(struct virtqueue *vq, void *buf, bool kick)
-{
-	struct scatterlist sg[1];
-
-	sg_init_one(sg, buf, MAX_IRQ_MSG_SIZE);
-	if (virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC))
-		kfree(buf);
-	else if (kick)
-		virtqueue_kick(vq);
-}
-
-static void um_pci_handle_irq_message(struct virtqueue *vq,
-				      struct virtio_pcidev_msg *msg)
-{
-	struct virtio_device *vdev = vq->vdev;
-	struct um_pci_device *dev = vdev->priv;
-
-	if (!dev->irq)
-		return;
-
-	/* we should properly chain interrupts, but on ARCH=um we don't care */
-
-	switch (msg->op) {
-	case VIRTIO_PCIDEV_OP_INT:
-		generic_handle_irq(dev->irq);
-		break;
-	case VIRTIO_PCIDEV_OP_MSI:
-		/* our MSI message is just the interrupt number */
-		if (msg->size == sizeof(u32))
-			generic_handle_irq(le32_to_cpup((void *)msg->data));
-		else
-			generic_handle_irq(le16_to_cpup((void *)msg->data));
-		break;
-	case VIRTIO_PCIDEV_OP_PME:
-		/* nothing to do - we already woke up due to the message */
-		break;
-	default:
-		dev_err(&vdev->dev, "unexpected virt-pci message %d\n", msg->op);
-		break;
-	}
-}
-
-static void um_pci_cmd_vq_cb(struct virtqueue *vq)
-{
-	struct virtio_device *vdev = vq->vdev;
-	struct um_pci_device *dev = vdev->priv;
-	void *cmd;
-	int len;
-
-	if (test_bit(UM_PCI_STAT_WAITING, &dev->status))
-		return;
-
-	while ((cmd = virtqueue_get_buf(vq, &len)))
-		um_pci_free_buf(dev, cmd);
-}
-
-static void um_pci_irq_vq_cb(struct virtqueue *vq)
-{
-	struct virtio_pcidev_msg *msg;
-	int len;
-
-	while ((msg = virtqueue_get_buf(vq, &len))) {
-		if (len >= sizeof(*msg))
-			um_pci_handle_irq_message(vq, msg);
-
-		/* recycle the message buffer */
-		um_pci_irq_vq_addbuf(vq, msg, true);
-	}
-}
-
 #ifdef CONFIG_OF
 /* Copied from arch/x86/kernel/devicetree.c */
 struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
@@ -577,200 +237,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
 }
 #endif
 
-static int um_pci_init_vqs(struct um_pci_device *dev)
-{
-	struct virtqueue_info vqs_info[] = {
-		{ "cmd", um_pci_cmd_vq_cb },
-		{ "irq", um_pci_irq_vq_cb },
-	};
-	struct virtqueue *vqs[2];
-	int err, i;
-
-	err = virtio_find_vqs(dev->vdev, 2, vqs, vqs_info, NULL);
-	if (err)
-		return err;
-
-	dev->cmd_vq = vqs[0];
-	dev->irq_vq = vqs[1];
-
-	virtio_device_ready(dev->vdev);
-
-	for (i = 0; i < NUM_IRQ_MSGS; i++) {
-		void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL);
-
-		if (msg)
-			um_pci_irq_vq_addbuf(dev->irq_vq, msg, false);
-	}
-
-	virtqueue_kick(dev->irq_vq);
-
-	return 0;
-}
-
-static void __um_pci_virtio_platform_remove(struct virtio_device *vdev,
-					    struct um_pci_device *dev)
-{
-	virtio_reset_device(vdev);
-	vdev->config->del_vqs(vdev);
-
-	mutex_lock(&um_pci_mtx);
-	um_pci_platform_device = NULL;
-	mutex_unlock(&um_pci_mtx);
-
-	kfree(dev);
-}
-
-static int um_pci_virtio_platform_probe(struct virtio_device *vdev,
-					struct um_pci_device *dev)
-{
-	int ret;
-
-	dev->platform = true;
-
-	mutex_lock(&um_pci_mtx);
-
-	if (um_pci_platform_device) {
-		mutex_unlock(&um_pci_mtx);
-		ret = -EBUSY;
-		goto out_free;
-	}
-
-	ret = um_pci_init_vqs(dev);
-	if (ret) {
-		mutex_unlock(&um_pci_mtx);
-		goto out_free;
-	}
-
-	um_pci_platform_device = dev;
-
-	mutex_unlock(&um_pci_mtx);
-
-	ret = of_platform_default_populate(vdev->dev.of_node, NULL, &vdev->dev);
-	if (ret)
-		__um_pci_virtio_platform_remove(vdev, dev);
-
-	return ret;
-
-out_free:
-	kfree(dev);
-	return ret;
-}
-
-static int um_pci_virtio_probe(struct virtio_device *vdev)
-{
-	struct um_pci_device *dev;
-	int i, free = -1;
-	int err = -ENOSPC;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->vdev = vdev;
-	vdev->priv = dev;
-
-	if (of_device_is_compatible(vdev->dev.of_node, "simple-bus"))
-		return um_pci_virtio_platform_probe(vdev, dev);
-
-	mutex_lock(&um_pci_mtx);
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (um_pci_devices[i].dev)
-			continue;
-		free = i;
-		break;
-	}
-
-	if (free < 0)
-		goto error;
-
-	err = um_pci_init_vqs(dev);
-	if (err)
-		goto error;
-
-	dev->irq = irq_alloc_desc(numa_node_id());
-	if (dev->irq < 0) {
-		err = dev->irq;
-		goto err_reset;
-	}
-	um_pci_devices[free].dev = dev;
-	vdev->priv = dev;
-
-	mutex_unlock(&um_pci_mtx);
-
-	device_set_wakeup_enable(&vdev->dev, true);
-
-	/*
-	 * In order to do suspend-resume properly, don't allow VQs
-	 * to be suspended.
-	 */
-	virtio_uml_set_no_vq_suspend(vdev, true);
-
-	um_pci_rescan();
-	return 0;
-err_reset:
-	virtio_reset_device(vdev);
-	vdev->config->del_vqs(vdev);
-error:
-	mutex_unlock(&um_pci_mtx);
-	kfree(dev);
-	return err;
-}
-
-static void um_pci_virtio_remove(struct virtio_device *vdev)
-{
-	struct um_pci_device *dev = vdev->priv;
-	int i;
-
-	if (dev->platform) {
-		of_platform_depopulate(&vdev->dev);
-		__um_pci_virtio_platform_remove(vdev, dev);
-		return;
-	}
-
-	device_set_wakeup_enable(&vdev->dev, false);
-
-	mutex_lock(&um_pci_mtx);
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (um_pci_devices[i].dev != dev)
-			continue;
-
-		um_pci_devices[i].dev = NULL;
-		irq_free_desc(dev->irq);
-
-		break;
-	}
-	mutex_unlock(&um_pci_mtx);
-
-	if (i < MAX_DEVICES) {
-		struct pci_dev *pci_dev;
-
-		pci_dev = pci_get_slot(bridge->bus, i);
-		if (pci_dev)
-			pci_stop_and_remove_bus_device_locked(pci_dev);
-	}
-
-	/* Stop all virtqueues */
-	virtio_reset_device(vdev);
-	dev->cmd_vq = NULL;
-	dev->irq_vq = NULL;
-	vdev->config->del_vqs(vdev);
-
-	kfree(dev);
-}
-
-static struct virtio_device_id id_table[] = {
-	{ CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID, VIRTIO_DEV_ANY_ID },
-	{ 0 },
-};
-MODULE_DEVICE_TABLE(virtio, id_table);
-
-static struct virtio_driver um_pci_virtio_driver = {
-	.driver.name = "virtio-pci",
-	.id_table = id_table,
-	.probe = um_pci_virtio_probe,
-	.remove = um_pci_virtio_remove,
-};
-
 static struct resource virt_cfgspace_resource = {
 	.name = "PCI config space",
 	.start = 0xf0000000 - MAX_DEVICES * CFG_SPACE_SIZE,
@@ -889,7 +355,7 @@ static void um_pci_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 }
 
 static struct irq_chip um_pci_msi_bottom_irq_chip = {
-	.name = "UM virtio MSI",
+	.name = "UM virtual MSI",
 	.irq_compose_msi_msg = um_pci_compose_msi_msg,
 };
 
@@ -939,7 +405,7 @@ static const struct irq_domain_ops um_pci_inner_domain_ops = {
 };
 
 static struct irq_chip um_pci_msi_irq_chip = {
-	.name = "UM virtio PCIe MSI",
+	.name = "UM virtual PCIe MSI",
 	.irq_mask = pci_msi_mask_irq,
 	.irq_unmask = pci_msi_unmask_irq,
 };
@@ -998,6 +464,78 @@ static struct resource virt_platform_resource = {
 	.flags = IORESOURCE_MEM,
 };
 
+int um_pci_device_register(struct um_pci_device *dev)
+{
+	int i, free = -1;
+	int err = 0;
+
+	mutex_lock(&um_pci_mtx);
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (um_pci_devices[i].dev)
+			continue;
+		free = i;
+		break;
+	}
+
+	if (free < 0) {
+		err = -ENOSPC;
+		goto out;
+	}
+
+	dev->irq = irq_alloc_desc(numa_node_id());
+	if (dev->irq < 0) {
+		err = dev->irq;
+		goto out;
+	}
+
+	um_pci_devices[free].dev = dev;
+
+out:
+	mutex_unlock(&um_pci_mtx);
+	if (!err)
+		um_pci_rescan();
+	return err;
+}
+
+void um_pci_device_unregister(struct um_pci_device *dev)
+{
+	int i;
+
+	mutex_lock(&um_pci_mtx);
+	for (i = 0; i < MAX_DEVICES; i++) {
+		if (um_pci_devices[i].dev != dev)
+			continue;
+		um_pci_devices[i].dev = NULL;
+		irq_free_desc(dev->irq);
+		break;
+	}
+	mutex_unlock(&um_pci_mtx);
+
+	if (i < MAX_DEVICES) {
+		struct pci_dev *pci_dev;
+
+		pci_dev = pci_get_slot(bridge->bus, i);
+		if (pci_dev)
+			pci_stop_and_remove_bus_device_locked(pci_dev);
+	}
+}
+
+int um_pci_platform_device_register(struct um_pci_device *dev)
+{
+	guard(mutex)(&um_pci_mtx);
+	if (um_pci_platform_device)
+		return -EBUSY;
+	um_pci_platform_device = dev;
+	return 0;
+}
+
+void um_pci_platform_device_unregister(struct um_pci_device *dev)
+{
+	guard(mutex)(&um_pci_mtx);
+	if (um_pci_platform_device == dev)
+		um_pci_platform_device = NULL;
+}
+
 static int __init um_pci_init(void)
 {
 	struct irq_domain_info inner_domain_info = {
@@ -1014,10 +552,6 @@ static int __init um_pci_init(void)
 	WARN_ON(logic_iomem_add_region(&virt_platform_resource,
 				       &um_pci_platform_ops));
 
-	if (WARN(CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID < 0,
-		 "No virtio device ID configured for PCI - no PCI support\n"))
-		return 0;
-
 	bridge = pci_alloc_host_bridge(0);
 	if (!bridge) {
 		err = -ENOMEM;
@@ -1065,10 +599,8 @@ static int __init um_pci_init(void)
 	if (err)
 		goto free;
 
-	err = register_virtio_driver(&um_pci_virtio_driver);
-	if (err)
-		goto free;
 	return 0;
+
 free:
 	if (!IS_ERR_OR_NULL(um_pci_inner_domain))
 		irq_domain_remove(um_pci_inner_domain);
@@ -1080,11 +612,10 @@ free:
 	}
 	return err;
 }
-module_init(um_pci_init);
+device_initcall(um_pci_init);
 
 static void __exit um_pci_exit(void)
 {
-	unregister_virtio_driver(&um_pci_virtio_driver);
 	irq_domain_remove(um_pci_msi_domain);
 	irq_domain_remove(um_pci_inner_domain);
 	pci_free_resource_list(&bridge->windows);
diff --git a/arch/um/drivers/virt-pci.h b/arch/um/drivers/virt-pci.h
new file mode 100644
index 000000000000..b20d1475d1eb
--- /dev/null
+++ b/arch/um/drivers/virt-pci.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_VIRT_PCI_H
+#define __UM_VIRT_PCI_H
+
+#include <linux/pci.h>
+
+struct um_pci_device {
+	const struct um_pci_ops *ops;
+
+	/* for now just standard BARs */
+	u8 resptr[PCI_STD_NUM_BARS];
+
+	int irq;
+};
+
+struct um_pci_ops {
+	unsigned long (*cfgspace_read)(struct um_pci_device *dev,
+				       unsigned int offset, int size);
+	void (*cfgspace_write)(struct um_pci_device *dev, unsigned int offset,
+			       int size, unsigned long val);
+
+	unsigned long (*bar_read)(struct um_pci_device *dev, int bar,
+				  unsigned int offset, int size);
+	void (*bar_write)(struct um_pci_device *dev, int bar,
+			  unsigned int offset, int size, unsigned long val);
+
+	void (*bar_copy_from)(struct um_pci_device *dev, int bar, void *buffer,
+			      unsigned int offset, int size);
+	void (*bar_copy_to)(struct um_pci_device *dev, int bar,
+			    unsigned int offset, const void *buffer, int size);
+	void (*bar_set)(struct um_pci_device *dev, int bar,
+			unsigned int offset, u8 value, int size);
+};
+
+int um_pci_device_register(struct um_pci_device *dev);
+void um_pci_device_unregister(struct um_pci_device *dev);
+
+int um_pci_platform_device_register(struct um_pci_device *dev);
+void um_pci_platform_device_unregister(struct um_pci_device *dev);
+
+#endif /* __UM_VIRT_PCI_H */
diff --git a/arch/um/drivers/virtio_pcidev.c b/arch/um/drivers/virtio_pcidev.c
new file mode 100644
index 000000000000..3c4c4c928fdd
--- /dev/null
+++ b/arch/um/drivers/virtio_pcidev.c
@@ -0,0 +1,628 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Intel Corporation
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/logic_iomem.h>
+#include <linux/of_platform.h>
+#include <linux/irqdomain.h>
+#include <linux/virtio_pcidev.h>
+#include <linux/virtio-uml.h>
+#include <linux/delay.h>
+#include <linux/msi.h>
+#include <linux/unaligned.h>
+#include <irq_kern.h>
+
+#include "virt-pci.h"
+
+#define to_virtio_pcidev(_pdev) \
+	container_of(_pdev, struct virtio_pcidev_device, pdev)
+
+/* for MSI-X we have a 32-bit payload */
+#define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32))
+#define NUM_IRQ_MSGS	10
+
+struct virtio_pcidev_message_buffer {
+	struct virtio_pcidev_msg hdr;
+	u8 data[8];
+};
+
+struct virtio_pcidev_device {
+	struct um_pci_device pdev;
+	struct virtio_device *vdev;
+
+	struct virtqueue *cmd_vq, *irq_vq;
+
+#define VIRTIO_PCIDEV_WRITE_BUFS	20
+	struct virtio_pcidev_message_buffer bufs[VIRTIO_PCIDEV_WRITE_BUFS + 1];
+	void *extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS + 1];
+	DECLARE_BITMAP(used_bufs, VIRTIO_PCIDEV_WRITE_BUFS);
+
+#define UM_PCI_STAT_WAITING	0
+	unsigned long status;
+
+	bool platform;
+};
+
+static unsigned int virtio_pcidev_max_delay_us = 40000;
+module_param_named(max_delay_us, virtio_pcidev_max_delay_us, uint, 0644);
+
+static int virtio_pcidev_get_buf(struct virtio_pcidev_device *dev, bool *posted)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_PCIDEV_WRITE_BUFS; i++) {
+		if (!test_and_set_bit(i, dev->used_bufs))
+			return i;
+	}
+
+	*posted = false;
+	return VIRTIO_PCIDEV_WRITE_BUFS;
+}
+
+static void virtio_pcidev_free_buf(struct virtio_pcidev_device *dev, void *buf)
+{
+	int i;
+
+	if (buf == &dev->bufs[VIRTIO_PCIDEV_WRITE_BUFS]) {
+		kfree(dev->extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS]);
+		dev->extra_ptrs[VIRTIO_PCIDEV_WRITE_BUFS] = NULL;
+		return;
+	}
+
+	for (i = 0; i < VIRTIO_PCIDEV_WRITE_BUFS; i++) {
+		if (buf == &dev->bufs[i]) {
+			kfree(dev->extra_ptrs[i]);
+			dev->extra_ptrs[i] = NULL;
+			WARN_ON(!test_and_clear_bit(i, dev->used_bufs));
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
+
+static int virtio_pcidev_send_cmd(struct virtio_pcidev_device *dev,
+				  struct virtio_pcidev_msg *cmd,
+				  unsigned int cmd_size,
+				  const void *extra, unsigned int extra_size,
+				  void *out, unsigned int out_size)
+{
+	struct scatterlist out_sg, extra_sg, in_sg;
+	struct scatterlist *sgs_list[] = {
+		[0] = &out_sg,
+		[1] = extra ? &extra_sg : &in_sg,
+		[2] = extra ? &in_sg : NULL,
+	};
+	struct virtio_pcidev_message_buffer *buf;
+	int delay_count = 0;
+	bool bounce_out;
+	int ret, len;
+	int buf_idx;
+	bool posted;
+
+	if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf)))
+		return -EINVAL;
+
+	switch (cmd->op) {
+	case VIRTIO_PCIDEV_OP_CFG_WRITE:
+	case VIRTIO_PCIDEV_OP_MMIO_WRITE:
+	case VIRTIO_PCIDEV_OP_MMIO_MEMSET:
+		/* in PCI, writes are posted, so don't wait */
+		posted = !out;
+		WARN_ON(!posted);
+		break;
+	default:
+		posted = false;
+		break;
+	}
+
+	bounce_out = !posted && cmd_size <= sizeof(*cmd) &&
+		     out && out_size <= sizeof(buf->data);
+
+	buf_idx = virtio_pcidev_get_buf(dev, &posted);
+	buf = &dev->bufs[buf_idx];
+	memcpy(buf, cmd, cmd_size);
+
+	if (posted && extra && extra_size > sizeof(buf) - cmd_size) {
+		dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size,
+						   GFP_ATOMIC);
+
+		if (!dev->extra_ptrs[buf_idx]) {
+			virtio_pcidev_free_buf(dev, buf);
+			return -ENOMEM;
+		}
+		extra = dev->extra_ptrs[buf_idx];
+	} else if (extra && extra_size <= sizeof(buf) - cmd_size) {
+		memcpy((u8 *)buf + cmd_size, extra, extra_size);
+		cmd_size += extra_size;
+		extra_size = 0;
+		extra = NULL;
+		cmd = (void *)buf;
+	} else {
+		cmd = (void *)buf;
+	}
+
+	sg_init_one(&out_sg, cmd, cmd_size);
+	if (extra)
+		sg_init_one(&extra_sg, extra, extra_size);
+	/* allow stack for small buffers */
+	if (bounce_out)
+		sg_init_one(&in_sg, buf->data, out_size);
+	else if (out)
+		sg_init_one(&in_sg, out, out_size);
+
+	/* add to internal virtio queue */
+	ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list,
+				extra ? 2 : 1,
+				out ? 1 : 0,
+				cmd, GFP_ATOMIC);
+	if (ret) {
+		virtio_pcidev_free_buf(dev, buf);
+		return ret;
+	}
+
+	if (posted) {
+		virtqueue_kick(dev->cmd_vq);
+		return 0;
+	}
+
+	/* kick and poll for getting a response on the queue */
+	set_bit(UM_PCI_STAT_WAITING, &dev->status);
+	virtqueue_kick(dev->cmd_vq);
+	ret = 0;
+
+	while (1) {
+		void *completed = virtqueue_get_buf(dev->cmd_vq, &len);
+
+		if (completed == buf)
+			break;
+
+		if (completed)
+			virtio_pcidev_free_buf(dev, completed);
+
+		if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) ||
+			      ++delay_count > virtio_pcidev_max_delay_us,
+			      "um virt-pci delay: %d", delay_count)) {
+			ret = -EIO;
+			break;
+		}
+		udelay(1);
+	}
+	clear_bit(UM_PCI_STAT_WAITING, &dev->status);
+
+	if (bounce_out)
+		memcpy(out, buf->data, out_size);
+
+	virtio_pcidev_free_buf(dev, buf);
+
+	return ret;
+}
+
+static unsigned long virtio_pcidev_cfgspace_read(struct um_pci_device *pdev,
+						 unsigned int offset, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_CFG_READ,
+		.size = size,
+		.addr = offset,
+	};
+	/* max 8, we might not use it all */
+	u8 data[8];
+
+	memset(data, 0xff, sizeof(data));
+
+	/* size has been checked in um_pci_cfgspace_read() */
+	if (virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size))
+		return ULONG_MAX;
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static void virtio_pcidev_cfgspace_write(struct um_pci_device *pdev,
+					 unsigned int offset, int size,
+					 unsigned long val)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct {
+		struct virtio_pcidev_msg hdr;
+		/* maximum size - we may only use parts of it */
+		u8 data[8];
+	} msg = {
+		.hdr = {
+			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
+			.size = size,
+			.addr = offset,
+		},
+	};
+
+	/* size has been checked in um_pci_cfgspace_write() */
+	switch (size) {
+	case 1:
+		msg.data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)msg.data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)msg.data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)msg.data);
+		break;
+#endif
+	}
+
+	WARN_ON(virtio_pcidev_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0));
+}
+
+static void virtio_pcidev_bar_copy_from(struct um_pci_device *pdev,
+					int bar, void *buffer,
+					unsigned int offset, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_MMIO_READ,
+		.bar = bar,
+		.size = size,
+		.addr = offset,
+	};
+
+	memset(buffer, 0xff, size);
+
+	virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, buffer, size);
+}
+
+static unsigned long virtio_pcidev_bar_read(struct um_pci_device *pdev, int bar,
+					    unsigned int offset, int size)
+{
+	/* 8 is maximum size - we may only use parts of it */
+	u8 data[8];
+
+	/* size has been checked in um_pci_bar_read() */
+	virtio_pcidev_bar_copy_from(pdev, bar, data, offset, size);
+
+	switch (size) {
+	case 1:
+		return data[0];
+	case 2:
+		return le16_to_cpup((void *)data);
+	case 4:
+		return le32_to_cpup((void *)data);
+#ifdef CONFIG_64BIT
+	case 8:
+		return le64_to_cpup((void *)data);
+#endif
+	default:
+		return ULONG_MAX;
+	}
+}
+
+static void virtio_pcidev_bar_copy_to(struct um_pci_device *pdev,
+				      int bar, unsigned int offset,
+				      const void *buffer, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct virtio_pcidev_msg hdr = {
+		.op = VIRTIO_PCIDEV_OP_MMIO_WRITE,
+		.bar = bar,
+		.size = size,
+		.addr = offset,
+	};
+
+	virtio_pcidev_send_cmd(dev, &hdr, sizeof(hdr), buffer, size, NULL, 0);
+}
+
+static void virtio_pcidev_bar_write(struct um_pci_device *pdev, int bar,
+				    unsigned int offset, int size,
+				    unsigned long val)
+{
+	/* maximum size - we may only use parts of it */
+	u8 data[8];
+
+	/* size has been checked in um_pci_bar_write() */
+	switch (size) {
+	case 1:
+		data[0] = (u8)val;
+		break;
+	case 2:
+		put_unaligned_le16(val, (void *)data);
+		break;
+	case 4:
+		put_unaligned_le32(val, (void *)data);
+		break;
+#ifdef CONFIG_64BIT
+	case 8:
+		put_unaligned_le64(val, (void *)data);
+		break;
+#endif
+	}
+
+	virtio_pcidev_bar_copy_to(pdev, bar, offset, data, size);
+}
+
+static void virtio_pcidev_bar_set(struct um_pci_device *pdev, int bar,
+				  unsigned int offset, u8 value, int size)
+{
+	struct virtio_pcidev_device *dev = to_virtio_pcidev(pdev);
+	struct {
+		struct virtio_pcidev_msg hdr;
+		u8 data;
+	} msg = {
+		.hdr = {
+			.op = VIRTIO_PCIDEV_OP_CFG_WRITE,
+			.bar = bar,
+			.size = size,
+			.addr = offset,
+		},
+		.data = value,
+	};
+
+	virtio_pcidev_send_cmd(dev, &msg.hdr, sizeof(msg), NULL, 0, NULL, 0);
+}
+
+static const struct um_pci_ops virtio_pcidev_um_pci_ops = {
+	.cfgspace_read	= virtio_pcidev_cfgspace_read,
+	.cfgspace_write	= virtio_pcidev_cfgspace_write,
+	.bar_read	= virtio_pcidev_bar_read,
+	.bar_write	= virtio_pcidev_bar_write,
+	.bar_copy_from	= virtio_pcidev_bar_copy_from,
+	.bar_copy_to	= virtio_pcidev_bar_copy_to,
+	.bar_set	= virtio_pcidev_bar_set,
+};
+
+static void virtio_pcidev_irq_vq_addbuf(struct virtqueue *vq, void *buf, bool kick)
+{
+	struct scatterlist sg[1];
+
+	sg_init_one(sg, buf, MAX_IRQ_MSG_SIZE);
+	if (virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC))
+		kfree(buf);
+	else if (kick)
+		virtqueue_kick(vq);
+}
+
+static void virtio_pcidev_handle_irq_message(struct virtqueue *vq,
+					     struct virtio_pcidev_msg *msg)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pcidev_device *dev = vdev->priv;
+
+	if (!dev->pdev.irq)
+		return;
+
+	/* we should properly chain interrupts, but on ARCH=um we don't care */
+
+	switch (msg->op) {
+	case VIRTIO_PCIDEV_OP_INT:
+		generic_handle_irq(dev->pdev.irq);
+		break;
+	case VIRTIO_PCIDEV_OP_MSI:
+		/* our MSI message is just the interrupt number */
+		if (msg->size == sizeof(u32))
+			generic_handle_irq(le32_to_cpup((void *)msg->data));
+		else
+			generic_handle_irq(le16_to_cpup((void *)msg->data));
+		break;
+	case VIRTIO_PCIDEV_OP_PME:
+		/* nothing to do - we already woke up due to the message */
+		break;
+	default:
+		dev_err(&vdev->dev, "unexpected virt-pci message %d\n", msg->op);
+		break;
+	}
+}
+
+static void virtio_pcidev_cmd_vq_cb(struct virtqueue *vq)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pcidev_device *dev = vdev->priv;
+	void *cmd;
+	int len;
+
+	if (test_bit(UM_PCI_STAT_WAITING, &dev->status))
+		return;
+
+	while ((cmd = virtqueue_get_buf(vq, &len)))
+		virtio_pcidev_free_buf(dev, cmd);
+}
+
+static void virtio_pcidev_irq_vq_cb(struct virtqueue *vq)
+{
+	struct virtio_pcidev_msg *msg;
+	int len;
+
+	while ((msg = virtqueue_get_buf(vq, &len))) {
+		if (len >= sizeof(*msg))
+			virtio_pcidev_handle_irq_message(vq, msg);
+
+		/* recycle the message buffer */
+		virtio_pcidev_irq_vq_addbuf(vq, msg, true);
+	}
+}
+
+static int virtio_pcidev_init_vqs(struct virtio_pcidev_device *dev)
+{
+	struct virtqueue_info vqs_info[] = {
+		{ "cmd", virtio_pcidev_cmd_vq_cb },
+		{ "irq", virtio_pcidev_irq_vq_cb },
+	};
+	struct virtqueue *vqs[2];
+	int err, i;
+
+	err = virtio_find_vqs(dev->vdev, 2, vqs, vqs_info, NULL);
+	if (err)
+		return err;
+
+	dev->cmd_vq = vqs[0];
+	dev->irq_vq = vqs[1];
+
+	virtio_device_ready(dev->vdev);
+
+	for (i = 0; i < NUM_IRQ_MSGS; i++) {
+		void *msg = kzalloc(MAX_IRQ_MSG_SIZE, GFP_KERNEL);
+
+		if (msg)
+			virtio_pcidev_irq_vq_addbuf(dev->irq_vq, msg, false);
+	}
+
+	virtqueue_kick(dev->irq_vq);
+
+	return 0;
+}
+
+static void __virtio_pcidev_virtio_platform_remove(struct virtio_device *vdev,
+						   struct virtio_pcidev_device *dev)
+{
+	um_pci_platform_device_unregister(&dev->pdev);
+
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+
+	kfree(dev);
+}
+
+static int virtio_pcidev_virtio_platform_probe(struct virtio_device *vdev,
+					       struct virtio_pcidev_device *dev)
+{
+	int err;
+
+	dev->platform = true;
+
+	err = virtio_pcidev_init_vqs(dev);
+	if (err)
+		goto err_free;
+
+	err = um_pci_platform_device_register(&dev->pdev);
+	if (err)
+		goto err_reset;
+
+	err = of_platform_default_populate(vdev->dev.of_node, NULL, &vdev->dev);
+	if (err)
+		goto err_unregister;
+
+	return 0;
+
+err_unregister:
+	um_pci_platform_device_unregister(&dev->pdev);
+err_reset:
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+err_free:
+	kfree(dev);
+	return err;
+}
+
+static int virtio_pcidev_virtio_probe(struct virtio_device *vdev)
+{
+	struct virtio_pcidev_device *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->vdev = vdev;
+	vdev->priv = dev;
+
+	dev->pdev.ops = &virtio_pcidev_um_pci_ops;
+
+	if (of_device_is_compatible(vdev->dev.of_node, "simple-bus"))
+		return virtio_pcidev_virtio_platform_probe(vdev, dev);
+
+	err = virtio_pcidev_init_vqs(dev);
+	if (err)
+		goto err_free;
+
+	err = um_pci_device_register(&dev->pdev);
+	if (err)
+		goto err_reset;
+
+	device_set_wakeup_enable(&vdev->dev, true);
+
+	/*
+	 * In order to do suspend-resume properly, don't allow VQs
+	 * to be suspended.
+	 */
+	virtio_uml_set_no_vq_suspend(vdev, true);
+
+	return 0;
+
+err_reset:
+	virtio_reset_device(vdev);
+	vdev->config->del_vqs(vdev);
+err_free:
+	kfree(dev);
+	return err;
+}
+
+static void virtio_pcidev_virtio_remove(struct virtio_device *vdev)
+{
+	struct virtio_pcidev_device *dev = vdev->priv;
+
+	if (dev->platform) {
+		of_platform_depopulate(&vdev->dev);
+		__virtio_pcidev_virtio_platform_remove(vdev, dev);
+		return;
+	}
+
+	device_set_wakeup_enable(&vdev->dev, false);
+
+	um_pci_device_unregister(&dev->pdev);
+
+	/* Stop all virtqueues */
+	virtio_reset_device(vdev);
+	dev->cmd_vq = NULL;
+	dev->irq_vq = NULL;
+	vdev->config->del_vqs(vdev);
+
+	kfree(dev);
+}
+
+static struct virtio_device_id id_table[] = {
+	{ CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(virtio, id_table);
+
+static struct virtio_driver virtio_pcidev_virtio_driver = {
+	.driver.name = "virtio-pci",
+	.id_table = id_table,
+	.probe = virtio_pcidev_virtio_probe,
+	.remove = virtio_pcidev_virtio_remove,
+};
+
+static int __init virtio_pcidev_init(void)
+{
+	if (WARN(CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID < 0,
+		 "No virtio device ID configured for PCI - no PCI support\n"))
+		return 0;
+
+	return register_virtio_driver(&virtio_pcidev_virtio_driver);
+}
+late_initcall(virtio_pcidev_init);
+
+static void __exit virtio_pcidev_exit(void)
+{
+	unregister_virtio_driver(&virtio_pcidev_virtio_driver);
+}
+module_exit(virtio_pcidev_exit);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 428f2c5158c2..04ab3b653a48 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mmiowb.h
+generic-y += module.h
 generic-y += module.lds.h
 generic-y += param.h
 generic-y += parport.h
diff --git a/arch/um/include/asm/fpu/api.h b/arch/um/include/asm/fpu/api.h
index 71bfd9ef3938..3abf67c83c40 100644
--- a/arch/um/include/asm/fpu/api.h
+++ b/arch/um/include/asm/fpu/api.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_UM_FPU_API_H
 #define _ASM_UM_FPU_API_H
 
+#include <linux/types.h>
+
 /* Copyright (c) 2020 Cambridge Greys Ltd
  * Copyright (c) 2020 Red Hat Inc.
  * A set of "dummy" defines to allow the direct inclusion
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index f0af23c3aeb2..826ec44b58cd 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -25,27 +25,18 @@
  */
 extern pgd_t *pgd_alloc(struct mm_struct *);
 
-#define __pte_free_tlb(tlb, pte, address)			\
-do {								\
-	pagetable_dtor(page_ptdesc(pte));			\
-	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
-} while (0)
+#define __pte_free_tlb(tlb, pte, address)	\
+	tlb_remove_ptdesc((tlb), page_ptdesc(pte))
 
 #if CONFIG_PGTABLE_LEVELS > 2
 
-#define __pmd_free_tlb(tlb, pmd, address)			\
-do {								\
-	pagetable_dtor(virt_to_ptdesc(pmd));			\
-	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd));	\
-} while (0)
+#define __pmd_free_tlb(tlb, pmd, address)	\
+	tlb_remove_ptdesc((tlb), virt_to_ptdesc(pmd))
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
-#define __pud_free_tlb(tlb, pud, address)			\
-do {								\
-	pagetable_dtor(virt_to_ptdesc(pud));		\
-	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud));	\
-} while (0)
+#define __pud_free_tlb(tlb, pud, address)	\
+	tlb_remove_ptdesc((tlb), virt_to_ptdesc(pud))
 
 #endif
 #endif
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 5d6356eafffe..8a789c17acd8 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -31,6 +31,8 @@ struct thread_struct {
 		} thread;
 	} request;
 
+	void *segv_continue;
+
 	/* Contains variable sized FP registers */
 	struct pt_regs regs;
 };
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index 1d4b6bbc1b65..1c6e0ae41b0c 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -9,6 +9,7 @@
 
 #include <asm/elf.h>
 #include <linux/unaligned.h>
+#include <sysdep/faultinfo.h>
 
 #define __under_task_size(addr, size) \
 	(((unsigned long) (addr) < TASK_SIZE) && \
@@ -44,19 +45,30 @@ static inline int __access_ok(const void __user *ptr, unsigned long size)
 		 __access_ok_vsyscall(addr, size));
 }
 
-/* no pagefaults for kernel addresses in um */
 #define __get_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	*((type *)dst) = get_unaligned((type *)(src));			\
-	if (0) /* make sure the label looks used to the compiler */	\
+	int __faulted;							\
+									\
+	___backtrack_faulted(__faulted);				\
+	if (__faulted) {						\
+		*((type *)dst) = (type) 0;				\
 		goto err_label;						\
+	}								\
+	*((type *)dst) = get_unaligned((type *)(src));			\
+	barrier();							\
+	current->thread.segv_continue = NULL;				\
 } while (0)
 
 #define __put_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	put_unaligned(*((type *)src), (type *)(dst));			\
-	if (0) /* make sure the label looks used to the compiler */	\
+	int __faulted;							\
+									\
+	___backtrack_faulted(__faulted);				\
+	if (__faulted)							\
 		goto err_label;						\
+	put_unaligned(*((type *)src), (type *)(dst));			\
+	barrier();							\
+	current->thread.segv_continue = NULL;				\
 } while (0)
 
 #endif
diff --git a/arch/um/include/linux/time-internal.h b/arch/um/include/linux/time-internal.h
index b22226634ff6..138908b999d7 100644
--- a/arch/um/include/linux/time-internal.h
+++ b/arch/um/include/linux/time-internal.h
@@ -83,6 +83,8 @@ extern void time_travel_not_configured(void);
 #define time_travel_del_event(...) time_travel_not_configured()
 #endif /* CONFIG_UML_TIME_TRAVEL_SUPPORT */
 
+extern unsigned long tt_extra_sched_jiffies;
+
 /*
  * Without CONFIG_UML_TIME_TRAVEL_SUPPORT this is a linker error if used,
  * which is intentional since we really shouldn't link it in that case.
diff --git a/arch/um/include/shared/arch.h b/arch/um/include/shared/arch.h
index 880ee42a3329..cc398a21ad96 100644
--- a/arch/um/include/shared/arch.h
+++ b/arch/um/include/shared/arch.h
@@ -12,4 +12,6 @@ extern void arch_check_bugs(void);
 extern int arch_fixup(unsigned long address, struct uml_pt_regs *regs);
 extern void arch_examine_signal(int sig, struct uml_pt_regs *regs);
 
+void mc_set_rip(void *_mc, void *target);
+
 #endif
diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h
index ea65f151bf48..4f44dcce8a7c 100644
--- a/arch/um/include/shared/as-layout.h
+++ b/arch/um/include/shared/as-layout.h
@@ -50,7 +50,7 @@ extern int linux_main(int argc, char **argv, char **envp);
 extern void uml_finishsetup(void);
 
 struct siginfo;
-extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *);
+extern void (*sig_info[])(int, struct siginfo *si, struct uml_pt_regs *, void *);
 
 #endif
 
diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h
index da0f6eea30d0..88835b52ae2b 100644
--- a/arch/um/include/shared/irq_user.h
+++ b/arch/um/include/shared/irq_user.h
@@ -15,7 +15,8 @@ enum um_irq_type {
 };
 
 struct siginfo;
-extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
+extern void sigio_handler(int sig, struct siginfo *unused_si,
+			  struct uml_pt_regs *regs, void *mc);
 void sigio_run_timetravel_handlers(void);
 extern void free_irq_by_fd(int fd);
 extern void deactivate_fd(int fd, int irqnum);
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index f21dc8517538..00ca3e12fd9a 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -24,10 +24,12 @@ extern void free_stack(unsigned long stack, int order);
 struct pt_regs;
 extern void do_signal(struct pt_regs *regs);
 extern void interrupt_end(void);
-extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs);
+extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs,
+			 void *mc);
 
 extern unsigned long segv(struct faultinfo fi, unsigned long ip,
-			  int is_user, struct uml_pt_regs *regs);
+			  int is_user, struct uml_pt_regs *regs,
+			  void *mc);
 extern int handle_page_fault(unsigned long address, unsigned long ip,
 			     int is_write, int is_user, int *code_out);
 
@@ -59,8 +61,10 @@ extern unsigned long from_irq_stack(int nested);
 
 extern int singlestepping(void);
 
-extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
-extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
+extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+			 void *mc);
+extern void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		  void *mc);
 extern void fatal_sigsegv(void) __attribute__ ((noreturn));
 
 void um_idle_sleep(void);
diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h
index adfa08062f88..d4727efcf23d 100644
--- a/arch/um/include/shared/mem_user.h
+++ b/arch/um/include/shared/mem_user.h
@@ -47,7 +47,6 @@ extern int iomem_size;
 #define ROUND_4M(n) ((((unsigned long) (n)) + (1 << 22)) & ~((1 << 22) - 1))
 
 extern unsigned long find_iomem(char *driver, unsigned long *len_out);
-extern void mem_total_pages(unsigned long physmem, unsigned long iomem);
 extern void setup_physmem(unsigned long start, unsigned long usable,
 			  unsigned long len);
 extern void map_memory(unsigned long virt, unsigned long phys,
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 5babad8c5f75..152a60080d5b 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -213,7 +213,6 @@ extern int os_protect_memory(void *addr, unsigned long len,
 extern int os_unmap_memory(void *addr, int len);
 extern int os_drop_memory(void *addr, int length);
 extern int can_drop_memory(void);
-extern int os_mincore(void *addr, unsigned long len);
 
 void os_set_pdeathsig(void);
 
@@ -225,6 +224,11 @@ extern int run_helper_thread(int (*proc)(void *), void *arg,
 			     unsigned int flags, unsigned long *stack_out);
 extern int helper_wait(int pid);
 
+struct os_helper_thread;
+int os_run_helper_thread(struct os_helper_thread **td_out,
+			 void *(*routine)(void *), void *arg);
+void os_kill_helper_thread(struct os_helper_thread *td);
+void os_fix_helper_thread_signals(void);
 
 /* umid.c */
 extern int umid_file_name(char *name, char *buf, int len);
@@ -310,7 +314,7 @@ extern void um_irqs_resume(void);
 extern int add_sigio_fd(int fd);
 extern int ignore_sigio_fd(int fd);
 extern void maybe_sigio_broken(int fd);
-extern void sigio_broken(int fd);
+extern void sigio_broken(void);
 /*
  * unlocked versions for IRQ controller code.
  *
diff --git a/arch/um/include/shared/sigio.h b/arch/um/include/shared/sigio.h
index e60c8b227844..c6c2edce1f6d 100644
--- a/arch/um/include/shared/sigio.h
+++ b/arch/um/include/shared/sigio.h
@@ -6,7 +6,6 @@
 #ifndef __SIGIO_H__
 #define __SIGIO_H__
 
-extern int write_sigio_irq(int fd);
 extern void sigio_lock(void);
 extern void sigio_unlock(void);
 
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index f8567b933ffa..4df1cd0d2017 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -17,7 +17,7 @@ extra-y := vmlinux.lds
 obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 	physmem.o process.o ptrace.o reboot.o sigio.o \
 	signal.o sysrq.o time.o tlb.o trap.o \
-	um_arch.o umid.o maccess.o kmsg_dump.o capflags.o skas/
+	um_arch.o umid.o kmsg_dump.o capflags.o skas/
 obj-y += load_file.o
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index a4991746f5ea..abe8f30a521c 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -236,7 +236,8 @@ static void _sigio_handler(struct uml_pt_regs *regs,
 		free_irqs();
 }
 
-void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		   void *mc)
 {
 	preempt_disable();
 	_sigio_handler(regs, irqs_suspended);
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
deleted file mode 100644
index 8ccd56813f68..000000000000
--- a/arch/um/kernel/maccess.c
+++ /dev/null
@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
- */
-
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <os.h>
-
-bool copy_from_kernel_nofault_allowed(const void *src, size_t size)
-{
-	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
-
-	if ((unsigned long)src < PAGE_SIZE || size <= 0)
-		return false;
-	if (os_mincore(psrc, size + src - psrc) <= 0)
-		return false;
-	return true;
-}
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index befed230aac2..76bec7de81b5 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -9,6 +9,8 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/init.h>
+#include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <as-layout.h>
@@ -54,7 +56,7 @@ int kmalloc_ok = 0;
 /* Used during early boot */
 static unsigned long brk_end;
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/* clear the zero-page */
 	memset(empty_zero_page, 0, PAGE_SIZE);
@@ -66,10 +68,12 @@ void __init mem_init(void)
 	map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
 	memblock_free((void *)brk_end, uml_reserved - brk_end);
 	uml_reserved = brk_end;
-
-	/* this will put all low memory onto the freelists */
-	memblock_free_all();
+	min_low_pfn = PFN_UP(__pa(uml_reserved));
 	max_pfn = max_low_pfn;
+}
+
+void __init mem_init(void)
+{
 	kmalloc_ok = 1;
 }
 
@@ -241,3 +245,11 @@ static const pgprot_t protection_map[16] = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED
 };
 DECLARE_VM_GET_PAGE_PROT
+
+void mark_rodata_ro(void)
+{
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
+
+	os_protect_memory((void *)rodata_start, rodata_end - rodata_start, 1, 0, 0);
+}
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index a74f17b033c4..af02b5f9911d 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -22,18 +22,6 @@ static int physmem_fd = -1;
 unsigned long high_physmem;
 EXPORT_SYMBOL(high_physmem);
 
-void __init mem_total_pages(unsigned long physmem, unsigned long iomem)
-{
-	unsigned long phys_pages, iomem_pages, total_pages;
-
-	phys_pages  = physmem >> PAGE_SHIFT;
-	iomem_pages = iomem   >> PAGE_SHIFT;
-
-	total_pages = phys_pages + iomem_pages;
-
-	max_mapnr = total_pages;
-}
-
 void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
 		int r, int w, int x)
 {
diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c
index 5085a50c3b8c..4fc04742048a 100644
--- a/arch/um/kernel/sigio.c
+++ b/arch/um/kernel/sigio.c
@@ -8,32 +8,6 @@
 #include <os.h>
 #include <sigio.h>
 
-/* Protected by sigio_lock() called from write_sigio_workaround */
-static int sigio_irq_fd = -1;
-
-static irqreturn_t sigio_interrupt(int irq, void *data)
-{
-	char c;
-
-	os_read_file(sigio_irq_fd, &c, sizeof(c));
-	return IRQ_HANDLED;
-}
-
-int write_sigio_irq(int fd)
-{
-	int err;
-
-	err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt,
-			     0, "write sigio", NULL);
-	if (err < 0) {
-		printk(KERN_ERR "write_sigio_irq : um_request_irq failed, "
-		       "err = %d\n", err);
-		return -1;
-	}
-	sigio_irq_fd = fd;
-	return 0;
-}
-
 /* These are called from os-Linux/sigio.c to protect its pollfds arrays. */
 static DEFINE_MUTEX(sigio_mutex);
 
diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index b09e85279d2b..a5beaea2967e 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -31,6 +31,17 @@ void handle_syscall(struct uml_pt_regs *r)
 		goto out;
 
 	syscall = UPT_SYSCALL_NR(r);
+
+	/*
+	 * If no time passes, then sched_yield may not actually yield, causing
+	 * broken spinlock implementations in userspace (ASAN) to hang for long
+	 * periods of time.
+	 */
+	if ((time_travel_mode == TT_MODE_INFCPU ||
+	     time_travel_mode == TT_MODE_EXTERNAL) &&
+	    syscall == __NR_sched_yield)
+		tt_extra_sched_jiffies += 1;
+
 	if (syscall >= 0 && syscall < __NR_syscalls) {
 		unsigned long ret = EXECUTE_SYSCALL(syscall, regs);
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index cdaee3e94273..ef2272e92a43 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -16,6 +16,7 @@
 #include <kern_util.h>
 #include <os.h>
 #include <skas.h>
+#include <arch.h>
 
 /*
  * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
@@ -175,12 +176,14 @@ void fatal_sigsegv(void)
  * @sig:	the signal number
  * @unused_si:	the signal info struct; unused in this handler
  * @regs:	the ptrace register information
+ * @mc:		the mcontext of the signal
  *
  * The handler first extracts the faultinfo from the UML ptrace regs struct.
  * If the userfault did not happen in an UML userspace process, bad_segv is called.
  * Otherwise the signal did happen in a cloned userspace process, handle it.
  */
-void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+		  void *mc)
 {
 	struct faultinfo * fi = UPT_FAULTINFO(regs);
 
@@ -189,7 +192,7 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 		bad_segv(*fi, UPT_IP(regs));
 		return;
 	}
-	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
+	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs, mc);
 }
 
 /*
@@ -199,7 +202,7 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
  * give us bad data!
  */
 unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
-		   struct uml_pt_regs *regs)
+		   struct uml_pt_regs *regs, void *mc)
 {
 	int si_code;
 	int err;
@@ -222,6 +225,19 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 			panic("Failed to sync kernel TLBs: %d", err);
 		goto out;
 	}
+	else if (current->pagefault_disabled) {
+		if (!mc) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault with pagefaults disabled but no mcontext");
+		}
+		if (!current->thread.segv_continue) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault without recovery target");
+		}
+		mc_set_rip(mc, current->thread.segv_continue);
+		current->thread.segv_continue = NULL;
+		goto out;
+	}
 	else if (current->mm == NULL) {
 		show_regs(container_of(regs, struct pt_regs, regs));
 		panic("Segfault with no mm");
@@ -274,7 +290,8 @@ out:
 	return 0;
 }
 
-void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
+void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs,
+		  void *mc)
 {
 	int code, err;
 	if (!UPT_IS_USER(regs)) {
@@ -302,7 +319,8 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
 	}
 }
 
-void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs,
+	   void *mc)
 {
 	do_IRQ(WINCH_IRQ, regs);
 }
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 79ea97d4797e..2f5ee045bc7a 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -12,6 +12,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/utsname.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
@@ -78,7 +79,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "model name\t: UML\n");
 	seq_printf(m, "mode\t\t: skas\n");
 	seq_printf(m, "host\t\t: %s\n", host_info);
-	seq_printf(m, "fpu\t\t: %s\n", cpu_has(&boot_cpu_data, X86_FEATURE_FPU) ? "yes" : "no");
+	seq_printf(m, "fpu\t\t: %s\n", str_yes_no(cpu_has(&boot_cpu_data, X86_FEATURE_FPU)));
 	seq_printf(m, "flags\t\t:");
 	for (i = 0; i < 32*NCAPINTS; i++)
 		if (cpu_has(&boot_cpu_data, i) && (x86_cap_flags[i] != NULL))
@@ -385,7 +386,6 @@ int __init linux_main(int argc, char **argv, char **envp)
 
 	high_physmem = uml_physmem + physmem_size;
 	end_iomem = high_physmem + iomem_size;
-	high_memory = (void *) end_iomem;
 
 	start_vm = VMALLOC_START;
 
@@ -419,7 +419,6 @@ void __init setup_arch(char **cmdline_p)
 
 	stack_protections((unsigned long) init_task.stack);
 	setup_physmem(uml_physmem, uml_reserved, physmem_size);
-	mem_total_pages(physmem_size, iomem_size);
 	uml_dtb_init();
 	read_initrd();
 
@@ -440,25 +439,24 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
 {
 }
 
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
 {
 }
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 }
 
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 
@@ -479,7 +477,7 @@ void *text_poke_copy(void *addr, const void *opcode, size_t len)
 	return text_poke(addr, opcode, len);
 }
 
-void text_poke_sync(void)
+void smp_text_poke_sync_each_cpu(void)
 {
 }
 
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index 3cb8ac63be6e..89c2ad2a4e3a 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -8,6 +8,7 @@
 #include <unistd.h>
 #include <errno.h>
 #include <sched.h>
+#include <pthread.h>
 #include <linux/limits.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
@@ -121,6 +122,10 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
 	unsigned long stack, sp;
 	int pid, status, err;
 
+	/* To share memory space, use os_run_helper_thread() instead. */
+	if (flags & CLONE_VM)
+		return -EINVAL;
+
 	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
@@ -167,3 +172,65 @@ int helper_wait(int pid)
 	} else
 		return 0;
 }
+
+struct os_helper_thread {
+	pthread_t handle;
+};
+
+int os_run_helper_thread(struct os_helper_thread **td_out,
+			 void *(*routine)(void *), void *arg)
+{
+	struct os_helper_thread *td;
+	sigset_t sigset, oset;
+	int err, flags;
+
+	flags = __uml_cant_sleep() ? UM_GFP_ATOMIC : UM_GFP_KERNEL;
+	td = uml_kmalloc(sizeof(*td), flags);
+	if (!td)
+		return -ENOMEM;
+
+	sigfillset(&sigset);
+	if (sigprocmask(SIG_SETMASK, &sigset, &oset) < 0) {
+		err = -errno;
+		kfree(td);
+		return err;
+	}
+
+	err = pthread_create(&td->handle, NULL, routine, arg);
+
+	if (sigprocmask(SIG_SETMASK, &oset, NULL) < 0)
+		panic("Failed to restore the signal mask: %d", errno);
+
+	if (err != 0)
+		kfree(td);
+	else
+		*td_out = td;
+
+	return -err;
+}
+
+void os_kill_helper_thread(struct os_helper_thread *td)
+{
+	pthread_cancel(td->handle);
+	pthread_join(td->handle, NULL);
+	kfree(td);
+}
+
+void os_fix_helper_thread_signals(void)
+{
+	sigset_t sigset;
+
+	sigemptyset(&sigset);
+
+	sigaddset(&sigset, SIGWINCH);
+	sigaddset(&sigset, SIGPIPE);
+	sigaddset(&sigset, SIGPROF);
+	sigaddset(&sigset, SIGINT);
+	sigaddset(&sigset, SIGTERM);
+	sigaddset(&sigset, SIGCHLD);
+	sigaddset(&sigset, SIGALRM);
+	sigaddset(&sigset, SIGIO);
+	sigaddset(&sigset, SIGUSR1);
+
+	pthread_sigmask(SIG_SETMASK, &sigset, NULL);
+}
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index 9f086f939420..184566edeee9 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -142,57 +142,6 @@ out:
 	return ok;
 }
 
-static int os_page_mincore(void *addr)
-{
-	char vec[2];
-	int ret;
-
-	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
-	if (ret < 0) {
-		if (errno == ENOMEM || errno == EINVAL)
-			return 0;
-		else
-			return -errno;
-	}
-
-	return vec[0] & 1;
-}
-
-int os_mincore(void *addr, unsigned long len)
-{
-	char *vec;
-	int ret, i;
-
-	if (len <= UM_KERN_PAGE_SIZE)
-		return os_page_mincore(addr);
-
-	vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
-	if (!vec)
-		return -ENOMEM;
-
-	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
-	if (ret < 0) {
-		if (errno == ENOMEM || errno == EINVAL)
-			ret = 0;
-		else
-			ret = -errno;
-
-		goto out;
-	}
-
-	for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
-		if (!(vec[i] & 1)) {
-			ret = 0;
-			goto out;
-		}
-	}
-
-	ret = 1;
-out:
-	free(vec);
-	return ret;
-}
-
 void init_new_thread_signals(void)
 {
 	set_handler(SIGSEGV);
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index 9aac8def4d63..a05a6ecee756 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -11,6 +11,7 @@
 #include <sched.h>
 #include <signal.h>
 #include <string.h>
+#include <sys/epoll.h>
 #include <kern_util.h>
 #include <init.h>
 #include <os.h>
@@ -21,184 +22,51 @@
  * Protected by sigio_lock(), also used by sigio_cleanup, which is an
  * exitcall.
  */
-static int write_sigio_pid = -1;
-static unsigned long write_sigio_stack;
+static struct os_helper_thread *write_sigio_td;
 
-/*
- * These arrays are initialized before the sigio thread is started, and
- * the descriptors closed after it is killed.  So, it can't see them change.
- * On the UML side, they are changed under the sigio_lock.
- */
-#define SIGIO_FDS_INIT {-1, -1}
-
-static int write_sigio_fds[2] = SIGIO_FDS_INIT;
-static int sigio_private[2] = SIGIO_FDS_INIT;
+static int epollfd = -1;
 
-struct pollfds {
-	struct pollfd *poll;
-	int size;
-	int used;
-};
+#define MAX_EPOLL_EVENTS 64
 
-/*
- * Protected by sigio_lock().  Used by the sigio thread, but the UML thread
- * synchronizes with it.
- */
-static struct pollfds current_poll;
-static struct pollfds next_poll;
-static struct pollfds all_sigio_fds;
+static struct epoll_event epoll_events[MAX_EPOLL_EVENTS];
 
-static int write_sigio_thread(void *unused)
+static void *write_sigio_thread(void *unused)
 {
-	struct pollfds *fds, tmp;
-	struct pollfd *p;
-	int i, n, respond_fd;
-	char c;
-
-	os_set_pdeathsig();
-	os_fix_helper_signals();
-	fds = &current_poll;
+	int pid = getpid();
+	int r;
+
+	os_fix_helper_thread_signals();
+
 	while (1) {
-		n = poll(fds->poll, fds->used, -1);
-		if (n < 0) {
+		r = epoll_wait(epollfd, epoll_events, MAX_EPOLL_EVENTS, -1);
+		if (r < 0) {
 			if (errno == EINTR)
 				continue;
-			printk(UM_KERN_ERR "write_sigio_thread : poll returned "
-			       "%d, errno = %d\n", n, errno);
+			printk(UM_KERN_ERR "%s: epoll_wait failed, errno = %d\n",
+			       __func__, errno);
 		}
-		for (i = 0; i < fds->used; i++) {
-			p = &fds->poll[i];
-			if (p->revents == 0)
-				continue;
-			if (p->fd == sigio_private[1]) {
-				CATCH_EINTR(n = read(sigio_private[1], &c,
-						     sizeof(c)));
-				if (n != sizeof(c))
-					printk(UM_KERN_ERR
-					       "write_sigio_thread : "
-					       "read on socket failed, "
-					       "err = %d\n", errno);
-				tmp = current_poll;
-				current_poll = next_poll;
-				next_poll = tmp;
-				respond_fd = sigio_private[1];
-			}
-			else {
-				respond_fd = write_sigio_fds[1];
-				fds->used--;
-				memmove(&fds->poll[i], &fds->poll[i + 1],
-					(fds->used - i) * sizeof(*fds->poll));
-			}
-
-			CATCH_EINTR(n = write(respond_fd, &c, sizeof(c)));
-			if (n != sizeof(c))
-				printk(UM_KERN_ERR "write_sigio_thread : "
-				       "write on socket failed, err = %d\n",
-				       errno);
-		}
-	}
 
-	return 0;
-}
-
-static int need_poll(struct pollfds *polls, int n)
-{
-	struct pollfd *new;
-
-	if (n <= polls->size)
-		return 0;
-
-	new = uml_kmalloc(n * sizeof(struct pollfd), UM_GFP_ATOMIC);
-	if (new == NULL) {
-		printk(UM_KERN_ERR "need_poll : failed to allocate new "
-		       "pollfds\n");
-		return -ENOMEM;
+		CATCH_EINTR(r = tgkill(pid, pid, SIGIO));
+		if (r < 0)
+			printk(UM_KERN_ERR "%s: tgkill failed, errno = %d\n",
+			       __func__, errno);
 	}
 
-	memcpy(new, polls->poll, polls->used * sizeof(struct pollfd));
-	kfree(polls->poll);
-
-	polls->poll = new;
-	polls->size = n;
-	return 0;
-}
-
-/*
- * Must be called with sigio_lock held, because it's needed by the marked
- * critical section.
- */
-static void update_thread(void)
-{
-	unsigned long flags;
-	int n;
-	char c;
-
-	flags = um_set_signals_trace(0);
-	CATCH_EINTR(n = write(sigio_private[0], &c, sizeof(c)));
-	if (n != sizeof(c)) {
-		printk(UM_KERN_ERR "update_thread : write failed, err = %d\n",
-		       errno);
-		goto fail;
-	}
-
-	CATCH_EINTR(n = read(sigio_private[0], &c, sizeof(c)));
-	if (n != sizeof(c)) {
-		printk(UM_KERN_ERR "update_thread : read failed, err = %d\n",
-		       errno);
-		goto fail;
-	}
-
-	um_set_signals_trace(flags);
-	return;
- fail:
-	/* Critical section start */
-	if (write_sigio_pid != -1) {
-		os_kill_process(write_sigio_pid, 1);
-		free_stack(write_sigio_stack, 0);
-	}
-	write_sigio_pid = -1;
-	close(sigio_private[0]);
-	close(sigio_private[1]);
-	close(write_sigio_fds[0]);
-	close(write_sigio_fds[1]);
-	/* Critical section end */
-	um_set_signals_trace(flags);
+	return NULL;
 }
 
 int __add_sigio_fd(int fd)
 {
-	struct pollfd *p;
-	int err, i, n;
-
-	for (i = 0; i < all_sigio_fds.used; i++) {
-		if (all_sigio_fds.poll[i].fd == fd)
-			break;
-	}
-	if (i == all_sigio_fds.used)
-		return -ENOSPC;
-
-	p = &all_sigio_fds.poll[i];
-
-	for (i = 0; i < current_poll.used; i++) {
-		if (current_poll.poll[i].fd == fd)
-			return 0;
-	}
-
-	n = current_poll.used;
-	err = need_poll(&next_poll, n + 1);
-	if (err)
-		return err;
-
-	memcpy(next_poll.poll, current_poll.poll,
-	       current_poll.used * sizeof(struct pollfd));
-	next_poll.poll[n] = *p;
-	next_poll.used = n + 1;
-	update_thread();
-
-	return 0;
+	struct epoll_event event = {
+		.data.fd = fd,
+		.events = EPOLLIN | EPOLLET,
+	};
+	int r;
+
+	CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &event));
+	return r < 0 ? -errno : 0;
 }
 
-
 int add_sigio_fd(int fd)
 {
 	int err;
@@ -212,38 +80,11 @@ int add_sigio_fd(int fd)
 
 int __ignore_sigio_fd(int fd)
 {
-	struct pollfd *p;
-	int err, i, n = 0;
-
-	/*
-	 * This is called from exitcalls elsewhere in UML - if
-	 * sigio_cleanup has already run, then update_thread will hang
-	 * or fail because the thread is no longer running.
-	 */
-	if (write_sigio_pid == -1)
-		return -EIO;
-
-	for (i = 0; i < current_poll.used; i++) {
-		if (current_poll.poll[i].fd == fd)
-			break;
-	}
-	if (i == current_poll.used)
-		return -ENOENT;
-
-	err = need_poll(&next_poll, current_poll.used - 1);
-	if (err)
-		return err;
-
-	for (i = 0; i < current_poll.used; i++) {
-		p = &current_poll.poll[i];
-		if (p->fd != fd)
-			next_poll.poll[n++] = *p;
-	}
-	next_poll.used = current_poll.used - 1;
-
-	update_thread();
+	struct epoll_event event;
+	int r;
 
-	return 0;
+	CATCH_EINTR(r = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event));
+	return r < 0 ? -errno : 0;
 }
 
 int ignore_sigio_fd(int fd)
@@ -257,125 +98,37 @@ int ignore_sigio_fd(int fd)
 	return err;
 }
 
-static struct pollfd *setup_initial_poll(int fd)
-{
-	struct pollfd *p;
-
-	p = uml_kmalloc(sizeof(struct pollfd), UM_GFP_KERNEL);
-	if (p == NULL) {
-		printk(UM_KERN_ERR "setup_initial_poll : failed to allocate "
-		       "poll\n");
-		return NULL;
-	}
-	*p = ((struct pollfd) { .fd		= fd,
-				.events 	= POLLIN,
-				.revents 	= 0 });
-	return p;
-}
-
 static void write_sigio_workaround(void)
 {
-	struct pollfd *p;
 	int err;
-	int l_write_sigio_fds[2];
-	int l_sigio_private[2];
-	int l_write_sigio_pid;
 
-	/* We call this *tons* of times - and most ones we must just fail. */
 	sigio_lock();
-	l_write_sigio_pid = write_sigio_pid;
-	sigio_unlock();
-
-	if (l_write_sigio_pid != -1)
-		return;
+	if (write_sigio_td)
+		goto out;
 
-	err = os_pipe(l_write_sigio_fds, 1, 1);
-	if (err < 0) {
-		printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 1 failed, "
-		       "err = %d\n", -err);
-		return;
+	epollfd = epoll_create(MAX_EPOLL_EVENTS);
+	if (epollfd < 0) {
+		printk(UM_KERN_ERR "%s: epoll_create failed, errno = %d\n",
+		       __func__, errno);
+		goto out;
 	}
-	err = os_pipe(l_sigio_private, 1, 1);
+
+	err = os_run_helper_thread(&write_sigio_td, write_sigio_thread, NULL);
 	if (err < 0) {
-		printk(UM_KERN_ERR "write_sigio_workaround - os_pipe 2 failed, "
-		       "err = %d\n", -err);
-		goto out_close1;
+		printk(UM_KERN_ERR "%s: os_run_helper_thread failed, errno = %d\n",
+		       __func__, -err);
+		close(epollfd);
+		epollfd = -1;
+		goto out;
 	}
 
-	p = setup_initial_poll(l_sigio_private[1]);
-	if (!p)
-		goto out_close2;
-
-	sigio_lock();
-
-	/*
-	 * Did we race? Don't try to optimize this, please, it's not so likely
-	 * to happen, and no more than once at the boot.
-	 */
-	if (write_sigio_pid != -1)
-		goto out_free;
-
-	current_poll = ((struct pollfds) { .poll 	= p,
-					   .used 	= 1,
-					   .size 	= 1 });
-
-	if (write_sigio_irq(l_write_sigio_fds[0]))
-		goto out_clear_poll;
-
-	memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds));
-	memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private));
-
-	write_sigio_pid = run_helper_thread(write_sigio_thread, NULL,
-					    CLONE_FILES | CLONE_VM,
-					    &write_sigio_stack);
-
-	if (write_sigio_pid < 0)
-		goto out_clear;
-
-	sigio_unlock();
-	return;
-
-out_clear:
-	write_sigio_pid = -1;
-	write_sigio_fds[0] = -1;
-	write_sigio_fds[1] = -1;
-	sigio_private[0] = -1;
-	sigio_private[1] = -1;
-out_clear_poll:
-	current_poll = ((struct pollfds) { .poll	= NULL,
-					   .size	= 0,
-					   .used	= 0 });
-out_free:
+out:
 	sigio_unlock();
-	kfree(p);
-out_close2:
-	close(l_sigio_private[0]);
-	close(l_sigio_private[1]);
-out_close1:
-	close(l_write_sigio_fds[0]);
-	close(l_write_sigio_fds[1]);
 }
 
-void sigio_broken(int fd)
+void sigio_broken(void)
 {
-	int err;
-
 	write_sigio_workaround();
-
-	sigio_lock();
-	err = need_poll(&all_sigio_fds, all_sigio_fds.used + 1);
-	if (err) {
-		printk(UM_KERN_ERR "maybe_sigio_broken - failed to add pollfd "
-		       "for descriptor %d\n", fd);
-		goto out;
-	}
-
-	all_sigio_fds.poll[all_sigio_fds.used++] =
-		((struct pollfd) { .fd  	= fd,
-				   .events 	= POLLIN,
-				   .revents 	= 0 });
-out:
-	sigio_unlock();
 }
 
 /* Changed during early boot */
@@ -389,17 +142,16 @@ void maybe_sigio_broken(int fd)
 	if (pty_output_sigio)
 		return;
 
-	sigio_broken(fd);
+	sigio_broken();
 }
 
 static void sigio_cleanup(void)
 {
-	if (write_sigio_pid == -1)
+	if (!write_sigio_td)
 		return;
 
-	os_kill_process(write_sigio_pid, 1);
-	free_stack(write_sigio_stack, 0);
-	write_sigio_pid = -1;
+	os_kill_helper_thread(write_sigio_td);
+	write_sigio_td = NULL;
 }
 
 __uml_exitcall(sigio_cleanup);
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 9ea7269ffb77..e71e5b4878d1 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -21,7 +21,7 @@
 #include <sys/ucontext.h>
 #include <timetravel.h>
 
-void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
+void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *, void *mc) = {
 	[SIGTRAP]	= relay_signal,
 	[SIGFPE]	= relay_signal,
 	[SIGILL]	= relay_signal,
@@ -47,7 +47,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 	if ((sig != SIGIO) && (sig != SIGWINCH))
 		unblock_signals_trace();
 
-	(*sig_info[sig])(sig, si, &r);
+	(*sig_info[sig])(sig, si, &r, mc);
 
 	errno = save_errno;
 }
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index e2f8f156402f..ae2aea062f06 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -166,7 +166,7 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi)
 static void handle_segv(int pid, struct uml_pt_regs *regs)
 {
 	get_skas_faultinfo(pid, &regs->faultinfo);
-	segv(regs->faultinfo, 0, 1, NULL);
+	segv(regs->faultinfo, 0, 1, NULL, NULL);
 }
 
 static void handle_trap(int pid, struct uml_pt_regs *regs)
@@ -525,7 +525,7 @@ void userspace(struct uml_pt_regs *regs)
 					get_skas_faultinfo(pid,
 							   &regs->faultinfo);
 					(*sig_info[SIGSEGV])(SIGSEGV, (struct siginfo *)&si,
-							     regs);
+							     regs, NULL);
 				}
 				else handle_segv(pid, regs);
 				break;
@@ -533,7 +533,7 @@ void userspace(struct uml_pt_regs *regs)
 				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
-				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
+				relay_signal(SIGTRAP, (struct siginfo *)&si, regs, NULL);
 				break;
 			case SIGALRM:
 				break;
@@ -543,7 +543,7 @@ void userspace(struct uml_pt_regs *regs)
 			case SIGFPE:
 			case SIGWINCH:
 				block_signals_trace();
-				(*sig_info[sig])(sig, (struct siginfo *)&si, regs);
+				(*sig_info[sig])(sig, (struct siginfo *)&si, regs, NULL);
 				unblock_signals_trace();
 				break;
 			default:
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index cf0ad89f5639..f7fb3d88c57b 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,4 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
+
+# Branch profiling isn't noinstr-safe.  Disable it for arch/x86/*
+subdir-ccflags-$(CONFIG_TRACE_BRANCH_PROFILING) += -DDISABLE_BRANCH_PROFILING
+
 obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += coco/
 
 obj-y += entry/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118..337ff193b566 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,8 @@ config X86_64
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
+	select ARCH_HAS_PTDUMP
+	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_PER_VMA_LOCK
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
@@ -77,7 +79,8 @@ config X86
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CRC32
-	select ARCH_HAS_CRC_T10DIF		if X86_64
+	select ARCH_HAS_CRC64			if X86_64
+	select ARCH_HAS_CRC_T10DIF
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
@@ -85,6 +88,7 @@ config X86
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_EXECMEM_ROX		if X86_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -132,7 +136,7 @@ config X86
 	select ARCH_SUPPORTS_AUTOFDO_CLANG
 	select ARCH_SUPPORTS_PROPELLER_CLANG    if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CMPXCHG64
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CX8
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
@@ -146,8 +150,10 @@ config X86
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP	if X86_64
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP	if X86_64
+	select ARCH_WANT_HUGETLB_VMEMMAP_PREINIT if X86_64
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select ARCH_HAS_PARANOID_L1D_FLUSH
+	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select BUILDTIME_TABLE_SORT
 	select CLKEVT_I8253
 	select CLOCKSOURCE_WATCHDOG
@@ -174,10 +180,10 @@ config X86
 	select GENERIC_IRQ_RESERVATION_MODE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PENDING_IRQ		if SMP
-	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_VDSO_DATA_STORE
 	select GENERIC_VDSO_TIME_NS
 	select GENERIC_VDSO_OVERFLOW_PROTECT
 	select GUP_GET_PXX_LOW_HIGH		if X86_PAE
@@ -232,7 +238,7 @@ config X86
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_EISA
+	select HAVE_EISA			if X86_32
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
@@ -277,7 +283,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_MERGE_VMAS
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
@@ -285,7 +291,7 @@ config X86
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
-	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
+	select HAVE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
@@ -421,20 +427,10 @@ config DYNAMIC_PHYSICAL_MASK
 
 config PGTABLE_LEVELS
 	int
-	default 5 if X86_5LEVEL
-	default 4 if X86_64
+	default 5 if X86_64
 	default 3 if X86_PAE
 	default 2
 
-config CC_HAS_SANE_STACKPROTECTOR
-	bool
-	default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
-	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC) $(CLANG_FLAGS))
-	help
-	  We have to make sure stack protector is unconditionally disabled if
-	  the compiler produces broken code or if it does not let us control
-	  the segment on 32-bit kernels.
-
 menu "Processor type and features"
 
 config SMP
@@ -466,20 +462,28 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config X86_X2APIC
-	bool "Support x2apic"
+	bool "x2APIC interrupt controller architecture support"
 	depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
+	default y
 	help
-	  This enables x2apic support on CPUs that have this feature.
+	  x2APIC is an interrupt controller architecture, a component of which
+	  (the local APIC) is present in the CPU. It allows faster access to
+	  the local APIC and supports a larger number of CPUs in the system
+	  than the predecessors.
 
-	  This allows 32-bit apic IDs (so it can support very large systems),
-	  and accesses the local apic via MSRs not via mmio.
+	  x2APIC was introduced in Intel CPUs around 2008 and in AMD EPYC CPUs
+	  in 2019, but it can be disabled by the BIOS. It is also frequently
+	  emulated in virtual machines, even when the host CPU does not support
+	  it. Support in the CPU can be checked by executing
+		grep x2apic /proc/cpuinfo
 
-	  Some Intel systems circa 2022 and later are locked into x2APIC mode
-	  and can not fall back to the legacy APIC modes if SGX or TDX are
-	  enabled in the BIOS. They will boot with very reduced functionality
-	  without enabling this option.
+	  If this configuration option is disabled, the kernel will boot with
+	  very reduced functionality and performance on some platforms that
+	  have x2APIC enabled. On the other hand, on hardware that does not
+	  support x2APIC, a kernel with this option enabled will just fallback
+	  to older APIC implementations.
 
-	  If you don't know what to do here, say N.
+	  If in doubt, say Y.
 
 config X86_POSTED_MSI
 	bool "Enable MSI and MSI-x delivery by posted interrupts"
@@ -503,8 +507,10 @@ config X86_MPPARSE
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
-	select KERNFS
-	select PROC_CPU_RESCTRL		if PROC_FS
+	depends on MISC_FILESYSTEMS
+	select ARCH_HAS_CPU_RESCTRL
+	select RESCTRL_FS
+	select RESCTRL_FS_PSEUDO_LOCK
 	help
 	  Enable x86 CPU resource control support.
 
@@ -530,12 +536,6 @@ config X86_FRED
 	  ring transitions and exception/interrupt handling if the
 	  system supports it.
 
-config X86_BIGSMP
-	bool "Support for big SMP systems with more than 8 CPUs"
-	depends on SMP && X86_32
-	help
-	  This option is needed for the systems that have more than 8 CPUs.
-
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
 	default y
@@ -549,17 +549,17 @@ config X86_EXTENDED_PLATFORM
 	  CONFIG_64BIT.
 
 	  32-bit platforms (CONFIG_64BIT=n):
-		Goldfish (Android emulator)
-		AMD Elan
+		Goldfish (mostly Android emulator)
+		Intel CE media processor (CE4100) SoC
+		Intel Quark
 		RDC R-321x SoC
-		SGI 320/540 (Visual Workstation)
-		STA2X11-based (e.g. Northville)
-		Moorestown MID devices
 
 	  64-bit platforms (CONFIG_64BIT=y):
 		Numascale NumaChip
 		ScaleMP vSMP
 		SGI Ultraviolet
+		Merrifield/Moorefield MID devices
+		Goldfish (mostly Android emulator)
 
 	  If you have one of these systems, or if you want to build a
 	  generic distribution kernel, say Y here - otherwise say N.
@@ -604,8 +604,31 @@ config X86_UV
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
 
-# Following is an alphabetically sorted list of 32 bit extended platforms
-# Please maintain the alphabetic order if and when there are additions
+config X86_INTEL_MID
+	bool "Intel Z34xx/Z35xx MID platform support"
+	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
+	depends on PCI
+	depends on X86_64 || (EXPERT && PCI_GOANY)
+	depends on X86_IO_APIC
+	select I2C
+	select DW_APB_TIMER
+	select INTEL_SCU_PCI
+	help
+	  Select to build a kernel capable of supporting 64-bit Intel MID
+	  (Mobile Internet Device) platform systems which do not have
+	  the PCI legacy interfaces.
+
+	  The only supported devices are the 22nm Merrified (Z34xx)
+	  and Moorefield (Z35xx) SoC used in the Intel Edison board and
+	  a small number of Android devices such as the Asus Zenfone 2,
+	  Asus FonePad 8 and Dell Venue 7.
+
+	  If you are building for a PC class system or non-MID tablet
+	  SoCs like Bay Trail (Z36xx/Z37xx), say N here.
+
+	  Intel MID platforms are based on an Intel processor and chipset which
+	  consume less power than most of the x86 derivatives.
 
 config X86_GOLDFISH
 	bool "Goldfish (Virtual Platform)"
@@ -615,6 +638,9 @@ config X86_GOLDFISH
 	  for Android development. Unless you are building for the Android
 	  Goldfish emulator say N here.
 
+# Following is an alphabetically sorted list of 32 bit extended platforms
+# Please maintain the alphabetic order if and when there are additions
+
 config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
@@ -630,24 +656,6 @@ config X86_INTEL_CE
 	  This option compiles in support for the CE4100 SOC for settop
 	  boxes and media devices.
 
-config X86_INTEL_MID
-	bool "Intel MID platform support"
-	depends on X86_EXTENDED_PLATFORM
-	depends on X86_PLATFORM_DEVICES
-	depends on PCI
-	depends on X86_64 || (PCI_GOANY && X86_32)
-	depends on X86_IO_APIC
-	select I2C
-	select DW_APB_TIMER
-	select INTEL_SCU_PCI
-	help
-	  Select to build a kernel capable of supporting Intel MID (Mobile
-	  Internet Device) platform systems which do not have the PCI legacy
-	  interfaces. If you are building for a PC class system say N here.
-
-	  Intel MID platforms are based on an Intel processor and chipset which
-	  consume less power than most of the x86 derivatives.
-
 config X86_INTEL_QUARK
 	bool "Intel Quark platform support"
 	depends on X86_32
@@ -665,6 +673,17 @@ config X86_INTEL_QUARK
 	  Say Y here if you have a Quark based system such as the Arduino
 	  compatible Intel Galileo.
 
+config X86_RDC321X
+	bool "RDC R-321x SoC"
+	depends on X86_32
+	depends on X86_EXTENDED_PLATFORM
+	select M486
+	select X86_REBOOTFIXUPS
+	help
+	  This option is needed for RDC R-321x system-on-chip, also known
+	  as R-8610-(G).
+	  If you don't have one of these chips, you should say N here.
+
 config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
 	depends on X86 && ACPI && PCI
@@ -718,29 +737,6 @@ config IOSF_MBI_DEBUG
 
 	  If you don't require the option or are in doubt, say N.
 
-config X86_RDC321X
-	bool "RDC R-321x SoC"
-	depends on X86_32
-	depends on X86_EXTENDED_PLATFORM
-	select M486
-	select X86_REBOOTFIXUPS
-	help
-	  This option is needed for RDC R-321x system-on-chip, also known
-	  as R-8610-(G).
-	  If you don't have one of these chips, you should say N here.
-
-config X86_32_NON_STANDARD
-	bool "Support non-standard 32-bit SMP architectures"
-	depends on X86_32 && SMP
-	depends on X86_EXTENDED_PLATFORM
-	help
-	  This option compiles in the bigsmp and STA2X11 default
-	  subarchitectures.  It is intended for a generic binary
-	  kernel. If you select them all, kernel will probe it one by
-	  one and will fallback to default.
-
-# Alphabetically sorted list of Non standard 32 bit platforms
-
 config X86_SUPPORTS_MEMORY_FAILURE
 	def_bool y
 	# MCE code calls memory_failure():
@@ -750,19 +746,6 @@ config X86_SUPPORTS_MEMORY_FAILURE
 	depends on X86_64 || !SPARSEMEM
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 
-config STA2X11
-	bool "STA2X11 Companion Chip Support"
-	depends on X86_32_NON_STANDARD && PCI
-	select SWIOTLB
-	select MFD_STA2X11
-	select GPIOLIB
-	help
-	  This adds support for boards based on the STA2X11 IO-Hub,
-	  a.k.a. "ConneXt". The chip is used in place of the standard
-	  PC chipset, so all "standard" peripherals are missing. If this
-	  option is selected the kernel will still be able to boot on
-	  standard PC machines.
-
 config X86_32_IRIS
 	tristate "Eurobraille/Iris poweroff module"
 	depends on X86_32
@@ -811,6 +794,7 @@ config PARAVIRT
 
 config PARAVIRT_XXL
 	bool
+	depends on X86_64
 
 config PARAVIRT_DEBUG
 	bool "paravirt-ops debugging"
@@ -902,6 +886,7 @@ config INTEL_TDX_GUEST
 	depends on X86_64 && CPU_SUP_INTEL
 	depends on X86_X2APIC
 	depends on EFI_STUB
+	depends on PARAVIRT
 	select ARCH_HAS_CC_PLATFORM
 	select X86_MEM_ENCRYPT
 	select X86_MCE
@@ -1012,8 +997,7 @@ config NR_CPUS_RANGE_BEGIN
 config NR_CPUS_RANGE_END
 	int
 	depends on X86_32
-	default   64 if  SMP &&  X86_BIGSMP
-	default    8 if  SMP && !X86_BIGSMP
+	default    8 if  SMP
 	default    1 if !SMP
 
 config NR_CPUS_RANGE_END
@@ -1026,7 +1010,6 @@ config NR_CPUS_RANGE_END
 config NR_CPUS_DEFAULT
 	int
 	depends on X86_32
-	default   32 if  X86_BIGSMP
 	default    8 if  SMP
 	default    1 if !SMP
 
@@ -1102,7 +1085,7 @@ config UP_LATE_INIT
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors" if !PCI_MSI
 	default PCI_MSI
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -1127,7 +1110,7 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+	depends on X86_64 || SMP || X86_UP_APIC || PCI_MSI
 	select IRQ_DOMAIN_HIERARCHY
 
 config ACPI_MADT_WAKEUP
@@ -1341,6 +1324,7 @@ config X86_REBOOTFIXUPS
 config MICROCODE
 	def_bool y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
+	select CRYPTO_LIB_SHA256 if CPU_SUP_AMD
 
 config MICROCODE_INITRD32
 	def_bool y
@@ -1395,15 +1379,11 @@ config X86_CPUID
 	  with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
 	  /dev/cpu/31/cpuid.
 
-choice
-	prompt "High Memory Support"
-	default HIGHMEM4G
+config HIGHMEM4G
+	bool "High Memory Support"
 	depends on X86_32
-
-config NOHIGHMEM
-	bool "off"
 	help
-	  Linux can use up to 64 Gigabytes of physical memory on x86 systems.
+	  Linux can use up to 4 Gigabytes of physical memory on x86 systems.
 	  However, the address space of 32-bit x86 processors is only 4
 	  Gigabytes large. That means that, if you have a large amount of
 	  physical memory, not all of it can be "permanently mapped" by the
@@ -1419,38 +1399,9 @@ config NOHIGHMEM
 	  possible.
 
 	  If the machine has between 1 and 4 Gigabytes physical RAM, then
-	  answer "4GB" here.
-
-	  If more than 4 Gigabytes is used then answer "64GB" here. This
-	  selection turns Intel PAE (Physical Address Extension) mode on.
-	  PAE implements 3-level paging on IA32 processors. PAE is fully
-	  supported by Linux, PAE mode is implemented on all recent Intel
-	  processors (Pentium Pro and better). NOTE: If you say "64GB" here,
-	  then the kernel will not boot on CPUs that don't support PAE!
-
-	  The actual amount of total physical memory will either be
-	  auto detected or can be forced by using a kernel command line option
-	  such as "mem=256M". (Try "man bootparam" or see the documentation of
-	  your boot loader (lilo or loadlin) about how to pass options to the
-	  kernel at boot time.)
-
-	  If unsure, say "off".
-
-config HIGHMEM4G
-	bool "4GB"
-	help
-	  Select this if you have a 32-bit processor and between 1 and 4
-	  gigabytes of physical RAM.
-
-config HIGHMEM64G
-	bool "64GB"
-	depends on X86_HAVE_PAE
-	select X86_PAE
-	help
-	  Select this if you have a 32-bit processor and more than 4
-	  gigabytes of physical RAM.
+	  answer "Y" here.
 
-endchoice
+	  If unsure, say N.
 
 choice
 	prompt "Memory split" if EXPERT
@@ -1496,41 +1447,18 @@ config PAGE_OFFSET
 	depends on X86_32
 
 config HIGHMEM
-	def_bool y
-	depends on X86_32 && (HIGHMEM64G || HIGHMEM4G)
+	def_bool HIGHMEM4G
 
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && X86_HAVE_PAE
 	select PHYS_ADDR_T_64BIT
-	select SWIOTLB
 	help
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
 	  has the cost of more pagetable lookup overhead, and also
 	  consumes more pagetable space per process.
 
-config X86_5LEVEL
-	bool "Enable 5-level page tables support"
-	default y
-	select DYNAMIC_MEMORY_LAYOUT
-	select SPARSEMEM_VMEMMAP
-	depends on X86_64
-	help
-	  5-level paging enables access to larger address space:
-	  up to 128 PiB of virtual address space and 4 PiB of
-	  physical address space.
-
-	  It will be supported by future Intel CPUs.
-
-	  A kernel with the option enabled can be booted on machines that
-	  support 4- or 5-level paging.
-
-	  See Documentation/arch/x86/x86_64/5level-paging.rst for more
-	  information.
-
-	  Say N if unsure.
-
 config X86_DIRECT_GBPAGES
 	def_bool y
 	depends on X86_64
@@ -1573,8 +1501,7 @@ config AMD_MEM_ENCRYPT
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
-	default y if X86_BIGSMP
+	depends on X86_64
 	select USE_PERCPU_NUMA_NODE_ID
 	select OF_NUMA if OF
 	help
@@ -1587,9 +1514,6 @@ config NUMA
 	  For 64-bit this is recommended if the system is Intel Core i7
 	  (or later), AMD Opteron, or EM64T NUMA.
 
-	  For 32-bit this is only needed if you boot a 32-bit
-	  kernel on a 64-bit NUMA platform.
-
 	  Otherwise, you should say N.
 
 config AMD_NUMA
@@ -1628,9 +1552,9 @@ config ARCH_FLATMEM_ENABLE
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
-	depends on X86_64 || NUMA || X86_32 || X86_32_NON_STANDARD
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
+	select SPARSEMEM_VMEMMAP if X86_64
 
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool X86_64 || (NUMA && X86_32)
@@ -1674,15 +1598,6 @@ config X86_PMEM_LEGACY
 
 	  Say Y if unsure.
 
-config HIGHPTE
-	bool "Allocate 3rd-level pagetables from highmem"
-	depends on HIGHMEM
-	help
-	  The VM uses one page table entry for each page of physical memory.
-	  For systems with a lot of RAM, this can be wasteful of precious
-	  low memory.  Setting this option will put user-space page table
-	  entries in high memory.
-
 config X86_CHECK_BIOS_CORRUPTION
 	bool "Check for low memory corruption"
 	help
@@ -2199,6 +2114,7 @@ config RANDOMIZE_BASE
 config X86_NEED_RELOCS
 	def_bool y
 	depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
+	select ARCH_VMLINUX_NEEDS_RELOCS
 
 config PHYSICAL_ALIGN
 	hex "Alignment value to which kernel should be aligned"
@@ -2227,17 +2143,10 @@ config PHYSICAL_ALIGN
 
 	  Don't change this unless you know what you are doing.
 
-config DYNAMIC_MEMORY_LAYOUT
-	bool
-	help
-	  This option makes base addresses of vmalloc and vmemmap as well as
-	  __PAGE_OFFSET movable during boot.
-
 config RANDOMIZE_MEMORY
 	bool "Randomize the kernel memory sections"
 	depends on X86_64
 	depends on RANDOMIZE_BASE
-	select DYNAMIC_MEMORY_LAYOUT
 	default RANDOMIZE_BASE
 	help
 	  Randomizes the base virtual address of kernel memory sections
@@ -2284,7 +2193,7 @@ config HOTPLUG_CPU
 
 config COMPAT_VDSO
 	def_bool n
-	prompt "Disable the 32-bit vDSO (needed for glibc 2.3.3)"
+	prompt "Workaround for glibc 2.3.2 / 2.3.3 (released in year 2003/2004)"
 	depends on COMPAT_32
 	help
 	  Certain buggy versions of glibc will crash if they are
@@ -2428,6 +2337,7 @@ config STRICT_SIGALTSTACK_SIZE
 config CFI_AUTO_DEFAULT
 	bool "Attempt to use FineIBT by default at boot time"
 	depends on FINEIBT
+	depends on !RUST || RUSTC_VERSION >= 108800
 	default y
 	help
 	  Attempt to use FineIBT by default at boot time. If enabled,
@@ -2450,18 +2360,20 @@ config CC_HAS_NAMED_AS
 	def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
 	depends on CC_IS_GCC
 
+#
+# -fsanitize=kernel-address (KASAN) and -fsanitize=thread (KCSAN)
+# are incompatible with named address spaces with GCC < 13.3
+# (see GCC PR sanitizer/111736 and also PR sanitizer/115172).
+#
+
 config CC_HAS_NAMED_AS_FIXED_SANITIZERS
-	def_bool CC_IS_GCC && GCC_VERSION >= 130300
+	def_bool y
+	depends on !(KASAN || KCSAN) || GCC_VERSION >= 130300
+	depends on !(UBSAN_BOOL && KASAN) || GCC_VERSION >= 140200
 
 config USE_X86_SEG_SUPPORT
-	def_bool y
-	depends on CC_HAS_NAMED_AS
-	#
-	# -fsanitize=kernel-address (KASAN) and -fsanitize=thread
-	# (KCSAN) are incompatible with named address spaces with
-	# GCC < 13.3 - see GCC PR sanitizer/111736.
-	#
-	depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS
+	def_bool CC_HAS_NAMED_AS
+	depends on CC_HAS_NAMED_AS_FIXED_SANITIZERS
 
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)
@@ -2472,6 +2384,10 @@ config CC_HAS_RETURN_THUNK
 config CC_HAS_ENTRY_PADDING
 	def_bool $(cc-option,-fpatchable-function-entry=16,16)
 
+config CC_HAS_KCFI_ARITY
+	def_bool $(cc-option,-fsanitize=kcfi -fsanitize-kcfi-arity)
+	depends on CC_IS_CLANG && !RUST
+
 config FUNCTION_PADDING_CFI
 	int
 	default 59 if FUNCTION_ALIGNMENT_64B
@@ -2497,6 +2413,10 @@ config FINEIBT
 	depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE
 	select CALL_PADDING
 
+config FINEIBT_BHI
+	def_bool y
+	depends on FINEIBT && CC_HAS_KCFI_ARITY
+
 config HAVE_CALL_THUNKS
 	def_bool y
 	depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL
@@ -2760,6 +2680,18 @@ config MITIGATION_SSB
 	  of speculative execution in a similar way to the Meltdown and Spectre
 	  security vulnerabilities.
 
+config MITIGATION_ITS
+	bool "Enable Indirect Target Selection mitigation"
+	depends on CPU_SUP_INTEL && X86_64
+	depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK
+	select EXECMEM
+	default y
+	help
+	  Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in
+	  BPU on some Intel CPUs that may allow Spectre V2 style attacks. If
+	  disabled, mitigation cannot be enabled via cmdline.
+	  See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+
 endif
 
 config ARCH_HAS_ADD_PAGES
@@ -2963,6 +2895,19 @@ config PCI_MMCONFIG
 	default y
 	depends on PCI && (ACPI || JAILHOUSE_GUEST)
 	depends on X86_64 || (PCI_GOANY || PCI_GOMMCONFIG)
+	help
+	  Add support for accessing the PCI configuration space as a memory
+	  mapped area. It is the recommended method if the system supports
+	  this (it must have PCI Express and ACPI for it to be available).
+
+	  In the unlikely case that enabling this configuration option causes
+	  problems, the mechanism can be switched off with the 'pci=nommconf'
+	  command line parameter.
+
+	  Say N only if you are sure that your platform does not support this
+	  access method or you have problems caused by it.
+
+	  Say Y otherwise.
 
 config PCI_OLPC
 	def_bool y
@@ -2977,13 +2922,21 @@ config MMCONF_FAM10H
 	depends on X86_64 && PCI_MMCONFIG && ACPI
 
 config PCI_CNB20LE_QUIRK
-	bool "Read CNB20LE Host Bridge Windows" if EXPERT
-	depends on PCI
+	bool "Read PCI host bridge windows from the CNB20LE chipset" if EXPERT
+	depends on X86_32 && PCI
 	help
 	  Read the PCI windows out of the CNB20LE host bridge. This allows
 	  PCI hotplug to work on systems with the CNB20LE chipset which do
 	  not have ACPI.
 
+	  The ServerWorks (later Broadcom) CNB20LE was a chipset designed
+	  most probably only for Pentium III.
+
+	  To find out if you have such a chipset, search for a PCI device with
+	  1166:0009 PCI IDs, for example by executing
+		lspci -nn | grep '1166:0009'
+	  The code is inactive if there is none.
+
 	  There's no public spec for this chipset, and this functionality
 	  is known to be incomplete.
 
@@ -3201,4 +3154,6 @@ config HAVE_ATOMIC_IOMAP
 
 source "arch/x86/kvm/Kconfig"
 
+source "arch/x86/Kconfig.cpufeatures"
+
 source "arch/x86/Kconfig.assembler"
diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 6d20a6ce0507..c827f694fb72 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,20 +6,6 @@ config AS_AVX512
 	help
 	  Supported by binutils >= 2.25 and LLVM integrated assembler
 
-config AS_SHA1_NI
-	def_bool $(as-instr,sha1msg1 %xmm0$(comma)%xmm1)
-	help
-	  Supported by binutils >= 2.24 and LLVM integrated assembler
-
-config AS_SHA256_NI
-	def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
-	help
-	  Supported by binutils >= 2.24 and LLVM integrated assembler
-config AS_TPAUSE
-	def_bool $(as-instr,tpause %ecx)
-	help
-	  Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7
-
 config AS_GFNI
 	def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2)
 	help
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2a7279d80460..f928cf6e3252 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Put here option for CPU selection and depending optimization
 choice
-	prompt "Processor family"
-	default M686 if X86_32
-	default GENERIC_CPU if X86_64
+	prompt "x86-32 Processor family"
+	depends on X86_32
+	default M686
 	help
 	  This is the processor type of your CPU. This information is
 	  used for optimizing purposes. In order to compile a kernel
@@ -31,7 +31,6 @@ choice
 	  - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
 	  - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
 	  - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
-	  - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs.
 	  - "Crusoe" for the Transmeta Crusoe series.
 	  - "Efficeon" for the Transmeta Efficeon series.
 	  - "Winchip-C6" for original IDT Winchip.
@@ -42,13 +41,10 @@ choice
 	  - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
 	  - "VIA C7" for VIA C7.
-	  - "Intel P4" for the Pentium 4/Netburst microarchitecture.
-	  - "Core 2/newer Xeon" for all core2 and newer Intel CPUs.
 	  - "Intel Atom" for the Atom-microarchitecture CPUs.
-	  - "Generic-x86-64" for a kernel which runs on any x86-64 CPU.
 
 	  See each option's help text for additional details. If you don't know
-	  what to do, choose "486".
+	  what to do, choose "Pentium-Pro".
 
 config M486SX
 	bool "486SX"
@@ -114,11 +110,11 @@ config MPENTIUMIII
 	  extensions.
 
 config MPENTIUMM
-	bool "Pentium M"
+	bool "Pentium M/Pentium Dual Core/Core Solo/Core Duo"
 	depends on X86_32
 	help
 	  Select this for Intel Pentium M (not Pentium-4 M)
-	  notebook chips.
+	  "Merom" Core Solo/Duo notebook chips
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
@@ -139,22 +135,10 @@ config MPENTIUM4
 		-Mobile Pentium 4
 		-Mobile Pentium 4 M
 		-Extreme Edition (Gallatin)
-		-Prescott
-		-Prescott 2M
-		-Cedar Mill
-		-Presler
-		-Smithfiled
 	    Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
 		-Foster
 		-Prestonia
 		-Gallatin
-		-Nocona
-		-Irwindale
-		-Cranford
-		-Potomac
-		-Paxville
-		-Dempsey
-
 
 config MK6
 	bool "K6/K6-II/K6-III"
@@ -172,13 +156,6 @@ config MK7
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
 
-config MK8
-	bool "Opteron/Athlon64/Hammer/K8"
-	help
-	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
-	  Enables use of some extended instructions, and passes appropriate
-	  optimization flags to GCC.
-
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -258,43 +235,39 @@ config MVIAC7
 	  Select this for a VIA C7.  Selecting this uses the correct cache
 	  shift and tells gcc to treat the CPU as a 686.
 
-config MPSC
-	bool "Intel P4 / older Netburst based Xeon"
-	depends on X86_64
-	help
-	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
-	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
-	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
-	  Netburst core and shouldn't use this option. You can distinguish them
-	  using the cpu family field
-	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
-
-config MCORE2
-	bool "Core 2/newer Xeon"
-	help
-
-	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
-	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
-	  (not a typo)
-
 config MATOM
 	bool "Intel Atom"
 	help
-
 	  Select this for the Intel Atom platform. Intel Atom CPUs have an
 	  in-order pipelining architecture and thus can benefit from
 	  accordingly optimized code. Use a recent GCC with specific Atom
 	  support in order to fully benefit from selecting this option.
 
-config GENERIC_CPU
-	bool "Generic-x86-64"
+endchoice
+
+config CC_HAS_MARCH_NATIVE
+	# This flag might not be available in cross-compilers:
+	def_bool $(cc-option, -march=native)
+	# LLVM 18 has an easily triggered internal compiler error in core
+	# networking code with '-march=native' on certain systems:
+	# https://github.com/llvm/llvm-project/issues/72026
+	# LLVM 19 introduces an optimization that resolves some high stack
+	# usage warnings that only appear wth '-march=native'.
+	depends on CC_IS_GCC || CLANG_VERSION >= 190100
+
+config X86_NATIVE_CPU
+	bool "Build and optimize for local/native CPU"
 	depends on X86_64
+	depends on CC_HAS_MARCH_NATIVE
 	help
-	  Generic x86-64 CPU.
-	  Run equally well on all x86-64 CPUs.
+	  Optimize for the current CPU used to compile the kernel.
+	  Use this option if you intend to build the kernel for your
+	  local machine.
 
-endchoice
+	  Note that such a kernel might not work optimally on a
+	  different x86 machine.
+
+	  If unsure, say N.
 
 config X86_GENERIC
 	bool "Generic x86 support"
@@ -317,8 +290,8 @@ config X86_INTERNODE_CACHE_SHIFT
 
 config X86_L1_CACHE_SHIFT
 	int
-	default "7" if MPENTIUM4 || MPSC
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "7" if MPENTIUM4
+	default "6" if MK7 || MPENTIUMM || MATOM || MVIAC7 || X86_GENERIC || X86_64
 	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
@@ -336,51 +309,35 @@ config X86_ALIGNMENT_16
 
 config X86_INTEL_USERCOPY
 	def_bool y
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK7 || MEFFICEON
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-
-#
-# P6_NOPs are a relatively minor optimization that require a family >=
-# 6 processor, except that it is broken on certain VIA chips.
-# Furthermore, AMD chips prefer a totally different sequence of NOPs
-# (which work on all CPUs).  In addition, it looks like Virtual PC
-# does not understand them.
-#
-# As a result, disallow these if we're not compiling for X86_64 (these
-# NOPs do work on all x86-64 capable chips); the list of processors in
-# the right-hand clause are the cores that benefit from this optimization.
-#
-config X86_P6_NOP
-	def_bool y
-	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MATOM
 
 config X86_TSC
 	def_bool y
-	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
+	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MATOM) || X86_64
 
 config X86_HAVE_PAE
 	def_bool y
-	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64
+	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC7 || MATOM || X86_64
 
-config X86_CMPXCHG64
+config X86_CX8
 	def_bool y
-	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7
+	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 || MGEODEGX1 || MGEODE_LX
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || MATOM || MGEODE_LX || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
-	default "5" if X86_32 && X86_CMPXCHG64
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MK7)
+	default "5" if X86_32 && X86_CX8
 	default "4"
 
 config X86_DEBUGCTLMSR
@@ -401,6 +358,10 @@ menuconfig PROCESSOR_SELECT
 	  This lets you choose what x86 vendor support code your kernel
 	  will include.
 
+config BROADCAST_TLB_FLUSH
+	def_bool y
+	depends on CPU_SUP_AMD && 64BIT
+
 config CPU_SUP_INTEL
 	default y
 	bool "Support Intel processors" if PROCESSOR_SELECT
diff --git a/arch/x86/Kconfig.cpufeatures b/arch/x86/Kconfig.cpufeatures
new file mode 100644
index 000000000000..250c10627ab3
--- /dev/null
+++ b/arch/x86/Kconfig.cpufeatures
@@ -0,0 +1,197 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# x86 feature bits (see arch/x86/include/asm/cpufeatures.h) that are
+# either REQUIRED to be enabled, or DISABLED (always ignored) for this
+# particular compile-time configuration.  The tests for these features
+# are turned into compile-time constants via the generated
+# <asm/cpufeaturemasks.h>.
+#
+# The naming of these variables *must* match asm/cpufeatures.h, e.g.,
+#     X86_FEATURE_ALWAYS <==> X86_REQUIRED_FEATURE_ALWAYS
+#     X86_FEATURE_FRED   <==> X86_DISABLED_FEATURE_FRED
+#
+# And these REQUIRED and DISABLED config options are manipulated in an
+# AWK script as the following example:
+#
+#                          +----------------------+
+#                          |    X86_FRED = y ?    |
+#                          +----------------------+
+#                              /             \
+#                           Y /               \ N
+#  +-------------------------------------+   +-------------------------------+
+#  | X86_DISABLED_FEATURE_FRED undefined |   | X86_DISABLED_FEATURE_FRED = y |
+#  +-------------------------------------+   +-------------------------------+
+#                                                        |
+#                                                        |
+#     +-------------------------------------------+      |
+#     | X86_FEATURE_FRED: feature word 12, bit 17 | ---->|
+#     +-------------------------------------------+      |
+#                                                        |
+#                                                        |
+#                                     +-------------------------------+
+#                                     | set bit 17 of DISABLED_MASK12 |
+#                                     +-------------------------------+
+#
+
+config X86_REQUIRED_FEATURE_ALWAYS
+	def_bool y
+
+config X86_REQUIRED_FEATURE_NOPL
+	def_bool y
+	depends on X86_64 || X86_P6_NOP
+
+config X86_REQUIRED_FEATURE_CX8
+	def_bool y
+	depends on X86_CX8
+
+# this should be set for all -march=.. options where the compiler
+# generates cmov.
+config X86_REQUIRED_FEATURE_CMOV
+	def_bool y
+	depends on X86_CMOV
+
+# this should be set for all -march= options where the compiler
+# generates movbe.
+config X86_REQUIRED_FEATURE_MOVBE
+	def_bool y
+	depends on MATOM
+
+config X86_REQUIRED_FEATURE_CPUID
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_UP
+	def_bool y
+	depends on !SMP
+
+config X86_REQUIRED_FEATURE_FPU
+	def_bool y
+	depends on !MATH_EMULATION
+
+config X86_REQUIRED_FEATURE_PAE
+	def_bool y
+	depends on X86_64 || X86_PAE
+
+config X86_REQUIRED_FEATURE_PSE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_PGE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_MSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_FXSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM2
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_LM
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_UMIP
+	def_bool y
+	depends on !X86_UMIP
+
+config X86_DISABLED_FEATURE_VME
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_K6_MTRR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CYRIX_ARR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CENTAUR_MCR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_PCID
+	def_bool y
+	depends on !X86_64
+
+config X86_DISABLED_FEATURE_PKU
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_OSPKE
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_PTI
+	def_bool y
+	depends on !MITIGATION_PAGE_TABLE_ISOLATION
+
+config X86_DISABLED_FEATURE_RETPOLINE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETPOLINE_LFENCE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETHUNK
+	def_bool y
+	depends on !MITIGATION_RETHUNK
+
+config X86_DISABLED_FEATURE_UNRET
+	def_bool y
+	depends on !MITIGATION_UNRET_ENTRY
+
+config X86_DISABLED_FEATURE_CALL_DEPTH
+	def_bool y
+	depends on !MITIGATION_CALL_DEPTH_TRACKING
+
+config X86_DISABLED_FEATURE_LAM
+	def_bool y
+	depends on !ADDRESS_MASKING
+
+config X86_DISABLED_FEATURE_ENQCMD
+	def_bool y
+	depends on !INTEL_IOMMU_SVM
+
+config X86_DISABLED_FEATURE_SGX
+	def_bool y
+	depends on !X86_SGX
+
+config X86_DISABLED_FEATURE_XENPV
+	def_bool y
+	depends on !XEN_PV
+
+config X86_DISABLED_FEATURE_TDX_GUEST
+	def_bool y
+	depends on !INTEL_TDX_GUEST
+
+config X86_DISABLED_FEATURE_USER_SHSTK
+	def_bool y
+	depends on !X86_USER_SHADOW_STACK
+
+config X86_DISABLED_FEATURE_IBT
+	def_bool y
+	depends on !X86_KERNEL_IBT
+
+config X86_DISABLED_FEATURE_FRED
+	def_bool y
+	depends on !X86_FRED
+
+config X86_DISABLED_FEATURE_SEV_SNP
+	def_bool y
+	depends on !KVM_AMD_SEV
+
+config X86_DISABLED_FEATURE_INVLPGB
+	def_bool y
+	depends on !BROADCAST_TLB_FLUSH
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 1eb4d23cdaae..c95c3aaadf97 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -59,7 +59,7 @@ config EARLY_PRINTK_USB_XDBC
 config EFI_PGT_DUMP
 	bool "Dump the EFI pagetable"
 	depends on EFI
-	select PTDUMP_CORE
+	select PTDUMP
 	help
 	  Enable this if you want to dump the EFI page table before
 	  enabling virtual mode. This can be used to debug miscellaneous
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b773b34768d..1913d342969b 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -137,17 +137,12 @@ ifeq ($(CONFIG_X86_32),y)
         include $(srctree)/arch/x86/Makefile_32.cpu
         KBUILD_CFLAGS += $(cflags-y)
 
-        # temporary until string.h is fixed
+    ifneq ($(call clang-min-version, 160000),y)
+        # https://github.com/llvm/llvm-project/issues/53645
         KBUILD_CFLAGS += -ffreestanding
-
-    ifeq ($(CONFIG_STACKPROTECTOR),y)
-        ifeq ($(CONFIG_SMP),y)
-            KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \
-                             -mstack-protector-guard-symbol=__ref_stack_chk_guard
-        else
-            KBUILD_CFLAGS += -mstack-protector-guard=global
-        endif
     endif
+
+        percpu_seg := fs
 else
         BITS := 64
         UTS_MACHINE := x86_64
@@ -178,25 +173,29 @@ else
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
-        # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
-        cflags-$(CONFIG_MK8)		+= -march=k8
-        cflags-$(CONFIG_MPSC)		+= -march=nocona
-        cflags-$(CONFIG_MCORE2)		+= -march=core2
-        cflags-$(CONFIG_MATOM)		+= -march=atom
-        cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
-        KBUILD_CFLAGS += $(cflags-y)
-
-        rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
-        rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
-        rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
-        rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
-        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ztune-cpu=generic
-        KBUILD_RUSTFLAGS += $(rustflags-y)
+ifdef CONFIG_X86_NATIVE_CPU
+        KBUILD_CFLAGS += -march=native
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=native
+else
+        KBUILD_CFLAGS += -march=x86-64 -mtune=generic
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
+endif
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
         KBUILD_RUSTFLAGS += -Cno-redzone=y
         KBUILD_RUSTFLAGS += -Ccode-model=kernel
+
+        percpu_seg := gs
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR),y)
+    ifeq ($(CONFIG_SMP),y)
+	KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
+	KBUILD_CFLAGS += -mstack-protector-guard-symbol=__ref_stack_chk_guard
+    else
+	KBUILD_CFLAGS += -mstack-protector-guard=global
+    endif
 endif
 
 #
@@ -251,12 +250,6 @@ endif
 
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
-ifdef CONFIG_X86_NEED_RELOCS
-LDFLAGS_vmlinux := --emit-relocs --discard-none
-else
-LDFLAGS_vmlinux :=
-endif
-
 #
 # The 64-bit kernel must be aligned to 2MB.  Pass -z max-page-size=0x200000 to
 # the linker to force 2MB page size regardless of the default page size used
@@ -277,8 +270,23 @@ archheaders:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
 ###
+# <asm/cpufeaturemasks.h> header generation
+
+cpufeaturemasks.hdr := arch/x86/include/generated/asm/cpufeaturemasks.h
+cpufeaturemasks.awk := $(srctree)/arch/x86/tools/cpufeaturemasks.awk
+cpufeatures_hdr := $(srctree)/arch/x86/include/asm/cpufeatures.h
+targets += $(cpufeaturemasks.hdr)
+      filechk_gen_featuremasks = $(AWK) -f $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG)
+
+$(cpufeaturemasks.hdr): $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG) FORCE
+	$(shell mkdir -p $(dir $@))
+	$(call filechk,gen_featuremasks)
+archprepare: $(cpufeaturemasks.hdr)
+
+###
 # Kernel objects
 
+core-y  += arch/x86/boot/startup/
 libs-y  += arch/x86/lib/
 
 # drivers-y are linked after core-y
diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink
deleted file mode 100644
index 8b8a68162c94..000000000000
--- a/arch/x86/Makefile.postlink
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# ===========================================================================
-# Post-link x86 pass
-# ===========================================================================
-#
-# 1. Separate relocations from vmlinux into vmlinux.relocs.
-# 2. Strip relocations from vmlinux.
-
-PHONY := __archpost
-__archpost:
-
--include include/config/auto.conf
-include $(srctree)/scripts/Kbuild.include
-include $(srctree)/scripts/Makefile.lib
-
-CMD_RELOCS = arch/x86/tools/relocs
-OUT_RELOCS = arch/x86/boot/compressed
-quiet_cmd_relocs = RELOCS  $(OUT_RELOCS)/$@.relocs
-      cmd_relocs = \
-	mkdir -p $(OUT_RELOCS); \
-	$(CMD_RELOCS) $@ > $(OUT_RELOCS)/$@.relocs; \
-	$(CMD_RELOCS) --abs-relocs $@
-
-# `@true` prevents complaint when there is nothing to be done
-
-vmlinux: FORCE
-	@true
-ifeq ($(CONFIG_X86_NEED_RELOCS),y)
-	$(call cmd,relocs)
-	$(call cmd,strip_relocs)
-endif
-
-clean:
-	@rm -f $(OUT_RELOCS)/vmlinux.relocs
-
-PHONY += FORCE clean
-
-FORCE:
-
-.PHONY: $(PHONY)
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index a46b1397ad01..c86cbd9cbba3 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -7,12 +7,13 @@ core-y += arch/x86/crypto/
 # GCC versions < 11. See:
 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99652
 #
-ifeq ($(CONFIG_CC_IS_CLANG),y)
-KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
-KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
+ifeq ($(call gcc-min-version, 110000)$(CONFIG_CC_IS_CLANG),y)
+KBUILD_CFLAGS +=  -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
 KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
 endif
 
+KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
+
 ifeq ($(CONFIG_X86_32),y)
 START := 0x8048000
 
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 94834c4b5e5e..af7de9a42752 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -24,7 +24,6 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # Please note, that patches that add -march=athlon-xp and friends are pointless.
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
-cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
 cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
 cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,9 +31,7 @@ cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
-cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
-cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
-	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
+cflags-$(CONFIG_MATOM)		+= -march=atom
 
 # AMD Elan support
 cflags-$(CONFIG_MELAN)		+= -march=i486
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index 1189be057ebd..070ef534c915 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -12,3 +12,4 @@ fdimage
 mtools.conf
 image.iso
 hdimage
+tools/
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 9cc0ff6e9067..640fcac3af74 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -35,7 +35,6 @@ setup-y		+= video-vesa.o
 setup-y		+= video-bios.o
 
 targets		+= $(setup-y)
-hostprogs	:= tools/build
 hostprogs	+= mkcpustr
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
@@ -54,18 +53,15 @@ targets += cpustr.h
 
 KBUILD_CFLAGS	:= $(REALMODE_CFLAGS) -D_SETUP
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
-KBUILD_CFLAGS	+= $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
 
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-silent_redirect_image = >/dev/null
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
-			       $(obj)/zoffset.h $@ $($(quiet)redirect_image)
+      cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
 
-$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
+$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
 	$(call if_changed,image)
 	@$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index aa9b96457584..cf4a6155714e 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -32,7 +32,7 @@ intcall:
 	movw	%dx, %si
 	movw	%sp, %di
 	movw	$11, %cx
-	rep; movsl
+	rep movsl
 
 	/* Pop full state from the stack */
 	popal
@@ -67,7 +67,7 @@ intcall:
 	jz	4f
 	movw	%sp, %si
 	movw	$11, %cx
-	rep; movsl
+	rep movsl
 4:	addw	$44, %sp
 
 	/* Restore state and return */
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0f24f7ebec9b..60580836daf7 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -16,7 +16,7 @@
 
 #define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stdarg.h>
 #include <linux/types.h>
@@ -34,7 +34,7 @@
 extern struct setup_header hdr;
 extern struct boot_params boot_params;
 
-#define cpu_relax()	asm volatile("rep; nop")
+#define cpu_relax()	asm volatile("pause")
 
 static inline void io_delay(void)
 {
@@ -155,14 +155,14 @@ static inline void wrgs32(u32 v, addr_t addr)
 static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("fs; repe; cmpsb" CC_SET(nz)
+	asm volatile("fs repe cmpsb" CC_SET(nz)
 		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("gs; repe; cmpsb" CC_SET(nz)
+	asm volatile("gs repe cmpsb" CC_SET(nz)
 		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
@@ -327,6 +327,6 @@ void probe_cards(int unsafe);
 /* video-vesa.c */
 void vesa_store_edid(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* BOOT_BOOT_H */
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 606c74f27459..f4f7b22d8113 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -38,17 +38,16 @@ KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
 KBUILD_CFLAGS += -Wno-pointer-sign
-KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 # Disable relocation relaxation in case the link is not PIE.
 KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
-# sev.c indirectly includes inat-table.h which is generated during
+# sev-decode-insn.c indirectly includes inat-table.c which is generated during
 # compilation and stored in $(objtree). Add the directory to the includes so
 # that the compiler finds it even with out-of-tree builds (make O=/some/path).
-CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
+CFLAGS_sev-handle-vc.o += -I$(objtree)/arch/x86/lib/
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 
@@ -74,7 +73,7 @@ LDFLAGS_vmlinux += -T
 hostprogs	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDGRSTtVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
 
 quiet_cmd_voffset = VOFFSET $@
       cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -97,7 +96,7 @@ ifdef CONFIG_X86_64
 	vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
 	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o
 	vmlinux-objs-y += $(obj)/pgtable_64.o
-	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o
+	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o $(obj)/sev-handle-vc.o
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
@@ -105,8 +104,8 @@ vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o $(obj)/td
 vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o
 
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
-vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o
 vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-libs-$(CONFIG_X86_64)	+= $(objtree)/arch/x86/boot/startup/lib.a
 
 $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
 	$(call if_changed,ld)
@@ -117,9 +116,12 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 
 targets += $(patsubst $(obj)/%,%,$(vmlinux-objs-y)) vmlinux.bin.all vmlinux.relocs
 
-# vmlinux.relocs is created by the vmlinux postlink step.
-$(obj)/vmlinux.relocs: vmlinux
-	@true
+CMD_RELOCS = arch/x86/tools/relocs
+quiet_cmd_relocs = RELOCS  $@
+      cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $<
+
+$(obj)/vmlinux.relocs: vmlinux.unstripped FORCE
+	$(call if_changed,relocs)
 
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
 vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S
deleted file mode 100644
index 876fc6d46a13..000000000000
--- a/arch/x86/boot/compressed/efi_mixed.S
+++ /dev/null
@@ -1,341 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
- *
- * Early support for invoking 32-bit EFI services from a 64-bit kernel.
- *
- * Because this thunking occurs before ExitBootServices() we have to
- * restore the firmware's 32-bit GDT and IDT before we make EFI service
- * calls.
- *
- * On the plus side, we don't have to worry about mangling 64-bit
- * addresses into 32-bits because we're executing with an identity
- * mapped pagetable and haven't transitioned to 64-bit virtual addresses
- * yet.
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/msr.h>
-#include <asm/page_types.h>
-#include <asm/processor-flags.h>
-#include <asm/segment.h>
-#include <asm/setup.h>
-
-	.code64
-	.text
-/*
- * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode()
- * is the first thing that runs after switching to long mode. Depending on
- * whether the EFI handover protocol or the compat entry point was used to
- * enter the kernel, it will either branch to the common 64-bit EFI stub
- * entrypoint efi_stub_entry() directly, or via the 64-bit EFI PE/COFF
- * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a
- * struct bootparams pointer as the third argument, so the presence of such a
- * pointer is used to disambiguate.
- *
- *                                                             +--------------+
- *  +------------------+     +------------+            +------>| efi_pe_entry |
- *  | efi32_pe_entry   |---->|            |            |       +-----------+--+
- *  +------------------+     |            |     +------+----------------+  |
- *                           | startup_32 |---->| startup_64_mixed_mode |  |
- *  +------------------+     |            |     +------+----------------+  |
- *  | efi32_stub_entry |---->|            |            |                   |
- *  +------------------+     +------------+            |                   |
- *                                                     V                   |
- *                           +------------+     +----------------+         |
- *                           | startup_64 |<----| efi_stub_entry |<--------+
- *                           +------------+     +----------------+
- */
-SYM_FUNC_START(startup_64_mixed_mode)
-	lea	efi32_boot_args(%rip), %rdx
-	mov	0(%rdx), %edi
-	mov	4(%rdx), %esi
-
-	/* Switch to the firmware's stack */
-	movl	efi32_boot_sp(%rip), %esp
-	andl	$~7, %esp
-
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-	mov	8(%rdx), %edx		// saved bootparams pointer
-	test	%edx, %edx
-	jnz	efi_stub_entry
-#endif
-	/*
-	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
-	 * shadow space on the stack even if all arguments are passed in
-	 * registers. We also need an additional 8 bytes for the space that
-	 * would be occupied by the return address, and this also results in
-	 * the correct stack alignment for entry.
-	 */
-	sub	$40, %rsp
-	mov	%rdi, %rcx		// MS calling convention
-	mov	%rsi, %rdx
-	jmp	efi_pe_entry
-SYM_FUNC_END(startup_64_mixed_mode)
-
-SYM_FUNC_START(__efi64_thunk)
-	push	%rbp
-	push	%rbx
-
-	movl	%ds, %eax
-	push	%rax
-	movl	%es, %eax
-	push	%rax
-	movl	%ss, %eax
-	push	%rax
-
-	/* Copy args passed on stack */
-	movq	0x30(%rsp), %rbp
-	movq	0x38(%rsp), %rbx
-	movq	0x40(%rsp), %rax
-
-	/*
-	 * Convert x86-64 ABI params to i386 ABI
-	 */
-	subq	$64, %rsp
-	movl	%esi, 0x0(%rsp)
-	movl	%edx, 0x4(%rsp)
-	movl	%ecx, 0x8(%rsp)
-	movl	%r8d, 0xc(%rsp)
-	movl	%r9d, 0x10(%rsp)
-	movl	%ebp, 0x14(%rsp)
-	movl	%ebx, 0x18(%rsp)
-	movl	%eax, 0x1c(%rsp)
-
-	leaq	0x20(%rsp), %rbx
-	sgdt	(%rbx)
-	sidt	16(%rbx)
-
-	leaq	1f(%rip), %rbp
-
-	/*
-	 * Switch to IDT and GDT with 32-bit segments. These are the firmware
-	 * GDT and IDT that were installed when the kernel started executing.
-	 * The pointers were saved by the efi32_entry() routine below.
-	 *
-	 * Pass the saved DS selector to the 32-bit code, and use far return to
-	 * restore the saved CS selector.
-	 */
-	lidt	efi32_boot_idt(%rip)
-	lgdt	efi32_boot_gdt(%rip)
-
-	movzwl	efi32_boot_ds(%rip), %edx
-	movzwq	efi32_boot_cs(%rip), %rax
-	pushq	%rax
-	leaq	efi_enter32(%rip), %rax
-	pushq	%rax
-	lretq
-
-1:	addq	$64, %rsp
-	movq	%rdi, %rax
-
-	pop	%rbx
-	movl	%ebx, %ss
-	pop	%rbx
-	movl	%ebx, %es
-	pop	%rbx
-	movl	%ebx, %ds
-	/* Clear out 32-bit selector from FS and GS */
-	xorl	%ebx, %ebx
-	movl	%ebx, %fs
-	movl	%ebx, %gs
-
-	pop	%rbx
-	pop	%rbp
-	RET
-SYM_FUNC_END(__efi64_thunk)
-
-	.code32
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-SYM_FUNC_START(efi32_stub_entry)
-	call	1f
-1:	popl	%ecx
-	leal	(efi32_boot_args - 1b)(%ecx), %ebx
-
-	/* Clear BSS */
-	xorl	%eax, %eax
-	leal	(_bss - 1b)(%ecx), %edi
-	leal	(_ebss - 1b)(%ecx), %ecx
-	subl	%edi, %ecx
-	shrl	$2, %ecx
-	cld
-	rep	stosl
-
-	add	$0x4, %esp		/* Discard return address */
-	popl	%ecx
-	popl	%edx
-	popl	%esi
-	movl	%esi, 8(%ebx)
-	jmp	efi32_entry
-SYM_FUNC_END(efi32_stub_entry)
-#endif
-
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-SYM_FUNC_START_LOCAL(efi_enter32)
-	/* Load firmware selector into data and stack segment registers */
-	movl	%edx, %ds
-	movl	%edx, %es
-	movl	%edx, %fs
-	movl	%edx, %gs
-	movl	%edx, %ss
-
-	/* Reload pgtables */
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	/* Disable paging */
-	movl	%cr0, %eax
-	btrl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	/* Disable long mode via EFER */
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btrl	$_EFER_LME, %eax
-	wrmsr
-
-	call	*%edi
-
-	/* We must preserve return value */
-	movl	%eax, %edi
-
-	/*
-	 * Some firmware will return with interrupts enabled. Be sure to
-	 * disable them before we switch GDTs and IDTs.
-	 */
-	cli
-
-	lidtl	16(%ebx)
-	lgdtl	(%ebx)
-
-	movl	%cr4, %eax
-	btsl	$(X86_CR4_PAE_BIT), %eax
-	movl	%eax, %cr4
-
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btsl	$_EFER_LME, %eax
-	wrmsr
-
-	xorl	%eax, %eax
-	lldt	%ax
-
-	pushl	$__KERNEL_CS
-	pushl	%ebp
-
-	/* Enable paging */
-	movl	%cr0, %eax
-	btsl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-	lret
-SYM_FUNC_END(efi_enter32)
-
-/*
- * This is the common EFI stub entry point for mixed mode.
- *
- * Arguments:	%ecx	image handle
- * 		%edx	EFI system table pointer
- *
- * Since this is the point of no return for ordinary execution, no registers
- * are considered live except for the function parameters. [Note that the EFI
- * stub may still exit and return to the firmware using the Exit() EFI boot
- * service.]
- */
-SYM_FUNC_START_LOCAL(efi32_entry)
-	call	1f
-1:	pop	%ebx
-
-	/* Save firmware GDTR and code/data selectors */
-	sgdtl	(efi32_boot_gdt - 1b)(%ebx)
-	movw	%cs, (efi32_boot_cs - 1b)(%ebx)
-	movw	%ds, (efi32_boot_ds - 1b)(%ebx)
-
-	/* Store firmware IDT descriptor */
-	sidtl	(efi32_boot_idt - 1b)(%ebx)
-
-	/* Store firmware stack pointer */
-	movl	%esp, (efi32_boot_sp - 1b)(%ebx)
-
-	/* Store boot arguments */
-	leal	(efi32_boot_args - 1b)(%ebx), %ebx
-	movl	%ecx, 0(%ebx)
-	movl	%edx, 4(%ebx)
-	movb	$0x0, 12(%ebx)          // efi_is64
-
-	/*
-	 * Allocate some memory for a temporary struct boot_params, which only
-	 * needs the minimal pieces that startup_32() relies on.
-	 */
-	subl	$PARAM_SIZE, %esp
-	movl	%esp, %esi
-	movl	$PAGE_SIZE, BP_kernel_alignment(%esi)
-	movl	$_end - 1b, BP_init_size(%esi)
-	subl	$startup_32 - 1b, BP_init_size(%esi)
-
-	/* Disable paging */
-	movl	%cr0, %eax
-	btrl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	jmp	startup_32
-SYM_FUNC_END(efi32_entry)
-
-/*
- * efi_status_t efi32_pe_entry(efi_handle_t image_handle,
- *			       efi_system_table_32_t *sys_table)
- */
-SYM_FUNC_START(efi32_pe_entry)
-	pushl	%ebp
-	movl	%esp, %ebp
-	pushl	%ebx				// save callee-save registers
-	pushl	%edi
-
-	call	verify_cpu			// check for long mode support
-	testl	%eax, %eax
-	movl	$0x80000003, %eax		// EFI_UNSUPPORTED
-	jnz	2f
-
-	movl	8(%ebp), %ecx			// image_handle
-	movl	12(%ebp), %edx			// sys_table
-	jmp	efi32_entry			// pass %ecx, %edx
-						// no other registers remain live
-
-2:	popl	%edi				// restore callee-save registers
-	popl	%ebx
-	leave
-	RET
-SYM_FUNC_END(efi32_pe_entry)
-
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-	.org	efi32_stub_entry + 0x200
-	.code64
-SYM_FUNC_START_NOALIGN(efi64_stub_entry)
-	jmp	efi_handover_entry
-SYM_FUNC_END(efi64_stub_entry)
-#endif
-
-	.data
-	.balign	8
-SYM_DATA_START_LOCAL(efi32_boot_gdt)
-	.word	0
-	.quad	0
-SYM_DATA_END(efi32_boot_gdt)
-
-SYM_DATA_START_LOCAL(efi32_boot_idt)
-	.word	0
-	.quad	0
-SYM_DATA_END(efi32_boot_idt)
-
-SYM_DATA_LOCAL(efi32_boot_cs, .word 0)
-SYM_DATA_LOCAL(efi32_boot_ds, .word 0)
-SYM_DATA_LOCAL(efi32_boot_sp, .long 0)
-SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0)
-SYM_DATA(efi_is64, .byte 1)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 1dcb794c5479..d9dab940ff62 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -35,7 +35,6 @@
 #include <asm/bootparam.h>
 #include <asm/desc_defs.h>
 #include <asm/trapnr.h>
-#include "pgtable.h"
 
 /*
  * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result
@@ -263,13 +262,6 @@ SYM_FUNC_START(startup_32)
 	 * used to perform that far jump.
 	 */
 	leal	rva(startup_64)(%ebp), %eax
-#ifdef CONFIG_EFI_MIXED
-	cmpb	$1, rva(efi_is64)(%ebp)
-	je	1f
-	leal	rva(startup_64_mixed_mode)(%ebp), %eax
-1:
-#endif
-
 	pushl	$__KERNEL_CS
 	pushl	%eax
 
@@ -483,110 +475,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
-/*
- * This is the 32-bit trampoline that will be copied over to low memory. It
- * will be called using the ordinary 64-bit calling convention from code
- * running in 64-bit mode.
- *
- * Return address is at the top of the stack (might be above 4G).
- * The first argument (EDI) contains the address of the temporary PGD level
- * page table in 32-bit addressable memory which will be programmed into
- * register CR3.
- */
-	.section ".rodata", "a", @progbits
-SYM_CODE_START(trampoline_32bit_src)
-	/*
-	 * Preserve callee save 64-bit registers on the stack: this is
-	 * necessary because the architecture does not guarantee that GPRs will
-	 * retain their full 64-bit values across a 32-bit mode switch.
-	 */
-	pushq	%r15
-	pushq	%r14
-	pushq	%r13
-	pushq	%r12
-	pushq	%rbp
-	pushq	%rbx
-
-	/* Preserve top half of RSP in a legacy mode GPR to avoid truncation */
-	movq	%rsp, %rbx
-	shrq	$32, %rbx
-
-	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
-	pushq	$__KERNEL32_CS
-	leaq	0f(%rip), %rax
-	pushq	%rax
-	lretq
-
-	/*
-	 * The 32-bit code below will do a far jump back to long mode and end
-	 * up here after reconfiguring the number of paging levels. First, the
-	 * stack pointer needs to be restored to its full 64-bit value before
-	 * the callee save register contents can be popped from the stack.
-	 */
-.Lret:
-	shlq	$32, %rbx
-	orq	%rbx, %rsp
-
-	/* Restore the preserved 64-bit registers */
-	popq	%rbx
-	popq	%rbp
-	popq	%r12
-	popq	%r13
-	popq	%r14
-	popq	%r15
-	retq
-
 	.code32
-0:
-	/* Disable paging */
-	movl	%cr0, %eax
-	btrl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	/* Point CR3 to the trampoline's new top level page table */
-	movl	%edi, %cr3
-
-	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btsl	$_EFER_LME, %eax
-	/* Avoid writing EFER if no change was made (for TDX guest) */
-	jc	1f
-	wrmsr
-1:
-	/* Toggle CR4.LA57 */
-	movl	%cr4, %eax
-	btcl	$X86_CR4_LA57_BIT, %eax
-	movl	%eax, %cr4
-
-	/* Enable paging again. */
-	movl	%cr0, %eax
-	btsl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	/*
-	 * Return to the 64-bit calling code using LJMP rather than LRET, to
-	 * avoid the need for a 32-bit addressable stack. The destination
-	 * address will be adjusted after the template code is copied into a
-	 * 32-bit addressable buffer.
-	 */
-.Ljmp:	ljmpl	$__KERNEL_CS, $(.Lret - trampoline_32bit_src)
-SYM_CODE_END(trampoline_32bit_src)
-
-/*
- * This symbol is placed right after trampoline_32bit_src() so its address can
- * be used to infer the size of the trampoline code.
- */
-SYM_DATA(trampoline_ljmp_imm_offset, .word  .Ljmp + 1 - trampoline_32bit_src)
-
-	/*
-         * The trampoline code has a size limit.
-         * Make sure we fail to compile if the trampoline code grows
-         * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes.
-	 */
-	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
-
-	.text
 SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode)
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index dbba332e4a12..0e9f84ab4bdc 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -38,7 +38,7 @@ void arch_accept_memory(phys_addr_t start, phys_addr_t end)
 	if (early_is_tdx_guest()) {
 		if (!tdx_accept_memory(start, end))
 			panic("TDX: Failed to accept memory\n");
-	} else if (sev_snp_enabled()) {
+	} else if (early_is_sevsnp_guest()) {
 		snp_accept_memory(start, end);
 	} else {
 		error("Cannot accept memory: unknown platform\n");
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0d37420cad02..94b5991da001 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -14,7 +14,6 @@
 
 #include "misc.h"
 #include "error.h"
-#include "pgtable.h"
 #include "../string.h"
 #include "../voffset.h"
 #include <asm/bootparam_utils.h>
@@ -235,7 +234,7 @@ static void handle_relocations(void *output, unsigned long output_len,
 
 	/*
 	 * Process relocations: 32 bit relocations first then 64 bit after.
-	 * Three sets of binary relocations are added to the end of the kernel
+	 * Two sets of binary relocations are added to the end of the kernel
 	 * before compression. Each relocation table entry is the kernel
 	 * address of the location which needs to be updated stored as a
 	 * 32-bit value which is sign extended to 64 bits.
@@ -245,8 +244,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 	 * kernel bits...
 	 * 0 - zero terminator for 64 bit relocations
 	 * 64 bit relocation repeated
-	 * 0 - zero terminator for inverse 32 bit relocations
-	 * 32 bit inverse relocation repeated
 	 * 0 - zero terminator for 32 bit relocations
 	 * 32 bit relocation repeated
 	 *
@@ -263,16 +260,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 		*(uint32_t *)ptr += delta;
 	}
 #ifdef CONFIG_X86_64
-	while (*--reloc) {
-		long extended = *reloc;
-		extended += map;
-
-		ptr = (unsigned long)extended;
-		if (ptr < min_addr || ptr > max_addr)
-			error("inverse 32-bit relocation outside of kernel!\n");
-
-		*(int32_t *)ptr -= delta;
-	}
 	for (reloc--; *reloc; reloc--) {
 		long extended = *reloc;
 		extended += map;
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index dd8d1a85f671..db1048621ea2 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -136,6 +136,9 @@ static inline void console_init(void)
 #endif
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
+struct es_em_ctxt;
+struct insn;
+
 void sev_enable(struct boot_params *bp);
 void snp_check_features(void);
 void sev_es_shutdown_ghcb(void);
@@ -143,6 +146,11 @@ extern bool sev_es_check_ghcb_fault(unsigned long address);
 void snp_set_page_private(unsigned long paddr);
 void snp_set_page_shared(unsigned long paddr);
 void sev_prep_identity_maps(unsigned long top_level_pgt);
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt);
+bool insn_has_rep_prefix(struct insn *insn);
+void sev_insn_decode_init(void);
+bool early_setup_ghcb(void);
 #else
 static inline void sev_enable(struct boot_params *bp)
 {
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
deleted file mode 100644
index 6d595abe06b3..000000000000
--- a/arch/x86/boot/compressed/pgtable.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef BOOT_COMPRESSED_PAGETABLE_H
-#define BOOT_COMPRESSED_PAGETABLE_H
-
-#define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
-
-#define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
-
-#ifndef __ASSEMBLER__
-
-extern unsigned long *trampoline_32bit;
-
-extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
-
-extern const u16 trampoline_ljmp_imm_offset;
-
-#endif /* __ASSEMBLER__ */
-#endif /* BOOT_COMPRESSED_PAGETABLE_H */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index c882e1f67af0..bdd26050dff7 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,21 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 #include <asm/bootparam.h>
+#include <asm/bootparam_utils.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
-#include "pgtable.h"
 #include "../string.h"
 #include "efi.h"
 
 #define BIOS_START_MIN		0x20000U	/* 128K, less than this is insane */
 #define BIOS_START_MAX		0x9f000U	/* 640K, absolute maximum */
 
-#ifdef CONFIG_X86_5LEVEL
 /* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */
 unsigned int __section(".data") __pgtable_l5_enabled;
 unsigned int __section(".data") pgdir_shift = 39;
 unsigned int __section(".data") ptrs_per_p4d = 1;
-#endif
 
 /* Buffer to preserve trampoline memory */
 static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
@@ -107,24 +105,20 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	sanitize_boot_params(bp);
 	boot_params_ptr = bp;
 
 	/*
 	 * Check if LA57 is desired and supported.
 	 *
 	 * There are several parts to the check:
-	 *   - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
 	 *   - if user asked to disable 5-level paging: no5lvl in cmdline
 	 *   - if the machine supports 5-level paging:
 	 *     + CPUID leaf 7 is supported
 	 *     + the leaf has the feature bit set
-	 *
-	 * That's substitute for boot_cpu_has() in early boot code.
 	 */
-	if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
-			!cmdline_find_option_bool("no5lvl") &&
-			native_cpuid_eax(0) >= 7 &&
-			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
+	if (!cmdline_find_option_bool("no5lvl") &&
+	    native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & BIT(16))) {
 		l5_required = true;
 
 		/* Initialize variables for 5-level paging */
diff --git a/arch/x86/boot/compressed/sev-handle-vc.c b/arch/x86/boot/compressed/sev-handle-vc.c
new file mode 100644
index 000000000000..89dd02de2a0f
--- /dev/null
+++ b/arch/x86/boot/compressed/sev-handle-vc.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "misc.h"
+#include "sev.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/insn.h>
+#include <asm/pgtable_types.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+#include <asm/trap_pf.h>
+#include <asm/fpu/xcr.h>
+
+#define __BOOT_COMPRESSED
+
+/* Basic instruction decoding support needed */
+#include "../../lib/inat.c"
+#include "../../lib/insn.c"
+
+/*
+ * Copy a version of this function here - insn-eval.c can't be used in
+ * pre-decompression code.
+ */
+bool insn_has_rep_prefix(struct insn *insn)
+{
+	insn_byte_t p;
+	int i;
+
+	insn_get_prefixes(insn);
+
+	for_each_insn_prefix(insn, i, p) {
+		if (p == 0xf2 || p == 0xf3)
+			return true;
+	}
+
+	return false;
+}
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int ret;
+
+	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
+
+	return ES_OK;
+}
+
+extern void sev_insn_decode_init(void) __alias(inat_init_tables);
+
+/*
+ * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
+ * doesn't use segments.
+ */
+static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+	return 0UL;
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+				   void *dst, char *buf, size_t size)
+{
+	memcpy(dst, buf, size);
+
+	return ES_OK;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+				  void *src, char *buf, size_t size)
+{
+	memcpy(buf, src, size);
+
+	return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+	return false;
+}
+
+#define sev_printk(fmt, ...)
+
+#include "../../coco/sev/vc-shared.c"
+
+void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
+{
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+
+	if (!boot_ghcb && !early_setup_ghcb())
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+	vc_ghcb_invalidate(boot_ghcb);
+	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+	if (result != ES_OK)
+		goto finish;
+
+	result = vc_check_opcode_bytes(&ctxt, exit_code);
+	if (result != ES_OK)
+		goto finish;
+
+	switch (exit_code) {
+	case SVM_EXIT_RDTSC:
+	case SVM_EXIT_RDTSCP:
+		result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
+		break;
+	case SVM_EXIT_IOIO:
+		result = vc_handle_ioio(boot_ghcb, &ctxt);
+		break;
+	case SVM_EXIT_CPUID:
+		result = vc_handle_cpuid(boot_ghcb, &ctxt);
+		break;
+	default:
+		result = ES_UNSUPPORTED;
+		break;
+	}
+
+finish:
+	if (result == ES_OK)
+		vc_finish_insn(&ctxt);
+	else if (result != ES_RETRY)
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index bb55934c1cee..fd1b67dfea22 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -21,99 +21,14 @@
 #include <asm/fpu/xcr.h>
 #include <asm/ptrace.h>
 #include <asm/svm.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 
 #include "error.h"
-#include "../msr.h"
+#include "sev.h"
 
 static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
 struct ghcb *boot_ghcb;
 
-/*
- * Copy a version of this function here - insn-eval.c can't be used in
- * pre-decompression code.
- */
-static bool insn_has_rep_prefix(struct insn *insn)
-{
-	insn_byte_t p;
-	int i;
-
-	insn_get_prefixes(insn);
-
-	for_each_insn_prefix(insn, i, p) {
-		if (p == 0xf2 || p == 0xf3)
-			return true;
-	}
-
-	return false;
-}
-
-/*
- * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
- * doesn't use segments.
- */
-static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
-{
-	return 0UL;
-}
-
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
-	struct msr m;
-
-	boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-
-	return m.q;
-}
-
-static inline void sev_es_wr_ghcb_msr(u64 val)
-{
-	struct msr m;
-
-	m.q = val;
-	boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-}
-
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
-{
-	char buffer[MAX_INSN_SIZE];
-	int ret;
-
-	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
-
-	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
-	if (ret < 0)
-		return ES_DECODE_FAILED;
-
-	return ES_OK;
-}
-
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
-				   void *dst, char *buf, size_t size)
-{
-	memcpy(dst, buf, size);
-
-	return ES_OK;
-}
-
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
-				  void *src, char *buf, size_t size)
-{
-	memcpy(buf, src, size);
-
-	return ES_OK;
-}
-
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
-{
-	return ES_OK;
-}
-
-static bool fault_in_kernel_space(unsigned long address)
-{
-	return false;
-}
-
 #undef __init
 #define __init
 
@@ -122,24 +37,27 @@ static bool fault_in_kernel_space(unsigned long address)
 
 #define __BOOT_COMPRESSED
 
-/* Basic instruction decoding support needed */
-#include "../../lib/inat.c"
-#include "../../lib/insn.c"
-
-/* Include code for early handlers */
-#include "../../coco/sev/shared.c"
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
 
-static struct svsm_ca *svsm_get_caa(void)
+struct svsm_ca *svsm_get_caa(void)
 {
 	return boot_svsm_caa;
 }
 
-static u64 svsm_get_caa_pa(void)
+u64 svsm_get_caa_pa(void)
 {
 	return boot_svsm_caa_pa;
 }
 
-static int svsm_perform_call_protocol(struct svsm_call *call)
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+u8 snp_vmpl;
+
+/* Include code for early handlers */
+#include "../../boot/startup/sev-shared.c"
+
+int svsm_perform_call_protocol(struct svsm_call *call)
 {
 	struct ghcb *ghcb;
 	int ret;
@@ -157,17 +75,14 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
 	return ret;
 }
 
-bool sev_snp_enabled(void)
+static bool sev_snp_enabled(void)
 {
 	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
 }
 
 static void __page_state_change(unsigned long paddr, enum psc_op op)
 {
-	u64 val;
-
-	if (!sev_snp_enabled())
-		return;
+	u64 val, msr;
 
 	/*
 	 * If private -> shared then invalidate the page before requesting the
@@ -176,6 +91,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	if (op == SNP_PAGE_STATE_SHARED)
 		pvalidate_4k_page(paddr, paddr, false);
 
+	/* Save the current GHCB MSR value */
+	msr = sev_es_rd_ghcb_msr();
+
 	/* Issue VMGEXIT to change the page state in RMP table. */
 	sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
 	VMGEXIT();
@@ -185,6 +103,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
 
+	/* Restore the GHCB MSR value */
+	sev_es_wr_ghcb_msr(msr);
+
 	/*
 	 * Now that page state is changed in the RMP table, validate it so that it is
 	 * consistent with the RMP entry.
@@ -195,15 +116,21 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 
 void snp_set_page_private(unsigned long paddr)
 {
+	if (!sev_snp_enabled())
+		return;
+
 	__page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
 }
 
 void snp_set_page_shared(unsigned long paddr)
 {
+	if (!sev_snp_enabled())
+		return;
+
 	__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
 }
 
-static bool early_setup_ghcb(void)
+bool early_setup_ghcb(void)
 {
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;
@@ -214,7 +141,7 @@ static bool early_setup_ghcb(void)
 	boot_ghcb = &boot_ghcb_page;
 
 	/* Initialize lookup tables for the instruction decoder */
-	inat_init_tables();
+	sev_insn_decode_init();
 
 	/* SNP guest requires the GHCB GPA must be registered */
 	if (sev_snp_enabled())
@@ -223,56 +150,10 @@ static bool early_setup_ghcb(void)
 	return true;
 }
 
-static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc,
-				       phys_addr_t pa, phys_addr_t pa_end)
-{
-	struct psc_hdr *hdr;
-	struct psc_entry *e;
-	unsigned int i;
-
-	hdr = &desc->hdr;
-	memset(hdr, 0, sizeof(*hdr));
-
-	e = desc->entries;
-
-	i = 0;
-	while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) {
-		hdr->end_entry = i;
-
-		e->gfn = pa >> PAGE_SHIFT;
-		e->operation = SNP_PAGE_STATE_PRIVATE;
-		if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) {
-			e->pagesize = RMP_PG_SIZE_2M;
-			pa += PMD_SIZE;
-		} else {
-			e->pagesize = RMP_PG_SIZE_4K;
-			pa += PAGE_SIZE;
-		}
-
-		e++;
-		i++;
-	}
-
-	if (vmgexit_psc(boot_ghcb, desc))
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
-	pvalidate_pages(desc);
-
-	return pa;
-}
-
 void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 {
-	struct snp_psc_desc desc = {};
-	unsigned int i;
-	phys_addr_t pa;
-
-	if (!boot_ghcb && !early_setup_ghcb())
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
-	pa = start;
-	while (pa < end)
-		pa = __snp_accept_memory(&desc, pa, end);
+	for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE)
+		__page_state_change(pa, SNP_PAGE_STATE_PRIVATE);
 }
 
 void sev_es_shutdown_ghcb(void)
@@ -333,46 +214,6 @@ bool sev_es_check_ghcb_fault(unsigned long address)
 	return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page);
 }
 
-void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
-{
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-
-	if (!boot_ghcb && !early_setup_ghcb())
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
-	vc_ghcb_invalidate(boot_ghcb);
-	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
-	if (result != ES_OK)
-		goto finish;
-
-	result = vc_check_opcode_bytes(&ctxt, exit_code);
-	if (result != ES_OK)
-		goto finish;
-
-	switch (exit_code) {
-	case SVM_EXIT_RDTSC:
-	case SVM_EXIT_RDTSCP:
-		result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
-		break;
-	case SVM_EXIT_IOIO:
-		result = vc_handle_ioio(boot_ghcb, &ctxt);
-		break;
-	case SVM_EXIT_CPUID:
-		result = vc_handle_cpuid(boot_ghcb, &ctxt);
-		break;
-	default:
-		result = ES_UNSUPPORTED;
-		break;
-	}
-
-finish:
-	if (result == ES_OK)
-		vc_finish_insn(&ctxt);
-	else if (result != ES_RETRY)
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
 /*
  * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
  * guest side implementation for proper functioning of the guest. If any
@@ -682,3 +523,43 @@ void sev_prep_identity_maps(unsigned long top_level_pgt)
 
 	sev_verify_cbit(top_level_pgt);
 }
+
+bool early_is_sevsnp_guest(void)
+{
+	static bool sevsnp;
+
+	if (sevsnp)
+		return true;
+
+	if (!(sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED))
+		return false;
+
+	sevsnp = true;
+
+	if (!snp_vmpl) {
+		unsigned int eax, ebx, ecx, edx;
+
+		/*
+		 * CPUID Fn8000_001F_EAX[28] - SVSM support
+		 */
+		eax = 0x8000001f;
+		ecx = 0;
+		native_cpuid(&eax, &ebx, &ecx, &edx);
+		if (eax & BIT(28)) {
+			struct msr m;
+
+			/* Obtain the address of the calling area to use */
+			boot_rdmsr(MSR_SVSM_CAA, &m);
+			boot_svsm_caa = (void *)m.q;
+			boot_svsm_caa_pa = m.q;
+
+			/*
+			 * The real VMPL level cannot be discovered, but the
+			 * memory acceptance routines make no use of that so
+			 * any non-zero value suffices here.
+			 */
+			snp_vmpl = U8_MAX;
+		}
+	}
+	return true;
+}
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index fc725a981b09..92f79c21939c 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -10,13 +10,34 @@
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
-bool sev_snp_enabled(void);
+#include "../msr.h"
+
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+u64 sev_get_status(void);
+bool early_is_sevsnp_guest(void);
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+	struct msr m;
+
+	boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+
+	return m.q;
+}
+
+static inline void sev_es_wr_ghcb_msr(u64 val)
+{
+	struct msr m;
+
+	m.q = val;
+	boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+}
 
 #else
 
-static inline bool sev_snp_enabled(void) { return false; }
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+static inline u64 sev_get_status(void) { return 0; }
+static inline bool early_is_sevsnp_guest(void) { return false; }
 
 #endif
 
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 81fc1eaa3229..9af19d9614cb 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -15,9 +15,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
 {
 	int d0, d1, d2;
 	asm volatile(
-		"rep ; movsl\n\t"
+		"rep movsl\n\t"
 		"movl %4,%%ecx\n\t"
-		"rep ; movsb\n\t"
+		"rep movsb"
 		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
 		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
 		: "memory");
@@ -29,9 +29,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
 {
 	long d0, d1, d2;
 	asm volatile(
-		"rep ; movsq\n\t"
+		"rep movsq\n\t"
 		"movq %4,%%rcx\n\t"
-		"rep ; movsb\n\t"
+		"rep movsb"
 		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
 		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
 		: "memory");
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 083ec6d7722a..3b2bc61c9408 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -48,7 +48,7 @@ SECTIONS
 		*(.data)
 		*(.data.*)
 
-		/* Add 4 bytes of extra space for a CRC-32 checksum */
+		/* Add 4 bytes of extra space for the obsolete CRC-32 checksum */
 		. = ALIGN(. + 4, 0x200);
 		_edata = . ;
 	}
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 6afd05e819d2..3973a67cd04e 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -22,10 +22,10 @@ SYM_FUNC_START_NOALIGN(memcpy)
 	movw	%dx, %si
 	pushw	%cx
 	shrw	$2, %cx
-	rep; movsl
+	rep movsl
 	popw	%cx
 	andw	$3, %cx
-	rep; movsb
+	rep movsb
 	popw	%di
 	popw	%si
 	retl
@@ -38,10 +38,10 @@ SYM_FUNC_START_NOALIGN(memset)
 	imull	$0x01010101,%eax
 	pushw	%cx
 	shrw	$2, %cx
-	rep; stosl
+	rep stosl
 	popw	%cx
 	andw	$3, %cx
-	rep; stosb
+	rep stosb
 	popw	%di
 	retl
 SYM_FUNC_END(memset)
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 0aae4d4ed615..f82de8de5dc6 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -22,10 +22,11 @@
 # include "boot.h"
 #endif
 #include <linux/types.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/intel-family.h>
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
+
 #include "string.h"
 #include "msr.h"
 
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index d75237ba7ce9..916bac09b464 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -3,7 +3,6 @@
 #include "bitops.h"
 
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
 #include "cpuflags.h"
 
@@ -29,40 +28,32 @@ static int has_fpu(void)
 	return fsw == 0 && (fcw & 0x103f) == 0x003f;
 }
 
+#ifdef CONFIG_X86_32
 /*
  * For building the 16-bit code we want to explicitly specify 32-bit
  * push/pop operations, rather than just saying 'pushf' or 'popf' and
- * letting the compiler choose. But this is also included from the
- * compressed/ directory where it may be 64-bit code, and thus needs
- * to be 'pushfq' or 'popfq' in that case.
+ * letting the compiler choose.
  */
-#ifdef __x86_64__
-#define PUSHF "pushfq"
-#define POPF "popfq"
-#else
-#define PUSHF "pushfl"
-#define POPF "popfl"
-#endif
-
-int has_eflag(unsigned long mask)
+bool has_eflag(unsigned long mask)
 {
 	unsigned long f0, f1;
 
-	asm volatile(PUSHF "	\n\t"
-		     PUSHF "	\n\t"
+	asm volatile("pushfl	\n\t"
+		     "pushfl	\n\t"
 		     "pop %0	\n\t"
 		     "mov %0,%1	\n\t"
 		     "xor %2,%1	\n\t"
 		     "push %1	\n\t"
-		     POPF "	\n\t"
-		     PUSHF "	\n\t"
+		     "popfl	\n\t"
+		     "pushfl	\n\t"
 		     "pop %1	\n\t"
-		     POPF
+		     "popfl"
 		     : "=&r" (f0), "=&r" (f1)
 		     : "ri" (mask));
 
 	return !!((f0^f1) & mask);
 }
+#endif
 
 void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d)
 {
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 475b8fde90f7..a398d9204ad0 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -15,8 +15,13 @@ struct cpu_features {
 extern struct cpu_features cpu;
 extern u32 cpu_vendor[3];
 
-int has_eflag(unsigned long mask);
+#ifdef CONFIG_X86_32
+bool has_eflag(unsigned long mask);
+#else
+static inline bool has_eflag(unsigned long mask) { return true; }
+#endif
 void get_cpuflags(void);
 void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d);
+bool has_cpuflag(int flag);
 
 #endif
diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh
index c9299aeb7333..3882ead513f7 100644
--- a/arch/x86/boot/genimage.sh
+++ b/arch/x86/boot/genimage.sh
@@ -22,6 +22,7 @@
 # This script requires:
 #   bash
 #   syslinux
+#   genisoimage
 #   mtools (for fdimage* and hdimage)
 #   edk2/OVMF (for hdimage)
 #
@@ -251,7 +252,9 @@ geniso() {
 	cp "$isolinux" "$ldlinux" "$tmp_dir"
 	cp "$FBZIMAGE" "$tmp_dir"/linux
 	echo default linux "$KCMDLINE" > "$tmp_dir"/isolinux.cfg
-	cp "${FDINITRDS[@]}" "$tmp_dir"/
+	if [ ${#FDINITRDS[@]} -gt 0 ]; then
+		cp "${FDINITRDS[@]}" "$tmp_dir"/
+	fi
 	genisoimage -J -r -appid 'LINUX_BOOT' -input-charset=utf-8 \
 		    -quiet -o "$FIMAGE" -b isolinux.bin \
 		    -c boot.cat -no-emul-boot -boot-load-size 4 \
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b5c79f43359b..e30649e44d8f 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -361,12 +361,8 @@ xloadflags:
 #endif
 
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_X86_5LEVEL
 #define XLF56 (XLF_5LEVEL|XLF_5LEVEL_ENABLED)
 #else
-#define XLF56 XLF_5LEVEL
-#endif
-#else
 #define XLF56 0
 #endif
 
@@ -585,7 +581,7 @@ start_of_setup:
 	xorl	%eax, %eax
 	subw	%di, %cx
 	shrw	$2, %cx
-	rep; stosl
+	rep stosl
 
 # Jump to C code (should not return)
 	calll	main
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index da0ccc5de538..22d730b227e3 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -12,8 +12,6 @@
 
 #include <stdio.h>
 
-#include "../include/asm/required-features.h"
-#include "../include/asm/disabled-features.h"
 #include "../include/asm/cpufeatures.h"
 #include "../include/asm/vmxfeatures.h"
 #include "../kernel/cpu/capflags.c"
@@ -23,6 +21,7 @@ int main(void)
 	int i, j;
 	const char *str;
 
+	printf("#include <asm/cpufeaturemasks.h>\n\n");
 	printf("static const char x86_cap_strs[] =\n");
 
 	for (i = 0; i < NCAPINTS; i++) {
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 3a2d1360abb0..e1d594a60204 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -45,6 +45,8 @@ SECTIONS
 
 		setup_size = ALIGN(ABSOLUTE(.), 4096);
 		setup_sects = ABSOLUTE(setup_size / 512);
+		ASSERT(setup_sects >= 5, "The setup must be at least 5 sectors in size");
+		ASSERT(setup_sects <= 64, "The setup must be at most 64 sectors in size");
 	}
 
 	. = ALIGN(16);
diff --git a/arch/x86/boot/startup/Makefile b/arch/x86/boot/startup/Makefile
new file mode 100644
index 000000000000..b514f7e81332
--- /dev/null
+++ b/arch/x86/boot/startup/Makefile
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KBUILD_AFLAGS		+= -D__DISABLE_EXPORTS
+KBUILD_CFLAGS		+= -D__DISABLE_EXPORTS -mcmodel=small -fPIC \
+			   -Os -DDISABLE_BRANCH_PROFILING \
+			   $(DISABLE_STACKLEAK_PLUGIN) \
+			   -fno-stack-protector -D__NO_FORTIFY \
+			   -fno-jump-tables \
+			   -include $(srctree)/include/linux/hidden.h
+
+# disable ftrace hooks and LTO
+KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS	:= $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+KASAN_SANITIZE	:= n
+KCSAN_SANITIZE	:= n
+KMSAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
+
+obj-$(CONFIG_X86_64)		+= gdt_idt.o map_kernel.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= sme.o sev-startup.o
+
+lib-$(CONFIG_X86_64)		+= la57toggle.o
+lib-$(CONFIG_EFI_MIXED)		+= efi-mixed.o
+
+#
+# Disable objtool validation for all library code, which is intended
+# to be linked into the decompressor or the EFI stub but not vmlinux
+#
+$(patsubst %.o,$(obj)/%.o,$(lib-y)): OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/x86/boot/startup/efi-mixed.S b/arch/x86/boot/startup/efi-mixed.S
new file mode 100644
index 000000000000..e04ed99bc449
--- /dev/null
+++ b/arch/x86/boot/startup/efi-mixed.S
@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT and IDT before we make EFI service
+ * calls.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identity
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/desc_defs.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+	.text
+	.code32
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+SYM_FUNC_START(efi32_stub_entry)
+	call	1f
+1:	popl	%ecx
+
+	/* Clear BSS */
+	xorl	%eax, %eax
+	leal	(_bss - 1b)(%ecx), %edi
+	leal	(_ebss - 1b)(%ecx), %ecx
+	subl	%edi, %ecx
+	shrl	$2, %ecx
+	cld
+	rep	stosl
+
+	add	$0x4, %esp		/* Discard return address */
+	movl	8(%esp), %ebx		/* struct boot_params pointer */
+	jmp	efi32_startup
+SYM_FUNC_END(efi32_stub_entry)
+#endif
+
+/*
+ * Called using a far call from __efi64_thunk() below, using the x86_64 SysV
+ * ABI (except for R8/R9 which are inaccessible to 32-bit code - EAX/EBX are
+ * used instead).  EBP+16 points to the arguments passed via the stack.
+ *
+ * The first argument (EDI) is a pointer to the boot service or protocol, to
+ * which the remaining arguments are passed, each truncated to 32 bits.
+ */
+SYM_FUNC_START_LOCAL(efi_enter32)
+	/*
+	 * Convert x86-64 SysV ABI params to i386 ABI
+	 */
+	pushl	32(%ebp)	/* Up to 3 args passed via the stack */
+	pushl	24(%ebp)
+	pushl	16(%ebp)
+	pushl	%ebx		/* R9 */
+	pushl	%eax		/* R8 */
+	pushl	%ecx
+	pushl	%edx
+	pushl	%esi
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Disable long mode via EFER */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btrl	$_EFER_LME, %eax
+	wrmsr
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	call	efi32_enable_long_mode
+
+	addl	$32, %esp
+	movl	%edi, %eax
+	lret
+SYM_FUNC_END(efi_enter32)
+
+	.code64
+SYM_FUNC_START(__efi64_thunk)
+	push	%rbp
+	movl	%esp, %ebp
+	push	%rbx
+
+	/* Move args #5 and #6 into 32-bit accessible registers */
+	movl	%r8d, %eax
+	movl	%r9d, %ebx
+
+	lcalll	*efi32_call(%rip)
+
+	pop	%rbx
+	pop	%rbp
+	RET
+SYM_FUNC_END(__efi64_thunk)
+
+	.code32
+SYM_FUNC_START_LOCAL(efi32_enable_long_mode)
+	movl	%cr4, %eax
+	btsl	$(X86_CR4_PAE_BIT), %eax
+	movl	%eax, %cr4
+
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	/* Disable interrupts - the firmware's IDT does not work in long mode */
+	cli
+
+	/* Enable paging */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+	ret
+SYM_FUNC_END(efi32_enable_long_mode)
+
+/*
+ * This is the common EFI stub entry point for mixed mode. It sets up the GDT
+ * and page tables needed for 64-bit execution, after which it calls the
+ * common 64-bit EFI entrypoint efi_stub_entry().
+ *
+ * Arguments:	0(%esp)	image handle
+ * 		4(%esp)	EFI system table pointer
+ *		%ebx	struct boot_params pointer (or NULL)
+ *
+ * Since this is the point of no return for ordinary execution, no registers
+ * are considered live except for the function parameters. [Note that the EFI
+ * stub may still exit and return to the firmware using the Exit() EFI boot
+ * service.]
+ */
+SYM_FUNC_START_LOCAL(efi32_startup)
+	movl	%esp, %ebp
+
+	subl	$8, %esp
+	sgdtl	(%esp)			/* Save GDT descriptor to the stack */
+	movl	2(%esp), %esi		/* Existing GDT pointer */
+	movzwl	(%esp), %ecx		/* Existing GDT limit */
+	inc	%ecx			/* Existing GDT size */
+	andl	$~7, %ecx		/* Ensure size is multiple of 8 */
+
+	subl	%ecx, %esp		/* Allocate new GDT */
+	andl	$~15, %esp		/* Realign the stack */
+	movl	%esp, %edi		/* New GDT address */
+	leal	7(%ecx), %eax		/* New GDT limit */
+	pushw	%cx			/* Push 64-bit CS (for LJMP below) */
+	pushl	%edi			/* Push new GDT address */
+	pushw	%ax			/* Push new GDT limit */
+
+	/* Copy GDT to the stack and add a 64-bit code segment at the end */
+	movl	$GDT_ENTRY(DESC_CODE64, 0, 0xfffff) & 0xffffffff, (%edi,%ecx)
+	movl	$GDT_ENTRY(DESC_CODE64, 0, 0xfffff) >> 32, 4(%edi,%ecx)
+	shrl	$2, %ecx
+	cld
+	rep	movsl			/* Copy the firmware GDT */
+	lgdtl	(%esp)			/* Switch to the new GDT */
+
+	call	1f
+1:	pop	%edi
+
+	/* Record mixed mode entry */
+	movb	$0x0, (efi_is64 - 1b)(%edi)
+
+	/* Set up indirect far call to re-enter 32-bit mode */
+	leal	(efi32_call - 1b)(%edi), %eax
+	addl	%eax, (%eax)
+	movw	%cs, 4(%eax)
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Set up 1:1 mapping */
+	leal	(pte - 1b)(%edi), %eax
+	movl	$_PAGE_PRESENT | _PAGE_RW | _PAGE_PSE, %ecx
+	leal	(_PAGE_PRESENT | _PAGE_RW)(%eax), %edx
+2:	movl	%ecx, (%eax)
+	addl	$8, %eax
+	addl	$PMD_SIZE, %ecx
+	jnc	2b
+
+	movl	$PAGE_SIZE, %ecx
+	.irpc	l, 0123
+	movl	%edx, \l * 8(%eax)
+	addl	%ecx, %edx
+	.endr
+	addl	%ecx, %eax
+	movl	%edx, (%eax)
+	movl	%eax, %cr3
+
+	call	efi32_enable_long_mode
+
+	/* Set up far jump to 64-bit mode (CS is already on the stack) */
+	leal	(efi_stub_entry - 1b)(%edi), %eax
+	movl	%eax, 2(%esp)
+
+	movl	0(%ebp), %edi
+	movl	4(%ebp), %esi
+	movl	%ebx, %edx
+	ljmpl	*2(%esp)
+SYM_FUNC_END(efi32_startup)
+
+/*
+ * efi_status_t efi32_pe_entry(efi_handle_t image_handle,
+ *			       efi_system_table_32_t *sys_table)
+ */
+SYM_FUNC_START(efi32_pe_entry)
+	pushl	%ebx				// save callee-save registers
+
+	/* Check whether the CPU supports long mode */
+	movl	$0x80000001, %eax		// assume extended info support
+	cpuid
+	btl	$29, %edx			// check long mode bit
+	jnc	1f
+	leal	8(%esp), %esp			// preserve stack alignment
+	xor	%ebx, %ebx			// no struct boot_params pointer
+	jmp	efi32_startup			// only ESP and EBX remain live
+1:	movl	$0x80000003, %eax		// EFI_UNSUPPORTED
+	popl	%ebx
+	RET
+SYM_FUNC_END(efi32_pe_entry)
+
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+	.org	efi32_stub_entry + 0x200
+	.code64
+SYM_FUNC_START_NOALIGN(efi64_stub_entry)
+	jmp	efi_handover_entry
+SYM_FUNC_END(efi64_stub_entry)
+#endif
+
+	.data
+	.balign	8
+SYM_DATA_START_LOCAL(efi32_call)
+	.long	efi_enter32 - .
+	.word	0x0
+SYM_DATA_END(efi32_call)
+SYM_DATA(efi_is64, .byte 1)
+
+	.bss
+	.balign PAGE_SIZE
+SYM_DATA_LOCAL(pte, .fill 6 * PAGE_SIZE, 1, 0)
diff --git a/arch/x86/boot/startup/gdt_idt.c b/arch/x86/boot/startup/gdt_idt.c
new file mode 100644
index 000000000000..a3112a69b06a
--- /dev/null
+++ b/arch/x86/boot/startup/gdt_idt.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+#include <asm/desc.h>
+#include <asm/init.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+
+/*
+ * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
+ * used until the idt_table takes over. On the boot CPU this happens in
+ * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
+ * this happens in the functions called from head_64.S.
+ *
+ * The idt_table can't be used that early because all the code modifying it is
+ * in idt.c and can be instrumented by tracing or KASAN, which both don't work
+ * during early CPU bringup. Also the idt_table has the runtime vectors
+ * configured which require certain CPU state to be setup already (like TSS),
+ * which also hasn't happened yet in early CPU bringup.
+ */
+static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
+
+/* This may run while still in the direct mapping */
+void __head startup_64_load_idt(void *vc_handler)
+{
+	struct desc_ptr desc = {
+		.address = (unsigned long)rip_rel_ptr(bringup_idt_table),
+		.size    = sizeof(bringup_idt_table) - 1,
+	};
+	struct idt_data data;
+	gate_desc idt_desc;
+
+	/* @vc_handler is set only for a VMM Communication Exception */
+	if (vc_handler) {
+		init_idt_data(&data, X86_TRAP_VC, vc_handler);
+		idt_init_desc(&idt_desc, &data);
+		native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
+	}
+
+	native_load_idt(&desc);
+}
+
+/*
+ * Setup boot CPU state needed before kernel switches to virtual addresses.
+ */
+void __head startup_64_setup_gdt_idt(void)
+{
+	struct gdt_page *gp = rip_rel_ptr((void *)(__force unsigned long)&gdt_page);
+	void *handler = NULL;
+
+	struct desc_ptr startup_gdt_descr = {
+		.address = (unsigned long)gp->gdt,
+		.size    = GDT_SIZE - 1,
+	};
+
+	/* Load GDT */
+	native_load_gdt(&startup_gdt_descr);
+
+	/* New GDT is live - reload data segment registers */
+	asm volatile("movl %%eax, %%ds\n"
+		     "movl %%eax, %%ss\n"
+		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+		handler = rip_rel_ptr(vc_no_ghcb);
+
+	startup_64_load_idt(handler);
+}
diff --git a/arch/x86/boot/startup/la57toggle.S b/arch/x86/boot/startup/la57toggle.S
new file mode 100644
index 000000000000..370075b4d95b
--- /dev/null
+++ b/arch/x86/boot/startup/la57toggle.S
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/boot.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+
+/*
+ * This is the 32-bit trampoline that will be copied over to low memory. It
+ * will be called using the ordinary 64-bit calling convention from code
+ * running in 64-bit mode.
+ *
+ * Return address is at the top of the stack (might be above 4G).
+ * The first argument (EDI) contains the address of the temporary PGD level
+ * page table in 32-bit addressable memory which will be programmed into
+ * register CR3.
+ */
+
+	.section ".rodata", "a", @progbits
+SYM_CODE_START(trampoline_32bit_src)
+	/*
+	 * Preserve callee save 64-bit registers on the stack: this is
+	 * necessary because the architecture does not guarantee that GPRs will
+	 * retain their full 64-bit values across a 32-bit mode switch.
+	 */
+	pushq	%r15
+	pushq	%r14
+	pushq	%r13
+	pushq	%r12
+	pushq	%rbp
+	pushq	%rbx
+
+	/* Preserve top half of RSP in a legacy mode GPR to avoid truncation */
+	movq	%rsp, %rbx
+	shrq	$32, %rbx
+
+	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
+	pushq	$__KERNEL32_CS
+	leaq	0f(%rip), %rax
+	pushq	%rax
+	lretq
+
+	/*
+	 * The 32-bit code below will do a far jump back to long mode and end
+	 * up here after reconfiguring the number of paging levels. First, the
+	 * stack pointer needs to be restored to its full 64-bit value before
+	 * the callee save register contents can be popped from the stack.
+	 */
+.Lret:
+	shlq	$32, %rbx
+	orq	%rbx, %rsp
+
+	/* Restore the preserved 64-bit registers */
+	popq	%rbx
+	popq	%rbp
+	popq	%r12
+	popq	%r13
+	popq	%r14
+	popq	%r15
+	retq
+
+	.code32
+0:
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Point CR3 to the trampoline's new top level page table */
+	movl	%edi, %cr3
+
+	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	/* Avoid writing EFER if no change was made (for TDX guest) */
+	jc	1f
+	wrmsr
+1:
+	/* Toggle CR4.LA57 */
+	movl	%cr4, %eax
+	btcl	$X86_CR4_LA57_BIT, %eax
+	movl	%eax, %cr4
+
+	/* Enable paging again. */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/*
+	 * Return to the 64-bit calling code using LJMP rather than LRET, to
+	 * avoid the need for a 32-bit addressable stack. The destination
+	 * address will be adjusted after the template code is copied into a
+	 * 32-bit addressable buffer.
+	 */
+.Ljmp:	ljmpl	$__KERNEL_CS, $(.Lret - trampoline_32bit_src)
+SYM_CODE_END(trampoline_32bit_src)
+
+/*
+ * This symbol is placed right after trampoline_32bit_src() so its address can
+ * be used to infer the size of the trampoline code.
+ */
+SYM_DATA(trampoline_ljmp_imm_offset, .word  .Ljmp + 1 - trampoline_32bit_src)
+
+	/*
+         * The trampoline code has a size limit.
+         * Make sure we fail to compile if the trampoline code grows
+         * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes.
+	 */
+	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
diff --git a/arch/x86/boot/startup/map_kernel.c b/arch/x86/boot/startup/map_kernel.c
new file mode 100644
index 000000000000..332dbe6688c4
--- /dev/null
+++ b/arch/x86/boot/startup/map_kernel.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
+
+#include <asm/init.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+
+extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
+extern unsigned int next_early_pgt;
+
+static inline bool check_la57_support(void)
+{
+	/*
+	 * 5-level paging is detected and enabled at kernel decompression
+	 * stage. Only check if it has been enabled there.
+	 */
+	if (!(native_read_cr4() & X86_CR4_LA57))
+		return false;
+
+	__pgtable_l5_enabled	= 1;
+	pgdir_shift		= 48;
+	ptrs_per_p4d		= 512;
+
+	return true;
+}
+
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
+						    pmdval_t *pmd,
+						    unsigned long p2v_offset)
+{
+	unsigned long paddr, paddr_end;
+	int i;
+
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
+
+	/*
+	 * Clear the memory encryption mask from the .bss..decrypted section.
+	 * The bss section will be memset to zero later in the initialization so
+	 * there is no need to zero it after changing the memory encryption
+	 * attribute.
+	 */
+	if (sme_get_me_mask()) {
+		paddr = (unsigned long)rip_rel_ptr(__start_bss_decrypted);
+		paddr_end = (unsigned long)rip_rel_ptr(__end_bss_decrypted);
+
+		for (; paddr < paddr_end; paddr += PMD_SIZE) {
+			/*
+			 * On SNP, transition the page to shared in the RMP table so that
+			 * it is consistent with the page table attribute change.
+			 *
+			 * __start_bss_decrypted has a virtual address in the high range
+			 * mapping (kernel .text). PVALIDATE, by way of
+			 * early_snp_set_memory_shared(), requires a valid virtual
+			 * address but the kernel is currently running off of the identity
+			 * mapping so use the PA to get a *currently* valid virtual address.
+			 */
+			early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
+
+			i = pmd_index(paddr - p2v_offset);
+			pmd[i] -= sme_get_me_mask();
+		}
+	}
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
+/*
+ * This code is compiled using PIC codegen because it will execute from the
+ * early 1:1 mapping of memory, which deviates from the mapping expected by the
+ * linker. Due to this deviation, taking the address of a global variable will
+ * produce an ambiguous result when using the plain & operator.  Instead,
+ * rip_rel_ptr() must be used, which will return the RIP-relative address in
+ * the 1:1 mapping of memory. Kernel virtual addresses can be determined by
+ * subtracting p2v_offset from the RIP-relative address.
+ */
+unsigned long __head __startup_64(unsigned long p2v_offset,
+				  struct boot_params *bp)
+{
+	pmd_t (*early_pgts)[PTRS_PER_PMD] = rip_rel_ptr(early_dynamic_pgts);
+	unsigned long physaddr = (unsigned long)rip_rel_ptr(_text);
+	unsigned long va_text, va_end;
+	unsigned long pgtable_flags;
+	unsigned long load_delta;
+	pgdval_t *pgd;
+	p4dval_t *p4d;
+	pudval_t *pud;
+	pmdval_t *pmd, pmd_entry;
+	bool la57;
+	int i;
+
+	la57 = check_la57_support();
+
+	/* Is the address too large? */
+	if (physaddr >> MAX_PHYSMEM_BITS)
+		for (;;);
+
+	/*
+	 * Compute the delta between the address I am compiled to run at
+	 * and the address I am actually running at.
+	 */
+	phys_base = load_delta = __START_KERNEL_map + p2v_offset;
+
+	/* Is the address not 2M aligned? */
+	if (load_delta & ~PMD_MASK)
+		for (;;);
+
+	va_text = physaddr - p2v_offset;
+	va_end  = (unsigned long)rip_rel_ptr(_end) - p2v_offset;
+
+	/* Include the SME encryption mask in the fixup value */
+	load_delta += sme_get_me_mask();
+
+	/* Fixup the physical addresses in the page table */
+
+	pgd = rip_rel_ptr(early_top_pgt);
+	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
+
+	if (la57) {
+		p4d = (p4dval_t *)rip_rel_ptr(level4_kernel_pgt);
+		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
+
+		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
+	}
+
+	level3_kernel_pgt[PTRS_PER_PUD - 2].pud += load_delta;
+	level3_kernel_pgt[PTRS_PER_PUD - 1].pud += load_delta;
+
+	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+		level2_fixmap_pgt[i].pmd += load_delta;
+
+	/*
+	 * Set up the identity mapping for the switchover.  These
+	 * entries should *NOT* have the global bit set!  This also
+	 * creates a bunch of nonsense entries but that is fine --
+	 * it avoids problems around wraparound.
+	 */
+
+	pud = &early_pgts[0]->pmd;
+	pmd = &early_pgts[1]->pmd;
+	next_early_pgt = 2;
+
+	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
+
+	if (la57) {
+		p4d = &early_pgts[next_early_pgt++]->pmd;
+
+		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
+
+		i = physaddr >> P4D_SHIFT;
+		p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+		p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+	} else {
+		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
+	}
+
+	i = physaddr >> PUD_SHIFT;
+	pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+	pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+
+	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	pmd_entry += sme_get_me_mask();
+	pmd_entry +=  physaddr;
+
+	for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
+		int idx = i + (physaddr >> PMD_SHIFT);
+
+		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
+	}
+
+	/*
+	 * Fixup the kernel text+data virtual addresses. Note that
+	 * we might write invalid pmds, when the kernel is relocated
+	 * cleanup_highmap() fixes this up along with the mappings
+	 * beyond _end.
+	 *
+	 * Only the region occupied by the kernel image has so far
+	 * been checked against the table of usable memory regions
+	 * provided by the firmware, so invalidate pages outside that
+	 * region. A page table entry that maps to a reserved area of
+	 * memory would allow processor speculation into that area,
+	 * and on some hardware (particularly the UV platform) even
+	 * speculative access to some reserved areas is caught as an
+	 * error, causing the BIOS to halt the system.
+	 */
+
+	pmd = rip_rel_ptr(level2_kernel_pgt);
+
+	/* invalidate pages before the kernel image */
+	for (i = 0; i < pmd_index(va_text); i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	/* fixup pages that are part of the kernel image */
+	for (; i <= pmd_index(va_end); i++)
+		if (pmd[i] & _PAGE_PRESENT)
+			pmd[i] += load_delta;
+
+	/* invalidate pages after the kernel image */
+	for (; i < PTRS_PER_PMD; i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	return sme_postprocess_startup(bp, pmd, p2v_offset);
+}
diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/boot/startup/sev-shared.c
index 2e4122f8aa6b..7a706db87b93 100644
--- a/arch/x86/coco/sev/shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -14,76 +14,23 @@
 #ifndef __BOOT_COMPRESSED
 #define error(v)			pr_err(v)
 #define has_cpuflag(f)			boot_cpu_has(f)
-#define sev_printk(fmt, ...)		printk(fmt, ##__VA_ARGS__)
-#define sev_printk_rtl(fmt, ...)	printk_ratelimited(fmt, ##__VA_ARGS__)
 #else
 #undef WARN
 #define WARN(condition, format...) (!!(condition))
-#define sev_printk(fmt, ...)
-#define sev_printk_rtl(fmt, ...)
 #undef vc_forward_exception
 #define vc_forward_exception(c)		panic("SNP: Hypervisor requested exception\n")
 #endif
 
 /*
  * SVSM related information:
- *   When running under an SVSM, the VMPL that Linux is executing at must be
- *   non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
- *
  *   During boot, the page tables are set up as identity mapped and later
  *   changed to use kernel virtual addresses. Maintain separate virtual and
  *   physical addresses for the CAA to allow SVSM functions to be used during
  *   early boot, both with identity mapped virtual addresses and proper kernel
  *   virtual addresses.
  */
-u8 snp_vmpl __ro_after_init;
-EXPORT_SYMBOL_GPL(snp_vmpl);
-static struct svsm_ca *boot_svsm_caa __ro_after_init;
-static u64 boot_svsm_caa_pa __ro_after_init;
-
-static struct svsm_ca *svsm_get_caa(void);
-static u64 svsm_get_caa_pa(void);
-static int svsm_perform_call_protocol(struct svsm_call *call);
-
-/* I/O parameters for CPUID-related helpers */
-struct cpuid_leaf {
-	u32 fn;
-	u32 subfn;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-};
-
-/*
- * Individual entries of the SNP CPUID table, as defined by the SNP
- * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
- */
-struct snp_cpuid_fn {
-	u32 eax_in;
-	u32 ecx_in;
-	u64 xcr0_in;
-	u64 xss_in;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u64 __reserved;
-} __packed;
-
-/*
- * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
- * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
- * of 64 entries per CPUID table.
- */
-#define SNP_CPUID_COUNT_MAX 64
-
-struct snp_cpuid_table {
-	u32 count;
-	u32 __reserved1;
-	u64 __reserved2;
-	struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
-} __packed;
+struct svsm_ca *boot_svsm_caa __ro_after_init;
+u64 boot_svsm_caa_pa __ro_after_init;
 
 /*
  * Since feature negotiation related variables are set early in the boot
@@ -107,7 +54,7 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
-static bool __init sev_es_check_cpu_features(void)
+bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {
 		error("RDRAND instruction not supported - no trusted source of randomness available\n");
@@ -117,7 +64,7 @@ static bool __init sev_es_check_cpu_features(void)
 	return true;
 }
 
-static void __head __noreturn
+void __head __noreturn
 sev_es_terminate(unsigned int set, unsigned int reason)
 {
 	u64 val = GHCB_MSR_TERM_REQ;
@@ -136,7 +83,7 @@ sev_es_terminate(unsigned int set, unsigned int reason)
 /*
  * The hypervisor features are available from GHCB version 2 onward.
  */
-static u64 get_hv_features(void)
+u64 get_hv_features(void)
 {
 	u64 val;
 
@@ -153,7 +100,7 @@ static u64 get_hv_features(void)
 	return GHCB_MSR_HV_FT_RESP_VAL(val);
 }
 
-static void snp_register_ghcb_early(unsigned long paddr)
+void snp_register_ghcb_early(unsigned long paddr)
 {
 	unsigned long pfn = paddr >> PAGE_SHIFT;
 	u64 val;
@@ -169,7 +116,7 @@ static void snp_register_ghcb_early(unsigned long paddr)
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER);
 }
 
-static bool sev_es_negotiate_protocol(void)
+bool sev_es_negotiate_protocol(void)
 {
 	u64 val;
 
@@ -190,39 +137,6 @@ static bool sev_es_negotiate_protocol(void)
 	return true;
 }
 
-static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
-{
-	ghcb->save.sw_exit_code = 0;
-	__builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-}
-
-static bool vc_decoding_needed(unsigned long exit_code)
-{
-	/* Exceptions don't require to decode the instruction */
-	return !(exit_code >= SVM_EXIT_EXCP_BASE &&
-		 exit_code <= SVM_EXIT_LAST_EXCP);
-}
-
-static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
-				      struct pt_regs *regs,
-				      unsigned long exit_code)
-{
-	enum es_result ret = ES_OK;
-
-	memset(ctxt, 0, sizeof(*ctxt));
-	ctxt->regs = regs;
-
-	if (vc_decoding_needed(exit_code))
-		ret = vc_decode_insn(ctxt);
-
-	return ret;
-}
-
-static void vc_finish_insn(struct es_em_ctxt *ctxt)
-{
-	ctxt->regs->ip += ctxt->insn.length;
-}
-
 static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
 	u32 ret;
@@ -344,7 +258,7 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
 	 * Fill in protocol and format specifiers. This can be called very early
 	 * in the boot, so use rip-relative references as needed.
 	 */
-	ghcb->protocol_version = RIP_REL_REF(ghcb_version);
+	ghcb->protocol_version = ghcb_version;
 	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
 
 	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL);
@@ -371,10 +285,10 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
 	return svsm_process_result_codes(call);
 }
 
-static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt,
-					  u64 exit_code, u64 exit_info_1,
-					  u64 exit_info_2)
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2)
 {
 	/* Fill in protocol and format specifiers */
 	ghcb->protocol_version = ghcb_version;
@@ -473,9 +387,9 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
  * while running with the initial identity mapping as well as the
  * switch-over to kernel virtual addresses later.
  */
-static const struct snp_cpuid_table *snp_cpuid_get_table(void)
+const struct snp_cpuid_table *snp_cpuid_get_table(void)
 {
-	return &RIP_REL_REF(cpuid_table_copy);
+	return rip_rel_ptr(&cpuid_table_copy);
 }
 
 /*
@@ -672,7 +586,7 @@ snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
  * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
  * should be treated as fatal by caller.
  */
-static int __head
+int __head
 snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -701,9 +615,9 @@ snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 		leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
 
 		/* Skip post-processing for out-of-range zero leafs. */
-		if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) ||
-		      (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) ||
-		      (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max))))
+		if (!(leaf->fn <= cpuid_std_range_max ||
+		      (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
+		      (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
 			return 0;
 	}
 
@@ -782,391 +696,6 @@ fail:
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }
 
-static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
-					   unsigned long address,
-					   bool write)
-{
-	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_USER;
-		ctxt->fi.cr2        = address;
-		if (write)
-			ctxt->fi.error_code |= X86_PF_WRITE;
-
-		return ES_EXCEPTION;
-	}
-
-	return ES_OK;
-}
-
-static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
-					  void *src, char *buf,
-					  unsigned int data_size,
-					  unsigned int count,
-					  bool backwards)
-{
-	int i, b = backwards ? -1 : 1;
-	unsigned long address = (unsigned long)src;
-	enum es_result ret;
-
-	ret = vc_insn_string_check(ctxt, address, false);
-	if (ret != ES_OK)
-		return ret;
-
-	for (i = 0; i < count; i++) {
-		void *s = src + (i * data_size * b);
-		char *d = buf + (i * data_size);
-
-		ret = vc_read_mem(ctxt, s, d, data_size);
-		if (ret != ES_OK)
-			break;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
-					   void *dst, char *buf,
-					   unsigned int data_size,
-					   unsigned int count,
-					   bool backwards)
-{
-	int i, s = backwards ? -1 : 1;
-	unsigned long address = (unsigned long)dst;
-	enum es_result ret;
-
-	ret = vc_insn_string_check(ctxt, address, true);
-	if (ret != ES_OK)
-		return ret;
-
-	for (i = 0; i < count; i++) {
-		void *d = dst + (i * data_size * s);
-		char *b = buf + (i * data_size);
-
-		ret = vc_write_mem(ctxt, d, b, data_size);
-		if (ret != ES_OK)
-			break;
-	}
-
-	return ret;
-}
-
-#define IOIO_TYPE_STR  BIT(2)
-#define IOIO_TYPE_IN   1
-#define IOIO_TYPE_INS  (IOIO_TYPE_IN | IOIO_TYPE_STR)
-#define IOIO_TYPE_OUT  0
-#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
-
-#define IOIO_REP       BIT(3)
-
-#define IOIO_ADDR_64   BIT(9)
-#define IOIO_ADDR_32   BIT(8)
-#define IOIO_ADDR_16   BIT(7)
-
-#define IOIO_DATA_32   BIT(6)
-#define IOIO_DATA_16   BIT(5)
-#define IOIO_DATA_8    BIT(4)
-
-#define IOIO_SEG_ES    (0 << 10)
-#define IOIO_SEG_DS    (3 << 10)
-
-static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
-{
-	struct insn *insn = &ctxt->insn;
-	size_t size;
-	u64 port;
-
-	*exitinfo = 0;
-
-	switch (insn->opcode.bytes[0]) {
-	/* INS opcodes */
-	case 0x6c:
-	case 0x6d:
-		*exitinfo |= IOIO_TYPE_INS;
-		*exitinfo |= IOIO_SEG_ES;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* OUTS opcodes */
-	case 0x6e:
-	case 0x6f:
-		*exitinfo |= IOIO_TYPE_OUTS;
-		*exitinfo |= IOIO_SEG_DS;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* IN immediate opcodes */
-	case 0xe4:
-	case 0xe5:
-		*exitinfo |= IOIO_TYPE_IN;
-		port	   = (u8)insn->immediate.value & 0xffff;
-		break;
-
-	/* OUT immediate opcodes */
-	case 0xe6:
-	case 0xe7:
-		*exitinfo |= IOIO_TYPE_OUT;
-		port	   = (u8)insn->immediate.value & 0xffff;
-		break;
-
-	/* IN register opcodes */
-	case 0xec:
-	case 0xed:
-		*exitinfo |= IOIO_TYPE_IN;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* OUT register opcodes */
-	case 0xee:
-	case 0xef:
-		*exitinfo |= IOIO_TYPE_OUT;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	default:
-		return ES_DECODE_FAILED;
-	}
-
-	*exitinfo |= port << 16;
-
-	switch (insn->opcode.bytes[0]) {
-	case 0x6c:
-	case 0x6e:
-	case 0xe4:
-	case 0xe6:
-	case 0xec:
-	case 0xee:
-		/* Single byte opcodes */
-		*exitinfo |= IOIO_DATA_8;
-		size       = 1;
-		break;
-	default:
-		/* Length determined by instruction parsing */
-		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
-						     : IOIO_DATA_32;
-		size       = (insn->opnd_bytes == 2) ? 2 : 4;
-	}
-
-	switch (insn->addr_bytes) {
-	case 2:
-		*exitinfo |= IOIO_ADDR_16;
-		break;
-	case 4:
-		*exitinfo |= IOIO_ADDR_32;
-		break;
-	case 8:
-		*exitinfo |= IOIO_ADDR_64;
-		break;
-	}
-
-	if (insn_has_rep_prefix(insn))
-		*exitinfo |= IOIO_REP;
-
-	return vc_ioio_check(ctxt, (u16)port, size);
-}
-
-static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	u64 exit_info_1, exit_info_2;
-	enum es_result ret;
-
-	ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
-	if (ret != ES_OK)
-		return ret;
-
-	if (exit_info_1 & IOIO_TYPE_STR) {
-
-		/* (REP) INS/OUTS */
-
-		bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
-		unsigned int io_bytes, exit_bytes;
-		unsigned int ghcb_count, op_count;
-		unsigned long es_base;
-		u64 sw_scratch;
-
-		/*
-		 * For the string variants with rep prefix the amount of in/out
-		 * operations per #VC exception is limited so that the kernel
-		 * has a chance to take interrupts and re-schedule while the
-		 * instruction is emulated.
-		 */
-		io_bytes   = (exit_info_1 >> 4) & 0x7;
-		ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
-
-		op_count    = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
-		exit_info_2 = min(op_count, ghcb_count);
-		exit_bytes  = exit_info_2 * io_bytes;
-
-		es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
-		/* Read bytes of OUTS into the shared buffer */
-		if (!(exit_info_1 & IOIO_TYPE_IN)) {
-			ret = vc_insn_string_read(ctxt,
-					       (void *)(es_base + regs->si),
-					       ghcb->shared_buffer, io_bytes,
-					       exit_info_2, df);
-			if (ret)
-				return ret;
-		}
-
-		/*
-		 * Issue an VMGEXIT to the HV to consume the bytes from the
-		 * shared buffer or to have it write them into the shared buffer
-		 * depending on the instruction: OUTS or INS.
-		 */
-		sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
-		ghcb_set_sw_scratch(ghcb, sw_scratch);
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
-					  exit_info_1, exit_info_2);
-		if (ret != ES_OK)
-			return ret;
-
-		/* Read bytes from shared buffer into the guest's destination. */
-		if (exit_info_1 & IOIO_TYPE_IN) {
-			ret = vc_insn_string_write(ctxt,
-						   (void *)(es_base + regs->di),
-						   ghcb->shared_buffer, io_bytes,
-						   exit_info_2, df);
-			if (ret)
-				return ret;
-
-			if (df)
-				regs->di -= exit_bytes;
-			else
-				regs->di += exit_bytes;
-		} else {
-			if (df)
-				regs->si -= exit_bytes;
-			else
-				regs->si += exit_bytes;
-		}
-
-		if (exit_info_1 & IOIO_REP)
-			regs->cx -= exit_info_2;
-
-		ret = regs->cx ? ES_RETRY : ES_OK;
-
-	} else {
-
-		/* IN/OUT into/from rAX */
-
-		int bits = (exit_info_1 & 0x70) >> 1;
-		u64 rax = 0;
-
-		if (!(exit_info_1 & IOIO_TYPE_IN))
-			rax = lower_bits(regs->ax, bits);
-
-		ghcb_set_rax(ghcb, rax);
-
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
-		if (ret != ES_OK)
-			return ret;
-
-		if (exit_info_1 & IOIO_TYPE_IN) {
-			if (!ghcb_rax_is_valid(ghcb))
-				return ES_VMM_ERROR;
-			regs->ax = lower_bits(ghcb->save.rax, bits);
-		}
-	}
-
-	return ret;
-}
-
-static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	struct cpuid_leaf leaf;
-	int ret;
-
-	leaf.fn = regs->ax;
-	leaf.subfn = regs->cx;
-	ret = snp_cpuid(ghcb, ctxt, &leaf);
-	if (!ret) {
-		regs->ax = leaf.eax;
-		regs->bx = leaf.ebx;
-		regs->cx = leaf.ecx;
-		regs->dx = leaf.edx;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	u32 cr4 = native_read_cr4();
-	enum es_result ret;
-	int snp_cpuid_ret;
-
-	snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
-	if (!snp_cpuid_ret)
-		return ES_OK;
-	if (snp_cpuid_ret != -EOPNOTSUPP)
-		return ES_VMM_ERROR;
-
-	ghcb_set_rax(ghcb, regs->ax);
-	ghcb_set_rcx(ghcb, regs->cx);
-
-	if (cr4 & X86_CR4_OSXSAVE)
-		/* Safe to read xcr0 */
-		ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
-	else
-		/* xgetbv will cause #GP - use reset value for xcr0 */
-		ghcb_set_xcr0(ghcb, 1);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) &&
-	      ghcb_rbx_is_valid(ghcb) &&
-	      ghcb_rcx_is_valid(ghcb) &&
-	      ghcb_rdx_is_valid(ghcb)))
-		return ES_VMM_ERROR;
-
-	regs->ax = ghcb->save.rax;
-	regs->bx = ghcb->save.rbx;
-	regs->cx = ghcb->save.rcx;
-	regs->dx = ghcb->save.rdx;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt,
-				      unsigned long exit_code)
-{
-	bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
-	enum es_result ret;
-
-	/*
-	 * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
-	 * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
-	 * instructions are being intercepted. If this should occur and Secure
-	 * TSC is enabled, guest execution should be terminated as the guest
-	 * cannot rely on the TSC value provided by the hypervisor.
-	 */
-	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
-		return ES_VMM_ERROR;
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
-	     (!rdtscp || ghcb_rcx_is_valid(ghcb))))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-	ctxt->regs->dx = ghcb->save.rdx;
-	if (rdtscp)
-		ctxt->regs->cx = ghcb->save.rcx;
-
-	return ES_OK;
-}
-
 struct cc_setup_data {
 	struct setup_data header;
 	u32 cc_blob_address;
@@ -1224,36 +753,14 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 		const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
 
 		if (fn->eax_in == 0x0)
-			RIP_REL_REF(cpuid_std_range_max) = fn->eax;
+			cpuid_std_range_max = fn->eax;
 		else if (fn->eax_in == 0x40000000)
-			RIP_REL_REF(cpuid_hyp_range_max) = fn->eax;
+			cpuid_hyp_range_max = fn->eax;
 		else if (fn->eax_in == 0x80000000)
-			RIP_REL_REF(cpuid_ext_range_max) = fn->eax;
+			cpuid_ext_range_max = fn->eax;
 	}
 }
 
-static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
-				    int ret, u64 svsm_ret)
-{
-	WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
-	     pfn, action, page_size, ret, svsm_ret);
-
-	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
-}
-
-static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
-{
-	unsigned int page_size;
-	bool action;
-	u64 pfn;
-
-	pfn = pc->entry[pc->cur_index].pfn;
-	action = pc->entry[pc->cur_index].action;
-	page_size = pc->entry[pc->cur_index].page_size;
-
-	__pval_terminate(pfn, action, page_size, ret, svsm_ret);
-}
-
 static void __head svsm_pval_4k_page(unsigned long paddr, bool validate)
 {
 	struct svsm_pvalidate_call *pc;
@@ -1296,11 +803,7 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
 {
 	int ret;
 
-	/*
-	 * This can be called very early during boot, so use rIP-relative
-	 * references as needed.
-	 */
-	if (RIP_REL_REF(snp_vmpl)) {
+	if (snp_vmpl) {
 		svsm_pval_4k_page(paddr, validate);
 	} else {
 		ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
@@ -1309,351 +812,6 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
 	}
 }
 
-static void pval_pages(struct snp_psc_desc *desc)
-{
-	struct psc_entry *e;
-	unsigned long vaddr;
-	unsigned int size;
-	unsigned int i;
-	bool validate;
-	u64 pfn;
-	int rc;
-
-	for (i = 0; i <= desc->hdr.end_entry; i++) {
-		e = &desc->entries[i];
-
-		pfn = e->gfn;
-		vaddr = (unsigned long)pfn_to_kaddr(pfn);
-		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
-		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
-
-		rc = pvalidate(vaddr, size, validate);
-		if (!rc)
-			continue;
-
-		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
-			unsigned long vaddr_end = vaddr + PMD_SIZE;
-
-			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
-				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
-				if (rc)
-					__pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
-			}
-		} else {
-			__pval_terminate(pfn, validate, size, rc, 0);
-		}
-	}
-}
-
-static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
-					struct svsm_pvalidate_call *pc)
-{
-	struct svsm_pvalidate_entry *pe;
-
-	/* Nothing in the CA yet */
-	pc->num_entries = 0;
-	pc->cur_index   = 0;
-
-	pe = &pc->entry[0];
-
-	while (pfn < pfn_end) {
-		pe->page_size = RMP_PG_SIZE_4K;
-		pe->action    = action;
-		pe->ignore_cf = 0;
-		pe->pfn       = pfn;
-
-		pe++;
-		pfn++;
-
-		pc->num_entries++;
-		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
-			break;
-	}
-
-	return pfn;
-}
-
-static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
-				       struct svsm_pvalidate_call *pc)
-{
-	struct svsm_pvalidate_entry *pe;
-	struct psc_entry *e;
-
-	/* Nothing in the CA yet */
-	pc->num_entries = 0;
-	pc->cur_index   = 0;
-
-	pe = &pc->entry[0];
-	e  = &desc->entries[desc_entry];
-
-	while (desc_entry <= desc->hdr.end_entry) {
-		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
-		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
-		pe->ignore_cf = 0;
-		pe->pfn       = e->gfn;
-
-		pe++;
-		e++;
-
-		desc_entry++;
-		pc->num_entries++;
-		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
-			break;
-	}
-
-	return desc_entry;
-}
-
-static void svsm_pval_pages(struct snp_psc_desc *desc)
-{
-	struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
-	unsigned int i, pv_4k_count = 0;
-	struct svsm_pvalidate_call *pc;
-	struct svsm_call call = {};
-	unsigned long flags;
-	bool action;
-	u64 pc_pa;
-	int ret;
-
-	/*
-	 * This can be called very early in the boot, use native functions in
-	 * order to avoid paravirt issues.
-	 */
-	flags = native_local_irq_save();
-
-	/*
-	 * The SVSM calling area (CA) can support processing 510 entries at a
-	 * time. Loop through the Page State Change descriptor until the CA is
-	 * full or the last entry in the descriptor is reached, at which time
-	 * the SVSM is invoked. This repeats until all entries in the descriptor
-	 * are processed.
-	 */
-	call.caa = svsm_get_caa();
-
-	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
-	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
-
-	/* Protocol 0, Call ID 1 */
-	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
-	call.rcx = pc_pa;
-
-	for (i = 0; i <= desc->hdr.end_entry;) {
-		i = svsm_build_ca_from_psc_desc(desc, i, pc);
-
-		do {
-			ret = svsm_perform_call_protocol(&call);
-			if (!ret)
-				continue;
-
-			/*
-			 * Check if the entry failed because of an RMP mismatch (a
-			 * PVALIDATE at 2M was requested, but the page is mapped in
-			 * the RMP as 4K).
-			 */
-
-			if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
-			    pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
-				/* Save this entry for post-processing at 4K */
-				pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
-
-				/* Skip to the next one unless at the end of the list */
-				pc->cur_index++;
-				if (pc->cur_index < pc->num_entries)
-					ret = -EAGAIN;
-				else
-					ret = 0;
-			}
-		} while (ret == -EAGAIN);
-
-		if (ret)
-			svsm_pval_terminate(pc, ret, call.rax_out);
-	}
-
-	/* Process any entries that failed to be validated at 2M and validate them at 4K */
-	for (i = 0; i < pv_4k_count; i++) {
-		u64 pfn, pfn_end;
-
-		action  = pv_4k[i].action;
-		pfn     = pv_4k[i].pfn;
-		pfn_end = pfn + 512;
-
-		while (pfn < pfn_end) {
-			pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
-
-			ret = svsm_perform_call_protocol(&call);
-			if (ret)
-				svsm_pval_terminate(pc, ret, call.rax_out);
-		}
-	}
-
-	native_local_irq_restore(flags);
-}
-
-static void pvalidate_pages(struct snp_psc_desc *desc)
-{
-	if (snp_vmpl)
-		svsm_pval_pages(desc);
-	else
-		pval_pages(desc);
-}
-
-static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
-{
-	int cur_entry, end_entry, ret = 0;
-	struct snp_psc_desc *data;
-	struct es_em_ctxt ctxt;
-
-	vc_ghcb_invalidate(ghcb);
-
-	/* Copy the input desc into GHCB shared buffer */
-	data = (struct snp_psc_desc *)ghcb->shared_buffer;
-	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
-
-	/*
-	 * As per the GHCB specification, the hypervisor can resume the guest
-	 * before processing all the entries. Check whether all the entries
-	 * are processed. If not, then keep retrying. Note, the hypervisor
-	 * will update the data memory directly to indicate the status, so
-	 * reference the data->hdr everywhere.
-	 *
-	 * The strategy here is to wait for the hypervisor to change the page
-	 * state in the RMP table before guest accesses the memory pages. If the
-	 * page state change was not successful, then later memory access will
-	 * result in a crash.
-	 */
-	cur_entry = data->hdr.cur_entry;
-	end_entry = data->hdr.end_entry;
-
-	while (data->hdr.cur_entry <= data->hdr.end_entry) {
-		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
-
-		/* This will advance the shared buffer data points to. */
-		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
-
-		/*
-		 * Page State Change VMGEXIT can pass error code through
-		 * exit_info_2.
-		 */
-		if (WARN(ret || ghcb->save.sw_exit_info_2,
-			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
-			 ret, ghcb->save.sw_exit_info_2)) {
-			ret = 1;
-			goto out;
-		}
-
-		/* Verify that reserved bit is not set */
-		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
-			ret = 1;
-			goto out;
-		}
-
-		/*
-		 * Sanity check that entry processing is not going backwards.
-		 * This will happen only if hypervisor is tricking us.
-		 */
-		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
-"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
-			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
-			ret = 1;
-			goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-
-static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
-					    unsigned long exit_code)
-{
-	unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
-	u8 modrm = ctxt->insn.modrm.value;
-
-	switch (exit_code) {
-
-	case SVM_EXIT_IOIO:
-	case SVM_EXIT_NPF:
-		/* handled separately */
-		return ES_OK;
-
-	case SVM_EXIT_CPUID:
-		if (opcode == 0xa20f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_INVD:
-		if (opcode == 0x080f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MONITOR:
-		/* MONITOR and MONITORX instructions generate the same error code */
-		if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MWAIT:
-		/* MWAIT and MWAITX instructions generate the same error code */
-		if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MSR:
-		/* RDMSR */
-		if (opcode == 0x320f ||
-		/* WRMSR */
-		    opcode == 0x300f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDPMC:
-		if (opcode == 0x330f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDTSC:
-		if (opcode == 0x310f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDTSCP:
-		if (opcode == 0x010f && modrm == 0xf9)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_READ_DR7:
-		if (opcode == 0x210f &&
-		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_VMMCALL:
-		if (opcode == 0x010f && modrm == 0xd9)
-			return ES_OK;
-
-		break;
-
-	case SVM_EXIT_WRITE_DR7:
-		if (opcode == 0x230f &&
-		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_WBINVD:
-		if (opcode == 0x90f)
-			return ES_OK;
-		break;
-
-	default:
-		break;
-	}
-
-	sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
-		   opcode, exit_code, ctxt->regs->ip);
-
-	return ES_UNSUPPORTED;
-}
-
 /*
  * Maintain the GPA of the SVSM Calling Area (CA) in order to utilize the SVSM
  * services needed when not running in VMPL0.
@@ -1681,7 +839,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	 * routine is running identity mapped when called, both by the decompressor
 	 * code and the early kernel code.
 	 */
-	if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1))
+	if (!rmpadjust((unsigned long)rip_rel_ptr(&boot_ghcb_page), RMP_PG_SIZE_4K, 1))
 		return false;
 
 	/*
@@ -1698,7 +856,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	if (!secrets_page->svsm_guest_vmpl)
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0);
 
-	RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl;
+	snp_vmpl = secrets_page->svsm_guest_vmpl;
 
 	caa = secrets_page->svsm_caa;
 
@@ -1713,8 +871,8 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	 * The CA is identity mapped when this routine is called, both by the
 	 * decompressor code and the early kernel code.
 	 */
-	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa;
-	RIP_REL_REF(boot_svsm_caa_pa) = caa;
+	boot_svsm_caa = (struct svsm_ca *)caa;
+	boot_svsm_caa_pa = caa;
 
 	/* Advertise the SVSM presence via CPUID. */
 	cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table();
diff --git a/arch/x86/boot/startup/sev-startup.c b/arch/x86/boot/startup/sev-startup.c
new file mode 100644
index 000000000000..0b7e3b950183
--- /dev/null
+++ b/arch/x86/boot/startup/sev-startup.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/percpu-defs.h>
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/set_memory.h>
+#include <linux/memblock.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/cpu_entry_area.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/realmode.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid/api.h>
+#include <asm/cmdline.h>
+
+/* For early boot hypervisor communication in SEV-ES enabled guests */
+struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
+
+/*
+ * Needs to be in the .data section because we need it NULL before bss is
+ * cleared
+ */
+struct ghcb *boot_ghcb __section(".data");
+
+/* Bitmap of SEV features supported by the hypervisor */
+u64 sev_hv_features __ro_after_init;
+
+/* Secrets page physical address from the CC blob */
+u64 sev_secrets_pa __ro_after_init;
+
+/* For early boot SVSM communication */
+struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+
+DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
+DEFINE_PER_CPU(u64, svsm_caa_pa);
+
+/*
+ * Nothing shall interrupt this code path while holding the per-CPU
+ * GHCB. The backup GHCB is only for NMIs interrupting this path.
+ *
+ * Callers must disable local interrupts around it.
+ */
+noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+{
+	struct sev_es_runtime_data *data;
+	struct ghcb *ghcb;
+
+	WARN_ON(!irqs_disabled());
+
+	data = this_cpu_read(runtime_data);
+	ghcb = &data->ghcb_page;
+
+	if (unlikely(data->ghcb_active)) {
+		/* GHCB is already in use - save its contents */
+
+		if (unlikely(data->backup_ghcb_active)) {
+			/*
+			 * Backup-GHCB is also already in use. There is no way
+			 * to continue here so just kill the machine. To make
+			 * panic() work, mark GHCBs inactive so that messages
+			 * can be printed out.
+			 */
+			data->ghcb_active        = false;
+			data->backup_ghcb_active = false;
+
+			instrumentation_begin();
+			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+			instrumentation_end();
+		}
+
+		/* Mark backup_ghcb active before writing to it */
+		data->backup_ghcb_active = true;
+
+		state->ghcb = &data->backup_ghcb;
+
+		/* Backup GHCB content */
+		*state->ghcb = *ghcb;
+	} else {
+		state->ghcb = NULL;
+		data->ghcb_active = true;
+	}
+
+	return ghcb;
+}
+
+/* Include code shared with pre-decompression boot stage */
+#include "sev-shared.c"
+
+noinstr void __sev_put_ghcb(struct ghcb_state *state)
+{
+	struct sev_es_runtime_data *data;
+	struct ghcb *ghcb;
+
+	WARN_ON(!irqs_disabled());
+
+	data = this_cpu_read(runtime_data);
+	ghcb = &data->ghcb_page;
+
+	if (state->ghcb) {
+		/* Restore GHCB from Backup */
+		*ghcb = *state->ghcb;
+		data->backup_ghcb_active = false;
+		state->ghcb = NULL;
+	} else {
+		/*
+		 * Invalidate the GHCB so a VMGEXIT instruction issued
+		 * from userspace won't appear to be valid.
+		 */
+		vc_ghcb_invalidate(ghcb);
+		data->ghcb_active = false;
+	}
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call)
+{
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_local_irq_save();
+
+	if (sev_cfg.ghcbs_initialized)
+		ghcb = __sev_get_ghcb(&state);
+	else if (boot_ghcb)
+		ghcb = boot_ghcb;
+	else
+		ghcb = NULL;
+
+	do {
+		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+			   : svsm_perform_msr_protocol(call);
+	} while (ret == -EAGAIN);
+
+	if (sev_cfg.ghcbs_initialized)
+		__sev_put_ghcb(&state);
+
+	native_local_irq_restore(flags);
+
+	return ret;
+}
+
+void __head
+early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+		      unsigned long npages, enum psc_op op)
+{
+	unsigned long paddr_end;
+	u64 val;
+
+	vaddr = vaddr & PAGE_MASK;
+
+	paddr = paddr & PAGE_MASK;
+	paddr_end = paddr + (npages << PAGE_SHIFT);
+
+	while (paddr < paddr_end) {
+		/* Page validation must be rescinded before changing to shared */
+		if (op == SNP_PAGE_STATE_SHARED)
+			pvalidate_4k_page(vaddr, paddr, false);
+
+		/*
+		 * Use the MSR protocol because this function can be called before
+		 * the GHCB is established.
+		 */
+		sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+		VMGEXIT();
+
+		val = sev_es_rd_ghcb_msr();
+
+		if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
+			goto e_term;
+
+		if (GHCB_MSR_PSC_RESP_VAL(val))
+			goto e_term;
+
+		/* Page validation must be performed after changing to private */
+		if (op == SNP_PAGE_STATE_PRIVATE)
+			pvalidate_4k_page(vaddr, paddr, true);
+
+		vaddr += PAGE_SIZE;
+		paddr += PAGE_SIZE;
+	}
+
+	return;
+
+e_term:
+	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+}
+
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+					 unsigned long npages)
+{
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	 /*
+	  * Ask the hypervisor to mark the memory pages as private in the RMP
+	  * table.
+	  */
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
+}
+
+void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+					unsigned long npages)
+{
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the kernel
+ * in the following ways, depending on how it is booted:
+ *
+ * - when booted via the boot/decompress kernel:
+ *   - via boot_params
+ *
+ * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
+ *   - via a setup_data entry, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+	struct cc_blob_sev_info *cc_info;
+
+	/* Boot kernel would have passed the CC blob via boot_params. */
+	if (bp->cc_blob_address) {
+		cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
+		goto found_cc_info;
+	}
+
+	/*
+	 * If kernel was booted directly, without the use of the
+	 * boot/decompression kernel, the CC blob may have been passed via
+	 * setup_data instead.
+	 */
+	cc_info = find_cc_blob_setup_data(bp);
+	if (!cc_info)
+		return NULL;
+
+found_cc_info:
+	if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+		snp_abort();
+
+	return cc_info;
+}
+
+static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
+{
+	struct svsm_call call = {};
+	int ret;
+	u64 pa;
+
+	/*
+	 * Record the SVSM Calling Area address (CAA) if the guest is not
+	 * running at VMPL0. The CA will be used to communicate with the
+	 * SVSM to perform the SVSM services.
+	 */
+	if (!svsm_setup_ca(cc_info))
+		return;
+
+	/*
+	 * It is very early in the boot and the kernel is running identity
+	 * mapped but without having adjusted the pagetables to where the
+	 * kernel was loaded (physbase), so the get the CA address using
+	 * RIP-relative addressing.
+	 */
+	pa = (u64)rip_rel_ptr(&boot_svsm_ca_page);
+
+	/*
+	 * Switch over to the boot SVSM CA while the current CA is still
+	 * addressable. There is no GHCB at this point so use the MSR protocol.
+	 *
+	 * SVSM_CORE_REMAP_CA call:
+	 *   RAX = 0 (Protocol=0, CallID=0)
+	 *   RCX = New CA GPA
+	 */
+	call.caa = svsm_get_caa();
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+	call.rcx = pa;
+	ret = svsm_perform_call_protocol(&call);
+	if (ret)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
+
+	boot_svsm_caa = (struct svsm_ca *)pa;
+	boot_svsm_caa_pa = pa;
+}
+
+bool __head snp_init(struct boot_params *bp)
+{
+	struct cc_blob_sev_info *cc_info;
+
+	if (!bp)
+		return false;
+
+	cc_info = find_cc_blob(bp);
+	if (!cc_info)
+		return false;
+
+	if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
+		sev_secrets_pa = cc_info->secrets_phys;
+	else
+		return false;
+
+	setup_cpuid_table(cc_info);
+
+	svsm_setup(cc_info);
+
+	/*
+	 * The CC blob will be used later to access the secrets page. Cache
+	 * it here like the boot kernel does.
+	 */
+	bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+	return true;
+}
+
+void __head __noreturn snp_abort(void)
+{
+	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/boot/startup/sme.c
index e6c7686f443a..70ea1748c0a7 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/boot/startup/sme.c
@@ -7,8 +7,6 @@
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  */
 
-#define DISABLE_BRANCH_PROFILING
-
 /*
  * Since we're dealing with identity mappings, physical and virtual
  * addresses are the same, so override these defines which are ultimately
@@ -47,8 +45,6 @@
 #include <asm/coco.h>
 #include <asm/sev.h>
 
-#include "mm_internal.h"
-
 #define PGD_FLAGS		_KERNPG_TABLE_NOENC
 #define P4D_FLAGS		_KERNPG_TABLE_NOENC
 #define PUD_FLAGS		_KERNPG_TABLE_NOENC
@@ -301,8 +297,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
 	 * function.
 	 */
-	if (!sme_get_me_mask() ||
-	    RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
+	if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
 		return;
 
 	/*
@@ -320,8 +315,8 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 *     memory from being cached.
 	 */
 
-	kernel_start = (unsigned long)RIP_REL_REF(_text);
-	kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
+	kernel_start = (unsigned long)rip_rel_ptr(_text);
+	kernel_end = ALIGN((unsigned long)rip_rel_ptr(_end), PMD_SIZE);
 	kernel_len = kernel_end - kernel_start;
 
 	initrd_start = 0;
@@ -347,7 +342,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 *   pagetable structures for the encryption of the kernel
 	 *   pagetable structures for workarea (in case not currently mapped)
 	 */
-	execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
+	execute_start = workarea_start = (unsigned long)rip_rel_ptr(sme_workarea);
 	execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
 	execute_len = execute_end - execute_start;
 
@@ -528,7 +523,7 @@ void __head sme_enable(struct boot_params *bp)
 	me_mask = 1UL << (ebx & 0x3f);
 
 	/* Check the SEV MSR whether SEV or SME is enabled */
-	RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+	sev_status = msr = native_rdmsrq(MSR_AMD64_SEV);
 	feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
 
 	/*
@@ -559,13 +554,22 @@ void __head sme_enable(struct boot_params *bp)
 			return;
 
 		/* For SME, check the SYSCFG MSR */
-		msr = __rdmsr(MSR_AMD64_SYSCFG);
+		msr = native_rdmsrq(MSR_AMD64_SYSCFG);
 		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			return;
 	}
 
-	RIP_REL_REF(sme_me_mask) = me_mask;
-	physical_mask &= ~me_mask;
-	cc_vendor = CC_VENDOR_AMD;
+	sme_me_mask	= me_mask;
+	physical_mask	&= ~me_mask;
+	cc_vendor	= CC_VENDOR_AMD;
 	cc_set_mask(me_mask);
 }
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+/* Local version for startup code, which never operates on user page tables */
+__weak
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 84f7a883ce1e..f35369bb14c5 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -32,7 +32,7 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb" CC_SET(nz)
+	asm("repe cmpsb" CC_SET(nz)
 	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
deleted file mode 100644
index 10311d77c67f..000000000000
--- a/arch/x86/boot/tools/build.c
+++ /dev/null
@@ -1,247 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 1997 Martin Mares
- *  Copyright (C) 2007 H. Peter Anvin
- */
-
-/*
- * This file builds a disk-image from three different files:
- *
- * - setup: 8086 machine code, sets up system parm
- * - system: 80386 code for actual system
- * - zoffset.h: header with ZO_* defines
- *
- * It does some checking that all files are of the correct type, and writes
- * the result to the specified destination, removing headers and padding to
- * the right amount. It also writes some system data to stdout.
- */
-
-/*
- * Changes by tytso to allow root device specification
- * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
- * Cross compiling fixes by Gertjan van Wingerde, July 1996
- * Rewritten by Martin Mares, April 1997
- * Substantially overhauled by H. Peter Anvin, April 2007
- */
-
-#include <stdio.h>
-#include <string.h>
-#include <stdlib.h>
-#include <stdarg.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <sys/mman.h>
-#include <tools/le_byteshift.h>
-
-typedef unsigned char  u8;
-typedef unsigned short u16;
-typedef unsigned int   u32;
-
-/* Minimal number of setup sectors */
-#define SETUP_SECT_MIN 5
-#define SETUP_SECT_MAX 64
-
-/* This must be large enough to hold the entire setup */
-u8 buf[SETUP_SECT_MAX*512];
-
-static unsigned long _edata;
-
-/*----------------------------------------------------------------------*/
-
-static const u32 crctab32[] = {
-	0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419,
-	0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4,
-	0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07,
-	0x90bf1d91, 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
-	0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856,
-	0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
-	0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4,
-	0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
-	0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3,
-	0x45df5c75, 0xdcd60dcf, 0xabd13d59, 0x26d930ac, 0x51de003a,
-	0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599,
-	0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-	0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190,
-	0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f,
-	0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e,
-	0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
-	0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed,
-	0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
-	0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3,
-	0xfbd44c65, 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
-	0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a,
-	0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5,
-	0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, 0xbe0b1010,
-	0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-	0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17,
-	0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6,
-	0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615,
-	0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
-	0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 0xf00f9344,
-	0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
-	0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a,
-	0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
-	0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1,
-	0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c,
-	0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef,
-	0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-	0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe,
-	0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31,
-	0x2cd99e8b, 0x5bdeae1d, 0x9b64c2b0, 0xec63f226, 0x756aa39c,
-	0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
-	0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b,
-	0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
-	0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1,
-	0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
-	0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 0xa00ae278,
-	0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7,
-	0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66,
-	0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-	0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605,
-	0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8,
-	0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b,
-	0x2d02ef8d
-};
-
-static u32 partial_crc32_one(u8 c, u32 crc)
-{
-	return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8);
-}
-
-static u32 partial_crc32(const u8 *s, int len, u32 crc)
-{
-	while (len--)
-		crc = partial_crc32_one(*s++, crc);
-	return crc;
-}
-
-static void die(const char * str, ...)
-{
-	va_list args;
-	va_start(args, str);
-	vfprintf(stderr, str, args);
-	va_end(args);
-	fputc('\n', stderr);
-	exit(1);
-}
-
-static void usage(void)
-{
-	die("Usage: build setup system zoffset.h image");
-}
-
-/*
- * Parse zoffset.h and find the entry points. We could just #include zoffset.h
- * but that would mean tools/build would have to be rebuilt every time. It's
- * not as if parsing it is hard...
- */
-#define PARSE_ZOFS(p, sym) do { \
-	if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym)))	\
-		sym = strtoul(p + 11 + sizeof(#sym), NULL, 16);		\
-} while (0)
-
-static void parse_zoffset(char *fname)
-{
-	FILE *file;
-	char *p;
-	int c;
-
-	file = fopen(fname, "r");
-	if (!file)
-		die("Unable to open `%s': %m", fname);
-	c = fread(buf, 1, sizeof(buf) - 1, file);
-	if (ferror(file))
-		die("read-error on `zoffset.h'");
-	fclose(file);
-	buf[c] = 0;
-
-	p = (char *)buf;
-
-	while (p && *p) {
-		PARSE_ZOFS(p, _edata);
-
-		p = strchr(p, '\n');
-		while (p && (*p == '\r' || *p == '\n'))
-			p++;
-	}
-}
-
-int main(int argc, char ** argv)
-{
-	unsigned int i, sz, setup_sectors;
-	int c;
-	struct stat sb;
-	FILE *file, *dest;
-	int fd;
-	void *kernel;
-	u32 crc = 0xffffffffUL;
-
-	if (argc != 5)
-		usage();
-	parse_zoffset(argv[3]);
-
-	dest = fopen(argv[4], "w");
-	if (!dest)
-		die("Unable to write `%s': %m", argv[4]);
-
-	/* Copy the setup code */
-	file = fopen(argv[1], "r");
-	if (!file)
-		die("Unable to open `%s': %m", argv[1]);
-	c = fread(buf, 1, sizeof(buf), file);
-	if (ferror(file))
-		die("read-error on `setup'");
-	if (c < 1024)
-		die("The setup must be at least 1024 bytes");
-	if (get_unaligned_le16(&buf[510]) != 0xAA55)
-		die("Boot block hasn't got boot flag (0xAA55)");
-	fclose(file);
-
-	/* Pad unused space with zeros */
-	setup_sectors = (c + 4095) / 4096;
-	setup_sectors *= 8;
-	if (setup_sectors < SETUP_SECT_MIN)
-		setup_sectors = SETUP_SECT_MIN;
-	i = setup_sectors*512;
-	memset(buf+c, 0, i-c);
-
-	/* Open and stat the kernel file */
-	fd = open(argv[2], O_RDONLY);
-	if (fd < 0)
-		die("Unable to open `%s': %m", argv[2]);
-	if (fstat(fd, &sb))
-		die("Unable to stat `%s': %m", argv[2]);
-	if (_edata != sb.st_size)
-		die("Unexpected file size `%s': %u != %u", argv[2], _edata,
-		    sb.st_size);
-	sz = _edata - 4;
-	kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
-	if (kernel == MAP_FAILED)
-		die("Unable to mmap '%s': %m", argv[2]);
-
-	crc = partial_crc32(buf, i, crc);
-	if (fwrite(buf, 1, i, dest) != i)
-		die("Writing setup failed");
-
-	/* Copy the kernel code */
-	crc = partial_crc32(kernel, sz, crc);
-	if (fwrite(kernel, 1, sz, dest) != sz)
-		die("Writing kernel failed");
-
-	/* Write the CRC */
-	put_unaligned_le32(crc, buf);
-	if (fwrite(buf, 1, 4, dest) != 4)
-		die("Writing CRC failed");
-
-	/* Catch any delayed write failures */
-	if (fclose(dest))
-		die("Writing image failed");
-
-	close(fd);
-
-	/* Everything is OK */
-	return 0;
-}
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index f2e96905b3fe..0641c8c46aee 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -292,7 +292,7 @@ static void restore_screen(void)
 			     "shrw %%cx ; "
 			     "jnc 1f ; "
 			     "stosw \n\t"
-			     "1: rep;stosl ; "
+			     "1: rep stosl ; "
 			     "popw %%es"
 			     : "+D" (dst), "+c" (npad)
 			     : "bdS" (video_segment),
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index 9a0ddda3aa69..d4610af68114 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,9 @@
 #include <asm/processor.h>
 
 enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
+SYM_PIC_ALIAS(cc_vendor);
 u64 cc_mask __ro_after_init;
+SYM_PIC_ALIAS(cc_mask);
 
 static struct cc_attr_flags {
 	__u64 host_sev_snp	: 1,
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index dcb06dc8b5ae..db3255b979bd 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -1,22 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y += core.o
-
-# jump tables are emitted using absolute references in non-PIC code
-# so they cannot be used in the early SEV startup code
-CFLAGS_core.o += -fno-jump-tables
-
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_core.o = -pg
-endif
-
-KASAN_SANITIZE_core.o	:= n
-KMSAN_SANITIZE_core.o	:= n
-KCOV_INSTRUMENT_core.o	:= n
-
-# With some compiler versions the generated code results in boot hangs, caused
-# by several compilation units. To be safe, disable all instrumentation.
-KCSAN_SANITIZE		:= n
+obj-y += core.o sev-nmi.o vc-handle.o
 
 # Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
-UBSAN_SANITIZE		:= n
+UBSAN_SANITIZE_sev-nmi.o	:= n
+
+# GCC may fail to respect __no_sanitize_address when inlining
+KASAN_SANITIZE_sev-nmi.o	:= n
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 82492efc5d94..fbc1215d2746 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -9,8 +9,6 @@
 
 #define pr_fmt(fmt)	"SEV: " fmt
 
-#define DISABLE_BRANCH_PROFILING
-
 #include <linux/sched/debug.h>	/* For show_regs() */
 #include <linux/percpu-defs.h>
 #include <linux/cc_platform.h>
@@ -33,6 +31,7 @@
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/sev.h>
+#include <asm/sev-internal.h>
 #include <asm/insn-eval.h>
 #include <asm/fpu/xcr.h>
 #include <asm/processor.h>
@@ -43,10 +42,9 @@
 #include <asm/smp.h>
 #include <asm/cpu.h>
 #include <asm/apic.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/cmdline.h>
-
-#define DR7_RESET_VALUE        0x400
+#include <asm/msr.h>
 
 /* AP INIT values as documented in the APM2  section "Processor Initialization State" */
 #define AP_INIT_CS_LIMIT		0xffff
@@ -83,21 +81,6 @@ static const char * const sev_status_feat_names[] = {
 	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
 };
 
-/* For early boot hypervisor communication in SEV-ES enabled guests */
-static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
-
-/*
- * Needs to be in the .data section because we need it NULL before bss is
- * cleared
- */
-static struct ghcb *boot_ghcb __section(".data");
-
-/* Bitmap of SEV features supported by the hypervisor */
-static u64 sev_hv_features __ro_after_init;
-
-/* Secrets page physical address from the CC blob */
-static u64 secrets_pa __ro_after_init;
-
 /*
  * For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and
  * initializes snp_tsc_scale and snp_tsc_offset. These values are replicated
@@ -107,558 +90,196 @@ static u64 snp_tsc_scale __ro_after_init;
 static u64 snp_tsc_offset __ro_after_init;
 static u64 snp_tsc_freq_khz __ro_after_init;
 
-/* #VC handler runtime per-CPU data */
-struct sev_es_runtime_data {
-	struct ghcb ghcb_page;
-
-	/*
-	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
-	 * It is needed when an NMI happens while the #VC handler uses the real
-	 * GHCB, and the NMI handler itself is causing another #VC exception. In
-	 * that case the GHCB content of the first handler needs to be backed up
-	 * and restored.
-	 */
-	struct ghcb backup_ghcb;
-
-	/*
-	 * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
-	 * There is no need for it to be atomic, because nothing is written to
-	 * the GHCB between the read and the write of ghcb_active. So it is safe
-	 * to use it when a nested #VC exception happens before the write.
-	 *
-	 * This is necessary for example in the #VC->NMI->#VC case when the NMI
-	 * happens while the first #VC handler uses the GHCB. When the NMI code
-	 * raises a second #VC handler it might overwrite the contents of the
-	 * GHCB written by the first handler. To avoid this the content of the
-	 * GHCB is saved and restored when the GHCB is detected to be in use
-	 * already.
-	 */
-	bool ghcb_active;
-	bool backup_ghcb_active;
-
-	/*
-	 * Cached DR7 value - write it on DR7 writes and return it on reads.
-	 * That value will never make it to the real hardware DR7 as debugging
-	 * is currently unsupported in SEV-ES guests.
-	 */
-	unsigned long dr7;
-};
-
-struct ghcb_state {
-	struct ghcb *ghcb;
-};
-
-/* For early boot SVSM communication */
-static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
-
-static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
-static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
-static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
-static DEFINE_PER_CPU(u64, svsm_caa_pa);
-
-static __always_inline bool on_vc_stack(struct pt_regs *regs)
-{
-	unsigned long sp = regs->sp;
-
-	/* User-mode RSP is not trusted */
-	if (user_mode(regs))
-		return false;
-
-	/* SYSCALL gap still has user-mode RSP */
-	if (ip_within_syscall_gap(regs))
-		return false;
-
-	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
-}
+DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
 
 /*
- * This function handles the case when an NMI is raised in the #VC
- * exception handler entry code, before the #VC handler has switched off
- * its IST stack. In this case, the IST entry for #VC must be adjusted,
- * so that any nested #VC exception will not overwrite the stack
- * contents of the interrupted #VC handler.
- *
- * The IST entry is adjusted unconditionally so that it can be also be
- * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
- * nested sev_es_ist_exit() call may adjust back the IST entry too
- * early.
- *
- * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
- * on the NMI IST stack, as they are only called from NMI handling code
- * right now.
+ * SVSM related information:
+ *   When running under an SVSM, the VMPL that Linux is executing at must be
+ *   non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
  */
-void noinstr __sev_es_ist_enter(struct pt_regs *regs)
-{
-	unsigned long old_ist, new_ist;
-
-	/* Read old IST entry */
-	new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
-
-	/*
-	 * If NMI happened while on the #VC IST stack, set the new IST
-	 * value below regs->sp, so that the interrupted stack frame is
-	 * not overwritten by subsequent #VC exceptions.
-	 */
-	if (on_vc_stack(regs))
-		new_ist = regs->sp;
-
-	/*
-	 * Reserve additional 8 bytes and store old IST value so this
-	 * adjustment can be unrolled in __sev_es_ist_exit().
-	 */
-	new_ist -= sizeof(old_ist);
-	*(unsigned long *)new_ist = old_ist;
+u8 snp_vmpl __ro_after_init;
+EXPORT_SYMBOL_GPL(snp_vmpl);
 
-	/* Set new IST entry */
-	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
-}
-
-void noinstr __sev_es_ist_exit(void)
+static u64 __init get_snp_jump_table_addr(void)
 {
-	unsigned long ist;
+	struct snp_secrets_page *secrets;
+	void __iomem *mem;
+	u64 addr;
 
-	/* Read IST entry */
-	ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+	mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+	if (!mem) {
+		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
+		return 0;
+	}
 
-	if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
-		return;
+	secrets = (__force struct snp_secrets_page *)mem;
 
-	/* Read back old IST entry and write it to the TSS */
-	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+	addr = secrets->os_area.ap_jump_table_pa;
+	iounmap(mem);
+
+	return addr;
 }
 
-/*
- * Nothing shall interrupt this code path while holding the per-CPU
- * GHCB. The backup GHCB is only for NMIs interrupting this path.
- *
- * Callers must disable local interrupts around it.
- */
-static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+static u64 __init get_jump_table_addr(void)
 {
-	struct sev_es_runtime_data *data;
+	struct ghcb_state state;
+	unsigned long flags;
 	struct ghcb *ghcb;
+	u64 ret = 0;
 
-	WARN_ON(!irqs_disabled());
-
-	data = this_cpu_read(runtime_data);
-	ghcb = &data->ghcb_page;
-
-	if (unlikely(data->ghcb_active)) {
-		/* GHCB is already in use - save its contents */
-
-		if (unlikely(data->backup_ghcb_active)) {
-			/*
-			 * Backup-GHCB is also already in use. There is no way
-			 * to continue here so just kill the machine. To make
-			 * panic() work, mark GHCBs inactive so that messages
-			 * can be printed out.
-			 */
-			data->ghcb_active        = false;
-			data->backup_ghcb_active = false;
-
-			instrumentation_begin();
-			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
-			instrumentation_end();
-		}
-
-		/* Mark backup_ghcb active before writing to it */
-		data->backup_ghcb_active = true;
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return get_snp_jump_table_addr();
 
-		state->ghcb = &data->backup_ghcb;
+	local_irq_save(flags);
 
-		/* Backup GHCB content */
-		*state->ghcb = *ghcb;
-	} else {
-		state->ghcb = NULL;
-		data->ghcb_active = true;
-	}
+	ghcb = __sev_get_ghcb(&state);
 
-	return ghcb;
-}
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
+	ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
-	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
-}
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
 
-static __always_inline void sev_es_wr_ghcb_msr(u64 val)
-{
-	u32 low, high;
+	if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
+	    ghcb_sw_exit_info_2_is_valid(ghcb))
+		ret = ghcb->save.sw_exit_info_2;
 
-	low  = (u32)(val);
-	high = (u32)(val >> 32);
+	__sev_put_ghcb(&state);
 
-	native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
-}
+	local_irq_restore(flags);
 
-static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
-				unsigned char *buffer)
-{
-	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+	return ret;
 }
 
-static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
+				    int ret, u64 svsm_ret)
 {
-	char buffer[MAX_INSN_SIZE];
-	int insn_bytes;
-
-	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
-	if (insn_bytes == 0) {
-		/* Nothing could be copied */
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
-		ctxt->fi.cr2        = ctxt->regs->ip;
-		return ES_EXCEPTION;
-	} else if (insn_bytes == -EINVAL) {
-		/* Effective RIP could not be calculated */
-		ctxt->fi.vector     = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		ctxt->fi.cr2        = 0;
-		return ES_EXCEPTION;
-	}
+	WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
+	     pfn, action, page_size, ret, svsm_ret);
 
-	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
-		return ES_DECODE_FAILED;
-
-	if (ctxt->insn.immediate.got)
-		return ES_OK;
-	else
-		return ES_DECODE_FAILED;
+	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
 }
 
-static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
 {
-	char buffer[MAX_INSN_SIZE];
-	int res, ret;
+	unsigned int page_size;
+	bool action;
+	u64 pfn;
 
-	res = vc_fetch_insn_kernel(ctxt, buffer);
-	if (res) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_INSTR;
-		ctxt->fi.cr2        = ctxt->regs->ip;
-		return ES_EXCEPTION;
-	}
+	pfn = pc->entry[pc->cur_index].pfn;
+	action = pc->entry[pc->cur_index].action;
+	page_size = pc->entry[pc->cur_index].page_size;
 
-	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
-	if (ret < 0)
-		return ES_DECODE_FAILED;
-	else
-		return ES_OK;
+	__pval_terminate(pfn, action, page_size, ret, svsm_ret);
 }
 
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+static void pval_pages(struct snp_psc_desc *desc)
 {
-	if (user_mode(ctxt->regs))
-		return __vc_decode_user_insn(ctxt);
-	else
-		return __vc_decode_kern_insn(ctxt);
-}
+	struct psc_entry *e;
+	unsigned long vaddr;
+	unsigned int size;
+	unsigned int i;
+	bool validate;
+	u64 pfn;
+	int rc;
 
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
-				   char *dst, char *buf, size_t size)
-{
-	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+	for (i = 0; i <= desc->hdr.end_entry; i++) {
+		e = &desc->entries[i];
 
-	/*
-	 * This function uses __put_user() independent of whether kernel or user
-	 * memory is accessed. This works fine because __put_user() does no
-	 * sanity checks of the pointer being accessed. All that it does is
-	 * to report when the access failed.
-	 *
-	 * Also, this function runs in atomic context, so __put_user() is not
-	 * allowed to sleep. The page-fault handler detects that it is running
-	 * in atomic context and will not try to take mmap_sem and handle the
-	 * fault, so additional pagefault_enable()/disable() calls are not
-	 * needed.
-	 *
-	 * The access can't be done via copy_to_user() here because
-	 * vc_write_mem() must not use string instructions to access unsafe
-	 * memory. The reason is that MOVS is emulated by the #VC handler by
-	 * splitting the move up into a read and a write and taking a nested #VC
-	 * exception on whatever of them is the MMIO access. Using string
-	 * instructions here would cause infinite nesting.
-	 */
-	switch (size) {
-	case 1: {
-		u8 d1;
-		u8 __user *target = (u8 __user *)dst;
-
-		memcpy(&d1, buf, 1);
-		if (__put_user(d1, target))
-			goto fault;
-		break;
-	}
-	case 2: {
-		u16 d2;
-		u16 __user *target = (u16 __user *)dst;
+		pfn = e->gfn;
+		vaddr = (unsigned long)pfn_to_kaddr(pfn);
+		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
 
-		memcpy(&d2, buf, 2);
-		if (__put_user(d2, target))
-			goto fault;
-		break;
-	}
-	case 4: {
-		u32 d4;
-		u32 __user *target = (u32 __user *)dst;
+		rc = pvalidate(vaddr, size, validate);
+		if (!rc)
+			continue;
 
-		memcpy(&d4, buf, 4);
-		if (__put_user(d4, target))
-			goto fault;
-		break;
-	}
-	case 8: {
-		u64 d8;
-		u64 __user *target = (u64 __user *)dst;
+		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
+			unsigned long vaddr_end = vaddr + PMD_SIZE;
 
-		memcpy(&d8, buf, 8);
-		if (__put_user(d8, target))
-			goto fault;
-		break;
-	}
-	default:
-		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
-		return ES_UNSUPPORTED;
+			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
+				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+				if (rc)
+					__pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
+			}
+		} else {
+			__pval_terminate(pfn, validate, size, rc, 0);
+		}
 	}
-
-	return ES_OK;
-
-fault:
-	if (user_mode(ctxt->regs))
-		error_code |= X86_PF_USER;
-
-	ctxt->fi.vector = X86_TRAP_PF;
-	ctxt->fi.error_code = error_code;
-	ctxt->fi.cr2 = (unsigned long)dst;
-
-	return ES_EXCEPTION;
 }
 
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
-				  char *src, char *buf, size_t size)
+static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
+					struct svsm_pvalidate_call *pc)
 {
-	unsigned long error_code = X86_PF_PROT;
+	struct svsm_pvalidate_entry *pe;
 
-	/*
-	 * This function uses __get_user() independent of whether kernel or user
-	 * memory is accessed. This works fine because __get_user() does no
-	 * sanity checks of the pointer being accessed. All that it does is
-	 * to report when the access failed.
-	 *
-	 * Also, this function runs in atomic context, so __get_user() is not
-	 * allowed to sleep. The page-fault handler detects that it is running
-	 * in atomic context and will not try to take mmap_sem and handle the
-	 * fault, so additional pagefault_enable()/disable() calls are not
-	 * needed.
-	 *
-	 * The access can't be done via copy_from_user() here because
-	 * vc_read_mem() must not use string instructions to access unsafe
-	 * memory. The reason is that MOVS is emulated by the #VC handler by
-	 * splitting the move up into a read and a write and taking a nested #VC
-	 * exception on whatever of them is the MMIO access. Using string
-	 * instructions here would cause infinite nesting.
-	 */
-	switch (size) {
-	case 1: {
-		u8 d1;
-		u8 __user *s = (u8 __user *)src;
-
-		if (__get_user(d1, s))
-			goto fault;
-		memcpy(buf, &d1, 1);
-		break;
-	}
-	case 2: {
-		u16 d2;
-		u16 __user *s = (u16 __user *)src;
-
-		if (__get_user(d2, s))
-			goto fault;
-		memcpy(buf, &d2, 2);
-		break;
-	}
-	case 4: {
-		u32 d4;
-		u32 __user *s = (u32 __user *)src;
-
-		if (__get_user(d4, s))
-			goto fault;
-		memcpy(buf, &d4, 4);
-		break;
-	}
-	case 8: {
-		u64 d8;
-		u64 __user *s = (u64 __user *)src;
-		if (__get_user(d8, s))
-			goto fault;
-		memcpy(buf, &d8, 8);
-		break;
-	}
-	default:
-		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
-		return ES_UNSUPPORTED;
-	}
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
 
-	return ES_OK;
+	pe = &pc->entry[0];
 
-fault:
-	if (user_mode(ctxt->regs))
-		error_code |= X86_PF_USER;
+	while (pfn < pfn_end) {
+		pe->page_size = RMP_PG_SIZE_4K;
+		pe->action    = action;
+		pe->ignore_cf = 0;
+		pe->pfn       = pfn;
 
-	ctxt->fi.vector = X86_TRAP_PF;
-	ctxt->fi.error_code = error_code;
-	ctxt->fi.cr2 = (unsigned long)src;
+		pe++;
+		pfn++;
 
-	return ES_EXCEPTION;
-}
-
-static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
-					   unsigned long vaddr, phys_addr_t *paddr)
-{
-	unsigned long va = (unsigned long)vaddr;
-	unsigned int level;
-	phys_addr_t pa;
-	pgd_t *pgd;
-	pte_t *pte;
-
-	pgd = __va(read_cr3_pa());
-	pgd = &pgd[pgd_index(va)];
-	pte = lookup_address_in_pgd(pgd, va, &level);
-	if (!pte) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.cr2        = vaddr;
-		ctxt->fi.error_code = 0;
-
-		if (user_mode(ctxt->regs))
-			ctxt->fi.error_code |= X86_PF_USER;
-
-		return ES_EXCEPTION;
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
 	}
 
-	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
-		/* Emulated MMIO to/from encrypted memory not supported */
-		return ES_UNSUPPORTED;
-
-	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
-	pa |= va & ~page_level_mask(level);
-
-	*paddr = pa;
-
-	return ES_OK;
+	return pfn;
 }
 
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
+				       struct svsm_pvalidate_call *pc)
 {
-	BUG_ON(size > 4);
-
-	if (user_mode(ctxt->regs)) {
-		struct thread_struct *t = &current->thread;
-		struct io_bitmap *iobm = t->io_bitmap;
-		size_t idx;
-
-		if (!iobm)
-			goto fault;
-
-		for (idx = port; idx < port + size; ++idx) {
-			if (test_bit(idx, iobm->bitmap))
-				goto fault;
-		}
-	}
-
-	return ES_OK;
+	struct svsm_pvalidate_entry *pe;
+	struct psc_entry *e;
 
-fault:
-	ctxt->fi.vector = X86_TRAP_GP;
-	ctxt->fi.error_code = 0;
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
 
-	return ES_EXCEPTION;
-}
+	pe = &pc->entry[0];
+	e  = &desc->entries[desc_entry];
 
-static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
-{
-	long error_code = ctxt->fi.error_code;
-	int trapnr = ctxt->fi.vector;
+	while (desc_entry <= desc->hdr.end_entry) {
+		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
+		pe->ignore_cf = 0;
+		pe->pfn       = e->gfn;
 
-	ctxt->regs->orig_ax = ctxt->fi.error_code;
+		pe++;
+		e++;
 
-	switch (trapnr) {
-	case X86_TRAP_GP:
-		exc_general_protection(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_UD:
-		exc_invalid_op(ctxt->regs);
-		break;
-	case X86_TRAP_PF:
-		write_cr2(ctxt->fi.cr2);
-		exc_page_fault(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_AC:
-		exc_alignment_check(ctxt->regs, error_code);
-		break;
-	default:
-		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
-		BUG();
+		desc_entry++;
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
 	}
-}
-
-/* Include code shared with pre-decompression boot stage */
-#include "shared.c"
-
-static inline struct svsm_ca *svsm_get_caa(void)
-{
-	/*
-	 * Use rIP-relative references when called early in the boot. If
-	 * ->use_cas is set, then it is late in the boot and no need
-	 * to worry about rIP-relative references.
-	 */
-	if (RIP_REL_REF(sev_cfg).use_cas)
-		return this_cpu_read(svsm_caa);
-	else
-		return RIP_REL_REF(boot_svsm_caa);
-}
 
-static u64 svsm_get_caa_pa(void)
-{
-	/*
-	 * Use rIP-relative references when called early in the boot. If
-	 * ->use_cas is set, then it is late in the boot and no need
-	 * to worry about rIP-relative references.
-	 */
-	if (RIP_REL_REF(sev_cfg).use_cas)
-		return this_cpu_read(svsm_caa_pa);
-	else
-		return RIP_REL_REF(boot_svsm_caa_pa);
+	return desc_entry;
 }
 
-static noinstr void __sev_put_ghcb(struct ghcb_state *state)
+static void svsm_pval_pages(struct snp_psc_desc *desc)
 {
-	struct sev_es_runtime_data *data;
-	struct ghcb *ghcb;
-
-	WARN_ON(!irqs_disabled());
-
-	data = this_cpu_read(runtime_data);
-	ghcb = &data->ghcb_page;
-
-	if (state->ghcb) {
-		/* Restore GHCB from Backup */
-		*ghcb = *state->ghcb;
-		data->backup_ghcb_active = false;
-		state->ghcb = NULL;
-	} else {
-		/*
-		 * Invalidate the GHCB so a VMGEXIT instruction issued
-		 * from userspace won't appear to be valid.
-		 */
-		vc_ghcb_invalidate(ghcb);
-		data->ghcb_active = false;
-	}
-}
-
-static int svsm_perform_call_protocol(struct svsm_call *call)
-{
-	struct ghcb_state state;
+	struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
+	unsigned int i, pv_4k_count = 0;
+	struct svsm_pvalidate_call *pc;
+	struct svsm_call call = {};
 	unsigned long flags;
-	struct ghcb *ghcb;
+	bool action;
+	u64 pc_pa;
 	int ret;
 
 	/*
@@ -668,180 +289,145 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
 	flags = native_local_irq_save();
 
 	/*
-	 * Use rip-relative references when called early in the boot. If
-	 * ghcbs_initialized is set, then it is late in the boot and no need
-	 * to worry about rip-relative references in called functions.
+	 * The SVSM calling area (CA) can support processing 510 entries at a
+	 * time. Loop through the Page State Change descriptor until the CA is
+	 * full or the last entry in the descriptor is reached, at which time
+	 * the SVSM is invoked. This repeats until all entries in the descriptor
+	 * are processed.
 	 */
-	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
-		ghcb = __sev_get_ghcb(&state);
-	else if (RIP_REL_REF(boot_ghcb))
-		ghcb = RIP_REL_REF(boot_ghcb);
-	else
-		ghcb = NULL;
+	call.caa = svsm_get_caa();
 
-	do {
-		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
-			   : svsm_perform_msr_protocol(call);
-	} while (ret == -EAGAIN);
+	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
 
-	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
-		__sev_put_ghcb(&state);
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pc_pa;
 
-	native_local_irq_restore(flags);
+	for (i = 0; i <= desc->hdr.end_entry;) {
+		i = svsm_build_ca_from_psc_desc(desc, i, pc);
 
-	return ret;
-}
+		do {
+			ret = svsm_perform_call_protocol(&call);
+			if (!ret)
+				continue;
 
-void noinstr __sev_es_nmi_complete(void)
-{
-	struct ghcb_state state;
-	struct ghcb *ghcb;
+			/*
+			 * Check if the entry failed because of an RMP mismatch (a
+			 * PVALIDATE at 2M was requested, but the page is mapped in
+			 * the RMP as 4K).
+			 */
 
-	ghcb = __sev_get_ghcb(&state);
+			if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+			    pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
+				/* Save this entry for post-processing at 4K */
+				pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
+
+				/* Skip to the next one unless at the end of the list */
+				pc->cur_index++;
+				if (pc->cur_index < pc->num_entries)
+					ret = -EAGAIN;
+				else
+					ret = 0;
+			}
+		} while (ret == -EAGAIN);
 
-	vc_ghcb_invalidate(ghcb);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
-	ghcb_set_sw_exit_info_1(ghcb, 0);
-	ghcb_set_sw_exit_info_2(ghcb, 0);
+		if (ret)
+			svsm_pval_terminate(pc, ret, call.rax_out);
+	}
 
-	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
-	VMGEXIT();
+	/* Process any entries that failed to be validated at 2M and validate them at 4K */
+	for (i = 0; i < pv_4k_count; i++) {
+		u64 pfn, pfn_end;
 
-	__sev_put_ghcb(&state);
-}
+		action  = pv_4k[i].action;
+		pfn     = pv_4k[i].pfn;
+		pfn_end = pfn + 512;
 
-static u64 __init get_snp_jump_table_addr(void)
-{
-	struct snp_secrets_page *secrets;
-	void __iomem *mem;
-	u64 addr;
+		while (pfn < pfn_end) {
+			pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
 
-	mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
-	if (!mem) {
-		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
-		return 0;
+			ret = svsm_perform_call_protocol(&call);
+			if (ret)
+				svsm_pval_terminate(pc, ret, call.rax_out);
+		}
 	}
 
-	secrets = (__force struct snp_secrets_page *)mem;
-
-	addr = secrets->os_area.ap_jump_table_pa;
-	iounmap(mem);
-
-	return addr;
+	native_local_irq_restore(flags);
 }
 
-static u64 __init get_jump_table_addr(void)
+static void pvalidate_pages(struct snp_psc_desc *desc)
 {
-	struct ghcb_state state;
-	unsigned long flags;
-	struct ghcb *ghcb;
-	u64 ret = 0;
-
-	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
-		return get_snp_jump_table_addr();
-
-	local_irq_save(flags);
+	if (snp_vmpl)
+		svsm_pval_pages(desc);
+	else
+		pval_pages(desc);
+}
 
-	ghcb = __sev_get_ghcb(&state);
+static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
+{
+	int cur_entry, end_entry, ret = 0;
+	struct snp_psc_desc *data;
+	struct es_em_ctxt ctxt;
 
 	vc_ghcb_invalidate(ghcb);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
-	ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
-	ghcb_set_sw_exit_info_2(ghcb, 0);
-
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
-
-	if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
-	    ghcb_sw_exit_info_2_is_valid(ghcb))
-		ret = ghcb->save.sw_exit_info_2;
-
-	__sev_put_ghcb(&state);
-
-	local_irq_restore(flags);
-
-	return ret;
-}
 
-static void __head
-early_set_pages_state(unsigned long vaddr, unsigned long paddr,
-		      unsigned long npages, enum psc_op op)
-{
-	unsigned long paddr_end;
-	u64 val;
+	/* Copy the input desc into GHCB shared buffer */
+	data = (struct snp_psc_desc *)ghcb->shared_buffer;
+	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
 
-	vaddr = vaddr & PAGE_MASK;
+	/*
+	 * As per the GHCB specification, the hypervisor can resume the guest
+	 * before processing all the entries. Check whether all the entries
+	 * are processed. If not, then keep retrying. Note, the hypervisor
+	 * will update the data memory directly to indicate the status, so
+	 * reference the data->hdr everywhere.
+	 *
+	 * The strategy here is to wait for the hypervisor to change the page
+	 * state in the RMP table before guest accesses the memory pages. If the
+	 * page state change was not successful, then later memory access will
+	 * result in a crash.
+	 */
+	cur_entry = data->hdr.cur_entry;
+	end_entry = data->hdr.end_entry;
 
-	paddr = paddr & PAGE_MASK;
-	paddr_end = paddr + (npages << PAGE_SHIFT);
+	while (data->hdr.cur_entry <= data->hdr.end_entry) {
+		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
 
-	while (paddr < paddr_end) {
-		/* Page validation must be rescinded before changing to shared */
-		if (op == SNP_PAGE_STATE_SHARED)
-			pvalidate_4k_page(vaddr, paddr, false);
+		/* This will advance the shared buffer data points to. */
+		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
 
 		/*
-		 * Use the MSR protocol because this function can be called before
-		 * the GHCB is established.
+		 * Page State Change VMGEXIT can pass error code through
+		 * exit_info_2.
 		 */
-		sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
-		VMGEXIT();
-
-		val = sev_es_rd_ghcb_msr();
-
-		if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
-			goto e_term;
-
-		if (GHCB_MSR_PSC_RESP_VAL(val))
-			goto e_term;
+		if (WARN(ret || ghcb->save.sw_exit_info_2,
+			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
+			 ret, ghcb->save.sw_exit_info_2)) {
+			ret = 1;
+			goto out;
+		}
 
-		/* Page validation must be performed after changing to private */
-		if (op == SNP_PAGE_STATE_PRIVATE)
-			pvalidate_4k_page(vaddr, paddr, true);
+		/* Verify that reserved bit is not set */
+		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
+			ret = 1;
+			goto out;
+		}
 
-		vaddr += PAGE_SIZE;
-		paddr += PAGE_SIZE;
+		/*
+		 * Sanity check that entry processing is not going backwards.
+		 * This will happen only if hypervisor is tricking us.
+		 */
+		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
+"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
+			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
+			ret = 1;
+			goto out;
+		}
 	}
 
-	return;
-
-e_term:
-	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-}
-
-void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
-					 unsigned long npages)
-{
-	/*
-	 * This can be invoked in early boot while running identity mapped, so
-	 * use an open coded check for SNP instead of using cc_platform_has().
-	 * This eliminates worries about jump tables or checking boot_cpu_data
-	 * in the cc_platform_has() function.
-	 */
-	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
-		return;
-
-	 /*
-	  * Ask the hypervisor to mark the memory pages as private in the RMP
-	  * table.
-	  */
-	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
-}
-
-void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
-					unsigned long npages)
-{
-	/*
-	 * This can be invoked in early boot while running identity mapped, so
-	 * use an open coded check for SNP instead of using cc_platform_has().
-	 * This eliminates worries about jump tables or checking boot_cpu_data
-	 * in the cc_platform_has() function.
-	 */
-	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
-		return;
-
-	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
-	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+out:
+	return ret;
 }
 
 static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
@@ -961,6 +547,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
+static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id)
+{
+	bool create = event != SVM_VMGEXIT_AP_DESTROY;
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret = 0;
+
+	local_irq_save(flags);
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+
+	if (create)
+		ghcb_set_rax(ghcb, vmsa->sev_features);
+
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
+	ghcb_set_sw_exit_info_1(ghcb,
+				((u64)apic_id << 32)	|
+				((u64)snp_vmpl << 16)	|
+				event);
+	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
+
+	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
+	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
+		pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY"));
+		ret = -EINVAL;
+	}
+
+	__sev_put_ghcb(&state);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
+{
+	int ret;
+
+	if (snp_vmpl) {
+		struct svsm_call call = {};
+		unsigned long flags;
+
+		local_irq_save(flags);
+
+		call.caa = this_cpu_read(svsm_caa);
+		call.rcx = __pa(va);
+
+		if (make_vmsa) {
+			/* Protocol 0, Call ID 2 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+			call.rdx = __pa(caa);
+			call.r8  = apic_id;
+		} else {
+			/* Protocol 0, Call ID 3 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+		}
+
+		ret = svsm_perform_call_protocol(&call);
+
+		local_irq_restore(flags);
+	} else {
+		/*
+		 * If the kernel runs at VMPL0, it can change the VMSA
+		 * bit for a page using the RMPADJUST instruction.
+		 * However, for the instruction to succeed it must
+		 * target the permissions of a lesser privileged (higher
+		 * numbered) VMPL level, so use VMPL1.
+		 */
+		u64 attrs = 1;
+
+		if (make_vmsa)
+			attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+	}
+
+	return ret;
+}
+
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
+{
+	int err;
+
+	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
+	if (err)
+		pr_err("clear VMSA page failed (%u), leaking page\n", err);
+	else
+		free_page((unsigned long)vmsa);
+}
+
 static void set_pte_enc(pte_t *kpte, int level, void *va)
 {
 	struct pte_enc_desc d = {
@@ -1007,7 +689,8 @@ static void unshare_all_memory(void)
 			data = per_cpu(runtime_data, cpu);
 			ghcb = (unsigned long)&data->ghcb_page;
 
-			if (addr <= ghcb && ghcb <= addr + size) {
+			/* Handle the case of a huge page containing the GHCB page */
+			if (addr <= ghcb && ghcb < addr + size) {
 				skipped_addr = true;
 				break;
 			}
@@ -1057,11 +740,70 @@ void snp_kexec_begin(void)
 		pr_warn("Failed to stop shared<->private conversions\n");
 }
 
+/*
+ * Shutdown all APs except the one handling kexec/kdump and clearing
+ * the VMSA tag on AP's VMSA pages as they are not being used as
+ * VMSA page anymore.
+ */
+static void shutdown_all_aps(void)
+{
+	struct sev_es_save_area *vmsa;
+	int apic_id, this_cpu, cpu;
+
+	this_cpu = get_cpu();
+
+	/*
+	 * APs are already in HLT loop when enc_kexec_finish() callback
+	 * is invoked.
+	 */
+	for_each_present_cpu(cpu) {
+		vmsa = per_cpu(sev_vmsa, cpu);
+
+		/*
+		 * The BSP or offlined APs do not have guest allocated VMSA
+		 * and there is no need  to clear the VMSA tag for this page.
+		 */
+		if (!vmsa)
+			continue;
+
+		/*
+		 * Cannot clear the VMSA tag for the currently running vCPU.
+		 */
+		if (this_cpu == cpu) {
+			unsigned long pa;
+			struct page *p;
+
+			pa = __pa(vmsa);
+			/*
+			 * Mark the VMSA page of the running vCPU as offline
+			 * so that is excluded and not touched by makedumpfile
+			 * while generating vmcore during kdump.
+			 */
+			p = pfn_to_online_page(pa >> PAGE_SHIFT);
+			if (p)
+				__SetPageOffline(p);
+			continue;
+		}
+
+		apic_id = cpuid_to_apicid[cpu];
+
+		/*
+		 * Issue AP destroy to ensure AP gets kicked out of guest mode
+		 * to allow using RMPADJUST to remove the VMSA tag on it's
+		 * VMSA page.
+		 */
+		vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id);
+		snp_cleanup_vmsa(vmsa, apic_id);
+	}
+
+	put_cpu();
+}
+
 void snp_kexec_finish(void)
 {
 	struct sev_es_runtime_data *data;
+	unsigned long size, addr;
 	unsigned int level, cpu;
-	unsigned long size;
 	struct ghcb *ghcb;
 	pte_t *pte;
 
@@ -1071,6 +813,8 @@ void snp_kexec_finish(void)
 	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
+	shutdown_all_aps();
+
 	unshare_all_memory();
 
 	/*
@@ -1087,54 +831,11 @@ void snp_kexec_finish(void)
 		ghcb = &data->ghcb_page;
 		pte = lookup_address((unsigned long)ghcb, &level);
 		size = page_level_size(level);
-		set_pte_enc(pte, level, (void *)ghcb);
-		snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE));
-	}
-}
-
-static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
-{
-	int ret;
-
-	if (snp_vmpl) {
-		struct svsm_call call = {};
-		unsigned long flags;
-
-		local_irq_save(flags);
-
-		call.caa = this_cpu_read(svsm_caa);
-		call.rcx = __pa(va);
-
-		if (make_vmsa) {
-			/* Protocol 0, Call ID 2 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
-			call.rdx = __pa(caa);
-			call.r8  = apic_id;
-		} else {
-			/* Protocol 0, Call ID 3 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
-		}
-
-		ret = svsm_perform_call_protocol(&call);
-
-		local_irq_restore(flags);
-	} else {
-		/*
-		 * If the kernel runs at VMPL0, it can change the VMSA
-		 * bit for a page using the RMPADJUST instruction.
-		 * However, for the instruction to succeed it must
-		 * target the permissions of a lesser privileged (higher
-		 * numbered) VMPL level, so use VMPL1.
-		 */
-		u64 attrs = 1;
-
-		if (make_vmsa)
-			attrs |= RMPADJUST_VMSA_PAGE_BIT;
-
-		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+		/* Handle the case of a huge page containing the GHCB page */
+		addr = (unsigned long)ghcb & page_level_mask(level);
+		set_pte_enc(pte, level, (void *)addr);
+		snp_set_memory_private(addr, (size / PAGE_SIZE));
 	}
-
-	return ret;
 }
 
 #define __ATTR_BASE		(SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
@@ -1168,24 +869,10 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
-{
-	int err;
-
-	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
-	if (err)
-		pr_err("clear VMSA page failed (%u), leaking page\n", err);
-	else
-		free_page((unsigned long)vmsa);
-}
-
 static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
-	struct ghcb_state state;
 	struct svsm_ca *caa;
-	unsigned long flags;
-	struct ghcb *ghcb;
 	u8 sipi_vector;
 	int cpu, ret;
 	u64 cr4;
@@ -1299,33 +986,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	}
 
 	/* Issue VMGEXIT AP Creation NAE event */
-	local_irq_save(flags);
-
-	ghcb = __sev_get_ghcb(&state);
-
-	vc_ghcb_invalidate(ghcb);
-	ghcb_set_rax(ghcb, vmsa->sev_features);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
-	ghcb_set_sw_exit_info_1(ghcb,
-				((u64)apic_id << 32)	|
-				((u64)snp_vmpl << 16)	|
-				SVM_VMGEXIT_AP_CREATE);
-	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
-
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
-
-	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
-	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
-		pr_err("SNP AP Creation error\n");
-		ret = -EINVAL;
-	}
-
-	__sev_put_ghcb(&state);
-
-	local_irq_restore(flags);
-
-	/* Perform cleanup if there was an error */
+	ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id);
 	if (ret) {
 		snp_cleanup_vmsa(vmsa, apic_id);
 		vmsa = NULL;
@@ -1419,91 +1080,6 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
 	return 0;
 }
 
-/* Writes to the SVSM CAA MSR are ignored */
-static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
-{
-	if (write)
-		return ES_OK;
-
-	regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
-	regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
-
-	return ES_OK;
-}
-
-/*
- * TSC related accesses should not exit to the hypervisor when a guest is
- * executing with Secure TSC enabled, so special handling is required for
- * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
- */
-static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
-{
-	u64 tsc;
-
-	/*
-	 * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
-	 * Terminate the SNP guest when the interception is enabled.
-	 */
-	if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
-		return ES_VMM_ERROR;
-
-	/*
-	 * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
-	 *         to return undefined values, so ignore all writes.
-	 *
-	 * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
-	 *        the value returned by rdtsc_ordered().
-	 */
-	if (write) {
-		WARN_ONCE(1, "TSC MSR writes are verboten!\n");
-		return ES_OK;
-	}
-
-	tsc = rdtsc_ordered();
-	regs->ax = lower_32_bits(tsc);
-	regs->dx = upper_32_bits(tsc);
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	enum es_result ret;
-	bool write;
-
-	/* Is it a WRMSR? */
-	write = ctxt->insn.opcode.bytes[1] == 0x30;
-
-	switch (regs->cx) {
-	case MSR_SVSM_CAA:
-		return __vc_handle_msr_caa(regs, write);
-	case MSR_IA32_TSC:
-	case MSR_AMD64_GUEST_TSC_FREQ:
-		if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
-			return __vc_handle_secure_tsc_msrs(regs, write);
-		else
-			break;
-	default:
-		break;
-	}
-
-	ghcb_set_rcx(ghcb, regs->cx);
-	if (write) {
-		ghcb_set_rax(ghcb, regs->ax);
-		ghcb_set_rdx(ghcb, regs->dx);
-	}
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
-
-	if ((ret == ES_OK) && !write) {
-		regs->ax = ghcb->save.rax;
-		regs->dx = ghcb->save.rdx;
-	}
-
-	return ret;
-}
-
 static void snp_register_per_cpu_ghcb(void)
 {
 	struct sev_es_runtime_data *data;
@@ -1716,748 +1292,6 @@ void __init sev_es_init_vc_handling(void)
 	initial_vc_handler = (unsigned long)kernel_exc_vmm_communication;
 }
 
-static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
-{
-	int trapnr = ctxt->fi.vector;
-
-	if (trapnr == X86_TRAP_PF)
-		native_write_cr2(ctxt->fi.cr2);
-
-	ctxt->regs->orig_ax = ctxt->fi.error_code;
-	do_early_exception(ctxt->regs, trapnr);
-}
-
-static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
-{
-	long *reg_array;
-	int offset;
-
-	reg_array = (long *)ctxt->regs;
-	offset    = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
-
-	if (offset < 0)
-		return NULL;
-
-	offset /= sizeof(long);
-
-	return reg_array + offset;
-}
-static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
-				 unsigned int bytes, bool read)
-{
-	u64 exit_code, exit_info_1, exit_info_2;
-	unsigned long ghcb_pa = __pa(ghcb);
-	enum es_result res;
-	phys_addr_t paddr;
-	void __user *ref;
-
-	ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
-	if (ref == (void __user *)-1L)
-		return ES_UNSUPPORTED;
-
-	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
-
-	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
-	if (res != ES_OK) {
-		if (res == ES_EXCEPTION && !read)
-			ctxt->fi.error_code |= X86_PF_WRITE;
-
-		return res;
-	}
-
-	exit_info_1 = paddr;
-	/* Can never be greater than 8 */
-	exit_info_2 = bytes;
-
-	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
-
-	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
-}
-
-/*
- * The MOVS instruction has two memory operands, which raises the
- * problem that it is not known whether the access to the source or the
- * destination caused the #VC exception (and hence whether an MMIO read
- * or write operation needs to be emulated).
- *
- * Instead of playing games with walking page-tables and trying to guess
- * whether the source or destination is an MMIO range, split the move
- * into two operations, a read and a write with only one memory operand.
- * This will cause a nested #VC exception on the MMIO address which can
- * then be handled.
- *
- * This implementation has the benefit that it also supports MOVS where
- * source _and_ destination are MMIO regions.
- *
- * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
- * rare operation. If it turns out to be a performance problem the split
- * operations can be moved to memcpy_fromio() and memcpy_toio().
- */
-static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
-					  unsigned int bytes)
-{
-	unsigned long ds_base, es_base;
-	unsigned char *src, *dst;
-	unsigned char buffer[8];
-	enum es_result ret;
-	bool rep;
-	int off;
-
-	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
-	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
-	if (ds_base == -1L || es_base == -1L) {
-		ctxt->fi.vector = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		return ES_EXCEPTION;
-	}
-
-	src = ds_base + (unsigned char *)ctxt->regs->si;
-	dst = es_base + (unsigned char *)ctxt->regs->di;
-
-	ret = vc_read_mem(ctxt, src, buffer, bytes);
-	if (ret != ES_OK)
-		return ret;
-
-	ret = vc_write_mem(ctxt, dst, buffer, bytes);
-	if (ret != ES_OK)
-		return ret;
-
-	if (ctxt->regs->flags & X86_EFLAGS_DF)
-		off = -bytes;
-	else
-		off =  bytes;
-
-	ctxt->regs->si += off;
-	ctxt->regs->di += off;
-
-	rep = insn_has_rep_prefix(&ctxt->insn);
-	if (rep)
-		ctxt->regs->cx -= 1;
-
-	if (!rep || ctxt->regs->cx == 0)
-		return ES_OK;
-	else
-		return ES_RETRY;
-}
-
-static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct insn *insn = &ctxt->insn;
-	enum insn_mmio_type mmio;
-	unsigned int bytes = 0;
-	enum es_result ret;
-	u8 sign_byte;
-	long *reg_data;
-
-	mmio = insn_decode_mmio(insn, &bytes);
-	if (mmio == INSN_MMIO_DECODE_FAILED)
-		return ES_DECODE_FAILED;
-
-	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
-		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
-		if (!reg_data)
-			return ES_DECODE_FAILED;
-	}
-
-	if (user_mode(ctxt->regs))
-		return ES_UNSUPPORTED;
-
-	switch (mmio) {
-	case INSN_MMIO_WRITE:
-		memcpy(ghcb->shared_buffer, reg_data, bytes);
-		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
-		break;
-	case INSN_MMIO_WRITE_IMM:
-		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
-		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
-		break;
-	case INSN_MMIO_READ:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		/* Zero-extend for 32-bit operation */
-		if (bytes == 4)
-			*reg_data = 0;
-
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_READ_ZERO_EXTEND:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		/* Zero extend based on operand size */
-		memset(reg_data, 0, insn->opnd_bytes);
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_READ_SIGN_EXTEND:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		if (bytes == 1) {
-			u8 *val = (u8 *)ghcb->shared_buffer;
-
-			sign_byte = (*val & 0x80) ? 0xff : 0x00;
-		} else {
-			u16 *val = (u16 *)ghcb->shared_buffer;
-
-			sign_byte = (*val & 0x8000) ? 0xff : 0x00;
-		}
-
-		/* Sign extend based on operand size */
-		memset(reg_data, sign_byte, insn->opnd_bytes);
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_MOVS:
-		ret = vc_handle_mmio_movs(ctxt, bytes);
-		break;
-	default:
-		ret = ES_UNSUPPORTED;
-		break;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt)
-{
-	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
-	long val, *reg = vc_insn_get_rm(ctxt);
-	enum es_result ret;
-
-	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
-		return ES_VMM_ERROR;
-
-	if (!reg)
-		return ES_DECODE_FAILED;
-
-	val = *reg;
-
-	/* Upper 32 bits must be written as zeroes */
-	if (val >> 32) {
-		ctxt->fi.vector = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		return ES_EXCEPTION;
-	}
-
-	/* Clear out other reserved bits and set bit 10 */
-	val = (val & 0xffff23ffL) | BIT(10);
-
-	/* Early non-zero writes to DR7 are not supported */
-	if (!data && (val & ~DR7_RESET_VALUE))
-		return ES_UNSUPPORTED;
-
-	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
-	ghcb_set_rax(ghcb, val);
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (data)
-		data->dr7 = val;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
-					 struct es_em_ctxt *ctxt)
-{
-	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
-	long *reg = vc_insn_get_rm(ctxt);
-
-	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
-		return ES_VMM_ERROR;
-
-	if (!reg)
-		return ES_DECODE_FAILED;
-
-	if (data)
-		*reg = data->dr7;
-	else
-		*reg = DR7_RESET_VALUE;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
-				       struct es_em_ctxt *ctxt)
-{
-	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
-}
-
-static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	enum es_result ret;
-
-	ghcb_set_rcx(ghcb, ctxt->regs->cx);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-	ctxt->regs->dx = ghcb->save.rdx;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_monitor(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	/*
-	 * Treat it as a NOP and do not leak a physical address to the
-	 * hypervisor.
-	 */
-	return ES_OK;
-}
-
-static enum es_result vc_handle_mwait(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt)
-{
-	/* Treat the same as MONITOR/MONITORX */
-	return ES_OK;
-}
-
-static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	enum es_result ret;
-
-	ghcb_set_rax(ghcb, ctxt->regs->ax);
-	ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
-
-	if (x86_platform.hyper.sev_es_hcall_prepare)
-		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!ghcb_rax_is_valid(ghcb))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-
-	/*
-	 * Call sev_es_hcall_finish() after regs->ax is already set.
-	 * This allows the hypervisor handler to overwrite it again if
-	 * necessary.
-	 */
-	if (x86_platform.hyper.sev_es_hcall_finish &&
-	    !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
-		return ES_VMM_ERROR;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	/*
-	 * Calling ecx_alignment_check() directly does not work, because it
-	 * enables IRQs and the GHCB is active. Forward the exception and call
-	 * it later from vc_forward_exception().
-	 */
-	ctxt->fi.vector = X86_TRAP_AC;
-	ctxt->fi.error_code = 0;
-	return ES_EXCEPTION;
-}
-
-static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
-					 struct ghcb *ghcb,
-					 unsigned long exit_code)
-{
-	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
-
-	if (result != ES_OK)
-		return result;
-
-	switch (exit_code) {
-	case SVM_EXIT_READ_DR7:
-		result = vc_handle_dr7_read(ghcb, ctxt);
-		break;
-	case SVM_EXIT_WRITE_DR7:
-		result = vc_handle_dr7_write(ghcb, ctxt);
-		break;
-	case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
-		result = vc_handle_trap_ac(ghcb, ctxt);
-		break;
-	case SVM_EXIT_RDTSC:
-	case SVM_EXIT_RDTSCP:
-		result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
-		break;
-	case SVM_EXIT_RDPMC:
-		result = vc_handle_rdpmc(ghcb, ctxt);
-		break;
-	case SVM_EXIT_INVD:
-		pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
-		result = ES_UNSUPPORTED;
-		break;
-	case SVM_EXIT_CPUID:
-		result = vc_handle_cpuid(ghcb, ctxt);
-		break;
-	case SVM_EXIT_IOIO:
-		result = vc_handle_ioio(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MSR:
-		result = vc_handle_msr(ghcb, ctxt);
-		break;
-	case SVM_EXIT_VMMCALL:
-		result = vc_handle_vmmcall(ghcb, ctxt);
-		break;
-	case SVM_EXIT_WBINVD:
-		result = vc_handle_wbinvd(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MONITOR:
-		result = vc_handle_monitor(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MWAIT:
-		result = vc_handle_mwait(ghcb, ctxt);
-		break;
-	case SVM_EXIT_NPF:
-		result = vc_handle_mmio(ghcb, ctxt);
-		break;
-	default:
-		/*
-		 * Unexpected #VC exception
-		 */
-		result = ES_UNSUPPORTED;
-	}
-
-	return result;
-}
-
-static __always_inline bool is_vc2_stack(unsigned long sp)
-{
-	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
-}
-
-static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
-{
-	unsigned long sp, prev_sp;
-
-	sp      = (unsigned long)regs;
-	prev_sp = regs->sp;
-
-	/*
-	 * If the code was already executing on the VC2 stack when the #VC
-	 * happened, let it proceed to the normal handling routine. This way the
-	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
-	 */
-	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
-}
-
-static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
-{
-	struct ghcb_state state;
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-	struct ghcb *ghcb;
-	bool ret = true;
-
-	ghcb = __sev_get_ghcb(&state);
-
-	vc_ghcb_invalidate(ghcb);
-	result = vc_init_em_ctxt(&ctxt, regs, error_code);
-
-	if (result == ES_OK)
-		result = vc_handle_exitcode(&ctxt, ghcb, error_code);
-
-	__sev_put_ghcb(&state);
-
-	/* Done - now check the result */
-	switch (result) {
-	case ES_OK:
-		vc_finish_insn(&ctxt);
-		break;
-	case ES_UNSUPPORTED:
-		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_VMM_ERROR:
-		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_DECODE_FAILED:
-		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_EXCEPTION:
-		vc_forward_exception(&ctxt);
-		break;
-	case ES_RETRY:
-		/* Nothing to do */
-		break;
-	default:
-		pr_emerg("Unknown result in %s():%d\n", __func__, result);
-		/*
-		 * Emulating the instruction which caused the #VC exception
-		 * failed - can't continue so print debug information
-		 */
-		BUG();
-	}
-
-	return ret;
-}
-
-static __always_inline bool vc_is_db(unsigned long error_code)
-{
-	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
-}
-
-/*
- * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
- * and will panic when an error happens.
- */
-DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
-{
-	irqentry_state_t irq_state;
-
-	/*
-	 * With the current implementation it is always possible to switch to a
-	 * safe stack because #VC exceptions only happen at known places, like
-	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
-	 * also happen with code instrumentation when the hypervisor intercepts
-	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
-	 * exceptions currently also only happen in safe places.
-	 *
-	 * But keep this here in case the noinstr annotations are violated due
-	 * to bug elsewhere.
-	 */
-	if (unlikely(vc_from_invalid_context(regs))) {
-		instrumentation_begin();
-		panic("Can't handle #VC exception from unsupported context\n");
-		instrumentation_end();
-	}
-
-	/*
-	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
-	 */
-	if (vc_is_db(error_code)) {
-		exc_debug(regs);
-		return;
-	}
-
-	irq_state = irqentry_nmi_enter(regs);
-
-	instrumentation_begin();
-
-	if (!vc_raw_handle_exception(regs, error_code)) {
-		/* Show some debug info */
-		show_regs(regs);
-
-		/* Ask hypervisor to sev_es_terminate */
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
-		/* If that fails and we get here - just panic */
-		panic("Returned from Terminate-Request to Hypervisor\n");
-	}
-
-	instrumentation_end();
-	irqentry_nmi_exit(regs, irq_state);
-}
-
-/*
- * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
- * and will kill the current task with SIGBUS when an error happens.
- */
-DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
-{
-	/*
-	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
-	 */
-	if (vc_is_db(error_code)) {
-		noist_exc_debug(regs);
-		return;
-	}
-
-	irqentry_enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	if (!vc_raw_handle_exception(regs, error_code)) {
-		/*
-		 * Do not kill the machine if user-space triggered the
-		 * exception. Send SIGBUS instead and let user-space deal with
-		 * it.
-		 */
-		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
-	}
-
-	instrumentation_end();
-	irqentry_exit_to_user_mode(regs);
-}
-
-bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
-{
-	unsigned long exit_code = regs->orig_ax;
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-
-	vc_ghcb_invalidate(boot_ghcb);
-
-	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
-	if (result == ES_OK)
-		result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
-
-	/* Done - now check the result */
-	switch (result) {
-	case ES_OK:
-		vc_finish_insn(&ctxt);
-		break;
-	case ES_UNSUPPORTED:
-		early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_VMM_ERROR:
-		early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_DECODE_FAILED:
-		early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_EXCEPTION:
-		vc_early_forward_exception(&ctxt);
-		break;
-	case ES_RETRY:
-		/* Nothing to do */
-		break;
-	default:
-		BUG();
-	}
-
-	return true;
-
-fail:
-	show_regs(regs);
-
-	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
-/*
- * Initial set up of SNP relies on information provided by the
- * Confidential Computing blob, which can be passed to the kernel
- * in the following ways, depending on how it is booted:
- *
- * - when booted via the boot/decompress kernel:
- *   - via boot_params
- *
- * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
- *   - via a setup_data entry, as defined by the Linux Boot Protocol
- *
- * Scan for the blob in that order.
- */
-static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
-{
-	struct cc_blob_sev_info *cc_info;
-
-	/* Boot kernel would have passed the CC blob via boot_params. */
-	if (bp->cc_blob_address) {
-		cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
-		goto found_cc_info;
-	}
-
-	/*
-	 * If kernel was booted directly, without the use of the
-	 * boot/decompression kernel, the CC blob may have been passed via
-	 * setup_data instead.
-	 */
-	cc_info = find_cc_blob_setup_data(bp);
-	if (!cc_info)
-		return NULL;
-
-found_cc_info:
-	if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
-		snp_abort();
-
-	return cc_info;
-}
-
-static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
-{
-	struct svsm_call call = {};
-	int ret;
-	u64 pa;
-
-	/*
-	 * Record the SVSM Calling Area address (CAA) if the guest is not
-	 * running at VMPL0. The CA will be used to communicate with the
-	 * SVSM to perform the SVSM services.
-	 */
-	if (!svsm_setup_ca(cc_info))
-		return;
-
-	/*
-	 * It is very early in the boot and the kernel is running identity
-	 * mapped but without having adjusted the pagetables to where the
-	 * kernel was loaded (physbase), so the get the CA address using
-	 * RIP-relative addressing.
-	 */
-	pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);
-
-	/*
-	 * Switch over to the boot SVSM CA while the current CA is still
-	 * addressable. There is no GHCB at this point so use the MSR protocol.
-	 *
-	 * SVSM_CORE_REMAP_CA call:
-	 *   RAX = 0 (Protocol=0, CallID=0)
-	 *   RCX = New CA GPA
-	 */
-	call.caa = svsm_get_caa();
-	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
-	call.rcx = pa;
-	ret = svsm_perform_call_protocol(&call);
-	if (ret)
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
-
-	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
-	RIP_REL_REF(boot_svsm_caa_pa) = pa;
-}
-
-bool __head snp_init(struct boot_params *bp)
-{
-	struct cc_blob_sev_info *cc_info;
-
-	if (!bp)
-		return false;
-
-	cc_info = find_cc_blob(bp);
-	if (!cc_info)
-		return false;
-
-	if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
-		secrets_pa = cc_info->secrets_phys;
-	else
-		return false;
-
-	setup_cpuid_table(cc_info);
-
-	svsm_setup(cc_info);
-
-	/*
-	 * The CC blob will be used later to access the secrets page. Cache
-	 * it here like the boot kernel does.
-	 */
-	bp->cc_blob_address = (u32)(unsigned long)cc_info;
-
-	return true;
-}
-
-void __head __noreturn snp_abort(void)
-{
-	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
-}
-
 /*
  * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
  * enabled, as the alternative (fallback) logic for DMI probing in the legacy
@@ -2628,11 +1462,74 @@ e_restore_irq:
 	return ret;
 }
 
+/**
+ * snp_svsm_vtpm_probe() - Probe if SVSM provides a vTPM device
+ *
+ * Check that there is SVSM and that it supports at least TPM_SEND_COMMAND
+ * which is the only request used so far.
+ *
+ * Return: true if the platform provides a vTPM SVSM device, false otherwise.
+ */
+static bool snp_svsm_vtpm_probe(void)
+{
+	struct svsm_call call = {};
+
+	/* The vTPM device is available only if a SVSM is present */
+	if (!snp_vmpl)
+		return false;
+
+	call.caa = svsm_get_caa();
+	call.rax = SVSM_VTPM_CALL(SVSM_VTPM_QUERY);
+
+	if (svsm_perform_call_protocol(&call))
+		return false;
+
+	/* Check platform commands contains TPM_SEND_COMMAND - platform command 8 */
+	return call.rcx_out & BIT_ULL(8);
+}
+
+/**
+ * snp_svsm_vtpm_send_command() - Execute a vTPM operation on SVSM
+ * @buffer: A buffer used to both send the command and receive the response.
+ *
+ * Execute a SVSM_VTPM_CMD call as defined by
+ * "Secure VM Service Module for SEV-SNP Guests" Publication # 58019 Revision: 1.00
+ *
+ * All command request/response buffers have a common structure as specified by
+ * the following table:
+ *     Byte      Size       In/Out    Description
+ *     Offset    (Bytes)
+ *     0x000     4          In        Platform command
+ *                          Out       Platform command response size
+ *
+ * Each command can build upon this common request/response structure to create
+ * a structure specific to the command. See include/linux/tpm_svsm.h for more
+ * details.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int snp_svsm_vtpm_send_command(u8 *buffer)
+{
+	struct svsm_call call = {};
+
+	call.caa = svsm_get_caa();
+	call.rax = SVSM_VTPM_CALL(SVSM_VTPM_CMD);
+	call.rcx = __pa(buffer);
+
+	return svsm_perform_call_protocol(&call);
+}
+EXPORT_SYMBOL_GPL(snp_svsm_vtpm_send_command);
+
 static struct platform_device sev_guest_device = {
 	.name		= "sev-guest",
 	.id		= -1,
 };
 
+static struct platform_device tpm_svsm_device = {
+	.name		= "tpm-svsm",
+	.id		= -1,
+};
+
 static int __init snp_init_platform_device(void)
 {
 	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
@@ -2641,7 +1538,11 @@ static int __init snp_init_platform_device(void)
 	if (platform_device_register(&sev_guest_device))
 		return -ENODEV;
 
-	pr_info("SNP guest platform device initialized.\n");
+	if (snp_svsm_vtpm_probe() &&
+	    platform_device_register(&tpm_svsm_device))
+		return -ENODEV;
+
+	pr_info("SNP guest platform devices initialized.\n");
 	return 0;
 }
 device_initcall(snp_init_platform_device);
@@ -2838,7 +1739,7 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc)
 		return ERR_PTR(-ENOMEM);
 
-	mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
+	mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
 	if (!mem)
 		goto e_free_mdesc;
 
@@ -2853,19 +1754,8 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc->response)
 		goto e_free_request;
 
-	mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE);
-	if (!mdesc->certs_data)
-		goto e_free_response;
-
-	/* initial the input address for guest request */
-	mdesc->input.req_gpa = __pa(mdesc->request);
-	mdesc->input.resp_gpa = __pa(mdesc->response);
-	mdesc->input.data_gpa = __pa(mdesc->certs_data);
-
 	return mdesc;
 
-e_free_response:
-	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 e_free_request:
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
 e_unmap:
@@ -2885,7 +1775,6 @@ void snp_msg_free(struct snp_msg_desc *mdesc)
 	kfree(mdesc->ctx);
 	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
-	free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE);
 	iounmap((__force void __iomem *)mdesc->secrets);
 
 	memset(mdesc, 0, sizeof(*mdesc));
@@ -3054,7 +1943,7 @@ retry_request:
 	 * sequence number must be incremented or the VMPCK must be deleted to
 	 * prevent reuse of the IV.
 	 */
-	rc = snp_issue_guest_request(req, &mdesc->input, rio);
+	rc = snp_issue_guest_request(req, &req->input, rio);
 	switch (rc) {
 	case -ENOSPC:
 		/*
@@ -3064,7 +1953,7 @@ retry_request:
 		 * order to increment the sequence number and thus avoid
 		 * IV reuse.
 		 */
-		override_npages = mdesc->input.data_npages;
+		override_npages = req->input.data_npages;
 		req->exit_code	= SVM_VMGEXIT_GUEST_REQUEST;
 
 		/*
@@ -3120,7 +2009,7 @@ retry_request:
 	}
 
 	if (override_npages)
-		mdesc->input.data_npages = override_npages;
+		req->input.data_npages = override_npages;
 
 	return rc;
 }
@@ -3158,6 +2047,11 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
 	 */
 	memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request));
 
+	/* Initialize the input address for guest request */
+	req->input.req_gpa = __pa(mdesc->request);
+	req->input.resp_gpa = __pa(mdesc->response);
+	req->input.data_gpa = req->certs_data ? __pa(req->certs_data) : 0;
+
 	rc = __handle_guest_request(mdesc, req, rio);
 	if (rc) {
 		if (rc == -EIO &&
@@ -3288,7 +2182,7 @@ void __init snp_secure_tsc_init(void)
 		return;
 
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	rdmsrl(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
+	rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
 	snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000);
 
 	x86_platform.calibrate_cpu = securetsc_get_tsc_khz;
diff --git a/arch/x86/coco/sev/sev-nmi.c b/arch/x86/coco/sev/sev-nmi.c
new file mode 100644
index 000000000000..d8dfaddfb367
--- /dev/null
+++ b/arch/x86/coco/sev/sev-nmi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/msr.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
+{
+	unsigned long sp = regs->sp;
+
+	/* User-mode RSP is not trusted */
+	if (user_mode(regs))
+		return false;
+
+	/* SYSCALL gap still has user-mode RSP */
+	if (ip_within_syscall_gap(regs))
+		return false;
+
+	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
+}
+
+/*
+ * This function handles the case when an NMI is raised in the #VC
+ * exception handler entry code, before the #VC handler has switched off
+ * its IST stack. In this case, the IST entry for #VC must be adjusted,
+ * so that any nested #VC exception will not overwrite the stack
+ * contents of the interrupted #VC handler.
+ *
+ * The IST entry is adjusted unconditionally so that it can be also be
+ * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
+ * nested sev_es_ist_exit() call may adjust back the IST entry too
+ * early.
+ *
+ * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
+ * on the NMI IST stack, as they are only called from NMI handling code
+ * right now.
+ */
+void noinstr __sev_es_ist_enter(struct pt_regs *regs)
+{
+	unsigned long old_ist, new_ist;
+
+	/* Read old IST entry */
+	new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+	/*
+	 * If NMI happened while on the #VC IST stack, set the new IST
+	 * value below regs->sp, so that the interrupted stack frame is
+	 * not overwritten by subsequent #VC exceptions.
+	 */
+	if (on_vc_stack(regs))
+		new_ist = regs->sp;
+
+	/*
+	 * Reserve additional 8 bytes and store old IST value so this
+	 * adjustment can be unrolled in __sev_es_ist_exit().
+	 */
+	new_ist -= sizeof(old_ist);
+	*(unsigned long *)new_ist = old_ist;
+
+	/* Set new IST entry */
+	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
+}
+
+void noinstr __sev_es_ist_exit(void)
+{
+	unsigned long ist;
+
+	/* Read IST entry */
+	ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+	if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
+		return;
+
+	/* Read back old IST entry and write it to the TSS */
+	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+}
+
+void noinstr __sev_es_nmi_complete(void)
+{
+	struct ghcb_state state;
+	struct ghcb *ghcb;
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
+	ghcb_set_sw_exit_info_1(ghcb, 0);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
+
+	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
+	VMGEXIT();
+
+	__sev_put_ghcb(&state);
+}
diff --git a/arch/x86/coco/sev/vc-handle.c b/arch/x86/coco/sev/vc-handle.c
new file mode 100644
index 000000000000..0989d98da130
--- /dev/null
+++ b/arch/x86/coco/sev/vc-handle.c
@@ -0,0 +1,1061 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/sched/debug.h>	/* For show_regs() */
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid/api.h>
+
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+					   unsigned long vaddr, phys_addr_t *paddr)
+{
+	unsigned long va = (unsigned long)vaddr;
+	unsigned int level;
+	phys_addr_t pa;
+	pgd_t *pgd;
+	pte_t *pte;
+
+	pgd = __va(read_cr3_pa());
+	pgd = &pgd[pgd_index(va)];
+	pte = lookup_address_in_pgd(pgd, va, &level);
+	if (!pte) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.cr2        = vaddr;
+		ctxt->fi.error_code = 0;
+
+		if (user_mode(ctxt->regs))
+			ctxt->fi.error_code |= X86_PF_USER;
+
+		return ES_EXCEPTION;
+	}
+
+	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+		/* Emulated MMIO to/from encrypted memory not supported */
+		return ES_UNSUPPORTED;
+
+	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
+	pa |= va & ~page_level_mask(level);
+
+	*paddr = pa;
+
+	return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	BUG_ON(size > 4);
+
+	if (user_mode(ctxt->regs)) {
+		struct thread_struct *t = &current->thread;
+		struct io_bitmap *iobm = t->io_bitmap;
+		size_t idx;
+
+		if (!iobm)
+			goto fault;
+
+		for (idx = port; idx < port + size; ++idx) {
+			if (test_bit(idx, iobm->bitmap))
+				goto fault;
+		}
+	}
+
+	return ES_OK;
+
+fault:
+	ctxt->fi.vector = X86_TRAP_GP;
+	ctxt->fi.error_code = 0;
+
+	return ES_EXCEPTION;
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt)
+{
+	long error_code = ctxt->fi.error_code;
+	int trapnr = ctxt->fi.vector;
+
+	ctxt->regs->orig_ax = ctxt->fi.error_code;
+
+	switch (trapnr) {
+	case X86_TRAP_GP:
+		exc_general_protection(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_UD:
+		exc_invalid_op(ctxt->regs);
+		break;
+	case X86_TRAP_PF:
+		write_cr2(ctxt->fi.cr2);
+		exc_page_fault(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_AC:
+		exc_alignment_check(ctxt->regs, error_code);
+		break;
+	default:
+		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
+		BUG();
+	}
+}
+
+static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
+				unsigned char *buffer)
+{
+	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+}
+
+static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int insn_bytes;
+
+	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+	if (insn_bytes == 0) {
+		/* Nothing could be copied */
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
+	} else if (insn_bytes == -EINVAL) {
+		/* Effective RIP could not be calculated */
+		ctxt->fi.vector     = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		ctxt->fi.cr2        = 0;
+		return ES_EXCEPTION;
+	}
+
+	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
+		return ES_DECODE_FAILED;
+
+	if (ctxt->insn.immediate.got)
+		return ES_OK;
+	else
+		return ES_DECODE_FAILED;
+}
+
+static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int res, ret;
+
+	res = vc_fetch_insn_kernel(ctxt, buffer);
+	if (res) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
+	}
+
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
+	else
+		return ES_OK;
+}
+
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	if (user_mode(ctxt->regs))
+		return __vc_decode_user_insn(ctxt);
+	else
+		return __vc_decode_kern_insn(ctxt);
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+				   char *dst, char *buf, size_t size)
+{
+	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+
+	/*
+	 * This function uses __put_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __put_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __put_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_to_user() here because
+	 * vc_write_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
+	switch (size) {
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
+		memcpy(&d1, buf, 1);
+		if (__put_user(d1, target))
+			goto fault;
+		break;
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
+		memcpy(&d2, buf, 2);
+		if (__put_user(d2, target))
+			goto fault;
+		break;
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
+		memcpy(&d4, buf, 4);
+		if (__put_user(d4, target))
+			goto fault;
+		break;
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
+		memcpy(&d8, buf, 8);
+		if (__put_user(d8, target))
+			goto fault;
+		break;
+	}
+	default:
+		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+		return ES_UNSUPPORTED;
+	}
+
+	return ES_OK;
+
+fault:
+	if (user_mode(ctxt->regs))
+		error_code |= X86_PF_USER;
+
+	ctxt->fi.vector = X86_TRAP_PF;
+	ctxt->fi.error_code = error_code;
+	ctxt->fi.cr2 = (unsigned long)dst;
+
+	return ES_EXCEPTION;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+				  char *src, char *buf, size_t size)
+{
+	unsigned long error_code = X86_PF_PROT;
+
+	/*
+	 * This function uses __get_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __get_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __get_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_from_user() here because
+	 * vc_read_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
+	switch (size) {
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
+		if (__get_user(d1, s))
+			goto fault;
+		memcpy(buf, &d1, 1);
+		break;
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
+		if (__get_user(d2, s))
+			goto fault;
+		memcpy(buf, &d2, 2);
+		break;
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
+		if (__get_user(d4, s))
+			goto fault;
+		memcpy(buf, &d4, 4);
+		break;
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
+		if (__get_user(d8, s))
+			goto fault;
+		memcpy(buf, &d8, 8);
+		break;
+	}
+	default:
+		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+		return ES_UNSUPPORTED;
+	}
+
+	return ES_OK;
+
+fault:
+	if (user_mode(ctxt->regs))
+		error_code |= X86_PF_USER;
+
+	ctxt->fi.vector = X86_TRAP_PF;
+	ctxt->fi.error_code = error_code;
+	ctxt->fi.cr2 = (unsigned long)src;
+
+	return ES_EXCEPTION;
+}
+
+#define sev_printk(fmt, ...)		printk(fmt, ##__VA_ARGS__)
+
+#include "vc-shared.c"
+
+/* Writes to the SVSM CAA MSR are ignored */
+static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
+{
+	if (write)
+		return ES_OK;
+
+	regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
+	regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
+
+	return ES_OK;
+}
+
+/*
+ * TSC related accesses should not exit to the hypervisor when a guest is
+ * executing with Secure TSC enabled, so special handling is required for
+ * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
+ */
+static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
+{
+	u64 tsc;
+
+	/*
+	 * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
+	 * Terminate the SNP guest when the interception is enabled.
+	 */
+	if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
+		return ES_VMM_ERROR;
+
+	/*
+	 * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
+	 *         to return undefined values, so ignore all writes.
+	 *
+	 * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
+	 *        the value returned by rdtsc_ordered().
+	 */
+	if (write) {
+		WARN_ONCE(1, "TSC MSR writes are verboten!\n");
+		return ES_OK;
+	}
+
+	tsc = rdtsc_ordered();
+	regs->ax = lower_32_bits(tsc);
+	regs->dx = upper_32_bits(tsc);
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	enum es_result ret;
+	bool write;
+
+	/* Is it a WRMSR? */
+	write = ctxt->insn.opcode.bytes[1] == 0x30;
+
+	switch (regs->cx) {
+	case MSR_SVSM_CAA:
+		return __vc_handle_msr_caa(regs, write);
+	case MSR_IA32_TSC:
+	case MSR_AMD64_GUEST_TSC_FREQ:
+		if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+			return __vc_handle_secure_tsc_msrs(regs, write);
+		break;
+	default:
+		break;
+	}
+
+	ghcb_set_rcx(ghcb, regs->cx);
+	if (write) {
+		ghcb_set_rax(ghcb, regs->ax);
+		ghcb_set_rdx(ghcb, regs->dx);
+	}
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
+
+	if ((ret == ES_OK) && !write) {
+		regs->ax = ghcb->save.rax;
+		regs->dx = ghcb->save.rdx;
+	}
+
+	return ret;
+}
+
+static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
+{
+	int trapnr = ctxt->fi.vector;
+
+	if (trapnr == X86_TRAP_PF)
+		native_write_cr2(ctxt->fi.cr2);
+
+	ctxt->regs->orig_ax = ctxt->fi.error_code;
+	do_early_exception(ctxt->regs, trapnr);
+}
+
+static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
+{
+	long *reg_array;
+	int offset;
+
+	reg_array = (long *)ctxt->regs;
+	offset    = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
+
+	if (offset < 0)
+		return NULL;
+
+	offset /= sizeof(long);
+
+	return reg_array + offset;
+}
+static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+				 unsigned int bytes, bool read)
+{
+	u64 exit_code, exit_info_1, exit_info_2;
+	unsigned long ghcb_pa = __pa(ghcb);
+	enum es_result res;
+	phys_addr_t paddr;
+	void __user *ref;
+
+	ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
+	if (ref == (void __user *)-1L)
+		return ES_UNSUPPORTED;
+
+	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
+
+	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+	if (res != ES_OK) {
+		if (res == ES_EXCEPTION && !read)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return res;
+	}
+
+	exit_info_1 = paddr;
+	/* Can never be greater than 8 */
+	exit_info_2 = bytes;
+
+	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
+
+	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
+}
+
+/*
+ * The MOVS instruction has two memory operands, which raises the
+ * problem that it is not known whether the access to the source or the
+ * destination caused the #VC exception (and hence whether an MMIO read
+ * or write operation needs to be emulated).
+ *
+ * Instead of playing games with walking page-tables and trying to guess
+ * whether the source or destination is an MMIO range, split the move
+ * into two operations, a read and a write with only one memory operand.
+ * This will cause a nested #VC exception on the MMIO address which can
+ * then be handled.
+ *
+ * This implementation has the benefit that it also supports MOVS where
+ * source _and_ destination are MMIO regions.
+ *
+ * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
+ * rare operation. If it turns out to be a performance problem the split
+ * operations can be moved to memcpy_fromio() and memcpy_toio().
+ */
+static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
+					  unsigned int bytes)
+{
+	unsigned long ds_base, es_base;
+	unsigned char *src, *dst;
+	unsigned char buffer[8];
+	enum es_result ret;
+	bool rep;
+	int off;
+
+	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
+	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+	if (ds_base == -1L || es_base == -1L) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	src = ds_base + (unsigned char *)ctxt->regs->si;
+	dst = es_base + (unsigned char *)ctxt->regs->di;
+
+	ret = vc_read_mem(ctxt, src, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	ret = vc_write_mem(ctxt, dst, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	if (ctxt->regs->flags & X86_EFLAGS_DF)
+		off = -bytes;
+	else
+		off =  bytes;
+
+	ctxt->regs->si += off;
+	ctxt->regs->di += off;
+
+	rep = insn_has_rep_prefix(&ctxt->insn);
+	if (rep)
+		ctxt->regs->cx -= 1;
+
+	if (!rep || ctxt->regs->cx == 0)
+		return ES_OK;
+	else
+		return ES_RETRY;
+}
+
+static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct insn *insn = &ctxt->insn;
+	enum insn_mmio_type mmio;
+	unsigned int bytes = 0;
+	enum es_result ret;
+	u8 sign_byte;
+	long *reg_data;
+
+	mmio = insn_decode_mmio(insn, &bytes);
+	if (mmio == INSN_MMIO_DECODE_FAILED)
+		return ES_DECODE_FAILED;
+
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
+		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
+		if (!reg_data)
+			return ES_DECODE_FAILED;
+	}
+
+	if (user_mode(ctxt->regs))
+		return ES_UNSUPPORTED;
+
+	switch (mmio) {
+	case INSN_MMIO_WRITE:
+		memcpy(ghcb->shared_buffer, reg_data, bytes);
+		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+		break;
+	case INSN_MMIO_WRITE_IMM:
+		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
+		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+		break;
+	case INSN_MMIO_READ:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		/* Zero-extend for 32-bit operation */
+		if (bytes == 4)
+			*reg_data = 0;
+
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_READ_ZERO_EXTEND:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		/* Zero extend based on operand size */
+		memset(reg_data, 0, insn->opnd_bytes);
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_READ_SIGN_EXTEND:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		if (bytes == 1) {
+			u8 *val = (u8 *)ghcb->shared_buffer;
+
+			sign_byte = (*val & 0x80) ? 0xff : 0x00;
+		} else {
+			u16 *val = (u16 *)ghcb->shared_buffer;
+
+			sign_byte = (*val & 0x8000) ? 0xff : 0x00;
+		}
+
+		/* Sign extend based on operand size */
+		memset(reg_data, sign_byte, insn->opnd_bytes);
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_MOVS:
+		ret = vc_handle_mmio_movs(ctxt, bytes);
+		break;
+	default:
+		ret = ES_UNSUPPORTED;
+		break;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
+					  struct es_em_ctxt *ctxt)
+{
+	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	long val, *reg = vc_insn_get_rm(ctxt);
+	enum es_result ret;
+
+	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+		return ES_VMM_ERROR;
+
+	if (!reg)
+		return ES_DECODE_FAILED;
+
+	val = *reg;
+
+	/* Upper 32 bits must be written as zeroes */
+	if (val >> 32) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	/* Clear out other reserved bits and set bit 10 */
+	val = (val & 0xffff23ffL) | BIT(10);
+
+	/* Early non-zero writes to DR7 are not supported */
+	if (!data && (val & ~DR7_RESET_VALUE))
+		return ES_UNSUPPORTED;
+
+	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
+	ghcb_set_rax(ghcb, val);
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (data)
+		data->dr7 = val;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
+					 struct es_em_ctxt *ctxt)
+{
+	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	long *reg = vc_insn_get_rm(ctxt);
+
+	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+		return ES_VMM_ERROR;
+
+	if (!reg)
+		return ES_DECODE_FAILED;
+
+	if (data)
+		*reg = data->dr7;
+	else
+		*reg = DR7_RESET_VALUE;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
+				       struct es_em_ctxt *ctxt)
+{
+	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
+}
+
+static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	enum es_result ret;
+
+	ghcb_set_rcx(ghcb, ctxt->regs->cx);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+	ctxt->regs->dx = ghcb->save.rdx;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_monitor(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	/*
+	 * Treat it as a NOP and do not leak a physical address to the
+	 * hypervisor.
+	 */
+	return ES_OK;
+}
+
+static enum es_result vc_handle_mwait(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt)
+{
+	/* Treat the same as MONITOR/MONITORX */
+	return ES_OK;
+}
+
+static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	enum es_result ret;
+
+	ghcb_set_rax(ghcb, ctxt->regs->ax);
+	ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
+
+	if (x86_platform.hyper.sev_es_hcall_prepare)
+		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!ghcb_rax_is_valid(ghcb))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+
+	/*
+	 * Call sev_es_hcall_finish() after regs->ax is already set.
+	 * This allows the hypervisor handler to overwrite it again if
+	 * necessary.
+	 */
+	if (x86_platform.hyper.sev_es_hcall_finish &&
+	    !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
+		return ES_VMM_ERROR;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	/*
+	 * Calling ecx_alignment_check() directly does not work, because it
+	 * enables IRQs and the GHCB is active. Forward the exception and call
+	 * it later from vc_forward_exception().
+	 */
+	ctxt->fi.vector = X86_TRAP_AC;
+	ctxt->fi.error_code = 0;
+	return ES_EXCEPTION;
+}
+
+static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
+					 struct ghcb *ghcb,
+					 unsigned long exit_code)
+{
+	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
+
+	if (result != ES_OK)
+		return result;
+
+	switch (exit_code) {
+	case SVM_EXIT_READ_DR7:
+		result = vc_handle_dr7_read(ghcb, ctxt);
+		break;
+	case SVM_EXIT_WRITE_DR7:
+		result = vc_handle_dr7_write(ghcb, ctxt);
+		break;
+	case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
+		result = vc_handle_trap_ac(ghcb, ctxt);
+		break;
+	case SVM_EXIT_RDTSC:
+	case SVM_EXIT_RDTSCP:
+		result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
+		break;
+	case SVM_EXIT_RDPMC:
+		result = vc_handle_rdpmc(ghcb, ctxt);
+		break;
+	case SVM_EXIT_INVD:
+		pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
+		result = ES_UNSUPPORTED;
+		break;
+	case SVM_EXIT_CPUID:
+		result = vc_handle_cpuid(ghcb, ctxt);
+		break;
+	case SVM_EXIT_IOIO:
+		result = vc_handle_ioio(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MSR:
+		result = vc_handle_msr(ghcb, ctxt);
+		break;
+	case SVM_EXIT_VMMCALL:
+		result = vc_handle_vmmcall(ghcb, ctxt);
+		break;
+	case SVM_EXIT_WBINVD:
+		result = vc_handle_wbinvd(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MONITOR:
+		result = vc_handle_monitor(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MWAIT:
+		result = vc_handle_mwait(ghcb, ctxt);
+		break;
+	case SVM_EXIT_NPF:
+		result = vc_handle_mmio(ghcb, ctxt);
+		break;
+	default:
+		/*
+		 * Unexpected #VC exception
+		 */
+		result = ES_UNSUPPORTED;
+	}
+
+	return result;
+}
+
+static __always_inline bool is_vc2_stack(unsigned long sp)
+{
+	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
+}
+
+static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
+{
+	unsigned long sp, prev_sp;
+
+	sp      = (unsigned long)regs;
+	prev_sp = regs->sp;
+
+	/*
+	 * If the code was already executing on the VC2 stack when the #VC
+	 * happened, let it proceed to the normal handling routine. This way the
+	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
+	 */
+	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
+}
+
+static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
+{
+	struct ghcb_state state;
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+	struct ghcb *ghcb;
+	bool ret = true;
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+	result = vc_init_em_ctxt(&ctxt, regs, error_code);
+
+	if (result == ES_OK)
+		result = vc_handle_exitcode(&ctxt, ghcb, error_code);
+
+	__sev_put_ghcb(&state);
+
+	/* Done - now check the result */
+	switch (result) {
+	case ES_OK:
+		vc_finish_insn(&ctxt);
+		break;
+	case ES_UNSUPPORTED:
+		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_VMM_ERROR:
+		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_DECODE_FAILED:
+		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_EXCEPTION:
+		vc_forward_exception(&ctxt);
+		break;
+	case ES_RETRY:
+		/* Nothing to do */
+		break;
+	default:
+		pr_emerg("Unknown result in %s():%d\n", __func__, result);
+		/*
+		 * Emulating the instruction which caused the #VC exception
+		 * failed - can't continue so print debug information
+		 */
+		BUG();
+	}
+
+	return ret;
+}
+
+static __always_inline bool vc_is_db(unsigned long error_code)
+{
+	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
+}
+
+/*
+ * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
+ * and will panic when an error happens.
+ */
+DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
+{
+	irqentry_state_t irq_state;
+
+	/*
+	 * With the current implementation it is always possible to switch to a
+	 * safe stack because #VC exceptions only happen at known places, like
+	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
+	 * also happen with code instrumentation when the hypervisor intercepts
+	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
+	 * exceptions currently also only happen in safe places.
+	 *
+	 * But keep this here in case the noinstr annotations are violated due
+	 * to bug elsewhere.
+	 */
+	if (unlikely(vc_from_invalid_context(regs))) {
+		instrumentation_begin();
+		panic("Can't handle #VC exception from unsupported context\n");
+		instrumentation_end();
+	}
+
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		exc_debug(regs);
+		return;
+	}
+
+	irq_state = irqentry_nmi_enter(regs);
+
+	instrumentation_begin();
+
+	if (!vc_raw_handle_exception(regs, error_code)) {
+		/* Show some debug info */
+		show_regs(regs);
+
+		/* Ask hypervisor to sev_es_terminate */
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+		/* If that fails and we get here - just panic */
+		panic("Returned from Terminate-Request to Hypervisor\n");
+	}
+
+	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
+}
+
+/*
+ * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
+ * and will kill the current task with SIGBUS when an error happens.
+ */
+DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
+{
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		noist_exc_debug(regs);
+		return;
+	}
+
+	irqentry_enter_from_user_mode(regs);
+	instrumentation_begin();
+
+	if (!vc_raw_handle_exception(regs, error_code)) {
+		/*
+		 * Do not kill the machine if user-space triggered the
+		 * exception. Send SIGBUS instead and let user-space deal with
+		 * it.
+		 */
+		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
+	}
+
+	instrumentation_end();
+	irqentry_exit_to_user_mode(regs);
+}
+
+bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
+{
+	unsigned long exit_code = regs->orig_ax;
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+
+	vc_ghcb_invalidate(boot_ghcb);
+
+	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+	if (result == ES_OK)
+		result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
+
+	/* Done - now check the result */
+	switch (result) {
+	case ES_OK:
+		vc_finish_insn(&ctxt);
+		break;
+	case ES_UNSUPPORTED:
+		early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_VMM_ERROR:
+		early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_DECODE_FAILED:
+		early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_EXCEPTION:
+		vc_early_forward_exception(&ctxt);
+		break;
+	case ES_RETRY:
+		/* Nothing to do */
+		break;
+	default:
+		BUG();
+	}
+
+	return true;
+
+fail:
+	show_regs(regs);
+
+	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
+
diff --git a/arch/x86/coco/sev/vc-shared.c b/arch/x86/coco/sev/vc-shared.c
new file mode 100644
index 000000000000..2c0ab0fdc060
--- /dev/null
+++ b/arch/x86/coco/sev/vc-shared.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
+					    unsigned long exit_code)
+{
+	unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
+	u8 modrm = ctxt->insn.modrm.value;
+
+	switch (exit_code) {
+
+	case SVM_EXIT_IOIO:
+	case SVM_EXIT_NPF:
+		/* handled separately */
+		return ES_OK;
+
+	case SVM_EXIT_CPUID:
+		if (opcode == 0xa20f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_INVD:
+		if (opcode == 0x080f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MONITOR:
+		/* MONITOR and MONITORX instructions generate the same error code */
+		if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MWAIT:
+		/* MWAIT and MWAITX instructions generate the same error code */
+		if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MSR:
+		/* RDMSR */
+		if (opcode == 0x320f ||
+		/* WRMSR */
+		    opcode == 0x300f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDPMC:
+		if (opcode == 0x330f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSC:
+		if (opcode == 0x310f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSCP:
+		if (opcode == 0x010f && modrm == 0xf9)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_READ_DR7:
+		if (opcode == 0x210f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_VMMCALL:
+		if (opcode == 0x010f && modrm == 0xd9)
+			return ES_OK;
+
+		break;
+
+	case SVM_EXIT_WRITE_DR7:
+		if (opcode == 0x230f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_WBINVD:
+		if (opcode == 0x90f)
+			return ES_OK;
+		break;
+
+	default:
+		break;
+	}
+
+	sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
+		   opcode, exit_code, ctxt->regs->ip);
+
+	return ES_UNSUPPORTED;
+}
+
+static bool vc_decoding_needed(unsigned long exit_code)
+{
+	/* Exceptions don't require to decode the instruction */
+	return !(exit_code >= SVM_EXIT_EXCP_BASE &&
+		 exit_code <= SVM_EXIT_LAST_EXCP);
+}
+
+static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
+				      struct pt_regs *regs,
+				      unsigned long exit_code)
+{
+	enum es_result ret = ES_OK;
+
+	memset(ctxt, 0, sizeof(*ctxt));
+	ctxt->regs = regs;
+
+	if (vc_decoding_needed(exit_code))
+		ret = vc_decode_insn(ctxt);
+
+	return ret;
+}
+
+static void vc_finish_insn(struct es_em_ctxt *ctxt)
+{
+	ctxt->regs->ip += ctxt->insn.length;
+}
+
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+					   unsigned long address,
+					   bool write)
+{
+	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_USER;
+		ctxt->fi.cr2        = address;
+		if (write)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return ES_EXCEPTION;
+	}
+
+	return ES_OK;
+}
+
+static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
+					  void *src, char *buf,
+					  unsigned int data_size,
+					  unsigned int count,
+					  bool backwards)
+{
+	int i, b = backwards ? -1 : 1;
+	unsigned long address = (unsigned long)src;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, false);
+	if (ret != ES_OK)
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		void *s = src + (i * data_size * b);
+		char *d = buf + (i * data_size);
+
+		ret = vc_read_mem(ctxt, s, d, data_size);
+		if (ret != ES_OK)
+			break;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
+					   void *dst, char *buf,
+					   unsigned int data_size,
+					   unsigned int count,
+					   bool backwards)
+{
+	int i, s = backwards ? -1 : 1;
+	unsigned long address = (unsigned long)dst;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, true);
+	if (ret != ES_OK)
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		void *d = dst + (i * data_size * s);
+		char *b = buf + (i * data_size);
+
+		ret = vc_write_mem(ctxt, d, b, data_size);
+		if (ret != ES_OK)
+			break;
+	}
+
+	return ret;
+}
+
+#define IOIO_TYPE_STR  BIT(2)
+#define IOIO_TYPE_IN   1
+#define IOIO_TYPE_INS  (IOIO_TYPE_IN | IOIO_TYPE_STR)
+#define IOIO_TYPE_OUT  0
+#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
+
+#define IOIO_REP       BIT(3)
+
+#define IOIO_ADDR_64   BIT(9)
+#define IOIO_ADDR_32   BIT(8)
+#define IOIO_ADDR_16   BIT(7)
+
+#define IOIO_DATA_32   BIT(6)
+#define IOIO_DATA_16   BIT(5)
+#define IOIO_DATA_8    BIT(4)
+
+#define IOIO_SEG_ES    (0 << 10)
+#define IOIO_SEG_DS    (3 << 10)
+
+static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
+{
+	struct insn *insn = &ctxt->insn;
+	size_t size;
+	u64 port;
+
+	*exitinfo = 0;
+
+	switch (insn->opcode.bytes[0]) {
+	/* INS opcodes */
+	case 0x6c:
+	case 0x6d:
+		*exitinfo |= IOIO_TYPE_INS;
+		*exitinfo |= IOIO_SEG_ES;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* OUTS opcodes */
+	case 0x6e:
+	case 0x6f:
+		*exitinfo |= IOIO_TYPE_OUTS;
+		*exitinfo |= IOIO_SEG_DS;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* IN immediate opcodes */
+	case 0xe4:
+	case 0xe5:
+		*exitinfo |= IOIO_TYPE_IN;
+		port	   = (u8)insn->immediate.value & 0xffff;
+		break;
+
+	/* OUT immediate opcodes */
+	case 0xe6:
+	case 0xe7:
+		*exitinfo |= IOIO_TYPE_OUT;
+		port	   = (u8)insn->immediate.value & 0xffff;
+		break;
+
+	/* IN register opcodes */
+	case 0xec:
+	case 0xed:
+		*exitinfo |= IOIO_TYPE_IN;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* OUT register opcodes */
+	case 0xee:
+	case 0xef:
+		*exitinfo |= IOIO_TYPE_OUT;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	default:
+		return ES_DECODE_FAILED;
+	}
+
+	*exitinfo |= port << 16;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0x6c:
+	case 0x6e:
+	case 0xe4:
+	case 0xe6:
+	case 0xec:
+	case 0xee:
+		/* Single byte opcodes */
+		*exitinfo |= IOIO_DATA_8;
+		size       = 1;
+		break;
+	default:
+		/* Length determined by instruction parsing */
+		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
+						     : IOIO_DATA_32;
+		size       = (insn->opnd_bytes == 2) ? 2 : 4;
+	}
+
+	switch (insn->addr_bytes) {
+	case 2:
+		*exitinfo |= IOIO_ADDR_16;
+		break;
+	case 4:
+		*exitinfo |= IOIO_ADDR_32;
+		break;
+	case 8:
+		*exitinfo |= IOIO_ADDR_64;
+		break;
+	}
+
+	if (insn_has_rep_prefix(insn))
+		*exitinfo |= IOIO_REP;
+
+	return vc_ioio_check(ctxt, (u16)port, size);
+}
+
+static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	u64 exit_info_1, exit_info_2;
+	enum es_result ret;
+
+	ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
+	if (ret != ES_OK)
+		return ret;
+
+	if (exit_info_1 & IOIO_TYPE_STR) {
+
+		/* (REP) INS/OUTS */
+
+		bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
+		unsigned int io_bytes, exit_bytes;
+		unsigned int ghcb_count, op_count;
+		unsigned long es_base;
+		u64 sw_scratch;
+
+		/*
+		 * For the string variants with rep prefix the amount of in/out
+		 * operations per #VC exception is limited so that the kernel
+		 * has a chance to take interrupts and re-schedule while the
+		 * instruction is emulated.
+		 */
+		io_bytes   = (exit_info_1 >> 4) & 0x7;
+		ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
+
+		op_count    = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
+		exit_info_2 = min(op_count, ghcb_count);
+		exit_bytes  = exit_info_2 * io_bytes;
+
+		es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+		/* Read bytes of OUTS into the shared buffer */
+		if (!(exit_info_1 & IOIO_TYPE_IN)) {
+			ret = vc_insn_string_read(ctxt,
+					       (void *)(es_base + regs->si),
+					       ghcb->shared_buffer, io_bytes,
+					       exit_info_2, df);
+			if (ret)
+				return ret;
+		}
+
+		/*
+		 * Issue an VMGEXIT to the HV to consume the bytes from the
+		 * shared buffer or to have it write them into the shared buffer
+		 * depending on the instruction: OUTS or INS.
+		 */
+		sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
+		ghcb_set_sw_scratch(ghcb, sw_scratch);
+		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
+					  exit_info_1, exit_info_2);
+		if (ret != ES_OK)
+			return ret;
+
+		/* Read bytes from shared buffer into the guest's destination. */
+		if (exit_info_1 & IOIO_TYPE_IN) {
+			ret = vc_insn_string_write(ctxt,
+						   (void *)(es_base + regs->di),
+						   ghcb->shared_buffer, io_bytes,
+						   exit_info_2, df);
+			if (ret)
+				return ret;
+
+			if (df)
+				regs->di -= exit_bytes;
+			else
+				regs->di += exit_bytes;
+		} else {
+			if (df)
+				regs->si -= exit_bytes;
+			else
+				regs->si += exit_bytes;
+		}
+
+		if (exit_info_1 & IOIO_REP)
+			regs->cx -= exit_info_2;
+
+		ret = regs->cx ? ES_RETRY : ES_OK;
+
+	} else {
+
+		/* IN/OUT into/from rAX */
+
+		int bits = (exit_info_1 & 0x70) >> 1;
+		u64 rax = 0;
+
+		if (!(exit_info_1 & IOIO_TYPE_IN))
+			rax = lower_bits(regs->ax, bits);
+
+		ghcb_set_rax(ghcb, rax);
+
+		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
+		if (ret != ES_OK)
+			return ret;
+
+		if (exit_info_1 & IOIO_TYPE_IN) {
+			if (!ghcb_rax_is_valid(ghcb))
+				return ES_VMM_ERROR;
+			regs->ax = lower_bits(ghcb->save.rax, bits);
+		}
+	}
+
+	return ret;
+}
+
+static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	struct cpuid_leaf leaf;
+	int ret;
+
+	leaf.fn = regs->ax;
+	leaf.subfn = regs->cx;
+	ret = snp_cpuid(ghcb, ctxt, &leaf);
+	if (!ret) {
+		regs->ax = leaf.eax;
+		regs->bx = leaf.ebx;
+		regs->cx = leaf.ecx;
+		regs->dx = leaf.edx;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	u32 cr4 = native_read_cr4();
+	enum es_result ret;
+	int snp_cpuid_ret;
+
+	snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
+	if (!snp_cpuid_ret)
+		return ES_OK;
+	if (snp_cpuid_ret != -EOPNOTSUPP)
+		return ES_VMM_ERROR;
+
+	ghcb_set_rax(ghcb, regs->ax);
+	ghcb_set_rcx(ghcb, regs->cx);
+
+	if (cr4 & X86_CR4_OSXSAVE)
+		/* Safe to read xcr0 */
+		ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
+	else
+		/* xgetbv will cause #GP - use reset value for xcr0 */
+		ghcb_set_xcr0(ghcb, 1);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) &&
+	      ghcb_rbx_is_valid(ghcb) &&
+	      ghcb_rcx_is_valid(ghcb) &&
+	      ghcb_rdx_is_valid(ghcb)))
+		return ES_VMM_ERROR;
+
+	regs->ax = ghcb->save.rax;
+	regs->bx = ghcb->save.rbx;
+	regs->cx = ghcb->save.rcx;
+	regs->dx = ghcb->save.rdx;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt,
+				      unsigned long exit_code)
+{
+	bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
+	enum es_result ret;
+
+	/*
+	 * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
+	 * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
+	 * instructions are being intercepted. If this should occur and Secure
+	 * TSC is enabled, guest execution should be terminated as the guest
+	 * cannot rely on the TSC value provided by the hypervisor.
+	 */
+	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+		return ES_VMM_ERROR;
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
+	     (!rdtscp || ghcb_rcx_is_valid(ghcb))))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+	ctxt->regs->dx = ghcb->save.rdx;
+	if (rdtscp)
+		ctxt->regs->cx = ghcb->save.rcx;
+
+	return ES_OK;
+}
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 32809a06dab4..edab6d6049be 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -14,6 +14,7 @@
 #include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
+#include <asm/paravirt_types.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/traps.h>
@@ -167,11 +168,11 @@ static void __noreturn tdx_panic(const char *msg)
 		/* Define register order according to the GHCI */
 		struct { u64 r14, r15, rbx, rdi, rsi, r8, r9, rdx; };
 
-		char str[64];
+		char bytes[64] __nonstring;
 	} message;
 
 	/* VMM assumes '\0' in byte 65, if the message took all 64 bytes */
-	strtomem_pad(message.str, msg, '\0');
+	strtomem_pad(message.bytes, msg, '\0');
 
 	args.r8  = message.r8;
 	args.r9  = message.r9;
@@ -392,13 +393,21 @@ static int handle_halt(struct ve_info *ve)
 {
 	const bool irq_disabled = irqs_disabled();
 
+	/*
+	 * HLT with IRQs enabled is unsafe, as an IRQ that is intended to be a
+	 * wake event may be consumed before requesting HLT emulation, leaving
+	 * the vCPU blocking indefinitely.
+	 */
+	if (WARN_ONCE(!irq_disabled, "HLT emulation with IRQs enabled"))
+		return -EIO;
+
 	if (__halt(irq_disabled))
 		return -EIO;
 
 	return ve_instr_len(ve);
 }
 
-void __cpuidle tdx_safe_halt(void)
+void __cpuidle tdx_halt(void)
 {
 	const bool irq_disabled = false;
 
@@ -409,6 +418,16 @@ void __cpuidle tdx_safe_halt(void)
 		WARN_ONCE(1, "HLT instruction emulation failed\n");
 }
 
+static void __cpuidle tdx_safe_halt(void)
+{
+	tdx_halt();
+	/*
+	 * "__cpuidle" section doesn't support instrumentation, so stick
+	 * with raw_* variant that avoids tracing hooks.
+	 */
+	raw_local_irq_enable();
+}
+
 static int read_msr(struct pt_regs *regs, struct ve_info *ve)
 {
 	struct tdx_module_args args = {
@@ -1110,6 +1129,19 @@ void __init tdx_early_init(void)
 	x86_platform.guest.enc_kexec_finish	     = tdx_kexec_finish;
 
 	/*
+	 * Avoid "sti;hlt" execution in TDX guests as HLT induces a #VE that
+	 * will enable interrupts before HLT TDCALL invocation if executed
+	 * in STI-shadow, possibly resulting in missed wakeup events.
+	 *
+	 * Modify all possible HLT execution paths to use TDX specific routines
+	 * that directly execute TDCALL and toggle the interrupt state as
+	 * needed after TDCALL completion. This also reduces HLT related #VEs
+	 * in addition to having a reliable halt logic execution.
+	 */
+	pv_ops.irq.safe_halt = tdx_safe_halt;
+	pv_ops.irq.halt = tdx_halt;
+
+	/*
 	 * TDX intercepts the RDMSR to read the X2APIC ID in the parallel
 	 * bringup low level code. That raises #VE which cannot be handled
 	 * there.
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 91801138b10b..7cd2f395f301 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,7 +1,6 @@
 CONFIG_WERROR=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_USELIB=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index 581296255b39..d5d091e03bd3 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -1,6 +1,4 @@
 # global x86 required specific stuff
-# On 32-bit HIGHMEM4G is not allowed
-CONFIG_HIGHMEM64G=y
 CONFIG_64BIT=y
 
 # These enable us to allow some of the
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index 4757bf922075..56cfdc79e2c6 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -3,10 +3,12 @@
 menu "Accelerated Cryptographic Algorithms for CPU (x86)"
 
 config CRYPTO_CURVE25519_X86
-	tristate "Public key crypto: Curve25519 (ADX)"
-	depends on X86 && 64BIT
+	tristate
+	depends on 64BIT
+	select CRYPTO_KPP
 	select CRYPTO_LIB_CURVE25519_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+	default CRYPTO_LIB_CURVE25519_INTERNAL
 	help
 	  Curve25519 algorithm
 
@@ -15,13 +17,11 @@ config CRYPTO_CURVE25519_X86
 
 config CRYPTO_AES_NI_INTEL
 	tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XCTR, XTS, GCM (AES-NI/VAES)"
-	depends on X86
 	select CRYPTO_AEAD
 	select CRYPTO_LIB_AES
 	select CRYPTO_LIB_GF128MUL
 	select CRYPTO_ALGAPI
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	help
 	  Block cipher: AES cipher algorithms
 	  AEAD cipher: AES with GCM
@@ -36,7 +36,7 @@ config CRYPTO_AES_NI_INTEL
 
 config CRYPTO_BLOWFISH_X86_64
 	tristate "Ciphers: Blowfish, modes: ECB, CBC"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_BLOWFISH_COMMON
 	imply CRYPTO_CTR
@@ -48,7 +48,7 @@ config CRYPTO_BLOWFISH_X86_64
 
 config CRYPTO_CAMELLIA_X86_64
 	tristate "Ciphers: Camellia with modes: ECB, CBC"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	imply CRYPTO_CTR
 	help
@@ -59,10 +59,9 @@ config CRYPTO_CAMELLIA_X86_64
 
 config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 	tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_CAMELLIA_X86_64
-	select CRYPTO_SIMD
 	imply CRYPTO_XTS
 	help
 	  Length-preserving ciphers: Camellia with ECB and CBC modes
@@ -73,7 +72,7 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 
 config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
 	tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_CAMELLIA_AESNI_AVX_X86_64
 	help
 	  Length-preserving ciphers: Camellia with ECB and CBC modes
@@ -84,11 +83,10 @@ config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
 
 config CRYPTO_CAST5_AVX_X86_64
 	tristate "Ciphers: CAST5 with modes: ECB, CBC (AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_CAST5
 	select CRYPTO_CAST_COMMON
-	select CRYPTO_SIMD
 	imply CRYPTO_CTR
 	help
 	  Length-preserving ciphers: CAST5 (CAST-128) cipher algorithm
@@ -101,11 +99,10 @@ config CRYPTO_CAST5_AVX_X86_64
 
 config CRYPTO_CAST6_AVX_X86_64
 	tristate "Ciphers: CAST6 with modes: ECB, CBC (AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_CAST6
 	select CRYPTO_CAST_COMMON
-	select CRYPTO_SIMD
 	imply CRYPTO_XTS
 	imply CRYPTO_CTR
 	help
@@ -119,7 +116,7 @@ config CRYPTO_CAST6_AVX_X86_64
 
 config CRYPTO_DES3_EDE_X86_64
 	tristate "Ciphers: Triple DES EDE with modes: ECB, CBC"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_DES
 	imply CRYPTO_CTR
@@ -133,10 +130,9 @@ config CRYPTO_DES3_EDE_X86_64
 
 config CRYPTO_SERPENT_SSE2_X86_64
 	tristate "Ciphers: Serpent with modes: ECB, CBC (SSE2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SERPENT
-	select CRYPTO_SIMD
 	imply CRYPTO_CTR
 	help
 	  Length-preserving ciphers: Serpent cipher algorithm
@@ -149,10 +145,9 @@ config CRYPTO_SERPENT_SSE2_X86_64
 
 config CRYPTO_SERPENT_SSE2_586
 	tristate "Ciphers: Serpent with modes: ECB, CBC (32-bit with SSE2)"
-	depends on X86 && !64BIT
+	depends on !64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SERPENT
-	select CRYPTO_SIMD
 	imply CRYPTO_CTR
 	help
 	  Length-preserving ciphers: Serpent cipher algorithm
@@ -165,10 +160,9 @@ config CRYPTO_SERPENT_SSE2_586
 
 config CRYPTO_SERPENT_AVX_X86_64
 	tristate "Ciphers: Serpent with modes: ECB, CBC (AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_SERPENT
-	select CRYPTO_SIMD
 	imply CRYPTO_XTS
 	imply CRYPTO_CTR
 	help
@@ -182,7 +176,7 @@ config CRYPTO_SERPENT_AVX_X86_64
 
 config CRYPTO_SERPENT_AVX2_X86_64
 	tristate "Ciphers: Serpent with modes: ECB, CBC (AVX2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SERPENT_AVX_X86_64
 	help
 	  Length-preserving ciphers: Serpent cipher algorithm
@@ -195,9 +189,8 @@ config CRYPTO_SERPENT_AVX2_X86_64
 
 config CRYPTO_SM4_AESNI_AVX_X86_64
 	tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_ALGAPI
 	select CRYPTO_SM4
 	help
@@ -216,9 +209,8 @@ config CRYPTO_SM4_AESNI_AVX_X86_64
 
 config CRYPTO_SM4_AESNI_AVX2_X86_64
 	tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_ALGAPI
 	select CRYPTO_SM4
 	select CRYPTO_SM4_AESNI_AVX_X86_64
@@ -238,7 +230,7 @@ config CRYPTO_SM4_AESNI_AVX2_X86_64
 
 config CRYPTO_TWOFISH_586
 	tristate "Ciphers: Twofish (32-bit)"
-	depends on (X86 || UML_X86) && !64BIT
+	depends on !64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
 	imply CRYPTO_CTR
@@ -249,7 +241,7 @@ config CRYPTO_TWOFISH_586
 
 config CRYPTO_TWOFISH_X86_64
 	tristate "Ciphers: Twofish"
-	depends on (X86 || UML_X86) && 64BIT
+	depends on 64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
 	imply CRYPTO_CTR
@@ -260,7 +252,7 @@ config CRYPTO_TWOFISH_X86_64
 
 config CRYPTO_TWOFISH_X86_64_3WAY
 	tristate "Ciphers: Twofish with modes: ECB, CBC (3-way parallel)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
@@ -275,9 +267,8 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 
 config CRYPTO_TWOFISH_AVX_X86_64
 	tristate "Ciphers: Twofish with modes: ECB, CBC (AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
 	select CRYPTO_TWOFISH_X86_64_3WAY
@@ -293,9 +284,8 @@ config CRYPTO_TWOFISH_AVX_X86_64
 
 config CRYPTO_ARIA_AESNI_AVX_X86_64
 	tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX/GFNI)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_ALGAPI
 	select CRYPTO_ARIA
 	help
@@ -311,9 +301,8 @@ config CRYPTO_ARIA_AESNI_AVX_X86_64
 
 config CRYPTO_ARIA_AESNI_AVX2_X86_64
 	tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX2/GFNI)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_ALGAPI
 	select CRYPTO_ARIA
 	select CRYPTO_ARIA_AESNI_AVX_X86_64
@@ -330,9 +319,8 @@ config CRYPTO_ARIA_AESNI_AVX2_X86_64
 
 config CRYPTO_ARIA_GFNI_AVX512_X86_64
 	tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)"
-	depends on X86 && 64BIT && AS_AVX512 && AS_GFNI
+	depends on 64BIT && AS_GFNI
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SIMD
 	select CRYPTO_ALGAPI
 	select CRYPTO_ARIA
 	select CRYPTO_ARIA_AESNI_AVX_X86_64
@@ -347,26 +335,10 @@ config CRYPTO_ARIA_GFNI_AVX512_X86_64
 
 	  Processes 64 blocks in parallel.
 
-config CRYPTO_CHACHA20_X86_64
-	tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (SSSE3/AVX2/AVX-512VL)"
-	depends on X86 && 64BIT
-	select CRYPTO_SKCIPHER
-	select CRYPTO_LIB_CHACHA_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-	help
-	  Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
-	  stream cipher algorithms
-
-	  Architecture: x86_64 using:
-	  - SSSE3 (Supplemental SSE3)
-	  - AVX2 (Advanced Vector Extensions 2)
-	  - AVX-512VL (Advanced Vector Extensions-512VL)
-
 config CRYPTO_AEGIS128_AESNI_SSE2
 	tristate "AEAD ciphers: AEGIS-128 (AES-NI/SSE4.1)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_AEAD
-	select CRYPTO_SIMD
 	help
 	  AEGIS-128 AEAD algorithm
 
@@ -376,7 +348,7 @@ config CRYPTO_AEGIS128_AESNI_SSE2
 
 config CRYPTO_NHPOLY1305_SSE2
 	tristate "Hash functions: NHPoly1305 (SSE2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_NHPOLY1305
 	help
 	  NHPoly1305 hash function for Adiantum
@@ -386,7 +358,7 @@ config CRYPTO_NHPOLY1305_SSE2
 
 config CRYPTO_NHPOLY1305_AVX2
 	tristate "Hash functions: NHPoly1305 (AVX2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_NHPOLY1305
 	help
 	  NHPoly1305 hash function for Adiantum
@@ -394,21 +366,9 @@ config CRYPTO_NHPOLY1305_AVX2
 	  Architecture: x86_64 using:
 	  - AVX2 (Advanced Vector Extensions 2)
 
-config CRYPTO_BLAKE2S_X86
-	bool "Hash functions: BLAKE2s (SSSE3/AVX-512)"
-	depends on X86 && 64BIT
-	select CRYPTO_LIB_BLAKE2S_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
-	help
-	  BLAKE2s cryptographic hash function (RFC 7693)
-
-	  Architecture: x86_64 using:
-	  - SSSE3 (Supplemental SSE3)
-	  - AVX-512 (Advanced Vector Extensions-512)
-
 config CRYPTO_POLYVAL_CLMUL_NI
 	tristate "Hash functions: POLYVAL (CLMUL-NI)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_POLYVAL
 	help
 	  POLYVAL hash function for HCTR2
@@ -416,21 +376,9 @@ config CRYPTO_POLYVAL_CLMUL_NI
 	  Architecture: x86_64 using:
 	  - CLMUL-NI (carry-less multiplication new instructions)
 
-config CRYPTO_POLY1305_X86_64
-	tristate "Hash functions: Poly1305 (SSE2/AVX2)"
-	depends on X86 && 64BIT
-	select CRYPTO_LIB_POLY1305_GENERIC
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
-	help
-	  Poly1305 authenticator algorithm (RFC7539)
-
-	  Architecture: x86_64 using:
-	  - SSE2 (Streaming SIMD Extensions 2)
-	  - AVX2 (Advanced Vector Extensions 2)
-
 config CRYPTO_SHA1_SSSE3
 	tristate "Hash functions: SHA-1 (SSSE3/AVX/AVX2/SHA-NI)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SHA1
 	select CRYPTO_HASH
 	help
@@ -442,23 +390,9 @@ config CRYPTO_SHA1_SSSE3
 	  - AVX2 (Advanced Vector Extensions 2)
 	  - SHA-NI (SHA Extensions New Instructions)
 
-config CRYPTO_SHA256_SSSE3
-	tristate "Hash functions: SHA-224 and SHA-256 (SSSE3/AVX/AVX2/SHA-NI)"
-	depends on X86 && 64BIT
-	select CRYPTO_SHA256
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: x86_64 using:
-	  - SSSE3 (Supplemental SSE3)
-	  - AVX (Advanced Vector Extensions)
-	  - AVX2 (Advanced Vector Extensions 2)
-	  - SHA-NI (SHA Extensions New Instructions)
-
 config CRYPTO_SHA512_SSSE3
 	tristate "Hash functions: SHA-384 and SHA-512 (SSSE3/AVX/AVX2)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_SHA512
 	select CRYPTO_HASH
 	help
@@ -471,9 +405,9 @@ config CRYPTO_SHA512_SSSE3
 
 config CRYPTO_SM3_AVX_X86_64
 	tristate "Hash functions: SM3 (AVX)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_HASH
-	select CRYPTO_SM3
+	select CRYPTO_LIB_SM3
 	help
 	  SM3 secure hash function as defined by OSCCA GM/T 0004-2012 SM3
 
@@ -484,7 +418,7 @@ config CRYPTO_SM3_AVX_X86_64
 
 config CRYPTO_GHASH_CLMUL_NI_INTEL
 	tristate "Hash functions: GHASH (CLMUL-NI)"
-	depends on X86 && 64BIT
+	depends on 64BIT
 	select CRYPTO_CRYPTD
 	help
 	  GCM GHASH hash function (NIST SP800-38D)
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 07b00bfca64b..aa289a9e0153 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -42,13 +42,9 @@ cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
 obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
 aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
 
-obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
-chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o
-chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
-
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
-aesni-intel-$(CONFIG_64BIT) += aes_ctrby8_avx-x86_64.o \
+aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \
 			       aes-gcm-aesni-x86_64.o \
 			       aes-xts-avx-x86_64.o
 ifeq ($(CONFIG_AS_VAES)$(CONFIG_AS_VPCLMULQDQ),yy)
@@ -56,29 +52,17 @@ aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o
 endif
 
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
-sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o
-
-obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
-sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
-sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
+sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ni_asm.o sha1_ssse3_glue.o
 
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
 sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
 
-obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o
-libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
-
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 
 obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o
 polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o
 
-obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
-poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
-targets += poly1305-x86_64-cryptogams.S
-
 obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
 nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
@@ -104,10 +88,5 @@ aria-aesni-avx2-x86_64-y := aria-aesni-avx2-asm_64.o aria_aesni_avx2_glue.o
 obj-$(CONFIG_CRYPTO_ARIA_GFNI_AVX512_X86_64) += aria-gfni-avx512-x86_64.o
 aria-gfni-avx512-x86_64-y := aria-gfni-avx512-asm_64.o aria_gfni_avx512_glue.o
 
-quiet_cmd_perlasm = PERLASM $@
-      cmd_perlasm = $(PERL) $< > $@
-$(obj)/%.S: $(src)/%.pl FORCE
-	$(call if_changed,perlasm)
-
 # Disable GCOV in odd or sensitive code
 GCOV_PROFILE_curve25519-x86_64.o := n
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 01fa568dc5fc..f1b6d40154e3 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -8,7 +8,6 @@
  */
 
 #include <crypto/internal/aead.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -71,10 +70,9 @@ static void crypto_aegis128_aesni_process_ad(
 
 	scatterwalk_start(&walk, sg_src);
 	while (assoclen != 0) {
-		unsigned int size = scatterwalk_clamp(&walk, assoclen);
+		unsigned int size = scatterwalk_next(&walk, assoclen);
+		const u8 *src = walk.addr;
 		unsigned int left = size;
-		void *mapped = scatterwalk_map(&walk);
-		const u8 *src = (const u8 *)mapped;
 
 		if (pos + size >= AEGIS128_BLOCK_SIZE) {
 			if (pos > 0) {
@@ -97,9 +95,7 @@ static void crypto_aegis128_aesni_process_ad(
 		pos += left;
 		assoclen -= size;
 
-		scatterwalk_unmap(mapped);
-		scatterwalk_advance(&walk, size);
-		scatterwalk_done(&walk, 0, assoclen);
+		scatterwalk_done_src(&walk, size);
 	}
 
 	if (pos > 0) {
@@ -236,21 +232,18 @@ static struct aead_alg crypto_aegis128_aesni_alg = {
 	.chunksize = AEGIS128_BLOCK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_INTERNAL,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct aegis_ctx) +
 			       __alignof__(struct aegis_ctx),
 		.cra_priority = 400,
 
-		.cra_name = "__aegis128",
-		.cra_driver_name = "__aegis128-aesni",
+		.cra_name = "aegis128",
+		.cra_driver_name = "aegis128-aesni",
 
 		.cra_module = THIS_MODULE,
 	}
 };
 
-static struct simd_aead_alg *simd_alg;
-
 static int __init crypto_aegis128_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM4_1) ||
@@ -258,13 +251,12 @@ static int __init crypto_aegis128_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return simd_register_aeads_compat(&crypto_aegis128_aesni_alg, 1,
-					  &simd_alg);
+	return crypto_register_aead(&crypto_aegis128_aesni_alg);
 }
 
 static void __exit crypto_aegis128_aesni_module_exit(void)
 {
-	simd_unregister_aeads(&crypto_aegis128_aesni_alg, 1, &simd_alg);
+	crypto_unregister_aead(&crypto_aegis128_aesni_alg);
 }
 
 module_init(crypto_aegis128_aesni_module_init);
diff --git a/arch/x86/crypto/aes-ctr-avx-x86_64.S b/arch/x86/crypto/aes-ctr-avx-x86_64.S
new file mode 100644
index 000000000000..bbbfd80f5a50
--- /dev/null
+++ b/arch/x86/crypto/aes-ctr-avx-x86_64.S
@@ -0,0 +1,573 @@
+/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */
+//
+// Copyright 2025 Google LLC
+//
+// Author: Eric Biggers <ebiggers@google.com>
+//
+// This file is dual-licensed, meaning that you can use it under your choice of
+// either of the following two licenses:
+//
+// Licensed under the Apache License 2.0 (the "License").  You may obtain a copy
+// of the License at
+//
+//	http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+// or
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+// 1. Redistributions of source code must retain the above copyright notice,
+//    this list of conditions and the following disclaimer.
+//
+// 2. Redistributions in binary form must reproduce the above copyright
+//    notice, this list of conditions and the following disclaimer in the
+//    documentation and/or other materials provided with the distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+// POSSIBILITY OF SUCH DAMAGE.
+//
+//------------------------------------------------------------------------------
+//
+// This file contains x86_64 assembly implementations of AES-CTR and AES-XCTR
+// using the following sets of CPU features:
+//	- AES-NI && AVX
+//	- VAES && AVX2
+//	- VAES && AVX512BW && AVX512VL && BMI2
+//
+// See the function definitions at the bottom of the file for more information.
+
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+
+.section .rodata
+.p2align 4
+
+.Lbswap_mask:
+	.octa	0x000102030405060708090a0b0c0d0e0f
+
+.Lctr_pattern:
+	.quad	0, 0
+.Lone:
+	.quad	1, 0
+.Ltwo:
+	.quad	2, 0
+	.quad	3, 0
+
+.Lfour:
+	.quad	4, 0
+
+.text
+
+// Move a vector between memory and a register.
+.macro	_vmovdqu	src, dst
+.if VL < 64
+	vmovdqu		\src, \dst
+.else
+	vmovdqu8	\src, \dst
+.endif
+.endm
+
+// Move a vector between registers.
+.macro	_vmovdqa	src, dst
+.if VL < 64
+	vmovdqa		\src, \dst
+.else
+	vmovdqa64	\src, \dst
+.endif
+.endm
+
+// Broadcast a 128-bit value from memory to all 128-bit lanes of a vector
+// register.
+.macro	_vbroadcast128	src, dst
+.if VL == 16
+	vmovdqu		\src, \dst
+.elseif VL == 32
+	vbroadcasti128	\src, \dst
+.else
+	vbroadcasti32x4	\src, \dst
+.endif
+.endm
+
+// XOR two vectors together.
+.macro	_vpxor	src1, src2, dst
+.if VL < 64
+	vpxor		\src1, \src2, \dst
+.else
+	vpxord		\src1, \src2, \dst
+.endif
+.endm
+
+// Load 1 <= %ecx <= 15 bytes from the pointer \src into the xmm register \dst
+// and zeroize any remaining bytes.  Clobbers %rax, %rcx, and \tmp{64,32}.
+.macro	_load_partial_block	src, dst, tmp64, tmp32
+	sub		$8, %ecx		// LEN - 8
+	jle		.Lle8\@
+
+	// Load 9 <= LEN <= 15 bytes.
+	vmovq		(\src), \dst		// Load first 8 bytes
+	mov		(\src, %rcx), %rax	// Load last 8 bytes
+	neg		%ecx
+	shl		$3, %ecx
+	shr		%cl, %rax		// Discard overlapping bytes
+	vpinsrq		$1, %rax, \dst, \dst
+	jmp		.Ldone\@
+
+.Lle8\@:
+	add		$4, %ecx		// LEN - 4
+	jl		.Llt4\@
+
+	// Load 4 <= LEN <= 8 bytes.
+	mov		(\src), %eax		// Load first 4 bytes
+	mov		(\src, %rcx), \tmp32	// Load last 4 bytes
+	jmp		.Lcombine\@
+
+.Llt4\@:
+	// Load 1 <= LEN <= 3 bytes.
+	add		$2, %ecx		// LEN - 2
+	movzbl		(\src), %eax		// Load first byte
+	jl		.Lmovq\@
+	movzwl		(\src, %rcx), \tmp32	// Load last 2 bytes
+.Lcombine\@:
+	shl		$3, %ecx
+	shl		%cl, \tmp64
+	or		\tmp64, %rax		// Combine the two parts
+.Lmovq\@:
+	vmovq		%rax, \dst
+.Ldone\@:
+.endm
+
+// Store 1 <= %ecx <= 15 bytes from the xmm register \src to the pointer \dst.
+// Clobbers %rax, %rcx, and \tmp{64,32}.
+.macro	_store_partial_block	src, dst, tmp64, tmp32
+	sub		$8, %ecx		// LEN - 8
+	jl		.Llt8\@
+
+	// Store 8 <= LEN <= 15 bytes.
+	vpextrq		$1, \src, %rax
+	mov		%ecx, \tmp32
+	shl		$3, %ecx
+	ror		%cl, %rax
+	mov		%rax, (\dst, \tmp64)	// Store last LEN - 8 bytes
+	vmovq		\src, (\dst)		// Store first 8 bytes
+	jmp		.Ldone\@
+
+.Llt8\@:
+	add		$4, %ecx		// LEN - 4
+	jl		.Llt4\@
+
+	// Store 4 <= LEN <= 7 bytes.
+	vpextrd		$1, \src, %eax
+	mov		%ecx, \tmp32
+	shl		$3, %ecx
+	ror		%cl, %eax
+	mov		%eax, (\dst, \tmp64)	// Store last LEN - 4 bytes
+	vmovd		\src, (\dst)		// Store first 4 bytes
+	jmp		.Ldone\@
+
+.Llt4\@:
+	// Store 1 <= LEN <= 3 bytes.
+	vpextrb		$0, \src, 0(\dst)
+	cmp		$-2, %ecx		// LEN - 4 == -2, i.e. LEN == 2?
+	jl		.Ldone\@
+	vpextrb		$1, \src, 1(\dst)
+	je		.Ldone\@
+	vpextrb		$2, \src, 2(\dst)
+.Ldone\@:
+.endm
+
+// Prepare the next two vectors of AES inputs in AESDATA\i0 and AESDATA\i1, and
+// XOR each with the zero-th round key.  Also update LE_CTR if !\final.
+.macro	_prepare_2_ctr_vecs	is_xctr, i0, i1, final=0
+.if \is_xctr
+  .if USE_AVX512
+	vmovdqa64	LE_CTR, AESDATA\i0
+	vpternlogd	$0x96, XCTR_IV, RNDKEY0, AESDATA\i0
+  .else
+	vpxor		XCTR_IV, LE_CTR, AESDATA\i0
+	vpxor		RNDKEY0, AESDATA\i0, AESDATA\i0
+  .endif
+	vpaddq		LE_CTR_INC1, LE_CTR, AESDATA\i1
+
+  .if USE_AVX512
+	vpternlogd	$0x96, XCTR_IV, RNDKEY0, AESDATA\i1
+  .else
+	vpxor		XCTR_IV, AESDATA\i1, AESDATA\i1
+	vpxor		RNDKEY0, AESDATA\i1, AESDATA\i1
+  .endif
+.else
+	vpshufb		BSWAP_MASK, LE_CTR, AESDATA\i0
+	_vpxor		RNDKEY0, AESDATA\i0, AESDATA\i0
+	vpaddq		LE_CTR_INC1, LE_CTR, AESDATA\i1
+	vpshufb		BSWAP_MASK, AESDATA\i1, AESDATA\i1
+	_vpxor		RNDKEY0, AESDATA\i1, AESDATA\i1
+.endif
+.if !\final
+	vpaddq		LE_CTR_INC2, LE_CTR, LE_CTR
+.endif
+.endm
+
+// Do all AES rounds on the data in the given AESDATA vectors, excluding the
+// zero-th and last rounds.
+.macro	_aesenc_loop	vecs:vararg
+	mov		KEY, %rax
+1:
+	_vbroadcast128	(%rax), RNDKEY
+.irp i, \vecs
+	vaesenc		RNDKEY, AESDATA\i, AESDATA\i
+.endr
+	add		$16, %rax
+	cmp		%rax, RNDKEYLAST_PTR
+	jne		1b
+.endm
+
+// Finalize the keystream blocks in the given AESDATA vectors by doing the last
+// AES round, then XOR those keystream blocks with the corresponding data.
+// Reduce latency by doing the XOR before the vaesenclast, utilizing the
+// property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a).
+.macro	_aesenclast_and_xor	vecs:vararg
+.irp i, \vecs
+	_vpxor		\i*VL(SRC), RNDKEYLAST, RNDKEY
+	vaesenclast	RNDKEY, AESDATA\i, AESDATA\i
+.endr
+.irp i, \vecs
+	_vmovdqu	AESDATA\i, \i*VL(DST)
+.endr
+.endm
+
+// XOR the keystream blocks in the specified AESDATA vectors with the
+// corresponding data.
+.macro	_xor_data	vecs:vararg
+.irp i, \vecs
+	_vpxor		\i*VL(SRC), AESDATA\i, AESDATA\i
+.endr
+.irp i, \vecs
+	_vmovdqu	AESDATA\i, \i*VL(DST)
+.endr
+.endm
+
+.macro	_aes_ctr_crypt		is_xctr
+
+	// Define register aliases V0-V15 that map to the xmm, ymm, or zmm
+	// registers according to the selected Vector Length (VL).
+.irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+  .if VL == 16
+	.set	V\i,		%xmm\i
+  .elseif VL == 32
+	.set	V\i,		%ymm\i
+  .elseif VL == 64
+	.set	V\i,		%zmm\i
+  .else
+	.error "Unsupported Vector Length (VL)"
+  .endif
+.endr
+
+	// Function arguments
+	.set	KEY,		%rdi	// Initially points to the start of the
+					// crypto_aes_ctx, then is advanced to
+					// point to the index 1 round key
+	.set	KEY32,		%edi	// Available as temp register after all
+					// keystream blocks have been generated
+	.set	SRC,		%rsi	// Pointer to next source data
+	.set	DST,		%rdx	// Pointer to next destination data
+	.set	LEN,		%ecx	// Remaining length in bytes.
+					// Note: _load_partial_block relies on
+					// this being in %ecx.
+	.set	LEN64,		%rcx	// Zero-extend LEN before using!
+	.set	LEN8,		%cl
+.if \is_xctr
+	.set	XCTR_IV_PTR,	%r8	// const u8 iv[AES_BLOCK_SIZE];
+	.set	XCTR_CTR,	%r9	// u64 ctr;
+.else
+	.set	LE_CTR_PTR,	%r8	// const u64 le_ctr[2];
+.endif
+
+	// Additional local variables
+	.set	RNDKEYLAST_PTR,	%r10
+	.set	AESDATA0,	V0
+	.set	AESDATA0_XMM,	%xmm0
+	.set	AESDATA1,	V1
+	.set	AESDATA1_XMM,	%xmm1
+	.set	AESDATA2,	V2
+	.set	AESDATA3,	V3
+	.set	AESDATA4,	V4
+	.set	AESDATA5,	V5
+	.set	AESDATA6,	V6
+	.set	AESDATA7,	V7
+.if \is_xctr
+	.set	XCTR_IV,	V8
+.else
+	.set	BSWAP_MASK,	V8
+.endif
+	.set	LE_CTR,		V9
+	.set	LE_CTR_XMM,	%xmm9
+	.set	LE_CTR_INC1,	V10
+	.set	LE_CTR_INC2,	V11
+	.set	RNDKEY0,	V12
+	.set	RNDKEYLAST,	V13
+	.set	RNDKEY,		V14
+
+	// Create the first vector of counters.
+.if \is_xctr
+  .if VL == 16
+	vmovq		XCTR_CTR, LE_CTR
+  .elseif VL == 32
+	vmovq		XCTR_CTR, LE_CTR_XMM
+	inc		XCTR_CTR
+	vmovq		XCTR_CTR, AESDATA0_XMM
+	vinserti128	$1, AESDATA0_XMM, LE_CTR, LE_CTR
+  .else
+	vpbroadcastq	XCTR_CTR, LE_CTR
+	vpsrldq		$8, LE_CTR, LE_CTR
+	vpaddq		.Lctr_pattern(%rip), LE_CTR, LE_CTR
+  .endif
+	_vbroadcast128	(XCTR_IV_PTR), XCTR_IV
+.else
+	_vbroadcast128	(LE_CTR_PTR), LE_CTR
+  .if VL > 16
+	vpaddq		.Lctr_pattern(%rip), LE_CTR, LE_CTR
+  .endif
+	_vbroadcast128	.Lbswap_mask(%rip), BSWAP_MASK
+.endif
+
+.if VL == 16
+	_vbroadcast128	.Lone(%rip), LE_CTR_INC1
+.elseif VL == 32
+	_vbroadcast128	.Ltwo(%rip), LE_CTR_INC1
+.else
+	_vbroadcast128	.Lfour(%rip), LE_CTR_INC1
+.endif
+	vpsllq		$1, LE_CTR_INC1, LE_CTR_INC2
+
+	// Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256).
+	movl		480(KEY), %eax
+
+	// Compute the pointer to the last round key.
+	lea		6*16(KEY, %rax, 4), RNDKEYLAST_PTR
+
+	// Load the zero-th and last round keys.
+	_vbroadcast128	(KEY), RNDKEY0
+	_vbroadcast128	(RNDKEYLAST_PTR), RNDKEYLAST
+
+	// Make KEY point to the first round key.
+	add		$16, KEY
+
+	// This is the main loop, which encrypts 8 vectors of data at a time.
+	add		$-8*VL, LEN
+	jl		.Lloop_8x_done\@
+.Lloop_8x\@:
+	_prepare_2_ctr_vecs	\is_xctr, 0, 1
+	_prepare_2_ctr_vecs	\is_xctr, 2, 3
+	_prepare_2_ctr_vecs	\is_xctr, 4, 5
+	_prepare_2_ctr_vecs	\is_xctr, 6, 7
+	_aesenc_loop	0,1,2,3,4,5,6,7
+	_aesenclast_and_xor 0,1,2,3,4,5,6,7
+	sub		$-8*VL, SRC
+	sub		$-8*VL, DST
+	add		$-8*VL, LEN
+	jge		.Lloop_8x\@
+.Lloop_8x_done\@:
+	sub		$-8*VL, LEN
+	jz		.Ldone\@
+
+	// 1 <= LEN < 8*VL.  Generate 2, 4, or 8 more vectors of keystream
+	// blocks, depending on the remaining LEN.
+
+	_prepare_2_ctr_vecs	\is_xctr, 0, 1
+	_prepare_2_ctr_vecs	\is_xctr, 2, 3
+	cmp		$4*VL, LEN
+	jle		.Lenc_tail_atmost4vecs\@
+
+	// 4*VL < LEN < 8*VL.  Generate 8 vectors of keystream blocks.  Use the
+	// first 4 to XOR 4 full vectors of data.  Then XOR the remaining data.
+	_prepare_2_ctr_vecs	\is_xctr, 4, 5
+	_prepare_2_ctr_vecs	\is_xctr, 6, 7, final=1
+	_aesenc_loop	0,1,2,3,4,5,6,7
+	_aesenclast_and_xor 0,1,2,3
+	vaesenclast	RNDKEYLAST, AESDATA4, AESDATA0
+	vaesenclast	RNDKEYLAST, AESDATA5, AESDATA1
+	vaesenclast	RNDKEYLAST, AESDATA6, AESDATA2
+	vaesenclast	RNDKEYLAST, AESDATA7, AESDATA3
+	sub		$-4*VL, SRC
+	sub		$-4*VL, DST
+	add		$-4*VL, LEN
+	cmp		$1*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_0\@
+	_xor_data	0
+	cmp		$2*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_1\@
+	_xor_data	1
+	cmp		$3*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_2\@
+	_xor_data	2
+	cmp		$4*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_3\@
+	_xor_data	3
+	jmp		.Ldone\@
+
+.Lenc_tail_atmost4vecs\@:
+	cmp		$2*VL, LEN
+	jle		.Lenc_tail_atmost2vecs\@
+
+	// 2*VL < LEN <= 4*VL.  Generate 4 vectors of keystream blocks.  Use the
+	// first 2 to XOR 2 full vectors of data.  Then XOR the remaining data.
+	_aesenc_loop	0,1,2,3
+	_aesenclast_and_xor 0,1
+	vaesenclast	RNDKEYLAST, AESDATA2, AESDATA0
+	vaesenclast	RNDKEYLAST, AESDATA3, AESDATA1
+	sub		$-2*VL, SRC
+	sub		$-2*VL, DST
+	add		$-2*VL, LEN
+	jmp		.Lxor_tail_upto2vecs\@
+
+.Lenc_tail_atmost2vecs\@:
+	// 1 <= LEN <= 2*VL.  Generate 2 vectors of keystream blocks.  Then XOR
+	// the remaining data.
+	_aesenc_loop	0,1
+	vaesenclast	RNDKEYLAST, AESDATA0, AESDATA0
+	vaesenclast	RNDKEYLAST, AESDATA1, AESDATA1
+
+.Lxor_tail_upto2vecs\@:
+	cmp		$1*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_0\@
+	_xor_data	0
+	cmp		$2*VL-1, LEN
+	jle		.Lxor_tail_partial_vec_1\@
+	_xor_data	1
+	jmp		.Ldone\@
+
+.Lxor_tail_partial_vec_1\@:
+	add		$-1*VL, LEN
+	jz		.Ldone\@
+	sub		$-1*VL, SRC
+	sub		$-1*VL, DST
+	_vmovdqa	AESDATA1, AESDATA0
+	jmp		.Lxor_tail_partial_vec_0\@
+
+.Lxor_tail_partial_vec_2\@:
+	add		$-2*VL, LEN
+	jz		.Ldone\@
+	sub		$-2*VL, SRC
+	sub		$-2*VL, DST
+	_vmovdqa	AESDATA2, AESDATA0
+	jmp		.Lxor_tail_partial_vec_0\@
+
+.Lxor_tail_partial_vec_3\@:
+	add		$-3*VL, LEN
+	jz		.Ldone\@
+	sub		$-3*VL, SRC
+	sub		$-3*VL, DST
+	_vmovdqa	AESDATA3, AESDATA0
+
+.Lxor_tail_partial_vec_0\@:
+	// XOR the remaining 1 <= LEN < VL bytes.  It's easy if masked
+	// loads/stores are available; otherwise it's a bit harder...
+.if USE_AVX512
+	mov		$-1, %rax
+	bzhi		LEN64, %rax, %rax
+	kmovq		%rax, %k1
+	vmovdqu8	(SRC), AESDATA1{%k1}{z}
+	vpxord		AESDATA1, AESDATA0, AESDATA0
+	vmovdqu8	AESDATA0, (DST){%k1}
+.else
+  .if VL == 32
+	cmp		$16, LEN
+	jl		1f
+	vpxor		(SRC), AESDATA0_XMM, AESDATA1_XMM
+	vmovdqu		AESDATA1_XMM, (DST)
+	add		$16, SRC
+	add		$16, DST
+	sub		$16, LEN
+	jz		.Ldone\@
+	vextracti128	$1, AESDATA0, AESDATA0_XMM
+1:
+  .endif
+	mov		LEN, %r10d
+	_load_partial_block	SRC, AESDATA1_XMM, KEY, KEY32
+	vpxor		AESDATA1_XMM, AESDATA0_XMM, AESDATA0_XMM
+	mov		%r10d, %ecx
+	_store_partial_block	AESDATA0_XMM, DST, KEY, KEY32
+.endif
+
+.Ldone\@:
+.if VL > 16
+	vzeroupper
+.endif
+	RET
+.endm
+
+// Below are the definitions of the functions generated by the above macro.
+// They have the following prototypes:
+//
+//
+// void aes_ctr64_crypt_##suffix(const struct crypto_aes_ctx *key,
+//				 const u8 *src, u8 *dst, int len,
+//				 const u64 le_ctr[2]);
+//
+// void aes_xctr_crypt_##suffix(const struct crypto_aes_ctx *key,
+//				const u8 *src, u8 *dst, int len,
+//				const u8 iv[AES_BLOCK_SIZE], u64 ctr);
+//
+// Both functions generate |len| bytes of keystream, XOR it with the data from
+// |src|, and write the result to |dst|.  On non-final calls, |len| must be a
+// multiple of 16.  On the final call, |len| can be any value.
+//
+// aes_ctr64_crypt_* implement "regular" CTR, where the keystream is generated
+// from a 128-bit big endian counter that increments by 1 for each AES block.
+// HOWEVER, to keep the assembly code simple, some of the counter management is
+// left to the caller.  aes_ctr64_crypt_* take the counter in little endian
+// form, only increment the low 64 bits internally, do the conversion to big
+// endian internally, and don't write the updated counter back to memory.  The
+// caller is responsible for converting the starting IV to the little endian
+// le_ctr, detecting the (very rare) case of a carry out of the low 64 bits
+// being needed and splitting at that point with a carry done in between, and
+// updating le_ctr after each part if the message is multi-part.
+//
+// aes_xctr_crypt_* implement XCTR as specified in "Length-preserving encryption
+// with HCTR2" (https://eprint.iacr.org/2021/1441.pdf).  XCTR is an
+// easier-to-implement variant of CTR that uses little endian byte order and
+// eliminates carries.  |ctr| is the per-message block counter starting at 1.
+
+.set	VL, 16
+.set	USE_AVX512, 0
+SYM_TYPED_FUNC_START(aes_ctr64_crypt_aesni_avx)
+	_aes_ctr_crypt	0
+SYM_FUNC_END(aes_ctr64_crypt_aesni_avx)
+SYM_TYPED_FUNC_START(aes_xctr_crypt_aesni_avx)
+	_aes_ctr_crypt	1
+SYM_FUNC_END(aes_xctr_crypt_aesni_avx)
+
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+.set	VL, 32
+.set	USE_AVX512, 0
+SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx2)
+	_aes_ctr_crypt	0
+SYM_FUNC_END(aes_ctr64_crypt_vaes_avx2)
+SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx2)
+	_aes_ctr_crypt	1
+SYM_FUNC_END(aes_xctr_crypt_vaes_avx2)
+
+.set	VL, 64
+.set	USE_AVX512, 1
+SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx512)
+	_aes_ctr_crypt	0
+SYM_FUNC_END(aes_ctr64_crypt_vaes_avx512)
+SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx512)
+	_aes_ctr_crypt	1
+SYM_FUNC_END(aes_xctr_crypt_vaes_avx512)
+#endif // CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index 8a3e23fbcf85..db79cdf81588 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -1,11 +1,50 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * AES-XTS for modern x86_64 CPUs
- *
- * Copyright 2024 Google LLC
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
+/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */
+//
+// AES-XTS for modern x86_64 CPUs
+//
+// Copyright 2024 Google LLC
+//
+// Author: Eric Biggers <ebiggers@google.com>
+//
+//------------------------------------------------------------------------------
+//
+// This file is dual-licensed, meaning that you can use it under your choice of
+// either of the following two licenses:
+//
+// Licensed under the Apache License 2.0 (the "License").  You may obtain a copy
+// of the License at
+//
+//	http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+// or
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+// 1. Redistributions of source code must retain the above copyright notice,
+//    this list of conditions and the following disclaimer.
+//
+// 2. Redistributions in binary form must reproduce the above copyright
+//    notice, this list of conditions and the following disclaimer in the
+//    documentation and/or other materials provided with the distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+// POSSIBILITY OF SUCH DAMAGE.
 
 /*
  * This file implements AES-XTS for modern x86_64 CPUs.  To handle the
@@ -13,32 +52,25 @@
  * different code, it uses a macro to generate several implementations that
  * share similar source code but are targeted at different CPUs, listed below:
  *
- * AES-NI + AVX
+ * AES-NI && AVX
  *    - 128-bit vectors (1 AES block per vector)
  *    - VEX-coded instructions
  *    - xmm0-xmm15
  *    - This is for older CPUs that lack VAES but do have AVX.
  *
- * VAES + VPCLMULQDQ + AVX2
+ * VAES && VPCLMULQDQ && AVX2
  *    - 256-bit vectors (2 AES blocks per vector)
  *    - VEX-coded instructions
  *    - ymm0-ymm15
- *    - This is for CPUs that have VAES but lack AVX512 or AVX10,
- *      e.g. Intel's Alder Lake and AMD's Zen 3.
+ *    - This is for CPUs that have VAES but either lack AVX512 (e.g. Intel's
+ *      Alder Lake and AMD's Zen 3) or downclock too eagerly when using zmm
+ *      registers (e.g. Intel's Ice Lake).
  *
- * VAES + VPCLMULQDQ + AVX10/256 + BMI2
- *    - 256-bit vectors (2 AES blocks per vector)
+ * VAES && VPCLMULQDQ && AVX512BW && AVX512VL && BMI2
+ *    - 512-bit vectors (4 AES blocks per vector)
  *    - EVEX-coded instructions
- *    - ymm0-ymm31
- *    - This is for CPUs that have AVX512 but where using zmm registers causes
- *      downclocking, and for CPUs that have AVX10/256 but not AVX10/512.
- *    - By "AVX10/256" we really mean (AVX512BW + AVX512VL) || AVX10/256.
- *      To avoid confusion with 512-bit, we just write AVX10/256.
- *
- * VAES + VPCLMULQDQ + AVX10/512 + BMI2
- *    - Same as the previous one, but upgrades to 512-bit vectors
- *      (4 AES blocks per vector) in zmm0-zmm31.
- *    - This is for CPUs that have good AVX512 or AVX10/512 support.
+ *    - zmm0-zmm31
+ *    - This is for CPUs that have good AVX512 support.
  *
  * This file doesn't have an implementation for AES-NI alone (without AVX), as
  * the lack of VEX would make all the assembly code different.
@@ -68,9 +100,20 @@
 	// exists when there's a carry out of the low 64 bits of the tweak.
 	.quad	0x87, 1
 
+	// These are the shift amounts that are needed when multiplying by [x^0,
+	// x^1, x^2, x^3] to compute the first vector of tweaks when VL=64.
+	//
+	// The right shifts by 64 are expected to zeroize the destination.
+	// 'vpsrlvq' is indeed defined to do that; i.e. it doesn't truncate the
+	// amount to 64 & 63 = 0 like the 'shr' scalar shift instruction would.
+.Lrshift_amounts:
+	.byte	64, 64, 63, 63, 62, 62, 61, 61
+.Llshift_amounts:
+	.byte	0, 0, 1, 1, 2, 2, 3, 3
+
 	// This table contains constants for vpshufb and vpblendvb, used to
 	// handle variable byte shifts and blending during ciphertext stealing
-	// on CPUs that don't support AVX10-style masking.
+	// on CPUs that don't support AVX512-style masking.
 .Lcts_permute_table:
 	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
 	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
@@ -99,7 +142,7 @@
 .irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
 	_define_Vi	\i
 .endr
-.if USE_AVX10
+.if USE_AVX512
 .irp i, 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
 	_define_Vi	\i
 .endr
@@ -154,7 +197,7 @@
 	// keys to the *end* of this register range.  I.e., AES-128 uses
 	// KEY5-KEY14, AES-192 uses KEY3-KEY14, and AES-256 uses KEY1-KEY14.
 	// (All also use KEY0 for the XOR-only "round" at the beginning.)
-.if USE_AVX10
+.if USE_AVX512
 	.set	KEY1_XMM,	%xmm16
 	.set	KEY1,		V16
 	.set	KEY2_XMM,	%xmm17
@@ -188,7 +231,6 @@
 .endm
 
 // Move a vector between memory and a register.
-// The register operand must be in the first 16 vector registers.
 .macro	_vmovdqu	src, dst
 .if VL < 64
 	vmovdqu		\src, \dst
@@ -199,9 +241,9 @@
 
 // Broadcast a 128-bit value into a vector.
 .macro	_vbroadcast128	src, dst
-.if VL == 16 && !USE_AVX10
+.if VL == 16
 	vmovdqu		\src, \dst
-.elseif VL == 32 && !USE_AVX10
+.elseif VL == 32
 	vbroadcasti128	\src, \dst
 .else
 	vbroadcasti32x4	\src, \dst
@@ -209,7 +251,6 @@
 .endm
 
 // XOR two vectors together.
-// Any register operands must be in the first 16 vector registers.
 .macro	_vpxor	src1, src2, dst
 .if VL < 64
 	vpxor		\src1, \src2, \dst
@@ -220,7 +261,7 @@
 
 // XOR three vectors together.
 .macro	_xor3	src1, src2, src3_and_dst
-.if USE_AVX10
+.if USE_AVX512
 	// vpternlogd with immediate 0x96 is a three-argument XOR.
 	vpternlogd	$0x96, \src1, \src2, \src3_and_dst
 .else
@@ -235,7 +276,7 @@
 	vpshufd		$0x13, \src, \tmp
 	vpaddq		\src, \src, \dst
 	vpsrad		$31, \tmp, \tmp
-.if USE_AVX10
+.if USE_AVX512
 	vpternlogd	$0x78, GF_POLY_XMM, \tmp, \dst
 .else
 	vpand		GF_POLY_XMM, \tmp, \tmp
@@ -264,52 +305,75 @@
 // Given the first XTS tweak at (TWEAK), compute the first set of tweaks and
 // store them in the vector registers TWEAK0-TWEAK3.  Clobbers V0-V5.
 .macro	_compute_first_set_of_tweaks
-	vmovdqu		(TWEAK), TWEAK0_XMM
-	_vbroadcast128	.Lgf_poly(%rip), GF_POLY
 .if VL == 16
-	// With VL=16, multiplying by x serially is fastest.
+	vmovdqu		(TWEAK), TWEAK0_XMM
+	vmovdqu		.Lgf_poly(%rip), GF_POLY
 	_next_tweak	TWEAK0, %xmm0, TWEAK1
 	_next_tweak	TWEAK1, %xmm0, TWEAK2
 	_next_tweak	TWEAK2, %xmm0, TWEAK3
-.else
-.if VL == 32
-	// Compute the second block of TWEAK0.
+.elseif VL == 32
+	vmovdqu		(TWEAK), TWEAK0_XMM
+	vbroadcasti128	.Lgf_poly(%rip), GF_POLY
+
+	// Compute the first vector of tweaks.
 	_next_tweak	TWEAK0_XMM, %xmm0, %xmm1
 	vinserti128	$1, %xmm1, TWEAK0, TWEAK0
-.elseif VL == 64
-	// Compute the remaining blocks of TWEAK0.
-	_next_tweak	TWEAK0_XMM, %xmm0, %xmm1
-	_next_tweak	%xmm1, %xmm0, %xmm2
-	_next_tweak	%xmm2, %xmm0, %xmm3
-	vinserti32x4	$1, %xmm1, TWEAK0, TWEAK0
-	vinserti32x4	$2, %xmm2, TWEAK0, TWEAK0
-	vinserti32x4	$3, %xmm3, TWEAK0, TWEAK0
-.endif
-	// Compute TWEAK[1-3] from TWEAK0.
-	vpsrlq		$64 - 1*VL/16, TWEAK0, V0
-	vpsrlq		$64 - 2*VL/16, TWEAK0, V2
-	vpsrlq		$64 - 3*VL/16, TWEAK0, V4
+
+	// Compute the next three vectors of tweaks:
+	//	TWEAK1 = TWEAK0 * [x^2, x^2]
+	//	TWEAK2 = TWEAK0 * [x^4, x^4]
+	//	TWEAK3 = TWEAK0 * [x^6, x^6]
+	vpsrlq		$64 - 2, TWEAK0, V0
+	vpsrlq		$64 - 4, TWEAK0, V2
+	vpsrlq		$64 - 6, TWEAK0, V4
 	vpclmulqdq	$0x01, GF_POLY, V0, V1
 	vpclmulqdq	$0x01, GF_POLY, V2, V3
 	vpclmulqdq	$0x01, GF_POLY, V4, V5
 	vpslldq		$8, V0, V0
 	vpslldq		$8, V2, V2
 	vpslldq		$8, V4, V4
-	vpsllq		$1*VL/16, TWEAK0, TWEAK1
-	vpsllq		$2*VL/16, TWEAK0, TWEAK2
-	vpsllq		$3*VL/16, TWEAK0, TWEAK3
-.if USE_AVX10
-	vpternlogd	$0x96, V0, V1, TWEAK1
-	vpternlogd	$0x96, V2, V3, TWEAK2
-	vpternlogd	$0x96, V4, V5, TWEAK3
-.else
+	vpsllq		$2, TWEAK0, TWEAK1
+	vpsllq		$4, TWEAK0, TWEAK2
+	vpsllq		$6, TWEAK0, TWEAK3
 	vpxor		V0, TWEAK1, TWEAK1
 	vpxor		V2, TWEAK2, TWEAK2
 	vpxor		V4, TWEAK3, TWEAK3
 	vpxor		V1, TWEAK1, TWEAK1
 	vpxor		V3, TWEAK2, TWEAK2
 	vpxor		V5, TWEAK3, TWEAK3
-.endif
+.else
+	vbroadcasti32x4	(TWEAK), TWEAK0
+	vbroadcasti32x4	.Lgf_poly(%rip), GF_POLY
+
+	// Compute the first vector of tweaks:
+	//	TWEAK0 = broadcast128(TWEAK) * [x^0, x^1, x^2, x^3]
+	vpmovzxbq	.Lrshift_amounts(%rip), V4
+	vpsrlvq		V4, TWEAK0, V0
+	vpclmulqdq	$0x01, GF_POLY, V0, V1
+	vpmovzxbq	.Llshift_amounts(%rip), V4
+	vpslldq		$8, V0, V0
+	vpsllvq		V4, TWEAK0, TWEAK0
+	vpternlogd	$0x96, V0, V1, TWEAK0
+
+	// Compute the next three vectors of tweaks:
+	//	TWEAK1 = TWEAK0 * [x^4, x^4, x^4, x^4]
+	//	TWEAK2 = TWEAK0 * [x^8, x^8, x^8, x^8]
+	//	TWEAK3 = TWEAK0 * [x^12, x^12, x^12, x^12]
+	// x^8 only needs byte-aligned shifts, so optimize accordingly.
+	vpsrlq		$64 - 4, TWEAK0, V0
+	vpsrldq		$(64 - 8) / 8, TWEAK0, V2
+	vpsrlq		$64 - 12, TWEAK0, V4
+	vpclmulqdq	$0x01, GF_POLY, V0, V1
+	vpclmulqdq	$0x01, GF_POLY, V2, V3
+	vpclmulqdq	$0x01, GF_POLY, V4, V5
+	vpslldq		$8, V0, V0
+	vpslldq		$8, V4, V4
+	vpsllq		$4, TWEAK0, TWEAK1
+	vpslldq		$8 / 8, TWEAK0, TWEAK2
+	vpsllq		$12, TWEAK0, TWEAK3
+	vpternlogd	$0x96, V0, V1, TWEAK1
+	vpxord		V3, TWEAK2, TWEAK2
+	vpternlogd	$0x96, V4, V5, TWEAK3
 .endif
 .endm
 
@@ -435,26 +499,26 @@
 	lea		OFFS-16(KEY, KEYLEN64, 4), KEY
 
 	// If all 32 SIMD registers are available, cache all the round keys.
-.if USE_AVX10
+.if USE_AVX512
 	cmp		$24, KEYLEN
 	jl		.Laes128\@
 	je		.Laes192\@
-	_vbroadcast128	-6*16(KEY), KEY1
-	_vbroadcast128	-5*16(KEY), KEY2
+	vbroadcasti32x4	-6*16(KEY), KEY1
+	vbroadcasti32x4	-5*16(KEY), KEY2
 .Laes192\@:
-	_vbroadcast128	-4*16(KEY), KEY3
-	_vbroadcast128	-3*16(KEY), KEY4
+	vbroadcasti32x4	-4*16(KEY), KEY3
+	vbroadcasti32x4	-3*16(KEY), KEY4
 .Laes128\@:
-	_vbroadcast128	-2*16(KEY), KEY5
-	_vbroadcast128	-1*16(KEY), KEY6
-	_vbroadcast128	0*16(KEY), KEY7
-	_vbroadcast128	1*16(KEY), KEY8
-	_vbroadcast128	2*16(KEY), KEY9
-	_vbroadcast128	3*16(KEY), KEY10
-	_vbroadcast128	4*16(KEY), KEY11
-	_vbroadcast128	5*16(KEY), KEY12
-	_vbroadcast128	6*16(KEY), KEY13
-	_vbroadcast128	7*16(KEY), KEY14
+	vbroadcasti32x4	-2*16(KEY), KEY5
+	vbroadcasti32x4	-1*16(KEY), KEY6
+	vbroadcasti32x4	0*16(KEY), KEY7
+	vbroadcasti32x4	1*16(KEY), KEY8
+	vbroadcasti32x4	2*16(KEY), KEY9
+	vbroadcasti32x4	3*16(KEY), KEY10
+	vbroadcasti32x4	4*16(KEY), KEY11
+	vbroadcasti32x4	5*16(KEY), KEY12
+	vbroadcasti32x4	6*16(KEY), KEY13
+	vbroadcasti32x4	7*16(KEY), KEY14
 .endif
 .endm
 
@@ -482,7 +546,7 @@
 // using the same key for all block(s).  The round key is loaded from the
 // appropriate register or memory location for round \i.  May clobber \tmp.
 .macro _vaes_1x		enc, i, xmm_suffix, data, tmp
-.if USE_AVX10
+.if USE_AVX512
 	_vaes		\enc, KEY\i\xmm_suffix, \data
 .else
 .ifnb \xmm_suffix
@@ -499,7 +563,7 @@
 // appropriate register or memory location for round \i.  In addition, does two
 // steps of the computation of the next set of tweaks.  May clobber V4 and V5.
 .macro	_vaes_4x	enc, i
-.if USE_AVX10
+.if USE_AVX512
 	_tweak_step	(2*(\i-5))
 	_vaes		\enc, KEY\i, V0
 	_vaes		\enc, KEY\i, V1
@@ -535,7 +599,7 @@
 .irp i, 5,6,7,8,9,10,11,12,13
 	_vaes_1x	\enc, \i, \xmm_suffix, \data, tmp=\tmp
 .endr
-.if USE_AVX10
+.if USE_AVX512
 	vpxord		KEY14\xmm_suffix, \tweak, \tmp
 .else
 .ifnb \xmm_suffix
@@ -578,11 +642,11 @@
 	// This is the main loop, en/decrypting 4*VL bytes per iteration.
 
 	// XOR each source block with its tweak and the zero-th round key.
-.if USE_AVX10
-	_vmovdqu	0*VL(SRC), V0
-	_vmovdqu	1*VL(SRC), V1
-	_vmovdqu	2*VL(SRC), V2
-	_vmovdqu	3*VL(SRC), V3
+.if USE_AVX512
+	vmovdqu8	0*VL(SRC), V0
+	vmovdqu8	1*VL(SRC), V1
+	vmovdqu8	2*VL(SRC), V2
+	vmovdqu8	3*VL(SRC), V3
 	vpternlogd	$0x96, TWEAK0, KEY0, V0
 	vpternlogd	$0x96, TWEAK1, KEY0, V1
 	vpternlogd	$0x96, TWEAK2, KEY0, V2
@@ -615,7 +679,7 @@
 	// Reduce latency by doing the XOR before the vaesenclast, utilizing the
 	// property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a)
 	// (and likewise for vaesdeclast).
-.if USE_AVX10
+.if USE_AVX512
 	_tweak_step	18
 	_tweak_step	19
 	vpxord		TWEAK0, KEY14, V4
@@ -723,7 +787,7 @@
 	_aes_crypt	\enc, _XMM, TWEAK1_XMM, %xmm0, tmp=%xmm1
 .endif
 
-.if USE_AVX10
+.if USE_AVX512
 	// Create a mask that has the first LEN bits set.
 	mov		$-1, %r9d
 	bzhi		LEN, %r9d, %r9d
@@ -772,7 +836,7 @@
 //			   u8 iv[AES_BLOCK_SIZE]);
 //
 // Encrypt |iv| using the AES key |tweak_key| to get the first tweak.  Assumes
-// that the CPU supports AES-NI and AVX, but not necessarily VAES or AVX10.
+// that the CPU supports AES-NI and AVX, but not necessarily VAES or AVX512.
 SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
 	.set	TWEAK_KEY,	%rdi
 	.set	IV,		%rsi
@@ -814,7 +878,7 @@ SYM_FUNC_END(aes_xts_encrypt_iv)
 // multiple of 16, then this function updates |tweak| to contain the next tweak.
 
 .set	VL, 16
-.set	USE_AVX10, 0
+.set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_xts_encrypt_aesni_avx)
 	_aes_xts_crypt	1
 SYM_FUNC_END(aes_xts_encrypt_aesni_avx)
@@ -824,7 +888,7 @@ SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
 
 #if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
 .set	VL, 32
-.set	USE_AVX10, 0
+.set	USE_AVX512, 0
 SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
 	_aes_xts_crypt	1
 SYM_FUNC_END(aes_xts_encrypt_vaes_avx2)
@@ -832,21 +896,12 @@ SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx2)
 	_aes_xts_crypt	0
 SYM_FUNC_END(aes_xts_decrypt_vaes_avx2)
 
-.set	VL, 32
-.set	USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_256)
-	_aes_xts_crypt	1
-SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_256)
-SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_256)
-	_aes_xts_crypt	0
-SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_256)
-
 .set	VL, 64
-.set	USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_512)
+.set	USE_AVX512, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx512)
 	_aes_xts_crypt	1
-SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_512)
-SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_512)
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx512)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx512)
 	_aes_xts_crypt	0
-SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_512)
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx512)
 #endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
deleted file mode 100644
index 2402b9418cd7..000000000000
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ /dev/null
@@ -1,597 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */
-/*
- * AES CTR mode by8 optimization with AVX instructions. (x86_64)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Sean Gulley <sean.m.gulley@intel.com>
- * Chandramouli Narayanan <mouli@linux.intel.com>
- */
-/*
- * This is AES128/192/256 CTR mode optimization implementation. It requires
- * the support of Intel(R) AESNI and AVX instructions.
- *
- * This work was inspired by the AES CTR mode optimization published
- * in Intel Optimized IPSEC Cryptographic library.
- * Additional information on it can be found at:
- *    https://github.com/intel/intel-ipsec-mb
- */
-
-#include <linux/linkage.h>
-
-#define VMOVDQ		vmovdqu
-
-/*
- * Note: the "x" prefix in these aliases means "this is an xmm register".  The
- * alias prefixes have no relation to XCTR where the "X" prefix means "XOR
- * counter".
- */
-#define xdata0		%xmm0
-#define xdata1		%xmm1
-#define xdata2		%xmm2
-#define xdata3		%xmm3
-#define xdata4		%xmm4
-#define xdata5		%xmm5
-#define xdata6		%xmm6
-#define xdata7		%xmm7
-#define xcounter	%xmm8	// CTR mode only
-#define xiv		%xmm8	// XCTR mode only
-#define xbyteswap	%xmm9	// CTR mode only
-#define xtmp		%xmm9	// XCTR mode only
-#define xkey0		%xmm10
-#define xkey4		%xmm11
-#define xkey8		%xmm12
-#define xkey12		%xmm13
-#define xkeyA		%xmm14
-#define xkeyB		%xmm15
-
-#define p_in		%rdi
-#define p_iv		%rsi
-#define p_keys		%rdx
-#define p_out		%rcx
-#define num_bytes	%r8
-#define counter		%r9	// XCTR mode only
-#define tmp		%r10
-#define	DDQ_DATA	0
-#define	XDATA		1
-#define KEY_128		1
-#define KEY_192		2
-#define KEY_256		3
-
-.section .rodata
-.align 16
-
-byteswap_const:
-	.octa 0x000102030405060708090A0B0C0D0E0F
-ddq_low_msk:
-	.octa 0x0000000000000000FFFFFFFFFFFFFFFF
-ddq_high_add_1:
-	.octa 0x00000000000000010000000000000000
-ddq_add_1:
-	.octa 0x00000000000000000000000000000001
-ddq_add_2:
-	.octa 0x00000000000000000000000000000002
-ddq_add_3:
-	.octa 0x00000000000000000000000000000003
-ddq_add_4:
-	.octa 0x00000000000000000000000000000004
-ddq_add_5:
-	.octa 0x00000000000000000000000000000005
-ddq_add_6:
-	.octa 0x00000000000000000000000000000006
-ddq_add_7:
-	.octa 0x00000000000000000000000000000007
-ddq_add_8:
-	.octa 0x00000000000000000000000000000008
-
-.text
-
-/* generate a unique variable for ddq_add_x */
-
-/* generate a unique variable for xmm register */
-.macro setxdata n
-	var_xdata = %xmm\n
-.endm
-
-/* club the numeric 'id' to the symbol 'name' */
-
-.macro club name, id
-.altmacro
-	.if \name == XDATA
-		setxdata %\id
-	.endif
-.noaltmacro
-.endm
-
-/*
- * do_aes num_in_par load_keys key_len
- * This increments p_in, but not p_out
- */
-.macro do_aes b, k, key_len, xctr
-	.set by, \b
-	.set load_keys, \k
-	.set klen, \key_len
-
-	.if (load_keys)
-		vmovdqa	0*16(p_keys), xkey0
-	.endif
-
-	.if \xctr
-		movq counter, xtmp
-		.set i, 0
-		.rept (by)
-			club XDATA, i
-			vpaddq	(ddq_add_1 + 16 * i)(%rip), xtmp, var_xdata
-			.set i, (i +1)
-		.endr
-		.set i, 0
-		.rept (by)
-			club	XDATA, i
-			vpxor	xiv, var_xdata, var_xdata
-			.set i, (i +1)
-		.endr
-	.else
-		vpshufb	xbyteswap, xcounter, xdata0
-		.set i, 1
-		.rept (by - 1)
-			club XDATA, i
-			vpaddq	(ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata
-			vptest	ddq_low_msk(%rip), var_xdata
-			jnz 1f
-			vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
-			vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
-			1:
-			vpshufb	xbyteswap, var_xdata, var_xdata
-			.set i, (i +1)
-		.endr
-	.endif
-
-	vmovdqa	1*16(p_keys), xkeyA
-
-	vpxor	xkey0, xdata0, xdata0
-	.if \xctr
-		add $by, counter
-	.else
-		vpaddq	(ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter
-		vptest	ddq_low_msk(%rip), xcounter
-		jnz	1f
-		vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
-		1:
-	.endif
-
-	.set i, 1
-	.rept (by - 1)
-		club XDATA, i
-		vpxor	xkey0, var_xdata, var_xdata
-		.set i, (i +1)
-	.endr
-
-	vmovdqa	2*16(p_keys), xkeyB
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 1 */
-		.set i, (i +1)
-	.endr
-
-	.if (klen == KEY_128)
-		.if (load_keys)
-			vmovdqa	3*16(p_keys), xkey4
-		.endif
-	.else
-		vmovdqa	3*16(p_keys), xkeyA
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		vaesenc	xkeyB, var_xdata, var_xdata		/* key 2 */
-		.set i, (i +1)
-	.endr
-
-	add	$(16*by), p_in
-
-	.if (klen == KEY_128)
-		vmovdqa	4*16(p_keys), xkeyB
-	.else
-		.if (load_keys)
-			vmovdqa	4*16(p_keys), xkey4
-		.endif
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 3 */
-		.if (klen == KEY_128)
-			vaesenc	xkey4, var_xdata, var_xdata
-		.else
-			vaesenc	xkeyA, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	vmovdqa	5*16(p_keys), xkeyA
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 4 */
-		.if (klen == KEY_128)
-			vaesenc	xkeyB, var_xdata, var_xdata
-		.else
-			vaesenc	xkey4, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	.if (klen == KEY_128)
-		.if (load_keys)
-			vmovdqa	6*16(p_keys), xkey8
-		.endif
-	.else
-		vmovdqa	6*16(p_keys), xkeyB
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 5 */
-		.set i, (i +1)
-	.endr
-
-	vmovdqa	7*16(p_keys), xkeyA
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 6 */
-		.if (klen == KEY_128)
-			vaesenc	xkey8, var_xdata, var_xdata
-		.else
-			vaesenc	xkeyB, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	.if (klen == KEY_128)
-		vmovdqa	8*16(p_keys), xkeyB
-	.else
-		.if (load_keys)
-			vmovdqa	8*16(p_keys), xkey8
-		.endif
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 7 */
-		.set i, (i +1)
-	.endr
-
-	.if (klen == KEY_128)
-		.if (load_keys)
-			vmovdqa	9*16(p_keys), xkey12
-		.endif
-	.else
-		vmovdqa	9*16(p_keys), xkeyA
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 8 */
-		.if (klen == KEY_128)
-			vaesenc	xkeyB, var_xdata, var_xdata
-		.else
-			vaesenc	xkey8, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	vmovdqa	10*16(p_keys), xkeyB
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 9 */
-		.if (klen == KEY_128)
-			vaesenc	xkey12, var_xdata, var_xdata
-		.else
-			vaesenc	xkeyA, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	.if (klen != KEY_128)
-		vmovdqa	11*16(p_keys), xkeyA
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		/* key 10 */
-		.if (klen == KEY_128)
-			vaesenclast	xkeyB, var_xdata, var_xdata
-		.else
-			vaesenc	xkeyB, var_xdata, var_xdata
-		.endif
-		.set i, (i +1)
-	.endr
-
-	.if (klen != KEY_128)
-		.if (load_keys)
-			vmovdqa	12*16(p_keys), xkey12
-		.endif
-
-		.set i, 0
-		.rept by
-			club XDATA, i
-			vaesenc	xkeyA, var_xdata, var_xdata	/* key 11 */
-			.set i, (i +1)
-		.endr
-
-		.if (klen == KEY_256)
-			vmovdqa	13*16(p_keys), xkeyA
-		.endif
-
-		.set i, 0
-		.rept by
-			club XDATA, i
-			.if (klen == KEY_256)
-				/* key 12 */
-				vaesenc	xkey12, var_xdata, var_xdata
-			.else
-				vaesenclast xkey12, var_xdata, var_xdata
-			.endif
-			.set i, (i +1)
-		.endr
-
-		.if (klen == KEY_256)
-			vmovdqa	14*16(p_keys), xkeyB
-
-			.set i, 0
-			.rept by
-				club XDATA, i
-				/* key 13 */
-				vaesenc	xkeyA, var_xdata, var_xdata
-				.set i, (i +1)
-			.endr
-
-			.set i, 0
-			.rept by
-				club XDATA, i
-				/* key 14 */
-				vaesenclast	xkeyB, var_xdata, var_xdata
-				.set i, (i +1)
-			.endr
-		.endif
-	.endif
-
-	.set i, 0
-	.rept (by / 2)
-		.set j, (i+1)
-		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
-		VMOVDQ	(j*16 - 16*by)(p_in), xkeyB
-		club XDATA, i
-		vpxor	xkeyA, var_xdata, var_xdata
-		club XDATA, j
-		vpxor	xkeyB, var_xdata, var_xdata
-		.set i, (i+2)
-	.endr
-
-	.if (i < by)
-		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
-		club XDATA, i
-		vpxor	xkeyA, var_xdata, var_xdata
-	.endif
-
-	.set i, 0
-	.rept by
-		club XDATA, i
-		VMOVDQ	var_xdata, i*16(p_out)
-		.set i, (i+1)
-	.endr
-.endm
-
-.macro do_aes_load val, key_len, xctr
-	do_aes \val, 1, \key_len, \xctr
-.endm
-
-.macro do_aes_noload val, key_len, xctr
-	do_aes \val, 0, \key_len, \xctr
-.endm
-
-/* main body of aes ctr load */
-
-.macro do_aes_ctrmain key_len, xctr
-	cmp	$16, num_bytes
-	jb	.Ldo_return2\xctr\key_len
-
-	.if \xctr
-		shr	$4, counter
-		vmovdqu	(p_iv), xiv
-	.else
-		vmovdqa	byteswap_const(%rip), xbyteswap
-		vmovdqu	(p_iv), xcounter
-		vpshufb	xbyteswap, xcounter, xcounter
-	.endif
-
-	mov	num_bytes, tmp
-	and	$(7*16), tmp
-	jz	.Lmult_of_8_blks\xctr\key_len
-
-	/* 1 <= tmp <= 7 */
-	cmp	$(4*16), tmp
-	jg	.Lgt4\xctr\key_len
-	je	.Leq4\xctr\key_len
-
-.Llt4\xctr\key_len:
-	cmp	$(2*16), tmp
-	jg	.Leq3\xctr\key_len
-	je	.Leq2\xctr\key_len
-
-.Leq1\xctr\key_len:
-	do_aes_load	1, \key_len, \xctr
-	add	$(1*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Leq2\xctr\key_len:
-	do_aes_load	2, \key_len, \xctr
-	add	$(2*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-
-.Leq3\xctr\key_len:
-	do_aes_load	3, \key_len, \xctr
-	add	$(3*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Leq4\xctr\key_len:
-	do_aes_load	4, \key_len, \xctr
-	add	$(4*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Lgt4\xctr\key_len:
-	cmp	$(6*16), tmp
-	jg	.Leq7\xctr\key_len
-	je	.Leq6\xctr\key_len
-
-.Leq5\xctr\key_len:
-	do_aes_load	5, \key_len, \xctr
-	add	$(5*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Leq6\xctr\key_len:
-	do_aes_load	6, \key_len, \xctr
-	add	$(6*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Leq7\xctr\key_len:
-	do_aes_load	7, \key_len, \xctr
-	add	$(7*16), p_out
-	and	$(~7*16), num_bytes
-	jz	.Ldo_return2\xctr\key_len
-	jmp	.Lmain_loop2\xctr\key_len
-
-.Lmult_of_8_blks\xctr\key_len:
-	.if (\key_len != KEY_128)
-		vmovdqa	0*16(p_keys), xkey0
-		vmovdqa	4*16(p_keys), xkey4
-		vmovdqa	8*16(p_keys), xkey8
-		vmovdqa	12*16(p_keys), xkey12
-	.else
-		vmovdqa	0*16(p_keys), xkey0
-		vmovdqa	3*16(p_keys), xkey4
-		vmovdqa	6*16(p_keys), xkey8
-		vmovdqa	9*16(p_keys), xkey12
-	.endif
-.align 16
-.Lmain_loop2\xctr\key_len:
-	/* num_bytes is a multiple of 8 and >0 */
-	do_aes_noload	8, \key_len, \xctr
-	add	$(8*16), p_out
-	sub	$(8*16), num_bytes
-	jne	.Lmain_loop2\xctr\key_len
-
-.Ldo_return2\xctr\key_len:
-	.if !\xctr
-		/* return updated IV */
-		vpshufb	xbyteswap, xcounter, xcounter
-		vmovdqu	xcounter, (p_iv)
-	.endif
-	RET
-.endm
-
-/*
- * routine to do AES128 CTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out,
- *			unsigned int num_bytes)
- */
-SYM_FUNC_START(aes_ctr_enc_128_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_128 0
-
-SYM_FUNC_END(aes_ctr_enc_128_avx_by8)
-
-/*
- * routine to do AES192 CTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out,
- *			unsigned int num_bytes)
- */
-SYM_FUNC_START(aes_ctr_enc_192_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_192 0
-
-SYM_FUNC_END(aes_ctr_enc_192_avx_by8)
-
-/*
- * routine to do AES256 CTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out,
- *			unsigned int num_bytes)
- */
-SYM_FUNC_START(aes_ctr_enc_256_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_256 0
-
-SYM_FUNC_END(aes_ctr_enc_256_avx_by8)
-
-/*
- * routine to do AES128 XCTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_xctr_enc_128_avx_by8(const u8 *in, const u8 *iv, const void *keys,
- * 	u8* out, unsigned int num_bytes, unsigned int byte_ctr)
- */
-SYM_FUNC_START(aes_xctr_enc_128_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_128 1
-
-SYM_FUNC_END(aes_xctr_enc_128_avx_by8)
-
-/*
- * routine to do AES192 XCTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_xctr_enc_192_avx_by8(const u8 *in, const u8 *iv, const void *keys,
- * 	u8* out, unsigned int num_bytes, unsigned int byte_ctr)
- */
-SYM_FUNC_START(aes_xctr_enc_192_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_192 1
-
-SYM_FUNC_END(aes_xctr_enc_192_avx_by8)
-
-/*
- * routine to do AES256 XCTR enc/decrypt "by8"
- * XMM registers are clobbered.
- * Saving/restoring must be done at a higher level
- * aes_xctr_enc_256_avx_by8(const u8 *in, const u8 *iv, const void *keys,
- * 	u8* out, unsigned int num_bytes, unsigned int byte_ctr)
- */
-SYM_FUNC_START(aes_xctr_enc_256_avx_by8)
-	/* call the aes main loop */
-	do_aes_ctrmain KEY_256 1
-
-SYM_FUNC_END(aes_xctr_enc_256_avx_by8)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index eb153eff9331..b37881bb9f15 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -17,6 +17,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/frame.h>
 
 #define STATE1	%xmm0
@@ -1071,6 +1072,7 @@ SYM_FUNC_END(_aesni_inc)
  *		      size_t len, u8 *iv)
  */
 SYM_FUNC_START(aesni_ctr_enc)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	cmp $16, LEN
 	jb .Lctr_enc_just_ret
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 11e95fc62636..061b1ced93c5 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -23,7 +23,6 @@
 #include <linux/err.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/ctr.h>
 #include <crypto/b128ops.h>
 #include <crypto/gcm.h>
 #include <crypto/xts.h>
@@ -82,30 +81,8 @@ asmlinkage void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 
 #ifdef CONFIG_X86_64
-
 asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
-DEFINE_STATIC_CALL(aesni_ctr_enc_tfm, aesni_ctr_enc);
-
-asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
-		void *keys, u8 *out, unsigned int num_bytes);
-asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
-		void *keys, u8 *out, unsigned int num_bytes);
-asmlinkage void aes_ctr_enc_256_avx_by8(const u8 *in, u8 *iv,
-		void *keys, u8 *out, unsigned int num_bytes);
-
-
-asmlinkage void aes_xctr_enc_128_avx_by8(const u8 *in, const u8 *iv,
-	const void *keys, u8 *out, unsigned int num_bytes,
-	unsigned int byte_ctr);
-
-asmlinkage void aes_xctr_enc_192_avx_by8(const u8 *in, const u8 *iv,
-	const void *keys, u8 *out, unsigned int num_bytes,
-	unsigned int byte_ctr);
-
-asmlinkage void aes_xctr_enc_256_avx_by8(const u8 *in, const u8 *iv,
-	const void *keys, u8 *out, unsigned int num_bytes,
-	unsigned int byte_ctr);
 #endif
 
 static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx)
@@ -376,24 +353,8 @@ static int cts_cbc_decrypt(struct skcipher_request *req)
 }
 
 #ifdef CONFIG_X86_64
-static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
-			      const u8 *in, unsigned int len, u8 *iv)
-{
-	/*
-	 * based on key length, override with the by8 version
-	 * of ctr mode encryption/decryption for improved performance
-	 * aes_set_key_common() ensures that key length is one of
-	 * {128,192,256}
-	 */
-	if (ctx->key_length == AES_KEYSIZE_128)
-		aes_ctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len);
-	else if (ctx->key_length == AES_KEYSIZE_192)
-		aes_ctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len);
-	else
-		aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len);
-}
-
-static int ctr_crypt(struct skcipher_request *req)
+/* This is the non-AVX version. */
+static int ctr_crypt_aesni(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
@@ -407,10 +368,9 @@ static int ctr_crypt(struct skcipher_request *req)
 	while ((nbytes = walk.nbytes) > 0) {
 		kernel_fpu_begin();
 		if (nbytes & AES_BLOCK_MASK)
-			static_call(aesni_ctr_enc_tfm)(ctx, walk.dst.virt.addr,
-						       walk.src.virt.addr,
-						       nbytes & AES_BLOCK_MASK,
-						       walk.iv);
+			aesni_ctr_enc(ctx, walk.dst.virt.addr,
+				      walk.src.virt.addr,
+				      nbytes & AES_BLOCK_MASK, walk.iv);
 		nbytes &= ~AES_BLOCK_MASK;
 
 		if (walk.nbytes == walk.total && nbytes > 0) {
@@ -426,59 +386,6 @@ static int ctr_crypt(struct skcipher_request *req)
 	}
 	return err;
 }
-
-static void aesni_xctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
-				   const u8 *in, unsigned int len, u8 *iv,
-				   unsigned int byte_ctr)
-{
-	if (ctx->key_length == AES_KEYSIZE_128)
-		aes_xctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len,
-					 byte_ctr);
-	else if (ctx->key_length == AES_KEYSIZE_192)
-		aes_xctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len,
-					 byte_ctr);
-	else
-		aes_xctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len,
-					 byte_ctr);
-}
-
-static int xctr_crypt(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_aes_ctx *ctx = aes_ctx(crypto_skcipher_ctx(tfm));
-	u8 keystream[AES_BLOCK_SIZE];
-	struct skcipher_walk walk;
-	unsigned int nbytes;
-	unsigned int byte_ctr = 0;
-	int err;
-	__le32 block[AES_BLOCK_SIZE / sizeof(__le32)];
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while ((nbytes = walk.nbytes) > 0) {
-		kernel_fpu_begin();
-		if (nbytes & AES_BLOCK_MASK)
-			aesni_xctr_enc_avx_tfm(ctx, walk.dst.virt.addr,
-				walk.src.virt.addr, nbytes & AES_BLOCK_MASK,
-				walk.iv, byte_ctr);
-		nbytes &= ~AES_BLOCK_MASK;
-		byte_ctr += walk.nbytes - nbytes;
-
-		if (walk.nbytes == walk.total && nbytes > 0) {
-			memcpy(block, walk.iv, AES_BLOCK_SIZE);
-			block[0] ^= cpu_to_le32(1 + byte_ctr / AES_BLOCK_SIZE);
-			aesni_enc(ctx, keystream, (u8 *)block);
-			crypto_xor_cpy(walk.dst.virt.addr + walk.nbytes -
-				       nbytes, walk.src.virt.addr + walk.nbytes
-				       - nbytes, keystream, nbytes);
-			byte_ctr += nbytes;
-			nbytes = 0;
-		}
-		kernel_fpu_end();
-		err = skcipher_walk_done(&walk, nbytes);
-	}
-	return err;
-}
 #endif
 
 static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key,
@@ -581,11 +488,8 @@ xts_crypt(struct skcipher_request *req, xts_encrypt_iv_func encrypt_iv,
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
-	const unsigned int cryptlen = req->cryptlen;
-	struct scatterlist *src = req->src;
-	struct scatterlist *dst = req->dst;
 
-	if (unlikely(cryptlen < AES_BLOCK_SIZE))
+	if (unlikely(req->cryptlen < AES_BLOCK_SIZE))
 		return -EINVAL;
 
 	kernel_fpu_begin();
@@ -593,23 +497,16 @@ xts_crypt(struct skcipher_request *req, xts_encrypt_iv_func encrypt_iv,
 
 	/*
 	 * In practice, virtually all XTS plaintexts and ciphertexts are either
-	 * 512 or 4096 bytes, aligned such that they don't span page boundaries.
-	 * To optimize the performance of these cases, and also any other case
-	 * where no page boundary is spanned, the below fast-path handles
-	 * single-page sources and destinations as efficiently as possible.
+	 * 512 or 4096 bytes and do not use multiple scatterlist elements.  To
+	 * optimize the performance of these cases, the below fast-path handles
+	 * single-scatterlist-element messages as efficiently as possible.  The
+	 * code is 64-bit specific, as it assumes no page mapping is needed.
 	 */
-	if (likely(src->length >= cryptlen && dst->length >= cryptlen &&
-		   src->offset + cryptlen <= PAGE_SIZE &&
-		   dst->offset + cryptlen <= PAGE_SIZE)) {
-		struct page *src_page = sg_page(src);
-		struct page *dst_page = sg_page(dst);
-		void *src_virt = kmap_local_page(src_page) + src->offset;
-		void *dst_virt = kmap_local_page(dst_page) + dst->offset;
-
-		(*crypt_func)(&ctx->crypt_ctx, src_virt, dst_virt, cryptlen,
-			      req->iv);
-		kunmap_local(dst_virt);
-		kunmap_local(src_virt);
+	if (IS_ENABLED(CONFIG_X86_64) &&
+	    likely(req->src->length >= req->cryptlen &&
+		   req->dst->length >= req->cryptlen)) {
+		(*crypt_func)(&ctx->crypt_ctx, sg_virt(req->src),
+			      sg_virt(req->dst), req->cryptlen, req->iv);
 		kernel_fpu_end();
 		return 0;
 	}
@@ -669,10 +566,9 @@ static struct crypto_alg aesni_cipher_alg = {
 static struct skcipher_alg aesni_skciphers[] = {
 	{
 		.base = {
-			.cra_name		= "__ecb(aes)",
-			.cra_driver_name	= "__ecb-aes-aesni",
+			.cra_name		= "ecb(aes)",
+			.cra_driver_name	= "ecb-aes-aesni",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= AES_BLOCK_SIZE,
 			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
 			.cra_module		= THIS_MODULE,
@@ -684,10 +580,9 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.decrypt	= ecb_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cbc(aes)",
-			.cra_driver_name	= "__cbc-aes-aesni",
+			.cra_name		= "cbc(aes)",
+			.cra_driver_name	= "cbc-aes-aesni",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= AES_BLOCK_SIZE,
 			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
 			.cra_module		= THIS_MODULE,
@@ -700,10 +595,9 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.decrypt	= cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cts(cbc(aes))",
-			.cra_driver_name	= "__cts-cbc-aes-aesni",
+			.cra_name		= "cts(cbc(aes))",
+			.cra_driver_name	= "cts-cbc-aes-aesni",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= AES_BLOCK_SIZE,
 			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
 			.cra_module		= THIS_MODULE,
@@ -718,10 +612,9 @@ static struct skcipher_alg aesni_skciphers[] = {
 #ifdef CONFIG_X86_64
 	}, {
 		.base = {
-			.cra_name		= "__ctr(aes)",
-			.cra_driver_name	= "__ctr-aes-aesni",
+			.cra_name		= "ctr(aes)",
+			.cra_driver_name	= "ctr-aes-aesni",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= 1,
 			.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
 			.cra_module		= THIS_MODULE,
@@ -731,15 +624,14 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.ivsize		= AES_BLOCK_SIZE,
 		.chunksize	= AES_BLOCK_SIZE,
 		.setkey		= aesni_skcipher_setkey,
-		.encrypt	= ctr_crypt,
-		.decrypt	= ctr_crypt,
+		.encrypt	= ctr_crypt_aesni,
+		.decrypt	= ctr_crypt_aesni,
 #endif
 	}, {
 		.base = {
-			.cra_name		= "__xts(aes)",
-			.cra_driver_name	= "__xts-aes-aesni",
+			.cra_name		= "xts(aes)",
+			.cra_driver_name	= "xts-aes-aesni",
 			.cra_priority		= 401,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= AES_BLOCK_SIZE,
 			.cra_ctxsize		= XTS_AES_CTX_SIZE,
 			.cra_module		= THIS_MODULE,
@@ -754,39 +646,106 @@ static struct skcipher_alg aesni_skciphers[] = {
 	}
 };
 
-static
-struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)];
-
 #ifdef CONFIG_X86_64
-/*
- * XCTR does not have a non-AVX implementation, so it must be enabled
- * conditionally.
- */
-static struct skcipher_alg aesni_xctr = {
-	.base = {
-		.cra_name		= "__xctr(aes)",
-		.cra_driver_name	= "__xctr-aes-aesni",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= CRYPTO_AES_CTX_SIZE,
-		.cra_module		= THIS_MODULE,
-	},
-	.min_keysize	= AES_MIN_KEY_SIZE,
-	.max_keysize	= AES_MAX_KEY_SIZE,
-	.ivsize		= AES_BLOCK_SIZE,
-	.chunksize	= AES_BLOCK_SIZE,
-	.setkey		= aesni_skcipher_setkey,
-	.encrypt	= xctr_crypt,
-	.decrypt	= xctr_crypt,
-};
-
-static struct simd_skcipher_alg *aesni_simd_xctr;
-
 asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
 				   u8 iv[AES_BLOCK_SIZE]);
 
-#define DEFINE_XTS_ALG(suffix, driver_name, priority)			       \
+/* __always_inline to avoid indirect call */
+static __always_inline int
+ctr_crypt(struct skcipher_request *req,
+	  void (*ctr64_func)(const struct crypto_aes_ctx *key,
+			     const u8 *src, u8 *dst, int len,
+			     const u64 le_ctr[2]))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_aes_ctx *key = aes_ctx(crypto_skcipher_ctx(tfm));
+	unsigned int nbytes, p1_nbytes, nblocks;
+	struct skcipher_walk walk;
+	u64 le_ctr[2];
+	u64 ctr64;
+	int err;
+
+	ctr64 = le_ctr[0] = get_unaligned_be64(&req->iv[8]);
+	le_ctr[1] = get_unaligned_be64(&req->iv[0]);
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((nbytes = walk.nbytes) != 0) {
+		if (nbytes < walk.total) {
+			/* Not the end yet, so keep the length block-aligned. */
+			nbytes = round_down(nbytes, AES_BLOCK_SIZE);
+			nblocks = nbytes / AES_BLOCK_SIZE;
+		} else {
+			/* It's the end, so include any final partial block. */
+			nblocks = DIV_ROUND_UP(nbytes, AES_BLOCK_SIZE);
+		}
+		ctr64 += nblocks;
+
+		kernel_fpu_begin();
+		if (likely(ctr64 >= nblocks)) {
+			/* The low 64 bits of the counter won't overflow. */
+			(*ctr64_func)(key, walk.src.virt.addr,
+				      walk.dst.virt.addr, nbytes, le_ctr);
+		} else {
+			/*
+			 * The low 64 bits of the counter will overflow.  The
+			 * assembly doesn't handle this case, so split the
+			 * operation into two at the point where the overflow
+			 * will occur.  After the first part, add the carry bit.
+			 */
+			p1_nbytes = min_t(unsigned int, nbytes,
+					  (nblocks - ctr64) * AES_BLOCK_SIZE);
+			(*ctr64_func)(key, walk.src.virt.addr,
+				      walk.dst.virt.addr, p1_nbytes, le_ctr);
+			le_ctr[0] = 0;
+			le_ctr[1]++;
+			(*ctr64_func)(key, walk.src.virt.addr + p1_nbytes,
+				      walk.dst.virt.addr + p1_nbytes,
+				      nbytes - p1_nbytes, le_ctr);
+		}
+		kernel_fpu_end();
+		le_ctr[0] = ctr64;
+
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	put_unaligned_be64(ctr64, &req->iv[8]);
+	put_unaligned_be64(le_ctr[1], &req->iv[0]);
+
+	return err;
+}
+
+/* __always_inline to avoid indirect call */
+static __always_inline int
+xctr_crypt(struct skcipher_request *req,
+	   void (*xctr_func)(const struct crypto_aes_ctx *key,
+			     const u8 *src, u8 *dst, int len,
+			     const u8 iv[AES_BLOCK_SIZE], u64 ctr))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct crypto_aes_ctx *key = aes_ctx(crypto_skcipher_ctx(tfm));
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	u64 ctr = 1;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) != 0) {
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, AES_BLOCK_SIZE);
+
+		kernel_fpu_begin();
+		(*xctr_func)(key, walk.src.virt.addr, walk.dst.virt.addr,
+			     nbytes, req->iv, ctr);
+		kernel_fpu_end();
+
+		ctr += DIV_ROUND_UP(nbytes, AES_BLOCK_SIZE);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+	return err;
+}
+
+#define DEFINE_AVX_SKCIPHER_ALGS(suffix, driver_name_suffix, priority)	       \
 									       \
 asmlinkage void								       \
 aes_xts_encrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src,      \
@@ -805,32 +764,73 @@ static int xts_decrypt_##suffix(struct skcipher_request *req)		       \
 	return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_decrypt_##suffix);   \
 }									       \
 									       \
-static struct skcipher_alg aes_xts_alg_##suffix = {			       \
-	.base = {							       \
-		.cra_name		= "__xts(aes)",			       \
-		.cra_driver_name	= "__" driver_name,		       \
-		.cra_priority		= priority,			       \
-		.cra_flags		= CRYPTO_ALG_INTERNAL,		       \
-		.cra_blocksize		= AES_BLOCK_SIZE,		       \
-		.cra_ctxsize		= XTS_AES_CTX_SIZE,		       \
-		.cra_module		= THIS_MODULE,			       \
-	},								       \
-	.min_keysize	= 2 * AES_MIN_KEY_SIZE,				       \
-	.max_keysize	= 2 * AES_MAX_KEY_SIZE,				       \
-	.ivsize		= AES_BLOCK_SIZE,				       \
-	.walksize	= 2 * AES_BLOCK_SIZE,				       \
-	.setkey		= xts_setkey_aesni,				       \
-	.encrypt	= xts_encrypt_##suffix,				       \
-	.decrypt	= xts_decrypt_##suffix,				       \
-};									       \
+asmlinkage void								       \
+aes_ctr64_crypt_##suffix(const struct crypto_aes_ctx *key,		       \
+			 const u8 *src, u8 *dst, int len, const u64 le_ctr[2]);\
+									       \
+static int ctr_crypt_##suffix(struct skcipher_request *req)		       \
+{									       \
+	return ctr_crypt(req, aes_ctr64_crypt_##suffix);		       \
+}									       \
 									       \
-static struct simd_skcipher_alg *aes_xts_simdalg_##suffix
+asmlinkage void								       \
+aes_xctr_crypt_##suffix(const struct crypto_aes_ctx *key,		       \
+			const u8 *src, u8 *dst, int len,		       \
+			const u8 iv[AES_BLOCK_SIZE], u64 ctr);		       \
+									       \
+static int xctr_crypt_##suffix(struct skcipher_request *req)		       \
+{									       \
+	return xctr_crypt(req, aes_xctr_crypt_##suffix);		       \
+}									       \
+									       \
+static struct skcipher_alg skcipher_algs_##suffix[] = {{		       \
+	.base.cra_name		= "xts(aes)",				       \
+	.base.cra_driver_name	= "xts-aes-" driver_name_suffix,	       \
+	.base.cra_priority	= priority,				       \
+	.base.cra_blocksize	= AES_BLOCK_SIZE,			       \
+	.base.cra_ctxsize	= XTS_AES_CTX_SIZE,			       \
+	.base.cra_module	= THIS_MODULE,				       \
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,			       \
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,			       \
+	.ivsize			= AES_BLOCK_SIZE,			       \
+	.walksize		= 2 * AES_BLOCK_SIZE,			       \
+	.setkey			= xts_setkey_aesni,			       \
+	.encrypt		= xts_encrypt_##suffix,			       \
+	.decrypt		= xts_decrypt_##suffix,			       \
+}, {									       \
+	.base.cra_name		= "ctr(aes)",				       \
+	.base.cra_driver_name	= "ctr-aes-" driver_name_suffix,	       \
+	.base.cra_priority	= priority,				       \
+	.base.cra_blocksize	= 1,					       \
+	.base.cra_ctxsize	= CRYPTO_AES_CTX_SIZE,			       \
+	.base.cra_module	= THIS_MODULE,				       \
+	.min_keysize		= AES_MIN_KEY_SIZE,			       \
+	.max_keysize		= AES_MAX_KEY_SIZE,			       \
+	.ivsize			= AES_BLOCK_SIZE,			       \
+	.chunksize		= AES_BLOCK_SIZE,			       \
+	.setkey			= aesni_skcipher_setkey,		       \
+	.encrypt		= ctr_crypt_##suffix,			       \
+	.decrypt		= ctr_crypt_##suffix,			       \
+}, {									       \
+	.base.cra_name		= "xctr(aes)",				       \
+	.base.cra_driver_name	= "xctr-aes-" driver_name_suffix,	       \
+	.base.cra_priority	= priority,				       \
+	.base.cra_blocksize	= 1,					       \
+	.base.cra_ctxsize	= CRYPTO_AES_CTX_SIZE,			       \
+	.base.cra_module	= THIS_MODULE,				       \
+	.min_keysize		= AES_MIN_KEY_SIZE,			       \
+	.max_keysize		= AES_MAX_KEY_SIZE,			       \
+	.ivsize			= AES_BLOCK_SIZE,			       \
+	.chunksize		= AES_BLOCK_SIZE,			       \
+	.setkey			= aesni_skcipher_setkey,		       \
+	.encrypt		= xctr_crypt_##suffix,			       \
+	.decrypt		= xctr_crypt_##suffix,			       \
+}}
 
-DEFINE_XTS_ALG(aesni_avx, "xts-aes-aesni-avx", 500);
+DEFINE_AVX_SKCIPHER_ALGS(aesni_avx, "aesni-avx", 500);
 #if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
-DEFINE_XTS_ALG(vaes_avx2, "xts-aes-vaes-avx2", 600);
-DEFINE_XTS_ALG(vaes_avx10_256, "xts-aes-vaes-avx10_256", 700);
-DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
+DEFINE_AVX_SKCIPHER_ALGS(vaes_avx2, "vaes-avx2", 600);
+DEFINE_AVX_SKCIPHER_ALGS(vaes_avx512, "vaes-avx512", 800);
 #endif
 
 /* The common part of the x86_64 AES-GCM key struct */
@@ -1291,41 +1291,40 @@ static void gcm_process_assoc(const struct aes_gcm_key *key, u8 ghash_acc[16],
 	scatterwalk_start(&walk, sg_src);
 
 	while (assoclen) {
-		unsigned int len_this_page = scatterwalk_clamp(&walk, assoclen);
-		void *mapped = scatterwalk_map(&walk);
-		const void *src = mapped;
+		unsigned int orig_len_this_step = scatterwalk_next(
+			&walk, assoclen);
+		unsigned int len_this_step = orig_len_this_step;
 		unsigned int len;
+		const u8 *src = walk.addr;
 
-		assoclen -= len_this_page;
-		scatterwalk_advance(&walk, len_this_page);
 		if (unlikely(pos)) {
-			len = min(len_this_page, 16 - pos);
+			len = min(len_this_step, 16 - pos);
 			memcpy(&buf[pos], src, len);
 			pos += len;
 			src += len;
-			len_this_page -= len;
+			len_this_step -= len;
 			if (pos < 16)
 				goto next;
 			aes_gcm_aad_update(key, ghash_acc, buf, 16, flags);
 			pos = 0;
 		}
-		len = len_this_page;
+		len = len_this_step;
 		if (unlikely(assoclen)) /* Not the last segment yet? */
 			len = round_down(len, 16);
 		aes_gcm_aad_update(key, ghash_acc, src, len, flags);
 		src += len;
-		len_this_page -= len;
-		if (unlikely(len_this_page)) {
-			memcpy(buf, src, len_this_page);
-			pos = len_this_page;
+		len_this_step -= len;
+		if (unlikely(len_this_step)) {
+			memcpy(buf, src, len_this_step);
+			pos = len_this_step;
 		}
 next:
-		scatterwalk_unmap(mapped);
-		scatterwalk_pagedone(&walk, 0, assoclen);
+		scatterwalk_done_src(&walk, orig_len_this_step);
 		if (need_resched()) {
 			kernel_fpu_end();
 			kernel_fpu_begin();
 		}
+		assoclen -= orig_len_this_step;
 	}
 	if (unlikely(pos))
 		aes_gcm_aad_update(key, ghash_acc, buf, pos, flags);
@@ -1485,10 +1484,9 @@ static struct aead_alg aes_gcm_algs_##suffix[] = { {			       \
 	.chunksize		= AES_BLOCK_SIZE,			       \
 	.maxauthsize		= 16,					       \
 	.base = {							       \
-		.cra_name		= "__gcm(aes)",			       \
-		.cra_driver_name	= "__" generic_driver_name,	       \
+		.cra_name		= "gcm(aes)",			       \
+		.cra_driver_name	= generic_driver_name,		       \
 		.cra_priority		= (priority),			       \
-		.cra_flags		= CRYPTO_ALG_INTERNAL,		       \
 		.cra_blocksize		= 1,				       \
 		.cra_ctxsize		= (ctxsize),			       \
 		.cra_module		= THIS_MODULE,			       \
@@ -1502,17 +1500,14 @@ static struct aead_alg aes_gcm_algs_##suffix[] = { {			       \
 	.chunksize		= AES_BLOCK_SIZE,			       \
 	.maxauthsize		= 16,					       \
 	.base = {							       \
-		.cra_name		= "__rfc4106(gcm(aes))",	       \
-		.cra_driver_name	= "__" rfc_driver_name,		       \
+		.cra_name		= "rfc4106(gcm(aes))",		       \
+		.cra_driver_name	= rfc_driver_name,		       \
 		.cra_priority		= (priority),			       \
-		.cra_flags		= CRYPTO_ALG_INTERNAL,		       \
 		.cra_blocksize		= 1,				       \
 		.cra_ctxsize		= (ctxsize),			       \
 		.cra_module		= THIS_MODULE,			       \
 	},								       \
-} };									       \
-									       \
-static struct simd_aead_alg *aes_gcm_simdalgs_##suffix[2]		       \
+} }
 
 /* aes_gcm_algs_aesni */
 DEFINE_GCM_ALGS(aesni, /* no flags */ 0,
@@ -1536,41 +1531,26 @@ DEFINE_GCM_ALGS(vaes_avx10_512, FLAG_AVX10_512,
 		AES_GCM_KEY_AVX10_SIZE, 800);
 #endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
 
-/*
- * This is a list of CPU models that are known to suffer from downclocking when
- * zmm registers (512-bit vectors) are used.  On these CPUs, the AES mode
- * implementations with zmm registers won't be used by default.  Implementations
- * with ymm registers (256-bit vectors) will be used by default instead.
- */
-static const struct x86_cpu_id zmm_exclusion_list[] = {
-	X86_MATCH_VFM(INTEL_SKYLAKE_X,		0),
-	X86_MATCH_VFM(INTEL_ICELAKE_X,		0),
-	X86_MATCH_VFM(INTEL_ICELAKE_D,		0),
-	X86_MATCH_VFM(INTEL_ICELAKE,		0),
-	X86_MATCH_VFM(INTEL_ICELAKE_L,		0),
-	X86_MATCH_VFM(INTEL_ICELAKE_NNPI,	0),
-	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	0),
-	X86_MATCH_VFM(INTEL_TIGERLAKE,		0),
-	/* Allow Rocket Lake and later, and Sapphire Rapids and later. */
-	/* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */
-	{},
-};
-
 static int __init register_avx_algs(void)
 {
 	int err;
 
 	if (!boot_cpu_has(X86_FEATURE_AVX))
 		return 0;
-	err = simd_register_skciphers_compat(&aes_xts_alg_aesni_avx, 1,
-					     &aes_xts_simdalg_aesni_avx);
+	err = crypto_register_skciphers(skcipher_algs_aesni_avx,
+					ARRAY_SIZE(skcipher_algs_aesni_avx));
 	if (err)
 		return err;
-	err = simd_register_aeads_compat(aes_gcm_algs_aesni_avx,
-					 ARRAY_SIZE(aes_gcm_algs_aesni_avx),
-					 aes_gcm_simdalgs_aesni_avx);
+	err = crypto_register_aeads(aes_gcm_algs_aesni_avx,
+				    ARRAY_SIZE(aes_gcm_algs_aesni_avx));
 	if (err)
 		return err;
+	/*
+	 * Note: not all the algorithms registered below actually require
+	 * VPCLMULQDQ.  But in practice every CPU with VAES also has VPCLMULQDQ.
+	 * Similarly, the assembler support was added at about the same time.
+	 * For simplicity, just always check for VAES and VPCLMULQDQ together.
+	 */
 #if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
 	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
 	    !boot_cpu_has(X86_FEATURE_VAES) ||
@@ -1578,8 +1558,8 @@ static int __init register_avx_algs(void)
 	    !boot_cpu_has(X86_FEATURE_PCLMULQDQ) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		return 0;
-	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx2, 1,
-					     &aes_xts_simdalg_vaes_avx2);
+	err = crypto_register_skciphers(skcipher_algs_vaes_avx2,
+					ARRAY_SIZE(skcipher_algs_vaes_avx2));
 	if (err)
 		return err;
 
@@ -1590,69 +1570,52 @@ static int __init register_avx_algs(void)
 			       XFEATURE_MASK_AVX512, NULL))
 		return 0;
 
-	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_256, 1,
-					     &aes_xts_simdalg_vaes_avx10_256);
-	if (err)
-		return err;
-	err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_256,
-					 ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
-					 aes_gcm_simdalgs_vaes_avx10_256);
+	err = crypto_register_aeads(aes_gcm_algs_vaes_avx10_256,
+				    ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256));
 	if (err)
 		return err;
 
-	if (x86_match_cpu(zmm_exclusion_list)) {
+	if (boot_cpu_has(X86_FEATURE_PREFER_YMM)) {
 		int i;
 
-		aes_xts_alg_vaes_avx10_512.base.cra_priority = 1;
+		for (i = 0; i < ARRAY_SIZE(skcipher_algs_vaes_avx512); i++)
+			skcipher_algs_vaes_avx512[i].base.cra_priority = 1;
 		for (i = 0; i < ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512); i++)
 			aes_gcm_algs_vaes_avx10_512[i].base.cra_priority = 1;
 	}
 
-	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_512, 1,
-					     &aes_xts_simdalg_vaes_avx10_512);
+	err = crypto_register_skciphers(skcipher_algs_vaes_avx512,
+					ARRAY_SIZE(skcipher_algs_vaes_avx512));
 	if (err)
 		return err;
-	err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_512,
-					 ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
-					 aes_gcm_simdalgs_vaes_avx10_512);
+	err = crypto_register_aeads(aes_gcm_algs_vaes_avx10_512,
+				    ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512));
 	if (err)
 		return err;
 #endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
 	return 0;
 }
 
+#define unregister_skciphers(A) \
+	if (refcount_read(&(A)[0].base.cra_refcnt) != 0) \
+		crypto_unregister_skciphers((A), ARRAY_SIZE(A))
+#define unregister_aeads(A) \
+	if (refcount_read(&(A)[0].base.cra_refcnt) != 0) \
+		crypto_unregister_aeads((A), ARRAY_SIZE(A))
+
 static void unregister_avx_algs(void)
 {
-	if (aes_xts_simdalg_aesni_avx)
-		simd_unregister_skciphers(&aes_xts_alg_aesni_avx, 1,
-					  &aes_xts_simdalg_aesni_avx);
-	if (aes_gcm_simdalgs_aesni_avx[0])
-		simd_unregister_aeads(aes_gcm_algs_aesni_avx,
-				      ARRAY_SIZE(aes_gcm_algs_aesni_avx),
-				      aes_gcm_simdalgs_aesni_avx);
+	unregister_skciphers(skcipher_algs_aesni_avx);
+	unregister_aeads(aes_gcm_algs_aesni_avx);
 #if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
-	if (aes_xts_simdalg_vaes_avx2)
-		simd_unregister_skciphers(&aes_xts_alg_vaes_avx2, 1,
-					  &aes_xts_simdalg_vaes_avx2);
-	if (aes_xts_simdalg_vaes_avx10_256)
-		simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_256, 1,
-					  &aes_xts_simdalg_vaes_avx10_256);
-	if (aes_gcm_simdalgs_vaes_avx10_256[0])
-		simd_unregister_aeads(aes_gcm_algs_vaes_avx10_256,
-				      ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
-				      aes_gcm_simdalgs_vaes_avx10_256);
-	if (aes_xts_simdalg_vaes_avx10_512)
-		simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_512, 1,
-					  &aes_xts_simdalg_vaes_avx10_512);
-	if (aes_gcm_simdalgs_vaes_avx10_512[0])
-		simd_unregister_aeads(aes_gcm_algs_vaes_avx10_512,
-				      ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
-				      aes_gcm_simdalgs_vaes_avx10_512);
+	unregister_skciphers(skcipher_algs_vaes_avx2);
+	unregister_skciphers(skcipher_algs_vaes_avx512);
+	unregister_aeads(aes_gcm_algs_vaes_avx10_256);
+	unregister_aeads(aes_gcm_algs_vaes_avx10_512);
 #endif
 }
 #else /* CONFIG_X86_64 */
 static struct aead_alg aes_gcm_algs_aesni[0];
-static struct simd_aead_alg *aes_gcm_simdalgs_aesni[0];
 
 static int __init register_avx_algs(void)
 {
@@ -1676,38 +1639,21 @@ static int __init aesni_init(void)
 
 	if (!x86_match_cpu(aesni_cpu_id))
 		return -ENODEV;
-#ifdef CONFIG_X86_64
-	if (boot_cpu_has(X86_FEATURE_AVX)) {
-		/* optimize performance of ctr mode encryption transform */
-		static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm);
-		pr_info("AES CTR mode by8 optimization enabled\n");
-	}
-#endif /* CONFIG_X86_64 */
 
 	err = crypto_register_alg(&aesni_cipher_alg);
 	if (err)
 		return err;
 
-	err = simd_register_skciphers_compat(aesni_skciphers,
-					     ARRAY_SIZE(aesni_skciphers),
-					     aesni_simd_skciphers);
+	err = crypto_register_skciphers(aesni_skciphers,
+					ARRAY_SIZE(aesni_skciphers));
 	if (err)
 		goto unregister_cipher;
 
-	err = simd_register_aeads_compat(aes_gcm_algs_aesni,
-					 ARRAY_SIZE(aes_gcm_algs_aesni),
-					 aes_gcm_simdalgs_aesni);
+	err = crypto_register_aeads(aes_gcm_algs_aesni,
+				    ARRAY_SIZE(aes_gcm_algs_aesni));
 	if (err)
 		goto unregister_skciphers;
 
-#ifdef CONFIG_X86_64
-	if (boot_cpu_has(X86_FEATURE_AVX))
-		err = simd_register_skciphers_compat(&aesni_xctr, 1,
-						     &aesni_simd_xctr);
-	if (err)
-		goto unregister_aeads;
-#endif /* CONFIG_X86_64 */
-
 	err = register_avx_algs();
 	if (err)
 		goto unregister_avx;
@@ -1716,17 +1662,11 @@ static int __init aesni_init(void)
 
 unregister_avx:
 	unregister_avx_algs();
-#ifdef CONFIG_X86_64
-	if (aesni_simd_xctr)
-		simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
-unregister_aeads:
-#endif /* CONFIG_X86_64 */
-	simd_unregister_aeads(aes_gcm_algs_aesni,
-			      ARRAY_SIZE(aes_gcm_algs_aesni),
-			      aes_gcm_simdalgs_aesni);
+	crypto_unregister_aeads(aes_gcm_algs_aesni,
+				ARRAY_SIZE(aes_gcm_algs_aesni));
 unregister_skciphers:
-	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
-				  aesni_simd_skciphers);
+	crypto_unregister_skciphers(aesni_skciphers,
+				    ARRAY_SIZE(aesni_skciphers));
 unregister_cipher:
 	crypto_unregister_alg(&aesni_cipher_alg);
 	return err;
@@ -1734,16 +1674,11 @@ unregister_cipher:
 
 static void __exit aesni_exit(void)
 {
-	simd_unregister_aeads(aes_gcm_algs_aesni,
-			      ARRAY_SIZE(aes_gcm_algs_aesni),
-			      aes_gcm_simdalgs_aesni);
-	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
-				  aesni_simd_skciphers);
+	crypto_unregister_aeads(aes_gcm_algs_aesni,
+				ARRAY_SIZE(aes_gcm_algs_aesni));
+	crypto_unregister_skciphers(aesni_skciphers,
+				    ARRAY_SIZE(aesni_skciphers));
 	crypto_unregister_alg(&aesni_cipher_alg);
-#ifdef CONFIG_X86_64
-	if (boot_cpu_has(X86_FEATURE_AVX))
-		simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
-#endif /* CONFIG_X86_64 */
 	unregister_avx_algs();
 }
 
diff --git a/arch/x86/crypto/aria_aesni_avx2_glue.c b/arch/x86/crypto/aria_aesni_avx2_glue.c
index 87a11804fc77..b4bddcd58457 100644
--- a/arch/x86/crypto/aria_aesni_avx2_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx2_glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/aria.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
@@ -165,10 +164,9 @@ static int aria_avx2_init_tfm(struct crypto_skcipher *tfm)
 
 static struct skcipher_alg aria_algs[] = {
 	{
-		.base.cra_name		= "__ecb(aria)",
-		.base.cra_driver_name	= "__ecb-aria-avx2",
+		.base.cra_name		= "ecb(aria)",
+		.base.cra_driver_name	= "ecb-aria-avx2",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= ARIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -178,11 +176,10 @@ static struct skcipher_alg aria_algs[] = {
 		.encrypt		= aria_avx2_ecb_encrypt,
 		.decrypt		= aria_avx2_ecb_decrypt,
 	}, {
-		.base.cra_name		= "__ctr(aria)",
-		.base.cra_driver_name	= "__ctr-aria-avx2",
+		.base.cra_name		= "ctr(aria)",
+		.base.cra_driver_name	= "ctr-aria-avx2",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL |
-					  CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
+		.base.cra_flags		= CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
 		.base.cra_blocksize	= 1,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -197,8 +194,6 @@ static struct skcipher_alg aria_algs[] = {
 	}
 };
 
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
 static int __init aria_avx2_init(void)
 {
 	const char *feature_name;
@@ -233,15 +228,12 @@ static int __init aria_avx2_init(void)
 		aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_ctr_crypt_32way;
 	}
 
-	return simd_register_skciphers_compat(aria_algs,
-					      ARRAY_SIZE(aria_algs),
-					      aria_simd_algs);
+	return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 static void __exit aria_avx2_exit(void)
 {
-	simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
-				  aria_simd_algs);
+	crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 module_init(aria_avx2_init);
diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c
index 4e1516b76669..ab9b38d05332 100644
--- a/arch/x86/crypto/aria_aesni_avx_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx_glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/aria.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
@@ -152,10 +151,9 @@ static int aria_avx_init_tfm(struct crypto_skcipher *tfm)
 
 static struct skcipher_alg aria_algs[] = {
 	{
-		.base.cra_name		= "__ecb(aria)",
-		.base.cra_driver_name	= "__ecb-aria-avx",
+		.base.cra_name		= "ecb(aria)",
+		.base.cra_driver_name	= "ecb-aria-avx",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= ARIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -165,10 +163,9 @@ static struct skcipher_alg aria_algs[] = {
 		.encrypt		= aria_avx_ecb_encrypt,
 		.decrypt		= aria_avx_ecb_decrypt,
 	}, {
-		.base.cra_name		= "__ctr(aria)",
-		.base.cra_driver_name	= "__ctr-aria-avx",
+		.base.cra_name		= "ctr(aria)",
+		.base.cra_driver_name	= "ctr-aria-avx",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= 1,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -184,8 +181,6 @@ static struct skcipher_alg aria_algs[] = {
 	}
 };
 
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
 static int __init aria_avx_init(void)
 {
 	const char *feature_name;
@@ -213,15 +208,12 @@ static int __init aria_avx_init(void)
 		aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_ctr_crypt_16way;
 	}
 
-	return simd_register_skciphers_compat(aria_algs,
-					      ARRAY_SIZE(aria_algs),
-					      aria_simd_algs);
+	return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 static void __exit aria_avx_exit(void)
 {
-	simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
-				  aria_simd_algs);
+	crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 module_init(aria_avx_init);
diff --git a/arch/x86/crypto/aria_gfni_avx512_glue.c b/arch/x86/crypto/aria_gfni_avx512_glue.c
index f4a2208d2638..363cbf4399cc 100644
--- a/arch/x86/crypto/aria_gfni_avx512_glue.c
+++ b/arch/x86/crypto/aria_gfni_avx512_glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/aria.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
@@ -165,10 +164,9 @@ static int aria_avx512_init_tfm(struct crypto_skcipher *tfm)
 
 static struct skcipher_alg aria_algs[] = {
 	{
-		.base.cra_name		= "__ecb(aria)",
-		.base.cra_driver_name	= "__ecb-aria-avx512",
+		.base.cra_name		= "ecb(aria)",
+		.base.cra_driver_name	= "ecb-aria-avx512",
 		.base.cra_priority	= 600,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= ARIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -178,11 +176,10 @@ static struct skcipher_alg aria_algs[] = {
 		.encrypt		= aria_avx512_ecb_encrypt,
 		.decrypt		= aria_avx512_ecb_decrypt,
 	}, {
-		.base.cra_name		= "__ctr(aria)",
-		.base.cra_driver_name	= "__ctr-aria-avx512",
+		.base.cra_name		= "ctr(aria)",
+		.base.cra_driver_name	= "ctr-aria-avx512",
 		.base.cra_priority	= 600,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL |
-					  CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
+		.base.cra_flags		= CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
 		.base.cra_blocksize	= 1,
 		.base.cra_ctxsize	= sizeof(struct aria_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -197,8 +194,6 @@ static struct skcipher_alg aria_algs[] = {
 	}
 };
 
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
 static int __init aria_avx512_init(void)
 {
 	const char *feature_name;
@@ -229,15 +224,12 @@ static int __init aria_avx512_init(void)
 	aria_ops.aria_decrypt_64way = aria_gfni_avx512_decrypt_64way;
 	aria_ops.aria_ctr_crypt_64way = aria_gfni_avx512_ctr_crypt_64way;
 
-	return simd_register_skciphers_compat(aria_algs,
-					      ARRAY_SIZE(aria_algs),
-					      aria_simd_algs);
+	return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 static void __exit aria_avx512_exit(void)
 {
-	simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
-				  aria_simd_algs);
+	crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
 }
 
 module_init(aria_avx512_init);
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 646477a13e11..1dfef28c1266 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
@@ -882,7 +883,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	jmp .Ldec_max24;
 SYM_FUNC_END(__camellia_dec_blk16)
 
-SYM_FUNC_START(camellia_ecb_enc_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -907,7 +908,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_enc_16way)
 
-SYM_FUNC_START(camellia_ecb_dec_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -937,7 +938,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_dec_16way)
 
-SYM_FUNC_START(camellia_cbc_dec_16way)
+SYM_TYPED_FUNC_START(camellia_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index a0eb94e53b1b..b1c9b9450555 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 816b6bb8bded..824cb94de6c2 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "camellia-x86_64-asm_64.S"
 .text
@@ -177,7 +178,7 @@
 	bswapq				RAB0; \
 	movq RAB0,			4*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk)
+SYM_TYPED_FUNC_START(__camellia_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -224,7 +225,7 @@ SYM_FUNC_START(__camellia_enc_blk)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk)
 
-SYM_FUNC_START(camellia_dec_blk)
+SYM_TYPED_FUNC_START(camellia_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -411,7 +412,7 @@ SYM_FUNC_END(camellia_dec_blk)
 		bswapq				RAB1; \
 		movq RAB1,			12*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk_2way)
+SYM_TYPED_FUNC_START(__camellia_enc_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -460,7 +461,7 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk_2way)
 
-SYM_FUNC_START(camellia_dec_blk_2way)
+SYM_TYPED_FUNC_START(camellia_dec_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index e7e4d64e9577..2d2f4e16537c 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -69,10 +68,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg camellia_algs[] = {
 	{
-		.base.cra_name		= "__ecb(camellia)",
-		.base.cra_driver_name	= "__ecb-camellia-aesni-avx2",
+		.base.cra_name		= "ecb(camellia)",
+		.base.cra_driver_name	= "ecb-camellia-aesni-avx2",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -82,10 +80,9 @@ static struct skcipher_alg camellia_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(camellia)",
-		.base.cra_driver_name	= "__cbc-camellia-aesni-avx2",
+		.base.cra_name		= "cbc(camellia)",
+		.base.cra_driver_name	= "cbc-camellia-aesni-avx2",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -98,8 +95,6 @@ static struct skcipher_alg camellia_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
-
 static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
@@ -118,15 +113,13 @@ static int __init camellia_aesni_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(camellia_algs,
-					      ARRAY_SIZE(camellia_algs),
-					      camellia_simd_algs);
+	return crypto_register_skciphers(camellia_algs,
+					 ARRAY_SIZE(camellia_algs));
 }
 
 static void __exit camellia_aesni_fini(void)
 {
-	simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
-				  camellia_simd_algs);
+	crypto_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs));
 }
 
 module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index c7ccf63e741e..a7d162388142 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -69,10 +68,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg camellia_algs[] = {
 	{
-		.base.cra_name		= "__ecb(camellia)",
-		.base.cra_driver_name	= "__ecb-camellia-aesni",
+		.base.cra_name		= "ecb(camellia)",
+		.base.cra_driver_name	= "ecb-camellia-aesni",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -82,10 +80,9 @@ static struct skcipher_alg camellia_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(camellia)",
-		.base.cra_driver_name	= "__cbc-camellia-aesni",
+		.base.cra_name		= "cbc(camellia)",
+		.base.cra_driver_name	= "cbc-camellia-aesni",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAMELLIA_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct camellia_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -98,8 +95,6 @@ static struct skcipher_alg camellia_algs[] = {
 	}
 };
 
-static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
-
 static int __init camellia_aesni_init(void)
 {
 	const char *feature_name;
@@ -117,15 +112,13 @@ static int __init camellia_aesni_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(camellia_algs,
-					      ARRAY_SIZE(camellia_algs),
-					      camellia_simd_algs);
+	return crypto_register_skciphers(camellia_algs,
+					 ARRAY_SIZE(camellia_algs));
 }
 
 static void __exit camellia_aesni_fini(void)
 {
-	simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
-				  camellia_simd_algs);
+	crypto_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs));
 }
 
 module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 3976a87f92ad..3aca04d43b34 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -8,7 +8,6 @@
 
 #include <crypto/algapi.h>
 #include <crypto/cast5.h>
-#include <crypto/internal/simd.h>
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -64,10 +63,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg cast5_algs[] = {
 	{
-		.base.cra_name		= "__ecb(cast5)",
-		.base.cra_driver_name	= "__ecb-cast5-avx",
+		.base.cra_name		= "ecb(cast5)",
+		.base.cra_driver_name	= "ecb-cast5-avx",
 		.base.cra_priority	= 200,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAST5_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct cast5_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -77,10 +75,9 @@ static struct skcipher_alg cast5_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(cast5)",
-		.base.cra_driver_name	= "__cbc-cast5-avx",
+		.base.cra_name		= "cbc(cast5)",
+		.base.cra_driver_name	= "cbc-cast5-avx",
 		.base.cra_priority	= 200,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAST5_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct cast5_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -93,8 +90,6 @@ static struct skcipher_alg cast5_algs[] = {
 	}
 };
 
-static struct simd_skcipher_alg *cast5_simd_algs[ARRAY_SIZE(cast5_algs)];
-
 static int __init cast5_init(void)
 {
 	const char *feature_name;
@@ -105,15 +100,13 @@ static int __init cast5_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(cast5_algs,
-					      ARRAY_SIZE(cast5_algs),
-					      cast5_simd_algs);
+	return crypto_register_skciphers(cast5_algs,
+					 ARRAY_SIZE(cast5_algs));
 }
 
 static void __exit cast5_exit(void)
 {
-	simd_unregister_skciphers(cast5_algs, ARRAY_SIZE(cast5_algs),
-				  cast5_simd_algs);
+	crypto_unregister_skciphers(cast5_algs, ARRAY_SIZE(cast5_algs));
 }
 
 module_init(cast5_init);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 7e2aea372349..c4dd28c30303 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -14,7 +14,6 @@
 #include <linux/err.h>
 #include <crypto/algapi.h>
 #include <crypto/cast6.h>
-#include <crypto/internal/simd.h>
 
 #include "ecb_cbc_helpers.h"
 
@@ -64,10 +63,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg cast6_algs[] = {
 	{
-		.base.cra_name		= "__ecb(cast6)",
-		.base.cra_driver_name	= "__ecb-cast6-avx",
+		.base.cra_name		= "ecb(cast6)",
+		.base.cra_driver_name	= "ecb-cast6-avx",
 		.base.cra_priority	= 200,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAST6_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct cast6_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -77,10 +75,9 @@ static struct skcipher_alg cast6_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(cast6)",
-		.base.cra_driver_name	= "__cbc-cast6-avx",
+		.base.cra_name		= "cbc(cast6)",
+		.base.cra_driver_name	= "cbc-cast6-avx",
 		.base.cra_priority	= 200,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= CAST6_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct cast6_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -93,8 +90,6 @@ static struct skcipher_alg cast6_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *cast6_simd_algs[ARRAY_SIZE(cast6_algs)];
-
 static int __init cast6_init(void)
 {
 	const char *feature_name;
@@ -105,15 +100,12 @@ static int __init cast6_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(cast6_algs,
-					      ARRAY_SIZE(cast6_algs),
-					      cast6_simd_algs);
+	return crypto_register_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs));
 }
 
 static void __exit cast6_exit(void)
 {
-	simd_unregister_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs),
-				  cast6_simd_algs);
+	crypto_unregister_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs));
 }
 
 module_init(cast6_init);
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
deleted file mode 100644
index 7b3a1cf0984b..000000000000
--- a/arch/x86/crypto/chacha_glue.c
+++ /dev/null
@@ -1,317 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * x64 SIMD accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
-				       unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
-					unsigned int len, int nrounds);
-asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
-
-asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-				       unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-				       unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
-				       unsigned int len, int nrounds);
-
-asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					   unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					   unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
-					   unsigned int len, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
-
-static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
-{
-	len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
-	return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
-}
-
-static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
-			  unsigned int bytes, int nrounds)
-{
-	if (IS_ENABLED(CONFIG_AS_AVX512) &&
-	    static_branch_likely(&chacha_use_avx512vl)) {
-		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
-			chacha_8block_xor_avx512vl(state, dst, src, bytes,
-						   nrounds);
-			bytes -= CHACHA_BLOCK_SIZE * 8;
-			src += CHACHA_BLOCK_SIZE * 8;
-			dst += CHACHA_BLOCK_SIZE * 8;
-			state[12] += 8;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 4) {
-			chacha_8block_xor_avx512vl(state, dst, src, bytes,
-						   nrounds);
-			state[12] += chacha_advance(bytes, 8);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 2) {
-			chacha_4block_xor_avx512vl(state, dst, src, bytes,
-						   nrounds);
-			state[12] += chacha_advance(bytes, 4);
-			return;
-		}
-		if (bytes) {
-			chacha_2block_xor_avx512vl(state, dst, src, bytes,
-						   nrounds);
-			state[12] += chacha_advance(bytes, 2);
-			return;
-		}
-	}
-
-	if (static_branch_likely(&chacha_use_avx2)) {
-		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
-			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
-			bytes -= CHACHA_BLOCK_SIZE * 8;
-			src += CHACHA_BLOCK_SIZE * 8;
-			dst += CHACHA_BLOCK_SIZE * 8;
-			state[12] += 8;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 4) {
-			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
-			state[12] += chacha_advance(bytes, 8);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE * 2) {
-			chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
-			state[12] += chacha_advance(bytes, 4);
-			return;
-		}
-		if (bytes > CHACHA_BLOCK_SIZE) {
-			chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
-			state[12] += chacha_advance(bytes, 2);
-			return;
-		}
-	}
-
-	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
-		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
-		bytes -= CHACHA_BLOCK_SIZE * 4;
-		src += CHACHA_BLOCK_SIZE * 4;
-		dst += CHACHA_BLOCK_SIZE * 4;
-		state[12] += 4;
-	}
-	if (bytes > CHACHA_BLOCK_SIZE) {
-		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
-		state[12] += chacha_advance(bytes, 4);
-		return;
-	}
-	if (bytes) {
-		chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
-		state[12]++;
-	}
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
-	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
-		hchacha_block_generic(state, stream, nrounds);
-	} else {
-		kernel_fpu_begin();
-		hchacha_block_ssse3(state, stream, nrounds);
-		kernel_fpu_end();
-	}
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
-{
-	chacha_init_generic(state, key, iv);
-}
-EXPORT_SYMBOL(chacha_init_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
-		       int nrounds)
-{
-	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
-	    bytes <= CHACHA_BLOCK_SIZE)
-		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
-	do {
-		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
-		kernel_fpu_begin();
-		chacha_dosimd(state, dst, src, todo, nrounds);
-		kernel_fpu_end();
-
-		bytes -= todo;
-		src += todo;
-		dst += todo;
-	} while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_simd_stream_xor(struct skcipher_request *req,
-				  const struct chacha_ctx *ctx, const u8 *iv)
-{
-	u32 state[CHACHA_STATE_WORDS] __aligned(8);
-	struct skcipher_walk walk;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	chacha_init_generic(state, ctx->key, iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
-
-		if (!static_branch_likely(&chacha_use_simd) ||
-		    !crypto_simd_usable()) {
-			chacha_crypt_generic(state, walk.dst.virt.addr,
-					     walk.src.virt.addr, nbytes,
-					     ctx->nrounds);
-		} else {
-			kernel_fpu_begin();
-			chacha_dosimd(state, walk.dst.virt.addr,
-				      walk.src.virt.addr, nbytes,
-				      ctx->nrounds);
-			kernel_fpu_end();
-		}
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
-	}
-
-	return err;
-}
-
-static int chacha_simd(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
-	return chacha_simd_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_simd(struct skcipher_request *req)
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	u32 state[CHACHA_STATE_WORDS] __aligned(8);
-	struct chacha_ctx subctx;
-	u8 real_iv[16];
-
-	chacha_init_generic(state, ctx->key, req->iv);
-
-	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
-		kernel_fpu_begin();
-		hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
-		kernel_fpu_end();
-	} else {
-		hchacha_block_generic(state, subctx.key, ctx->nrounds);
-	}
-	subctx.nrounds = ctx->nrounds;
-
-	memcpy(&real_iv[0], req->iv + 24, 8);
-	memcpy(&real_iv[8], req->iv + 16, 8);
-	return chacha_simd_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
-	{
-		.base.cra_name		= "chacha20",
-		.base.cra_driver_name	= "chacha20-simd",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= CHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= chacha_simd,
-		.decrypt		= chacha_simd,
-	}, {
-		.base.cra_name		= "xchacha20",
-		.base.cra_driver_name	= "xchacha20-simd",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha20_setkey,
-		.encrypt		= xchacha_simd,
-		.decrypt		= xchacha_simd,
-	}, {
-		.base.cra_name		= "xchacha12",
-		.base.cra_driver_name	= "xchacha12-simd",
-		.base.cra_priority	= 300,
-		.base.cra_blocksize	= 1,
-		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
-		.base.cra_module	= THIS_MODULE,
-
-		.min_keysize		= CHACHA_KEY_SIZE,
-		.max_keysize		= CHACHA_KEY_SIZE,
-		.ivsize			= XCHACHA_IV_SIZE,
-		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= chacha12_setkey,
-		.encrypt		= xchacha_simd,
-		.decrypt		= xchacha_simd,
-	},
-};
-
-static int __init chacha_simd_mod_init(void)
-{
-	if (!boot_cpu_has(X86_FEATURE_SSSE3))
-		return 0;
-
-	static_branch_enable(&chacha_use_simd);
-
-	if (boot_cpu_has(X86_FEATURE_AVX) &&
-	    boot_cpu_has(X86_FEATURE_AVX2) &&
-	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
-		static_branch_enable(&chacha_use_avx2);
-
-		if (IS_ENABLED(CONFIG_AS_AVX512) &&
-		    boot_cpu_has(X86_FEATURE_AVX512VL) &&
-		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
-			static_branch_enable(&chacha_use_avx512vl);
-	}
-	return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
-		crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3))
-		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (x64 SIMD accelerated)");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-simd");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-simd");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-simd");
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index e88439d3828e..34600f90d8a6 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -73,7 +73,7 @@ static int ecb_crypt(struct skcipher_request *req, const u32 *expkey)
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		u8 *wsrc = walk.src.virt.addr;
+		const u8 *wsrc = walk.src.virt.addr;
 		u8 *wdst = walk.dst.virt.addr;
 
 		/* Process four block batch */
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 99cb983ded9e..c4fbaa82ed7a 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -103,8 +103,8 @@ SYM_FUNC_START(clmul_ghash_mul)
 SYM_FUNC_END(clmul_ghash_mul)
 
 /*
- * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- *			   const le128 *shash);
+ * int clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
+ *			  const le128 *shash);
  */
 SYM_FUNC_START(clmul_ghash_update)
 	FRAME_BEGIN
@@ -127,6 +127,7 @@ SYM_FUNC_START(clmul_ghash_update)
 	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
+	mov %rdx, %rax
 	FRAME_END
 	RET
 SYM_FUNC_END(clmul_ghash_update)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 41bc02e48916..aea5d4d06be7 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -7,41 +7,27 @@
  *   Author: Huang Ying <ying.huang@intel.com>
  */
 
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
-#include <crypto/cryptd.h>
-#include <crypto/gf128mul.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <asm/cpu_device_id.h>
 #include <asm/simd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ghash.h>
+#include <crypto/internal/hash.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
 #include <linux/unaligned.h>
 
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
+asmlinkage void clmul_ghash_mul(char *dst, const le128 *shash);
 
-void clmul_ghash_mul(char *dst, const le128 *shash);
+asmlinkage int clmul_ghash_update(char *dst, const char *src,
+				  unsigned int srclen, const le128 *shash);
 
-void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
-			const le128 *shash);
-
-struct ghash_async_ctx {
-	struct cryptd_ahash *cryptd_tfm;
-};
-
-struct ghash_ctx {
+struct x86_ghash_ctx {
 	le128 shash;
 };
 
-struct ghash_desc_ctx {
-	u8 buffer[GHASH_BLOCK_SIZE];
-	u32 bytes;
-};
-
 static int ghash_init(struct shash_desc *desc)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -54,7 +40,7 @@ static int ghash_init(struct shash_desc *desc)
 static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(tfm);
 	u64 a, b;
 
 	if (keylen != GHASH_BLOCK_SIZE)
@@ -95,64 +81,38 @@ static int ghash_setkey(struct crypto_shash *tfm,
 static int ghash_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *dst = dctx->buffer;
+	int remain;
 
 	kernel_fpu_begin();
-	if (dctx->bytes) {
-		int n = min(srclen, dctx->bytes);
-		u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
-		dctx->bytes -= n;
-		srclen -= n;
-
-		while (n--)
-			*pos++ ^= *src++;
-
-		if (!dctx->bytes)
-			clmul_ghash_mul(dst, &ctx->shash);
-	}
-
-	clmul_ghash_update(dst, src, srclen, &ctx->shash);
+	remain = clmul_ghash_update(dst, src, srclen, &ctx->shash);
 	kernel_fpu_end();
-
-	if (srclen & 0xf) {
-		src += srclen - (srclen & 0xf);
-		srclen &= 0xf;
-		dctx->bytes = GHASH_BLOCK_SIZE - srclen;
-		while (srclen--)
-			*dst++ ^= *src++;
-	}
-
-	return 0;
+	return remain;
 }
 
-static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static void ghash_flush(struct x86_ghash_ctx *ctx, struct ghash_desc_ctx *dctx,
+			const u8 *src, unsigned int len)
 {
 	u8 *dst = dctx->buffer;
 
-	if (dctx->bytes) {
-		u8 *tmp = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
-		while (dctx->bytes--)
-			*tmp++ ^= 0;
-
-		kernel_fpu_begin();
+	kernel_fpu_begin();
+	if (len) {
+		crypto_xor(dst, src, len);
 		clmul_ghash_mul(dst, &ctx->shash);
-		kernel_fpu_end();
 	}
-
-	dctx->bytes = 0;
+	kernel_fpu_end();
 }
 
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *dst)
 {
+	struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	u8 *buf = dctx->buffer;
 
-	ghash_flush(ctx, dctx);
+	ghash_flush(ctx, dctx, src, len);
 	memcpy(dst, buf, GHASH_BLOCK_SIZE);
 
 	return 0;
@@ -162,175 +122,20 @@ static struct shash_alg ghash_alg = {
 	.digestsize	= GHASH_DIGEST_SIZE,
 	.init		= ghash_init,
 	.update		= ghash_update,
-	.final		= ghash_final,
+	.finup		= ghash_finup,
 	.setkey		= ghash_setkey,
 	.descsize	= sizeof(struct ghash_desc_ctx),
 	.base		= {
-		.cra_name		= "__ghash",
-		.cra_driver_name	= "__ghash-pclmulqdqni",
-		.cra_priority		= 0,
-		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_name		= "ghash",
+		.cra_driver_name	= "ghash-pclmulqdqni",
+		.cra_priority		= 400,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct ghash_ctx),
+		.cra_ctxsize		= sizeof(struct x86_ghash_ctx),
 		.cra_module		= THIS_MODULE,
 	},
 };
 
-static int ghash_async_init(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-	desc->tfm = child;
-	return crypto_shash_init(desc);
-}
-
-static int ghash_async_update(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_update(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return shash_ahash_update(req, desc);
-	}
-}
-
-static int ghash_async_final(struct ahash_request *req)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_final(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		return crypto_shash_final(desc, req->result);
-	}
-}
-
-static int ghash_async_import(struct ahash_request *req, const void *in)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	ghash_async_init(req);
-	memcpy(dctx, in, sizeof(*dctx));
-	return 0;
-
-}
-
-static int ghash_async_export(struct ahash_request *req, void *out)
-{
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	memcpy(out, dctx, sizeof(*dctx));
-	return 0;
-
-}
-
-static int ghash_async_digest(struct ahash_request *req)
-{
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ahash_request *cryptd_req = ahash_request_ctx(req);
-	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
-	if (!crypto_simd_usable() ||
-	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_digest(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		return shash_ahash_digest(req, desc);
-	}
-}
-
-static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct crypto_ahash *child = &ctx->cryptd_tfm->base;
-
-	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
-			       & CRYPTO_TFM_REQ_MASK);
-	return crypto_ahash_setkey(child, key, keylen);
-}
-
-static int ghash_async_init_tfm(struct crypto_tfm *tfm)
-{
-	struct cryptd_ahash *cryptd_tfm;
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni",
-					CRYPTO_ALG_INTERNAL,
-					CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-	ctx->cryptd_tfm = cryptd_tfm;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct ahash_request) +
-				 crypto_ahash_reqsize(&cryptd_tfm->base));
-
-	return 0;
-}
-
-static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ahash(ctx->cryptd_tfm);
-}
-
-static struct ahash_alg ghash_async_alg = {
-	.init		= ghash_async_init,
-	.update		= ghash_async_update,
-	.final		= ghash_async_final,
-	.setkey		= ghash_async_setkey,
-	.digest		= ghash_async_digest,
-	.export		= ghash_async_export,
-	.import		= ghash_async_import,
-	.halg = {
-		.digestsize	= GHASH_DIGEST_SIZE,
-		.statesize = sizeof(struct ghash_desc_ctx),
-		.base = {
-			.cra_name		= "ghash",
-			.cra_driver_name	= "ghash-clmulni",
-			.cra_priority		= 400,
-			.cra_ctxsize		= sizeof(struct ghash_async_ctx),
-			.cra_flags		= CRYPTO_ALG_ASYNC,
-			.cra_blocksize		= GHASH_BLOCK_SIZE,
-			.cra_module		= THIS_MODULE,
-			.cra_init		= ghash_async_init_tfm,
-			.cra_exit		= ghash_async_exit_tfm,
-		},
-	},
-};
-
 static const struct x86_cpu_id pcmul_cpu_id[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), /* Pickle-Mickle-Duck */
 	{}
@@ -339,29 +144,14 @@ MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
 
 static int __init ghash_pclmulqdqni_mod_init(void)
 {
-	int err;
-
 	if (!x86_match_cpu(pcmul_cpu_id))
 		return -ENODEV;
 
-	err = crypto_register_shash(&ghash_alg);
-	if (err)
-		goto err_out;
-	err = crypto_register_ahash(&ghash_async_alg);
-	if (err)
-		goto err_shash;
-
-	return 0;
-
-err_shash:
-	crypto_unregister_shash(&ghash_alg);
-err_out:
-	return err;
+	return crypto_register_shash(&ghash_alg);
 }
 
 static void __exit ghash_pclmulqdqni_mod_exit(void)
 {
-	crypto_unregister_ahash(&ghash_async_alg);
 	crypto_unregister_shash(&ghash_alg);
 }
 
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
deleted file mode 100644
index 08ff4b489f7e..000000000000
--- a/arch/x86/crypto/poly1305_glue.c
+++ /dev/null
@@ -1,290 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/crypto.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-asmlinkage void poly1305_init_x86_64(void *ctx,
-				     const u8 key[POLY1305_BLOCK_SIZE]);
-asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp,
-				       const size_t len, const u32 padbit);
-asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
-				     const u32 nonce[4]);
-asmlinkage void poly1305_emit_avx(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
-				  const u32 nonce[4]);
-asmlinkage void poly1305_blocks_avx(void *ctx, const u8 *inp, const size_t len,
-				    const u32 padbit);
-asmlinkage void poly1305_blocks_avx2(void *ctx, const u8 *inp, const size_t len,
-				     const u32 padbit);
-asmlinkage void poly1305_blocks_avx512(void *ctx, const u8 *inp,
-				       const size_t len, const u32 padbit);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512);
-
-struct poly1305_arch_internal {
-	union {
-		struct {
-			u32 h[5];
-			u32 is_base2_26;
-		};
-		u64 hs[3];
-	};
-	u64 r[2];
-	u64 pad;
-	struct { u32 r2, r1, r4, r3; } rn[9];
-};
-
-/* The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit
- * the unfortunate situation of using AVX and then having to go back to scalar
- * -- because the user is silly and has called the update function from two
- * separate contexts -- then we need to convert back to the original base before
- * proceeding. It is possible to reason that the initial reduction below is
- * sufficient given the implementation invariants. However, for an avoidance of
- * doubt and because this is not performance critical, we do the full reduction
- * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py
- */
-static void convert_to_base2_64(void *ctx)
-{
-	struct poly1305_arch_internal *state = ctx;
-	u32 cy;
-
-	if (!state->is_base2_26)
-		return;
-
-	cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy;
-	cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy;
-	cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy;
-	cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy;
-	state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0];
-	state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12);
-	state->hs[2] = state->h[4] >> 24;
-#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1))
-	cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL);
-	state->hs[2] &= 3;
-	state->hs[0] += cy;
-	state->hs[1] += (cy = ULT(state->hs[0], cy));
-	state->hs[2] += ULT(state->hs[1], cy);
-#undef ULT
-	state->is_base2_26 = 0;
-}
-
-static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_BLOCK_SIZE])
-{
-	poly1305_init_x86_64(ctx, key);
-}
-
-static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
-				 const u32 padbit)
-{
-	struct poly1305_arch_internal *state = ctx;
-
-	/* SIMD disables preemption, so relax after processing each page. */
-	BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE ||
-		     SZ_4K % POLY1305_BLOCK_SIZE);
-
-	if (!static_branch_likely(&poly1305_use_avx) ||
-	    (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) ||
-	    !crypto_simd_usable()) {
-		convert_to_base2_64(ctx);
-		poly1305_blocks_x86_64(ctx, inp, len, padbit);
-		return;
-	}
-
-	do {
-		const size_t bytes = min_t(size_t, len, SZ_4K);
-
-		kernel_fpu_begin();
-		if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512))
-			poly1305_blocks_avx512(ctx, inp, bytes, padbit);
-		else if (static_branch_likely(&poly1305_use_avx2))
-			poly1305_blocks_avx2(ctx, inp, bytes, padbit);
-		else
-			poly1305_blocks_avx(ctx, inp, bytes, padbit);
-		kernel_fpu_end();
-
-		len -= bytes;
-		inp += bytes;
-	} while (len);
-}
-
-static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
-			       const u32 nonce[4])
-{
-	if (!static_branch_likely(&poly1305_use_avx))
-		poly1305_emit_x86_64(ctx, mac, nonce);
-	else
-		poly1305_emit_avx(ctx, mac, nonce);
-}
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	poly1305_simd_init(&dctx->h, key);
-	dctx->s[0] = get_unaligned_le32(&key[16]);
-	dctx->s[1] = get_unaligned_le32(&key[20]);
-	dctx->s[2] = get_unaligned_le32(&key[24]);
-	dctx->s[3] = get_unaligned_le32(&key[28]);
-	dctx->buflen = 0;
-	dctx->sset = true;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx,
-					       const u8 *inp, unsigned int len)
-{
-	unsigned int acc = 0;
-	if (unlikely(!dctx->sset)) {
-		if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) {
-			poly1305_simd_init(&dctx->h, inp);
-			inp += POLY1305_BLOCK_SIZE;
-			len -= POLY1305_BLOCK_SIZE;
-			acc += POLY1305_BLOCK_SIZE;
-			dctx->rset = 1;
-		}
-		if (len >= POLY1305_BLOCK_SIZE) {
-			dctx->s[0] = get_unaligned_le32(&inp[0]);
-			dctx->s[1] = get_unaligned_le32(&inp[4]);
-			dctx->s[2] = get_unaligned_le32(&inp[8]);
-			dctx->s[3] = get_unaligned_le32(&inp[12]);
-			acc += POLY1305_BLOCK_SIZE;
-			dctx->sset = true;
-		}
-	}
-	return acc;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int srclen)
-{
-	unsigned int bytes, used;
-
-	if (unlikely(dctx->buflen)) {
-		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		srclen -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf, POLY1305_BLOCK_SIZE)))
-				poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
-		srclen -= bytes;
-		used = crypto_poly1305_setdctxkey(dctx, src, bytes);
-		if (likely(bytes - used))
-			poly1305_simd_blocks(&dctx->h, src + used, bytes - used, 1);
-		src += bytes;
-	}
-
-	if (unlikely(srclen)) {
-		dctx->buflen = srclen;
-		memcpy(dctx->buf, src, srclen);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_simd_emit(&dctx->h, dst, dctx->s);
-	memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int crypto_poly1305_init(struct shash_desc *desc)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	*dctx = (struct poly1305_desc_ctx){};
-	return 0;
-}
-
-static int crypto_poly1305_update(struct shash_desc *desc,
-				  const u8 *src, unsigned int srclen)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	poly1305_update_arch(dctx, src, srclen);
-	return 0;
-}
-
-static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
-	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	if (unlikely(!dctx->sset))
-		return -ENOKEY;
-
-	poly1305_final_arch(dctx, dst);
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	= POLY1305_DIGEST_SIZE,
-	.init		= crypto_poly1305_init,
-	.update		= crypto_poly1305_update,
-	.final		= crypto_poly1305_final,
-	.descsize	= sizeof(struct poly1305_desc_ctx),
-	.base		= {
-		.cra_name		= "poly1305",
-		.cra_driver_name	= "poly1305-simd",
-		.cra_priority		= 300,
-		.cra_blocksize		= POLY1305_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	},
-};
-
-static int __init poly1305_simd_mod_init(void)
-{
-	if (boot_cpu_has(X86_FEATURE_AVX) &&
-	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
-		static_branch_enable(&poly1305_use_avx);
-	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
-	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
-		static_branch_enable(&poly1305_use_avx2);
-	if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) &&
-	    boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) &&
-	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
-	    /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
-	    boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
-		static_branch_enable(&poly1305_use_avx512);
-	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0;
-}
-
-static void __exit poly1305_simd_mod_exit(void)
-{
-	if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
-		crypto_unregister_shash(&alg);
-}
-
-module_init(poly1305_simd_mod_init);
-module_exit(poly1305_simd_mod_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
-MODULE_DESCRIPTION("Poly1305 authenticator");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-simd");
diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c
index 8fa58b0f3cb3..6b466867f91a 100644
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -16,16 +16,15 @@
  * operations.
  */
 
-#include <crypto/algapi.h>
+#include <asm/cpu_device_id.h>
+#include <asm/fpu/api.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
 #include <crypto/polyval.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
+#include <linux/string.h>
 
 #define POLYVAL_ALIGN	16
 #define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
@@ -42,7 +41,6 @@ struct polyval_tfm_ctx {
 
 struct polyval_desc_ctx {
 	u8 buffer[POLYVAL_BLOCK_SIZE];
-	u32 bytes;
 };
 
 asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
@@ -57,25 +55,16 @@ static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
 static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator)
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_fpu_begin();
-		clmul_polyval_update(keys, in, nblocks, accumulator);
-		kernel_fpu_end();
-	} else {
-		polyval_update_non4k(keys->key_powers[NUM_KEY_POWERS-1], in,
-			nblocks, accumulator);
-	}
+	kernel_fpu_begin();
+	clmul_polyval_update(keys, in, nblocks, accumulator);
+	kernel_fpu_end();
 }
 
 static void internal_polyval_mul(u8 *op1, const u8 *op2)
 {
-	if (likely(crypto_simd_usable())) {
-		kernel_fpu_begin();
-		clmul_polyval_mul(op1, op2);
-		kernel_fpu_end();
-	} else {
-		polyval_mul_non4k(op1, op2);
-	}
+	kernel_fpu_begin();
+	clmul_polyval_mul(op1, op2);
+	kernel_fpu_end();
 }
 
 static int polyval_x86_setkey(struct crypto_shash *tfm,
@@ -112,49 +101,27 @@ static int polyval_x86_update(struct shash_desc *desc,
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
 	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
-	u8 *pos;
 	unsigned int nblocks;
-	unsigned int n;
-
-	if (dctx->bytes) {
-		n = min(srclen, dctx->bytes);
-		pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes;
-
-		dctx->bytes -= n;
-		srclen -= n;
-
-		while (n--)
-			*pos++ ^= *src++;
 
-		if (!dctx->bytes)
-			internal_polyval_mul(dctx->buffer,
-					    tctx->key_powers[NUM_KEY_POWERS-1]);
-	}
-
-	while (srclen >= POLYVAL_BLOCK_SIZE) {
+	do {
 		/* Allow rescheduling every 4K bytes. */
 		nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
 		internal_polyval_update(tctx, src, nblocks, dctx->buffer);
 		srclen -= nblocks * POLYVAL_BLOCK_SIZE;
 		src += nblocks * POLYVAL_BLOCK_SIZE;
-	}
+	} while (srclen >= POLYVAL_BLOCK_SIZE);
 
-	if (srclen) {
-		dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
-		pos = dctx->buffer;
-		while (srclen--)
-			*pos++ ^= *src++;
-	}
-
-	return 0;
+	return srclen;
 }
 
-static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
+static int polyval_x86_finup(struct shash_desc *desc, const u8 *src,
+			     unsigned int len, u8 *dst)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
 	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
 
-	if (dctx->bytes) {
+	if (len) {
+		crypto_xor(dctx->buffer, src, len);
 		internal_polyval_mul(dctx->buffer,
 				     tctx->key_powers[NUM_KEY_POWERS-1]);
 	}
@@ -168,13 +135,14 @@ static struct shash_alg polyval_alg = {
 	.digestsize	= POLYVAL_DIGEST_SIZE,
 	.init		= polyval_x86_init,
 	.update		= polyval_x86_update,
-	.final		= polyval_x86_final,
+	.finup		= polyval_x86_finup,
 	.setkey		= polyval_x86_setkey,
 	.descsize	= sizeof(struct polyval_desc_ctx),
 	.base		= {
 		.cra_name		= "polyval",
 		.cra_driver_name	= "polyval-clmulni",
 		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
 		.cra_ctxsize		= POLYVAL_CTX_SIZE,
 		.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 97e283621851..84e47f7f6188 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
@@ -656,7 +657,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	RET;
 SYM_FUNC_END(__serpent_dec_blk8_avx)
 
-SYM_FUNC_START(serpent_ecb_enc_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -674,7 +675,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
-SYM_FUNC_START(serpent_ecb_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -692,7 +693,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
-SYM_FUNC_START(serpent_cbc_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_cbc_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 347e97f4b713..f5f2121b7956 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -10,7 +10,6 @@
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
 
 #include "serpent-avx.h"
@@ -65,10 +64,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg serpent_algs[] = {
 	{
-		.base.cra_name		= "__ecb(serpent)",
-		.base.cra_driver_name	= "__ecb-serpent-avx2",
+		.base.cra_name		= "ecb(serpent)",
+		.base.cra_driver_name	= "ecb-serpent-avx2",
 		.base.cra_priority	= 600,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -78,10 +76,9 @@ static struct skcipher_alg serpent_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(serpent)",
-		.base.cra_driver_name	= "__cbc-serpent-avx2",
+		.base.cra_name		= "cbc(serpent)",
+		.base.cra_driver_name	= "cbc-serpent-avx2",
 		.base.cra_priority	= 600,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -94,8 +91,6 @@ static struct skcipher_alg serpent_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
 static int __init serpent_avx2_init(void)
 {
 	const char *feature_name;
@@ -110,15 +105,13 @@ static int __init serpent_avx2_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(serpent_algs,
-					      ARRAY_SIZE(serpent_algs),
-					      serpent_simd_algs);
+	return crypto_register_skciphers(serpent_algs,
+					 ARRAY_SIZE(serpent_algs));
 }
 
 static void __exit serpent_avx2_fini(void)
 {
-	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
-				  serpent_simd_algs);
+	crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
 }
 
 module_init(serpent_avx2_init);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 6c248e1ea4ef..e640abc1cb8a 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -13,7 +13,6 @@
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
 
 #include "serpent-avx.h"
@@ -71,10 +70,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg serpent_algs[] = {
 	{
-		.base.cra_name		= "__ecb(serpent)",
-		.base.cra_driver_name	= "__ecb-serpent-avx",
+		.base.cra_name		= "ecb(serpent)",
+		.base.cra_driver_name	= "ecb-serpent-avx",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -84,10 +82,9 @@ static struct skcipher_alg serpent_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(serpent)",
-		.base.cra_driver_name	= "__cbc-serpent-avx",
+		.base.cra_name		= "cbc(serpent)",
+		.base.cra_driver_name	= "cbc-serpent-avx",
 		.base.cra_priority	= 500,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -100,8 +97,6 @@ static struct skcipher_alg serpent_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
 static int __init serpent_init(void)
 {
 	const char *feature_name;
@@ -112,15 +107,13 @@ static int __init serpent_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(serpent_algs,
-					      ARRAY_SIZE(serpent_algs),
-					      serpent_simd_algs);
+	return crypto_register_skciphers(serpent_algs,
+					 ARRAY_SIZE(serpent_algs));
 }
 
 static void __exit serpent_exit(void)
 {
-	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
-				  serpent_simd_algs);
+	crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
 }
 
 module_init(serpent_init);
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index d78f37e9b2cf..80ee17ec21b4 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -18,7 +18,6 @@
 #include <linux/err.h>
 #include <crypto/algapi.h>
 #include <crypto/b128ops.h>
-#include <crypto/internal/simd.h>
 #include <crypto/serpent.h>
 
 #include "serpent-sse2.h"
@@ -74,10 +73,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg serpent_algs[] = {
 	{
-		.base.cra_name		= "__ecb(serpent)",
-		.base.cra_driver_name	= "__ecb-serpent-sse2",
+		.base.cra_name		= "ecb(serpent)",
+		.base.cra_driver_name	= "ecb-serpent-sse2",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -87,10 +85,9 @@ static struct skcipher_alg serpent_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(serpent)",
-		.base.cra_driver_name	= "__cbc-serpent-sse2",
+		.base.cra_name		= "cbc(serpent)",
+		.base.cra_driver_name	= "cbc-serpent-sse2",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= SERPENT_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct serpent_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -103,8 +100,6 @@ static struct skcipher_alg serpent_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
 static int __init serpent_sse2_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2)) {
@@ -112,15 +107,13 @@ static int __init serpent_sse2_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(serpent_algs,
-					      ARRAY_SIZE(serpent_algs),
-					      serpent_simd_algs);
+	return crypto_register_skciphers(serpent_algs,
+					 ARRAY_SIZE(serpent_algs));
 }
 
 static void __exit serpent_sse2_exit(void)
 {
-	simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
-				  serpent_simd_algs);
+	crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
 }
 
 module_init(serpent_sse2_init);
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index ab8bc54f254d..0a912bfc86c5 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -16,21 +16,17 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
 #include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 static const struct x86_cpu_id module_cpu_ids[] = {
-#ifdef CONFIG_AS_SHA1_NI
 	X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
-#endif
 	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
@@ -38,14 +34,10 @@ static const struct x86_cpu_id module_cpu_ids[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
 
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, sha1_block_fn *sha1_xform)
+static inline int sha1_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, sha1_block_fn *sha1_xform)
 {
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
-		return crypto_sha1_update(desc, data, len);
+	int remain;
 
 	/*
 	 * Make sure struct sha1_state begins directly with the SHA1
@@ -54,22 +46,18 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 	BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
 
 	kernel_fpu_begin();
-	sha1_base_do_update(desc, data, len, sha1_xform);
+	remain = sha1_base_do_update_blocks(desc, data, len, sha1_xform);
 	kernel_fpu_end();
 
-	return 0;
+	return remain;
 }
 
-static int sha1_finup(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out, sha1_block_fn *sha1_xform)
+static inline int sha1_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out,
+			     sha1_block_fn *sha1_xform)
 {
-	if (!crypto_simd_usable())
-		return crypto_sha1_finup(desc, data, len, out);
-
 	kernel_fpu_begin();
-	if (len)
-		sha1_base_do_update(desc, data, len, sha1_xform);
-	sha1_base_do_finalize(desc, sha1_xform);
+	sha1_base_do_finup(desc, data, len, sha1_xform);
 	kernel_fpu_end();
 
 	return sha1_base_finish(desc, out);
@@ -90,23 +78,17 @@ static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
 	return sha1_finup(desc, data, len, out, sha1_transform_ssse3);
 }
 
-/* Add padding and return the message digest. */
-static int sha1_ssse3_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_ssse3_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha1_ssse3_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_ssse3_update,
-	.final		=	sha1_ssse3_final,
 	.finup		=	sha1_ssse3_finup,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-ssse3",
 		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -140,22 +122,17 @@ static int sha1_avx_finup(struct shash_desc *desc, const u8 *data,
 	return sha1_finup(desc, data, len, out, sha1_transform_avx);
 }
 
-static int sha1_avx_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_avx_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha1_avx_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_avx_update,
-	.final		=	sha1_avx_final,
 	.finup		=	sha1_avx_finup,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-avx",
 		.cra_priority	=	160,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -200,8 +177,8 @@ static bool avx2_usable(void)
 	return false;
 }
 
-static void sha1_apply_transform_avx2(struct sha1_state *state,
-				      const u8 *data, int blocks)
+static inline void sha1_apply_transform_avx2(struct sha1_state *state,
+					     const u8 *data, int blocks)
 {
 	/* Select the optimal transform based on data block size */
 	if (blocks >= SHA1_AVX2_BLOCK_OPTSIZE)
@@ -222,22 +199,17 @@ static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data,
 	return sha1_finup(desc, data, len, out, sha1_apply_transform_avx2);
 }
 
-static int sha1_avx2_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_avx2_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha1_avx2_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_avx2_update,
-	.final		=	sha1_avx2_final,
 	.finup		=	sha1_avx2_finup,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-avx2",
 		.cra_priority	=	170,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -256,7 +228,6 @@ static void unregister_sha1_avx2(void)
 		crypto_unregister_shash(&sha1_avx2_alg);
 }
 
-#ifdef CONFIG_AS_SHA1_NI
 asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data,
 				  int rounds);
 
@@ -272,22 +243,17 @@ static int sha1_ni_finup(struct shash_desc *desc, const u8 *data,
 	return sha1_finup(desc, data, len, out, sha1_ni_transform);
 }
 
-static int sha1_ni_final(struct shash_desc *desc, u8 *out)
-{
-	return sha1_ni_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha1_ni_alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_base_init,
 	.update		=	sha1_ni_update,
-	.final		=	sha1_ni_final,
 	.finup		=	sha1_ni_finup,
-	.descsize	=	sizeof(struct sha1_state),
+	.descsize	=	SHA1_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-ni",
 		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -306,11 +272,6 @@ static void unregister_sha1_ni(void)
 		crypto_unregister_shash(&sha1_ni_alg);
 }
 
-#else
-static inline int register_sha1_ni(void) { return 0; }
-static inline void unregister_sha1_ni(void) { }
-#endif
-
 static int __init sha1_ssse3_mod_init(void)
 {
 	if (!x86_match_cpu(module_cpu_ids))
@@ -360,6 +321,4 @@ MODULE_ALIAS_CRYPTO("sha1");
 MODULE_ALIAS_CRYPTO("sha1-ssse3");
 MODULE_ALIAS_CRYPTO("sha1-avx");
 MODULE_ALIAS_CRYPTO("sha1-avx2");
-#ifdef CONFIG_AS_SHA1_NI
 MODULE_ALIAS_CRYPTO("sha1-ni");
-#endif
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
deleted file mode 100644
index e04a43d9f7d5..000000000000
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ /dev/null
@@ -1,467 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Glue code for the SHA256 Secure Hash Algorithm assembler implementations
- * using SSSE3, AVX, AVX2, and SHA-NI instructions.
- *
- * This file is based on sha256_generic.c
- *
- * Copyright (C) 2013 Intel Corporation.
- *
- * Author:
- *     Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/string.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
-				       const u8 *data, int blocks);
-
-static const struct x86_cpu_id module_cpu_ids[] = {
-#ifdef CONFIG_AS_SHA256_NI
-	X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
-#endif
-	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
-	X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
-	X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
-
-static int _sha256_update(struct shash_desc *desc, const u8 *data,
-			  unsigned int len, sha256_block_fn *sha256_xform)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
-		return crypto_sha256_update(desc, data, len);
-
-	/*
-	 * Make sure struct sha256_state begins directly with the SHA256
-	 * 256-bit internal state, as this is what the asm functions expect.
-	 */
-	BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
-
-	kernel_fpu_begin();
-	sha256_base_do_update(desc, data, len, sha256_xform);
-	kernel_fpu_end();
-
-	return 0;
-}
-
-static int sha256_finup(struct shash_desc *desc, const u8 *data,
-	      unsigned int len, u8 *out, sha256_block_fn *sha256_xform)
-{
-	if (!crypto_simd_usable())
-		return crypto_sha256_finup(desc, data, len, out);
-
-	kernel_fpu_begin();
-	if (len)
-		sha256_base_do_update(desc, data, len, sha256_xform);
-	sha256_base_do_finalize(desc, sha256_xform);
-	kernel_fpu_end();
-
-	return sha256_base_finish(desc, out);
-}
-
-static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	return _sha256_update(desc, data, len, sha256_transform_ssse3);
-}
-
-static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data,
-	      unsigned int len, u8 *out)
-{
-	return sha256_finup(desc, data, len, out, sha256_transform_ssse3);
-}
-
-/* Add padding and return the message digest. */
-static int sha256_ssse3_final(struct shash_desc *desc, u8 *out)
-{
-	return sha256_ssse3_finup(desc, NULL, 0, out);
-}
-
-static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data,
-	      unsigned int len, u8 *out)
-{
-	return sha256_base_init(desc) ?:
-	       sha256_ssse3_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_ssse3_algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	sha256_ssse3_update,
-	.final		=	sha256_ssse3_final,
-	.finup		=	sha256_ssse3_finup,
-	.digest		=	sha256_ssse3_digest,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-ssse3",
-		.cra_priority	=	150,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	sha256_ssse3_update,
-	.final		=	sha256_ssse3_final,
-	.finup		=	sha256_ssse3_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-ssse3",
-		.cra_priority	=	150,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int register_sha256_ssse3(void)
-{
-	if (boot_cpu_has(X86_FEATURE_SSSE3))
-		return crypto_register_shashes(sha256_ssse3_algs,
-				ARRAY_SIZE(sha256_ssse3_algs));
-	return 0;
-}
-
-static void unregister_sha256_ssse3(void)
-{
-	if (boot_cpu_has(X86_FEATURE_SSSE3))
-		crypto_unregister_shashes(sha256_ssse3_algs,
-				ARRAY_SIZE(sha256_ssse3_algs));
-}
-
-asmlinkage void sha256_transform_avx(struct sha256_state *state,
-				     const u8 *data, int blocks);
-
-static int sha256_avx_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	return _sha256_update(desc, data, len, sha256_transform_avx);
-}
-
-static int sha256_avx_finup(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_finup(desc, data, len, out, sha256_transform_avx);
-}
-
-static int sha256_avx_final(struct shash_desc *desc, u8 *out)
-{
-	return sha256_avx_finup(desc, NULL, 0, out);
-}
-
-static int sha256_avx_digest(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_base_init(desc) ?:
-	       sha256_avx_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_avx_algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	sha256_avx_update,
-	.final		=	sha256_avx_final,
-	.finup		=	sha256_avx_finup,
-	.digest		=	sha256_avx_digest,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-avx",
-		.cra_priority	=	160,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	sha256_avx_update,
-	.final		=	sha256_avx_final,
-	.finup		=	sha256_avx_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-avx",
-		.cra_priority	=	160,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static bool avx_usable(void)
-{
-	if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
-		if (boot_cpu_has(X86_FEATURE_AVX))
-			pr_info("AVX detected but unusable.\n");
-		return false;
-	}
-
-	return true;
-}
-
-static int register_sha256_avx(void)
-{
-	if (avx_usable())
-		return crypto_register_shashes(sha256_avx_algs,
-				ARRAY_SIZE(sha256_avx_algs));
-	return 0;
-}
-
-static void unregister_sha256_avx(void)
-{
-	if (avx_usable())
-		crypto_unregister_shashes(sha256_avx_algs,
-				ARRAY_SIZE(sha256_avx_algs));
-}
-
-asmlinkage void sha256_transform_rorx(struct sha256_state *state,
-				      const u8 *data, int blocks);
-
-static int sha256_avx2_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	return _sha256_update(desc, data, len, sha256_transform_rorx);
-}
-
-static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_finup(desc, data, len, out, sha256_transform_rorx);
-}
-
-static int sha256_avx2_final(struct shash_desc *desc, u8 *out)
-{
-	return sha256_avx2_finup(desc, NULL, 0, out);
-}
-
-static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_base_init(desc) ?:
-	       sha256_avx2_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_avx2_algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	sha256_avx2_update,
-	.final		=	sha256_avx2_final,
-	.finup		=	sha256_avx2_finup,
-	.digest		=	sha256_avx2_digest,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-avx2",
-		.cra_priority	=	170,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	sha256_avx2_update,
-	.final		=	sha256_avx2_final,
-	.finup		=	sha256_avx2_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-avx2",
-		.cra_priority	=	170,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static bool avx2_usable(void)
-{
-	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) &&
-		    boot_cpu_has(X86_FEATURE_BMI2))
-		return true;
-
-	return false;
-}
-
-static int register_sha256_avx2(void)
-{
-	if (avx2_usable())
-		return crypto_register_shashes(sha256_avx2_algs,
-				ARRAY_SIZE(sha256_avx2_algs));
-	return 0;
-}
-
-static void unregister_sha256_avx2(void)
-{
-	if (avx2_usable())
-		crypto_unregister_shashes(sha256_avx2_algs,
-				ARRAY_SIZE(sha256_avx2_algs));
-}
-
-#ifdef CONFIG_AS_SHA256_NI
-asmlinkage void sha256_ni_transform(struct sha256_state *digest,
-				    const u8 *data, int rounds);
-
-static int sha256_ni_update(struct shash_desc *desc, const u8 *data,
-			 unsigned int len)
-{
-	return _sha256_update(desc, data, len, sha256_ni_transform);
-}
-
-static int sha256_ni_finup(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_finup(desc, data, len, out, sha256_ni_transform);
-}
-
-static int sha256_ni_final(struct shash_desc *desc, u8 *out)
-{
-	return sha256_ni_finup(desc, NULL, 0, out);
-}
-
-static int sha256_ni_digest(struct shash_desc *desc, const u8 *data,
-		      unsigned int len, u8 *out)
-{
-	return sha256_base_init(desc) ?:
-	       sha256_ni_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_ni_algs[] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	sha256_ni_update,
-	.final		=	sha256_ni_final,
-	.finup		=	sha256_ni_finup,
-	.digest		=	sha256_ni_digest,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name =	"sha256-ni",
-		.cra_priority	=	250,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	sha256_ni_update,
-	.final		=	sha256_ni_final,
-	.finup		=	sha256_ni_finup,
-	.descsize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name =	"sha224-ni",
-		.cra_priority	=	250,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int register_sha256_ni(void)
-{
-	if (boot_cpu_has(X86_FEATURE_SHA_NI))
-		return crypto_register_shashes(sha256_ni_algs,
-				ARRAY_SIZE(sha256_ni_algs));
-	return 0;
-}
-
-static void unregister_sha256_ni(void)
-{
-	if (boot_cpu_has(X86_FEATURE_SHA_NI))
-		crypto_unregister_shashes(sha256_ni_algs,
-				ARRAY_SIZE(sha256_ni_algs));
-}
-
-#else
-static inline int register_sha256_ni(void) { return 0; }
-static inline void unregister_sha256_ni(void) { }
-#endif
-
-static int __init sha256_ssse3_mod_init(void)
-{
-	if (!x86_match_cpu(module_cpu_ids))
-		return -ENODEV;
-
-	if (register_sha256_ssse3())
-		goto fail;
-
-	if (register_sha256_avx()) {
-		unregister_sha256_ssse3();
-		goto fail;
-	}
-
-	if (register_sha256_avx2()) {
-		unregister_sha256_avx();
-		unregister_sha256_ssse3();
-		goto fail;
-	}
-
-	if (register_sha256_ni()) {
-		unregister_sha256_avx2();
-		unregister_sha256_avx();
-		unregister_sha256_ssse3();
-		goto fail;
-	}
-
-	return 0;
-fail:
-	return -ENODEV;
-}
-
-static void __exit sha256_ssse3_mod_fini(void)
-{
-	unregister_sha256_ni();
-	unregister_sha256_avx2();
-	unregister_sha256_avx();
-	unregister_sha256_ssse3();
-}
-
-module_init(sha256_ssse3_mod_init);
-module_exit(sha256_ssse3_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha256-ssse3");
-MODULE_ALIAS_CRYPTO("sha256-avx");
-MODULE_ALIAS_CRYPTO("sha256-avx2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha224-ssse3");
-MODULE_ALIAS_CRYPTO("sha224-avx");
-MODULE_ALIAS_CRYPTO("sha224-avx2");
-#ifdef CONFIG_AS_SHA256_NI
-MODULE_ALIAS_CRYPTO("sha256-ni");
-MODULE_ALIAS_CRYPTO("sha224-ni");
-#endif
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 6d3b85e53d0e..067684c54395 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -27,17 +27,13 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 #include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/types.h>
 #include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
 
 asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
 				       const u8 *data, int blocks);
@@ -45,11 +41,7 @@ asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
 static int sha512_update(struct shash_desc *desc, const u8 *data,
 		       unsigned int len, sha512_block_fn *sha512_xform)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
-		return crypto_sha512_update(desc, data, len);
+	int remain;
 
 	/*
 	 * Make sure struct sha512_state begins directly with the SHA512
@@ -58,22 +50,17 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
 	BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0);
 
 	kernel_fpu_begin();
-	sha512_base_do_update(desc, data, len, sha512_xform);
+	remain = sha512_base_do_update_blocks(desc, data, len, sha512_xform);
 	kernel_fpu_end();
 
-	return 0;
+	return remain;
 }
 
 static int sha512_finup(struct shash_desc *desc, const u8 *data,
 	      unsigned int len, u8 *out, sha512_block_fn *sha512_xform)
 {
-	if (!crypto_simd_usable())
-		return crypto_sha512_finup(desc, data, len, out);
-
 	kernel_fpu_begin();
-	if (len)
-		sha512_base_do_update(desc, data, len, sha512_xform);
-	sha512_base_do_finalize(desc, sha512_xform);
+	sha512_base_do_finup(desc, data, len, sha512_xform);
 	kernel_fpu_end();
 
 	return sha512_base_finish(desc, out);
@@ -91,23 +78,18 @@ static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data,
 	return sha512_finup(desc, data, len, out, sha512_transform_ssse3);
 }
 
-/* Add padding and return the message digest. */
-static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
-{
-	return sha512_ssse3_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha512_ssse3_algs[] = { {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	sha512_ssse3_update,
-	.final		=	sha512_ssse3_final,
 	.finup		=	sha512_ssse3_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-ssse3",
 		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -115,13 +97,14 @@ static struct shash_alg sha512_ssse3_algs[] = { {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	sha512_ssse3_update,
-	.final		=	sha512_ssse3_final,
 	.finup		=	sha512_ssse3_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-ssse3",
 		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -167,23 +150,18 @@ static int sha512_avx_finup(struct shash_desc *desc, const u8 *data,
 	return sha512_finup(desc, data, len, out, sha512_transform_avx);
 }
 
-/* Add padding and return the message digest. */
-static int sha512_avx_final(struct shash_desc *desc, u8 *out)
-{
-	return sha512_avx_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha512_avx_algs[] = { {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	sha512_avx_update,
-	.final		=	sha512_avx_final,
 	.finup		=	sha512_avx_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-avx",
 		.cra_priority	=	160,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -191,13 +169,14 @@ static struct shash_alg sha512_avx_algs[] = { {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	sha512_avx_update,
-	.final		=	sha512_avx_final,
 	.finup		=	sha512_avx_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-avx",
 		.cra_priority	=	160,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -233,23 +212,18 @@ static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data,
 	return sha512_finup(desc, data, len, out, sha512_transform_rorx);
 }
 
-/* Add padding and return the message digest. */
-static int sha512_avx2_final(struct shash_desc *desc, u8 *out)
-{
-	return sha512_avx2_finup(desc, NULL, 0, out);
-}
-
 static struct shash_alg sha512_avx2_algs[] = { {
 	.digestsize	=	SHA512_DIGEST_SIZE,
 	.init		=	sha512_base_init,
 	.update		=	sha512_avx2_update,
-	.final		=	sha512_avx2_final,
 	.finup		=	sha512_avx2_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-avx2",
 		.cra_priority	=	170,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -257,13 +231,14 @@ static struct shash_alg sha512_avx2_algs[] = { {
 	.digestsize	=	SHA384_DIGEST_SIZE,
 	.init		=	sha384_base_init,
 	.update		=	sha512_avx2_update,
-	.final		=	sha512_avx2_final,
 	.finup		=	sha512_avx2_finup,
-	.descsize	=	sizeof(struct sha512_state),
+	.descsize	=	SHA512_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-avx2",
 		.cra_priority	=	170,
+		.cra_flags	=	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/x86/crypto/sm3_avx_glue.c b/arch/x86/crypto/sm3_avx_glue.c
index 661b6f22ffcd..6e8c42b9dc8e 100644
--- a/arch/x86/crypto/sm3_avx_glue.c
+++ b/arch/x86/crypto/sm3_avx_glue.c
@@ -10,12 +10,11 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/types.h>
 #include <crypto/sm3.h>
 #include <crypto/sm3_base.h>
-#include <asm/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
 asmlinkage void sm3_transform_avx(struct sm3_state *state,
 			const u8 *data, int nblocks);
@@ -23,13 +22,7 @@ asmlinkage void sm3_transform_avx(struct sm3_state *state,
 static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
 			 unsigned int len)
 {
-	struct sm3_state *sctx = shash_desc_ctx(desc);
-
-	if (!crypto_simd_usable() ||
-			(sctx->count % SM3_BLOCK_SIZE) + len < SM3_BLOCK_SIZE) {
-		sm3_update(sctx, data, len);
-		return 0;
-	}
+	int remain;
 
 	/*
 	 * Make sure struct sm3_state begins directly with the SM3
@@ -38,45 +31,17 @@ static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
 	BUILD_BUG_ON(offsetof(struct sm3_state, state) != 0);
 
 	kernel_fpu_begin();
-	sm3_base_do_update(desc, data, len, sm3_transform_avx);
+	remain = sm3_base_do_update_blocks(desc, data, len, sm3_transform_avx);
 	kernel_fpu_end();
-
-	return 0;
+	return remain;
 }
 
 static int sm3_avx_finup(struct shash_desc *desc, const u8 *data,
 		      unsigned int len, u8 *out)
 {
-	if (!crypto_simd_usable()) {
-		struct sm3_state *sctx = shash_desc_ctx(desc);
-
-		if (len)
-			sm3_update(sctx, data, len);
-
-		sm3_final(sctx, out);
-		return 0;
-	}
-
 	kernel_fpu_begin();
-	if (len)
-		sm3_base_do_update(desc, data, len, sm3_transform_avx);
-	sm3_base_do_finalize(desc, sm3_transform_avx);
+	sm3_base_do_finup(desc, data, len, sm3_transform_avx);
 	kernel_fpu_end();
-
-	return sm3_base_finish(desc, out);
-}
-
-static int sm3_avx_final(struct shash_desc *desc, u8 *out)
-{
-	if (!crypto_simd_usable()) {
-		sm3_final(shash_desc_ctx(desc), out);
-		return 0;
-	}
-
-	kernel_fpu_begin();
-	sm3_base_do_finalize(desc, sm3_transform_avx);
-	kernel_fpu_end();
-
 	return sm3_base_finish(desc, out);
 }
 
@@ -84,13 +49,14 @@ static struct shash_alg sm3_avx_alg = {
 	.digestsize	=	SM3_DIGEST_SIZE,
 	.init		=	sm3_base_init,
 	.update		=	sm3_avx_update,
-	.final		=	sm3_avx_final,
 	.finup		=	sm3_avx_finup,
-	.descsize	=	sizeof(struct sm3_state),
+	.descsize	=	SM3_STATE_SIZE,
 	.base		=	{
 		.cra_name	=	"sm3",
 		.cra_driver_name =	"sm3-avx",
 		.cra_priority	=	300,
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY |
+					CRYPTO_AHASH_ALG_FINUP_MAX,
 		.cra_blocksize	=	SM3_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c
index 1148fd4cd57f..fec0ab7a63dd 100644
--- a/arch/x86/crypto/sm4_aesni_avx2_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c
@@ -8,11 +8,10 @@
  * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
  */
 
+#include <asm/fpu/api.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/sm4.h>
 #include "sm4-avx.h"
@@ -48,10 +47,9 @@ static int ctr_crypt(struct skcipher_request *req)
 static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
 	{
 		.base = {
-			.cra_name		= "__ecb(sm4)",
-			.cra_driver_name	= "__ecb-sm4-aesni-avx2",
+			.cra_name		= "ecb(sm4)",
+			.cra_driver_name	= "ecb-sm4-aesni-avx2",
 			.cra_priority		= 500,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -64,10 +62,9 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
 		.decrypt	= sm4_avx_ecb_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cbc(sm4)",
-			.cra_driver_name	= "__cbc-sm4-aesni-avx2",
+			.cra_name		= "cbc(sm4)",
+			.cra_driver_name	= "cbc-sm4-aesni-avx2",
 			.cra_priority		= 500,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -81,10 +78,9 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
 		.decrypt	= cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__ctr(sm4)",
-			.cra_driver_name	= "__ctr-sm4-aesni-avx2",
+			.cra_name		= "ctr(sm4)",
+			.cra_driver_name	= "ctr-sm4-aesni-avx2",
 			.cra_priority		= 500,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= 1,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -100,9 +96,6 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
 	}
 };
 
-static struct simd_skcipher_alg *
-simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)];
-
 static int __init sm4_init(void)
 {
 	const char *feature_name;
@@ -121,16 +114,14 @@ static int __init sm4_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers,
-					ARRAY_SIZE(sm4_aesni_avx2_skciphers),
-					simd_sm4_aesni_avx2_skciphers);
+	return crypto_register_skciphers(sm4_aesni_avx2_skciphers,
+					 ARRAY_SIZE(sm4_aesni_avx2_skciphers));
 }
 
 static void __exit sm4_exit(void)
 {
-	simd_unregister_skciphers(sm4_aesni_avx2_skciphers,
-				ARRAY_SIZE(sm4_aesni_avx2_skciphers),
-				simd_sm4_aesni_avx2_skciphers);
+	crypto_unregister_skciphers(sm4_aesni_avx2_skciphers,
+				    ARRAY_SIZE(sm4_aesni_avx2_skciphers));
 }
 
 module_init(sm4_init);
diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c
index 85b4ca78b47b..72867fc49ce8 100644
--- a/arch/x86/crypto/sm4_aesni_avx_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx_glue.c
@@ -8,11 +8,10 @@
  * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
  */
 
+#include <asm/fpu/api.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/sm4.h>
 #include "sm4-avx.h"
@@ -263,10 +262,9 @@ static int ctr_crypt(struct skcipher_request *req)
 static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
 	{
 		.base = {
-			.cra_name		= "__ecb(sm4)",
-			.cra_driver_name	= "__ecb-sm4-aesni-avx",
+			.cra_name		= "ecb(sm4)",
+			.cra_driver_name	= "ecb-sm4-aesni-avx",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -279,10 +277,9 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
 		.decrypt	= sm4_avx_ecb_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__cbc(sm4)",
-			.cra_driver_name	= "__cbc-sm4-aesni-avx",
+			.cra_name		= "cbc(sm4)",
+			.cra_driver_name	= "cbc-sm4-aesni-avx",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= SM4_BLOCK_SIZE,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -296,10 +293,9 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
 		.decrypt	= cbc_decrypt,
 	}, {
 		.base = {
-			.cra_name		= "__ctr(sm4)",
-			.cra_driver_name	= "__ctr-sm4-aesni-avx",
+			.cra_name		= "ctr(sm4)",
+			.cra_driver_name	= "ctr-sm4-aesni-avx",
 			.cra_priority		= 400,
-			.cra_flags		= CRYPTO_ALG_INTERNAL,
 			.cra_blocksize		= 1,
 			.cra_ctxsize		= sizeof(struct sm4_ctx),
 			.cra_module		= THIS_MODULE,
@@ -315,9 +311,6 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
 	}
 };
 
-static struct simd_skcipher_alg *
-simd_sm4_aesni_avx_skciphers[ARRAY_SIZE(sm4_aesni_avx_skciphers)];
-
 static int __init sm4_init(void)
 {
 	const char *feature_name;
@@ -335,16 +328,14 @@ static int __init sm4_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(sm4_aesni_avx_skciphers,
-					ARRAY_SIZE(sm4_aesni_avx_skciphers),
-					simd_sm4_aesni_avx_skciphers);
+	return crypto_register_skciphers(sm4_aesni_avx_skciphers,
+					 ARRAY_SIZE(sm4_aesni_avx_skciphers));
 }
 
 static void __exit sm4_exit(void)
 {
-	simd_unregister_skciphers(sm4_aesni_avx_skciphers,
-					ARRAY_SIZE(sm4_aesni_avx_skciphers),
-					simd_sm4_aesni_avx_skciphers);
+	crypto_unregister_skciphers(sm4_aesni_avx_skciphers,
+				    ARRAY_SIZE(sm4_aesni_avx_skciphers));
 }
 
 module_init(sm4_init);
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index d2288bf38a8a..071e90e7f0d8 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "twofish-x86_64-asm-3way.S"
 .text
@@ -220,7 +221,7 @@
 	rorq $32,			RAB2; \
 	outunpack3(mov, RIO, 2, RAB, 2);
 
-SYM_FUNC_START(__twofish_enc_blk_3way)
+SYM_TYPED_FUNC_START(__twofish_enc_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -269,7 +270,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	RET;
 SYM_FUNC_END(__twofish_enc_blk_3way)
 
-SYM_FUNC_START(twofish_dec_blk_3way)
+SYM_TYPED_FUNC_START(twofish_dec_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 775af290cd19..e08b4ba07b93 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -8,6 +8,7 @@
 .text
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm-offsets.h>
 
 #define a_offset	0
@@ -202,7 +203,7 @@
 	xor	%r8d,		d ## D;\
 	ror	$1,		d ## D;
 
-SYM_FUNC_START(twofish_enc_blk)
+SYM_TYPED_FUNC_START(twofish_enc_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -255,7 +256,7 @@ SYM_FUNC_START(twofish_enc_blk)
 	RET
 SYM_FUNC_END(twofish_enc_blk)
 
-SYM_FUNC_START(twofish_dec_blk)
+SYM_TYPED_FUNC_START(twofish_dec_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 3eb3440b477a..9e20db013750 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -13,7 +13,6 @@
 #include <linux/crypto.h>
 #include <linux/err.h>
 #include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
 #include <crypto/twofish.h>
 
 #include "twofish.h"
@@ -74,10 +73,9 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 static struct skcipher_alg twofish_algs[] = {
 	{
-		.base.cra_name		= "__ecb(twofish)",
-		.base.cra_driver_name	= "__ecb-twofish-avx",
+		.base.cra_name		= "ecb(twofish)",
+		.base.cra_driver_name	= "ecb-twofish-avx",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= TF_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -87,10 +85,9 @@ static struct skcipher_alg twofish_algs[] = {
 		.encrypt		= ecb_encrypt,
 		.decrypt		= ecb_decrypt,
 	}, {
-		.base.cra_name		= "__cbc(twofish)",
-		.base.cra_driver_name	= "__cbc-twofish-avx",
+		.base.cra_name		= "cbc(twofish)",
+		.base.cra_driver_name	= "cbc-twofish-avx",
 		.base.cra_priority	= 400,
-		.base.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.base.cra_blocksize	= TF_BLOCK_SIZE,
 		.base.cra_ctxsize	= sizeof(struct twofish_ctx),
 		.base.cra_module	= THIS_MODULE,
@@ -103,8 +100,6 @@ static struct skcipher_alg twofish_algs[] = {
 	},
 };
 
-static struct simd_skcipher_alg *twofish_simd_algs[ARRAY_SIZE(twofish_algs)];
-
 static int __init twofish_init(void)
 {
 	const char *feature_name;
@@ -114,15 +109,13 @@ static int __init twofish_init(void)
 		return -ENODEV;
 	}
 
-	return simd_register_skciphers_compat(twofish_algs,
-					      ARRAY_SIZE(twofish_algs),
-					      twofish_simd_algs);
+	return crypto_register_skciphers(twofish_algs,
+					 ARRAY_SIZE(twofish_algs));
 }
 
 static void __exit twofish_exit(void)
 {
-	simd_unregister_skciphers(twofish_algs, ARRAY_SIZE(twofish_algs),
-				  twofish_simd_algs);
+	crypto_unregister_skciphers(twofish_algs, ARRAY_SIZE(twofish_algs));
 }
 
 module_init(twofish_init);
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index ce1cc1622385..72cae8e0ce85 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,12 +7,13 @@ KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
 
-CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
 
 obj-y				:= entry.o entry_$(BITS).o syscall_$(BITS).o
-obj-y				+= common.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/
@@ -23,4 +24,3 @@ CFLAGS_REMOVE_entry_fred.o	+= -pg $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_X86_FRED)		+= entry_64_fred.o entry_fred.o
 
 obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
-obj-$(CONFIG_X86_X32_ABI)	+= syscall_x32.o
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index ea81770629ee..d83236b96f22 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -70,6 +70,8 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
 	movq	%rdi, 8(%rsp)	/* pt_regs->di (overwriting original return address) */
+	/* We just clobbered the return address - use the IRET frame for unwinding: */
+	UNWIND_HINT_IRET_REGS offset=3*8
 	.else
 	pushq   %rdi		/* pt_regs->di */
 	pushq   %rsi		/* pt_regs->si */
@@ -431,6 +433,7 @@ For 32-bit we have the following conventions - kernel is built with
 /* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 .macro THUNK name, func
 SYM_FUNC_START(\name)
+	ANNOTATE_NOENDBR
 	pushq %rbp
 	movq %rsp, %rbp
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
deleted file mode 100644
index 94941c5a10ac..000000000000
--- a/arch/x86/entry/common.c
+++ /dev/null
@@ -1,523 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * common.c - C code for kernel entry and exit
- * Copyright (c) 2015 Andrew Lutomirski
- *
- * Based on asm and ptrace code by many authors.  The code here originated
- * in ptrace.c and signal.c.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/entry-common.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/export.h>
-#include <linux/nospec.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/init.h>
-
-#ifdef CONFIG_XEN_PV
-#include <xen/xen-ops.h>
-#include <xen/events.h>
-#endif
-
-#include <asm/apic.h>
-#include <asm/desc.h>
-#include <asm/traps.h>
-#include <asm/vdso.h>
-#include <asm/cpufeature.h>
-#include <asm/fpu/api.h>
-#include <asm/nospec-branch.h>
-#include <asm/io_bitmap.h>
-#include <asm/syscall.h>
-#include <asm/irq_stack.h>
-
-#ifdef CONFIG_X86_64
-
-static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Convert negative numbers to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int unr = nr;
-
-	if (likely(unr < NR_syscalls)) {
-		unr = array_index_nospec(unr, NR_syscalls);
-		regs->ax = x64_sys_call(regs, unr);
-		return true;
-	}
-	return false;
-}
-
-static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Adjust the starting offset of the table, and convert numbers
-	 * < __X32_SYSCALL_BIT to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int xnr = nr - __X32_SYSCALL_BIT;
-
-	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
-		xnr = array_index_nospec(xnr, X32_NR_syscalls);
-		regs->ax = x32_sys_call(regs, xnr);
-		return true;
-	}
-	return false;
-}
-
-/* Returns true to return using SYSRET, or false to use IRET */
-__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
-{
-	add_random_kstack_offset();
-	nr = syscall_enter_from_user_mode(regs, nr);
-
-	instrumentation_begin();
-
-	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
-		/* Invalid system call, but still a system call. */
-		regs->ax = __x64_sys_ni_syscall(regs);
-	}
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-
-	/*
-	 * Check that the register state is valid for using SYSRET to exit
-	 * to userspace.  Otherwise use the slower but fully capable IRET
-	 * exit path.
-	 */
-
-	/* XEN PV guests always use the IRET path */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
-	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
-		return false;
-
-	/* CS and SS must match the values set in MSR_STAR */
-	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
-		return false;
-
-	/*
-	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
-	 * in kernel space.  This essentially lets the user take over
-	 * the kernel, since userspace controls RSP.
-	 *
-	 * TASK_SIZE_MAX covers all user-accessible addresses other than
-	 * the deprecated vsyscall page.
-	 */
-	if (unlikely(regs->ip >= TASK_SIZE_MAX))
-		return false;
-
-	/*
-	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
-	 * restoring TF results in a trap from userspace immediately after
-	 * SYSRET.
-	 */
-	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
-		return false;
-
-	/* Use SYSRET to exit to userspace */
-	return true;
-}
-#endif
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
-static __always_inline int syscall_32_enter(struct pt_regs *regs)
-{
-	if (IS_ENABLED(CONFIG_IA32_EMULATION))
-		current_thread_info()->status |= TS_COMPAT;
-
-	return (int)regs->orig_ax;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
-
-static int ia32_emulation_override_cmdline(char *arg)
-{
-	return kstrtobool(arg, &__ia32_enabled);
-}
-early_param("ia32_emulation", ia32_emulation_override_cmdline);
-#endif
-
-/*
- * Invoke a 32-bit syscall.  Called with IRQs on in CT_STATE_KERNEL.
- */
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Convert negative numbers to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int unr = nr;
-
-	if (likely(unr < IA32_NR_syscalls)) {
-		unr = array_index_nospec(unr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call(regs, unr);
-	} else if (nr != -1) {
-		regs->ax = __ia32_sys_ni_syscall(regs);
-	}
-}
-
-#ifdef CONFIG_IA32_EMULATION
-static __always_inline bool int80_is_external(void)
-{
-	const unsigned int offs = (0x80 / 32) * 0x10;
-	const u32 bit = BIT(0x80 % 32);
-
-	/* The local APIC on XENPV guests is fake */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/*
-	 * If vector 0x80 is set in the APIC ISR then this is an external
-	 * interrupt. Either from broken hardware or injected by a VMM.
-	 *
-	 * Note: In guest mode this is only valid for secure guests where
-	 * the secure module fully controls the vAPIC exposed to the guest.
-	 */
-	return apic_read(APIC_ISR + offs) & bit;
-}
-
-/**
- * do_int80_emulation - 32-bit legacy syscall C entry from asm
- *
- * This entry point can be used by 32-bit and 64-bit programs to perform
- * 32-bit system calls.  Instances of INT $0x80 can be found inline in
- * various programs and libraries.  It is also used by the vDSO's
- * __kernel_vsyscall fallback for hardware that doesn't support a faster
- * entry method.  Restarted 32-bit system calls also fall back to INT
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * The arguments for the INT $0x80 based syscall are on stack in the
- * pt_regs structure:
- *   eax:				system call number
- *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
- */
-__visible noinstr void do_int80_emulation(struct pt_regs *regs)
-{
-	int nr;
-
-	/* Kernel does not use INT $0x80! */
-	if (unlikely(!user_mode(regs))) {
-		irqentry_enter(regs);
-		instrumentation_begin();
-		panic("Unexpected external interrupt 0x80\n");
-	}
-
-	/*
-	 * Establish kernel context for instrumentation, including for
-	 * int80_is_external() below which calls into the APIC driver.
-	 * Identical for soft and external interrupts.
-	 */
-	enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	add_random_kstack_offset();
-
-	/* Validate that this is a soft interrupt to the extent possible */
-	if (unlikely(int80_is_external()))
-		panic("Unexpected external interrupt 0x80\n");
-
-	/*
-	 * The low level idtentry code pushed -1 into regs::orig_ax
-	 * and regs::ax contains the syscall number.
-	 *
-	 * User tracing code (ptrace or signal handlers) might assume
-	 * that the regs::orig_ax contains a 32-bit number on invoking
-	 * a 32-bit syscall.
-	 *
-	 * Establish the syscall convention by saving the 32bit truncated
-	 * syscall number in regs::orig_ax and by invalidating regs::ax.
-	 */
-	regs->orig_ax = regs->ax & GENMASK(31, 0);
-	regs->ax = -ENOSYS;
-
-	nr = syscall_32_enter(regs);
-
-	local_irq_enable();
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-
-#ifdef CONFIG_X86_FRED
-/*
- * A FRED-specific INT80 handler is warranted for the follwing reasons:
- *
- * 1) As INT instructions and hardware interrupts are separate event
- *    types, FRED does not preclude the use of vector 0x80 for external
- *    interrupts. As a result, the FRED setup code does not reserve
- *    vector 0x80 and calling int80_is_external() is not merely
- *    suboptimal but actively incorrect: it could cause a system call
- *    to be incorrectly ignored.
- *
- * 2) It is called only for handling vector 0x80 of event type
- *    EVENT_TYPE_SWINT and will never be called to handle any external
- *    interrupt (event type EVENT_TYPE_EXTINT).
- *
- * 3) FRED has separate entry flows depending on if the event came from
- *    user space or kernel space, and because the kernel does not use
- *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
- *    falls through to fred_bad_type() if the event type is
- *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
- *    an INT insn, it can only be from a user level.
- *
- * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
- *    likely take a different approach if it is ever needed: it
- *    probably belongs in either fred_intx()/ fred_other() or
- *    asm_fred_entrypoint_user(), depending on if this ought to be done
- *    for all entries from userspace or only system
- *    calls.
- *
- * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
- */
-DEFINE_FREDENTRY_RAW(int80_emulation)
-{
-	int nr;
-
-	enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	add_random_kstack_offset();
-
-	/*
-	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
-	 * syscall number.
-	 *
-	 * User tracing code (ptrace or signal handlers) might assume
-	 * that the regs::orig_ax contains a 32-bit number on invoking
-	 * a 32-bit syscall.
-	 *
-	 * Establish the syscall convention by saving the 32bit truncated
-	 * syscall number in regs::orig_ax and by invalidating regs::ax.
-	 */
-	regs->orig_ax = regs->ax & GENMASK(31, 0);
-	regs->ax = -ENOSYS;
-
-	nr = syscall_32_enter(regs);
-
-	local_irq_enable();
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-#endif
-#else /* CONFIG_IA32_EMULATION */
-
-/* Handles int $0x80 on a 32bit kernel */
-__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
-{
-	int nr = syscall_32_enter(regs);
-
-	add_random_kstack_offset();
-	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
-	 * orig_ax, the int return value truncates it. This matches
-	 * the semantics of syscall_get_nr().
-	 */
-	nr = syscall_enter_from_user_mode(regs, nr);
-	instrumentation_begin();
-
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-#endif /* !CONFIG_IA32_EMULATION */
-
-static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
-{
-	int nr = syscall_32_enter(regs);
-	int res;
-
-	add_random_kstack_offset();
-	/*
-	 * This cannot use syscall_enter_from_user_mode() as it has to
-	 * fetch EBP before invoking any of the syscall entry work
-	 * functions.
-	 */
-	syscall_enter_from_user_mode_prepare(regs);
-
-	instrumentation_begin();
-	/* Fetch EBP from where the vDSO stashed it. */
-	if (IS_ENABLED(CONFIG_X86_64)) {
-		/*
-		 * Micro-optimization: the pointer we're following is
-		 * explicitly 32 bits, so it can't be out of range.
-		 */
-		res = __get_user(*(u32 *)&regs->bp,
-			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
-	} else {
-		res = get_user(*(u32 *)&regs->bp,
-		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
-	}
-
-	if (res) {
-		/* User code screwed up. */
-		regs->ax = -EFAULT;
-
-		local_irq_disable();
-		instrumentation_end();
-		irqentry_exit_to_user_mode(regs);
-		return false;
-	}
-
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-
-	/* Now this is just like a normal syscall. */
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-	return true;
-}
-
-/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
-__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
-{
-	/*
-	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
-	 * convention.  Adjust regs so it looks like we entered using int80.
-	 */
-	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
-					vdso_image_32.sym_int80_landing_pad;
-
-	/*
-	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
-	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
-	 * Fix it up.
-	 */
-	regs->ip = landing_pad;
-
-	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
-	if (!__do_fast_syscall_32(regs))
-		return false;
-
-	/*
-	 * Check that the register state is valid for using SYSRETL/SYSEXIT
-	 * to exit to userspace.  Otherwise use the slower but fully capable
-	 * IRET exit path.
-	 */
-
-	/* XEN PV guests always use the IRET path */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/* EIP must point to the VDSO landing pad */
-	if (unlikely(regs->ip != landing_pad))
-		return false;
-
-	/* CS and SS must match the values set in MSR_STAR */
-	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
-		return false;
-
-	/* If the TF, RF, or VM flags are set, use IRET */
-	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
-		return false;
-
-	/* Use SYSRETL/SYSEXIT to exit to userspace */
-	return true;
-}
-
-/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
-__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
-{
-	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
-	regs->sp = regs->bp;
-
-	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
-	regs->flags |= X86_EFLAGS_IF;
-
-	return do_fast_syscall_32(regs);
-}
-#endif
-
-SYSCALL_DEFINE0(ni_syscall)
-{
-	return -ENOSYS;
-}
-
-#ifdef CONFIG_XEN_PV
-#ifndef CONFIG_PREEMPTION
-/*
- * Some hypercalls issued by the toolstack can take many 10s of
- * seconds. Allow tasks running hypercalls via the privcmd driver to
- * be voluntarily preempted even if full kernel preemption is
- * disabled.
- *
- * Such preemptible hypercalls are bracketed by
- * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
- * calls.
- */
-DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
-EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
-
-/*
- * In case of scheduling the flag must be cleared and restored after
- * returning from schedule as the task might move to a different CPU.
- */
-static __always_inline bool get_and_clear_inhcall(void)
-{
-	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
-
-	__this_cpu_write(xen_in_preemptible_hcall, false);
-	return inhcall;
-}
-
-static __always_inline void restore_inhcall(bool inhcall)
-{
-	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
-}
-#else
-static __always_inline bool get_and_clear_inhcall(void) { return false; }
-static __always_inline void restore_inhcall(bool inhcall) { }
-#endif
-
-static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	inc_irq_stat(irq_hv_callback_count);
-
-	xen_evtchn_do_upcall();
-
-	set_irq_regs(old_regs);
-}
-
-__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
-{
-	irqentry_state_t state = irqentry_enter(regs);
-	bool inhcall;
-
-	instrumentation_begin();
-	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
-
-	inhcall = get_and_clear_inhcall();
-	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
-		irqentry_exit_cond_resched();
-		instrumentation_end();
-		restore_inhcall(inhcall);
-	} else {
-		instrumentation_end();
-		irqentry_exit(regs, state);
-	}
-}
-#endif /* CONFIG_XEN_PV */
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9ecc..175958b02f2b 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/segment.h>
@@ -16,18 +17,20 @@
 
 .pushsection .noinstr.text, "ax"
 
-SYM_FUNC_START(entry_ibpb)
+/* Clobbers AX, CX, DX */
+SYM_FUNC_START(write_ibpb)
+	ANNOTATE_NOENDBR
 	movl	$MSR_IA32_PRED_CMD, %ecx
-	movl	$PRED_CMD_IBPB, %eax
+	movl	_ASM_RIP(x86_pred_cmd), %eax
 	xorl	%edx, %edx
 	wrmsr
 
 	/* Make sure IBPB clears return stack preductions too. */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET
 	RET
-SYM_FUNC_END(entry_ibpb)
+SYM_FUNC_END(write_ibpb)
 /* For KVM */
-EXPORT_SYMBOL_GPL(entry_ibpb);
+EXPORT_SYMBOL_GPL(write_ibpb);
 
 .popsection
 
@@ -52,7 +55,6 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
 
 THUNK warn_thunk_thunk, __warn_thunk
 
-#ifndef CONFIG_X86_64
 /*
  * Clang's implementation of TLS stack cookies requires the variable in
  * question to be a TLS variable. If the variable happens to be defined as an
@@ -63,7 +65,6 @@ THUNK warn_thunk_thunk, __warn_thunk
  * entirely in the C code, and use an alias emitted by the linker script
  * instead.
  */
-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) && defined(CONFIG_SMP)
 EXPORT_SYMBOL(__ref_stack_chk_guard);
 #endif
-#endif
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 20be5758c2d2..92c0b4a94e0a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1153,7 +1153,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 * is using the thread stack right now, so it's safe for us to use it.
 	 */
 	movl	%esp, %ebx
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esp
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	exc_nmi
 	movl	%ebx, %esp
 
@@ -1217,7 +1217,7 @@ SYM_CODE_START(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esi
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
 	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
 
 	call	make_task_dead
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93c..ed04a968cc7d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ SYM_CODE_START(entry_SYSCALL_64)
 	/* tss.sp2 is scratch space. */
 	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -175,6 +175,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  */
 .pushsection .text, "ax"
 SYM_FUNC_START(__switch_to_asm)
+	ANNOTATE_NOENDBR
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -192,7 +193,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
+	movq	%rbx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 	/*
@@ -742,6 +743,7 @@ _ASM_NOKPROBE(common_interrupt_return)
  * Is in entry.text as it shouldn't be instrumented.
  */
 SYM_FUNC_START(asm_load_gs_index)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	swapgs
 .Lgs_change:
@@ -1166,7 +1168,7 @@ SYM_CODE_START(asm_exc_nmi)
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
 	pushq	5*8(%rdx)	/* pt_regs->ss */
 	pushq	4*8(%rdx)	/* pt_regs->rsp */
@@ -1484,7 +1486,7 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rax
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
 	UNWIND_HINT_REGS
 
@@ -1523,9 +1525,12 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * ORC to unwind properly.
  *
  * The alignment is for performance and not for safety, and may be safely
- * refactored in the future if needed.
+ * refactored in the future if needed. The .skips are for safety, to ensure
+ * that all RETs are in the second half of a cacheline to mitigate Indirect
+ * Target Selection, rather than taking the slowpath via its_return_thunk.
  */
 SYM_FUNC_START(clear_bhb_loop)
+	ANNOTATE_NOENDBR
 	push	%rbp
 	mov	%rsp, %rbp
 	movl	$5, %ecx
@@ -1533,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop)
 	call	1f
 	jmp	5f
 	.align 64, 0xcc
+	/*
+	 * Shift instructions so that the RET is in the upper half of the
+	 * cacheline and don't take the slowpath to its_return_thunk.
+	 */
+	.skip 32 - (.Lret1 - 1f), 0xcc
 	ANNOTATE_INTRA_FUNCTION_CALL
 1:	call	2f
-	RET
+.Lret1:	RET
 	.align 64, 0xcc
+	/*
+	 * As above shift instructions for RET at .Lret2 as well.
+	 *
+	 * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc
+	 * but some Clang versions (e.g. 18) don't like this.
+	 */
+	.skip 32 - 18, 0xcc
 2:	movl	$5, %eax
 3:	jmp	4f
 	nop
@@ -1544,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop)
 	jnz	3b
 	sub	$1, %ecx
 	jnz	1b
-	RET
+.Lret2:	RET
 5:	lfence
 	pop	%rbp
 	RET
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index ed0a5f2dc129..a45e1125fc6c 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -57,7 +57,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	popq	%rax
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS		/* pt_regs->ss */
@@ -193,7 +193,7 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
 
 	/* Switch to the kernel stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index a02bc6f3d2e6..29c5c32c16c3 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -58,6 +58,7 @@ SYM_CODE_END(asm_fred_entrypoint_kernel)
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 SYM_FUNC_START(asm_fred_entry_from_kvm)
+	ANNOTATE_NOENDBR
 	push %rbp
 	mov %rsp, %rbp
 
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cc9950d7104..2b15ea17bb7c 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -1,10 +1,16 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for i386. */
+// SPDX-License-Identifier: GPL-2.0-only
+/* 32-bit system call dispatch */
 
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
+#include <linux/entry-common.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+#include <asm/apic.h>
+#include <asm/traps.h>
+#include <asm/cpufeature.h>
 #include <asm/syscall.h>
 
 #ifdef CONFIG_IA32_EMULATION
@@ -41,4 +47,324 @@ long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
 	#include <asm/syscalls_32.h>
 	default: return __ia32_sys_ni_syscall(regs);
 	}
-};
+}
+
+static __always_inline int syscall_32_enter(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_IA32_EMULATION))
+		current_thread_info()->status |= TS_COMPAT;
+
+	return (int)regs->orig_ax;
+}
+
+#ifdef CONFIG_IA32_EMULATION
+bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
+
+static int __init ia32_emulation_override_cmdline(char *arg)
+{
+	return kstrtobool(arg, &__ia32_enabled);
+}
+early_param("ia32_emulation", ia32_emulation_override_cmdline);
+#endif
+
+/*
+ * Invoke a 32-bit syscall.  Called with IRQs on in CT_STATE_KERNEL.
+ */
+static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < IA32_NR_syscalls)) {
+		unr = array_index_nospec(unr, IA32_NR_syscalls);
+		regs->ax = ia32_sys_call(regs, unr);
+	} else if (nr != -1) {
+		regs->ax = __ia32_sys_ni_syscall(regs);
+	}
+}
+
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+
+#ifdef CONFIG_X86_FRED
+/*
+ * A FRED-specific INT80 handler is warranted for the follwing reasons:
+ *
+ * 1) As INT instructions and hardware interrupts are separate event
+ *    types, FRED does not preclude the use of vector 0x80 for external
+ *    interrupts. As a result, the FRED setup code does not reserve
+ *    vector 0x80 and calling int80_is_external() is not merely
+ *    suboptimal but actively incorrect: it could cause a system call
+ *    to be incorrectly ignored.
+ *
+ * 2) It is called only for handling vector 0x80 of event type
+ *    EVENT_TYPE_SWINT and will never be called to handle any external
+ *    interrupt (event type EVENT_TYPE_EXTINT).
+ *
+ * 3) FRED has separate entry flows depending on if the event came from
+ *    user space or kernel space, and because the kernel does not use
+ *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
+ *    falls through to fred_bad_type() if the event type is
+ *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
+ *    an INT insn, it can only be from a user level.
+ *
+ * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
+ *    likely take a different approach if it is ever needed: it
+ *    probably belongs in either fred_intx()/ fred_other() or
+ *    asm_fred_entrypoint_user(), depending on if this ought to be done
+ *    for all entries from userspace or only system
+ *    calls.
+ *
+ * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
+ */
+DEFINE_FREDENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/*
+	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
+	 * syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif /* CONFIG_X86_FRED */
+
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
+__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
+{
+	int nr = syscall_32_enter(regs);
+
+	add_random_kstack_offset();
+	/*
+	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
+	 * orig_ax, the int return value truncates it. This matches
+	 * the semantics of syscall_get_nr().
+	 */
+	nr = syscall_enter_from_user_mode(regs, nr);
+	instrumentation_begin();
+
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif /* !CONFIG_IA32_EMULATION */
+
+static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
+{
+	int nr = syscall_32_enter(regs);
+	int res;
+
+	add_random_kstack_offset();
+	/*
+	 * This cannot use syscall_enter_from_user_mode() as it has to
+	 * fetch EBP before invoking any of the syscall entry work
+	 * functions.
+	 */
+	syscall_enter_from_user_mode_prepare(regs);
+
+	instrumentation_begin();
+	/* Fetch EBP from where the vDSO stashed it. */
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		/*
+		 * Micro-optimization: the pointer we're following is
+		 * explicitly 32 bits, so it can't be out of range.
+		 */
+		res = __get_user(*(u32 *)&regs->bp,
+			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	} else {
+		res = get_user(*(u32 *)&regs->bp,
+		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	}
+
+	if (res) {
+		/* User code screwed up. */
+		regs->ax = -EFAULT;
+
+		local_irq_disable();
+		instrumentation_end();
+		irqentry_exit_to_user_mode(regs);
+		return false;
+	}
+
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+
+	/* Now this is just like a normal syscall. */
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+	return true;
+}
+
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
+{
+	/*
+	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
+	 * convention.  Adjust regs so it looks like we entered using int80.
+	 */
+	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
+					vdso_image_32.sym_int80_landing_pad;
+
+	/*
+	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
+	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
+	 * Fix it up.
+	 */
+	regs->ip = landing_pad;
+
+	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
+	if (!__do_fast_syscall_32(regs))
+		return false;
+
+	/*
+	 * Check that the register state is valid for using SYSRETL/SYSEXIT
+	 * to exit to userspace.  Otherwise use the slower but fully capable
+	 * IRET exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* EIP must point to the VDSO landing pad */
+	if (unlikely(regs->ip != landing_pad))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
+		return false;
+
+	/* If the TF, RF, or VM flags are set, use IRET */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
+		return false;
+
+	/* Use SYSRETL/SYSEXIT to exit to userspace */
+	return true;
+}
+
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
+{
+	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
+	regs->sp = regs->bp;
+
+	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
+	regs->flags |= X86_EFLAGS_IF;
+
+	return do_fast_syscall_32(regs);
+}
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index ba8354424860..b6e68ea98b83 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -1,15 +1,20 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for x86-64. */
+// SPDX-License-Identifier: GPL-2.0-only
+/* 64-bit system call dispatch */
 
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
+#include <linux/entry-common.h>
+#include <linux/nospec.h>
 #include <asm/syscall.h>
 
 #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
 #define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
 #include <asm/syscalls_64.h>
+#ifdef CONFIG_X86_X32_ABI
+#include <asm/syscalls_x32.h>
+#endif
 #undef  __SYSCALL
 
 #undef  __SYSCALL_NORETURN
@@ -33,4 +38,104 @@ long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
 	#include <asm/syscalls_64.h>
 	default: return __x64_sys_ni_syscall(regs);
 	}
-};
+}
+
+#ifdef CONFIG_X86_X32_ABI
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_x32.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
+}
+#endif
+
+static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < NR_syscalls)) {
+		unr = array_index_nospec(unr, NR_syscalls);
+		regs->ax = x64_sys_call(regs, unr);
+		return true;
+	}
+	return false;
+}
+
+static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Adjust the starting offset of the table, and convert numbers
+	 * < __X32_SYSCALL_BIT to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int xnr = nr - __X32_SYSCALL_BIT;
+
+	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
+		xnr = array_index_nospec(xnr, X32_NR_syscalls);
+		regs->ax = x32_sys_call(regs, xnr);
+		return true;
+	}
+	return false;
+}
+
+/* Returns true to return using SYSRET, or false to use IRET */
+__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
+{
+	add_random_kstack_offset();
+	nr = syscall_enter_from_user_mode(regs, nr);
+
+	instrumentation_begin();
+
+	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
+		/* Invalid system call, but still a system call. */
+		regs->ax = __x64_sys_ni_syscall(regs);
+	}
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+
+	/*
+	 * Check that the register state is valid for using SYSRET to exit
+	 * to userspace.  Otherwise use the slower but fully capable IRET
+	 * exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
+	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
+		return false;
+
+	/*
+	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+	 * in kernel space.  This essentially lets the user take over
+	 * the kernel, since userspace controls RSP.
+	 *
+	 * TASK_SIZE_MAX covers all user-accessible addresses other than
+	 * the deprecated vsyscall page.
+	 */
+	if (unlikely(regs->ip >= TASK_SIZE_MAX))
+		return false;
+
+	/*
+	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.
+	 */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
+		return false;
+
+	/* Use SYSRET to exit to userspace */
+	return true;
+}
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
deleted file mode 100644
index fb77908f44f3..000000000000
--- a/arch/x86/entry/syscall_x32.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for x32 ABI. */
-
-#include <linux/linkage.h>
-#include <linux/sys.h>
-#include <linux/cache.h>
-#include <linux/syscalls.h>
-#include <asm/syscall.h>
-
-#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
-#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
-#include <asm/syscalls_x32.h>
-#undef  __SYSCALL
-
-#undef  __SYSCALL_NORETURN
-#define __SYSCALL_NORETURN __SYSCALL
-
-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
-{
-	switch (nr) {
-	#include <asm/syscalls_x32.h>
-	default: return __x64_sys_ni_syscall(regs);
-	}
-};
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 4d0fb2fba7e2..ac007ea00979 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
-384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+384	i386	arch_prctl		sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq
 393	i386	semget			sys_semget
@@ -472,3 +472,4 @@
 464	i386	getxattrat		sys_getxattrat
 465	i386	listxattrat		sys_listxattrat
 466	i386	removexattrat		sys_removexattrat
+467	i386	open_tree_attr		sys_open_tree_attr
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708bff1c7..cfb5ca41e30d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -390,6 +390,7 @@
 464	common	getxattrat		sys_getxattrat
 465	common	listxattrat		sys_listxattrat
 466	common	removexattrat		sys_removexattrat
+467	common	open_tree_attr		sys_open_tree_attr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c9216ac4fb1e..54d3e9774d62 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -4,7 +4,7 @@
 #
 
 # Include the generic Makefile to check the built vDSO:
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 # Files to link into the vDSO:
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrandom-chacha.o
@@ -32,7 +32,7 @@ targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 \
 			-z max-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
@@ -133,6 +133,7 @@ KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS_32 += -DBUILD_VDSO
 
 ifdef CONFIG_MITIGATION_RETPOLINE
 ifneq ($(RETPOLINE_VDSO_CFLAGS),)
@@ -151,10 +152,9 @@ $(obj)/vdso32.so.dbg: $(obj)/vdso32/vdso32.lds $(vobjs32) FORCE
 quiet_cmd_vdso = VDSO    $@
       cmd_vdso = $(LD) -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
-		 sh $(src)/checkundef.sh '$(NM)' '$@'
+		       -T $(filter %.lds,$^) $(filter %.o,$^)
 
-VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \
+VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 --no-undefined \
 	$(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack
 
 quiet_cmd_vdso_and_check = VDSO    $@
diff --git a/arch/x86/entry/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
deleted file mode 100755
index 7ee90a9b549d..000000000000
--- a/arch/x86/entry/vdso/checkundef.sh
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-nm="$1"
-file="$2"
-$nm "$file" | grep '^ *U' > /dev/null 2>&1
-if [ $? -eq 1 ]; then
-    exit 0
-else
-    echo "$file: undefined symbols found" >&2
-    exit 1
-fi
diff --git a/arch/x86/entry/vdso/extable.h b/arch/x86/entry/vdso/extable.h
index b56f6b012941..baba612b832c 100644
--- a/arch/x86/entry/vdso/extable.h
+++ b/arch/x86/entry/vdso/extable.h
@@ -7,7 +7,7 @@
  * vDSO uses a dedicated handler the addresses are relative to the overall
  * exception table, not each individual entry.
  */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ASM_VDSO_EXTABLE_HANDLE(from, to)	\
 	ASM_VDSO_EXTABLE_HANDLE from to
 
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 872947c1004c..ec1ac191a057 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <asm/vdso.h>
 #include <asm/vdso/vsyscall.h>
+#include <vdso/datapage.h>
 
 /*
  * Linker script for vDSO.  This is an ELF shared object prelinked to
@@ -17,14 +18,9 @@ SECTIONS
 	 * segment.
 	 */
 
-	vvar_start = . - __VVAR_PAGES * PAGE_SIZE;
-	vvar_page  = vvar_start;
+	VDSO_VVAR_SYMS
 
-	vdso_rng_data = vvar_page + __VDSO_RND_DATA_OFFSET;
-
-	timens_page  = vvar_start + PAGE_SIZE;
-
-	vclock_pages = vvar_start + VDSO_NR_VCLOCK_PAGES * PAGE_SIZE;
+	vclock_pages = VDSO_VCLOCK_PAGES_START(vdso_u_data);
 	pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE;
 	hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE;
 
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 90d15f2a7205..f84e8f8fa5fe 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -69,33 +69,12 @@
 
 const char *outfilename;
 
-/* Symbols that we need in vdso2c. */
-enum {
-	sym_vvar_start,
-	sym_vvar_page,
-	sym_pvclock_page,
-	sym_hvclock_page,
-	sym_timens_page,
-};
-
-const int special_pages[] = {
-	sym_vvar_page,
-	sym_pvclock_page,
-	sym_hvclock_page,
-	sym_timens_page,
-};
-
 struct vdso_sym {
 	const char *name;
 	bool export;
 };
 
 struct vdso_sym required_syms[] = {
-	[sym_vvar_start] = {"vvar_start", true},
-	[sym_vvar_page] = {"vvar_page", true},
-	[sym_pvclock_page] = {"pvclock_page", true},
-	[sym_hvclock_page] = {"hvclock_page", true},
-	[sym_timens_page] = {"timens_page", true},
 	{"VDSO32_NOTE_MASK", true},
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 67b3e37576a6..78ed1c1f28b9 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -150,26 +150,6 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		}
 	}
 
-	/* Validate mapping addresses. */
-	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
-		INT_BITS symval = syms[special_pages[i]];
-
-		if (!symval)
-			continue;  /* The mapping isn't used; ignore it. */
-
-		if (symval % 4096)
-			fail("%s must be a multiple of 4096\n",
-			     required_syms[i].name);
-		if (symval + 4096 < syms[sym_vvar_start])
-			fail("%s underruns vvar_start\n",
-			     required_syms[i].name);
-		if (symval + 4096 > 0)
-			fail("%s is on the wrong side of the vdso text\n",
-			     required_syms[i].name);
-	}
-	if (syms[sym_vvar_start] % 4096)
-		fail("vvar_begin must be a multiple of 4096\n");
-
 	if (!image_name) {
 		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index f6d2d8aba643..8894013eea1d 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -51,15 +51,17 @@ __setup("vdso32=", vdso32_setup);
 __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 #endif
 
-#ifdef CONFIG_X86_64
 
 #ifdef CONFIG_SYSCTL
-/* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static const struct ctl_table abi_table2[] = {
+static const struct ctl_table vdso_table[] = {
 	{
+#ifdef CONFIG_X86_64
 		.procname	= "vsyscall32",
+#else
+		.procname	= "vdso_enabled",
+#endif
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
@@ -71,10 +73,14 @@ static const struct ctl_table abi_table2[] = {
 
 static __init int ia32_binfmt_init(void)
 {
-	register_sysctl("abi", abi_table2);
+#ifdef CONFIG_X86_64
+	/* Register vsyscall32 into the ABI table */
+	register_sysctl("abi", vdso_table);
+#else
+	register_sysctl_init("vm", vdso_table);
+#endif
 	return 0;
 }
 __initcall(ia32_binfmt_init);
 #endif /* CONFIG_SYSCTL */
 
-#endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9ca..afe105b2f907 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -14,7 +14,7 @@
 #include <linux/elf.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/pvclock.h>
 #include <asm/vgtod.h>
@@ -27,13 +27,7 @@
 #include <asm/vdso/vsyscall.h>
 #include <clocksource/hyperv_timer.h>
 
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)vvar_page;
-}
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = vdso_data_store.data;
+static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES);
 
 unsigned int vclocks_used __read_mostly;
 
@@ -48,13 +42,11 @@ int __init init_vdso_image(const struct vdso_image *image)
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
-						image->alt_len),
-			   NULL);
+						image->alt_len));
 
 	return 0;
 }
 
-static const struct vm_special_mapping vvar_mapping;
 struct linux_binprm;
 
 static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
@@ -73,7 +65,6 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 static void vdso_fix_landing(const struct vdso_image *image,
 		struct vm_area_struct *new_vma)
 {
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 	if (in_ia32_syscall() && image == &vdso_image_32) {
 		struct pt_regs *regs = current_pt_regs();
 		unsigned long vdso_land = image->sym_int80_landing_pad;
@@ -84,7 +75,6 @@ static void vdso_fix_landing(const struct vdso_image *image,
 		if (regs->ip == old_land_addr)
 			regs->ip = new_vma->vm_start + vdso_land;
 	}
-#endif
 }
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
@@ -98,99 +88,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-#ifdef CONFIG_TIME_NS
-/*
- * The vvar page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-		      struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
-	unsigned long pfn;
-	long sym_offset;
-
-	if (!image)
-		return VM_FAULT_SIGBUS;
-
-	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
-		image->sym_vvar_start;
-
-	/*
-	 * Sanity check: a symbol offset of zero means that the page
-	 * does not exist for this vdso image, not that the page is at
-	 * offset zero relative to the text mapping.  This should be
-	 * impossible here, because sym_offset should only be zero for
-	 * the page past the end of the vvar mapping.
-	 */
-	if (sym_offset == 0)
-		return VM_FAULT_SIGBUS;
-
-	if (sym_offset == image->sym_vvar_page) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
-
-		/*
-		 * If a task belongs to a time namespace then a namespace
-		 * specific VVAR is mapped with the sym_vvar_page offset and
-		 * the real VVAR page is mapped with the sym_timens_page
-		 * offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (timens_page) {
-			unsigned long addr;
-			vm_fault_t err;
-
-			/*
-			 * Optimization: inside time namespace pre-fault
-			 * VVAR page too. As on timens page there are only
-			 * offsets for clocks on VVAR, it'll be faulted
-			 * shortly by VDSO code.
-			 */
-			addr = vmf->address + (image->sym_timens_page - sym_offset);
-			err = vmf_insert_pfn(vma, addr, pfn);
-			if (unlikely(err & VM_FAULT_ERROR))
-				return err;
-
-			pfn = page_to_pfn(timens_page);
-		}
-
-		return vmf_insert_pfn(vma, vmf->address, pfn);
-
-	} else if (sym_offset == image->sym_timens_page) {
-		struct page *timens_page = find_timens_vvar_page(vma);
-
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-
-		pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT;
-		return vmf_insert_pfn(vma, vmf->address, pfn);
-	}
-
-	return VM_FAULT_SIGBUS;
-}
-
 static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
 				    struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -212,7 +109,6 @@ static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
 	case VDSO_PAGE_HVCLOCK_OFFSET:
 	{
 		unsigned long pfn = hv_get_tsc_pfn();
-
 		if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
 			return vmf_insert_pfn(vma, vmf->address, pfn);
 		break;
@@ -228,10 +124,6 @@ static const struct vm_special_mapping vdso_mapping = {
 	.fault = vdso_fault,
 	.mremap = vdso_mremap,
 };
-static const struct vm_special_mapping vvar_mapping = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
 static const struct vm_special_mapping vvar_vclock_mapping = {
 	.name = "[vvar_vclock]",
 	.fault = vvar_vclock_fault,
@@ -253,13 +145,13 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		return -EINTR;
 
 	addr = get_unmapped_area(NULL, addr,
-				 image->size - image->sym_vvar_start, 0, 0);
+				 image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
 	}
 
-	text_start = addr - image->sym_vvar_start;
+	text_start = addr + __VDSO_PAGES * PAGE_SIZE;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -268,7 +160,8 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 				       text_start,
 				       image->size,
 				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
 				       &vdso_mapping);
 
 	if (IS_ERR(vma)) {
@@ -276,13 +169,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 		goto up_fail;
 	}
 
-	vma = _install_special_mapping(mm,
-				       addr,
-				       (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
-				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
-				       &vvar_mapping);
-
+	vma = vdso_install_vvar_mapping(mm, addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		do_munmap(mm, text_start, image->size, NULL);
@@ -290,10 +177,10 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	}
 
 	vma = _install_special_mapping(mm,
-				       addr + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE,
+				       VDSO_VCLOCK_PAGES_START(addr),
 				       VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
 				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
-				       VM_PFNMAP,
+				       VM_PFNMAP|VM_SEALED_SYSMAP,
 				       &vvar_vclock_mapping);
 
 	if (IS_ERR(vma)) {
@@ -327,7 +214,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 	 */
 	for_each_vma(vmi, vma) {
 		if (vma_is_special_mapping(vma, &vdso_mapping) ||
-				vma_is_special_mapping(vma, &vvar_mapping) ||
+				vma_is_special_mapping(vma, &vdso_vvar_mapping) ||
 				vma_is_special_mapping(vma, &vvar_vclock_mapping)) {
 			mmap_write_unlock(mm);
 			return -EEXIST;
@@ -338,7 +225,6 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 	return map_vdso(image, addr);
 }
 
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static int load_vdso32(void)
 {
 	if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
@@ -346,45 +232,38 @@ static int load_vdso32(void)
 
 	return map_vdso(&vdso_image_32, 0);
 }
-#endif
 
-#ifdef CONFIG_X86_64
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
-	if (!vdso64_enabled)
-		return 0;
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		if (!vdso64_enabled)
+			return 0;
+
+		return map_vdso(&vdso_image_64, 0);
+	}
 
-	return map_vdso(&vdso_image_64, 0);
+	return load_vdso32();
 }
 
 #ifdef CONFIG_COMPAT
 int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp, bool x32)
 {
-#ifdef CONFIG_X86_X32_ABI
-	if (x32) {
+	if (IS_ENABLED(CONFIG_X86_X32_ABI) && x32) {
 		if (!vdso64_enabled)
 			return 0;
 		return map_vdso(&vdso_image_x32, 0);
 	}
-#endif
-#ifdef CONFIG_IA32_EMULATION
-	return load_vdso32();
-#else
+
+	if (IS_ENABLED(CONFIG_IA32_EMULATION))
+		return load_vdso32();
+
 	return 0;
-#endif
-}
-#endif
-#else
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
-{
-	return load_vdso32();
 }
 #endif
 
 bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
 {
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 	const struct vdso_image *image = current->mm->context.vdso_image;
 	unsigned long vdso = (unsigned long) current->mm->context.vdso;
 
@@ -393,7 +272,6 @@ bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
 		    regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad)
 			return true;
 	}
-#endif
 	return false;
 }
 
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2fb7d53cf333..c9103a6fa06e 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -341,9 +341,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
 	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
 	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
 	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
-#if CONFIG_PGTABLE_LEVELS >= 5
 	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
-#endif
 	pud = pud_offset(p4d, VSYSCALL_ADDR);
 	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
 	pmd = pmd_offset(pud, VSYSCALL_ADDR);
diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
index 780acd3dff22..06f35a6b58a5 100644
--- a/arch/x86/events/amd/brs.c
+++ b/arch/x86/events/amd/brs.c
@@ -44,12 +44,12 @@ static inline unsigned int brs_to(int idx)
 static __always_inline void set_debug_extn_cfg(u64 val)
 {
 	/* bits[4:3] must always be set to 11b */
-	__wrmsr(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3, val >> 32);
+	native_wrmsrq(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3);
 }
 
 static __always_inline u64 get_debug_extn_cfg(void)
 {
-	return __rdmsr(MSR_AMD_DBG_EXTN_CFG);
+	return native_rdmsrq(MSR_AMD_DBG_EXTN_CFG);
 }
 
 static bool __init amd_brs_detect(void)
@@ -187,7 +187,7 @@ void amd_brs_reset(void)
 	/*
 	 * Mark first entry as poisoned
 	 */
-	wrmsrl(brs_to(0), BRS_POISON);
+	wrmsrq(brs_to(0), BRS_POISON);
 }
 
 int __init amd_brs_init(void)
@@ -325,7 +325,7 @@ void amd_brs_drain(void)
 		u32 brs_idx = tos - i;
 		u64 from, to;
 
-		rdmsrl(brs_to(brs_idx), to);
+		rdmsrq(brs_to(brs_idx), to);
 
 		/* Entry does not belong to us (as marked by kernel) */
 		if (to == BRS_POISON)
@@ -341,7 +341,7 @@ void amd_brs_drain(void)
 		if (!amd_brs_match_plm(event, to))
 			continue;
 
-		rdmsrl(brs_from(brs_idx), from);
+		rdmsrq(brs_from(brs_idx), from);
 
 		perf_clear_branch_entry_bitfields(br+nr);
 
@@ -371,7 +371,7 @@ static void amd_brs_poison_buffer(void)
 	idx = amd_brs_get_tos(&cfg);
 
 	/* Poison target of entry */
-	wrmsrl(brs_to(idx), BRS_POISON);
+	wrmsrq(brs_to(idx), BRS_POISON);
 }
 
 /*
@@ -381,7 +381,8 @@ static void amd_brs_poison_buffer(void)
  * On ctxswin, sched_in = true, called after the PMU has started
  * On ctxswout, sched_in = false, called before the PMU is stopped
  */
-void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 30d6ceb4c8ad..b20661b8621d 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -9,6 +9,7 @@
 #include <linux/jiffies.h>
 #include <asm/apicdef.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 #include <asm/nmi.h>
 
 #include "../perf_event.h"
@@ -563,13 +564,13 @@ static void amd_pmu_cpu_reset(int cpu)
 		return;
 
 	/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
 
 	/*
 	 * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
 	 * and PerfCntrGLobalStatus.PerfCntrOvfl
 	 */
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
 	       GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
 }
 
@@ -651,7 +652,7 @@ static void amd_pmu_cpu_dead(int cpu)
 
 static __always_inline void amd_pmu_set_global_ctl(u64 ctl)
 {
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
 }
 
 static inline u64 amd_pmu_get_global_status(void)
@@ -659,7 +660,7 @@ static inline u64 amd_pmu_get_global_status(void)
 	u64 status;
 
 	/* PerfCntrGlobalStatus is read-only */
-	rdmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status);
+	rdmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status);
 
 	return status;
 }
@@ -672,14 +673,14 @@ static inline void amd_pmu_ack_global_status(u64 status)
 	 * clears the same bit in PerfCntrGlobalStatus
 	 */
 
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status);
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status);
 }
 
 static bool amd_pmu_test_overflow_topbit(int idx)
 {
 	u64 counter;
 
-	rdmsrl(x86_pmu_event_addr(idx), counter);
+	rdmsrq(x86_pmu_event_addr(idx), counter);
 
 	return !(counter & BIT_ULL(x86_pmu.cntval_bits - 1));
 }
@@ -1003,8 +1004,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 
 		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index e7a8b8758e08..112f43b23ebf 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -15,6 +15,7 @@
 #include <linux/sched/clock.h>
 
 #include <asm/apic.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -26,10 +27,7 @@ static u32 ibs_caps;
 #include <linux/hardirq.h>
 
 #include <asm/nmi.h>
-#include <asm/amd-ibs.h>
-
-#define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
-#define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
+#include <asm/amd/ibs.h>
 
 /* attr.config2 */
 #define IBS_SW_FILTER_MASK	1
@@ -89,6 +87,7 @@ struct perf_ibs {
 	u64				cnt_mask;
 	u64				enable_mask;
 	u64				valid_mask;
+	u16				min_period;
 	u64				max_period;
 	unsigned long			offset_mask[1];
 	int				offset_max;
@@ -270,11 +269,19 @@ static int validate_group(struct perf_event *event)
 	return 0;
 }
 
+static bool perf_ibs_ldlat_event(struct perf_ibs *perf_ibs,
+				 struct perf_event *event)
+{
+	return perf_ibs == &perf_ibs_op &&
+	       (ibs_caps & IBS_CAPS_OPLDLAT) &&
+	       (event->attr.config1 & 0xFFF);
+}
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_ibs *perf_ibs;
-	u64 max_cnt, config;
+	u64 config;
 	int ret;
 
 	perf_ibs = get_ibs_pmu(event->attr.type);
@@ -310,25 +317,47 @@ static int perf_ibs_init(struct perf_event *event)
 		if (config & perf_ibs->cnt_mask)
 			/* raw max_cnt may not be set */
 			return -EINVAL;
-		if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
-			/*
-			 * lower 4 bits can not be set in ibs max cnt,
-			 * but allowing it in case we adjust the
-			 * sample period to set a frequency.
-			 */
-			return -EINVAL;
-		hwc->sample_period &= ~0x0FULL;
-		if (!hwc->sample_period)
-			hwc->sample_period = 0x10;
+
+		if (event->attr.freq) {
+			hwc->sample_period = perf_ibs->min_period;
+		} else {
+			/* Silently mask off lower nibble. IBS hw mandates it. */
+			hwc->sample_period &= ~0x0FULL;
+			if (hwc->sample_period < perf_ibs->min_period)
+				return -EINVAL;
+		}
 	} else {
-		max_cnt = config & perf_ibs->cnt_mask;
+		u64 period = 0;
+
+		if (event->attr.freq)
+			return -EINVAL;
+
+		if (perf_ibs == &perf_ibs_op) {
+			period = (config & IBS_OP_MAX_CNT) << 4;
+			if (ibs_caps & IBS_CAPS_OPCNTEXT)
+				period |= config & IBS_OP_MAX_CNT_EXT_MASK;
+		} else {
+			period = (config & IBS_FETCH_MAX_CNT) << 4;
+		}
+
 		config &= ~perf_ibs->cnt_mask;
-		event->attr.sample_period = max_cnt << 4;
-		hwc->sample_period = event->attr.sample_period;
+		event->attr.sample_period = period;
+		hwc->sample_period = period;
+
+		if (hwc->sample_period < perf_ibs->min_period)
+			return -EINVAL;
 	}
 
-	if (!hwc->sample_period)
-		return -EINVAL;
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		u64 ldlat = event->attr.config1 & 0xFFF;
+
+		if (ldlat < 128 || ldlat > 2048)
+			return -EINVAL;
+		ldlat >>= 7;
+
+		config |= (ldlat - 1) << 59;
+		config |= IBS_OP_L3MISSONLY | IBS_OP_LDLAT_EN;
+	}
 
 	/*
 	 * If we modify hwc->sample_period, we also need to update
@@ -349,7 +378,8 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
 	int overflow;
 
 	/* ignore lower 4 bits in min count: */
-	overflow = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period);
+	overflow = perf_event_set_period(hwc, perf_ibs->min_period,
+					 perf_ibs->max_period, period);
 	local64_set(&hwc->prev_count, 0);
 
 	return overflow;
@@ -395,7 +425,7 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event,
 	 * prev count manually on overflow.
 	 */
 	while (!perf_event_try_update(event, count, 64)) {
-		rdmsrl(event->hw.config_base, *config);
+		rdmsrq(event->hw.config_base, *config);
 		count = perf_ibs->get_count(*config);
 	}
 }
@@ -406,9 +436,9 @@ static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs,
 	u64 tmp = hwc->config | config;
 
 	if (perf_ibs->fetch_count_reset_broken)
-		wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask);
+		wrmsrq(hwc->config_base, tmp & ~perf_ibs->enable_mask);
 
-	wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask);
+	wrmsrq(hwc->config_base, tmp | perf_ibs->enable_mask);
 }
 
 /*
@@ -423,9 +453,9 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
 {
 	config &= ~perf_ibs->cnt_mask;
 	if (boot_cpu_data.x86 == 0x10)
-		wrmsrl(hwc->config_base, config);
+		wrmsrq(hwc->config_base, config);
 	config &= ~perf_ibs->enable_mask;
-	wrmsrl(hwc->config_base, config);
+	wrmsrq(hwc->config_base, config);
 }
 
 /*
@@ -447,6 +477,9 @@ static void perf_ibs_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 	perf_ibs_set_period(perf_ibs, hwc, &period);
 	if (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_OPCNTEXT)) {
 		config |= period & IBS_OP_MAX_CNT_EXT_MASK;
@@ -481,7 +514,7 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
 	if (!stopping && (hwc->state & PERF_HES_UPTODATE))
 		return;
 
-	rdmsrl(hwc->config_base, config);
+	rdmsrq(hwc->config_base, config);
 
 	if (stopping) {
 		/*
@@ -554,6 +587,28 @@ static void perf_ibs_del(struct perf_event *event, int flags)
 
 static void perf_ibs_read(struct perf_event *event) { }
 
+static int perf_ibs_check_period(struct perf_event *event, u64 value)
+{
+	struct perf_ibs *perf_ibs;
+	u64 low_nibble;
+
+	if (event->attr.freq)
+		return 0;
+
+	perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	low_nibble = value & 0xFULL;
+
+	/*
+	 * This contradicts with perf_ibs_init() which allows sample period
+	 * with lower nibble bits set but silently masks them off. Whereas
+	 * this returns error.
+	 */
+	if (low_nibble || value < perf_ibs->min_period)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * We need to initialize with empty group if all attributes in the
  * group are dynamic.
@@ -572,7 +627,10 @@ PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
 PMU_FORMAT_ATTR(swfilt,		"config2:0");
 PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
 PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_format, "config1:0-11");
 PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_cap, "1");
+PMU_EVENT_ATTR_STRING(dtlb_pgsize, ibs_op_dtlb_pgsize_cap, "1");
 
 static umode_t
 zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
@@ -580,6 +638,18 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int
 	return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
 }
 
+static umode_t
+ibs_op_ldlat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPLDLAT ? attr->mode : 0;
+}
+
+static umode_t
+ibs_op_dtlb_pgsize_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPDTLBPGSIZE ? attr->mode : 0;
+}
+
 static struct attribute *fetch_attrs[] = {
 	&format_attr_rand_en.attr,
 	&format_attr_swfilt.attr,
@@ -596,6 +666,16 @@ static struct attribute *zen4_ibs_extensions_attrs[] = {
 	NULL,
 };
 
+static struct attribute *ibs_op_ldlat_cap_attrs[] = {
+	&ibs_op_ldlat_cap.attr.attr,
+	NULL,
+};
+
+static struct attribute *ibs_op_dtlb_pgsize_cap_attrs[] = {
+	&ibs_op_dtlb_pgsize_cap.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_fetch_formats = {
 	.name = "format",
 	.attrs = fetch_attrs,
@@ -613,6 +693,18 @@ static struct attribute_group group_zen4_ibs_extensions = {
 	.is_visible = zen4_ibs_extensions_is_visible,
 };
 
+static struct attribute_group group_ibs_op_ldlat_cap = {
+	.name = "caps",
+	.attrs = ibs_op_ldlat_cap_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
+static struct attribute_group group_ibs_op_dtlb_pgsize_cap = {
+	.name = "caps",
+	.attrs = ibs_op_dtlb_pgsize_cap_attrs,
+	.is_visible = ibs_op_dtlb_pgsize_is_visible,
+};
+
 static const struct attribute_group *fetch_attr_groups[] = {
 	&group_fetch_formats,
 	&empty_caps_group,
@@ -651,6 +743,11 @@ static struct attribute_group group_op_formats = {
 	.attrs = op_attrs,
 };
 
+static struct attribute *ibs_op_ldlat_format_attrs[] = {
+	&ibs_op_ldlat_format.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_cnt_ctl = {
 	.name = "format",
 	.attrs = cnt_ctl_attrs,
@@ -669,10 +766,19 @@ static const struct attribute_group *op_attr_groups[] = {
 	NULL,
 };
 
+static struct attribute_group group_ibs_op_ldlat_format = {
+	.name = "format",
+	.attrs = ibs_op_ldlat_format_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
 static const struct attribute_group *op_attr_update[] = {
 	&group_cnt_ctl,
 	&group_op_l3missonly,
 	&group_zen4_ibs_extensions,
+	&group_ibs_op_ldlat_cap,
+	&group_ibs_op_ldlat_format,
+	&group_ibs_op_dtlb_pgsize_cap,
 	NULL,
 };
 
@@ -686,12 +792,14 @@ static struct perf_ibs perf_ibs_fetch = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSFETCHCTL,
-	.config_mask		= IBS_FETCH_CONFIG_MASK,
+	.config_mask		= IBS_FETCH_MAX_CNT | IBS_FETCH_RAND_EN,
 	.cnt_mask		= IBS_FETCH_MAX_CNT,
 	.enable_mask		= IBS_FETCH_ENABLE,
 	.valid_mask		= IBS_FETCH_VAL,
+	.min_period		= 0x10,
 	.max_period		= IBS_FETCH_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
@@ -709,13 +817,15 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
-	.config_mask		= IBS_OP_CONFIG_MASK,
+	.config_mask		= IBS_OP_MAX_CNT,
 	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
 				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
+	.min_period		= 0x90,
 	.max_period		= IBS_OP_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,
@@ -917,6 +1027,10 @@ static void perf_ibs_get_tlb_lvl(union ibs_op_data3 *op_data3,
 	if (!op_data3->dc_lin_addr_valid)
 		return;
 
+	if ((ibs_caps & IBS_CAPS_OPDTLBPGSIZE) &&
+	    !op_data3->dc_phy_addr_valid)
+		return;
+
 	if (!op_data3->dc_l1tlb_miss) {
 		data_src->mem_dtlb = PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT;
 		return;
@@ -941,6 +1055,8 @@ static void perf_ibs_get_mem_lock(union ibs_op_data3 *op_data3,
 		data_src->mem_lock = PERF_MEM_LOCK_LOCKED;
 }
 
+/* Be careful. Works only for contiguous MSRs. */
+#define ibs_fetch_msr_idx(msr)	(msr - MSR_AMD64_IBSFETCHCTL)
 #define ibs_op_msr_idx(msr)	(msr - MSR_AMD64_IBSOPCTL)
 
 static void perf_ibs_get_data_src(struct perf_ibs_data *ibs_data,
@@ -1021,21 +1137,92 @@ static void perf_ibs_parse_ld_st_data(__u64 sample_type,
 	}
 }
 
-static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs, u64 sample_type,
+static bool perf_ibs_is_mem_sample_type(struct perf_ibs *perf_ibs,
+					struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	return perf_ibs == &perf_ibs_op &&
+	       sample_type & (PERF_SAMPLE_DATA_SRC |
+			      PERF_SAMPLE_WEIGHT_TYPE |
+			      PERF_SAMPLE_ADDR |
+			      PERF_SAMPLE_PHYS_ADDR);
+}
+
+static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs,
+				   struct perf_event *event,
 				   int check_rip)
 {
-	if (sample_type & PERF_SAMPLE_RAW ||
-	    (perf_ibs == &perf_ibs_op &&
-	     (sample_type & PERF_SAMPLE_DATA_SRC ||
-	      sample_type & PERF_SAMPLE_WEIGHT_TYPE ||
-	      sample_type & PERF_SAMPLE_ADDR ||
-	      sample_type & PERF_SAMPLE_PHYS_ADDR)))
+	if (event->attr.sample_type & PERF_SAMPLE_RAW ||
+	    perf_ibs_is_mem_sample_type(perf_ibs, event) ||
+	    perf_ibs_ldlat_event(perf_ibs, event))
 		return perf_ibs->offset_max;
 	else if (check_rip)
 		return 3;
 	return 1;
 }
 
+static bool perf_ibs_is_kernel_data_addr(struct perf_event *event,
+					 struct perf_ibs_data *ibs_data)
+{
+	u64 sample_type_mask = PERF_SAMPLE_ADDR | PERF_SAMPLE_RAW;
+	union ibs_op_data3 op_data3;
+	u64 dc_lin_addr;
+
+	op_data3.val = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)];
+	dc_lin_addr = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSDCLINAD)];
+
+	return unlikely((event->attr.sample_type & sample_type_mask) &&
+			op_data3.dc_lin_addr_valid && kernel_ip(dc_lin_addr));
+}
+
+static bool perf_ibs_is_kernel_br_target(struct perf_event *event,
+					 struct perf_ibs_data *ibs_data,
+					 int br_target_idx)
+{
+	union ibs_op_data op_data;
+	u64 br_target;
+
+	op_data.val = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA)];
+	br_target = ibs_data->regs[br_target_idx];
+
+	return unlikely((event->attr.sample_type & PERF_SAMPLE_RAW) &&
+			op_data.op_brn_ret && kernel_ip(br_target));
+}
+
+static bool perf_ibs_swfilt_discard(struct perf_ibs *perf_ibs, struct perf_event *event,
+				    struct pt_regs *regs, struct perf_ibs_data *ibs_data,
+				    int br_target_idx)
+{
+	if (perf_exclude_event(event, regs))
+		return true;
+
+	if (perf_ibs != &perf_ibs_op || !event->attr.exclude_kernel)
+		return false;
+
+	if (perf_ibs_is_kernel_data_addr(event, ibs_data))
+		return true;
+
+	if (br_target_idx != -1 &&
+	    perf_ibs_is_kernel_br_target(event, ibs_data, br_target_idx))
+		return true;
+
+	return false;
+}
+
+static void perf_ibs_phyaddr_clear(struct perf_ibs *perf_ibs,
+				   struct perf_ibs_data *ibs_data)
+{
+	if (perf_ibs == &perf_ibs_op) {
+		ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)] &= ~(1ULL << 18);
+		ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSDCPHYSAD)] = 0;
+		return;
+	}
+
+	ibs_data->regs[ibs_fetch_msr_idx(MSR_AMD64_IBSFETCHCTL)] &= ~(1ULL << 52);
+	ibs_data->regs[ibs_fetch_msr_idx(MSR_AMD64_IBSFETCHPHYSAD)] = 0;
+}
+
 static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
@@ -1048,6 +1235,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	int offset, size, check_rip, offset_max, throttle = 0;
 	unsigned int msr;
 	u64 *buf, *config, period, new_config = 0;
+	int br_target_idx = -1;
 
 	if (!test_bit(IBS_STARTED, pcpu->state)) {
 fail:
@@ -1069,7 +1257,7 @@ fail:
 	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
-	rdmsrl(msr, *buf);
+	rdmsrq(msr, *buf);
 	if (!(*buf++ & perf_ibs->valid_mask))
 		goto fail;
 
@@ -1084,15 +1272,31 @@ fail:
 	offset = 1;
 	check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK));
 
-	offset_max = perf_ibs_get_offset_max(perf_ibs, event->attr.sample_type, check_rip);
+	offset_max = perf_ibs_get_offset_max(perf_ibs, event, check_rip);
 
 	do {
-		rdmsrl(msr + offset, *buf++);
+		rdmsrq(msr + offset, *buf++);
 		size++;
 		offset = find_next_bit(perf_ibs->offset_mask,
 				       perf_ibs->offset_max,
 				       offset + 1);
 	} while (offset < offset_max);
+
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		union ibs_op_data3 op_data3;
+
+		op_data3.val = ibs_data.regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)];
+		/*
+		 * Opening event is errored out if load latency threshold is
+		 * outside of [128, 2048] range. Since the event has reached
+		 * interrupt handler, we can safely assume the threshold is
+		 * within [128, 2048] range.
+		 */
+		if (!op_data3.ld_op || !op_data3.dc_miss ||
+		    op_data3.dc_miss_lat <= (event->attr.config1 & 0xFFF))
+			goto out;
+	}
+
 	/*
 	 * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately
 	 * depending on their availability.
@@ -1101,16 +1305,17 @@ fail:
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		if (perf_ibs == &perf_ibs_op) {
 			if (ibs_caps & IBS_CAPS_BRNTRGT) {
-				rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+				rdmsrq(MSR_AMD64_IBSBRTARGET, *buf++);
+				br_target_idx = size;
 				size++;
 			}
 			if (ibs_caps & IBS_CAPS_OPDATA4) {
-				rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+				rdmsrq(MSR_AMD64_IBSOPDATA4, *buf++);
 				size++;
 			}
 		}
 		if (perf_ibs == &perf_ibs_fetch && (ibs_caps & IBS_CAPS_FETCHCTLEXTD)) {
-			rdmsrl(MSR_AMD64_ICIBSEXTDCTL, *buf++);
+			rdmsrq(MSR_AMD64_ICIBSEXTDCTL, *buf++);
 			size++;
 		}
 	}
@@ -1129,10 +1334,19 @@ fail:
 	}
 
 	if ((event->attr.config2 & IBS_SW_FILTER_MASK) &&
-	    perf_exclude_event(event, &regs)) {
+	    perf_ibs_swfilt_discard(perf_ibs, event, &regs, &ibs_data, br_target_idx)) {
 		throttle = perf_event_account_interrupt(event);
 		goto out;
 	}
+	/*
+	 * Prevent leaking physical addresses to unprivileged users. Skip
+	 * PERF_SAMPLE_PHYS_ADDR check since generic code prevents it for
+	 * unprivileged users.
+	 */
+	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
+	    perf_allow_kernel()) {
+		perf_ibs_phyaddr_clear(perf_ibs, &ibs_data);
+	}
 
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
 		raw = (struct perf_raw_record){
@@ -1155,10 +1369,12 @@ fail:
 	perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
+
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 out:
-	if (throttle) {
-		perf_ibs_stop(event, 0);
-	} else {
+	if (!throttle) {
 		if (perf_ibs == &perf_ibs_op) {
 			if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 				new_config = period & IBS_OP_MAX_CNT_EXT_MASK;
@@ -1244,7 +1460,8 @@ static __init int perf_ibs_op_init(void)
 	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 		perf_ibs_op.max_period  |= IBS_OP_MAX_CNT_EXT_MASK;
 		perf_ibs_op.config_mask	|= IBS_OP_MAX_CNT_EXT_MASK;
-		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
+		perf_ibs_op.cnt_mask    |= (IBS_OP_MAX_CNT_EXT_MASK |
+					    IBS_OP_CUR_CNT_EXT_MASK);
 	}
 
 	if (ibs_caps & IBS_CAPS_ZEN4)
@@ -1347,7 +1564,7 @@ static inline int ibs_eilvt_valid(void)
 
 	preempt_disable();
 
-	rdmsrl(MSR_AMD64_IBSCTL, val);
+	rdmsrq(MSR_AMD64_IBSCTL, val);
 	offset = val & IBSCTL_LVT_OFFSET_MASK;
 
 	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
@@ -1462,7 +1679,7 @@ static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
 
-	rdmsrl(MSR_AMD64_IBSCTL, val);
+	rdmsrq(MSR_AMD64_IBSCTL, val);
 	if (!(val & IBSCTL_LVT_OFFSET_VALID))
 		return -EINVAL;
 
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index b15f7b950d2e..a721da9987dd 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -16,6 +16,8 @@
 #include <linux/slab.h>
 #include <linux/amd-iommu.h>
 
+#include <asm/msr.h>
+
 #include "../perf_event.h"
 #include "iommu.h"
 
@@ -30,7 +32,7 @@
 #define GET_DOMID_MASK(x)  (((x)->conf1 >> 16) & 0xFFFFULL)
 #define GET_PASID_MASK(x)  (((x)->conf1 >> 32) & 0xFFFFFULL)
 
-#define IOMMU_NAME_SIZE 16
+#define IOMMU_NAME_SIZE 24
 
 struct perf_amd_iommu {
 	struct list_head list;
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 19c7b76e21bc..d24da377df77 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/perf_event.h>
+#include <asm/msr.h>
 #include <asm/perf_event.h>
 
 #include "../perf_event.h"
@@ -61,19 +62,19 @@ struct branch_entry {
 
 static __always_inline void amd_pmu_lbr_set_from(unsigned int idx, u64 val)
 {
-	wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
+	wrmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
 }
 
 static __always_inline void amd_pmu_lbr_set_to(unsigned int idx, u64 val)
 {
-	wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
+	wrmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
 }
 
 static __always_inline u64 amd_pmu_lbr_get_from(unsigned int idx)
 {
 	u64 val;
 
-	rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
+	rdmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
 
 	return val;
 }
@@ -82,7 +83,7 @@ static __always_inline u64 amd_pmu_lbr_get_to(unsigned int idx)
 {
 	u64 val;
 
-	rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
+	rdmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
 
 	return val;
 }
@@ -333,7 +334,7 @@ void amd_pmu_lbr_reset(void)
 
 	cpuc->last_task_ctx = NULL;
 	cpuc->last_log_id = 0;
-	wrmsrl(MSR_AMD64_LBR_SELECT, 0);
+	wrmsrq(MSR_AMD64_LBR_SELECT, 0);
 }
 
 void amd_pmu_lbr_add(struct perf_event *event)
@@ -371,7 +372,8 @@ void amd_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->pmu);
 }
 
-void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
@@ -395,16 +397,16 @@ void amd_pmu_lbr_enable_all(void)
 	/* Set hardware branch filter */
 	if (cpuc->lbr_select) {
 		lbr_select = cpuc->lbr_sel->config & LBR_SELECT_MASK;
-		wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select);
+		wrmsrq(MSR_AMD64_LBR_SELECT, lbr_select);
 	}
 
 	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
 	}
 
-	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
-	wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
+	rdmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+	wrmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
 }
 
 void amd_pmu_lbr_disable_all(void)
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 37d5b380516e..dad42790cf7d 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include "../perf_event.h"
 
 /* Event code: LSB 8 bits, passed in attr->config any other bit is reserved. */
@@ -48,8 +49,8 @@ static void event_update(struct perf_event *event)
 
 	prev_pwr_acc = hwc->pwr_acc;
 	prev_ptsc = hwc->ptsc;
-	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
-	rdmsrl(MSR_F15H_PTSC, new_ptsc);
+	rdmsrq(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
+	rdmsrq(MSR_F15H_PTSC, new_ptsc);
 
 	/*
 	 * Calculate the CU power consumption over a time period, the unit of
@@ -75,8 +76,8 @@ static void __pmu_event_start(struct perf_event *event)
 
 	event->hw.state = 0;
 
-	rdmsrl(MSR_F15H_PTSC, event->hw.ptsc);
-	rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
+	rdmsrq(MSR_F15H_PTSC, event->hw.ptsc);
+	rdmsrq(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
 }
 
 static void pmu_event_start(struct perf_event *event, int mode)
@@ -272,7 +273,7 @@ static int __init amd_power_pmu_init(void)
 
 	cpu_pwr_sample_ratio = cpuid_ecx(0x80000007);
 
-	if (rdmsrl_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
+	if (rdmsrq_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
 		pr_err("Failed to read max compute unit power accumulator MSR\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 49c26ce2b115..e8b6af199c73 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -21,6 +21,7 @@
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
 #define NUM_COUNTERS_L3		6
+#define NUM_COUNTERS_MAX	64
 
 #define RDPMC_BASE_NB		6
 #define RDPMC_BASE_LLC		10
@@ -38,7 +39,10 @@ struct amd_uncore_ctx {
 	int refcnt;
 	int cpu;
 	struct perf_event **events;
-	struct hlist_node node;
+	unsigned long active_mask[BITS_TO_LONGS(NUM_COUNTERS_MAX)];
+	int nr_active;
+	struct hrtimer hrtimer;
+	u64 hrtimer_duration;
 };
 
 struct amd_uncore_pmu {
@@ -83,11 +87,51 @@ struct amd_uncore {
 
 static struct amd_uncore uncores[UNCORE_TYPE_MAX];
 
+/* Interval for hrtimer, defaults to 60000 milliseconds */
+static unsigned int update_interval = 60 * MSEC_PER_SEC;
+module_param(update_interval, uint, 0444);
+
 static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct amd_uncore_pmu, pmu);
 }
 
+static enum hrtimer_restart amd_uncore_hrtimer(struct hrtimer *hrtimer)
+{
+	struct amd_uncore_ctx *ctx;
+	struct perf_event *event;
+	int bit;
+
+	ctx = container_of(hrtimer, struct amd_uncore_ctx, hrtimer);
+
+	if (!ctx->nr_active || ctx->cpu != smp_processor_id())
+		return HRTIMER_NORESTART;
+
+	for_each_set_bit(bit, ctx->active_mask, NUM_COUNTERS_MAX) {
+		event = ctx->events[bit];
+		event->pmu->read(event);
+	}
+
+	hrtimer_forward_now(hrtimer, ns_to_ktime(ctx->hrtimer_duration));
+	return HRTIMER_RESTART;
+}
+
+static void amd_uncore_start_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_start(&ctx->hrtimer, ns_to_ktime(ctx->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED_HARD);
+}
+
+static void amd_uncore_cancel_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_cancel(&ctx->hrtimer);
+}
+
+static void amd_uncore_init_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_setup(&ctx->hrtimer, amd_uncore_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+}
+
 static void amd_uncore_read(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -106,9 +150,9 @@ static void amd_uncore_read(struct perf_event *event)
 	 * read counts directly from the corresponding PERF_CTR.
 	 */
 	if (hwc->event_base_rdpmc < 0)
-		rdmsrl(hwc->event_base, new);
+		rdmsrq(hwc->event_base, new);
 	else
-		rdpmcl(hwc->event_base_rdpmc, new);
+		new = rdpmc(hwc->event_base_rdpmc);
 
 	local64_set(&hwc->prev_count, new);
 	delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
@@ -118,27 +162,40 @@ static void amd_uncore_read(struct perf_event *event)
 
 static void amd_uncore_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
-		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+		wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
-	wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
+	__set_bit(hwc->idx, ctx->active_mask);
+	wrmsrq(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
 	perf_event_update_userpage(event);
 }
 
 static void amd_uncore_stop(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrq(hwc->config_base, hwc->config);
 	hwc->state |= PERF_HES_STOPPED;
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
 		event->pmu->read(event);
 		hwc->state |= PERF_HES_UPTODATE;
 	}
+
+	if (!--ctx->nr_active)
+		amd_uncore_cancel_hrtimer(ctx);
+
+	__clear_bit(hwc->idx, ctx->active_mask);
 }
 
 static int amd_uncore_add(struct perf_event *event, int flags)
@@ -491,6 +548,9 @@ static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				goto fail;
 			}
 
+			amd_uncore_init_hrtimer(curr);
+			curr->hrtimer_duration = (u64)update_interval * NSEC_PER_MSEC;
+
 			cpumask_set_cpu(cpu, &pmu->active_mask);
 		}
 
@@ -880,16 +940,55 @@ static int amd_uncore_umc_event_init(struct perf_event *event)
 
 static void amd_uncore_umc_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
-		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+		wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
-	wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
+	__set_bit(hwc->idx, ctx->active_mask);
+	wrmsrq(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
 	perf_event_update_userpage(event);
 }
 
+static void amd_uncore_umc_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev, new, shift;
+	s64 delta;
+
+	shift = COUNTER_SHIFT + 1;
+	prev = local64_read(&hwc->prev_count);
+
+	/*
+	 * UMC counters do not have RDPMC assignments. Read counts directly
+	 * from the corresponding PERF_CTR.
+	 */
+	rdmsrl(hwc->event_base, new);
+
+	/*
+	 * Unlike the other uncore counters, UMC counters saturate and set the
+	 * Overflow bit (bit 48) on overflow. Since they do not roll over,
+	 * proactively reset the corresponding PERF_CTR when bit 47 is set so
+	 * that the counter never gets a chance to saturate.
+	 */
+	if (new & BIT_ULL(63 - COUNTER_SHIFT)) {
+		wrmsrl(hwc->event_base, 0);
+		local64_set(&hwc->prev_count, 0);
+	} else {
+		local64_set(&hwc->prev_count, new);
+	}
+
+	delta = (new << shift) - (prev << shift);
+	delta >>= shift;
+	local64_add(delta, &event->count);
+}
+
 static
 void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
@@ -968,7 +1067,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				.del		= amd_uncore_del,
 				.start		= amd_uncore_umc_start,
 				.stop		= amd_uncore_stop,
-				.read		= amd_uncore_read,
+				.read		= amd_uncore_umc_read,
 				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 				.module		= THIS_MODULE,
 			};
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445..7610f26dfbd9 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -32,6 +32,7 @@
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
+#include <asm/msr.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
@@ -87,13 +88,19 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_commit_scheduling, *x86_pmu.commit_scheduling);
 DEFINE_STATIC_CALL_NULL(x86_pmu_stop_scheduling,   *x86_pmu.stop_scheduling);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_sched_task,    *x86_pmu.sched_task);
-DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs,   *x86_pmu.drain_pebs);
 DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
+
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
+
 /*
  * This one is magic, it will get called even when PMU init fails (because
  * there is no PMU), in which case it should simply return NULL.
@@ -133,7 +140,7 @@ u64 x86_perf_event_update(struct perf_event *event)
 	 */
 	prev_raw_count = local64_read(&hwc->prev_count);
 	do {
-		rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+		new_raw_count = rdpmc(hwc->event_base_rdpmc);
 	} while (!local64_try_cmpxchg(&hwc->prev_count,
 				      &prev_raw_count, new_raw_count));
 
@@ -268,7 +275,7 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
 	 */
 	for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
-		ret = rdmsrl_safe(reg, &val);
+		ret = rdmsrq_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
 		if (val & ARCH_PERFMON_EVENTSEL_ENABLE) {
@@ -282,7 +289,7 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
 
 	if (*(u64 *)fixed_cntr_mask) {
 		reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		ret = rdmsrl_safe(reg, &val);
+		ret = rdmsrq_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
 		for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
@@ -313,11 +320,11 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
 	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
 	reg = x86_pmu_event_addr(reg_safe);
-	if (rdmsrl_safe(reg, &val))
+	if (rdmsrq_safe(reg, &val))
 		goto msr_fail;
 	val ^= 0xffffUL;
-	ret = wrmsrl_safe(reg, val);
-	ret |= rdmsrl_safe(reg, &val_new);
+	ret = wrmsrq_safe(reg, val);
+	ret |= rdmsrq_safe(reg, &val_new);
 	if (ret || val != val_new)
 		goto msr_fail;
 
@@ -628,7 +635,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)
@@ -673,6 +680,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	event->hw.idx = -1;
 	event->hw.last_cpu = -1;
 	event->hw.last_tag = ~0ULL;
+	event->hw.dyn_constraint = ~0ULL;
 
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -692,13 +700,13 @@ void x86_pmu_disable_all(void)
 
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		rdmsrl(x86_pmu_config_addr(idx), val);
+		rdmsrq(x86_pmu_config_addr(idx), val);
 		if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
 			continue;
 		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
-		wrmsrl(x86_pmu_config_addr(idx), val);
+		wrmsrq(x86_pmu_config_addr(idx), val);
 		if (is_counter_pair(hwc))
-			wrmsrl(x86_pmu_config_addr(idx + 1), 0);
+			wrmsrq(x86_pmu_config_addr(idx + 1), 0);
 	}
 }
 
@@ -753,17 +761,18 @@ void x86_pmu_enable_all(int added)
 	}
 }
 
-static inline int is_x86_event(struct perf_event *event)
+int is_x86_event(struct perf_event *event)
 {
-	int i;
-
-	if (!is_hybrid())
-		return event->pmu == &pmu;
-
-	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		if (event->pmu == &x86_pmu.hybrid_pmu[i].pmu)
-			return true;
-	}
+	/*
+	 * For a non-hybrid platforms, the type of X86 pmu is
+	 * always PERF_TYPE_RAW.
+	 * For a hybrid platform, the PERF_PMU_CAP_EXTENDED_HW_TYPE
+	 * is a unique capability for the X86 PMU.
+	 * Use them to detect a X86 event.
+	 */
+	if (event->pmu->type == PERF_TYPE_RAW ||
+	    event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE)
+		return true;
 
 	return false;
 }
@@ -1298,6 +1307,15 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 	if (cpuc->n_added) {
 		int n_running = cpuc->n_events - cpuc->n_added;
+
+		/*
+		 * The late setup (after counters are scheduled)
+		 * is required for some cases, e.g., PEBS counters
+		 * snapshotting. Because an accurate counter index
+		 * is needed.
+		 */
+		static_call_cond(x86_pmu_late_setup)();
+
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -1410,14 +1428,14 @@ int x86_perf_event_set_period(struct perf_event *event)
 	 */
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	wrmsrq(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
 
 	/*
 	 * Sign extend the Merge event counter's upper 16 bits since
 	 * we currently declare a 48-bit counter width
 	 */
 	if (is_counter_pair(hwc))
-		wrmsrl(x86_pmu_event_addr(idx + 1), 0xffff);
+		wrmsrq(x86_pmu_event_addr(idx + 1), 0xffff);
 
 	perf_event_update_userpage(event);
 
@@ -1540,10 +1558,10 @@ void perf_event_print_debug(void)
 		return;
 
 	if (x86_pmu.version >= 2) {
-		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
-		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
-		rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
-		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+		rdmsrq(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
+		rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
+		rdmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
+		rdmsrq(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
 
 		pr_info("\n");
 		pr_info("CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
@@ -1551,19 +1569,19 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
 		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
 		if (pebs_constraints) {
-			rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
+			rdmsrq(MSR_IA32_PEBS_ENABLE, pebs);
 			pr_info("CPU#%d: pebs:       %016llx\n", cpu, pebs);
 		}
 		if (x86_pmu.lbr_nr) {
-			rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+			rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 			pr_info("CPU#%d: debugctl:   %016llx\n", cpu, debugctl);
 		}
 	}
 	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
 	for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
-		rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
-		rdmsrl(x86_pmu_event_addr(idx), pmc_count);
+		rdmsrq(x86_pmu_config_addr(idx), pmc_ctrl);
+		rdmsrq(x86_pmu_event_addr(idx), pmc_count);
 
 		prev_left = per_cpu(pmc_prev_left[idx], cpu);
 
@@ -1577,7 +1595,7 @@ void perf_event_print_debug(void)
 	for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
+		rdmsrq(x86_pmu_fixed_ctr_addr(idx), pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
@@ -1673,6 +1691,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	struct cpu_hw_events *cpuc;
 	struct perf_event *event;
 	int idx, handled = 0;
+	u64 last_period;
 	u64 val;
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1692,6 +1711,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 		event = cpuc->events[idx];
+		last_period = event->hw.last_period;
 
 		val = static_call(x86_pmu_update)(event);
 		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1705,12 +1725,11 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		if (!static_call(x86_pmu_set_period)(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
 		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	if (handled)
@@ -2028,13 +2047,19 @@ static void x86_pmu_static_call_update(void)
 	static_call_update(x86_pmu_stop_scheduling, x86_pmu.stop_scheduling);
 
 	static_call_update(x86_pmu_sched_task, x86_pmu.sched_task);
-	static_call_update(x86_pmu_swap_task_ctx, x86_pmu.swap_task_ctx);
 
 	static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs);
 	static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases);
 
 	static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs);
 	static_call_update(x86_pmu_filter, x86_pmu.filter);
+
+	static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
+
+	static_call_update(x86_pmu_pebs_enable, x86_pmu.pebs_enable);
+	static_call_update(x86_pmu_pebs_disable, x86_pmu.pebs_disable);
+	static_call_update(x86_pmu_pebs_enable_all, x86_pmu.pebs_enable_all);
+	static_call_update(x86_pmu_pebs_disable_all, x86_pmu.pebs_disable_all);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
@@ -2485,9 +2510,9 @@ void perf_clear_dirty_counters(void)
 			if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
 				continue;
 
-			wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
+			wrmsrq(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
 		} else {
-			wrmsrl(x86_pmu_event_addr(i), 0);
+			wrmsrq(x86_pmu_event_addr(i), 0);
 		}
 	}
 
@@ -2625,15 +2650,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
-static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
-{
-	static_call_cond(x86_pmu_sched_task)(pmu_ctx, sched_in);
-}
-
-static void x86_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
-				  struct perf_event_pmu_context *next_epc)
+static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			       struct task_struct *task, bool sched_in)
 {
-	static_call_cond(x86_pmu_swap_task_ctx)(prev_epc, next_epc);
+	static_call_cond(x86_pmu_sched_task)(pmu_ctx, task, sched_in);
 }
 
 void perf_check_microcode(void)
@@ -2700,7 +2720,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
 	.aux_output_match	= x86_pmu_aux_output_match,
@@ -2798,8 +2817,15 @@ static unsigned long get_segment_base(unsigned int segment)
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 		struct ldt_struct *ldt;
 
+		/*
+		 * If we're not in a valid context with a real (not just lazy)
+		 * user mm, then don't even try.
+		 */
+		if (!nmi_uaccess_okay())
+			return 0;
+
 		/* IRQs are off, so this synchronizes with smp_store_release */
-		ldt = READ_ONCE(current->active_mm->context.ldt);
+		ldt = smp_load_acquire(&current->mm->context.ldt);
 		if (!ldt || idx >= ldt->nr_entries)
 			return 0;
 
@@ -2844,7 +2870,7 @@ static bool is_uprobe_at_func_entry(struct pt_regs *regs)
 		return true;
 
 	/* endbr64 (64-bit only) */
-	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+	if (user_64bit_mode(regs) && is_endbr((u32 *)auprobe->insn))
 		return true;
 
 	return false;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8f78b0c900ef..61da6b8a3d51 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -17,6 +17,7 @@
 
 #include <linux/sizes.h>
 #include <asm/perf_event.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -36,7 +37,7 @@ enum {
 	BTS_STATE_ACTIVE,
 };
 
-static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
+static struct bts_ctx __percpu *bts_ctx;
 
 #define BTS_RECORD_SIZE		24
 #define BTS_SAFETY_MARGIN	4080
@@ -58,7 +59,7 @@ struct bts_buffer {
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
-	struct bts_phys	buf[];
+	struct bts_phys	buf[] __counted_by(nr_bufs);
 };
 
 static struct pmu bts_pmu;
@@ -80,54 +81,54 @@ static void *
 bts_buffer_setup_aux(struct perf_event *event, void **pages,
 		     int nr_pages, bool overwrite)
 {
-	struct bts_buffer *buf;
+	struct bts_buffer *bb;
 	struct page *page;
 	int cpu = event->cpu;
 	int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
 	unsigned long offset;
 	size_t size = nr_pages << PAGE_SHIFT;
-	int pg, nbuf, pad;
+	int pg, nr_buf, pad;
 
 	/* count all the high order buffers */
-	for (pg = 0, nbuf = 0; pg < nr_pages;) {
+	for (pg = 0, nr_buf = 0; pg < nr_pages;) {
 		page = virt_to_page(pages[pg]);
 		pg += buf_nr_pages(page);
-		nbuf++;
+		nr_buf++;
 	}
 
 	/*
 	 * to avoid interrupts in overwrite mode, only allow one physical
 	 */
-	if (overwrite && nbuf > 1)
+	if (overwrite && nr_buf > 1)
 		return NULL;
 
-	buf = kzalloc_node(offsetof(struct bts_buffer, buf[nbuf]), GFP_KERNEL, node);
-	if (!buf)
+	bb = kzalloc_node(struct_size(bb, buf, nr_buf), GFP_KERNEL, node);
+	if (!bb)
 		return NULL;
 
-	buf->nr_pages = nr_pages;
-	buf->nr_bufs = nbuf;
-	buf->snapshot = overwrite;
-	buf->data_pages = pages;
-	buf->real_size = size - size % BTS_RECORD_SIZE;
+	bb->nr_pages = nr_pages;
+	bb->nr_bufs = nr_buf;
+	bb->snapshot = overwrite;
+	bb->data_pages = pages;
+	bb->real_size = size - size % BTS_RECORD_SIZE;
 
-	for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) {
+	for (pg = 0, nr_buf = 0, offset = 0, pad = 0; nr_buf < bb->nr_bufs; nr_buf++) {
 		unsigned int __nr_pages;
 
 		page = virt_to_page(pages[pg]);
 		__nr_pages = buf_nr_pages(page);
-		buf->buf[nbuf].page = page;
-		buf->buf[nbuf].offset = offset;
-		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
-		buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement;
-		pad = buf->buf[nbuf].size % BTS_RECORD_SIZE;
-		buf->buf[nbuf].size -= pad;
+		bb->buf[nr_buf].page = page;
+		bb->buf[nr_buf].offset = offset;
+		bb->buf[nr_buf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
+		bb->buf[nr_buf].size = buf_size(page) - bb->buf[nr_buf].displacement;
+		pad = bb->buf[nr_buf].size % BTS_RECORD_SIZE;
+		bb->buf[nr_buf].size -= pad;
 
 		pg += __nr_pages;
 		offset += __nr_pages << PAGE_SHIFT;
 	}
 
-	return buf;
+	return bb;
 }
 
 static void bts_buffer_free_aux(void *data)
@@ -135,25 +136,25 @@ static void bts_buffer_free_aux(void *data)
 	kfree(data);
 }
 
-static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx)
+static unsigned long bts_buffer_offset(struct bts_buffer *bb, unsigned int idx)
 {
-	return buf->buf[idx].offset + buf->buf[idx].displacement;
+	return bb->buf[idx].offset + bb->buf[idx].displacement;
 }
 
 static void
-bts_config_buffer(struct bts_buffer *buf)
+bts_config_buffer(struct bts_buffer *bb)
 {
 	int cpu = raw_smp_processor_id();
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	struct bts_phys *phys = &buf->buf[buf->cur_buf];
+	struct bts_phys *phys = &bb->buf[bb->cur_buf];
 	unsigned long index, thresh = 0, end = phys->size;
 	struct page *page = phys->page;
 
-	index = local_read(&buf->head);
+	index = local_read(&bb->head);
 
-	if (!buf->snapshot) {
-		if (buf->end < phys->offset + buf_size(page))
-			end = buf->end - phys->offset - phys->displacement;
+	if (!bb->snapshot) {
+		if (bb->end < phys->offset + buf_size(page))
+			end = bb->end - phys->offset - phys->displacement;
 
 		index -= phys->offset + phys->displacement;
 
@@ -168,7 +169,7 @@ bts_config_buffer(struct bts_buffer *buf)
 	ds->bts_buffer_base = (u64)(long)page_address(page) + phys->displacement;
 	ds->bts_index = ds->bts_buffer_base + index;
 	ds->bts_absolute_maximum = ds->bts_buffer_base + end;
-	ds->bts_interrupt_threshold = !buf->snapshot
+	ds->bts_interrupt_threshold = !bb->snapshot
 		? ds->bts_buffer_base + thresh
 		: ds->bts_absolute_maximum + BTS_RECORD_SIZE;
 }
@@ -184,16 +185,16 @@ static void bts_update(struct bts_ctx *bts)
 {
 	int cpu = raw_smp_processor_id();
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *bb = perf_get_aux(&bts->handle);
 	unsigned long index = ds->bts_index - ds->bts_buffer_base, old, head;
 
-	if (!buf)
+	if (!bb)
 		return;
 
-	head = index + bts_buffer_offset(buf, buf->cur_buf);
-	old = local_xchg(&buf->head, head);
+	head = index + bts_buffer_offset(bb, bb->cur_buf);
+	old = local_xchg(&bb->head, head);
 
-	if (!buf->snapshot) {
+	if (!bb->snapshot) {
 		if (old == head)
 			return;
 
@@ -205,9 +206,9 @@ static void bts_update(struct bts_ctx *bts)
 		 * old and head are always in the same physical buffer, so we
 		 * can subtract them to get the data size.
 		 */
-		local_add(head - old, &buf->data_size);
+		local_add(head - old, &bb->data_size);
 	} else {
-		local_set(&buf->data_size, head);
+		local_set(&bb->data_size, head);
 	}
 
 	/*
@@ -218,7 +219,7 @@ static void bts_update(struct bts_ctx *bts)
 }
 
 static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle);
 
 /*
  * Ordering PMU callbacks wrt themselves and the PMI is done by means
@@ -231,18 +232,18 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 
 static void __bts_event_start(struct perf_event *event)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
+	struct bts_buffer *bb = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
-	if (!buf->snapshot)
+	if (!bb->snapshot)
 		config |= ARCH_PERFMON_EVENTSEL_INT;
 	if (!event->attr.exclude_kernel)
 		config |= ARCH_PERFMON_EVENTSEL_OS;
 	if (!event->attr.exclude_user)
 		config |= ARCH_PERFMON_EVENTSEL_USR;
 
-	bts_config_buffer(buf);
+	bts_config_buffer(bb);
 
 	/*
 	 * local barrier to make sure that ds configuration made it
@@ -260,14 +261,14 @@ static void __bts_event_start(struct perf_event *event)
 static void bts_event_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf;
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
+	struct bts_buffer *bb;
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
+	bb = perf_aux_output_begin(&bts->handle, event);
+	if (!bb)
 		goto fail_stop;
 
-	if (bts_buffer_reset(buf, &bts->handle))
+	if (bts_buffer_reset(bb, &bts->handle))
 		goto fail_end_stop;
 
 	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
@@ -290,7 +291,7 @@ fail_stop:
 
 static void __bts_event_stop(struct perf_event *event, int state)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
 	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
 	WRITE_ONCE(bts->state, state);
@@ -305,28 +306,28 @@ static void __bts_event_stop(struct perf_event *event, int state)
 static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = NULL;
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
+	struct bts_buffer *bb = NULL;
 	int state = READ_ONCE(bts->state);
 
 	if (state == BTS_STATE_ACTIVE)
 		__bts_event_stop(event, BTS_STATE_STOPPED);
 
 	if (state != BTS_STATE_STOPPED)
-		buf = perf_get_aux(&bts->handle);
+		bb = perf_get_aux(&bts->handle);
 
 	event->hw.state |= PERF_HES_STOPPED;
 
 	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
 
-		if (buf) {
-			if (buf->snapshot)
+		if (bb) {
+			if (bb->snapshot)
 				bts->handle.head =
-					local_xchg(&buf->data_size,
-						   buf->nr_pages << PAGE_SHIFT);
+					local_xchg(&bb->data_size,
+						   bb->nr_pages << PAGE_SHIFT);
 			perf_aux_output_end(&bts->handle,
-			                    local_xchg(&buf->data_size, 0));
+					    local_xchg(&bb->data_size, 0));
 		}
 
 		cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
@@ -338,9 +339,14 @@ static void bts_event_stop(struct perf_event *event, int flags)
 
 void intel_bts_enable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	int state = READ_ONCE(bts->state);
+	struct bts_ctx *bts;
+	int state;
+
+	if (!bts_ctx)
+		return;
 
+	bts = this_cpu_ptr(bts_ctx);
+	state = READ_ONCE(bts->state);
 	/*
 	 * Here we transition from INACTIVE to ACTIVE;
 	 * if we instead are STOPPED from the interrupt handler,
@@ -358,7 +364,12 @@ void intel_bts_enable_local(void)
 
 void intel_bts_disable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts;
+
+	if (!bts_ctx)
+		return;
+
+	bts = this_cpu_ptr(bts_ctx);
 
 	/*
 	 * Here we transition from ACTIVE to INACTIVE;
@@ -372,19 +383,19 @@ void intel_bts_disable_local(void)
 }
 
 static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle)
 {
 	unsigned long head, space, next_space, pad, gap, skip, wakeup;
 	unsigned int next_buf;
 	struct bts_phys *phys, *next_phys;
 	int ret;
 
-	if (buf->snapshot)
+	if (bb->snapshot)
 		return 0;
 
-	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
+	head = handle->head & ((bb->nr_pages << PAGE_SHIFT) - 1);
 
-	phys = &buf->buf[buf->cur_buf];
+	phys = &bb->buf[bb->cur_buf];
 	space = phys->offset + phys->displacement + phys->size - head;
 	pad = space;
 	if (space > handle->size) {
@@ -393,10 +404,10 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 	}
 	if (space <= BTS_SAFETY_MARGIN) {
 		/* See if next phys buffer has more space */
-		next_buf = buf->cur_buf + 1;
-		if (next_buf >= buf->nr_bufs)
+		next_buf = bb->cur_buf + 1;
+		if (next_buf >= bb->nr_bufs)
 			next_buf = 0;
-		next_phys = &buf->buf[next_buf];
+		next_phys = &bb->buf[next_buf];
 		gap = buf_size(phys->page) - phys->displacement - phys->size +
 		      next_phys->displacement;
 		skip = pad + gap;
@@ -421,8 +432,8 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 				 * anymore, so we must not be racing with
 				 * bts_update().
 				 */
-				buf->cur_buf = next_buf;
-				local_set(&buf->head, head);
+				bb->cur_buf = next_buf;
+				local_set(&bb->head, head);
 			}
 		}
 	}
@@ -435,7 +446,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 		space -= space % BTS_RECORD_SIZE;
 	}
 
-	buf->end = head + space;
+	bb->end = head + space;
 
 	/*
 	 * If we have no space, the lost notification would have been sent when
@@ -450,12 +461,17 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 int intel_bts_interrupt(void)
 {
 	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct perf_event *event = bts->handle.event;
-	struct bts_buffer *buf;
+	struct bts_ctx *bts;
+	struct perf_event *event;
+	struct bts_buffer *bb;
 	s64 old_head;
 	int err = -ENOSPC, handled = 0;
 
+	if (!bts_ctx)
+		return 0;
+
+	bts = this_cpu_ptr(bts_ctx);
+	event = bts->handle.event;
 	/*
 	 * The only surefire way of knowing if this NMI is ours is by checking
 	 * the write ptr against the PMI threshold.
@@ -470,8 +486,8 @@ int intel_bts_interrupt(void)
 	if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
 		return handled;
 
-	buf = perf_get_aux(&bts->handle);
-	if (!buf)
+	bb = perf_get_aux(&bts->handle);
+	if (!bb)
 		return handled;
 
 	/*
@@ -479,26 +495,26 @@ int intel_bts_interrupt(void)
 	 * there's no other way of telling, because the pointer will
 	 * keep moving
 	 */
-	if (buf->snapshot)
+	if (bb->snapshot)
 		return 0;
 
-	old_head = local_read(&buf->head);
+	old_head = local_read(&bb->head);
 	bts_update(bts);
 
 	/* no new data */
-	if (old_head == local_read(&buf->head))
+	if (old_head == local_read(&bb->head))
 		return handled;
 
-	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
+	perf_aux_output_end(&bts->handle, local_xchg(&bb->data_size, 0));
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (buf)
-		err = bts_buffer_reset(buf, &bts->handle);
+	bb = perf_aux_output_begin(&bts->handle, event);
+	if (bb)
+		err = bts_buffer_reset(bb, &bts->handle);
 
 	if (err) {
 		WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
 
-		if (buf) {
+		if (bb) {
 			/*
 			 * BTS_STATE_STOPPED should be visible before
 			 * cleared handle::event
@@ -518,7 +534,7 @@ static void bts_event_del(struct perf_event *event, int mode)
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -559,7 +575,7 @@ static int bts_event_init(struct perf_event *event)
 	 * to the user in a zero-copy fashion.
 	 */
 	if (event->attr.exclude_kernel) {
-		ret = perf_allow_kernel(&event->attr);
+		ret = perf_allow_kernel();
 		if (ret)
 			return ret;
 	}
@@ -584,7 +600,11 @@ static void bts_event_read(struct perf_event *event)
 
 static __init int bts_init(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
+	if (!boot_cpu_has(X86_FEATURE_DTES64))
+		return -ENODEV;
+
+	x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
+	if (!x86_pmu.bts)
 		return -ENODEV;
 
 	if (boot_cpu_has(X86_FEATURE_PTI)) {
@@ -605,6 +625,10 @@ static __init int bts_init(void)
 		return -ENODEV;
 	}
 
+	bts_ctx = alloc_percpu(struct bts_ctx);
+	if (!bts_ctx)
+		return -ENOMEM;
+
 	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
 				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cdcebf30468a..466283326630 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -23,6 +23,7 @@
 #include <asm/intel_pt.h>
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -2224,6 +2225,18 @@ static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(topdown-fe-bound,       td_fe_bound_skt,        "event=0x9c,umask=0x01");
+EVENT_ATTR_STR(topdown-retiring,       td_retiring_skt,        "event=0xc2,umask=0x02");
+EVENT_ATTR_STR(topdown-be-bound,       td_be_bound_skt,        "event=0xa4,umask=0x02");
+
+static struct attribute *skt_events_attrs[] = {
+	EVENT_PTR(td_fe_bound_skt),
+	EVENT_PTR(td_retiring_skt),
+	EVENT_PTR(td_bad_spec_cmt),
+	EVENT_PTR(td_be_bound_skt),
+	NULL,
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -2285,7 +2298,7 @@ static __always_inline void __intel_pmu_disable_all(bool bts)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
 	if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
@@ -2294,7 +2307,7 @@ static __always_inline void __intel_pmu_disable_all(bool bts)
 static __always_inline void intel_pmu_disable_all(void)
 {
 	__intel_pmu_disable_all(true);
-	intel_pmu_pebs_disable_all();
+	static_call_cond(x86_pmu_pebs_disable_all)();
 	intel_pmu_lbr_disable_all();
 }
 
@@ -2306,11 +2319,11 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 	intel_pmu_lbr_enable_all(pmi);
 
 	if (cpuc->fixed_ctrl_val != cpuc->active_fixed_ctrl_val) {
-		wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, cpuc->fixed_ctrl_val);
+		wrmsrq(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, cpuc->fixed_ctrl_val);
 		cpuc->active_fixed_ctrl_val = cpuc->fixed_ctrl_val;
 	}
 
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL,
 	       intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
 
 	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
@@ -2326,7 +2339,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 
 static void intel_pmu_enable_all(int added)
 {
-	intel_pmu_pebs_enable_all();
+	static_call_cond(x86_pmu_pebs_enable_all)();
 	__intel_pmu_enable_all(added, false);
 }
 
@@ -2426,12 +2439,12 @@ static void intel_pmu_nhm_workaround(void)
 	}
 
 	for (i = 0; i < 4; i++) {
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
-		wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
+		wrmsrq(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
+		wrmsrq(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
 	}
 
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
 
 	for (i = 0; i < 4; i++) {
 		event = cpuc->events[i];
@@ -2441,7 +2454,7 @@ static void intel_pmu_nhm_workaround(void)
 			__x86_pmu_enable_event(&event->hw,
 					ARCH_PERFMON_EVENTSEL_ENABLE);
 		} else
-			wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
+			wrmsrq(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
 	}
 }
 
@@ -2458,7 +2471,7 @@ static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on)
 
 	if (cpuc->tfa_shadow != val) {
 		cpuc->tfa_shadow = val;
-		wrmsrl(MSR_TSX_FORCE_ABORT, val);
+		wrmsrq(MSR_TSX_FORCE_ABORT, val);
 	}
 }
 
@@ -2489,14 +2502,14 @@ static inline u64 intel_pmu_get_status(void)
 {
 	u64 status;
 
-	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
 
 	return status;
 }
 
 static inline void intel_pmu_ack_status(u64 ack)
 {
-	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
 static inline bool event_is_checkpointed(struct perf_event *event)
@@ -2583,7 +2596,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	 * so we don't trigger the event without PEBS bit set.
 	 */
 	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
+		static_call(x86_pmu_pebs_disable)(event);
 }
 
 static void intel_pmu_assign_event(struct perf_event *event, int idx)
@@ -2603,6 +2616,9 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
 static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2619,15 +2635,15 @@ static int icl_set_topdown_event_period(struct perf_event *event)
 	 * Don't need to clear them again.
 	 */
 	if (left == x86_pmu.max_period) {
-		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
-		wrmsrl(MSR_PERF_METRICS, 0);
+		wrmsrq(MSR_CORE_PERF_FIXED_CTR3, 0);
+		wrmsrq(MSR_PERF_METRICS, 0);
 		hwc->saved_slots = 0;
 		hwc->saved_metric = 0;
 	}
 
 	if ((hwc->saved_slots) && is_slots_event(event)) {
-		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
-		wrmsrl(MSR_PERF_METRICS, hwc->saved_metric);
+		wrmsrq(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
+		wrmsrq(MSR_PERF_METRICS, hwc->saved_metric);
 	}
 
 	perf_event_update_userpage(event);
@@ -2714,7 +2730,7 @@ static void update_saved_topdown_regs(struct perf_event *event, u64 slots,
  * modify by a NMI. PMU has to be disabled before calling this function.
  */
 
-static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
+static u64 intel_update_topdown_event(struct perf_event *event, int metric_end, u64 *val)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
@@ -2722,13 +2738,24 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	bool reset = true;
 	int idx;
 
-	/* read Fixed counter 3 */
-	rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
-	if (!slots)
-		return 0;
+	if (!val) {
+		/* read Fixed counter 3 */
+		slots = rdpmc(3 | INTEL_PMC_FIXED_RDPMC_BASE);
+		if (!slots)
+			return 0;
 
-	/* read PERF_METRICS */
-	rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+		/* read PERF_METRICS */
+		metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+	} else {
+		slots = val[0];
+		metrics = val[1];
+		/*
+		 * Don't reset the PERF_METRICS and Fixed counter 3
+		 * for each PEBS record read. Utilize the RDPMC metrics
+		 * clear mode.
+		 */
+		reset = false;
+	}
 
 	for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) {
 		if (!is_topdown_idx(idx))
@@ -2762,8 +2789,8 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 
 	if (reset) {
 		/* The fixed counter 3 has to be written before the PERF_METRICS. */
-		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
-		wrmsrl(MSR_PERF_METRICS, 0);
+		wrmsrq(MSR_CORE_PERF_FIXED_CTR3, 0);
+		wrmsrq(MSR_PERF_METRICS, 0);
 		if (event)
 			update_saved_topdown_regs(event, 0, 0, metric_end);
 	}
@@ -2771,36 +2798,47 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	return slots;
 }
 
-static u64 icl_update_topdown_event(struct perf_event *event)
+static u64 icl_update_topdown_event(struct perf_event *event, u64 *val)
 {
 	return intel_update_topdown_event(event, INTEL_PMC_IDX_METRIC_BASE +
-						 x86_pmu.num_topdown_events - 1);
+						 x86_pmu.num_topdown_events - 1,
+					  val);
 }
 
-DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
+DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
 
-static void intel_pmu_read_topdown_event(struct perf_event *event)
+static void intel_pmu_read_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) ||
+	    is_pebs_counter_event_group(event)) {
+		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+		bool pmu_enabled = cpuc->enabled;
 
-	/* Only need to call update_topdown_event() once for group read. */
-	if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
-	    !is_slots_event(event))
-		return;
+		/* Only need to call update_topdown_event() once for group read. */
+		if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ))
+			return;
 
-	perf_pmu_disable(event->pmu);
-	static_call(intel_pmu_update_topdown_event)(event);
-	perf_pmu_enable(event->pmu);
-}
+		cpuc->enabled = 0;
+		if (pmu_enabled)
+			intel_pmu_disable_all();
 
-static void intel_pmu_read_event(struct perf_event *event)
-{
-	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
-		intel_pmu_auto_reload_read(event);
-	else if (is_topdown_count(event))
-		intel_pmu_read_topdown_event(event);
-	else
-		x86_perf_event_update(event);
+		/*
+		 * If the PEBS counters snapshotting is enabled,
+		 * the topdown event is available in PEBS records.
+		 */
+		if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+			static_call(intel_pmu_update_topdown_event)(event, NULL);
+		else
+			intel_pmu_drain_pebs_buffer();
+
+		cpuc->enabled = pmu_enabled;
+		if (pmu_enabled)
+			intel_pmu_enable_all(0);
+
+		return;
+	}
+
+	x86_perf_event_update(event);
 }
 
 static void intel_pmu_enable_fixed(struct perf_event *event)
@@ -2858,6 +2896,52 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	cpuc->fixed_ctrl_val |= bits;
 }
 
+static void intel_pmu_config_acr(int idx, u64 mask, u32 reload)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int msr_b, msr_c;
+
+	if (!mask && !cpuc->acr_cfg_b[idx])
+		return;
+
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		msr_b = MSR_IA32_PMC_V6_GP0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_GP0_CFG_C;
+	} else {
+		msr_b = MSR_IA32_PMC_V6_FX0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_FX0_CFG_C;
+		idx -= INTEL_PMC_IDX_FIXED;
+	}
+
+	if (cpuc->acr_cfg_b[idx] != mask) {
+		wrmsrl(msr_b + x86_pmu.addr_offset(idx, false), mask);
+		cpuc->acr_cfg_b[idx] = mask;
+	}
+	/* Only need to update the reload value when there is a valid config value. */
+	if (mask && cpuc->acr_cfg_c[idx] != reload) {
+		wrmsrl(msr_c + x86_pmu.addr_offset(idx, false), reload);
+		cpuc->acr_cfg_c[idx] = reload;
+	}
+}
+
+static void intel_pmu_enable_acr(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_acr_event_group(event) || !event->attr.config2) {
+		/*
+		 * The disable doesn't clear the ACR CFG register.
+		 * Check and clear the ACR CFG register.
+		 */
+		intel_pmu_config_acr(hwc->idx, 0, 0);
+		return;
+	}
+
+	intel_pmu_config_acr(hwc->idx, hwc->config1, -hwc->sample_period);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
+
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2865,16 +2949,19 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
+		static_call(x86_pmu_pebs_enable)(event);
 
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		if (branch_sample_counters(event))
 			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
+		static_call_cond(intel_pmu_enable_acr_event)(event);
 		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+		static_call_cond(intel_pmu_enable_acr_event)(event);
+		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
 		break;
@@ -2892,12 +2979,51 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	}
 }
 
+static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
+{
+	struct perf_event *event, *leader;
+	int i, j, idx;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		leader = cpuc->event_list[i];
+		if (!is_acr_event_group(leader))
+			continue;
+
+		/* The ACR events must be contiguous. */
+		for (j = i; j < cpuc->n_events; j++) {
+			event = cpuc->event_list[j];
+			if (event->group_leader != leader->group_leader)
+				break;
+			for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
+				if (WARN_ON_ONCE(i + idx > cpuc->n_events))
+					return;
+				__set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
+			}
+		}
+		i = j - 1;
+	}
+}
+
+void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!cpuc->n_late_setup)
+		return;
+
+	intel_pmu_pebs_late_setup(cpuc);
+	intel_pmu_acr_late_setup(cpuc);
+}
+
 static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
 	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
 }
 
 /*
@@ -2915,7 +3041,7 @@ int intel_pmu_save_and_restart(struct perf_event *event)
 	 */
 	if (unlikely(event_is_checkpointed(event))) {
 		/* No race with NMIs because the counter should not be armed */
-		wrmsrl(event->hw.event_base, 0);
+		wrmsrq(event->hw.event_base, 0);
 		local64_set(&event->hw.prev_count, 0);
 	}
 	return static_call(x86_pmu_set_period)(event);
@@ -2932,7 +3058,7 @@ static int intel_pmu_set_period(struct perf_event *event)
 static u64 intel_pmu_update(struct perf_event *event)
 {
 	if (unlikely(is_topdown_count(event)))
-		return static_call(intel_pmu_update_topdown_event)(event);
+		return static_call(intel_pmu_update_topdown_event)(event, NULL);
 
 	return x86_perf_event_update(event);
 }
@@ -2954,13 +3080,13 @@ static void intel_pmu_reset(void)
 	pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
 
 	for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
-		wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
-		wrmsrl_safe(x86_pmu_event_addr(idx),  0ull);
+		wrmsrq_safe(x86_pmu_config_addr(idx), 0ull);
+		wrmsrq_safe(x86_pmu_event_addr(idx),  0ull);
 	}
 	for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		wrmsrl_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
+		wrmsrq_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
 	}
 
 	if (ds)
@@ -2969,7 +3095,7 @@ static void intel_pmu_reset(void)
 	/* Ack all overflows and disable fixed counters */
 	if (x86_pmu.version >= 2) {
 		intel_pmu_ack_status(intel_pmu_get_status());
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+		wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 	}
 
 	/* Reset LBRs and LBR freezing */
@@ -3013,8 +3139,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
 			continue;
 
 		perf_sample_data_init(data, 0, event->hw.last_period);
-		if (perf_event_overflow(event, data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, data, regs);
 
 		/* Inject one fake event is enough. */
 		break;
@@ -3027,7 +3152,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int bit;
 	int handled = 0;
-	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
 
 	inc_irq_stat(apic_perf_irqs);
 
@@ -3070,8 +3194,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 		handled++;
 		x86_pmu_handle_guest_pebs(regs, &data);
-		x86_pmu.drain_pebs(regs, &data);
-		status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
+		static_call(x86_pmu_drain_pebs)(regs, &data);
 
 		/*
 		 * PMI throttle may be triggered, which stops the PEBS event.
@@ -3081,7 +3204,16 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		 * Update the MSR if pebs_enabled is changed.
 		 */
 		if (pebs_enabled != cpuc->pebs_enabled)
-			wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+			wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+		/*
+		 * Above PEBS handler (PEBS counters snapshotting) has updated fixed
+		 * counter 3 and perf metrics counts if they are in counter group,
+		 * unnecessary to update again.
+		 */
+		if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] &&
+		    is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS]))
+			status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT;
 	}
 
 	/*
@@ -3098,9 +3230,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
 		handled++;
-		static_call(intel_pmu_update_topdown_event)(NULL);
+		static_call(intel_pmu_update_topdown_event)(NULL, NULL);
 	}
 
+	status &= hybrid(cpuc->pmu, intel_ctrl);
+
 	/*
 	 * Checkpointed counters can lead to 'spurious' PMIs because the
 	 * rollback caused by the PMI will have cleared the overflow status
@@ -3110,22 +3244,45 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
+		u64 last_period;
 
 		handled++;
 
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
+		/*
+		 * There may be unprocessed PEBS records in the PEBS buffer,
+		 * which still stores the previous values.
+		 * Process those records first before handling the latest value.
+		 * For example,
+		 * A is a regular counter
+		 * B is a PEBS event which reads A
+		 * C is a PEBS event
+		 *
+		 * The following can happen:
+		 * B-assist			A=1
+		 * C				A=2
+		 * B-assist			A=3
+		 * A-overflow-PMI		A=4
+		 * C-assist-PMI (PEBS buffer)	A=5
+		 *
+		 * The PEBS buffer has to be drained before handling the A-PMI
+		 */
+		if (is_pebs_counter_event_group(event))
+			x86_pmu.drain_pebs(regs, &data);
+
+		last_period = event->hw.last_period;
+
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
 		if (has_branch_stack(event))
 			intel_pmu_lbr_save_brstack(&data, cpuc, event);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	return handled;
@@ -3687,10 +3844,9 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	if (cpuc->excl_cntrs)
 		return intel_get_excl_constraints(cpuc, event, idx, c2);
 
-	/* Not all counters support the branch counter feature. */
-	if (branch_sample_counters(event)) {
+	if (event->hw.dyn_constraint != ~0ULL) {
 		c2 = dyn_constraint(cpuc, c2, idx);
-		c2->idxmsk64 &= x86_pmu.lbr_counters;
+		c2->idxmsk64 &= event->hw.dyn_constraint;
 		c2->weight = hweight64(c2->idxmsk64);
 	}
 
@@ -3952,6 +4108,118 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
+static inline bool intel_pmu_has_acr(struct pmu *pmu)
+{
+	return !!hybrid(pmu, acr_cause_mask64);
+}
+
+static bool intel_pmu_is_acr_group(struct perf_event *event)
+{
+	/* The group leader has the ACR flag set */
+	if (is_acr_event_group(event))
+		return true;
+
+	/* The acr_mask is set */
+	if (event->attr.config2)
+		return true;
+
+	return false;
+}
+
+static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event,
+						 u64 *cause_mask, int *num)
+{
+	event->hw.dyn_constraint &= hybrid(event->pmu, acr_cntr_mask64);
+	*cause_mask |= event->attr.config2;
+	*num += 1;
+}
+
+static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event,
+						   int idx, u64 cause_mask)
+{
+	if (test_bit(idx, (unsigned long *)&cause_mask))
+		event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3963,6 +4231,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
@@ -4007,15 +4281,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		leader = event->group_leader;
 		if (branch_sample_call_stack(leader))
 			return -EINVAL;
-		if (branch_sample_counters(leader))
+		if (branch_sample_counters(leader)) {
 			num++;
+			leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
+		}
 		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
 
 		for_each_sibling_event(sibling, leader) {
 			if (branch_sample_call_stack(sibling))
 				return -EINVAL;
-			if (branch_sample_counters(sibling))
+			if (branch_sample_counters(sibling)) {
 				num++;
+				sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
+			}
 		}
 
 		if (num > fls(x86_pmu.lbr_counters))
@@ -4063,6 +4341,101 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
 	}
 
+	if ((event->attr.sample_type & PERF_SAMPLE_READ) &&
+	    (x86_pmu.intel_cap.pebs_format >= 6) &&
+	    x86_pmu.intel_cap.pebs_baseline &&
+	    is_sampling_event(event) &&
+	    event->attr.precise_ip)
+		event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
+
+	if (intel_pmu_has_acr(event->pmu) && intel_pmu_is_acr_group(event)) {
+		struct perf_event *sibling, *leader = event->group_leader;
+		struct pmu *pmu = event->pmu;
+		bool has_sw_event = false;
+		int num = 0, idx = 0;
+		u64 cause_mask = 0;
+
+		/* Not support perf metrics */
+		if (is_metric_event(event))
+			return -EINVAL;
+
+		/* Not support freq mode */
+		if (event->attr.freq)
+			return -EINVAL;
+
+		/* PDist is not supported */
+		if (event->attr.config2 && event->attr.precise_ip > 2)
+			return -EINVAL;
+
+		/* The reload value cannot exceeds the max period */
+		if (event->attr.sample_period > x86_pmu.max_period)
+			return -EINVAL;
+		/*
+		 * The counter-constraints of each event cannot be finalized
+		 * unless the whole group is scanned. However, it's hard
+		 * to know whether the event is the last one of the group.
+		 * Recalculate the counter-constraints for each event when
+		 * adding a new event.
+		 *
+		 * The group is traversed twice, which may be optimized later.
+		 * In the first round,
+		 * - Find all events which do reload when other events
+		 *   overflow and set the corresponding counter-constraints
+		 * - Add all events, which can cause other events reload,
+		 *   in the cause_mask
+		 * - Error out if the number of events exceeds the HW limit
+		 * - The ACR events must be contiguous.
+		 *   Error out if there are non-X86 events between ACR events.
+		 *   This is not a HW limit, but a SW limit.
+		 *   With the assumption, the intel_pmu_acr_late_setup() can
+		 *   easily convert the event idx to counter idx without
+		 *   traversing the whole event list.
+		 */
+		if (!is_x86_event(leader))
+			return -EINVAL;
+
+		if (leader->attr.config2)
+			intel_pmu_set_acr_cntr_constr(leader, &cause_mask, &num);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader) {
+				if (!is_x86_event(sibling)) {
+					has_sw_event = true;
+					continue;
+				}
+				if (!sibling->attr.config2)
+					continue;
+				if (has_sw_event)
+					return -EINVAL;
+				intel_pmu_set_acr_cntr_constr(sibling, &cause_mask, &num);
+			}
+		}
+		if (leader != event && event->attr.config2) {
+			if (has_sw_event)
+				return -EINVAL;
+			intel_pmu_set_acr_cntr_constr(event, &cause_mask, &num);
+		}
+
+		if (hweight64(cause_mask) > hweight64(hybrid(pmu, acr_cause_mask64)) ||
+		    num > hweight64(hybrid(event->pmu, acr_cntr_mask64)))
+			return -EINVAL;
+		/*
+		 * In the second round, apply the counter-constraints for
+		 * the events which can cause other events reload.
+		 */
+		intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader)
+				intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+		}
+
+		if (leader != event)
+			intel_pmu_set_acr_caused_constr(event, idx, cause_mask);
+
+		leader->hw.flags |= PERF_X86_EVENT_ACR;
+	}
+
 	if ((event->attr.type == PERF_TYPE_HARDWARE) ||
 	    (event->attr.type == PERF_TYPE_HW_CACHE))
 		return 0;
@@ -4162,7 +4535,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (x86_pmu.version < 3)
 		return -EINVAL;
 
-	ret = perf_allow_cpu(&event->attr);
+	ret = perf_allow_cpu();
 	if (ret)
 		return ret;
 
@@ -4210,7 +4583,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		.guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask,
 	};
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return arr;
 
 	/*
@@ -4251,7 +4624,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	arr[pebs_enable] = (struct perf_guest_switch_msr){
 		.msr = MSR_IA32_PEBS_ENABLE,
 		.host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
-		.guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+		.guest = pebs_mask & ~cpuc->intel_ctrl_host_mask & kvm_pmu->pebs_enable,
 	};
 
 	if (arr[pebs_enable].host) {
@@ -4600,9 +4973,9 @@ static int adl_hw_config(struct perf_event *event)
 	return -EOPNOTSUPP;
 }
 
-static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+static enum intel_cpu_type adl_get_hybrid_cpu_type(void)
 {
-	return HYBRID_INTEL_CORE;
+	return INTEL_CPU_TYPE_CORE;
 }
 
 static inline bool erratum_hsw11(struct perf_event *event)
@@ -4808,7 +5181,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 			goto err;
 	}
 
-	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_DYN_CONSTRAINT)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
 		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -4897,7 +5270,7 @@ static inline bool intel_pmu_broken_perf_cap(void)
 	return false;
 }
 
-static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+static void update_pmu_cap(struct pmu *pmu)
 {
 	unsigned int cntr, fixed_cntr, ecx, edx;
 	union cpuid35_eax eax;
@@ -4906,20 +5279,30 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
 
 	if (ebx.split.umask2)
-		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
 	if (ebx.split.eq)
-		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
 
 	if (eax.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
 			    &cntr, &fixed_cntr, &ecx, &edx);
-		pmu->cntr_mask64 = cntr;
-		pmu->fixed_cntr_mask64 = fixed_cntr;
+		hybrid(pmu, cntr_mask64) = cntr;
+		hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
+	}
+
+	if (eax.split.acr_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		/* The mask of the counters which can be reloaded */
+		hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
+
+		/* The mask of the counters which can cause a reload of reloadable counters */
+		hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
 		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
+		rdmsrq(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
 	}
 }
 
@@ -4947,7 +5330,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 
 static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 {
-	u8 cpu_type = get_this_hybrid_cpu_type();
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	enum intel_cpu_type cpu_type = c->topo.intel_type;
 	int i;
 
 	/*
@@ -4956,7 +5340,7 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 	 * on it. There should be a fixup function provided for these
 	 * troublesome CPUs (->get_hybrid_cpu_type).
 	 */
-	if (cpu_type == HYBRID_INTEL_NONE) {
+	if (cpu_type == INTEL_CPU_TYPE_UNKNOWN) {
 		if (x86_pmu.get_hybrid_cpu_type)
 			cpu_type = x86_pmu.get_hybrid_cpu_type();
 		else
@@ -4973,16 +5357,16 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
 		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
+		if (cpu_type == INTEL_CPU_TYPE_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM) {
+		if (cpu_type == INTEL_CPU_TYPE_ATOM) {
 			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
 
-			native_id = get_this_hybrid_cpu_native_id();
-			if (native_id == skt_native_id && pmu_type == hybrid_small)
+			native_id = c->topo.intel_native_model_id;
+			if (native_id == INTEL_ATOM_SKT_NATIVE_ID && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
-			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+			if (native_id == INTEL_ATOM_CMT_NATIVE_ID && pmu_type == hybrid_tiny)
 				return &x86_pmu.hybrid_pmu[i];
 		}
 	}
@@ -5005,7 +5389,7 @@ static bool init_hybrid_pmu(int cpu)
 		goto end;
 
 	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
-		update_pmu_cap(pmu);
+		update_pmu_cap(&pmu->pmu);
 
 	intel_pmu_check_hybrid_pmus(pmu);
 
@@ -5066,7 +5450,7 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics) {
 		union perf_capabilities perf_cap;
 
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
+		rdmsrq(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
 		if (!perf_cap.perf_metrics) {
 			x86_pmu.intel_cap.perf_metrics = 0;
 			x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
@@ -5159,16 +5543,10 @@ static void intel_pmu_cpu_dead(int cpu)
 }
 
 static void intel_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
-				 bool sched_in)
+				 struct task_struct *task, bool sched_in)
 {
 	intel_pmu_pebs_sched_task(pmu_ctx, sched_in);
-	intel_pmu_lbr_sched_task(pmu_ctx, sched_in);
-}
-
-static void intel_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
-				    struct perf_event_pmu_context *next_epc)
-{
-	intel_pmu_lbr_swap_task_ctx(prev_epc, next_epc);
+	intel_pmu_lbr_sched_task(pmu_ctx, task, sched_in);
 }
 
 static int intel_pmu_check_period(struct perf_event *event, u64 value)
@@ -5339,7 +5717,6 @@ static __initconst const struct x86_pmu intel_pmu = {
 
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
-	.swap_task_ctx		= intel_pmu_swap_task_ctx,
 
 	.check_period		= intel_pmu_check_period,
 
@@ -5386,7 +5763,7 @@ static __init void intel_clovertown_quirk(void)
 	 * these chips.
 	 */
 	pr_warn("PEBS disabled due to CPU errata\n");
-	x86_pmu.pebs = 0;
+	x86_pmu.ds_pebs = 0;
 	x86_pmu.pebs_constraints = NULL;
 }
 
@@ -5481,24 +5858,24 @@ static bool check_msr(unsigned long msr, u64 mask)
 	 * matches, this is needed to detect certain hardware emulators
 	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	if (rdmsrl_safe(msr, &val_old))
+	if (rdmsrq_safe(msr, &val_old))
 		return false;
 
 	/*
-	 * Only change the bits which can be updated by wrmsrl.
+	 * Only change the bits which can be updated by wrmsrq.
 	 */
 	val_tmp = val_old ^ mask;
 
 	if (is_lbr_from(msr))
 		val_tmp = lbr_from_signext_quirk_wr(val_tmp);
 
-	if (wrmsrl_safe(msr, val_tmp) ||
-	    rdmsrl_safe(msr, &val_new))
+	if (wrmsrq_safe(msr, val_tmp) ||
+	    rdmsrq_safe(msr, &val_new))
 		return false;
 
 	/*
-	 * Quirk only affects validation in wrmsr(), so wrmsrl()'s value
-	 * should equal rdmsrl()'s even with the quirk.
+	 * Quirk only affects validation in wrmsr(), so wrmsrq()'s value
+	 * should equal rdmsrq()'s even with the quirk.
 	 */
 	if (val_new != val_tmp)
 		return false;
@@ -5509,7 +5886,7 @@ static bool check_msr(unsigned long msr, u64 mask)
 	/* Here it's sure that the MSR can be safely accessed.
 	 * Restore the old value and return.
 	 */
-	wrmsrl(msr, val_old);
+	wrmsrq(msr, val_old);
 
 	return true;
 }
@@ -5874,7 +6251,7 @@ tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 static umode_t
 pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
-	return x86_pmu.pebs ? attr->mode : 0;
+	return x86_pmu.ds_pebs ? attr->mode : 0;
 }
 
 static umode_t
@@ -5905,6 +6282,21 @@ td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return attr->mode;
 }
 
+PMU_FORMAT_ATTR(acr_mask,	"config2:0-63");
+
+static struct attribute *format_acr_attrs[] = {
+	&format_attr_acr_mask.attr,
+	NULL
+};
+
+static umode_t
+acr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+
+	return intel_pmu_has_acr(dev_get_drvdata(dev)) ? attr->mode : 0;
+}
+
 static struct attribute_group group_events_td  = {
 	.name = "events",
 	.is_visible = td_is_visible,
@@ -5947,6 +6339,12 @@ static struct attribute_group group_format_evtsel_ext = {
 	.is_visible = evtsel_ext_is_visible,
 };
 
+static struct attribute_group group_format_acr = {
+	.name       = "format",
+	.attrs      = format_acr_attrs,
+	.is_visible = acr_is_visible,
+};
+
 static struct attribute_group group_default = {
 	.attrs      = intel_pmu_attrs,
 	.is_visible = default_is_visible,
@@ -5961,6 +6359,7 @@ static const struct attribute_group *attr_update[] = {
 	&group_format_extra,
 	&group_format_extra_skl,
 	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	NULL,
 };
@@ -6245,6 +6644,7 @@ static const struct attribute_group *hybrid_attr_update[] = {
 	&group_caps_lbr,
 	&hybrid_group_format_extra,
 	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	&hybrid_group_cpus,
 	NULL,
@@ -6437,6 +6837,7 @@ static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
 	intel_pmu_init_grt(pmu);
 	hybrid(pmu, event_constraints) = intel_skt_event_constraints;
 	hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 }
 
 __init int intel_pmu_init(void)
@@ -6455,15 +6856,21 @@ __init int intel_pmu_init(void)
 	char *name;
 	struct x86_hybrid_pmu *pmu;
 
+	/* Architectural Perfmon was introduced starting with Core "Yonah" */
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
-		case 0x6:
-			return p6_pmu_init();
-		case 0xb:
+		case  6:
+			if (boot_cpu_data.x86_vfm < INTEL_CORE_YONAH)
+				return p6_pmu_init();
+			break;
+		case 11:
 			return knc_pmu_init();
-		case 0xf:
+		case 15:
 			return p4_pmu_init();
 		}
+
+		pr_cont("unsupported CPU family %d model %d ",
+			boot_cpu_data.x86, boot_cpu_data.x86_model);
 		return -ENODEV;
 	}
 
@@ -6491,6 +6898,7 @@ __init int intel_pmu_init(void)
 
 	x86_pmu.pebs_events_mask	= intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
 	x86_pmu.pebs_capable		= PEBS_COUNTER_MASK;
+	x86_pmu.config_mask		= X86_RAW_EVENT_MASK;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
@@ -6507,7 +6915,7 @@ __init int intel_pmu_init(void)
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
 
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+		rdmsrq(MSR_IA32_PERF_CAPABILITIES, capabilities);
 		x86_pmu.intel_cap.capabilities = capabilities;
 	}
 
@@ -6519,7 +6927,7 @@ __init int intel_pmu_init(void)
 	if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
 		intel_pmu_arch_lbr_init();
 
-	intel_ds_init();
+	intel_pebs_init();
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
 
@@ -6530,6 +6938,12 @@ __init int intel_pmu_init(void)
 	}
 
 	/*
+	 * Many features on and after V6 require dynamic constraint,
+	 * e.g., Arch PEBS, ACR.
+	 */
+	if (version >= 6)
+		x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
+	/*
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_vfm) {
@@ -6611,7 +7025,7 @@ __init int intel_pmu_init(void)
 	case INTEL_ATOM_SILVERMONT_D:
 	case INTEL_ATOM_SILVERMONT_MID:
 	case INTEL_ATOM_AIRMONT:
-	case INTEL_ATOM_AIRMONT_MID:
+	case INTEL_ATOM_SILVERMONT_MID2:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -6740,6 +7154,18 @@ __init int intel_pmu_init(void)
 		name = "crestmont";
 		break;
 
+	case INTEL_ATOM_DARKMONT_X:
+		intel_pmu_init_skt(NULL);
+		intel_pmu_pebs_data_source_cmt();
+		x86_pmu.pebs_latency_data = cmt_latency_data;
+		x86_pmu.get_event_constraints = cmt_get_event_constraints;
+		td_attr = skt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = cmt_format_attr;
+		pr_cont("Darkmont events, ");
+		name = "darkmont";
+		break;
+
 	case INTEL_WESTMERE:
 	case INTEL_WESTMERE_EP:
 	case INTEL_WESTMERE_EX:
@@ -7170,8 +7596,17 @@ __init int intel_pmu_init(void)
 		name = "meteorlake_hybrid";
 		break;
 
+	case INTEL_PANTHERLAKE_L:
+		pr_cont("Pantherlake Hybrid events, ");
+		name = "pantherlake_hybrid";
+		goto lnl_common;
+
 	case INTEL_LUNARLAKE_M:
 	case INTEL_ARROWLAKE:
+		pr_cont("Lunarlake Hybrid events, ");
+		name = "lunarlake_hybrid";
+
+	lnl_common:
 		intel_pmu_init_hybrid(hybrid_big_small);
 
 		x86_pmu.pebs_latency_data = lnl_latency_data;
@@ -7193,8 +7628,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_init_skt(&pmu->pmu);
 
 		intel_pmu_pebs_data_source_lnl();
-		pr_cont("Lunarlake Hybrid events, ");
-		name = "lunarlake_hybrid";
 		break;
 
 	case INTEL_ARROWLAKE_H:
@@ -7282,6 +7715,18 @@ __init int intel_pmu_init(void)
 		x86_pmu.attr_update = hybrid_attr_update;
 	}
 
+	/*
+	 * The archPerfmonExt (0x23) includes an enhanced enumeration of
+	 * PMU architectural features with a per-core view. For non-hybrid,
+	 * each core has the same PMU capabilities. It's good enough to
+	 * update the x86_pmu from the booting CPU. For hybrid, the x86_pmu
+	 * is used to keep the common capabilities. Still keep the values
+	 * from the leaf 0xa. The core specific update will be done later
+	 * when a new type is online.
+	 */
+	if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		update_pmu_cap(NULL);
+
 	intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
 				      &x86_pmu.fixed_cntr_mask64,
 				      &x86_pmu.intel_ctrl);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index ae4ec16156bb..ec753e39b007 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -111,6 +111,7 @@
 #include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/msr.h>
 #include "../perf_event.h"
 #include "../probe.h"
 
@@ -320,7 +321,7 @@ static inline u64 cstate_pmu_read_counter(struct perf_event *event)
 {
 	u64 val;
 
-	rdmsrl(event->hw.event_base, val);
+	rdmsrq(event->hw.event_base, val);
 	return val;
 }
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f122882ef278..c0b7ac1c7594 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -10,6 +10,7 @@
 #include <asm/tlbflush.h>
 #include <asm/insn.h>
 #include <asm/io.h>
+#include <asm/msr.h>
 #include <asm/timer.h>
 
 #include "../perf_event.h"
@@ -624,7 +625,7 @@ static int alloc_pebs_buffer(int cpu)
 	int max, node = cpu_to_node(cpu);
 	void *buffer, *insn_buff, *cea;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return 0;
 
 	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
@@ -659,7 +660,7 @@ static void release_pebs_buffer(int cpu)
 	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
 	void *cea;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return;
 
 	kfree(per_cpu(insn_buffer, cpu));
@@ -734,7 +735,7 @@ void release_ds_buffers(void)
 {
 	int cpu;
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
 	for_each_possible_cpu(cpu)
@@ -750,7 +751,8 @@ void release_ds_buffers(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		release_pebs_buffer(cpu);
+		if (x86_pmu.ds_pebs)
+			release_pebs_buffer(cpu);
 		release_bts_buffer(cpu);
 	}
 }
@@ -761,15 +763,17 @@ void reserve_ds_buffers(void)
 	int cpu;
 
 	x86_pmu.bts_active = 0;
-	x86_pmu.pebs_active = 0;
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (x86_pmu.ds_pebs)
+		x86_pmu.pebs_active = 0;
+
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
 	if (!x86_pmu.bts)
 		bts_err = 1;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		pebs_err = 1;
 
 	for_each_possible_cpu(cpu) {
@@ -781,7 +785,8 @@ void reserve_ds_buffers(void)
 		if (!bts_err && alloc_bts_buffer(cpu))
 			bts_err = 1;
 
-		if (!pebs_err && alloc_pebs_buffer(cpu))
+		if (x86_pmu.ds_pebs && !pebs_err &&
+		    alloc_pebs_buffer(cpu))
 			pebs_err = 1;
 
 		if (bts_err && pebs_err)
@@ -793,7 +798,7 @@ void reserve_ds_buffers(void)
 			release_bts_buffer(cpu);
 	}
 
-	if (pebs_err) {
+	if (x86_pmu.ds_pebs && pebs_err) {
 		for_each_possible_cpu(cpu)
 			release_pebs_buffer(cpu);
 	}
@@ -805,7 +810,7 @@ void reserve_ds_buffers(void)
 		if (x86_pmu.bts && !bts_err)
 			x86_pmu.bts_active = 1;
 
-		if (x86_pmu.pebs && !pebs_err)
+		if (x86_pmu.ds_pebs && !pebs_err)
 			x86_pmu.pebs_active = 1;
 
 		for_each_possible_cpu(cpu) {
@@ -953,11 +958,11 @@ unlock:
 	return 1;
 }
 
-static inline void intel_pmu_drain_pebs_buffer(void)
+void intel_pmu_drain_pebs_buffer(void)
 {
 	struct perf_sample_data data;
 
-	x86_pmu.drain_pebs(NULL, &data);
+	static_call(x86_pmu_drain_pebs)(NULL, &data);
 }
 
 /*
@@ -1294,6 +1299,19 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 	ds->pebs_interrupt_threshold = threshold;
 }
 
+#define PEBS_DATACFG_CNTRS(x)						\
+	((x >> PEBS_DATACFG_CNTR_SHIFT) & PEBS_DATACFG_CNTR_MASK)
+
+#define PEBS_DATACFG_CNTR_BIT(x)					\
+	(((1ULL << x) & PEBS_DATACFG_CNTR_MASK) << PEBS_DATACFG_CNTR_SHIFT)
+
+#define PEBS_DATACFG_FIX(x)						\
+	((x >> PEBS_DATACFG_FIX_SHIFT) & PEBS_DATACFG_FIX_MASK)
+
+#define PEBS_DATACFG_FIX_BIT(x)						\
+	(((1ULL << (x)) & PEBS_DATACFG_FIX_MASK)			\
+	 << PEBS_DATACFG_FIX_SHIFT)
+
 static void adaptive_pebs_record_size_update(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1308,10 +1326,57 @@ static void adaptive_pebs_record_size_update(void)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
 		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+	if (pebs_data_cfg & (PEBS_DATACFG_METRICS | PEBS_DATACFG_CNTR)) {
+		sz += sizeof(struct pebs_cntr_header);
+
+		/* Metrics base and Metrics Data */
+		if (pebs_data_cfg & PEBS_DATACFG_METRICS)
+			sz += 2 * sizeof(u64);
+
+		if (pebs_data_cfg & PEBS_DATACFG_CNTR) {
+			sz += (hweight64(PEBS_DATACFG_CNTRS(pebs_data_cfg)) +
+			       hweight64(PEBS_DATACFG_FIX(pebs_data_cfg))) *
+			      sizeof(u64);
+		}
+	}
 
 	cpuc->pebs_record_size = sz;
 }
 
+static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
+					int idx, u64 *pebs_data_cfg)
+{
+	if (is_metric_event(event)) {
+		*pebs_data_cfg |= PEBS_DATACFG_METRICS;
+		return;
+	}
+
+	*pebs_data_cfg |= PEBS_DATACFG_CNTR;
+
+	if (idx >= INTEL_PMC_IDX_FIXED)
+		*pebs_data_cfg |= PEBS_DATACFG_FIX_BIT(idx - INTEL_PMC_IDX_FIXED);
+	else
+		*pebs_data_cfg |= PEBS_DATACFG_CNTR_BIT(idx);
+}
+
+
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
+{
+	struct perf_event *event;
+	u64 pebs_data_cfg = 0;
+	int i;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		event = cpuc->event_list[i];
+		if (!is_pebs_counter_event_group(event))
+			continue;
+		__intel_pmu_pebs_update_cfg(event, cpuc->assign[i], &pebs_data_cfg);
+	}
+
+	if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
+		cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
+}
+
 #define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
 				PERF_SAMPLE_PHYS_ADDR |			     \
 				PERF_SAMPLE_WEIGHT_TYPE |		     \
@@ -1338,8 +1403,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	 * + precise_ip < 2 for the non event IP
 	 * + For RTM TSX weight we need GPRs for the abort code.
 	 */
-	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
-	       (attr->sample_regs_intr & PEBS_GP_REGS);
+	gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+		(attr->sample_regs_intr & PEBS_GP_REGS)) ||
+	       ((sample_type & PERF_SAMPLE_REGS_USER) &&
+		(attr->sample_regs_user & PEBS_GP_REGS));
 
 	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
 		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -1454,7 +1521,7 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 		else
 			value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
 	}
-	wrmsrl(base + idx, value);
+	wrmsrq(base + idx, value);
 }
 
 static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
@@ -1491,7 +1558,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 			 */
 			intel_pmu_drain_pebs_buffer();
 			adaptive_pebs_record_size_update();
-			wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
+			wrmsrq(MSR_PEBS_DATA_CFG, pebs_data_cfg);
 			cpuc->active_pebs_data_cfg = pebs_data_cfg;
 		}
 	}
@@ -1554,7 +1621,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	intel_pmu_pebs_via_pt_disable(event);
 
 	if (cpuc->enabled)
-		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+		wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
 	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
 }
@@ -1564,7 +1631,7 @@ void intel_pmu_pebs_enable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
-		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+		wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 }
 
 void intel_pmu_pebs_disable_all(void)
@@ -1765,8 +1832,6 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 
 	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data->period = event->hw.last_period;
-
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
@@ -1914,12 +1979,89 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 #endif
 }
 
+static void intel_perf_event_update_pmc(struct perf_event *event, u64 pmc)
+{
+	int shift = 64 - x86_pmu.cntval_bits;
+	struct hw_perf_event *hwc;
+	u64 delta, prev_pmc;
+
+	/*
+	 * A recorded counter may not have an assigned event in the
+	 * following cases. The value should be dropped.
+	 * - An event is deleted. There is still an active PEBS event.
+	 *   The PEBS record doesn't shrink on pmu::del().
+	 *   If the counter of the deleted event once occurred in a PEBS
+	 *   record, PEBS still records the counter until the counter is
+	 *   reassigned.
+	 * - An event is stopped for some reason, e.g., throttled.
+	 *   During this period, another event is added and takes the
+	 *   counter of the stopped event. The stopped event is assigned
+	 *   to another new and uninitialized counter, since the
+	 *   x86_pmu_start(RELOAD) is not invoked for a stopped event.
+	 *   The PEBS__DATA_CFG is updated regardless of the event state.
+	 *   The uninitialized counter can be recorded in a PEBS record.
+	 *   But the cpuc->events[uninitialized_counter] is always NULL,
+	 *   because the event is stopped. The uninitialized value is
+	 *   safely dropped.
+	 */
+	if (!event)
+		return;
+
+	hwc = &event->hw;
+	prev_pmc = local64_read(&hwc->prev_count);
+
+	/* Only update the count when the PMU is disabled */
+	WARN_ON(this_cpu_read(cpu_hw_events.enabled));
+	local64_set(&hwc->prev_count, pmc);
+
+	delta = (pmc << shift) - (prev_pmc << shift);
+	delta >>= shift;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static inline void __setup_pebs_counter_group(struct cpu_hw_events *cpuc,
+					      struct perf_event *event,
+					      struct pebs_cntr_header *cntr,
+					      void *next_record)
+{
+	int bit;
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->cntr, INTEL_PMC_MAX_GENERIC) {
+		intel_perf_event_update_pmc(cpuc->events[bit], *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->fixed, INTEL_PMC_MAX_FIXED) {
+		/* The slots event will be handled with perf_metric later */
+		if ((cntr->metrics == INTEL_CNTR_METRICS) &&
+		    (bit + INTEL_PMC_IDX_FIXED == INTEL_PMC_IDX_FIXED_SLOTS)) {
+			next_record += sizeof(u64);
+			continue;
+		}
+		intel_perf_event_update_pmc(cpuc->events[bit + INTEL_PMC_IDX_FIXED],
+					    *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	/* HW will reload the value right after the overflow. */
+	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+		local64_set(&event->hw.prev_count, (u64)-event->hw.sample_period);
+
+	if (cntr->metrics == INTEL_CNTR_METRICS) {
+		static_call(intel_pmu_update_topdown_event)
+			   (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS],
+			    (u64 *)next_record);
+		next_record += 2 * sizeof(u64);
+	}
+}
+
 #define PEBS_LATENCY_MASK			0xffff
 
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
  */
-
 static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 					    struct pt_regs *iregs, void *__pebs,
 					    struct perf_sample_data *data,
@@ -1942,7 +2084,6 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	sample_type = event->attr.sample_type;
 	format_group = basic->format_group;
 	perf_sample_data_init(data, 0, event->hw.last_period);
-	data->period = event->hw.last_period;
 
 	setup_pebs_time(event, data, basic->tsc);
 
@@ -1985,7 +2126,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			regs->flags &= ~PERF_EFLAGS_EXACT;
 		}
 
-		if (sample_type & PERF_SAMPLE_REGS_INTR)
+		if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
@@ -2049,6 +2190,28 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
+	if (format_group & (PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS)) {
+		struct pebs_cntr_header *cntr = next_record;
+		unsigned int nr;
+
+		next_record += sizeof(struct pebs_cntr_header);
+		/*
+		 * The PEBS_DATA_CFG is a global register, which is the
+		 * superset configuration for all PEBS events.
+		 * For the PEBS record of non-sample-read group, ignore
+		 * the counter snapshot fields.
+		 */
+		if (is_pebs_counter_event_group(event)) {
+			__setup_pebs_counter_group(cpuc, event, cntr, next_record);
+			data->sample_flags |= PERF_SAMPLE_READ;
+		}
+
+		nr = hweight32(cntr->cntr) + hweight32(cntr->fixed);
+		if (cntr->metrics == INTEL_CNTR_METRICS)
+			nr += 2;
+		next_record += nr * sizeof(u64);
+	}
+
 	WARN_ONCE(next_record != __pebs + basic->format_size,
 			"PEBS record size %u, expected %llu, config %llx\n",
 			basic->format_size,
@@ -2094,15 +2257,6 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	return NULL;
 }
 
-void intel_pmu_auto_reload_read(struct perf_event *event)
-{
-	WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));
-
-	perf_pmu_disable(event->pmu);
-	intel_pmu_drain_pebs_buffer();
-	perf_pmu_enable(event->pmu);
-}
-
 /*
  * Special variant of intel_pmu_save_and_restart() for auto-reload.
  */
@@ -2123,7 +2277,7 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	WARN_ON(this_cpu_read(cpu_hw_events.enabled));
 
 	prev_raw_count = local64_read(&hwc->prev_count);
-	rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+	new_raw_count = rdpmc(hwc->event_base_rdpmc);
 	local64_set(&hwc->prev_count, new_raw_count);
 
 	/*
@@ -2206,20 +2360,44 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
 		 * All but the last records are processed.
 		 * The last one is left to be able to call the overflow handler.
 		 */
-		if (perf_event_overflow(event, data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, data, regs);
 	}
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		if ((is_pebs_counter_event_group(event))) {
+			/*
+			 * The value of each sample has been updated when setup
+			 * the corresponding sample data.
+			 */
+			perf_event_update_userpage(event);
+		} else {
+			/*
+			 * Now, auto-reload is only enabled in fixed period mode.
+			 * The reload value is always hwc->sample_period.
+			 * May need to change it, if auto-reload is enabled in
+			 * freq mode later.
+			 */
+			intel_pmu_save_and_restart_reload(event, count);
+		}
+	} else {
 		/*
-		 * Now, auto-reload is only enabled in fixed period mode.
-		 * The reload value is always hwc->sample_period.
-		 * May need to change it, if auto-reload is enabled in
-		 * freq mode later.
+		 * For a non-precise event, it's possible the
+		 * counters-snapshotting records a positive value for the
+		 * overflowed event. Then the HW auto-reload mechanism
+		 * reset the counter to 0 immediately, because the
+		 * pebs_event_reset is cleared if the PERF_X86_EVENT_AUTO_RELOAD
+		 * is not set. The counter backwards may be observed in a
+		 * PMI handler.
+		 *
+		 * Since the event value has been updated when processing the
+		 * counters-snapshotting record, only needs to set the new
+		 * period for the counter.
 		 */
-		intel_pmu_save_and_restart_reload(event, count);
-	} else
-		intel_pmu_save_and_restart(event);
+		if (is_pebs_counter_event_group(event))
+			static_call(x86_pmu_set_period)(event);
+		else
+			intel_pmu_save_and_restart(event);
+	}
 }
 
 static __always_inline void
@@ -2287,8 +2465,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 				setup_pebs_fixed_sample_data);
 }
 
-static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask)
 {
+	u64 pebs_enabled = cpuc->pebs_enabled & mask;
 	struct perf_event *event;
 	int bit;
 
@@ -2299,7 +2478,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int
 	 * It needs to call intel_pmu_save_and_restart_reload() to
 	 * update the event->count for this case.
 	 */
-	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+	for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) {
 		event = cpuc->events[bit];
 		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 			intel_pmu_save_and_restart_reload(event, 0);
@@ -2334,7 +2513,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	}
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
@@ -2410,8 +2589,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
-			if (iregs && perf_event_account_interrupt(event))
-				x86_pmu_stop(event, 0);
+			if (iregs)
+				perf_event_account_interrupt(event);
 		}
 
 		if (counts[bit]) {
@@ -2448,7 +2627,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
 		return;
 	}
 
@@ -2491,10 +2670,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 }
 
 /*
- * BTS, PEBS probe and setup
+ * PEBS probe and setup
  */
 
-void __init intel_ds_init(void)
+void __init intel_pebs_init(void)
 {
 	/*
 	 * No support for 32bit formats
@@ -2502,13 +2681,12 @@ void __init intel_ds_init(void)
 	if (!boot_cpu_has(X86_FEATURE_DTES64))
 		return;
 
-	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
-	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.ds_pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.version <= 4)
 		x86_pmu.pebs_no_isolation = 1;
 
-	if (x86_pmu.pebs) {
+	if (x86_pmu.ds_pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		char *pebs_qual = "";
 		int format = x86_pmu.intel_cap.pebs_format;
@@ -2516,6 +2694,11 @@ void __init intel_ds_init(void)
 		if (format < 4)
 			x86_pmu.intel_cap.pebs_baseline = 0;
 
+		x86_pmu.pebs_enable = intel_pmu_pebs_enable;
+		x86_pmu.pebs_disable = intel_pmu_pebs_disable;
+		x86_pmu.pebs_enable_all = intel_pmu_pebs_enable_all;
+		x86_pmu.pebs_disable_all = intel_pmu_pebs_disable_all;
+
 		switch (format) {
 		case 0:
 			pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -2552,6 +2735,11 @@ void __init intel_ds_init(void)
 			break;
 
 		case 6:
+			if (x86_pmu.intel_cap.pebs_baseline) {
+				x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ;
+				x86_pmu.late_setup = intel_pmu_late_setup;
+			}
+			fallthrough;
 		case 5:
 			x86_pmu.pebs_ept = 1;
 			fallthrough;
@@ -2576,7 +2764,7 @@ void __init intel_ds_init(void)
 					  PERF_SAMPLE_REGS_USER |
 					  PERF_SAMPLE_REGS_INTR);
 			}
-			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+			pr_cont("PEBS fmt%d%c%s, ", format, pebs_type, pebs_qual);
 
 			/*
 			 * The PEBS-via-PT is not supported on hybrid platforms,
@@ -2595,7 +2783,7 @@ void __init intel_ds_init(void)
 
 		default:
 			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
-			x86_pmu.pebs = 0;
+			x86_pmu.ds_pebs = 0;
 		}
 	}
 }
@@ -2604,8 +2792,8 @@ void perf_restore_debug_store(void)
 {
 	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
-	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+	wrmsrq(MSR_IA32_DS_AREA, (unsigned long)ds);
 }
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 034a1f6a457c..e614baf42926 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 
 #include <asm/hardirq.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -159,18 +160,18 @@ static void knc_pmu_disable_all(void)
 {
 	u64 val;
 
-	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
 	val &= ~(KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
-	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
 }
 
 static void knc_pmu_enable_all(int added)
 {
 	u64 val;
 
-	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
 	val |= (KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
-	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
 }
 
 static inline void
@@ -182,7 +183,7 @@ knc_pmu_disable_event(struct perf_event *event)
 	val = hwc->config;
 	val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+	(void)wrmsrq_safe(hwc->config_base + hwc->idx, val);
 }
 
 static void knc_pmu_enable_event(struct perf_event *event)
@@ -193,21 +194,21 @@ static void knc_pmu_enable_event(struct perf_event *event)
 	val = hwc->config;
 	val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+	(void)wrmsrq_safe(hwc->config_base + hwc->idx, val);
 }
 
 static inline u64 knc_pmu_get_status(void)
 {
 	u64 status;
 
-	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
+	rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
 
 	return status;
 }
 
 static inline void knc_pmu_ack_status(u64 ack)
 {
-	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
+	wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
 }
 
 static int knc_pmu_handle_irq(struct pt_regs *regs)
@@ -241,19 +242,20 @@ again:
 
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
+		u64 last_period;
 
 		handled++;
 
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
+		last_period = event->hw.last_period;
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index dc641b50814e..7aa59966e7c3 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -137,9 +137,9 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	if (cpuc->lbr_sel)
 		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
 	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
-		wrmsrl(MSR_LBR_SELECT, lbr_select);
+		wrmsrq(MSR_LBR_SELECT, lbr_select);
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	orig_debugctl = debugctl;
 
 	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
@@ -155,10 +155,10 @@ static void __intel_pmu_lbr_enable(bool pmi)
 		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
 	if (orig_debugctl != debugctl)
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
-		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
+		wrmsrq(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
 void intel_pmu_lbr_reset_32(void)
@@ -166,7 +166,7 @@ void intel_pmu_lbr_reset_32(void)
 	int i;
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++)
-		wrmsrl(x86_pmu.lbr_from + i, 0);
+		wrmsrq(x86_pmu.lbr_from + i, 0);
 }
 
 void intel_pmu_lbr_reset_64(void)
@@ -174,17 +174,17 @@ void intel_pmu_lbr_reset_64(void)
 	int i;
 
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
-		wrmsrl(x86_pmu.lbr_from + i, 0);
-		wrmsrl(x86_pmu.lbr_to   + i, 0);
+		wrmsrq(x86_pmu.lbr_from + i, 0);
+		wrmsrq(x86_pmu.lbr_to   + i, 0);
 		if (x86_pmu.lbr_has_info)
-			wrmsrl(x86_pmu.lbr_info + i, 0);
+			wrmsrq(x86_pmu.lbr_info + i, 0);
 	}
 }
 
 static void intel_pmu_arch_lbr_reset(void)
 {
 	/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
-	wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
+	wrmsrq(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
 }
 
 void intel_pmu_lbr_reset(void)
@@ -199,7 +199,7 @@ void intel_pmu_lbr_reset(void)
 	cpuc->last_task_ctx = NULL;
 	cpuc->last_log_id = 0;
 	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select)
-		wrmsrl(MSR_LBR_SELECT, 0);
+		wrmsrq(MSR_LBR_SELECT, 0);
 }
 
 /*
@@ -209,7 +209,7 @@ static inline u64 intel_pmu_lbr_tos(void)
 {
 	u64 tos;
 
-	rdmsrl(x86_pmu.lbr_tos, tos);
+	rdmsrq(x86_pmu.lbr_tos, tos);
 	return tos;
 }
 
@@ -282,17 +282,17 @@ static u64 lbr_from_signext_quirk_rd(u64 val)
 static __always_inline void wrlbr_from(unsigned int idx, u64 val)
 {
 	val = lbr_from_signext_quirk_wr(val);
-	wrmsrl(x86_pmu.lbr_from + idx, val);
+	wrmsrq(x86_pmu.lbr_from + idx, val);
 }
 
 static __always_inline void wrlbr_to(unsigned int idx, u64 val)
 {
-	wrmsrl(x86_pmu.lbr_to + idx, val);
+	wrmsrq(x86_pmu.lbr_to + idx, val);
 }
 
 static __always_inline void wrlbr_info(unsigned int idx, u64 val)
 {
-	wrmsrl(x86_pmu.lbr_info + idx, val);
+	wrmsrq(x86_pmu.lbr_info + idx, val);
 }
 
 static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
@@ -302,7 +302,7 @@ static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
 	if (lbr)
 		return lbr->from;
 
-	rdmsrl(x86_pmu.lbr_from + idx, val);
+	rdmsrq(x86_pmu.lbr_from + idx, val);
 
 	return lbr_from_signext_quirk_rd(val);
 }
@@ -314,7 +314,7 @@ static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
 	if (lbr)
 		return lbr->to;
 
-	rdmsrl(x86_pmu.lbr_to + idx, val);
+	rdmsrq(x86_pmu.lbr_to + idx, val);
 
 	return val;
 }
@@ -326,7 +326,7 @@ static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
 	if (lbr)
 		return lbr->info;
 
-	rdmsrl(x86_pmu.lbr_info + idx, val);
+	rdmsrq(x86_pmu.lbr_info + idx, val);
 
 	return val;
 }
@@ -380,10 +380,10 @@ void intel_pmu_lbr_restore(void *ctx)
 			wrlbr_info(lbr_idx, 0);
 	}
 
-	wrmsrl(x86_pmu.lbr_tos, tos);
+	wrmsrq(x86_pmu.lbr_tos, tos);
 
 	if (cpuc->lbr_select)
-		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+		wrmsrq(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 static void intel_pmu_arch_lbr_restore(void *ctx)
@@ -422,11 +422,17 @@ static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
 	return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos, NULL);
 }
 
+static inline bool has_lbr_callstack_users(void *ctx)
+{
+	return task_context_opt(ctx)->lbr_callstack_users ||
+	       x86_pmu.lbr_callstack_users;
+}
+
 static void __intel_pmu_lbr_restore(void *ctx)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
+	if (!has_lbr_callstack_users(ctx) ||
 	    task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
 		intel_pmu_lbr_reset();
 		return;
@@ -469,7 +475,7 @@ void intel_pmu_lbr_save(void *ctx)
 	task_ctx->tos = tos;
 
 	if (cpuc->lbr_select)
-		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+		rdmsrq(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 static void intel_pmu_arch_lbr_save(void *ctx)
@@ -503,7 +509,7 @@ static void __intel_pmu_lbr_save(void *ctx)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (task_context_opt(ctx)->lbr_callstack_users == 0) {
+	if (!has_lbr_callstack_users(ctx)) {
 		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
 		return;
 	}
@@ -516,32 +522,11 @@ static void __intel_pmu_lbr_save(void *ctx)
 	cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
 }
 
-void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
-				 struct perf_event_pmu_context *next_epc)
-{
-	void *prev_ctx_data, *next_ctx_data;
-
-	swap(prev_epc->task_ctx_data, next_epc->task_ctx_data);
-
-	/*
-	 * Architecture specific synchronization makes sense in case
-	 * both prev_epc->task_ctx_data and next_epc->task_ctx_data
-	 * pointers are allocated.
-	 */
-
-	prev_ctx_data = next_epc->task_ctx_data;
-	next_ctx_data = prev_epc->task_ctx_data;
-
-	if (!prev_ctx_data || !next_ctx_data)
-		return;
-
-	swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
-	     task_context_opt(next_ctx_data)->lbr_callstack_users);
-}
-
-void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			      struct task_struct *task, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_ctx_data *ctx_data;
 	void *task_ctx;
 
 	if (!cpuc->lbr_users)
@@ -552,14 +537,18 @@ void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched
 	 * the task was scheduled out, restore the stack. Otherwise flush
 	 * the LBR stack.
 	 */
-	task_ctx = pmu_ctx ? pmu_ctx->task_ctx_data : NULL;
+	rcu_read_lock();
+	ctx_data = rcu_dereference(task->perf_ctx_data);
+	task_ctx = ctx_data ? ctx_data->data : NULL;
 	if (task_ctx) {
 		if (sched_in)
 			__intel_pmu_lbr_restore(task_ctx);
 		else
 			__intel_pmu_lbr_save(task_ctx);
+		rcu_read_unlock();
 		return;
 	}
+	rcu_read_unlock();
 
 	/*
 	 * Since a context switch can flip the address space and LBR entries
@@ -588,9 +577,19 @@ void intel_pmu_lbr_add(struct perf_event *event)
 
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
-	if (branch_user_callstack(cpuc->br_sel) && event->pmu_ctx->task_ctx_data)
-		task_context_opt(event->pmu_ctx->task_ctx_data)->lbr_callstack_users++;
+	if (branch_user_callstack(cpuc->br_sel)) {
+		if (event->attach_state & PERF_ATTACH_TASK) {
+			struct task_struct *task = event->hw.target;
+			struct perf_ctx_data *ctx_data;
 
+			rcu_read_lock();
+			ctx_data = rcu_dereference(task->perf_ctx_data);
+			if (ctx_data)
+				task_context_opt(ctx_data->data)->lbr_callstack_users++;
+			rcu_read_unlock();
+		} else
+			x86_pmu.lbr_callstack_users++;
+	}
 	/*
 	 * Request pmu::sched_task() callback, which will fire inside the
 	 * regular perf event scheduling, so that call will:
@@ -664,9 +663,19 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
-	if (branch_user_callstack(cpuc->br_sel) &&
-	    event->pmu_ctx->task_ctx_data)
-		task_context_opt(event->pmu_ctx->task_ctx_data)->lbr_callstack_users--;
+	if (branch_user_callstack(cpuc->br_sel)) {
+		if (event->attach_state & PERF_ATTACH_TASK) {
+			struct task_struct *task = event->hw.target;
+			struct perf_ctx_data *ctx_data;
+
+			rcu_read_lock();
+			ctx_data = rcu_dereference(task->perf_ctx_data);
+			if (ctx_data)
+				task_context_opt(ctx_data->data)->lbr_callstack_users--;
+			rcu_read_unlock();
+		} else
+			x86_pmu.lbr_callstack_users--;
+	}
 
 	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
 		cpuc->lbr_select = 0;
@@ -743,7 +752,7 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 			u64     lbr;
 		} msr_lastbranch;
 
-		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
+		rdmsrq(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
 		perf_clear_branch_entry_bitfields(br);
 
@@ -1593,7 +1602,7 @@ void __init intel_pmu_arch_lbr_init(void)
 		goto clear_arch_lbr;
 
 	/* Apply the max depth of Arch LBR */
-	if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
+	if (wrmsrq_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
 		goto clear_arch_lbr;
 
 	x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
@@ -1609,7 +1618,7 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_nr = lbr_nr;
 
 	if (!!x86_pmu.lbr_counters)
-		x86_pmu.flags |= PMU_FL_BR_CNTR;
+		x86_pmu.flags |= PMU_FL_BR_CNTR | PMU_FL_DYN_CONSTRAINT;
 
 	if (x86_pmu.lbr_mispred)
 		static_branch_enable(&x86_lbr_mispred);
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 844bc4fc4724..e5fd7367e45d 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -10,8 +10,10 @@
 #include <linux/perf_event.h>
 
 #include <asm/perf_event_p4.h>
+#include <asm/cpu_device_id.h>
 #include <asm/hardirq.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -732,9 +734,9 @@ static bool p4_event_match_cpu_model(unsigned int event_idx)
 {
 	/* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */
 	if (event_idx == P4_EVENT_INSTR_COMPLETED) {
-		if (boot_cpu_data.x86_model != 3 &&
-			boot_cpu_data.x86_model != 4 &&
-			boot_cpu_data.x86_model != 6)
+		if (boot_cpu_data.x86_vfm != INTEL_P4_PRESCOTT &&
+		    boot_cpu_data.x86_vfm != INTEL_P4_PRESCOTT_2M &&
+		    boot_cpu_data.x86_vfm != INTEL_P4_CEDARMILL)
 			return false;
 	}
 
@@ -776,7 +778,7 @@ static int p4_validate_raw_event(struct perf_event *event)
 	 * the user needs special permissions to be able to use it
 	 */
 	if (p4_ht_active() && p4_event_bind_map[v].shared) {
-		v = perf_allow_cpu(&event->attr);
+		v = perf_allow_cpu();
 		if (v)
 			return v;
 	}
@@ -858,9 +860,9 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 	u64 v;
 
 	/* an official way for overflow indication */
-	rdmsrl(hwc->config_base, v);
+	rdmsrq(hwc->config_base, v);
 	if (v & P4_CCCR_OVF) {
-		wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
+		wrmsrq(hwc->config_base, v & ~P4_CCCR_OVF);
 		return 1;
 	}
 
@@ -871,7 +873,7 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 	 * the counter has reached zero value and continued counting before
 	 * real NMI signal was received:
 	 */
-	rdmsrl(hwc->event_base, v);
+	rdmsrq(hwc->event_base, v);
 	if (!(v & ARCH_P4_UNFLAGGED_BIT))
 		return 1;
 
@@ -896,8 +898,8 @@ static void p4_pmu_disable_pebs(void)
 	 * So at moment let leave metrics turned on forever -- it's
 	 * ok for now but need to be revisited!
 	 *
-	 * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0);
-	 * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
+	 * (void)wrmsrq_safe(MSR_IA32_PEBS_ENABLE, 0);
+	 * (void)wrmsrq_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
 	 */
 }
 
@@ -910,7 +912,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 	 * state we need to clear P4_CCCR_OVF, otherwise interrupt get
 	 * asserted again and again
 	 */
-	(void)wrmsrl_safe(hwc->config_base,
+	(void)wrmsrq_safe(hwc->config_base,
 		p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
 }
 
@@ -943,8 +945,8 @@ static void p4_pmu_enable_pebs(u64 config)
 
 	bind = &p4_pebs_bind_map[idx];
 
-	(void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE,	(u64)bind->metric_pebs);
-	(void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT,	(u64)bind->metric_vert);
+	(void)wrmsrq_safe(MSR_IA32_PEBS_ENABLE,	(u64)bind->metric_pebs);
+	(void)wrmsrq_safe(MSR_P4_PEBS_MATRIX_VERT,	(u64)bind->metric_vert);
 }
 
 static void __p4_pmu_enable_event(struct perf_event *event)
@@ -978,8 +980,8 @@ static void __p4_pmu_enable_event(struct perf_event *event)
 	 */
 	p4_pmu_enable_pebs(hwc->config);
 
-	(void)wrmsrl_safe(escr_addr, escr_conf);
-	(void)wrmsrl_safe(hwc->config_base,
+	(void)wrmsrq_safe(escr_addr, escr_conf);
+	(void)wrmsrq_safe(hwc->config_base,
 				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
 }
 
@@ -1023,7 +1025,7 @@ static int p4_pmu_set_period(struct perf_event *event)
 		 *
 		 * the former idea is taken from OProfile code
 		 */
-		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrq(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
 	}
 
 	return ret;
@@ -1071,8 +1073,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	if (handled)
@@ -1397,7 +1398,7 @@ __init int p4_pmu_init(void)
 	 */
 	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
-		wrmsrl_safe(reg, 0ULL);
+		wrmsrq_safe(reg, 0ULL);
 	}
 
 	return 0;
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index a6cffb4f4ef5..6e41de355bd8 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -2,6 +2,9 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
+#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
+
 #include "../perf_event.h"
 
 /*
@@ -140,9 +143,9 @@ static void p6_pmu_disable_all(void)
 	u64 val;
 
 	/* p6 only has one enable register */
-	rdmsrl(MSR_P6_EVNTSEL0, val);
+	rdmsrq(MSR_P6_EVNTSEL0, val);
 	val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
-	wrmsrl(MSR_P6_EVNTSEL0, val);
+	wrmsrq(MSR_P6_EVNTSEL0, val);
 }
 
 static void p6_pmu_enable_all(int added)
@@ -150,9 +153,9 @@ static void p6_pmu_enable_all(int added)
 	unsigned long val;
 
 	/* p6 only has one enable register */
-	rdmsrl(MSR_P6_EVNTSEL0, val);
+	rdmsrq(MSR_P6_EVNTSEL0, val);
 	val |= ARCH_PERFMON_EVENTSEL_ENABLE;
-	wrmsrl(MSR_P6_EVNTSEL0, val);
+	wrmsrq(MSR_P6_EVNTSEL0, val);
 }
 
 static inline void
@@ -161,7 +164,7 @@ p6_pmu_disable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
-	(void)wrmsrl_safe(hwc->config_base, val);
+	(void)wrmsrq_safe(hwc->config_base, val);
 }
 
 static void p6_pmu_enable_event(struct perf_event *event)
@@ -178,7 +181,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
 	 * to actually enable the events.
 	 */
 
-	(void)wrmsrl_safe(hwc->config_base, val);
+	(void)wrmsrq_safe(hwc->config_base, val);
 }
 
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
@@ -248,30 +251,8 @@ __init int p6_pmu_init(void)
 {
 	x86_pmu = p6_pmu;
 
-	switch (boot_cpu_data.x86_model) {
-	case  1: /* Pentium Pro */
+	if (boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO)
 		x86_add_quirk(p6_pmu_rdpmc_quirk);
-		break;
-
-	case  3: /* Pentium II - Klamath */
-	case  5: /* Pentium II - Deschutes */
-	case  6: /* Pentium II - Mendocino */
-		break;
-
-	case  7: /* Pentium III - Katmai */
-	case  8: /* Pentium III - Coppermine */
-	case 10: /* Pentium III Xeon */
-	case 11: /* Pentium III - Tualatin */
-		break;
-
-	case  9: /* Pentium M - Banias */
-	case 13: /* Pentium M - Dothan */
-		break;
-
-	default:
-		pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
-		return -ENODEV;
-	}
 
 	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
 		sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fa37565f6418..e8cf29d2b10c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -18,12 +18,13 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/intel_pt.h>
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 #include "pt.h"
@@ -194,7 +195,7 @@ static int __init pt_pmu_hw_init(void)
 	int ret;
 	long i;
 
-	rdmsrl(MSR_PLATFORM_INFO, reg);
+	rdmsrq(MSR_PLATFORM_INFO, reg);
 	pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8;
 
 	/*
@@ -230,7 +231,7 @@ static int __init pt_pmu_hw_init(void)
 		 * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace
 		 * post-VMXON.
 		 */
-		rdmsrl(MSR_IA32_VMX_MISC, reg);
+		rdmsrq(MSR_IA32_VMX_MISC, reg);
 		if (reg & BIT(14))
 			pt_pmu.vmx = true;
 	}
@@ -426,7 +427,7 @@ static void pt_config_start(struct perf_event *event)
 	if (READ_ONCE(pt->vmx_on))
 		perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
 	else
-		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+		wrmsrq(MSR_IA32_RTIT_CTL, ctl);
 
 	WRITE_ONCE(event->hw.aux_config, ctl);
 }
@@ -485,12 +486,12 @@ static u64 pt_config_filters(struct perf_event *event)
 
 		/* avoid redundant msr writes */
 		if (pt->filters.filter[range].msr_a != filter->msr_a) {
-			wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a);
+			wrmsrq(pt_address_ranges[range].msr_a, filter->msr_a);
 			pt->filters.filter[range].msr_a = filter->msr_a;
 		}
 
 		if (pt->filters.filter[range].msr_b != filter->msr_b) {
-			wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b);
+			wrmsrq(pt_address_ranges[range].msr_b, filter->msr_b);
 			pt->filters.filter[range].msr_b = filter->msr_b;
 		}
 
@@ -509,7 +510,7 @@ static void pt_config(struct perf_event *event)
 	/* First round: clear STATUS, in particular the PSB byte counter. */
 	if (!event->hw.aux_config) {
 		perf_event_itrace_started(event);
-		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
+		wrmsrq(MSR_IA32_RTIT_STATUS, 0);
 	}
 
 	reg = pt_config_filters(event);
@@ -569,7 +570,7 @@ static void pt_config_stop(struct perf_event *event)
 
 	ctl &= ~RTIT_CTL_TRACEEN;
 	if (!READ_ONCE(pt->vmx_on))
-		wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+		wrmsrq(MSR_IA32_RTIT_CTL, ctl);
 
 	WRITE_ONCE(event->hw.aux_config, ctl);
 
@@ -658,13 +659,13 @@ static void pt_config_buffer(struct pt_buffer *buf)
 	reg = virt_to_phys(base);
 	if (pt->output_base != reg) {
 		pt->output_base = reg;
-		wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, reg);
+		wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, reg);
 	}
 
 	reg = 0x7f | (mask << 7) | ((u64)buf->output_off << 32);
 	if (pt->output_mask != reg) {
 		pt->output_mask = reg;
-		wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
+		wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, reg);
 	}
 }
 
@@ -926,7 +927,7 @@ static void pt_handle_status(struct pt *pt)
 	int advance = 0;
 	u64 status;
 
-	rdmsrl(MSR_IA32_RTIT_STATUS, status);
+	rdmsrq(MSR_IA32_RTIT_STATUS, status);
 
 	if (status & RTIT_STATUS_ERROR) {
 		pr_err_ratelimited("ToPA ERROR encountered, trying to recover\n");
@@ -970,7 +971,7 @@ static void pt_handle_status(struct pt *pt)
 	if (advance)
 		pt_buffer_advance(buf);
 
-	wrmsrl(MSR_IA32_RTIT_STATUS, status);
+	wrmsrq(MSR_IA32_RTIT_STATUS, status);
 }
 
 /**
@@ -985,12 +986,12 @@ static void pt_read_offset(struct pt_buffer *buf)
 	struct topa_page *tp;
 
 	if (!buf->single) {
-		rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base);
+		rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base);
 		tp = phys_to_virt(pt->output_base);
 		buf->cur = &tp->topa;
 	}
 
-	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask);
+	rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask);
 	/* offset within current output region */
 	buf->output_off = pt->output_mask >> 32;
 	/* index of current output region within this table */
@@ -1585,7 +1586,7 @@ void intel_pt_handle_vmx(int on)
 
 	/* Turn PTs back on */
 	if (!on && event)
-		wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config);
+		wrmsrq(MSR_IA32_RTIT_CTL, event->hw.aux_config);
 
 	local_irq_restore(flags);
 }
@@ -1611,7 +1612,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 			 * PMI might have just cleared these, so resume_allowed
 			 * must be checked again also.
 			 */
-			rdmsrl(MSR_IA32_RTIT_STATUS, status);
+			rdmsrq(MSR_IA32_RTIT_STATUS, status);
 			if (!(status & (RTIT_STATUS_TRIGGEREN |
 					RTIT_STATUS_ERROR |
 					RTIT_STATUS_STOPPED)) &&
@@ -1839,7 +1840,7 @@ static __init int pt_init(void)
 	for_each_online_cpu(cpu) {
 		u64 ctl;
 
-		ret = rdmsrl_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl);
+		ret = rdmsrq_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl);
 		if (!ret && (ctl & RTIT_CTL_TRACEEN))
 			prior_warn++;
 	}
@@ -1863,6 +1864,8 @@ static __init int pt_init(void)
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
 		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
+	else
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_PREFER_LARGE;
 
 	pt_pmu.pmu.capabilities		|= PERF_PMU_CAP_EXCLUSIVE |
 					   PERF_PMU_CAP_ITRACE |
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 60b3078b7502..e0815a12db90 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -3,6 +3,7 @@
 
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/msr.h>
 #include "uncore.h"
 #include "uncore_discovery.h"
 
@@ -150,7 +151,7 @@ u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *eve
 {
 	u64 count;
 
-	rdmsrl(event->hw.event_base, count);
+	rdmsrq(event->hw.event_base, count);
 
 	return count;
 }
@@ -305,17 +306,11 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 {
 	struct intel_uncore_box *box;
 	struct perf_event *event;
-	unsigned long flags;
 	int bit;
 
 	box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
 	if (!box->n_active || box->cpu != smp_processor_id())
 		return HRTIMER_NORESTART;
-	/*
-	 * disable local interrupt to prevent uncore_pmu_event_start/stop
-	 * to interrupt the update process
-	 */
-	local_irq_save(flags);
 
 	/*
 	 * handle boxes with an active event list as opposed to active
@@ -328,8 +323,6 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 	for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
 		uncore_perf_event_update(box, box->events[bit]);
 
-	local_irq_restore(flags);
-
 	hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
 	return HRTIMER_RESTART;
 }
@@ -337,7 +330,7 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
 	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
-		      HRTIMER_MODE_REL_PINNED);
+		      HRTIMER_MODE_REL_PINNED_HARD);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -347,8 +340,7 @@ void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
 
 static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 {
-	hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	box->hrtimer.function = uncore_pmu_hrtimer;
+	hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 }
 
 static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 571e44b49691..18a3022f26a0 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -5,6 +5,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/msr.h>
 #include "uncore.h"
 #include "uncore_discovery.h"
 
@@ -441,17 +442,17 @@ static u64 intel_generic_uncore_box_ctl(struct intel_uncore_box *box)
 
 void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box)
 {
-	wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
+	wrmsrq(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
 }
 
 void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
+	wrmsrq(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
 }
 
 void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(intel_generic_uncore_box_ctl(box), 0);
+	wrmsrq(intel_generic_uncore_box_ctl(box), 0);
 }
 
 static void intel_generic_uncore_msr_enable_event(struct intel_uncore_box *box,
@@ -459,7 +460,7 @@ static void intel_generic_uncore_msr_enable_event(struct intel_uncore_box *box,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrq(hwc->config_base, hwc->config);
 }
 
 static void intel_generic_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -467,7 +468,7 @@ static void intel_generic_uncore_msr_disable_event(struct intel_uncore_box *box,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, 0);
+	wrmsrq(hwc->config_base, 0);
 }
 
 static struct intel_uncore_ops generic_uncore_msr_ops = {
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 466833478e81..8962e7cb21e3 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Nehalem-EX/Westmere-EX uncore support */
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include "uncore.h"
 
 /* NHM-EX event control */
@@ -200,12 +201,12 @@ DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
 
 static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
 {
-	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+	wrmsrq(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
 }
 
 static void nhmex_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
-	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0);
+	wrmsrq(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0);
 }
 
 static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -214,12 +215,12 @@ static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
 	u64 config;
 
 	if (msr) {
-		rdmsrl(msr, config);
+		rdmsrq(msr, config);
 		config &= ~((1ULL << uncore_num_counters(box)) - 1);
 		/* WBox has a fixed counter */
 		if (uncore_msr_fixed_ctl(box))
 			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
+		wrmsrq(msr, config);
 	}
 }
 
@@ -229,18 +230,18 @@ static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
 	u64 config;
 
 	if (msr) {
-		rdmsrl(msr, config);
+		rdmsrq(msr, config);
 		config |= (1ULL << uncore_num_counters(box)) - 1;
 		/* WBox has a fixed counter */
 		if (uncore_msr_fixed_ctl(box))
 			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
+		wrmsrq(msr, config);
 	}
 }
 
 static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
-	wrmsrl(event->hw.config_base, 0);
+	wrmsrq(event->hw.config_base, 0);
 }
 
 static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -248,11 +249,11 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (hwc->idx == UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+		wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
 	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+		wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
 	else
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+		wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
 }
 
 #define NHMEX_UNCORE_OPS_COMMON_INIT()				\
@@ -382,10 +383,10 @@ static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, reg2->config);
+		wrmsrq(reg1->reg, reg1->config);
+		wrmsrq(reg1->reg + 1, reg2->config);
 	}
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+	wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
 		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
 }
 
@@ -467,12 +468,12 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, 0);
-		wrmsrl(reg1->reg + 1, reg1->config);
-		wrmsrl(reg1->reg + 2, reg2->config);
-		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+		wrmsrq(reg1->reg, 0);
+		wrmsrq(reg1->reg + 1, reg1->config);
+		wrmsrq(reg1->reg + 2, reg2->config);
+		wrmsrq(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
 	}
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+	wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
 }
 
 static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
@@ -842,25 +843,25 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per
 
 	idx = __BITS_VALUE(reg1->idx, 0, 8);
 	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+		wrmsrq(__BITS_VALUE(reg1->reg, 0, 16),
 			nhmex_mbox_shared_reg_config(box, idx));
 	idx = __BITS_VALUE(reg1->idx, 1, 8);
 	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+		wrmsrq(__BITS_VALUE(reg1->reg, 1, 16),
 			nhmex_mbox_shared_reg_config(box, idx));
 
 	if (reg2->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg2->reg, 0);
+		wrmsrq(reg2->reg, 0);
 		if (reg2->config != ~0ULL) {
-			wrmsrl(reg2->reg + 1,
+			wrmsrq(reg2->reg + 1,
 				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+			wrmsrq(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
 				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+			wrmsrq(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
 		}
 	}
 
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+	wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
 }
 
 DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
@@ -1121,31 +1122,31 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 
 	switch (idx % 6) {
 	case 0:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
 		break;
 	case 1:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
 		break;
 	case 2:
 	case 3:
-		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+		wrmsrq(NHMEX_R_MSR_PORTN_QLX_CFG(port),
 			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
 		break;
 	case 4:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
 			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
 		break;
 	case 5:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
 			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
 		break;
 	}
 
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+	wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
 		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
 }
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index edb7fd50efe0..a1a96833e30e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */
+#include <asm/msr.h>
 #include "uncore.h"
 #include "uncore_discovery.h"
 
@@ -260,34 +261,34 @@ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+		wrmsrq(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
 	else
-		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+		wrmsrq(hwc->config_base, SNB_UNC_CTL_EN);
 }
 
 static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
-	wrmsrl(event->hw.config_base, 0);
+	wrmsrq(event->hw.config_base, 0);
 }
 
 static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0) {
-		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+		wrmsrq(SNB_UNC_PERF_GLOBAL_CTL,
 			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
 	}
 }
 
 static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+	wrmsrq(SNB_UNC_PERF_GLOBAL_CTL,
 		SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
 }
 
 static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, 0);
+		wrmsrq(SNB_UNC_PERF_GLOBAL_CTL, 0);
 }
 
 static struct uncore_event_desc snb_uncore_events[] = {
@@ -372,7 +373,7 @@ void snb_uncore_cpu_init(void)
 static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0) {
-		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+		wrmsrq(SKL_UNC_PERF_GLOBAL_CTL,
 			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
 	}
 
@@ -383,14 +384,14 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 
 static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+	wrmsrq(SKL_UNC_PERF_GLOBAL_CTL,
 		SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
 }
 
 static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, 0);
+		wrmsrq(SKL_UNC_PERF_GLOBAL_CTL, 0);
 }
 
 static struct intel_uncore_ops skl_uncore_msr_ops = {
@@ -504,7 +505,7 @@ static int icl_get_cbox_num(void)
 {
 	u64 num_boxes;
 
-	rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+	rdmsrq(ICL_UNC_CBO_CONFIG, num_boxes);
 
 	return num_boxes & ICL_UNC_NUM_CBO_MASK;
 }
@@ -525,7 +526,7 @@ static struct intel_uncore_type *tgl_msr_uncores[] = {
 static void rkl_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+		wrmsrq(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
 }
 
 void tgl_uncore_cpu_init(void)
@@ -541,24 +542,24 @@ void tgl_uncore_cpu_init(void)
 static void adl_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+		wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
 }
 
 static void adl_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+	wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
 }
 
 static void adl_uncore_msr_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, 0);
+		wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, 0);
 }
 
 static void adl_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, 0);
+		wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, 0);
 }
 
 static struct intel_uncore_ops adl_uncore_msr_ops = {
@@ -691,7 +692,7 @@ static struct intel_uncore_type mtl_uncore_hac_cbox = {
 
 static void mtl_uncore_msr_init_box(struct intel_uncore_box *box)
 {
-	wrmsrl(uncore_msr_box_ctl(box), SNB_UNC_GLOBAL_CTL_EN);
+	wrmsrq(uncore_msr_box_ctl(box), SNB_UNC_GLOBAL_CTL_EN);
 }
 
 static struct intel_uncore_ops mtl_uncore_msr_ops = {
@@ -758,7 +759,7 @@ static struct intel_uncore_type *lnl_msr_uncores[] = {
 static void lnl_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
-		wrmsrl(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+		wrmsrq(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
 }
 
 static struct intel_uncore_ops lnl_uncore_msr_ops = {
@@ -1306,12 +1307,12 @@ int skl_uncore_pci_init(void)
 /* Nehalem uncore support */
 static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+	wrmsrq(NHM_UNC_PERF_GLOBAL_CTL, 0);
 }
 
 static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+	wrmsrq(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
 }
 
 static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -1319,9 +1320,9 @@ static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct per
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+		wrmsrq(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
 	else
-		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+		wrmsrq(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
 }
 
 static struct attribute *nhm_uncore_formats_attr[] = {
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 60973c209c0e..2824dc9950be 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* SandyBridge-EP/IvyTown uncore support */
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include "uncore.h"
 #include "uncore_discovery.h"
 
@@ -618,9 +619,9 @@ static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
 
 	msr = uncore_msr_box_ctl(box);
 	if (msr) {
-		rdmsrl(msr, config);
+		rdmsrq(msr, config);
 		config |= SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
+		wrmsrq(msr, config);
 	}
 }
 
@@ -631,9 +632,9 @@ static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
 
 	msr = uncore_msr_box_ctl(box);
 	if (msr) {
-		rdmsrl(msr, config);
+		rdmsrq(msr, config);
 		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
+		wrmsrq(msr, config);
 	}
 }
 
@@ -643,9 +644,9 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
+		wrmsrq(reg1->reg, uncore_shared_reg_config(box, 0));
 
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+	wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
 static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -653,7 +654,7 @@ static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrq(hwc->config_base, hwc->config);
 }
 
 static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
@@ -661,7 +662,7 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
 	unsigned msr = uncore_msr_box_ctl(box);
 
 	if (msr)
-		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+		wrmsrq(msr, SNBEP_PMON_BOX_CTL_INT);
 }
 
 static struct attribute *snbep_uncore_formats_attr[] = {
@@ -1532,7 +1533,7 @@ static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	unsigned msr = uncore_msr_box_ctl(box);
 	if (msr)
-		wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT);
+		wrmsrq(msr, IVBEP_PMON_BOX_CTL_INT);
 }
 
 static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box)
@@ -1783,11 +1784,11 @@ static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_ev
 
 	if (reg1->idx != EXTRA_REG_NONE) {
 		u64 filter = uncore_shared_reg_config(box, 0);
-		wrmsrl(reg1->reg, filter & 0xffffffff);
-		wrmsrl(reg1->reg + 6, filter >> 32);
+		wrmsrq(reg1->reg, filter & 0xffffffff);
+		wrmsrq(reg1->reg + 6, filter >> 32);
 	}
 
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+	wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
 static struct intel_uncore_ops ivbep_uncore_cbox_ops = {
@@ -2767,11 +2768,11 @@ static void hswep_cbox_enable_event(struct intel_uncore_box *box,
 
 	if (reg1->idx != EXTRA_REG_NONE) {
 		u64 filter = uncore_shared_reg_config(box, 0);
-		wrmsrl(reg1->reg, filter & 0xffffffff);
-		wrmsrl(reg1->reg + 1, filter >> 32);
+		wrmsrq(reg1->reg, filter & 0xffffffff);
+		wrmsrq(reg1->reg + 1, filter >> 32);
 	}
 
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+	wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
 static struct intel_uncore_ops hswep_uncore_cbox_ops = {
@@ -2816,7 +2817,7 @@ static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
 
 		for_each_set_bit(i, (unsigned long *)&init, 64) {
 			flags |= (1ULL << i);
-			wrmsrl(msr, flags);
+			wrmsrq(msr, flags);
 		}
 	}
 }
@@ -3708,7 +3709,7 @@ static void skx_iio_enable_event(struct intel_uncore_box *box,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+	wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
 static struct intel_uncore_ops skx_uncore_iio_ops = {
@@ -3765,7 +3766,7 @@ static int skx_msr_cpu_bus_read(int cpu, u64 *topology)
 {
 	u64 msr_value;
 
-	if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
+	if (rdmsrq_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
 			!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
 		return -ENXIO;
 
@@ -4655,9 +4656,9 @@ static void snr_cha_enable_event(struct intel_uncore_box *box,
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrq(reg1->reg, reg1->config);
 
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+	wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
 static struct intel_uncore_ops snr_uncore_chabox_ops = {
@@ -4891,28 +4892,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
 	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
 	/* Free-Running IIO BANDWIDTH IN Counters */
 	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.0517578125e-5"),
 	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
 	{ /* end: all zeroes */ },
 };
@@ -5485,37 +5486,6 @@ static struct freerunning_counters icx_iio_freerunning[] = {
 	[ICX_IIO_MSR_BW_IN]	= { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets },
 };
 
-static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = {
-	/* Free-Running IIO CLOCKS Counter */
-	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
-	/* Free-Running IIO BANDWIDTH IN Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
-	{ /* end: all zeroes */ },
-};
-
 static struct intel_uncore_type icx_uncore_iio_free_running = {
 	.name			= "iio_free_running",
 	.num_counters		= 9,
@@ -5523,7 +5493,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = {
 	.num_freerunning_types	= ICX_IIO_FREERUNNING_TYPE_MAX,
 	.freerunning		= icx_iio_freerunning,
 	.ops			= &skx_uncore_iio_freerunning_ops,
-	.event_descs		= icx_uncore_iio_freerunning_events,
+	.event_descs		= snr_uncore_iio_freerunning_events,
 	.format_group		= &skx_uncore_iio_freerunning_format_group,
 };
 
@@ -5913,9 +5883,9 @@ static void spr_uncore_msr_enable_event(struct intel_uncore_box *box,
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrq(reg1->reg, reg1->config);
 
-	wrmsrl(hwc->config_base, hwc->config);
+	wrmsrq(hwc->config_base, hwc->config);
 }
 
 static void spr_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -5925,9 +5895,9 @@ static void spr_uncore_msr_disable_event(struct intel_uncore_box *box,
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, 0);
+		wrmsrq(reg1->reg, 0);
 
-	wrmsrl(hwc->config_base, 0);
+	wrmsrq(hwc->config_base, 0);
 }
 
 static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -6320,69 +6290,13 @@ static struct freerunning_counters spr_iio_freerunning[] = {
 	[SPR_IIO_MSR_BW_OUT]	= { 0x3808, 0x1, 0x10, 8, 48 },
 };
 
-static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = {
-	/* Free-Running IIO CLOCKS Counter */
-	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
-	/* Free-Running IIO BANDWIDTH IN Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4,		"event=0xff,umask=0x24"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5,		"event=0xff,umask=0x25"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6,		"event=0xff,umask=0x26"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7,		"event=0xff,umask=0x27"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit,	"MiB"),
-	/* Free-Running IIO BANDWIDTH OUT Counters */
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0,		"event=0xff,umask=0x30"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1,		"event=0xff,umask=0x31"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2,		"event=0xff,umask=0x32"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3,		"event=0xff,umask=0x33"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4,		"event=0xff,umask=0x34"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5,		"event=0xff,umask=0x35"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6,		"event=0xff,umask=0x36"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit,	"MiB"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7,		"event=0xff,umask=0x37"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale,	"3.814697266e-6"),
-	INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit,	"MiB"),
-	{ /* end: all zeroes */ },
-};
-
 static struct intel_uncore_type spr_uncore_iio_free_running = {
 	.name			= "iio_free_running",
 	.num_counters		= 17,
 	.num_freerunning_types	= SPR_IIO_FREERUNNING_TYPE_MAX,
 	.freerunning		= spr_iio_freerunning,
 	.ops			= &skx_uncore_iio_freerunning_ops,
-	.event_descs		= spr_uncore_iio_freerunning_events,
+	.event_descs		= snr_uncore_iio_freerunning_events,
 	.format_group		= &skx_uncore_iio_freerunning_format_group,
 };
 
@@ -6572,7 +6486,7 @@ void spr_uncore_cpu_init(void)
 		 * of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a
 		 * firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it.
 		 */
-		rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
+		rdmsrq(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
 		/*
 		 * The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact
 		 * the EMR XCC. Don't let the value from the MSR replace the existing value.
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 45b1866ff051..7f5007a4752a 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -3,6 +3,8 @@
 #include <linux/sysfs.h>
 #include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
+
 #include "probe.h"
 
 enum perf_msr_id {
@@ -231,7 +233,7 @@ static inline u64 msr_read_counter(struct perf_event *event)
 	u64 now;
 
 	if (event->hw.event_base)
-		rdmsrl(event->hw.event_base, now);
+		rdmsrq(event->hw.event_base, now);
 	else
 		now = rdtsc_ordered();
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 31c2771545a6..2b969386dcdd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -17,6 +17,7 @@
 #include <asm/fpu/xstate.h>
 #include <asm/intel_ds.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 /* To enable MSR tracing please use the generic trace points. */
 
@@ -110,9 +111,26 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+	return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
 static inline bool is_branch_counters_group(struct perf_event *event)
 {
-	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
+}
+
+static inline bool is_pebs_counter_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
+}
+
+static inline bool is_acr_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
 }
 
 struct amd_nb {
@@ -256,6 +274,7 @@ struct cpu_hw_events {
 	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
 
 	int			n_excl; /* the number of exclusive events */
+	int			n_late_setup; /* the num of events needs late setup */
 
 	unsigned int		txn_flags;
 	int			is_fake;
@@ -281,6 +300,10 @@ struct cpu_hw_events {
 	u64			fixed_ctrl_val;
 	u64			active_fixed_ctrl_val;
 
+	/* Intel ACR configuration */
+	u64			acr_cfg_b[X86_PMC_IDX_MAX];
+	u64			acr_cfg_c[X86_PMC_IDX_MAX];
+
 	/*
 	 * Intel LBR bits
 	 */
@@ -669,18 +692,6 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
-/*
- * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
- * of the core. Bits 31-24 indicates its core type (Core or Atom)
- * and Bits [23:0] indicates the native model ID of the core.
- * Core type and native model ID are defined in below enumerations.
- */
-enum hybrid_cpu_type {
-	HYBRID_INTEL_NONE,
-	HYBRID_INTEL_ATOM	= 0x20,
-	HYBRID_INTEL_CORE	= 0x40,
-};
-
 #define X86_HYBRID_PMU_ATOM_IDX		0
 #define X86_HYBRID_PMU_CORE_IDX		1
 #define X86_HYBRID_PMU_TINY_IDX		2
@@ -697,11 +708,6 @@ enum hybrid_pmu_type {
 	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-enum atom_native_id {
-	cmt_native_id           = 0x2,  /* Crestmont */
-	skt_native_id           = 0x3,  /* Skymont */
-};
-
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
@@ -719,6 +725,15 @@ struct x86_hybrid_pmu {
 			u64		fixed_cntr_mask64;
 			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	};
+
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -800,6 +815,11 @@ struct x86_pmu {
 	u64		(*update)(struct perf_event *event);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
+	void		(*late_setup)(void);
+	void		(*pebs_enable)(struct perf_event *event);
+	void		(*pebs_disable)(struct perf_event *event);
+	void		(*pebs_enable_all)(void);
+	void		(*pebs_disable_all)(void);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	unsigned	fixedctr;
@@ -816,6 +836,14 @@ struct x86_pmu {
 			u64		fixed_cntr_mask64;
 			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	};
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -869,7 +897,7 @@ struct x86_pmu {
 
 	void		(*check_microcode)(void);
 	void		(*sched_task)(struct perf_event_pmu_context *pmu_ctx,
-				      bool sched_in);
+				      struct task_struct *task, bool sched_in);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -882,7 +910,7 @@ struct x86_pmu {
 	 */
 	unsigned int	bts			:1,
 			bts_active		:1,
-			pebs			:1,
+			ds_pebs			:1,
 			pebs_active		:1,
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
@@ -914,6 +942,7 @@ struct x86_pmu {
 		const int	*lbr_sel_map;	   /* lbr_select mappings */
 		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
 	};
+	u64		lbr_callstack_users;	   /* lbr callstack system wide users */
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
 	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
 
@@ -952,14 +981,6 @@ struct x86_pmu {
 	int		num_topdown_events;
 
 	/*
-	 * perf task context (i.e. struct perf_event_pmu_context::task_ctx_data)
-	 * switch helper to bridge calls from perf/core to perf/x86.
-	 * See struct pmu::swap_task_ctx() usage for examples;
-	 */
-	void		(*swap_task_ctx)(struct perf_event_pmu_context *prev_epc,
-					 struct perf_event_pmu_context *next_epc);
-
-	/*
 	 * AMD bits
 	 */
 	unsigned int	amd_nb_constraints : 1;
@@ -994,7 +1015,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	enum hybrid_cpu_type (*get_hybrid_cpu_type)	(void);
+	enum intel_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
@@ -1060,6 +1081,7 @@ do {									\
 #define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
 #define PMU_FL_RETIRE_LATENCY	0x200 /* Support Retire Latency in PEBS */
 #define PMU_FL_BR_CNTR		0x400 /* Support branch counter logging */
+#define PMU_FL_DYN_CONSTRAINT	0x800 /* Needs dynamic constraint */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1102,11 +1124,18 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\
 	.pmu_type	= _pmu,						\
 }
 
+int is_x86_event(struct perf_event *event);
 struct pmu *x86_get_pmu(unsigned int cpu);
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
+DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
+DECLARE_STATIC_CALL(x86_pmu_late_setup,	*x86_pmu.late_setup);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {
@@ -1148,6 +1177,12 @@ extern u64 __read_mostly hw_cache_extra_regs
 
 u64 x86_perf_event_update(struct perf_event *event);
 
+static inline u64 intel_pmu_topdown_event_update(struct perf_event *event, u64 *val)
+{
+	return x86_perf_event_update(event);
+}
+DECLARE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
+
 static inline unsigned int x86_pmu_config_addr(int index)
 {
 	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
@@ -1208,16 +1243,16 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 
 	if (hwc->extra_reg.reg)
-		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
+		wrmsrq(hwc->extra_reg.reg, hwc->extra_reg.config);
 
 	/*
 	 * Add enabled Merge event on next counter
 	 * if large increment event being enabled on this counter
 	 */
 	if (is_counter_pair(hwc))
-		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
+		wrmsrq(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
 
-	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
+	wrmsrq(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
 void x86_pmu_enable_all(int added);
@@ -1233,10 +1268,10 @@ static inline void x86_pmu_disable_event(struct perf_event *event)
 	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
+	wrmsrq(hwc->config_base, hwc->config & ~disable_mask);
 
 	if (is_counter_pair(hwc))
-		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
+		wrmsrq(x86_pmu_config_addr(hwc->idx + 1), 0);
 }
 
 void x86_pmu_enable_event(struct perf_event *event);
@@ -1394,7 +1429,8 @@ void amd_pmu_lbr_reset(void);
 void amd_pmu_lbr_read(void);
 void amd_pmu_lbr_add(struct perf_event *event);
 void amd_pmu_lbr_del(struct perf_event *event);
-void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in);
 void amd_pmu_lbr_enable_all(void);
 void amd_pmu_lbr_disable_all(void);
 int amd_pmu_lbr_hw_config(struct perf_event *event);
@@ -1403,12 +1439,12 @@ static __always_inline void __amd_pmu_lbr_disable(void)
 {
 	u64 dbg_ctl, dbg_extn_cfg;
 
-	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
-	wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
+	rdmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+	wrmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
 
 	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
 	}
 }
 
@@ -1448,7 +1484,8 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 	perf_sched_cb_dec(event->pmu);
 }
 
-void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in);
 #else
 static inline int amd_brs_init(void)
 {
@@ -1473,7 +1510,8 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 {
 }
 
-static inline void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static inline void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+					  struct task_struct *task, bool sched_in)
 {
 }
 
@@ -1538,21 +1576,21 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 
 static __always_inline void __intel_pmu_pebs_disable_all(void)
 {
-	wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+	wrmsrq(MSR_IA32_PEBS_ENABLE, 0);
 }
 
 static __always_inline void __intel_pmu_arch_lbr_disable(void)
 {
-	wrmsrl(MSR_ARCH_LBR_CTL, 0);
+	wrmsrq(MSR_ARCH_LBR_CTL, 0);
 }
 
 static __always_inline void __intel_pmu_lbr_disable(void)
 {
 	u64 debugctl;
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
@@ -1587,6 +1625,8 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
+void intel_pmu_late_setup(void);
+
 u64 grt_latency_data(struct perf_event *event, u64 status);
 
 u64 cmt_latency_data(struct perf_event *event, u64 status);
@@ -1643,20 +1683,20 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
-void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
+
+void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
-void intel_ds_init(void);
+void intel_pebs_init(void);
 
 void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
 				struct cpu_hw_events *cpuc,
 				struct perf_event *event);
 
-void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
-				 struct perf_event_pmu_context *next_epc);
-
-void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			      struct task_struct *task, bool sched_in);
 
 u64 lbr_from_signext_quirk_wr(u64 val);
 
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 6c977c19f2cd..70078334e4a3 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -2,23 +2,24 @@
 /*
  * struct hw_perf_event.flags flags
  */
-PERF_ARCH(PEBS_LDLAT,		0x00001) /* ld+ldlat data address sampling */
-PERF_ARCH(PEBS_ST,		0x00002) /* st data address sampling */
-PERF_ARCH(PEBS_ST_HSW,		0x00004) /* haswell style datala, store */
-PERF_ARCH(PEBS_LD_HSW,		0x00008) /* haswell style datala, load */
-PERF_ARCH(PEBS_NA_HSW,		0x00010) /* haswell style datala, unknown */
-PERF_ARCH(EXCL,			0x00020) /* HT exclusivity on counter */
-PERF_ARCH(DYNAMIC,		0x00040) /* dynamic alloc'd constraint */
-			/*	0x00080	*/
-PERF_ARCH(EXCL_ACCT,		0x00100) /* accounted EXCL event */
-PERF_ARCH(AUTO_RELOAD,		0x00200) /* use PEBS auto-reload */
-PERF_ARCH(LARGE_PEBS,		0x00400) /* use large PEBS */
-PERF_ARCH(PEBS_VIA_PT,		0x00800) /* use PT buffer for PEBS */
-PERF_ARCH(PAIR,			0x01000) /* Large Increment per Cycle */
-PERF_ARCH(LBR_SELECT,		0x02000) /* Save/Restore MSR_LBR_SELECT */
-PERF_ARCH(TOPDOWN,		0x04000) /* Count Topdown slots/metrics events */
-PERF_ARCH(PEBS_STLAT,		0x08000) /* st+stlat data address sampling */
-PERF_ARCH(AMD_BRS,		0x10000) /* AMD Branch Sampling */
-PERF_ARCH(PEBS_LAT_HYBRID,	0x20000) /* ld and st lat for hybrid */
-PERF_ARCH(NEEDS_BRANCH_STACK,	0x40000) /* require branch stack setup */
-PERF_ARCH(BRANCH_COUNTERS,	0x80000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(PEBS_LDLAT,		0x0000001) /* ld+ldlat data address sampling */
+PERF_ARCH(PEBS_ST,		0x0000002) /* st data address sampling */
+PERF_ARCH(PEBS_ST_HSW,		0x0000004) /* haswell style datala, store */
+PERF_ARCH(PEBS_LD_HSW,		0x0000008) /* haswell style datala, load */
+PERF_ARCH(PEBS_NA_HSW,		0x0000010) /* haswell style datala, unknown */
+PERF_ARCH(EXCL,			0x0000020) /* HT exclusivity on counter */
+PERF_ARCH(DYNAMIC,		0x0000040) /* dynamic alloc'd constraint */
+PERF_ARCH(PEBS_CNTR,		0x0000080) /* PEBS counters snapshot */
+PERF_ARCH(EXCL_ACCT,		0x0000100) /* accounted EXCL event */
+PERF_ARCH(AUTO_RELOAD,		0x0000200) /* use PEBS auto-reload */
+PERF_ARCH(LARGE_PEBS,		0x0000400) /* use large PEBS */
+PERF_ARCH(PEBS_VIA_PT,		0x0000800) /* use PT buffer for PEBS */
+PERF_ARCH(PAIR,			0x0001000) /* Large Increment per Cycle */
+PERF_ARCH(LBR_SELECT,		0x0002000) /* Save/Restore MSR_LBR_SELECT */
+PERF_ARCH(TOPDOWN,		0x0004000) /* Count Topdown slots/metrics events */
+PERF_ARCH(PEBS_STLAT,		0x0008000) /* st+stlat data address sampling */
+PERF_ARCH(AMD_BRS,		0x0010000) /* AMD Branch Sampling */
+PERF_ARCH(PEBS_LAT_HYBRID,	0x0020000) /* ld and st lat for hybrid */
+PERF_ARCH(NEEDS_BRANCH_STACK,	0x0040000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS,	0x0080000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(ACR,			0x0100000) /* Auto counter reload */
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
index 600bf8d15c0c..bb719d0d3f0b 100644
--- a/arch/x86/events/probe.c
+++ b/arch/x86/events/probe.c
@@ -2,6 +2,8 @@
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/bits.h>
+
+#include <asm/msr.h>
 #include "probe.h"
 
 static umode_t
@@ -43,7 +45,7 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
 			if (msr[bit].test && !msr[bit].test(bit, data))
 				continue;
 			/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
-			if (rdmsrl_safe(msr[bit].msr, &val))
+			if (rdmsrq_safe(msr[bit].msr, &val))
 				continue;
 
 			mask = msr[bit].mask;
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82..defd86137f12 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -65,6 +65,7 @@
 #include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/msr.h>
 #include "perf_event.h"
 #include "probe.h"
 
@@ -192,7 +193,7 @@ static inline unsigned int get_rapl_pmu_idx(int cpu, int scope)
 static inline u64 rapl_read_counter(struct perf_event *event)
 {
 	u64 raw;
-	rdmsrl(event->hw.event_base, raw);
+	rdmsrq(event->hw.event_base, raw);
 	return raw;
 }
 
@@ -221,7 +222,7 @@ static u64 rapl_event_update(struct perf_event *event)
 
 	prev_raw_count = local64_read(&hwc->prev_count);
 	do {
-		rdmsrl(event->hw.event_base, new_raw_count);
+		rdmsrq(event->hw.event_base, new_raw_count);
 	} while (!local64_try_cmpxchg(&hwc->prev_count,
 				      &prev_raw_count, new_raw_count));
 
@@ -274,8 +275,7 @@ static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu)
 {
 	struct hrtimer *hr = &rapl_pmu->hrtimer;
 
-	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hr->function = rapl_hrtimer_handle;
+	hrtimer_setup(hr, rapl_hrtimer_handle, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 }
 
 static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu,
@@ -611,8 +611,8 @@ static int rapl_check_hw_unit(void)
 	u64 msr_rapl_power_unit_bits;
 	int i;
 
-	/* protect rdmsrl() to handle virtualization */
-	if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
+	/* protect rdmsrq() to handle virtualization */
+	if (rdmsrq_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
 		return -1;
 	for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++)
 		rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
@@ -730,6 +730,7 @@ static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_
 {
 	int nr_rapl_pmu = topology_max_packages();
 	struct rapl_pmus *rapl_pmus;
+	int ret;
 
 	/*
 	 * rapl_pmu_scope must be either PKG, DIE or CORE
@@ -761,7 +762,11 @@ static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_
 	rapl_pmus->pmu.module		= THIS_MODULE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
 
-	return init_rapl_pmu(rapl_pmus);
+	ret = init_rapl_pmu(rapl_pmus);
+	if (ret)
+		kfree(rapl_pmus);
+
+	return ret;
 }
 
 static struct rapl_model model_snb = {
@@ -879,6 +884,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };
diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c
index dab4ed199227..77fd00b3305e 100644
--- a/arch/x86/events/utils.c
+++ b/arch/x86/events/utils.c
@@ -2,6 +2,7 @@
 #include <asm/insn.h>
 #include <linux/mm.h>
 
+#include <asm/msr.h>
 #include "perf_event.h"
 
 static int decode_branch_type(struct insn *insn)
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 2fd9b0cf9a5e..4bdfcf091200 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -15,6 +15,7 @@
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 
 #include "../perf_event.h"
 
@@ -254,26 +255,26 @@ static __initconst const u64 zxe_hw_cache_event_ids
 
 static void zhaoxin_pmu_disable_all(void)
 {
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 }
 
 static void zhaoxin_pmu_enable_all(int added)
 {
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
 }
 
 static inline u64 zhaoxin_pmu_get_status(void)
 {
 	u64 status;
 
-	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
 
 	return status;
 }
 
 static inline void zhaoxin_pmu_ack_status(u64 ack)
 {
-	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+	wrmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
 static inline void zxc_pmu_ack_status(u64 ack)
@@ -293,9 +294,9 @@ static void zhaoxin_pmu_disable_fixed(struct hw_perf_event *hwc)
 
 	mask = 0xfULL << (idx * 4);
 
-	rdmsrl(hwc->config_base, ctrl_val);
+	rdmsrq(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
-	wrmsrl(hwc->config_base, ctrl_val);
+	wrmsrq(hwc->config_base, ctrl_val);
 }
 
 static void zhaoxin_pmu_disable_event(struct perf_event *event)
@@ -329,10 +330,10 @@ static void zhaoxin_pmu_enable_fixed(struct hw_perf_event *hwc)
 	bits <<= (idx * 4);
 	mask = 0xfULL << (idx * 4);
 
-	rdmsrl(hwc->config_base, ctrl_val);
+	rdmsrq(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	ctrl_val |= bits;
-	wrmsrl(hwc->config_base, ctrl_val);
+	wrmsrq(hwc->config_base, ctrl_val);
 }
 
 static void zhaoxin_pmu_enable_event(struct perf_event *event)
@@ -397,8 +398,7 @@ again:
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 3a1548054b48..d55f494f471d 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y			:= hv_init.o mmu.o nested.o irqdomain.o ivm.o
-obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
+obj-$(CONFIG_X86_64)	+= hv_apic.o
 obj-$(CONFIG_HYPERV_VTL_MODE)	+= hv_vtl.o
 
 ifdef CONFIG_X86_64
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index f022d5f64fb6..bfde0a3498b9 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -28,6 +28,7 @@
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 
 #include <asm/trace/hyperv.h>
 
@@ -37,7 +38,7 @@ static u64 hv_apic_icr_read(void)
 {
 	u64 reg_val;
 
-	rdmsrl(HV_X64_MSR_ICR, reg_val);
+	rdmsrq(HV_X64_MSR_ICR, reg_val);
 	return reg_val;
 }
 
@@ -49,7 +50,7 @@ static void hv_apic_icr_write(u32 low, u32 id)
 	reg_val = reg_val << 32;
 	reg_val |= low;
 
-	wrmsrl(HV_X64_MSR_ICR, reg_val);
+	wrmsrq(HV_X64_MSR_ICR, reg_val);
 }
 
 static u32 hv_apic_read(u32 reg)
@@ -75,10 +76,10 @@ static void hv_apic_write(u32 reg, u32 val)
 {
 	switch (reg) {
 	case APIC_EOI:
-		wrmsr(HV_X64_MSR_EOI, val, 0);
+		wrmsrq(HV_X64_MSR_EOI, val);
 		break;
 	case APIC_TASKPRI:
-		wrmsr(HV_X64_MSR_TPR, val, 0);
+		wrmsrq(HV_X64_MSR_TPR, val);
 		break;
 	default:
 		native_apic_mem_write(reg, val);
@@ -92,7 +93,7 @@ static void hv_apic_eoi_write(void)
 	if (hvp && (xchg(&hvp->apic_assist, 0) & 0x1))
 		return;
 
-	wrmsr(HV_X64_MSR_EOI, APIC_EOI_ACK, 0);
+	wrmsrq(HV_X64_MSR_EOI, APIC_EOI_ACK);
 }
 
 static bool cpu_is_self(int cpu)
@@ -145,6 +146,11 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 	}
 
+	/*
+	 * For this hypercall, Hyper-V treats the valid_bank_mask field
+	 * of ipi_arg->vp_set as part of the fixed size input header.
+	 * So the variable input header size is equal to nr_bank.
+	 */
 	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
 				     ipi_arg, NULL);
 
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 173005e6a95d..5d27194a2efa 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -21,6 +21,7 @@
 #include <asm/hypervisor.h>
 #include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
+#include <asm/msr.h>
 #include <asm/idtentry.h>
 #include <asm/set_memory.h>
 #include <linux/kexec.h>
@@ -34,9 +35,6 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 
-u64 hv_current_partition_id = ~0ull;
-EXPORT_SYMBOL_GPL(hv_current_partition_id);
-
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -65,7 +63,7 @@ static int hyperv_init_ghcb(void)
 	 * returned by MSR_AMD64_SEV_ES_GHCB is above shared
 	 * memory boundary and map it here.
 	 */
-	rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+	rdmsrq(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
 
 	/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 	ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary;
@@ -93,12 +91,12 @@ static int hv_cpu_init(unsigned int cpu)
 		return 0;
 
 	hvp = &hv_vp_assist_page[cpu];
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		/*
 		 * For root partition we get the hypervisor provided VP assist
 		 * page, instead of allocating a new page.
 		 */
-		rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 		*hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
 				PAGE_SIZE, MEMREMAP_WB);
 	} else {
@@ -131,7 +129,7 @@ static int hv_cpu_init(unsigned int cpu)
 	}
 	if (!WARN_ON(!(*hvp))) {
 		msr.enable = 1;
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 	}
 
 	return hyperv_init_ghcb();
@@ -143,7 +141,7 @@ static void hv_reenlightenment_notify(struct work_struct *dummy)
 {
 	struct hv_tsc_emulation_status emu_status;
 
-	rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+	rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
 
 	/* Don't issue the callback if TSC accesses are not emulated */
 	if (hv_reenlightenment_cb && emu_status.inprogress)
@@ -156,11 +154,11 @@ void hyperv_stop_tsc_emulation(void)
 	u64 freq;
 	struct hv_tsc_emulation_status emu_status;
 
-	rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+	rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
 	emu_status.inprogress = 0;
-	wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+	wrmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
 
-	rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+	rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
 	tsc_khz = div64_u64(freq, 1000);
 }
 EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
@@ -206,8 +204,8 @@ void set_hv_tscchange_cb(void (*cb)(void))
 
 	re_ctrl.target_vp = hv_vp_index[get_cpu()];
 
-	wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
-	wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+	wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+	wrmsrq(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
 
 	put_cpu();
 }
@@ -220,9 +218,9 @@ void clear_hv_tscchange_cb(void)
 	if (!hv_reenlightenment_available())
 		return;
 
-	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+	rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
 	re_ctrl.enabled = 0;
-	wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+	wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
 
 	hv_reenlightenment_cb = NULL;
 }
@@ -245,7 +243,7 @@ static int hv_cpu_die(unsigned int cpu)
 
 	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
 		union hv_vp_assist_msr_contents msr = { 0 };
-		if (hv_root_partition) {
+		if (hv_root_partition()) {
 			/*
 			 * For root partition the VP assist page is mapped to
 			 * hypervisor provided page, and thus we unmap the
@@ -254,16 +252,16 @@ static int hv_cpu_die(unsigned int cpu)
 			 */
 			memunmap(hv_vp_assist_page[cpu]);
 			hv_vp_assist_page[cpu] = NULL;
-			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+			rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 			msr.enable = 0;
 		}
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 	}
 
 	if (hv_reenlightenment_cb == NULL)
 		return 0;
 
-	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+	rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
 	if (re_ctrl.target_vp == hv_vp_index[cpu]) {
 		/*
 		 * Reassign reenlightenment notifications to some other online
@@ -277,7 +275,7 @@ static int hv_cpu_die(unsigned int cpu)
 		else
 			re_ctrl.enabled = 0;
 
-		wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+		wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
 	}
 
 	return 0;
@@ -320,7 +318,7 @@ static int hv_suspend(void)
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int ret;
 
-	if (hv_root_partition)
+	if (hv_root_partition())
 		return -EPERM;
 
 	/*
@@ -334,9 +332,9 @@ static int hv_suspend(void)
 	hv_hypercall_pg = NULL;
 
 	/* Disable the hypercall page in the hypervisor */
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 0;
-	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	ret = hv_cpu_die(0);
 	return ret;
@@ -351,11 +349,11 @@ static void hv_resume(void)
 	WARN_ON(ret);
 
 	/* Re-enable the hypercall page */
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
 	hypercall_msr.guest_physical_address =
 		vmalloc_to_pfn(hv_hypercall_pg_saved);
-	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	hv_hypercall_pg = hv_hypercall_pg_saved;
 	hv_hypercall_pg_saved = NULL;
@@ -393,24 +391,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
-static void __init hv_get_partition_id(void)
-{
-	struct hv_get_partition_id *output_page;
-	u64 status;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
-	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
-	if (!hv_result_success(status)) {
-		/* No point in proceeding if this failed */
-		pr_err("Failed to get partition ID: %lld\n", status);
-		BUG();
-	}
-	hv_current_partition_id = output_page->partition_id;
-	local_irq_restore(flags);
-}
-
 #if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
 static u8 __init get_vtl(void)
 {
@@ -520,7 +500,7 @@ void __init hyperv_init(void)
 	 * in such a VM and is only used in such a VM.
 	 */
 	guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+	wrmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
 	/* With the paravisor, the VM must also write the ID via GHCB/GHCI */
 	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
@@ -536,10 +516,10 @@ void __init hyperv_init(void)
 	if (hv_hypercall_pg == NULL)
 		goto clean_guest_os_id;
 
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
 
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		struct page *pg;
 		void *src;
 
@@ -553,7 +533,7 @@ void __init hyperv_init(void)
 		 * so it is populated with code, then copy the code to an
 		 * executable page.
 		 */
-		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 		pg = vmalloc_to_page(hv_hypercall_pg);
 		src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
@@ -565,7 +545,7 @@ void __init hyperv_init(void)
 		hv_remap_tsc_clocksource();
 	} else {
 		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
-		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	}
 
 skip_hypercall_pg_init:
@@ -605,17 +585,15 @@ skip_hypercall_pg_init:
 
 	register_syscore_ops(&hv_syscore_ops);
 
-	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
 
-	BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);
-
 #ifdef CONFIG_PCI_MSI
 	/*
 	 * If we're running as root, we want to create our own PCI MSI domain.
 	 * We can't set this in hv_pci_init because that would be too late.
 	 */
-	if (hv_root_partition)
+	if (hv_root_partition())
 		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
 #endif
 
@@ -631,7 +609,7 @@ skip_hypercall_pg_init:
 	return;
 
 clean_guest_os_id:
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+	wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
 	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
 	cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
 free_ghcb_page:
@@ -652,7 +630,7 @@ void hyperv_cleanup(void)
 	union hv_reference_tsc_msr tsc_msr;
 
 	/* Reset our OS id */
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+	wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
 	hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
 
 	/*
@@ -690,18 +668,18 @@ void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
 		return;
 	panic_reported = true;
 
-	rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+	rdmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	wrmsrl(HV_X64_MSR_CRASH_P0, err);
-	wrmsrl(HV_X64_MSR_CRASH_P1, guest_id);
-	wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip);
-	wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax);
-	wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp);
+	wrmsrq(HV_X64_MSR_CRASH_P0, err);
+	wrmsrq(HV_X64_MSR_CRASH_P1, guest_id);
+	wrmsrq(HV_X64_MSR_CRASH_P2, regs->ip);
+	wrmsrq(HV_X64_MSR_CRASH_P3, regs->ax);
+	wrmsrq(HV_X64_MSR_CRASH_P4, regs->sp);
 
 	/*
 	 * Let Hyper-V know there is crash data available
 	 */
-	wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+	wrmsrq(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
 }
 EXPORT_SYMBOL_GPL(hyperv_report_panic);
 
@@ -724,7 +702,7 @@ bool hv_is_hyperv_initialized(void)
 	 * that the hypercall page is setup
 	 */
 	hypercall_msr.as_uint64 = 0;
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
 	return hypercall_msr.enable;
 }
diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c
deleted file mode 100644
index ac4c834d4435..000000000000
--- a/arch/x86/hyperv/hv_proc.c
+++ /dev/null
@@ -1,198 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/clockchips.h>
-#include <linux/slab.h>
-#include <linux/cpuhotplug.h>
-#include <linux/minmax.h>
-#include <asm/hypervisor.h>
-#include <asm/mshyperv.h>
-#include <asm/apic.h>
-
-#include <asm/trace/hyperv.h>
-
-/*
- * See struct hv_deposit_memory. The first u64 is partition ID, the rest
- * are GPAs.
- */
-#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1)
-
-/* Deposits exact number of pages. Must be called with interrupts enabled.  */
-int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
-{
-	struct page **pages, *page;
-	int *counts;
-	int num_allocations;
-	int i, j, page_count;
-	int order;
-	u64 status;
-	int ret;
-	u64 base_pfn;
-	struct hv_deposit_memory *input_page;
-	unsigned long flags;
-
-	if (num_pages > HV_DEPOSIT_MAX)
-		return -E2BIG;
-	if (!num_pages)
-		return 0;
-
-	/* One buffer for page pointers and counts */
-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-	pages = page_address(page);
-
-	counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL);
-	if (!counts) {
-		free_page((unsigned long)pages);
-		return -ENOMEM;
-	}
-
-	/* Allocate all the pages before disabling interrupts */
-	i = 0;
-
-	while (num_pages) {
-		/* Find highest order we can actually allocate */
-		order = 31 - __builtin_clz(num_pages);
-
-		while (1) {
-			pages[i] = alloc_pages_node(node, GFP_KERNEL, order);
-			if (pages[i])
-				break;
-			if (!order) {
-				ret = -ENOMEM;
-				num_allocations = i;
-				goto err_free_allocations;
-			}
-			--order;
-		}
-
-		split_page(pages[i], order);
-		counts[i] = 1 << order;
-		num_pages -= counts[i];
-		i++;
-	}
-	num_allocations = i;
-
-	local_irq_save(flags);
-
-	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
-
-	input_page->partition_id = partition_id;
-
-	/* Populate gpa_page_list - these will fit on the input page */
-	for (i = 0, page_count = 0; i < num_allocations; ++i) {
-		base_pfn = page_to_pfn(pages[i]);
-		for (j = 0; j < counts[i]; ++j, ++page_count)
-			input_page->gpa_page_list[page_count] = base_pfn + j;
-	}
-	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
-				     page_count, 0, input_page, NULL);
-	local_irq_restore(flags);
-	if (!hv_result_success(status)) {
-		pr_err("Failed to deposit pages: %lld\n", status);
-		ret = hv_result(status);
-		goto err_free_allocations;
-	}
-
-	ret = 0;
-	goto free_buf;
-
-err_free_allocations:
-	for (i = 0; i < num_allocations; ++i) {
-		base_pfn = page_to_pfn(pages[i]);
-		for (j = 0; j < counts[i]; ++j)
-			__free_page(pfn_to_page(base_pfn + j));
-	}
-
-free_buf:
-	free_page((unsigned long)pages);
-	kfree(counts);
-	return ret;
-}
-
-int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
-{
-	struct hv_input_add_logical_processor *input;
-	struct hv_output_add_logical_processor *output;
-	u64 status;
-	unsigned long flags;
-	int ret = HV_STATUS_SUCCESS;
-
-	/*
-	 * When adding a logical processor, the hypervisor may return
-	 * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more
-	 * pages and retry.
-	 */
-	do {
-		local_irq_save(flags);
-
-		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-		/* We don't do anything with the output right now */
-		output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-		input->lp_index = lp_index;
-		input->apic_id = apic_id;
-		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
-		status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
-					 input, output);
-		local_irq_restore(flags);
-
-		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (!hv_result_success(status)) {
-				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
-				       lp_index, apic_id, status);
-				ret = hv_result(status);
-			}
-			break;
-		}
-		ret = hv_call_deposit_pages(node, hv_current_partition_id, 1);
-	} while (!ret);
-
-	return ret;
-}
-
-int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
-{
-	struct hv_create_vp *input;
-	u64 status;
-	unsigned long irq_flags;
-	int ret = HV_STATUS_SUCCESS;
-
-	/* Root VPs don't seem to need pages deposited */
-	if (partition_id != hv_current_partition_id) {
-		/* The value 90 is empirically determined. It may change. */
-		ret = hv_call_deposit_pages(node, partition_id, 90);
-		if (ret)
-			return ret;
-	}
-
-	do {
-		local_irq_save(irq_flags);
-
-		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-
-		input->partition_id = partition_id;
-		input->vp_index = vp_index;
-		input->flags = flags;
-		input->subnode_type = HV_SUBNODE_ANY;
-		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
-		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
-		local_irq_restore(irq_flags);
-
-		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (!hv_result_success(status)) {
-				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
-				       vp_index, flags, status);
-				ret = hv_result(status);
-			}
-			break;
-		}
-		ret = hv_call_deposit_pages(node, partition_id, 1);
-
-	} while (!ret);
-
-	return ret;
-}
-
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index 151e851bef09..81b006601370 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -15,6 +15,7 @@
 #include <asm/mshyperv.h>
 #include <asm/paravirt.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 
 static bool hv_pvspin __initdata = true;
 
@@ -39,18 +40,18 @@ static void hv_qlock_wait(u8 *byte, u8 val)
 	 * To prevent a race against the unlock path it is required to
 	 * disable interrupts before accessing the HV_X64_MSR_GUEST_IDLE
 	 * MSR. Otherwise, if the IPI from hv_qlock_kick() arrives between
-	 * the lock value check and the rdmsrl() then the vCPU might be put
+	 * the lock value check and the rdmsrq() then the vCPU might be put
 	 * into 'idle' state by the hypervisor and kept in that state for
 	 * an unspecified amount of time.
 	 */
 	local_irq_save(flags);
 	/*
-	 * Only issue the rdmsrl() when the lock state has not changed.
+	 * Only issue the rdmsrq() when the lock state has not changed.
 	 */
 	if (READ_ONCE(*byte) == val) {
 		unsigned long msr_val;
 
-		rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+		rdmsrq(HV_X64_MSR_GUEST_IDLE, msr_val);
 
 		(void)msr_val;
 	}
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 4e1b1e3b5658..4580936dcb03 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -11,7 +11,9 @@
 #include <asm/desc.h>
 #include <asm/i8259.h>
 #include <asm/mshyperv.h>
+#include <asm/msr.h>
 #include <asm/realmode.h>
+#include <asm/reboot.h>
 #include <../kernel/smpboot.h>
 
 extern struct boot_params boot_params;
@@ -22,6 +24,36 @@ static bool __init hv_vtl_msi_ext_dest_id(void)
 	return true;
 }
 
+/*
+ * The `native_machine_emergency_restart` function from `reboot.c` writes
+ * to the physical address 0x472 to indicate the type of reboot for the
+ * firmware. We cannot have that in VSM as the memory composition might
+ * be more generic, and such write effectively corrupts the memory thus
+ * making diagnostics harder at the very least.
+ */
+static void  __noreturn hv_vtl_emergency_restart(void)
+{
+	/*
+	 * Cause a triple fault and the immediate reset. Here the code does not run
+	 * on the top of any firmware, whereby cannot reach out to its services.
+	 * The inifinite loop is for the improbable case that the triple fault does
+	 * not work and have to preserve the state intact for debugging.
+	 */
+	for (;;) {
+		idt_invalidate();
+		__asm__ __volatile__("int3");
+	}
+}
+
+/*
+ * The only way to restart in the VTL mode is to triple fault as the kernel runs
+ * as firmware.
+ */
+static void  __noreturn hv_vtl_restart(char __maybe_unused *cmd)
+{
+	hv_vtl_emergency_restart();
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -30,6 +62,7 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.realmode_init = x86_init_noop;
 	x86_init.irqs.pre_vector_init = x86_init_noop;
 	x86_init.timers.timer_init = x86_init_noop;
+	x86_init.resources.probe_roms = x86_init_noop;
 
 	/* Avoid searching for BIOS MP tables */
 	x86_init.mpparse.find_mptable = x86_init_noop;
@@ -117,11 +150,11 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored)
 	input->vp_context.rip = rip;
 	input->vp_context.rsp = rsp;
 	input->vp_context.rflags = 0x0000000000000002;
-	input->vp_context.efer = __rdmsr(MSR_EFER);
+	input->vp_context.efer = native_rdmsrq(MSR_EFER);
 	input->vp_context.cr0 = native_read_cr0();
 	input->vp_context.cr3 = __native_read_cr3();
 	input->vp_context.cr4 = native_read_cr4();
-	input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT);
+	input->vp_context.msr_cr_pat = native_rdmsrq(MSR_IA32_CR_PAT);
 	input->vp_context.idtr.limit = idt_ptr.size;
 	input->vp_context.idtr.base = idt_ptr.address;
 	input->vp_context.gdtr.limit = gdt_ptr.size;
@@ -235,6 +268,9 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 
 int __init hv_vtl_early_init(void)
 {
+	machine_ops.emergency_restart = hv_vtl_emergency_restart;
+	machine_ops.restart = hv_vtl_restart;
+
 	/*
 	 * `boot_cpu_has` returns the runtime feature support,
 	 * and here is the earliest it can be used.
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 64b921360b0f..31f0d29cbc5e 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -64,7 +64,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 	local_irq_restore(flags);
 
 	if (!hv_result_success(status))
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 
 	return hv_result(status);
 }
@@ -224,7 +224,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		kfree(stored_entry);
 
 		if (status != HV_STATUS_SUCCESS) {
-			pr_debug("%s: failed to unmap, status %lld", __func__, status);
+			hv_status_debug(status, "failed to unmap\n");
 			return;
 		}
 	}
@@ -273,7 +273,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 	status = hv_unmap_msi_interrupt(dev, &old_entry);
 
 	if (status != HV_STATUS_SUCCESS)
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 }
 
 static void hv_msi_free_irq(struct irq_domain *domain,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index dd68d9ad9b22..09a165a3c41e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -22,6 +22,7 @@
 #include <asm/realmode.h>
 #include <asm/e820/api.h>
 #include <asm/desc.h>
+#include <asm/msr.h>
 #include <uapi/asm/vmx.h>
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -110,12 +111,12 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
 
 static inline u64 rd_ghcb_msr(void)
 {
-	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
+	return native_rdmsrq(MSR_AMD64_SEV_ES_GHCB);
 }
 
 static inline void wr_ghcb_msr(u64 val)
 {
-	native_wrmsrl(MSR_AMD64_SEV_ES_GHCB, val);
+	native_wrmsrq(MSR_AMD64_SEV_ES_GHCB, val);
 }
 
 static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code,
@@ -338,7 +339,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 	vmsa->sev_features = sev_status >> 2;
 
 	ret = snp_set_vmsa(vmsa, true);
-	if (!ret) {
+	if (ret) {
 		pr_err("RMPADJUST(%llx) failed: %llx\n", (u64)vmsa, ret);
 		free_page((u64)vmsa);
 		return ret;
@@ -464,7 +465,6 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 			   enum hv_mem_host_visibility visibility)
 {
 	struct hv_gpa_range_for_visibility *input;
-	u16 pages_processed;
 	u64 hv_status;
 	unsigned long flags;
 
@@ -493,7 +493,7 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 	memcpy((void *)input->gpa_page_list, pfn, count * sizeof(*pfn));
 	hv_status = hv_do_rep_hypercall(
 			HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY, count,
-			0, input, &pages_processed);
+			0, input, NULL);
 	local_irq_restore(flags);
 
 	if (hv_result_success(hv_status))
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index cc8c3bd0e7c2..cfcb60468b01 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -205,6 +205,10 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
 	 * whole address space if we were asked to do more.
+	 *
+	 * For these hypercalls, Hyper-V treats the valid_bank_mask field
+	 * of flush->hv_vp_set as part of the fixed size input header.
+	 * So the variable input header size is equal to nr_bank.
 	 */
 	max_gvas =
 		(PAGE_SIZE - sizeof(*flush) - nr_bank *
@@ -239,5 +243,4 @@ void hyperv_setup_mmu_ops(void)
 
 	pr_info("Using hypercall for remote TLB flush\n");
 	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
-	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 58f4ddecc5fa..4566000e15c4 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -8,6 +8,7 @@ generated-y += syscalls_x32.h
 generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
+generated-y += cpufeaturemasks.h
 
 generic-y += early_ioremap.h
 generic-y += fprobe.h
diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
index 1dd14381bcb6..fab11192c60a 100644
--- a/arch/x86/include/asm/acrn.h
+++ b/arch/x86/include/asm/acrn.h
@@ -25,7 +25,7 @@ void acrn_remove_intr_handler(void);
 static inline u32 acrn_cpuid_base(void)
 {
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return hypervisor_cpuid_base("ACRNACRNACRN", 0);
+		return cpuid_base_hypervisor("ACRNACRNACRN", 0);
 
 	return 0;
 }
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b731305..15bc07a5ebb3 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -6,6 +6,7 @@
 #include <linux/stringify.h>
 #include <linux/objtool.h>
 #include <asm/asm.h>
+#include <asm/bug.h>
 
 #define ALT_FLAGS_SHIFT		16
 
@@ -15,7 +16,7 @@
 #define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature))
 #define ALT_CALL_ALWAYS		ALT_DIRECT_CALL(X86_FEATURE_ALWAYS)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stddef.h>
 
@@ -48,7 +49,7 @@
 		".popsection\n"				\
 		"671:"
 
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
+#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock "
 
 #else /* ! CONFIG_SMP */
 #define LOCK_PREFIX_HERE ""
@@ -82,25 +83,30 @@ struct alt_instr {
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __return_sites[],	__return_sites_end[];
+extern s32 __cfi_sites[],	__cfi_sites_end[];
+extern s32 __ibt_endbr_seal[],	__ibt_endbr_seal_end[];
+extern s32 __smp_locks[],	__smp_locks_end[];
+
 /*
  * Debug flag that can be tested to see whether alternative
  * instructions were patched in already:
  */
 extern int alternatives_patched;
-struct module;
 
 extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			       struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
-			  s32 *start_cfi, s32 *end_cfi, struct module *mod);
+			  s32 *start_cfi, s32 *end_cfi);
+
+struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
@@ -125,6 +131,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
 }
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_init_mod(struct module *mod);
+extern void its_fini_mod(struct module *mod);
+extern void its_free_mod(struct module *mod);
+extern u8 *its_static_thunk(int reg);
+#else /* CONFIG_MITIGATION_ITS */
+static inline void its_init_mod(struct module *mod) { }
+static inline void its_fini_mod(struct module *mod) { }
+static inline void its_free_mod(struct module *mod) { }
+static inline u8 *its_static_thunk(int reg)
+{
+	WARN_ONCE(1, "ITS not compiled in");
+
+	return NULL;
+}
+#endif
+
+#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL)
+extern bool cpu_wants_rethunk(void);
+extern bool cpu_wants_rethunk_at(void *addr);
+#else
+static __always_inline bool cpu_wants_rethunk(void)
+{
+	return false;
+}
+static __always_inline bool cpu_wants_rethunk_at(void *addr)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 extern void alternatives_smp_module_add(struct module *mod, char *name,
 					void *locks, void *locks_end,
@@ -237,10 +274,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * references: i.e., if used for a function, it would add the PLT
  * suffix.
  */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)			\
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input, clobbers...)	\
 	asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags)	\
 		: ALT_OUTPUT_SP(output)							\
-		: [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+		: [old] "i" (oldfunc), [new] "i" (newfunc)				\
+		  COMMA(input)								\
+		: clobbers)
 
 /*
  * Like alternative_call, but there are two features and respective functions.
@@ -249,24 +288,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, old function is used.
  */
 #define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,		\
-			   output, input...)						\
+			   output, input, clobbers...)					\
 	asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1,	\
 		"call %c[new2]", ft_flags2)						\
 		: ALT_OUTPUT_SP(output)							\
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),				\
-		  [new2] "i" (newfunc2), ## input)
-
-/*
- * use this macro(s) if you need more than one output parameter
- * in alternative_io
- */
-#define ASM_OUTPUT2(a...) a
-
-/*
- * use this macro if you need clobbers but no inputs in
- * alternative_{input,io,call}()
- */
-#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+		  [new2] "i" (newfunc2)							\
+		  COMMA(input)								\
+		: clobbers)
 
 #define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
 
@@ -286,7 +315,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 void BUG_func(void);
 void nop_func(void);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #ifdef CONFIG_SMP
 	.macro LOCK_PREFIX
@@ -344,11 +373,6 @@ void nop_func(void);
 	__ALTERNATIVE(\oldinstr, \newinstr, \ft_flags)
 .endm
 
-#define old_len			141b-140b
-#define new_len1		144f-143f
-#define new_len2		145f-144f
-#define new_len3		146f-145f
-
 /*
  * Same as ALTERNATIVE macro above but for two alternatives. If CPU
  * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
@@ -369,6 +393,6 @@ void nop_func(void);
 	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
 	newinstr_yes, ft_flags
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd/fch.h b/arch/x86/include/asm/amd/fch.h
new file mode 100644
index 000000000000..2cf5153edbc2
--- /dev/null
+++ b/arch/x86/include/asm/amd/fch.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_FCH_H_
+#define _ASM_X86_AMD_FCH_H_
+
+#define FCH_PM_BASE			0xFED80300
+
+/* Register offsets from PM base: */
+#define FCH_PM_DECODEEN			0x00
+#define FCH_PM_DECODEEN_SMBUS0SEL	GENMASK(20, 19)
+#define FCH_PM_SCRATCH			0x80
+#define FCH_PM_S5_RESET_STATUS		0xC0
+
+#endif /* _ASM_X86_AMD_FCH_H_ */
diff --git a/arch/x86/include/asm/amd_hsmp.h b/arch/x86/include/asm/amd/hsmp.h
index 03c2ce3edaf5..2137f62853ed 100644
--- a/arch/x86/include/asm/amd_hsmp.h
+++ b/arch/x86/include/asm/amd/hsmp.h
@@ -1,5 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-
 #ifndef _ASM_X86_AMD_HSMP_H_
 #define _ASM_X86_AMD_HSMP_H_
 
@@ -13,4 +12,5 @@ static inline int hsmp_send_message(struct hsmp_message *msg)
 	return -ENODEV;
 }
 #endif
+
 #endif /*_ASM_X86_AMD_HSMP_H_*/
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd/ibs.h
index cb2a5e113daa..3ee5903982c2 100644
--- a/arch/x86/include/asm/amd-ibs.h
+++ b/arch/x86/include/asm/amd/ibs.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_IBS_H
+#define _ASM_X86_AMD_IBS_H
+
 /*
  * From PPR Vol 1 for AMD Family 19h Model 01h B1
  * 55898 Rev 0.35 - Feb 5, 2021
@@ -64,7 +67,8 @@ union ibs_op_ctl {
 			opmaxcnt_ext:7,	/* 20-26: upper 7 bits of periodic op maximum count */
 			reserved0:5,	/* 27-31: reserved */
 			opcurcnt:27,	/* 32-58: periodic op counter current count */
-			reserved1:5;	/* 59-63: reserved */
+			ldlat_thrsh:4,	/* 59-62: Load Latency threshold */
+			ldlat_en:1;	/* 63: Load Latency enabled */
 	};
 };
 
@@ -150,3 +154,5 @@ struct perf_ibs_data {
 	};
 	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
 };
+
+#endif /* _ASM_X86_AMD_IBS_H */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd/nb.h
index 4c4efb93045e..ddb5108cf46c 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd/nb.h
@@ -4,7 +4,7 @@
 
 #include <linux/ioport.h>
 #include <linux/pci.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
 
 struct amd_nb_bus_dev_range {
 	u8 bus;
@@ -27,7 +27,6 @@ struct amd_l3_cache {
 };
 
 struct amd_northbridge {
-	struct pci_dev *root;
 	struct pci_dev *misc;
 	struct pci_dev *link;
 	struct amd_l3_cache l3_cache;
diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd/node.h
index 113ad3e8ee40..23fe617898a8 100644
--- a/arch/x86/include/asm/amd_node.h
+++ b/arch/x86/include/asm/amd/node.h
@@ -30,7 +30,31 @@ static inline u16 amd_num_nodes(void)
 	return topology_amd_nodes_per_pkg() * topology_max_packages();
 }
 
+#ifdef CONFIG_AMD_NODE
 int __must_check amd_smn_read(u16 node, u32 address, u32 *value);
 int __must_check amd_smn_write(u16 node, u32 address, u32 value);
 
+/* Should only be used by the HSMP driver. */
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write);
+#else
+static inline int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { return -ENODEV; }
+static inline int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return -ENODEV; }
+
+static inline int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_NODE */
+
+/* helper for use with read_poll_timeout */
+static inline int smn_read_register(u32 reg)
+{
+	int data, rc;
+
+	rc = amd_smn_read(0, reg, &data);
+	if (rc)
+		return rc;
+
+	return data;
+}
 #endif /*_ASM_X86_AMD_NODE_H_*/
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f21ff1932699..68e10e30fe9b 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -99,8 +99,8 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
 	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
-		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
-		       ASM_OUTPUT2("0" (v), "m" (*addr)));
+		       ASM_OUTPUT("=r" (v), "=m" (*addr)),
+		       ASM_INPUT("0" (v), "m" (*addr)));
 }
 
 static inline u32 native_apic_mem_read(u32 reg)
@@ -120,7 +120,7 @@ static inline bool apic_is_x2apic_enabled(void)
 {
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_IA32_APICBASE, &msr))
+	if (rdmsrq_safe(MSR_IA32_APICBASE, &msr))
 		return false;
 	return msr & X2APIC_ENABLE;
 }
@@ -209,12 +209,12 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 	    reg == APIC_LVR)
 		return;
 
-	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
+	wrmsrq(APIC_BASE_MSR + (reg >> 4), v);
 }
 
 static inline void native_apic_msr_eoi(void)
 {
-	__wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+	native_wrmsrq(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK);
 }
 
 static inline u32 native_apic_msr_read(u32 reg)
@@ -224,20 +224,20 @@ static inline u32 native_apic_msr_read(u32 reg)
 	if (reg == APIC_DFR)
 		return -1;
 
-	rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+	rdmsrq(APIC_BASE_MSR + (reg >> 4), msr);
 	return (u32)msr;
 }
 
 static inline void native_x2apic_icr_write(u32 low, u32 id)
 {
-	wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+	wrmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
 }
 
 static inline u64 native_x2apic_icr_read(void)
 {
 	unsigned long val;
 
-	rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+	rdmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), val);
 	return val;
 }
 
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index ba88edd0d58b..b5982b94bdba 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -16,9 +16,10 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res;
 
-	asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+	asm_inline (ALTERNATIVE("call __sw_hweight32",
+				"popcntl %[val], %[cnt]", X86_FEATURE_POPCNT)
+			 : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
+			 : [val] REG_IN (w));
 
 	return res;
 }
@@ -44,9 +45,10 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
 	unsigned long res;
 
-	asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+	asm_inline (ALTERNATIVE("call __sw_hweight64",
+				"popcntq %[val], %[cnt]", X86_FEATURE_POPCNT)
+			 : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
+			 : [val] REG_IN (w));
 
 	return res;
 }
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 3674006e3974..11c6fecc3ad7 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -16,10 +16,10 @@
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 
-#if defined(__GENKSYMS__) && defined(CONFIG_STACKPROTECTOR)
+#ifdef CONFIG_STACKPROTECTOR
 extern unsigned long __ref_stack_chk_guard;
 #endif
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 2bec0c89a95c..f963848024a5 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ASM_H
 #define _ASM_X86_ASM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 # define __ASM_FORM(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_RAW(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_COMMA(x, ...)	x,## __VA_ARGS__,
@@ -113,18 +113,13 @@
 
 #endif
 
-#ifndef __ASSEMBLY__
-#ifndef __pic__
+#ifndef __ASSEMBLER__
 static __always_inline __pure void *rip_rel_ptr(void *p)
 {
 	asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p));
 
 	return p;
 }
-#define RIP_REL_REF(var)	(*(typeof(&(var)))rip_rel_ptr(&(var)))
-#else
-#define RIP_REL_REF(var)	(var)
-#endif
 #endif
 
 /*
@@ -144,7 +139,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 # include <asm/extable_fixup_types.h>
 
 /* Exception table entry */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 # define _ASM_EXTABLE_TYPE(from, to, type)			\
 	.pushsection "__ex_table","a" ;				\
@@ -164,7 +159,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 #  define _ASM_NOKPROBE(entry)
 # endif
 
-#else /* ! __ASSEMBLY__ */
+#else /* ! __ASSEMBLER__ */
 
 # define DEFINE_EXTABLE_TYPE_REG \
 	".macro extable_type_reg type:req reg:req\n"						\
@@ -213,6 +208,17 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
+/* Insert a comma if args are non-empty */
+#define COMMA(x...)		__COMMA(x)
+#define __COMMA(...)		, ##__VA_ARGS__
+
+/*
+ * Combine multiple asm inline constraint args into a single arg for passing to
+ * another macro.
+ */
+#define ASM_OUTPUT(x...)	x
+#define ASM_INPUT(x...)		x
+
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -221,7 +227,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
  */
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define _ASM_EXTABLE(from, to)					\
 	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT)
@@ -232,5 +238,24 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
 #define _ASM_EXTABLE_FAULT(from, to)				\
 	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
 
+/*
+ * Both i386 and x86_64 returns 64-bit values in edx:eax for certain
+ * instructions, but GCC's "A" constraint has different meanings.
+ * For i386, "A" means exactly edx:eax, while for x86_64 it
+ * means rax *or* rdx.
+ *
+ * These helpers wrapping these semantic differences save one instruction
+ * clearing the high half of 'low':
+ */
+#ifdef CONFIG_X86_64
+# define EAX_EDX_DECLARE_ARGS(val, low, high)	unsigned long low, high
+# define EAX_EDX_VAL(val, low, high)		((low) | (high) << 32)
+# define EAX_EDX_RET(val, low, high)		"=a" (low), "=d" (high)
+#else
+# define EAX_EDX_DECLARE_ARGS(val, low, high)	u64 val
+# define EAX_EDX_VAL(val, low, high)		(val)
+# define EAX_EDX_RET(val, low, high)		"=A" (val)
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 55b4d24356ea..75743f1dfd4e 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -30,14 +30,14 @@ static __always_inline void arch_atomic_set(atomic_t *v, int i)
 
 static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "addl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "addl %1, %0"
 		     : "+m" (v->counter)
 		     : "ir" (i) : "memory");
 }
 
 static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "subl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "subl %1, %0"
 		     : "+m" (v->counter)
 		     : "ir" (i) : "memory");
 }
@@ -50,14 +50,14 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "incl %0"
+	asm_inline volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_inc arch_atomic_inc
 
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "decl %0"
+	asm_inline volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_dec arch_atomic_dec
@@ -116,7 +116,7 @@ static __always_inline int arch_atomic_xchg(atomic_t *v, int new)
 
 static __always_inline void arch_atomic_and(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "andl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "andl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
@@ -134,7 +134,7 @@ static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_or(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "orl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "orl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
@@ -152,7 +152,7 @@ static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_xor(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "xorl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "xorl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6c6e9b9f98a4..ab838205c1c6 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -48,17 +48,20 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %c[func]" \
+#ifdef CONFIG_X86_CX8
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	asm volatile("call %c[func]"					\
 		     : ALT_OUTPUT_SP(out) \
-		     : [func] "i" (atomic64_##g##_cx8), ## in)
+		     : [func] "i" (atomic64_##g##_cx8)			\
+		       COMMA(in)					\
+		     : clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define __alternative_atomic64(f, g, out, in...) \
-	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
-			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8,	\
+			 X86_FEATURE_CX8, ASM_OUTPUT(out),		\
+			 ASM_INPUT(in), clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
 	ATOMIC64_DECL_ONE(sym##_386)
@@ -69,8 +72,8 @@ ATOMIC64_DECL_ONE(inc_386);
 ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define alternative_atomic64(f, out, in...) \
-	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+#define alternative_atomic64(f, out, in, clobbers...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers)
 
 ATOMIC64_DECL(read);
 ATOMIC64_DECL(set);
@@ -105,9 +108,10 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	alternative_atomic64(xchg, "=&A" (o),
-			     "S" (v), "b" (low), "c" (high)
-			     : "memory");
+	alternative_atomic64(xchg,
+			     "=&A" (o),
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "memory");
 	return o;
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
@@ -116,23 +120,25 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	alternative_atomic64(set, /* no output */,
-			     "S" (v), "b" (low), "c" (high)
-			     : "eax", "edx", "memory");
+	alternative_atomic64(set,
+			     /* no output */,
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "eax", "edx", "memory");
 }
 
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+	alternative_atomic64(read, "=&A" (r), "c" (v), "memory");
 	return r;
 }
 
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
@@ -140,8 +146,9 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
@@ -149,8 +156,10 @@ static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(inc_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(inc_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
@@ -158,8 +167,10 @@ static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(dec_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(dec_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
@@ -167,28 +178,34 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	__alternative_atomic64(inc, inc_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(inc, inc_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	__alternative_atomic64(dec, dec_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(dec, dec_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
@@ -197,8 +214,9 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
 	alternative_atomic64(add_unless,
-			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
-			     "S" (v) : "memory");
+			     ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v),
+			     "memory");
 	return (int)a;
 }
 #define arch_atomic64_add_unless arch_atomic64_add_unless
@@ -206,8 +224,10 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	alternative_atomic64(inc_not_zero, "=&a" (r),
-			     "S" (v) : "ecx", "edx", "memory");
+	alternative_atomic64(inc_not_zero,
+			     "=&a" (r),
+			     "S" (v),
+			     "ecx", "edx", "memory");
 	return r;
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
@@ -215,8 +235,10 @@ static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(dec_if_positive, "=&A" (r),
-			     "S" (v) : "ecx", "memory");
+	alternative_atomic64(dec_if_positive,
+			     "=&A" (r),
+			     "S" (v),
+			     "ecx", "memory");
 	return r;
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index ae12acae5b06..87b496325b5b 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -22,14 +22,14 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "addq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "addq %1, %0"
 		     : "=m" (v->counter)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "subq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "subq %1, %0"
 		     : "=m" (v->counter)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
@@ -42,7 +42,7 @@ static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "incq %0"
+	asm_inline volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter) : "memory");
 }
@@ -50,7 +50,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "decq %0"
+	asm_inline volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter) : "memory");
 }
@@ -110,7 +110,7 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 
 static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "andq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "andq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
@@ -128,7 +128,7 @@ static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "orq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "orq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
@@ -146,7 +146,7 @@ static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "xorq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "xorq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7b44b3c4cce1..db70832232d4 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define __mb()	asm volatile("mfence":::"memory")
@@ -50,7 +50,7 @@
 #define __dma_rmb()	barrier()
 #define __dma_wmb()	barrier()
 
-#define __smp_mb()	asm volatile("lock; addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
+#define __smp_mb()	asm volatile("lock addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
 
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index b96d45944c59..eebbc8889e70 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -52,12 +52,12 @@ static __always_inline void
 arch_set_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "orb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "orb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
@@ -72,11 +72,11 @@ static __always_inline void
 arch_clear_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "andb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "andb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
@@ -98,7 +98,7 @@ static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
 		volatile unsigned long *addr)
 {
 	bool negative;
-	asm volatile(LOCK_PREFIX "xorb %2,%1"
+	asm_inline volatile(LOCK_PREFIX "xorb %2,%1"
 		CC_SET(s)
 		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
 		: "iq" ((char)mask) : "memory");
@@ -122,11 +122,11 @@ static __always_inline void
 arch_change_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "xorb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "xorb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
@@ -248,7 +248,7 @@ arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
 
 static __always_inline unsigned long variable__ffs(unsigned long word)
 {
-	asm("rep; bsf %1,%0"
+	asm("tzcnt %1,%0"
 		: "=r" (word)
 		: ASM_INPUT_RM (word));
 	return word;
@@ -267,10 +267,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
 
 static __always_inline unsigned long variable_ffz(unsigned long word)
 {
-	asm("rep; bsf %1,%0"
-		: "=r" (word)
-		: "r" (~word));
-	return word;
+	return variable__ffs(~word);
 }
 
 /**
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3e5b111e619d..02b23aa78955 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -74,7 +74,12 @@
 # define BOOT_STACK_SIZE	0x1000
 #endif
 
-#ifndef __ASSEMBLY__
+#define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
+
+#define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
+#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
+
+#ifndef __ASSEMBLER__
 extern unsigned int output_len;
 extern const unsigned long kernel_text_size;
 extern const unsigned long kernel_total_size;
@@ -83,6 +88,11 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
 				void (*error)(char *x));
 
 extern struct boot_params *boot_params_ptr;
+extern unsigned long *trampoline_32bit;
+extern const u16 trampoline_ljmp_imm_offset;
+
+void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
+
 #endif
 
 #endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index e85ac0c7c039..f0e9acf72547 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -17,13 +17,17 @@
  * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
  */
 #define INSN_ASOP		0x67
+#define INSN_LOCK		0xf0
 #define OPCODE_ESCAPE		0x0f
 #define SECOND_BYTE_OPCODE_UD1	0xb9
 #define SECOND_BYTE_OPCODE_UD2	0x0b
 
 #define BUG_NONE		0xffff
-#define BUG_UD1			0xfffe
-#define BUG_UD2			0xfffd
+#define BUG_UD2			0xfffe
+#define BUG_UD1			0xfffd
+#define BUG_UD1_UBSAN		0xfffc
+#define BUG_EA			0xffea
+#define BUG_LOCK		0xfff0
 
 #ifdef CONFIG_GENERIC_BUG
 
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 31d19c815f99..3e51ba459154 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -101,6 +101,16 @@ enum cfi_mode {
 
 extern enum cfi_mode cfi_mode;
 
+#ifdef CONFIG_FINEIBT_BHI
+extern bool cfi_bhi;
+#else
+#define cfi_bhi (0)
+#endif
+
+typedef u8 bhi_thunk[32];
+extern bhi_thunk __bhi_args[];
+extern bhi_thunk __bhi_args_end[];
+
 struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
@@ -125,6 +135,18 @@ static inline int cfi_get_offset(void)
 #define cfi_get_offset cfi_get_offset
 
 extern u32 cfi_get_func_hash(void *func);
+extern int cfi_get_func_arity(void *func);
+
+#ifdef CONFIG_FINEIBT
+extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type);
+#else
+static inline bool
+decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	return false;
+}
+
+#endif
 
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
@@ -137,6 +159,10 @@ static inline u32 cfi_get_func_hash(void *func)
 {
 	return 0;
 }
+static inline int cfi_get_func_arity(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
 #if HAS_KERNEL_IBT == 1
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 5612648b0202..b61f32c3459f 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -44,22 +44,22 @@ extern void __add_wrong_size(void)
 	        __typeof__ (*(ptr)) __ret = (arg);			\
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
-			asm volatile (lock #op "b %b0, %1\n"		\
+			asm_inline volatile (lock #op "b %b0, %1"	\
 				      : "+q" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
-			asm volatile (lock #op "w %w0, %1\n"		\
+			asm_inline volatile (lock #op "w %w0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_L:					\
-			asm volatile (lock #op "l %0, %1\n"		\
+			asm_inline volatile (lock #op "l %0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_Q:					\
-			asm volatile (lock #op "q %q0, %1\n"		\
+			asm_inline volatile (lock #op "q %q0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
@@ -91,7 +91,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_B:						\
 	{								\
 		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
-		asm volatile(lock "cmpxchgb %2,%1"			\
+		asm_inline volatile(lock "cmpxchgb %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "q" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -100,7 +100,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_W:						\
 	{								\
 		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
-		asm volatile(lock "cmpxchgw %2,%1"			\
+		asm_inline volatile(lock "cmpxchgw %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -109,7 +109,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_L:						\
 	{								\
 		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
-		asm volatile(lock "cmpxchgl %2,%1"			\
+		asm_inline volatile(lock "cmpxchgl %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -118,7 +118,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_Q:						\
 	{								\
 		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
-		asm volatile(lock "cmpxchgq %2,%1"			\
+		asm_inline volatile(lock "cmpxchgq %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -134,7 +134,7 @@ extern void __add_wrong_size(void)
 	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
 
 #define __sync_cmpxchg(ptr, old, new, size)				\
-	__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
+	__raw_cmpxchg((ptr), (old), (new), (size), "lock ")
 
 #define __cmpxchg_local(ptr, old, new, size)				\
 	__raw_cmpxchg((ptr), (old), (new), (size), "")
@@ -165,7 +165,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_B:						\
 	{								\
 		volatile u8 *__ptr = (volatile u8 *)(_ptr);		\
-		asm volatile(lock "cmpxchgb %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgb %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -177,7 +177,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_W:						\
 	{								\
 		volatile u16 *__ptr = (volatile u16 *)(_ptr);		\
-		asm volatile(lock "cmpxchgw %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgw %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -189,7 +189,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_L:						\
 	{								\
 		volatile u32 *__ptr = (volatile u32 *)(_ptr);		\
-		asm volatile(lock "cmpxchgl %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgl %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -201,7 +201,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_Q:						\
 	{								\
 		volatile u64 *__ptr = (volatile u64 *)(_ptr);		\
-		asm volatile(lock "cmpxchgq %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgq %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -222,7 +222,7 @@ extern void __add_wrong_size(void)
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
 #define __sync_try_cmpxchg(ptr, pold, new, size)			\
-	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+	__raw_try_cmpxchg((ptr), (pold), (new), (size), "lock ")
 
 #define __try_cmpxchg_local(ptr, pold, new, size)			\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a783dd..371f7906019e 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -19,7 +19,7 @@ union __u64_halves {
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg8b %[ptr]"			\
 		     : [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
@@ -45,7 +45,7 @@ static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg8b %[ptr]"			\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
@@ -69,7 +69,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
@@ -91,19 +91,21 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8)	\
+		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	o.full;								\
 })
 
 static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
 {
-	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_cmpxchg64 arch_cmpxchg64
 
@@ -119,14 +121,16 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     CC_SET(e)						\
-		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
-				     "+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+		CC_SET(e)						\
+		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				"+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	if (unlikely(!ret))						\
 		*(_oldp) = o.full;					\
@@ -136,7 +140,7 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 
 static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock ");
 }
 #define arch_try_cmpxchg64 arch_try_cmpxchg64
 
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 5e241306db26..71d1e72ed879 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -38,7 +38,7 @@ union __u128_halves {
 	union __u128_halves o = { .full = (_old), },			\
 			    n = { .full = (_new), };			\
 									\
-	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg16b %[ptr]"			\
 		     : [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
@@ -65,7 +65,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 			    n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg16b %[ptr]"			\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index aa6c8f8ca958..e1dbf8df1b69 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -15,9 +15,14 @@ enum cc_vendor {
 extern enum cc_vendor cc_vendor;
 extern u64 cc_mask;
 
+static inline u64 cc_get_mask(void)
+{
+	return cc_mask;
+}
+
 static inline void cc_set_mask(u64 mask)
 {
-	RIP_REL_REF(cc_mask) = mask;
+	cc_mask = mask;
 }
 
 u64 cc_mkenc(u64 val);
@@ -25,7 +30,10 @@ u64 cc_mkdec(u64 val);
 void cc_random_init(void);
 #else
 #define cc_vendor (CC_VENDOR_NONE)
-static const u64 cc_mask = 0;
+static inline u64 cc_get_mask(void)
+{
+	return 0;
+}
 
 static inline u64 cc_mkenc(u64 val)
 {
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca..ad235dda1ded 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -12,7 +12,6 @@
 #ifndef CONFIG_SMP
 #define cpu_physical_id(cpu)			boot_cpu_physical_apicid
 #define cpu_acpi_id(cpu)			0
-#define safe_smp_processor_id()			0
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -50,20 +49,6 @@ static inline void split_lock_init(void) {}
 static inline void bus_lock_init(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
-u8 get_this_hybrid_cpu_type(void);
-u32 get_this_hybrid_cpu_native_id(void);
-#else
-static inline u8 get_this_hybrid_cpu_type(void)
-{
-	return 0;
-}
-
-static inline u32 get_this_hybrid_cpu_native_id(void)
-{
-	return 0;
-}
-#endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
 #else
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index ba32e0f44cba..6be777a06944 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -57,7 +57,7 @@
 #define X86_CPU_ID_FLAG_ENTRY_VALID	BIT(0)
 
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
+ * X86_MATCH_CPU -  Base macro for CPU matching
  * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@_vendor
  * @_family:	The family number or X86_FAMILY_ANY
@@ -74,47 +74,18 @@
  * into another macro at the usage site for good reasons, then please
  * start this local macro with X86_MATCH to allow easy grepping.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
-						    _steppings, _feature, _data) { \
-	.vendor		= X86_VENDOR_##_vendor,				\
-	.family		= _family,					\
-	.model		= _model,					\
-	.steppings	= _steppings,					\
-	.feature	= _feature,					\
-	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
-	.driver_data	= (unsigned long) _data				\
-}
-
-#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
-						    _steppings, _feature, _data) { \
+#define X86_MATCH_CPU(_vendor, _family, _model, _steppings, _feature, _type, _data) { \
 	.vendor		= _vendor,					\
 	.family		= _family,					\
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
 	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
+	.type		= _type,					\
 	.driver_data	= (unsigned long) _data				\
 }
 
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Macro for CPU matching
- * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
- *		The name is expanded to X86_VENDOR_@_vendor
- * @_family:	The family number or X86_FAMILY_ANY
- * @_model:	The model number, model constant or X86_MODEL_ANY
- * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
- * @_data:	Driver specific data or NULL. The internal storage
- *		format is unsigned long. The supplied value, pointer
- *		etc. is casted to unsigned long internally.
- *
- * The steppings arguments of X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE() is
- * set to wildcards.
- */
-#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, feature, data) \
-	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(vendor, family, model, \
-						X86_STEPPING_ANY, feature, data)
-
-/**
  * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
  * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@vendor
@@ -123,13 +94,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data)	\
-	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family,		\
-					   X86_MODEL_ANY, feature, data)
+#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data)		\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature
@@ -139,12 +107,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data)			\
-	X86_MATCH_VENDOR_FAM_FEATURE(vendor, X86_FAMILY_ANY, feature, data)
+#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data)				\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, X86_FAMILY_ANY, X86_MODEL_ANY,	\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_FEATURE - Macro for matching a CPU feature
@@ -152,12 +118,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_FEATURE(feature, data)				\
-	X86_MATCH_VENDOR_FEATURE(ANY, feature, data)
+#define X86_MATCH_FEATURE(feature, data)					\
+	X86_MATCH_CPU(X86_VENDOR_ANY, X86_FAMILY_ANY, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model
@@ -168,13 +132,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data)		\
-	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model,	\
-					   X86_FEATURE_ANY, data)
+#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data)			\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, model, X86_STEPPING_ANY,	\
+		      X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FAM - Match vendor and family
@@ -184,12 +145,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments to X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set of wildcards.
  */
-#define X86_MATCH_VENDOR_FAM(vendor, family, data)			\
-	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data)
+#define X86_MATCH_VENDOR_FAM(vendor, family, data)				\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VFM - Match encoded vendor/family/model
@@ -197,34 +156,26 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * Stepping and feature are set to wildcards
  */
-#define X86_MATCH_VFM(vfm, data)			\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
-		VFM_VENDOR(vfm),			\
-		VFM_FAMILY(vfm),			\
-		VFM_MODEL(vfm),				\
-		X86_STEPPING_ANY, X86_FEATURE_ANY, data)
+#define X86_MATCH_VFM(vfm, data)						\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm),	VFM_MODEL(vfm),		\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 #define __X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
- * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping
+ * X86_MATCH_VFM_STEPS - Match encoded vendor/family/model and steppings
+ *			 range.
  * @vfm:	Encoded 8-bits each for vendor, family, model
- * @steppings:	Bitmask of steppings to match
+ * @min_step:	Lowest stepping number to match
+ * @max_step:	Highest stepping number to match
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * feature is set to wildcard
  */
-#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data)	\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(		\
-		VFM_VENDOR(vfm),				\
-		VFM_FAMILY(vfm),				\
-		VFM_MODEL(vfm),					\
-		__X86_STEPPINGS(min_step, max_step),		\
-		X86_FEATURE_ANY, data)
+#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data)			\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),		\
+		      __X86_STEPPINGS(min_step, max_step), X86_FEATURE_ANY,	\
+		      X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature
@@ -233,15 +184,22 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * Steppings is set to wildcard
  */
-#define X86_MATCH_VFM_FEATURE(vfm, feature, data)	\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
-		VFM_VENDOR(vfm),			\
-		VFM_FAMILY(vfm),			\
-		VFM_MODEL(vfm),				\
-		X86_STEPPING_ANY, feature, data)
+#define X86_MATCH_VFM_FEATURE(vfm, feature, data)				\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_CPU_TYPE - Match encoded vendor/family/model/type
+ * @vfm:	Encoded 8-bits each for vendor, family, model
+ * @type:	CPU type e.g. P-core, E-core
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is cast to unsigned long internally.
+ */
+#define X86_MATCH_VFM_CPU_TYPE(vfm, type, data)				\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),	\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, type, data)
 
 extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index de1ad09fe8d7..893cbca37fe9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -4,11 +4,12 @@
 
 #include <asm/processor.h>
 
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#if defined(__KERNEL__) && !defined(__ASSEMBLER__)
 
 #include <asm/asm.h>
 #include <linux/bitops.h>
 #include <asm/alternative.h>
+#include <asm/cpufeaturemasks.h>
 
 enum cpuid_leafs
 {
@@ -37,92 +38,19 @@ enum cpuid_leafs
 	NR_CPUID_WORDS,
 };
 
-#define X86_CAP_FMT_NUM "%d:%d"
-#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31)
-
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
-#define X86_CAP_FMT "%s"
-#define x86_cap_flag(flag) x86_cap_flags[flag]
 
 /*
  * In order to save room, we index into this array by doing
  * X86_BUG_<name> - NCAPINTS*32.
  */
 extern const char * const x86_bug_flags[NBUGINTS*32];
+#define x86_bug_flag(flag) x86_bug_flags[flag]
 
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-/*
- * There are 32 bits/features in each mask word.  The high bits
- * (selected with (bit>>5) give us the word number and the low 5
- * bits give us the bit/feature number inside the word.
- * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
- * see if it is set in the mask word.
- */
-#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
-	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
-
-/*
- * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the
- * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all
- * header macros which use NCAPINTS need to be changed. The duplicated macro
- * use causes the compiler to issue errors for all headers so that all usage
- * sites can be corrected.
- */
-#define REQUIRED_MASK_BIT_SET(feature_bit)		\
-	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
-	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
-#define DISABLED_MASK_BIT_SET(feature_bit)				\
-	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
-	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
@@ -149,6 +77,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 
 extern void setup_clear_cpu_cap(unsigned int bit);
 extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
+void check_cpufeature_deps(struct cpuinfo_x86 *c);
 
 #define setup_force_cpu_cap(bit) do {			\
 							\
@@ -208,5 +137,5 @@ t_no:
 #define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
 					boot_cpu_data.x86_model
 
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 508c0dad116b..5b50e0e35129 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
 /*
  * Defines x86 CPU feature bits
  */
@@ -83,7 +75,7 @@
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8			( 3*32+ 4) /* Opteron, Athlon64 */
 #define X86_FEATURE_ZEN5		( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-/* Free                                 ( 3*32+ 6) */
+#define X86_FEATURE_ZEN6		( 3*32+ 6) /* CPU based on Zen6 microarchitecture */
 /* Free                                 ( 3*32+ 7) */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
 #define X86_FEATURE_UP			( 3*32+ 9) /* "up" SMP kernel running on UP */
@@ -210,7 +202,6 @@
 #define X86_FEATURE_MBA			( 7*32+18) /* "mba" Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 #define X86_FEATURE_PERFMON_V2		( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */
-#define X86_FEATURE_USE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* Use IBRS during runtime firmware calls */
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* Disable Speculative Store Bypass. */
 #define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* AMD SSBD implementation via LS_CFG MSR */
@@ -338,6 +329,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* "irperf" Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_INVLPGB		(13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */
 #define X86_FEATURE_RDPRU		(13*32+ 4) /* "rdpru" Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
@@ -386,6 +378,7 @@
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
 #define X86_FEATURE_VNMI		(15*32+25) /* "vnmi" Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* SVME addr check */
+#define X86_FEATURE_IDLE_HLT		(15*32+30) /* IDLE HLT intercept */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
 #define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/
@@ -468,6 +461,10 @@
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
 #define X86_FEATURE_SRSO_USER_KERNEL_NO	(20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */
+#define X86_FEATURE_SRSO_BP_SPEC_REDUCE	(20*32+31) /*
+						    * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs.
+						    * (SRSO_MSR_FIX in the official doc).
+						    */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
@@ -479,10 +476,13 @@
 #define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* Clear branch history at syscall entry using SW loop */
 #define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* BHI_DIS_S HW control available */
 #define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* BHI_DIS_S HW control enabled */
-#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
-#define X86_FEATURE_AMD_FAST_CPPC	(21*32 + 5) /* Fast CPPC */
-#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
-#define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32 + 7) /* Workload Classification */
+#define X86_FEATURE_CLEAR_BHB_VMEXIT	(21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_FAST_CPPC	(21*32+ 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
+#define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
 
 /*
  * BUG word(s)
@@ -521,7 +521,7 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+/* unused, was #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
@@ -529,9 +529,14 @@
 #define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
-#define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
-#define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
-#define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
-#define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SRSO			X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
+#define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index b2b9b4ef3dae..d5749b25fa10 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -1,222 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * CPUID-related helpers/definitions
- */
 
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
-#include <linux/types.h>
-
-#include <asm/string.h>
-
-struct cpuid_regs {
-	u32 eax, ebx, ecx, edx;
-};
-
-enum cpuid_regs_idx {
-	CPUID_EAX = 0,
-	CPUID_EBX,
-	CPUID_ECX,
-	CPUID_EDX,
-};
-
-#define CPUID_LEAF_MWAIT	0x5
-#define CPUID_LEAF_DCA		0x9
-#define CPUID_LEAF_XSTATE	0x0d
-#define CPUID_LEAF_TSC		0x15
-#define CPUID_LEAF_FREQ		0x16
-#define CPUID_LEAF_TILE		0x1d
-
-#ifdef CONFIG_X86_32
-bool have_cpuid_p(void);
-#else
-static inline bool have_cpuid_p(void)
-{
-	return true;
-}
-#endif
-static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
-				unsigned int *ecx, unsigned int *edx)
-{
-	/* ecx is often an input as well as an output. */
-	asm volatile("cpuid"
-	    : "=a" (*eax),
-	      "=b" (*ebx),
-	      "=c" (*ecx),
-	      "=d" (*edx)
-	    : "0" (*eax), "2" (*ecx)
-	    : "memory");
-}
-
-#define native_cpuid_reg(reg)					\
-static inline unsigned int native_cpuid_##reg(unsigned int op)	\
-{								\
-	unsigned int eax = op, ebx, ecx = 0, edx;		\
-								\
-	native_cpuid(&eax, &ebx, &ecx, &edx);			\
-								\
-	return reg;						\
-}
-
-/*
- * Native CPUID functions returning a single datum.
- */
-native_cpuid_reg(eax)
-native_cpuid_reg(ebx)
-native_cpuid_reg(ecx)
-native_cpuid_reg(edx)
-
-#ifdef CONFIG_PARAVIRT_XXL
-#include <asm/paravirt.h>
-#else
-#define __cpuid			native_cpuid
-#endif
-
-/*
- * Generic CPUID function
- * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
- * resulting in stale register contents being returned.
- */
-static inline void cpuid(unsigned int op,
-			 unsigned int *eax, unsigned int *ebx,
-			 unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = 0;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/* Some CPUID calls want 'count' to be placed in ecx */
-static inline void cpuid_count(unsigned int op, int count,
-			       unsigned int *eax, unsigned int *ebx,
-			       unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = count;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/*
- * CPUID functions returning a single datum
- */
-static inline unsigned int cpuid_eax(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return eax;
-}
-
-static inline unsigned int cpuid_ebx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ebx;
-}
-
-static inline unsigned int cpuid_ecx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ecx;
-}
-
-static inline unsigned int cpuid_edx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return edx;
-}
-
-static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs)
-{
-	regs[CPUID_EAX] = leaf;
-	regs[CPUID_ECX] = subleaf;
-	__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
-}
-
-#define cpuid_subleaf(leaf, subleaf, regs) {		\
-	static_assert(sizeof(*(regs)) == 16);		\
-	__cpuid_read(leaf, subleaf, (u32 *)(regs));	\
-}
-
-#define cpuid_leaf(leaf, regs) {			\
-	static_assert(sizeof(*(regs)) == 16);		\
-	__cpuid_read(leaf, 0, (u32 *)(regs));		\
-}
-
-static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf,
-				    enum cpuid_regs_idx regidx, u32 *reg)
-{
-	u32 regs[4];
-
-	__cpuid_read(leaf, subleaf, regs);
-	*reg = regs[regidx];
-}
-
-#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) {		\
-	static_assert(sizeof(*(reg)) == 4);			\
-	__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg));	\
-}
-
-#define cpuid_leaf_reg(leaf, regidx, reg) {			\
-	static_assert(sizeof(*(reg)) == 4);			\
-	__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg));	\
-}
-
-static __always_inline bool cpuid_function_is_indexed(u32 function)
-{
-	switch (function) {
-	case 4:
-	case 7:
-	case 0xb:
-	case 0xd:
-	case 0xf:
-	case 0x10:
-	case 0x12:
-	case 0x14:
-	case 0x17:
-	case 0x18:
-	case 0x1d:
-	case 0x1e:
-	case 0x1f:
-	case 0x24:
-	case 0x8000001d:
-		return true;
-	}
-
-	return false;
-}
-
-#define for_each_possible_hypervisor_cpuid_base(function) \
-	for (function = 0x40000000; function < 0x40010000; function += 0x100)
-
-static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
-{
-	uint32_t base, eax, signature[3];
-
-	for_each_possible_hypervisor_cpuid_base(base) {
-		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
-
-		/*
-		 * This must not compile to "call memcmp" because it's called
-		 * from PVH early boot code before instrumentation is set up
-		 * and memcmp() itself may be instrumented.
-		 */
-		if (!__builtin_memcmp(sig, signature, 12) &&
-		    (leaves == 0 || ((eax - base) >= leaves)))
-			return base;
-	}
-
-	return 0;
-}
+#include <asm/cpuid/api.h>
 
 #endif /* _ASM_X86_CPUID_H */
diff --git a/arch/x86/include/asm/cpuid/api.h b/arch/x86/include/asm/cpuid/api.h
new file mode 100644
index 000000000000..44fa82e1267c
--- /dev/null
+++ b/arch/x86/include/asm/cpuid/api.h
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CPUID_API_H
+#define _ASM_X86_CPUID_API_H
+
+#include <asm/cpuid/types.h>
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+#include <asm/string.h>
+
+/*
+ * Raw CPUID accessors:
+ */
+
+#ifdef CONFIG_X86_32
+bool cpuid_feature(void);
+#else
+static inline bool cpuid_feature(void)
+{
+	return true;
+}
+#endif
+
+static inline void native_cpuid(u32 *eax, u32 *ebx,
+				u32 *ecx, u32 *edx)
+{
+	/* ecx is often an input as well as an output. */
+	asm volatile("cpuid"
+	    : "=a" (*eax),
+	      "=b" (*ebx),
+	      "=c" (*ecx),
+	      "=d" (*edx)
+	    : "0" (*eax), "2" (*ecx)
+	    : "memory");
+}
+
+#define NATIVE_CPUID_REG(reg)					\
+static inline u32 native_cpuid_##reg(u32 op)			\
+{								\
+	u32 eax = op, ebx, ecx = 0, edx;			\
+								\
+	native_cpuid(&eax, &ebx, &ecx, &edx);			\
+								\
+	return reg;						\
+}
+
+/*
+ * Native CPUID functions returning a single datum:
+ */
+NATIVE_CPUID_REG(eax)
+NATIVE_CPUID_REG(ebx)
+NATIVE_CPUID_REG(ecx)
+NATIVE_CPUID_REG(edx)
+
+#ifdef CONFIG_PARAVIRT_XXL
+# include <asm/paravirt.h>
+#else
+# define __cpuid native_cpuid
+#endif
+
+/*
+ * Generic CPUID function
+ *
+ * Clear ECX since some CPUs (Cyrix MII) do not set or clear ECX
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(u32 op,
+			 u32 *eax, u32 *ebx,
+			 u32 *ecx, u32 *edx)
+{
+	*eax = op;
+	*ecx = 0;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/* Some CPUID calls want 'count' to be placed in ECX */
+static inline void cpuid_count(u32 op, int count,
+			       u32 *eax, u32 *ebx,
+			       u32 *ecx, u32 *edx)
+{
+	*eax = op;
+	*ecx = count;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/*
+ * CPUID functions returning a single datum:
+ */
+
+static inline u32 cpuid_eax(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return eax;
+}
+
+static inline u32 cpuid_ebx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ebx;
+}
+
+static inline u32 cpuid_ecx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ecx;
+}
+
+static inline u32 cpuid_edx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return edx;
+}
+
+static inline void __cpuid_read(u32 leaf, u32 subleaf, u32 *regs)
+{
+	regs[CPUID_EAX] = leaf;
+	regs[CPUID_ECX] = subleaf;
+	__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
+}
+
+#define cpuid_subleaf(leaf, subleaf, regs) {		\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, subleaf, (u32 *)(regs));	\
+}
+
+#define cpuid_leaf(leaf, regs) {			\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, 0, (u32 *)(regs));		\
+}
+
+static inline void __cpuid_read_reg(u32 leaf, u32 subleaf,
+				    enum cpuid_regs_idx regidx, u32 *reg)
+{
+	u32 regs[4];
+
+	__cpuid_read(leaf, subleaf, regs);
+	*reg = regs[regidx];
+}
+
+#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) {		\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg));	\
+}
+
+#define cpuid_leaf_reg(leaf, regidx, reg) {			\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg));	\
+}
+
+/*
+ * Hypervisor-related APIs:
+ */
+
+static __always_inline bool cpuid_function_is_indexed(u32 function)
+{
+	switch (function) {
+	case 4:
+	case 7:
+	case 0xb:
+	case 0xd:
+	case 0xf:
+	case 0x10:
+	case 0x12:
+	case 0x14:
+	case 0x17:
+	case 0x18:
+	case 0x1d:
+	case 0x1e:
+	case 0x1f:
+	case 0x24:
+	case 0x8000001d:
+		return true;
+	}
+
+	return false;
+}
+
+#define for_each_possible_cpuid_base_hypervisor(function) \
+	for (function = 0x40000000; function < 0x40010000; function += 0x100)
+
+static inline u32 cpuid_base_hypervisor(const char *sig, u32 leaves)
+{
+	u32 base, eax, signature[3];
+
+	for_each_possible_cpuid_base_hypervisor(base) {
+		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
+
+		/*
+		 * This must not compile to "call memcmp" because it's called
+		 * from PVH early boot code before instrumentation is set up
+		 * and memcmp() itself may be instrumented.
+		 */
+		if (!__builtin_memcmp(sig, signature, 12) &&
+		    (leaves == 0 || ((eax - base) >= leaves)))
+			return base;
+	}
+
+	return 0;
+}
+
+/*
+ * CPUID(0x2) parsing:
+ */
+
+/**
+ * cpuid_leaf_0x2() - Return sanitized CPUID(0x2) register output
+ * @regs:	Output parameter
+ *
+ * Query CPUID(0x2) and store its output in @regs.  Force set any
+ * invalid 1-byte descriptor returned by the hardware to zero (the NULL
+ * cache/TLB descriptor) before returning it to the caller.
+ *
+ * Use for_each_cpuid_0x2_desc() to iterate over the register output in
+ * parsed form.
+ */
+static inline void cpuid_leaf_0x2(union leaf_0x2_regs *regs)
+{
+	cpuid_leaf(0x2, regs);
+
+	/*
+	 * All Intel CPUs must report an iteration count of 1.	In case
+	 * of bogus hardware, treat all returned descriptors as NULL.
+	 */
+	if (regs->desc[0] != 0x01) {
+		for (int i = 0; i < 4; i++)
+			regs->regv[i] = 0;
+		return;
+	}
+
+	/*
+	 * The most significant bit (MSB) of each register must be clear.
+	 * If a register is invalid, replace its descriptors with NULL.
+	 */
+	for (int i = 0; i < 4; i++) {
+		if (regs->reg[i].invalid)
+			regs->regv[i] = 0;
+	}
+}
+
+/**
+ * for_each_cpuid_0x2_desc() - Iterator for parsed CPUID(0x2) descriptors
+ * @_regs:	CPUID(0x2) register output, as returned by cpuid_leaf_0x2()
+ * @_ptr:	u8 pointer, for macro internal use only
+ * @_desc:	Pointer to the parsed CPUID(0x2) descriptor at each iteration
+ *
+ * Loop over the 1-byte descriptors in the passed CPUID(0x2) output registers
+ * @_regs.  Provide the parsed information for each descriptor through @_desc.
+ *
+ * To handle cache-specific descriptors, switch on @_desc->c_type.  For TLB
+ * descriptors, switch on @_desc->t_type.
+ *
+ * Example usage for cache descriptors::
+ *
+ *	const struct leaf_0x2_table *desc;
+ *	union leaf_0x2_regs regs;
+ *	u8 *ptr;
+ *
+ *	cpuid_leaf_0x2(&regs);
+ *	for_each_cpuid_0x2_desc(regs, ptr, desc) {
+ *		switch (desc->c_type) {
+ *			...
+ *		}
+ *	}
+ */
+#define for_each_cpuid_0x2_desc(_regs, _ptr, _desc)				\
+	for (_ptr = &(_regs).desc[1];						\
+	     _ptr < &(_regs).desc[16] && (_desc = &cpuid_0x2_table[*_ptr]);	\
+	     _ptr++)
+
+/*
+ * CPUID(0x80000006) parsing:
+ */
+
+static inline bool cpuid_amd_hygon_has_l3_cache(void)
+{
+	return cpuid_edx(0x80000006);
+}
+
+#endif /* _ASM_X86_CPUID_API_H */
diff --git a/arch/x86/include/asm/cpuid/types.h b/arch/x86/include/asm/cpuid/types.h
new file mode 100644
index 000000000000..8a00364b79de
--- /dev/null
+++ b/arch/x86/include/asm/cpuid/types.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CPUID_TYPES_H
+#define _ASM_X86_CPUID_TYPES_H
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+/*
+ * Types for raw CPUID access:
+ */
+
+struct cpuid_regs {
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
+#define CPUID_LEAF_MWAIT	0x05
+#define CPUID_LEAF_DCA		0x09
+#define CPUID_LEAF_XSTATE	0x0d
+#define CPUID_LEAF_TSC		0x15
+#define CPUID_LEAF_FREQ		0x16
+#define CPUID_LEAF_TILE		0x1d
+
+/*
+ * Types for CPUID(0x2) parsing:
+ */
+
+struct leaf_0x2_reg {
+		u32		: 31,
+			invalid	: 1;
+};
+
+union leaf_0x2_regs {
+	struct leaf_0x2_reg	reg[4];
+	u32			regv[4];
+	u8			desc[16];
+};
+
+/*
+ * Leaf 0x2 1-byte descriptors' cache types
+ * To be used for their mappings at cpuid_0x2_table[]
+ *
+ * Start at 1 since type 0 is reserved for HW byte descriptors which are
+ * not recognized by the kernel; i.e., those without an explicit mapping.
+ */
+enum _cache_table_type {
+	CACHE_L1_INST		= 1,
+	CACHE_L1_DATA,
+	CACHE_L2,
+	CACHE_L3
+	/* Adjust __TLB_TABLE_TYPE_BEGIN before adding more types */
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _cache_table_type) == 1);
+#endif
+
+/*
+ * Ensure that leaf 0x2 cache and TLB type values do not intersect,
+ * since they share the same type field at struct cpuid_0x2_table.
+ */
+#define __TLB_TABLE_TYPE_BEGIN		(CACHE_L3 + 1)
+
+/*
+ * Leaf 0x2 1-byte descriptors' TLB types
+ * To be used for their mappings at cpuid_0x2_table[]
+ */
+enum _tlb_table_type {
+	TLB_INST_4K		= __TLB_TABLE_TYPE_BEGIN,
+	TLB_INST_4M,
+	TLB_INST_2M_4M,
+	TLB_INST_ALL,
+
+	TLB_DATA_4K,
+	TLB_DATA_4M,
+	TLB_DATA_2M_4M,
+	TLB_DATA_4K_4M,
+	TLB_DATA_1G,
+	TLB_DATA_1G_2M_4M,
+
+	TLB_DATA0_4K,
+	TLB_DATA0_4M,
+	TLB_DATA0_2M_4M,
+
+	STLB_4K,
+	STLB_4K_2M,
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _tlb_table_type) == 1);
+#endif
+
+/*
+ * Combined parsing table for leaf 0x2 cache and TLB descriptors.
+ */
+
+struct leaf_0x2_table {
+	union {
+		enum _cache_table_type	c_type;
+		enum _tlb_table_type	t_type;
+	};
+	union {
+		short			c_size;
+		short			entries;
+	};
+};
+
+extern const struct leaf_0x2_table cpuid_0x2_table[256];
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of entries
+ * for their respective TLB types.  TLB descriptor 0x63 is an exception: it
+ * implies 4 dTLB entries for 1GB pages and 32 dTLB entries for 2MB or 4MB pages.
+ *
+ * Encode that descriptor's dTLB entry count for 2MB/4MB pages here, as the entry
+ * count for dTLB 1GB pages is already encoded at the cpuid_0x2_table[]'s mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES		32
+
+#endif /* _ASM_X86_CPUID_TYPES_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 4acfd57de8f1..70f6b60ad67b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_CPUMASK_H
 #define _ASM_X86_CPUMASK_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cpumask.h>
 
 extern void setup_cpu_local_masks(void);
@@ -34,5 +34,5 @@ static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp
 
 #define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index bf5953883ec3..cc4a3f725b37 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -5,52 +5,28 @@
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/cache.h>
 #include <asm/percpu.h>
 
 struct task_struct;
 
-struct pcpu_hot {
-	union {
-		struct {
-			struct task_struct	*current_task;
-			int			preempt_count;
-			int			cpu_number;
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-			u64			call_depth;
-#endif
-			unsigned long		top_of_stack;
-			void			*hardirq_stack_ptr;
-			u16			softirq_pending;
-#ifdef CONFIG_X86_64
-			bool			hardirq_stack_inuse;
-#else
-			void			*softirq_stack_ptr;
-#endif
-		};
-		u8	pad[64];
-	};
-};
-static_assert(sizeof(struct pcpu_hot) == 64);
-
-DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
-
-/* const-qualified alias to pcpu_hot, aliased by linker. */
-DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
-			const_pcpu_hot);
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct *, current_task);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct * const __percpu_seg_override,
+			  const_current_task);
 
 static __always_inline struct task_struct *get_current(void)
 {
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.current_task);
+		return this_cpu_read_const(const_current_task);
 
-	return this_cpu_read_stable(pcpu_hot.current_task);
+	return this_cpu_read_stable(current_task);
 }
 
 #define current get_current()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index fdbbbfec745a..363110e6b2e3 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -23,7 +23,7 @@ DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
 static __always_inline unsigned long native_get_debugreg(int regno)
 {
-	unsigned long val = 0;	/* Damn you, gcc! */
+	unsigned long val;
 
 	switch (regno) {
 	case 0:
@@ -43,7 +43,7 @@ static __always_inline unsigned long native_get_debugreg(int regno)
 		break;
 	case 7:
 		/*
-		 * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them
+		 * Use "asm volatile" for DR7 reads to forbid re-ordering them
 		 * with other code.
 		 *
 		 * This is needed because a DR7 access can cause a #VC exception
@@ -55,7 +55,7 @@ static __always_inline unsigned long native_get_debugreg(int regno)
 		 * re-ordered to happen before the call to sev_es_ist_enter(),
 		 * causing stack recursion.
 		 */
-		asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER);
+		asm volatile("mov %%db7, %0" : "=r" (val));
 		break;
 	default:
 		BUG();
@@ -83,15 +83,15 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 		break;
 	case 7:
 		/*
-		 * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them
+		 * Use "asm volatile" for DR7 writes to forbid re-ordering them
 		 * with other code.
 		 *
 		 * While is didn't happen with a DR7 write (see the DR7 read
 		 * comment above which explains where it happened), add the
-		 * __FORCE_ORDER here too to avoid similar problems in the
+		 * "asm volatile" here too to avoid similar problems in the
 		 * future.
 		 */
-		asm volatile("mov %0, %%db7"	::"r" (value), __FORCE_ORDER);
+		asm volatile("mov %0, %%db7"	::"r" (value));
 		break;
 	default:
 		BUG();
@@ -169,7 +169,7 @@ static inline unsigned long get_debugctlmsr(void)
 	if (boot_cpu_data.x86 < 6)
 		return 0;
 #endif
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 
 	return debugctlmsr;
 }
@@ -180,7 +180,7 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	if (boot_cpu_data.x86 < 6)
 		return;
 #endif
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea76..ec95fe44fa3a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index d440a65af8f3..7e6b9314758a 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -58,7 +58,7 @@
 
 #define DESC_USER		(_DESC_DPL(3))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -166,7 +166,7 @@ struct desc_ptr {
 	unsigned long address;
 } __attribute__((packed)) ;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* Boot IDT definitions */
 #define	BOOT_IDT_ENTRIES	32
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
deleted file mode 100644
index c492bdc97b05..000000000000
--- a/arch/x86/include/asm/disabled-features.h
+++ /dev/null
@@ -1,161 +0,0 @@
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#define _ASM_X86_DISABLED_FEATURES_H
-
-/* These features, although they might be available in a CPU
- * will not be used because the compile options to support
- * them are not present.
- *
- * This code allows them to be checked and disabled at
- * compile time without an explicit #ifdef.  Use
- * cpu_feature_enabled().
- */
-
-#ifdef CONFIG_X86_UMIP
-# define DISABLE_UMIP	0
-#else
-# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
-#endif
-
-#ifdef CONFIG_X86_64
-# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
-# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
-# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
-# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
-#else
-# define DISABLE_VME		0
-# define DISABLE_K6_MTRR	0
-# define DISABLE_CYRIX_ARR	0
-# define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
-#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		0
-# define DISABLE_OSPKE		0
-#else
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
-#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
-
-#ifdef CONFIG_X86_5LEVEL
-# define DISABLE_LA57	0
-#else
-# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-# define DISABLE_PTI		0
-#else
-# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETPOLINE
-# define DISABLE_RETPOLINE	0
-#else
-# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
-				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETHUNK
-# define DISABLE_RETHUNK	0
-#else
-# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_UNRET_ENTRY
-# define DISABLE_UNRET		0
-#else
-# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-# define DISABLE_CALL_DEPTH_TRACKING	0
-#else
-# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
-#endif
-
-#ifdef CONFIG_ADDRESS_MASKING
-# define DISABLE_LAM		0
-#else
-# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
-#endif
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-# define DISABLE_ENQCMD		0
-#else
-# define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#endif
-
-#ifdef CONFIG_X86_SGX
-# define DISABLE_SGX	0
-#else
-# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
-#endif
-
-#ifdef CONFIG_XEN_PV
-# define DISABLE_XENPV		0
-#else
-# define DISABLE_XENPV		(1 << (X86_FEATURE_XENPV & 31))
-#endif
-
-#ifdef CONFIG_INTEL_TDX_GUEST
-# define DISABLE_TDX_GUEST	0
-#else
-# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
-#endif
-
-#ifdef CONFIG_X86_USER_SHADOW_STACK
-#define DISABLE_USER_SHSTK	0
-#else
-#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
-#endif
-
-#ifdef CONFIG_X86_KERNEL_IBT
-#define DISABLE_IBT	0
-#else
-#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
-#endif
-
-#ifdef CONFIG_X86_FRED
-# define DISABLE_FRED	0
-#else
-# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
-#endif
-
-#ifdef CONFIG_KVM_AMD_SEV
-#define DISABLE_SEV_SNP		0
-#else
-#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
-#endif
-
-/*
- * Make sure to add features to the correct mask
- */
-#define DISABLED_MASK0	(DISABLE_VME)
-#define DISABLED_MASK1	0
-#define DISABLED_MASK2	0
-#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
-#define DISABLED_MASK5	0
-#define DISABLED_MASK6	0
-#define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
-#define DISABLED_MASK9	(DISABLE_SGX)
-#define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	0
-#define DISABLED_MASK14	0
-#define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
-			 DISABLE_ENQCMD)
-#define DISABLED_MASK17	0
-#define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	(DISABLE_SEV_SNP)
-#define DISABLED_MASK20	0
-#define DISABLED_MASK21	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 430fca13bb56..302e11b15da8 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_DWARF2_H
 #define _ASM_X86_DWARF2_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #warning "asm/dwarf2.h should be only included in pure assembly files"
 #endif
 
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index 2e74a7f0e935..c83645d5b2a8 100644
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -29,7 +29,6 @@ extern unsigned long e820__end_of_low_ram_pfn(void);
 extern u64  e820__memblock_alloc_reserved(u64 size, u64 align);
 extern void e820__memblock_setup(void);
 
-extern void e820__reserve_setup_data(void);
 extern void e820__finish_early_params(void);
 extern void e820__reserve_resources(void);
 extern void e820__reserve_resources_late(void);
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
index 314f75d886d0..80c4a7266629 100644
--- a/arch/x86/include/asm/e820/types.h
+++ b/arch/x86/include/asm/e820/types.h
@@ -35,15 +35,6 @@ enum e820_type {
 	 * marking it with the IORES_DESC_SOFT_RESERVED designation.
 	 */
 	E820_TYPE_SOFT_RESERVED	= 0xefffffff,
-
-	/*
-	 * Reserved RAM used by the kernel itself if
-	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
-	 * will be included in the S3 integrity calculation
-	 * and so should not include any memory that the BIOS
-	 * might alter over the S3 transition:
-	 */
-	E820_TYPE_RESERVED_KERN	= 128,
 };
 
 /*
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
index 426fc53ff803..dfbd1ebb9f10 100644
--- a/arch/x86/include/asm/edac.h
+++ b/arch/x86/include/asm/edac.h
@@ -13,7 +13,7 @@ static inline void edac_atomic_scrub(void *va, u32 size)
 	 * are interrupt, DMA and SMP safe.
 	 */
 	for (i = 0; i < size / 4; i++, virt_addr++)
-		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
+		asm volatile("lock addl $0, %0"::"m" (*virt_addr));
 }
 
 #endif /* _ASM_X86_EDAC_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f..6c8fdc96be7e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
 #define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
 #define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
 #define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX	41
+#define R_X86_64_REX_GOTPCRELX	42
 #define R_X86_64_32		10	/* Direct 32 bit zero extended */
 #define R_X86_64_32S		11	/* Direct 32 bit sign extended */
 #define R_X86_64_16		12	/* Direct 16 bit zero extended */
@@ -75,12 +76,8 @@ typedef struct user_i387_struct elf_fpregset_t;
 
 #include <asm/vdso.h>
 
-#ifdef CONFIG_X86_64
 extern unsigned int vdso64_enabled;
-#endif
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 extern unsigned int vdso32_enabled;
-#endif
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 77d20555e04d..d535a97c7284 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -53,7 +53,6 @@ static inline void arch_exit_work(unsigned long ti_work)
 	if (unlikely(ti_work & _TIF_IO_BITMAP))
 		tss_update_io_bitmap();
 
-	fpregs_assert_state_consistent();
 	if (unlikely(ti_work & _TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
 }
@@ -61,7 +60,9 @@ static inline void arch_exit_work(unsigned long ti_work)
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
 {
-	if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work))
+	fpregs_assert_state_consistent();
+
+	if (unlikely(ti_work))
 		arch_exit_work(ti_work);
 
 	fred_update_rsp0();
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index d0dcefb5cc59..4519c9f35ba0 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -31,7 +31,7 @@
 /* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
 #define FIXMAP_PMD_TOP	507
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/kernel.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
@@ -196,5 +196,5 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
 void __early_set_fixmap(enum fixed_addresses idx,
 			phys_addr_t phys, pgprot_t flags);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index f86ad3335529..cd6f194a912b 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -16,10 +16,9 @@
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
- * disables preemption so be careful if you intend to use it for long periods
- * of time.
- * If you intend to use the FPU in irq/softirq you need to check first with
- * irq_fpu_usable() if it is possible.
+ * disables preemption and softirq processing, so be careful if you intend to
+ * use it for long periods of time.  Kernel-mode FPU cannot be used in all
+ * contexts -- see irq_fpu_usable() for details.
  */
 
 /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
@@ -50,10 +49,10 @@ static inline void kernel_fpu_begin(void)
 }
 
 /*
- * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate.
- * A context switch will (and softirq might) save CPU's FPU registers to
- * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
- * a random state.
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while
+ * using the FPU in kernel mode.  A context switch will (and softirq might) save
+ * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving
+ * CPU's FPU registers in a random state.
  *
  * local_bh_disable() protects against both preemption and soft interrupts
  * on !RT kernels.
@@ -63,8 +62,6 @@ static inline void kernel_fpu_begin(void)
  * preemptible. Disabling preemption is the right choice here as bottom
  * half processing is always in thread context on RT kernels so it
  * implicitly prevents bottom half processing as well.
- *
- * Disabling preemption also serializes against kernel_fpu_begin().
  */
 static inline void fpregs_lock(void)
 {
@@ -129,6 +126,7 @@ static inline void fpstate_init_soft(struct swregs_state *soft) {}
 #endif
 
 /* State tracking */
+DECLARE_PER_CPU(bool, kernel_fpu_allowed);
 DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
 
 /* Process cleanup */
@@ -139,7 +137,7 @@ static inline void fpstate_free(struct fpu *fpu) { }
 #endif
 
 /* fpstate-related functions which are exported to KVM */
-extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature);
+extern void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature);
 
 extern u64 xstate_get_guest_group_perm(void);
 
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index c485f1944c5f..c060549c6c94 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -10,7 +10,7 @@
 #include <asm/trace/fpu.h>
 
 extern void save_fpregs_to_fpstate(struct fpu *fpu);
-extern void fpu__drop(struct fpu *fpu);
+extern void fpu__drop(struct task_struct *tsk);
 extern int  fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 		      unsigned long shstk_addr);
 extern void fpu_flush_thread(void);
@@ -18,31 +18,25 @@ extern void fpu_flush_thread(void);
 /*
  * FPU state switching for scheduling.
  *
- * This is a two-stage process:
+ * switch_fpu() saves the old state and sets TIF_NEED_FPU_LOAD if
+ * TIF_NEED_FPU_LOAD is not set.  This is done within the context
+ * of the old process.
  *
- *  - switch_fpu_prepare() saves the old state.
- *    This is done within the context of the old process.
- *
- *  - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
- *    will get loaded on return to userspace, or when the kernel needs it.
- *
- * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
- * are saved in the current thread's FPU register state.
- *
- * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
- * hold current()'s FPU registers. It is required to load the
+ * Once TIF_NEED_FPU_LOAD is set, it is required to load the
  * registers before returning to userland or using the content
  * otherwise.
  *
  * The FPU context is only stored/restored for a user task and
  * PF_KTHREAD is used to distinguish between kernel and user threads.
  */
-static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
+static inline void switch_fpu(struct task_struct *old, int cpu)
 {
-	if (cpu_feature_enabled(X86_FEATURE_FPU) &&
+	if (!test_tsk_thread_flag(old, TIF_NEED_FPU_LOAD) &&
+	    cpu_feature_enabled(X86_FEATURE_FPU) &&
 	    !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
-		struct fpu *old_fpu = &old->thread.fpu;
+		struct fpu *old_fpu = x86_task_fpu(old);
 
+		set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD);
 		save_fpregs_to_fpstate(old_fpu);
 		/*
 		 * The save operation preserved register state, so the
@@ -50,7 +44,7 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
 		 * current CPU number in @old_fpu, so the next return
 		 * to user space can avoid the FPU register restore
 		 * when is returns on the same CPU and still owns the
-		 * context.
+		 * context. See fpregs_restore_userregs().
 		 */
 		old_fpu->last_cpu = cpu;
 
@@ -58,14 +52,4 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
 	}
 }
 
-/*
- * Delay loading of the complete FPU state until the return to userland.
- * PKRU is handled separately.
- */
-static inline void switch_fpu_finish(struct task_struct *new)
-{
-	if (cpu_feature_enabled(X86_FEATURE_FPU))
-		set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD);
-}
-
 #endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index de16862bf230..1c94121acd3d 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -125,6 +125,7 @@ enum xfeature {
 	XFEATURE_RSRVD_COMP_16,
 	XFEATURE_XTILE_CFG,
 	XFEATURE_XTILE_DATA,
+	XFEATURE_APX,
 
 	XFEATURE_MAX,
 };
@@ -145,6 +146,7 @@ enum xfeature {
 #define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 #define XFEATURE_MASK_XTILE_CFG		(1 << XFEATURE_XTILE_CFG)
 #define XFEATURE_MASK_XTILE_DATA	(1 << XFEATURE_XTILE_DATA)
+#define XFEATURE_MASK_APX		(1 << XFEATURE_APX)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -304,6 +306,13 @@ struct xtile_data {
 } __packed;
 
 /*
+ * State component 19: 8B extended general purpose register.
+ */
+struct apx_state {
+	u64				egpr[16];
+} __packed;
+
+/*
  * State component 10 is supervisor state used for context-switching the
  * PASID state.
  */
@@ -407,9 +416,11 @@ struct fpu_state_perm {
 	/*
 	 * @__state_perm:
 	 *
-	 * This bitmap indicates the permission for state components, which
-	 * are available to a thread group. The permission prctl() sets the
-	 * enabled state bits in thread_group_leader()->thread.fpu.
+	 * This bitmap indicates the permission for state components
+	 * available to a thread group, including both user and supervisor
+	 * components and software-defined bits like FPU_GUEST_PERM_LOCKED.
+	 * The permission prctl() sets the enabled state bits in
+	 * thread_group_leader()->thread.fpu.
 	 *
 	 * All run time operations use the per thread information in the
 	 * currently active fpu.fpstate which contains the xfeature masks
@@ -525,13 +536,6 @@ struct fpu_guest {
 	u64				xfeatures;
 
 	/*
-	 * @perm:			xfeature bitmap of features which are
-	 *				permitted to be enabled for the guest
-	 *				vCPU.
-	 */
-	u64				perm;
-
-	/*
 	 * @xfd_err:			Save the guest value.
 	 */
 	u64				xfd_err;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 7f39fe7980c5..b308a76afbb7 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -32,7 +32,8 @@
 				      XFEATURE_MASK_PKRU | \
 				      XFEATURE_MASK_BNDREGS | \
 				      XFEATURE_MASK_BNDCSR | \
-				      XFEATURE_MASK_XTILE)
+				      XFEATURE_MASK_XTILE | \
+				      XFEATURE_MASK_APX)
 
 /*
  * Features which are restored when returning to user space.
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index fb42659f6e98..0ab65073c1cc 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_FRAME_POINTER
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro FRAME_BEGIN
 	push %_ASM_BP
@@ -51,7 +51,7 @@
 .endm
 #endif /* CONFIG_X86_64 */
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #define FRAME_BEGIN				\
 	"push %" _ASM_BP "\n"			\
@@ -82,18 +82,18 @@ static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
 
 #endif /* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define FRAME_OFFSET __ASM_SEL(4, 8)
 
 #else /* !CONFIG_FRAME_POINTER */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro ENCODE_FRAME_POINTER ptregs_offset=0
 .endm
 
-#else /* !__ASSEMBLY */
+#else /* !__ASSEMBLER__ */
 
 #define ENCODE_FRAME_POINTER
 
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
index 25ca00bd70e8..12b34d5b2953 100644
--- a/arch/x86/include/asm/fred.h
+++ b/arch/x86/include/asm/fred.h
@@ -9,6 +9,7 @@
 #include <linux/const.h>
 
 #include <asm/asm.h>
+#include <asm/msr.h>
 #include <asm/trapnr.h>
 
 /*
@@ -32,7 +33,7 @@
 #define FRED_CONFIG_INT_STKLVL(l)	(_AT(unsigned long, l) << 9)
 #define FRED_CONFIG_ENTRYPOINT(p)	_AT(unsigned long, (p))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_FRED
 #include <linux/kernel.h>
@@ -113,6 +114,6 @@ static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) {
 static inline void fred_sync_rsp0(unsigned long rsp0) { }
 static inline void fred_update_rsp0(void) { }
 #endif /* CONFIG_X86_FRED */
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* ASM_X86_FRED_H */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 9e7e8ca8e299..ab2547f97c2c 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_FSGSBASE_H
 #define _ASM_FSGSBASE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_64
 
@@ -60,7 +60,7 @@ static inline unsigned long x86_fsbase_read_cpu(void)
 	if (boot_cpu_has(X86_FEATURE_FSGSBASE))
 		fsbase = rdfsbase();
 	else
-		rdmsrl(MSR_FS_BASE, fsbase);
+		rdmsrq(MSR_FS_BASE, fsbase);
 
 	return fsbase;
 }
@@ -70,7 +70,7 @@ static inline void x86_fsbase_write_cpu(unsigned long fsbase)
 	if (boot_cpu_has(X86_FEATURE_FSGSBASE))
 		wrfsbase(fsbase);
 	else
-		wrmsrl(MSR_FS_BASE, fsbase);
+		wrmsrq(MSR_FS_BASE, fsbase);
 }
 
 extern unsigned long x86_gsbase_read_cpu_inactive(void);
@@ -80,6 +80,6 @@ extern unsigned long x86_fsgsbase_read_task(struct task_struct *task,
 
 #endif /* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_FSGSBASE_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f9cb4d07df58..93156ac4ffe0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -22,7 +22,7 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern void __fentry__(void);
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
@@ -36,21 +36,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 {
-#ifdef CONFIG_X86_KERNEL_IBT
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+	if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
-#endif
+
 	return fentry_ip;
 }
 #define ftrace_get_symaddr(fentry_ip)	arch_ftrace_get_symaddr(fentry_ip)
@@ -118,11 +106,11 @@ struct dyn_arch_ftrace {
 };
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer);
@@ -166,6 +154,6 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
 }
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
 #endif /* !COMPILE_OFFSETS */
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 6ffa8b75f4cd..f00c09ffe6a9 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <asm/current.h>
 
 typedef struct {
 #if IS_ENABLED(CONFIG_KVM_INTEL)
@@ -66,7 +65,8 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
-#define local_softirq_pending_ref       pcpu_hot.softirq_pending
+DECLARE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+#define local_softirq_pending_ref       __softirq_pending
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 /*
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 731ee7cc40a5..585bdadba47d 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -69,9 +69,6 @@ extern unsigned long highstart_pfn, highend_pfn;
 		arch_flush_lazy_mmu_mode();		\
 	} while (0)
 
-extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
-					unsigned long end_pfn);
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_HIGHMEM_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index edebf1020e04..162ebd73a698 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,7 +16,7 @@
 
 #include <asm/irq_vectors.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/percpu.h>
 #include <linux/profile.h>
@@ -128,6 +128,6 @@ extern char spurious_entries_start[];
 typedef struct irq_desc* vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
 
-#endif /* !ASSEMBLY_ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_HW_IRQ_H */
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 1e59581d500c..28d845257303 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -21,7 +21,7 @@
 
 #define HAS_KERNEL_IBT	1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_64
 #define ASM_ENDBR	"endbr64\n\t"
@@ -41,7 +41,7 @@
 	_ASM_PTR fname "\n\t"				\
 	".popsection\n\t"
 
-static inline __attribute_const__ u32 gen_endbr(void)
+static __always_inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
 
@@ -56,7 +56,7 @@ static inline __attribute_const__ u32 gen_endbr(void)
 	return endbr;
 }
 
-static inline __attribute_const__ u32 gen_endbr_poison(void)
+static __always_inline __attribute_const__ u32 gen_endbr_poison(void)
 {
 	/*
 	 * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it
@@ -65,19 +65,24 @@ static inline __attribute_const__ u32 gen_endbr_poison(void)
 	return 0x001f0f66; /* osp nopl (%rax) */
 }
 
-static inline bool is_endbr(u32 val)
+static inline bool __is_endbr(u32 val)
 {
 	if (val == gen_endbr_poison())
 		return true;
 
+	/* See cfi_fineibt_bhi_preamble() */
+	if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
+		return true;
+
 	val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
 	return val == gen_endbr();
 }
 
+extern __noendbr bool is_endbr(u32 *val);
 extern __noendbr u64 ibt_save(bool disable);
 extern __noendbr void ibt_restore(u64 save);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #ifdef CONFIG_X86_64
 #define ENDBR	endbr64
@@ -85,29 +90,29 @@ extern __noendbr void ibt_restore(u64 save);
 #define ENDBR	endbr32
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #else /* !IBT */
 
 #define HAS_KERNEL_IBT	0
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define ASM_ENDBR
 #define IBT_NOSEAL(name)
 
 #define __noendbr
 
-static inline bool is_endbr(u32 val) { return false; }
+static inline bool is_endbr(u32 *val) { return false; }
 
 static inline u64 ibt_save(bool disable) { return 0; }
 static inline void ibt_restore(u64 save) { }
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define ENDBR
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index ad5c68f0509d..a4ec27c67988 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -7,7 +7,7 @@
 
 #define IDT_ALIGN	(8 * (1 + HAS_KERNEL_IBT))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/entry-common.h>
 #include <linux/hardirq.h>
 
@@ -474,7 +474,7 @@ static inline void fred_install_sysvec(unsigned int vector, const idtentry_t fun
 		idt_install_sysvec(vector, asm_##function);		\
 }
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 /*
  * The ASM variants for DECLARE_IDTENTRY*() which emit the ASM entry stubs.
@@ -579,7 +579,7 @@ SYM_CODE_START(spurious_entries_start)
 SYM_CODE_END(spurious_entries_start)
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * The actual entry points. Note that DECLARE_IDTENTRY*() serves two
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 53e4015242b4..97f341777db5 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -82,6 +82,7 @@
 #define INAT_NO_REX2	(1 << (INAT_FLAG_OFFS + 8))
 #define INAT_REX2_VARIANT	(1 << (INAT_FLAG_OFFS + 9))
 #define INAT_EVEX_SCALABLE	(1 << (INAT_FLAG_OFFS + 10))
+#define INAT_INV64	(1 << (INAT_FLAG_OFFS + 11))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -242,4 +243,9 @@ static inline int inat_evex_scalable(insn_attr_t attr)
 {
 	return attr & INAT_EVEX_SCALABLE;
 }
+
+static inline int inat_is_invalid64(insn_attr_t attr)
+{
+	return attr & INAT_INV64;
+}
 #endif
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 0e82ebc5d1e1..8b1b1abcef15 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,7 +2,11 @@
 #ifndef _ASM_X86_INIT_H
 #define _ASM_X86_INIT_H
 
+#if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+#define __head	__section(".head.text") __no_sanitize_undefined __no_stack_protector
+#else
 #define __head	__section(".head.text") __no_sanitize_undefined
+#endif
 
 struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 438ccd4f3cc4..e48a00b3311d 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -6,7 +6,7 @@
 #ifndef X86_ASM_INST_H
 #define X86_ASM_INST_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define REG_NUM_INVALID		100
 
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6d7b04ffc5fd..be10c188614f 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -45,7 +45,18 @@
 /* Wildcard match so X86_MATCH_VFM(ANY) works */
 #define INTEL_ANY			IFM(X86_FAMILY_ANY, X86_MODEL_ANY)
 
+/* Family 5 */
+#define INTEL_FAM5_START		IFM(5, 0x00) /* Notational marker, also P5 A-step */
+#define INTEL_PENTIUM_75		IFM(5, 0x02) /* P54C */
+#define INTEL_PENTIUM_MMX		IFM(5, 0x04) /* P55C */
+#define INTEL_QUARK_X1000		IFM(5, 0x09) /* Quark X1000 SoC */
+
+/* Family 6 */
 #define INTEL_PENTIUM_PRO		IFM(6, 0x01)
+#define INTEL_PENTIUM_II_KLAMATH	IFM(6, 0x03)
+#define INTEL_PENTIUM_III_DESCHUTES	IFM(6, 0x05)
+#define INTEL_PENTIUM_III_TUALATIN	IFM(6, 0x0B)
+#define INTEL_PENTIUM_M_DOTHAN		IFM(6, 0x0D)
 
 #define INTEL_CORE_YONAH		IFM(6, 0x0E)
 
@@ -110,11 +121,13 @@
 
 #define INTEL_SAPPHIRERAPIDS_X		IFM(6, 0x8F) /* Golden Cove */
 
-#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF)
+#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF) /* Raptor Cove */
 
-#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD)
+#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
+#define INTEL_BARTLETTLAKE		IFM(6, 0xD7) /* Raptor Cove */
+
 /* "Hybrid" Processors (P-Core/E-Core) */
 
 #define INTEL_LAKEFIELD			IFM(6, 0x8A) /* Sunny Cove / Tremont */
@@ -126,16 +139,16 @@
 #define INTEL_RAPTORLAKE_P		IFM(6, 0xBA)
 #define INTEL_RAPTORLAKE_S		IFM(6, 0xBF)
 
-#define INTEL_METEORLAKE		IFM(6, 0xAC)
+#define INTEL_METEORLAKE		IFM(6, 0xAC) /* Redwood Cove / Crestmont */
 #define INTEL_METEORLAKE_L		IFM(6, 0xAA)
 
-#define INTEL_ARROWLAKE_H		IFM(6, 0xC5)
+#define INTEL_ARROWLAKE_H		IFM(6, 0xC5) /* Lion Cove / Skymont */
 #define INTEL_ARROWLAKE			IFM(6, 0xC6)
 #define INTEL_ARROWLAKE_U		IFM(6, 0xB5)
 
-#define INTEL_LUNARLAKE_M		IFM(6, 0xBD)
+#define INTEL_LUNARLAKE_M		IFM(6, 0xBD) /* Lion Cove / Skymont */
 
-#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC)
+#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC) /* Cougar Cove / Crestmont */
 
 /* "Small Core" Processors (Atom/E-Core) */
 
@@ -149,9 +162,9 @@
 #define INTEL_ATOM_SILVERMONT		IFM(6, 0x37) /* Bay Trail, Valleyview */
 #define INTEL_ATOM_SILVERMONT_D		IFM(6, 0x4D) /* Avaton, Rangely */
 #define INTEL_ATOM_SILVERMONT_MID	IFM(6, 0x4A) /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID2	IFM(6, 0x5A) /* Anniedale */
 
 #define INTEL_ATOM_AIRMONT		IFM(6, 0x4C) /* Cherry Trail, Braswell */
-#define INTEL_ATOM_AIRMONT_MID		IFM(6, 0x5A) /* Moorefield */
 #define INTEL_ATOM_AIRMONT_NP		IFM(6, 0x75) /* Lightning Mountain */
 
 #define INTEL_ATOM_GOLDMONT		IFM(6, 0x5C) /* Apollo Lake */
@@ -176,16 +189,35 @@
 #define INTEL_XEON_PHI_KNL		IFM(6, 0x57) /* Knights Landing */
 #define INTEL_XEON_PHI_KNM		IFM(6, 0x85) /* Knights Mill */
 
-/* Family 5 */
-#define INTEL_QUARK_X1000		IFM(5, 0x09) /* Quark X1000 SoC */
+/* Notational marker denoting the last Family 6 model */
+#define INTEL_FAM6_LAST			IFM(6, 0xFF)
+
+/* Family 15 - NetBurst */
+#define INTEL_P4_WILLAMETTE		IFM(15, 0x01) /* Also Xeon Foster */
+#define INTEL_P4_PRESCOTT		IFM(15, 0x03)
+#define INTEL_P4_PRESCOTT_2M		IFM(15, 0x04)
+#define INTEL_P4_CEDARMILL		IFM(15, 0x06) /* Also Xeon Dempsey */
 
 /* Family 19 */
 #define INTEL_PANTHERCOVE_X		IFM(19, 0x01) /* Diamond Rapids */
 
-/* CPU core types */
+/*
+ * Intel CPU core types
+ *
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum intel_cpu_type {
+	INTEL_CPU_TYPE_UNKNOWN,
 	INTEL_CPU_TYPE_ATOM = 0x20,
 	INTEL_CPU_TYPE_CORE = 0x40,
 };
 
+enum intel_native_id {
+	INTEL_ATOM_CMT_NATIVE_ID = 0x2,  /* Crestmont */
+	INTEL_ATOM_SKT_NATIVE_ID = 0x3,  /* Skymont */
+};
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ed580c7f9d0a..ca309a3227c7 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -170,11 +170,14 @@ extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
 #define ioremap_uc ioremap_uc
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
 #define ioremap_cache ioremap_cache
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,  pgprot_t prot);
 #define ioremap_prot ioremap_prot
 extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
 #define ioremap_encrypted ioremap_encrypted
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
+#define arch_memremap_wb arch_memremap_wb
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
@@ -214,7 +217,7 @@ void memset_io(volatile void __iomem *, int, size_t);
 static inline void __iowrite32_copy(void __iomem *to, const void *from,
 				    size_t count)
 {
-	asm volatile("rep ; movsl"
+	asm volatile("rep movsl"
 		     : "=&c"(count), "=&D"(to), "=&S"(from)
 		     : "0"(count), "1"(to), "2"(from)
 		     : "memory");
@@ -279,7 +282,7 @@ static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \
 			count--;					\
 		}							\
 	} else {							\
-		asm volatile("rep; outs" #bwl				\
+		asm volatile("rep outs" #bwl				\
 			     : "+S"(addr), "+c"(count)			\
 			     : "d"(port) : "memory");			\
 	}								\
@@ -295,7 +298,7 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count)	\
 			count--;					\
 		}							\
 	} else {							\
-		asm volatile("rep; ins" #bwl				\
+		asm volatile("rep ins" #bwl				\
 			     : "+D"(addr), "+c"(count)			\
 			     : "d"(port) : "memory");			\
 	}								\
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index af7541c11821..8ace6559d399 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -168,13 +168,6 @@ void iosf_mbi_unblock_punit_i2c_access(void);
 int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb);
 
 /**
- * iosf_mbi_register_pmic_bus_access_notifier - Unregister PMIC bus notifier
- *
- * @nb: notifier_block to unregister
- */
-int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
-
-/**
  * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus
  *                                                         notifier, unlocked
  *
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 562a547c29a5..735c3a491f60 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -116,7 +116,7 @@
 	ASM_CALL_ARG2
 
 #define call_on_irqstack(func, asm_call, argconstr...)			\
-	call_on_stack(__this_cpu_read(pcpu_hot.hardirq_stack_ptr),	\
+	call_on_stack(__this_cpu_read(hardirq_stack_ptr),		\
 		      func, asm_call, argconstr)
 
 /* Macros to assert type correctness for run_*_on_irqstack macros */
@@ -135,7 +135,7 @@
 	 * User mode entry and interrupt on the irq stack do not	\
 	 * switch stacks. If from user mode the task stack is empty.	\
 	 */								\
-	if (user_mode(regs) || __this_cpu_read(pcpu_hot.hardirq_stack_inuse)) { \
+	if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) {	\
 		irq_enter_rcu();					\
 		func(c_args);						\
 		irq_exit_rcu();						\
@@ -146,9 +146,9 @@
 		 * places. Invoke the stack switch macro with the call	\
 		 * sequence which matches the above direct invocation.	\
 		 */							\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);	\
+		__this_cpu_write(hardirq_stack_inuse, true);		\
 		call_on_irqstack(func, asm_call, constr);		\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);	\
+		__this_cpu_write(hardirq_stack_inuse, false);		\
 	}								\
 }
 
@@ -212,9 +212,9 @@
  */
 #define do_softirq_own_stack()						\
 {									\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);		\
+	__this_cpu_write(hardirq_stack_inuse, true);			\
 	call_on_irqstack(__do_softirq, ASM_CALL_ARG0);			\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);		\
+	__this_cpu_write(hardirq_stack_inuse, false);			\
 }
 
 #endif
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index cf7fc2b8e3ce..9a9b21b78905 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -4,7 +4,7 @@
 
 #include <asm/processor-flags.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/nospec-branch.h>
 
@@ -76,10 +76,32 @@ static __always_inline void native_local_irq_restore(unsigned long flags)
 
 #endif
 
+#ifndef CONFIG_PARAVIRT
+#ifndef __ASSEMBLY__
+/*
+ * Used in the idle loop; sti takes one instruction cycle
+ * to complete:
+ */
+static __always_inline void arch_safe_halt(void)
+{
+	native_safe_halt();
+}
+
+/*
+ * Used when interrupts are already enabled or to
+ * shutdown the processor:
+ */
+static __always_inline void halt(void)
+{
+	native_halt();
+}
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 static __always_inline unsigned long arch_local_save_flags(void)
@@ -98,24 +120,6 @@ static __always_inline void arch_local_irq_enable(void)
 }
 
 /*
- * Used in the idle loop; sti takes one instruction cycle
- * to complete:
- */
-static __always_inline void arch_safe_halt(void)
-{
-	native_safe_halt();
-}
-
-/*
- * Used when interrupts are already enabled or to
- * shutdown the processor:
- */
-static __always_inline void halt(void)
-{
-	native_halt();
-}
-
-/*
  * For spinlocks, etc:
  */
 static __always_inline unsigned long arch_local_irq_save(void)
@@ -133,10 +137,10 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_PARAVIRT_XXL */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static __always_inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & X86_EFLAGS_IF);
@@ -154,6 +158,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags)
 	if (!arch_irqs_disabled_flags(flags))
 		arch_local_irq_enable();
 }
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3f1c1d6c0da1..61dd1dee7812 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -7,7 +7,7 @@
 #include <asm/asm.h>
 #include <asm/nops.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 #include <linux/types.h>
@@ -55,6 +55,6 @@ l_yes:
 
 extern int arch_jump_entry_size(struct jump_entry *entry);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index de75306b932e..d7e33c7f096b 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -23,7 +23,7 @@
 					(1ULL << (__VIRTUAL_MASK_SHIFT - \
 						  KASAN_SHADOW_SCALE_SHIFT)))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_KASAN
 void __init kasan_early_init(void);
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 8ad187462b68..f2ad77929d6e 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -8,16 +8,20 @@
 # define PA_PGD			2
 # define PA_SWAP_PAGE		3
 # define PAGES_NR		4
+#else
+/* Size of each exception handler referenced by the IDT */
+# define KEXEC_DEBUG_EXC_HANDLER_SIZE	6 /* PUSHI, PUSHI, 2-byte JMP */
 #endif
 
 # define KEXEC_CONTROL_PAGE_SIZE	4096
 # define KEXEC_CONTROL_CODE_MAX_SIZE	2048
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/string.h>
 #include <linux/kernel.h>
 
+#include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
@@ -58,6 +62,10 @@ struct kimage;
 extern unsigned long kexec_va_control_page;
 extern unsigned long kexec_pa_table_page;
 extern unsigned long kexec_pa_swap_page;
+extern gate_desc kexec_debug_idt[];
+extern unsigned char kexec_debug_exc_vectors[];
+extern uint16_t kexec_debug_8250_port;
+extern unsigned long kexec_debug_8250_mmio32;
 #endif
 
 /*
@@ -71,41 +79,32 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 	if (oldregs) {
 		memcpy(newregs, oldregs, sizeof(*newregs));
 	} else {
+		asm volatile("mov %%" _ASM_BX ",%0" : "=m"(newregs->bx));
+		asm volatile("mov %%" _ASM_CX ",%0" : "=m"(newregs->cx));
+		asm volatile("mov %%" _ASM_DX ",%0" : "=m"(newregs->dx));
+		asm volatile("mov %%" _ASM_SI ",%0" : "=m"(newregs->si));
+		asm volatile("mov %%" _ASM_DI ",%0" : "=m"(newregs->di));
+		asm volatile("mov %%" _ASM_BP ",%0" : "=m"(newregs->bp));
+		asm volatile("mov %%" _ASM_AX ",%0" : "=m"(newregs->ax));
+		asm volatile("mov %%" _ASM_SP ",%0" : "=m"(newregs->sp));
+#ifdef CONFIG_X86_64
+		asm volatile("mov %%r8,%0" : "=m"(newregs->r8));
+		asm volatile("mov %%r9,%0" : "=m"(newregs->r9));
+		asm volatile("mov %%r10,%0" : "=m"(newregs->r10));
+		asm volatile("mov %%r11,%0" : "=m"(newregs->r11));
+		asm volatile("mov %%r12,%0" : "=m"(newregs->r12));
+		asm volatile("mov %%r13,%0" : "=m"(newregs->r13));
+		asm volatile("mov %%r14,%0" : "=m"(newregs->r14));
+		asm volatile("mov %%r15,%0" : "=m"(newregs->r15));
+#endif
+		asm volatile("mov %%ss,%k0" : "=a"(newregs->ss));
+		asm volatile("mov %%cs,%k0" : "=a"(newregs->cs));
 #ifdef CONFIG_X86_32
-		asm volatile("movl %%ebx,%0" : "=m"(newregs->bx));
-		asm volatile("movl %%ecx,%0" : "=m"(newregs->cx));
-		asm volatile("movl %%edx,%0" : "=m"(newregs->dx));
-		asm volatile("movl %%esi,%0" : "=m"(newregs->si));
-		asm volatile("movl %%edi,%0" : "=m"(newregs->di));
-		asm volatile("movl %%ebp,%0" : "=m"(newregs->bp));
-		asm volatile("movl %%eax,%0" : "=m"(newregs->ax));
-		asm volatile("movl %%esp,%0" : "=m"(newregs->sp));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("movl %%ds, %%eax;" :"=a"(newregs->ds));
-		asm volatile("movl %%es, %%eax;" :"=a"(newregs->es));
-		asm volatile("pushfl; popl %0" :"=m"(newregs->flags));
-#else
-		asm volatile("movq %%rbx,%0" : "=m"(newregs->bx));
-		asm volatile("movq %%rcx,%0" : "=m"(newregs->cx));
-		asm volatile("movq %%rdx,%0" : "=m"(newregs->dx));
-		asm volatile("movq %%rsi,%0" : "=m"(newregs->si));
-		asm volatile("movq %%rdi,%0" : "=m"(newregs->di));
-		asm volatile("movq %%rbp,%0" : "=m"(newregs->bp));
-		asm volatile("movq %%rax,%0" : "=m"(newregs->ax));
-		asm volatile("movq %%rsp,%0" : "=m"(newregs->sp));
-		asm volatile("movq %%r8,%0" : "=m"(newregs->r8));
-		asm volatile("movq %%r9,%0" : "=m"(newregs->r9));
-		asm volatile("movq %%r10,%0" : "=m"(newregs->r10));
-		asm volatile("movq %%r11,%0" : "=m"(newregs->r11));
-		asm volatile("movq %%r12,%0" : "=m"(newregs->r12));
-		asm volatile("movq %%r13,%0" : "=m"(newregs->r13));
-		asm volatile("movq %%r14,%0" : "=m"(newregs->r14));
-		asm volatile("movq %%r15,%0" : "=m"(newregs->r15));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("pushfq; popq %0" :"=m"(newregs->flags));
+		asm volatile("mov %%ds,%k0" : "=a"(newregs->ds));
+		asm volatile("mov %%es,%k0" : "=a"(newregs->es));
 #endif
+		asm volatile("pushf\n\t"
+			     "pop %0" : "=m"(newregs->flags));
 		newregs->ip = _THIS_IP_;
 	}
 }
@@ -225,6 +224,6 @@ unsigned int arch_crash_get_elfcorehdr_size(void);
 #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0b7af5902ff7..9c971f846108 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,13 +27,16 @@
 #include <linux/kfifo.h>
 #include <linux/sched/vhost_task.h>
 #include <linux/call_once.h>
+#include <linux/atomic.h>
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
+#include <asm/msr.h>
 #include <asm/asm.h>
+#include <asm/irq_remapping.h>
 #include <asm/kvm_page_track.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/reboot.h>
@@ -405,7 +408,7 @@ union kvm_cpu_role {
 };
 
 struct kvm_rmap_head {
-	unsigned long val;
+	atomic_long_t val;
 };
 
 struct kvm_pio_request {
@@ -780,6 +783,7 @@ struct kvm_vcpu_arch {
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
+	u64 host_debugctl;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	bool load_eoi_exitmap_pending;
@@ -879,6 +883,7 @@ struct kvm_vcpu_arch {
 
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
+	bool cpuid_dynamic_bits_dirty;
 	bool is_amd_compatible;
 
 	/*
@@ -908,7 +913,8 @@ struct kvm_vcpu_arch {
 	int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
 
 	gpa_t time;
-	struct pvclock_vcpu_time_info hv_clock;
+	s8  pvclock_tsc_shift;
+	u32 pvclock_tsc_mul;
 	unsigned int hw_tsc_khz;
 	struct gfn_to_pfn_cache pv_time;
 	/* set guest stopped flag in pvclock flags field */
@@ -996,8 +1002,8 @@ struct kvm_vcpu_arch {
 		u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
 		u16 vec;
 		u32 id;
-		bool send_user_only;
 		u32 host_apf_flags;
+		bool send_always;
 		bool delivery_as_pf_vmexit;
 		bool pageready_pending;
 	} apf;
@@ -1052,6 +1058,7 @@ struct kvm_vcpu_arch {
 
 	/* Protected Guests */
 	bool guest_state_protected;
+	bool guest_tsc_protected;
 
 	/*
 	 * Set when PDPTS were loaded directly by the userspace without
@@ -1188,6 +1195,8 @@ struct kvm_xen {
 	struct gfn_to_pfn_cache shinfo_cache;
 	struct idr evtchn_ports;
 	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+
+	struct kvm_xen_hvm_config hvm_config;
 };
 #endif
 
@@ -1353,8 +1362,6 @@ struct kvm_arch {
 
 	u64 shadow_mmio_value;
 
-	struct iommu_domain *iommu_domain;
-	bool iommu_noncoherent;
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA
 	atomic_t noncoherent_dma_count;
 #define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
@@ -1410,8 +1417,6 @@ struct kvm_arch {
 	struct delayed_work kvmclock_update_work;
 	struct delayed_work kvmclock_sync_work;
 
-	struct kvm_xen_hvm_config xen_hvm_config;
-
 	/* reads protected by irq_srcu, writes by irq_lock */
 	struct hlist_head mask_notifier_list;
 
@@ -1469,8 +1474,13 @@ struct kvm_arch {
 	struct once nx_once;
 
 #ifdef CONFIG_X86_64
-	/* The number of TDP MMU pages across all roots. */
+#ifdef CONFIG_KVM_PROVE_MMU
+	/*
+	 * The number of TDP MMU pages across all roots.  Used only to sanity
+	 * check that KVM isn't leaking TDP MMU pages.
+	 */
 	atomic64_t tdp_mmu_pages;
+#endif
 
 	/*
 	 * List of struct kvm_mmu_pages being used as roots.
@@ -1478,6 +1488,7 @@ struct kvm_arch {
 	 * tdp_mmu_page set.
 	 *
 	 * For reads, this list is protected by:
+	 *	RCU alone or
 	 *	the MMU lock in read mode + RCU or
 	 *	the MMU lock in write mode
 	 *
@@ -2163,8 +2174,8 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu);
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
-void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
-void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr,
+			   bool has_error_code, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 				    struct x86_exception *fault);
@@ -2268,7 +2279,7 @@ static inline unsigned long read_msr(unsigned long msr)
 {
 	u64 value;
 
-	rdmsrl(msr, value);
+	rdmsrq(msr, value);
 	return value;
 }
 #endif
@@ -2414,4 +2425,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
  */
 #define KVM_EXIT_HYPERCALL_MBZ		GENMASK_ULL(31, 1)
 
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index dc31b13b87a0..9d38ae744a2e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -38,7 +38,7 @@
 #define ASM_FUNC_ALIGN		__stringify(__FUNC_ALIGN)
 #define SYM_F_ALIGN		__FUNC_ALIGN
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define RET	jmp __x86_return_thunk
@@ -50,7 +50,7 @@
 #endif
 #endif /* CONFIG_MITIGATION_RETPOLINE */
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define ASM_RET	"jmp __x86_return_thunk\n\t"
@@ -62,7 +62,7 @@
 #endif
 #endif /* CONFIG_MITIGATION_RETPOLINE */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the
@@ -119,33 +119,37 @@
 
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
-	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
 #define SYM_FUNC_START_NOALIGN(name)			\
-	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_LOCAL -- use for local functions */
 #define SYM_FUNC_START_LOCAL(name)			\
-	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
 #define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
-	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_WEAK -- use for weak functions */
 #define SYM_FUNC_START_WEAK(name)			\
-	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
 #define SYM_FUNC_START_WEAK_NOALIGN(name)		\
-	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
+
+/*
+ * Expose 'sym' to the startup code in arch/x86/boot/startup/, by emitting an
+ * alias prefixed with __pi_
+ */
+#ifdef __ASSEMBLER__
+#define SYM_PIC_ALIAS(sym)	SYM_ALIAS(__pi_ ## sym, sym, SYM_L_GLOBAL)
+#else
+#define SYM_PIC_ALIAS(sym)	extern typeof(sym) __PASTE(__pi_, sym) __alias(sym)
+#endif
 
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index eb2db07ef39c..6c77c03139f7 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -296,8 +296,6 @@ enum mcp_flags {
 
 void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
-bool mce_notify_irq(void);
-
 DECLARE_PER_CPU(struct mce, injectm);
 
 /* Disable CMCI/polling for MCA bank claimed by firmware */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index f922b682b9b4..ea6494628cb0 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -10,7 +10,7 @@
 #ifndef __X86_MEM_ENCRYPT_H__
 #define __X86_MEM_ENCRYPT_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/init.h>
 #include <linux/cc_platform.h>
@@ -61,7 +61,7 @@ void __init sev_es_init_vc_handling(void);
 
 static inline u64 sme_get_me_mask(void)
 {
-	return RIP_REL_REF(sme_me_mask);
+	return sme_me_mask;
 }
 
 #define __bss_decrypted __section(".bss..decrypted")
@@ -114,6 +114,6 @@ void add_encrypt_protection_map(void);
 
 extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 695e569159c1..8b41f26f003b 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#include <asm/msr.h>
+
 struct cpu_signature {
 	unsigned int sig;
 	unsigned int pf;
@@ -17,10 +19,12 @@ struct ucode_cpu_info {
 void load_ucode_bsp(void);
 void load_ucode_ap(void);
 void microcode_bsp_resume(void);
+bool __init microcode_loader_disabled(void);
 #else
 static inline void load_ucode_bsp(void)	{ }
 static inline void load_ucode_ap(void) { }
 static inline void microcode_bsp_resume(void) { }
+static inline bool __init microcode_loader_disabled(void) { return false; }
 #endif
 
 extern unsigned long initrd_start_early;
@@ -61,7 +65,7 @@ static inline u32 intel_get_microcode_revision(void)
 {
 	u32 rev, dummy;
 
-	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
+	native_wrmsrq(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
 	native_cpuid_eax(1);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 3b496cdcb74b..0fe9c569d171 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -16,6 +16,8 @@
 #define MM_CONTEXT_LOCK_LAM		2
 /* Allow LAM and SVA coexisting */
 #define MM_CONTEXT_FORCE_TAGGED_SVA	3
+/* Tracks mm_cpumask */
+#define MM_CONTEXT_NOTRACK		4
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.
@@ -44,9 +46,7 @@ typedef struct {
 	struct ldt_struct	*ldt;
 #endif
 
-#ifdef CONFIG_X86_64
 	unsigned long flags;
-#endif
 
 #ifdef CONFIG_ADDRESS_MASKING
 	/* Active LAM mode:  X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
@@ -69,6 +69,18 @@ typedef struct {
 	u16 pkey_allocation_map;
 	s16 execute_only_pkey;
 #endif
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	/*
+	 * The global ASID will be a non-zero value when the process has
+	 * the same ASID across all CPUs, allowing it to make use of
+	 * hardware-assisted remote TLB invalidation like AMD INVLPGB.
+	 */
+	u16 global_asid;
+
+	/* The process is transitioning to a new global ASID number. */
+	bool asid_transition;
+#endif
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(mm)						\
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 795fdd53bd0a..73bf3b1b44e8 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_MMU_CONTEXT_H
 #define _ASM_X86_MMU_CONTEXT_H
 
-#include <asm/desc.h>
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
 #include <linux/pkeys.h>
@@ -13,6 +12,7 @@
 #include <asm/paravirt.h>
 #include <asm/debugreg.h>
 #include <asm/gsseg.h>
+#include <asm/desc.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -139,6 +139,11 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+#define mm_init_global_asid mm_init_global_asid
+extern void mm_init_global_asid(struct mm_struct *mm);
+
+extern void mm_free_global_asid(struct mm_struct *mm);
+
 /*
  * Init a new mm.  Used on mm copies, like at fork()
  * and on mm's that are brand-new, like at execve().
@@ -161,6 +166,8 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 #endif
+
+	mm_init_global_asid(mm);
 	mm_reset_untag_mask(mm);
 	init_new_context_ldt(mm);
 	return 0;
@@ -170,6 +177,7 @@ static inline int init_new_context(struct task_struct *tsk,
 static inline void destroy_context(struct mm_struct *mm)
 {
 	destroy_context_ldt(mm);
+	mm_free_global_asid(mm);
 }
 
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
@@ -182,7 +190,7 @@ extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 #define activate_mm(prev, next)			\
 do {						\
 	paravirt_enter_mmap(next);		\
-	switch_mm((prev), (next), NULL);	\
+	switch_mm_irqs_off((prev), (next), NULL);	\
 } while (0);
 
 #ifdef CONFIG_X86_32
@@ -239,6 +247,16 @@ static inline bool is_64bit_mm(struct mm_struct *mm)
 }
 #endif
 
+static inline bool is_notrack_mm(struct mm_struct *mm)
+{
+	return test_bit(MM_CONTEXT_NOTRACK, &mm->context.flags);
+}
+
+static inline void set_notrack_mm(struct mm_struct *mm)
+{
+	set_bit(MM_CONTEXT_NOTRACK, &mm->context.flags);
+}
+
 /*
  * We only want to enforce protection keys on the current process
  * because we effectively have no access to PKRU for other
@@ -264,4 +282,7 @@ unsigned long __get_current_cr3_fast(void);
 
 #include <asm-generic/mmu_context.h>
 
+extern struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm);
+extern void unuse_temporary_mm(struct mm_struct *prev_mm);
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f91ab1e75f9f..778444310cfb 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -8,6 +8,7 @@
 #include <linux/io.h>
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
+#include <asm/msr.h>
 #include <hyperv/hvhdk.h>
 
 /*
@@ -43,8 +44,6 @@ extern bool hyperv_paravisor_present;
 
 extern void *hv_hypercall_pg;
 
-extern u64 hv_current_partition_id;
-
 extern union hv_ghcb * __percpu *hv_ghcb_pg;
 
 bool hv_isolation_type_snp(void);
@@ -58,10 +57,6 @@ u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
 #define HV_AP_INIT_GPAT_DEFAULT		0x0007040600070406ULL
 #define HV_AP_SEGMENT_LIMIT		0xffffffff
 
-int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
-int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
-int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
-
 /*
  * If the hypercall involves no input or output parameters, the hypervisor
  * ignores the corresponding GPA pointer.
@@ -77,11 +72,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return hv_tdx_hypercall(control, input_address, output_address);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[output_address], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input_address)
-				     :  "r" (output_address)
+				     : [output_address] "r" (output_address)
 				     : "cc", "memory", "r8", "r9", "r10", "r11");
 		return hv_status;
 	}
@@ -89,12 +84,12 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("mov %4, %%r8\n"
+	__asm__ __volatile__("mov %[output_address], %%r8\n"
 			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address),
-				THUNK_TARGET(hv_hypercall_pg)
+			     : [output_address] "r" (output_address),
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -160,7 +155,7 @@ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
 				      : "cc", "edi", "esi");
 	}
 #endif
-		return hv_status;
+	return hv_status;
 }
 
 static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
@@ -187,18 +182,18 @@ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 		return hv_tdx_hypercall(control, input1, input2);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2)
+				     : [input2] "r" (input2)
 				     : "cc", "r8", "r9", "r10", "r11");
 	} else {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2),
+				     : [input2] "r" (input2),
 				       THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
@@ -310,7 +305,7 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value);
 
 static __always_inline u64 hv_raw_get_msr(unsigned int reg)
 {
-	return __rdmsr(reg);
+	return native_rdmsrq(reg);
 }
 
 #else /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 72765b2fe0d8..b7dded3c8113 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_TCE		15 /* Enable Translation Cache Extensions */
 #define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -34,6 +35,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_TCE		(1<<_EFER_TCE)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /*
@@ -209,6 +211,14 @@
 						 * VERW clears CPU Register
 						 * File.
 						 */
+#define ARCH_CAP_ITS_NO			BIT_ULL(62) /*
+						     * Not susceptible to
+						     * Indirect Target Selection.
+						     * This bit is not set by
+						     * HW, but is synthesized by
+						     * VMMs for guests to know
+						     * their affected status.
+						     */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -523,7 +533,7 @@
 #define MSR_HWP_CAPABILITIES		0x00000771
 #define MSR_HWP_REQUEST_PKG		0x00000772
 #define MSR_HWP_INTERRUPT		0x00000773
-#define MSR_HWP_REQUEST 		0x00000774
+#define MSR_HWP_REQUEST			0x00000774
 #define MSR_HWP_STATUS			0x00000777
 
 /* CPUID.6.EAX */
@@ -540,16 +550,16 @@
 #define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
 
 /* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) 		(x & 0xff)
-#define HWP_MAX_PERF(x) 		((x & 0xff) << 8)
+#define HWP_MIN_PERF(x)			(x & 0xff)
+#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
 #define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
+#define HWP_ENERGY_PERF_PREFERENCE(x)	(((u64)x & 0xff) << 24)
 #define HWP_EPP_PERFORMANCE		0x00
 #define HWP_EPP_BALANCE_PERFORMANCE	0x80
 #define HWP_EPP_BALANCE_POWERSAVE	0xC0
 #define HWP_EPP_POWERSAVE		0xFF
-#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
+#define HWP_ACTIVITY_WINDOW(x)		((u64)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x)		((u64)(x & 0x1) << 42)
 
 /* IA32_HWP_STATUS */
 #define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
@@ -592,7 +602,11 @@
 /* V6 PMON MSR range */
 #define MSR_IA32_PMC_V6_GP0_CTR		0x1900
 #define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B	0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C	0x1903
 #define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B	0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C	0x1983
 #define MSR_IA32_PMC_V6_STEP		4
 
 /* KeyID partitioning between MKTME and TDX */
@@ -701,15 +715,17 @@
 #define MSR_AMD_CPPC_REQ		0xc00102b3
 #define MSR_AMD_CPPC_STATUS		0xc00102b4
 
-#define AMD_CPPC_LOWEST_PERF(x)		(((x) >> 0) & 0xff)
-#define AMD_CPPC_LOWNONLIN_PERF(x)	(((x) >> 8) & 0xff)
-#define AMD_CPPC_NOMINAL_PERF(x)	(((x) >> 16) & 0xff)
-#define AMD_CPPC_HIGHEST_PERF(x)	(((x) >> 24) & 0xff)
+/* Masks for use with MSR_AMD_CPPC_CAP1 */
+#define AMD_CPPC_LOWEST_PERF_MASK	GENMASK(7, 0)
+#define AMD_CPPC_LOWNONLIN_PERF_MASK	GENMASK(15, 8)
+#define AMD_CPPC_NOMINAL_PERF_MASK	GENMASK(23, 16)
+#define AMD_CPPC_HIGHEST_PERF_MASK	GENMASK(31, 24)
 
-#define AMD_CPPC_MAX_PERF(x)		(((x) & 0xff) << 0)
-#define AMD_CPPC_MIN_PERF(x)		(((x) & 0xff) << 8)
-#define AMD_CPPC_DES_PERF(x)		(((x) & 0xff) << 16)
-#define AMD_CPPC_ENERGY_PERF_PREF(x)	(((x) & 0xff) << 24)
+/* Masks for use with MSR_AMD_CPPC_REQ */
+#define AMD_CPPC_MAX_PERF_MASK		GENMASK(7, 0)
+#define AMD_CPPC_MIN_PERF_MASK		GENMASK(15, 8)
+#define AMD_CPPC_DES_PERF_MASK		GENMASK(23, 16)
+#define AMD_CPPC_EPP_PERF_MASK		GENMASK(31, 24)
 
 /* AMD Performance Counter Global Status and Control MSRs */
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
@@ -721,6 +737,7 @@
 
 /* Zen4 */
 #define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4
 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
 
 /* Fam 19h MSRs */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 001853541f1e..4096b8af4ba7 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -4,7 +4,7 @@
 
 #include "msr-index.h"
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/errno.h>
@@ -12,6 +12,7 @@
 #include <uapi/asm/msr.h>
 #include <asm/shared/msr.h>
 
+#include <linux/types.h>
 #include <linux/percpu.h>
 
 struct msr_info {
@@ -37,23 +38,6 @@ struct saved_msrs {
 };
 
 /*
- * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
- * constraint has different meanings. For i386, "A" means exactly
- * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
- * it means rax *or* rdx.
- */
-#ifdef CONFIG_X86_64
-/* Using 64-bit values saves one instruction clearing the high half of low */
-#define DECLARE_ARGS(val, low, high)	unsigned long low, high
-#define EAX_EDX_VAL(val, low, high)	((low) | (high) << 32)
-#define EAX_EDX_RET(val, low, high)	"=a" (low), "=d" (high)
-#else
-#define DECLARE_ARGS(val, low, high)	unsigned long long val
-#define EAX_EDX_VAL(val, low, high)	(val)
-#define EAX_EDX_RET(val, low, high)	"=A" (val)
-#endif
-
-/*
  * Be very careful with includes. This header is prone to include loops.
  */
 #include <asm/atomic.h>
@@ -63,13 +47,13 @@ struct saved_msrs {
 DECLARE_TRACEPOINT(read_msr);
 DECLARE_TRACEPOINT(write_msr);
 DECLARE_TRACEPOINT(rdpmc);
-extern void do_trace_write_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_read_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed);
+extern void do_trace_write_msr(u32 msr, u64 val, int failed);
+extern void do_trace_read_msr(u32 msr, u64 val, int failed);
+extern void do_trace_rdpmc(u32 msr, u64 val, int failed);
 #else
-static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
+static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {}
 #endif
 
 /*
@@ -79,9 +63,9 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
  * think of extending them - you will be slapped with a stinking trout or a frozen
  * shark will reach you, wherever you are! You've been warned.
  */
-static __always_inline unsigned long long __rdmsr(unsigned int msr)
+static __always_inline u64 __rdmsr(u32 msr)
 {
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("1: rdmsr\n"
 		     "2:\n"
@@ -91,12 +75,12 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsrq(u32 msr, u64 val)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
-		     : : "c" (msr), "a"(low), "d" (high) : "memory");
+		     : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory");
 }
 
 #define native_rdmsr(msr, val1, val2)			\
@@ -106,16 +90,20 @@ do {							\
 	(void)((val2) = (u32)(__val >> 32));		\
 } while (0)
 
+static __always_inline u64 native_rdmsrq(u32 msr)
+{
+	return __rdmsr(msr);
+}
+
 #define native_wrmsr(msr, low, high)			\
-	__wrmsr(msr, low, high)
+	__wrmsrq((msr), (u64)(high) << 32 | (low))
 
-#define native_wrmsrl(msr, val)				\
-	__wrmsr((msr), (u32)((u64)(val)),		\
-		       (u32)((u64)(val) >> 32))
+#define native_wrmsrq(msr, val)				\
+	__wrmsrq((msr), (val))
 
-static inline unsigned long long native_read_msr(unsigned int msr)
+static inline u64 native_read_msr(u32 msr)
 {
-	unsigned long long val;
+	u64 val;
 
 	val = __rdmsr(msr);
 
@@ -125,34 +113,35 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 	return val;
 }
 
-static inline unsigned long long native_read_msr_safe(unsigned int msr,
-						      int *err)
+static inline int native_read_msr_safe(u32 msr, u64 *p)
 {
-	DECLARE_ARGS(val, low, high);
+	int err;
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
 		     "2:\n\t"
 		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
-		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : [err] "=r" (err), EAX_EDX_RET(val, low, high)
 		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
-		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
-	return EAX_EDX_VAL(val, low, high);
+		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err);
+
+	*p = EAX_EDX_VAL(val, low, high);
+
+	return err;
 }
 
 /* Can be uninlined because referenced by paravirt */
-static inline void notrace
-native_write_msr(unsigned int msr, u32 low, u32 high)
+static inline void notrace native_write_msr(u32 msr, u64 val)
 {
-	__wrmsr(msr, low, high);
+	native_wrmsrq(msr, val);
 
 	if (tracepoint_enabled(write_msr))
-		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
+		do_trace_write_msr(msr, val, 0);
 }
 
 /* Can be uninlined because referenced by paravirt */
-static inline int notrace
-native_write_msr_safe(unsigned int msr, u32 low, u32 high)
+static inline int notrace native_write_msr_safe(u32 msr, u64 val)
 {
 	int err;
 
@@ -160,73 +149,19 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 		     "2:\n\t"
 		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high)
+		     : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32))
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
-		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
+		do_trace_write_msr(msr, val, err);
 	return err;
 }
 
 extern int rdmsr_safe_regs(u32 regs[8]);
 extern int wrmsr_safe_regs(u32 regs[8]);
 
-/**
- * rdtsc() - returns the current TSC without ordering constraints
- *
- * rdtsc() returns the result of RDTSC as a 64-bit integer.  The
- * only ordering constraint it supplies is the ordering implied by
- * "asm volatile": it will put the RDTSC in the place you expect.  The
- * CPU can and will speculatively execute that RDTSC, though, so the
- * results can be non-monotonic if compared on different CPUs.
- */
-static __always_inline unsigned long long rdtsc(void)
+static inline u64 native_read_pmc(int counter)
 {
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
-
-	return EAX_EDX_VAL(val, low, high);
-}
-
-/**
- * rdtsc_ordered() - read the current TSC in program order
- *
- * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
- * It is ordered like a load to a global in-memory counter.  It should
- * be impossible to observe non-monotonic rdtsc_unordered() behavior
- * across multiple CPUs as long as the TSC is synced.
- */
-static __always_inline unsigned long long rdtsc_ordered(void)
-{
-	DECLARE_ARGS(val, low, high);
-
-	/*
-	 * The RDTSC instruction is not ordered relative to memory
-	 * access.  The Intel SDM and the AMD APM are both vague on this
-	 * point, but empirically an RDTSC instruction can be
-	 * speculatively executed before prior loads.  An RDTSC
-	 * immediately after an appropriate barrier appears to be
-	 * ordered as a normal load, that is, it provides the same
-	 * ordering guarantees as reading from a global memory location
-	 * that some other imaginary CPU is updating continuously with a
-	 * time stamp.
-	 *
-	 * Thus, use the preferred barrier on the respective CPU, aiming for
-	 * RDTSCP as the default.
-	 */
-	asm volatile(ALTERNATIVE_2("rdtsc",
-				   "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
-				   "rdtscp", X86_FEATURE_RDTSCP)
-			: EAX_EDX_RET(val, low, high)
-			/* RDTSCP clobbers ECX with MSR_TSC_AUX. */
-			:: "ecx");
-
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_pmc(int counter)
-{
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
 	if (tracepoint_enabled(rdpmc))
@@ -251,51 +186,44 @@ do {								\
 	(void)((high) = (u32)(__val >> 32));			\
 } while (0)
 
-static inline void wrmsr(unsigned int msr, u32 low, u32 high)
+static inline void wrmsr(u32 msr, u32 low, u32 high)
 {
-	native_write_msr(msr, low, high);
+	native_write_msr(msr, (u64)high << 32 | low);
 }
 
-#define rdmsrl(msr, val)			\
+#define rdmsrq(msr, val)			\
 	((val) = native_read_msr((msr)))
 
-static inline void wrmsrl(unsigned int msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
 {
-	native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+	native_write_msr(msr, val);
 }
 
 /* wrmsr with exception handling */
-static inline int wrmsr_safe(unsigned int msr, u32 low, u32 high)
+static inline int wrmsrq_safe(u32 msr, u64 val)
 {
-	return native_write_msr_safe(msr, low, high);
+	return native_write_msr_safe(msr, val);
 }
 
 /* rdmsr with exception handling */
 #define rdmsr_safe(msr, low, high)				\
 ({								\
-	int __err;						\
-	u64 __val = native_read_msr_safe((msr), &__err);	\
+	u64 __val;						\
+	int __err = native_read_msr_safe((msr), &__val);	\
 	(*low) = (u32)__val;					\
 	(*high) = (u32)(__val >> 32);				\
 	__err;							\
 })
 
-static inline int rdmsrl_safe(unsigned int msr, unsigned long long *p)
+static inline int rdmsrq_safe(u32 msr, u64 *p)
 {
-	int err;
-
-	*p = native_read_msr_safe(msr, &err);
-	return err;
+	return native_read_msr_safe(msr, p);
 }
 
-#define rdpmc(counter, low, high)			\
-do {							\
-	u64 _l = native_read_pmc((counter));		\
-	(low)  = (u32)_l;				\
-	(high) = (u32)(_l >> 32);			\
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+static __always_inline u64 rdpmc(int counter)
+{
+	return native_read_pmc(counter);
+}
 
 #endif	/* !CONFIG_PARAVIRT_XXL */
 
@@ -315,11 +243,11 @@ static __always_inline void wrmsrns(u32 msr, u64 val)
 }
 
 /*
- * 64-bit version of wrmsr_safe():
+ * Dual u32 version of wrmsrq_safe():
  */
-static inline int wrmsrl_safe(u32 msr, u64 val)
+static inline int wrmsr_safe(u32 msr, u32 low, u32 high)
 {
-	return wrmsr_safe(msr, (u32)val,  (u32)(val >> 32));
+	return wrmsrq_safe(msr, (u64)high << 32 | low);
 }
 
 struct msr __percpu *msrs_alloc(void);
@@ -330,14 +258,14 @@ int msr_clear_bit(u32 msr, u8 bit);
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
 void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 #else  /*  CONFIG_SMP  */
@@ -351,14 +279,14 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 	wrmsr(msr_no, l, h);
 	return 0;
 }
-static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
-	rdmsrl(msr_no, *q);
+	rdmsrq(msr_no, *q);
 	return 0;
 }
-static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
-	wrmsrl(msr_no, q);
+	wrmsrq(msr_no, q);
 	return 0;
 }
 static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
@@ -380,13 +308,13 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
 	return wrmsr_safe(msr_no, l, h);
 }
-static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
-	return rdmsrl_safe(msr_no, q);
+	return rdmsrq_safe(msr_no, q);
 }
-static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
-	return wrmsrl_safe(msr_no, q);
+	return wrmsrq_safe(msr_no, q);
 }
 static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 {
@@ -397,5 +325,11 @@ static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 	return wrmsr_safe_regs(regs);
 }
 #endif  /* CONFIG_SMP */
-#endif /* __ASSEMBLY__ */
+
+/* Compatibility wrappers: */
+#define rdmsrl(msr, val) rdmsrq(msr, val)
+#define wrmsrl(msr, val) wrmsrq(msr, val)
+#define rdmsrl_on_cpu(cpu, msr, q) rdmsrq_on_cpu(cpu, msr, q)
+
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index ce857ef54cf1..dd2b129b0418 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,29 +25,31 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-static __always_inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
+static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx));
 }
 
-static __always_inline void __monitorx(const void *eax, unsigned long ecx,
-			      unsigned long edx)
+static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitorx %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfa;"
+	/* "monitorx %eax, %ecx, %edx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfa"
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
 
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -76,13 +78,12 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
  * EAX                     (logical) address to monitor
  * ECX                     #GP if not zero
  */
-static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
-				     unsigned long ecx)
+static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
 	/* No MDS buffer clear as this is AMD/HYGON only */
 
-	/* "mwaitx %eax, %ebx, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb;"
+	/* "mwaitx %eax, %ebx, %ecx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfb"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
@@ -95,12 +96,11 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
  * executing mwait, it would otherwise go unnoticed and the next tick
  * would not be reprogrammed accordingly before mwait ever wakes up.
  */
-static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+
+	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -113,16 +113,13 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  * New with Core Duo processors, MWAIT can take some hints based on CPU
  * capability.
  */
-static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
-		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
-			mb();
-			clflush((void *)&current_thread_info()->flags);
-			mb();
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 
 		if (!need_resched()) {
 			if (ecx & 1) {
@@ -144,16 +141,9 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
  */
 static inline void __tpause(u32 ecx, u32 edx, u32 eax)
 {
-	/* "tpause %ecx, %edx, %eax;" */
-	#ifdef CONFIG_AS_TPAUSE
-	asm volatile("tpause %%ecx\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#else
-	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#endif
+	/* "tpause %ecx" */
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+		     :: "c" (ecx), "d" (edx), "a" (eax));
 }
 
 #endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 41a0ebb699ec..79d88d12c8fb 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -14,12 +14,26 @@ extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-extern int unknown_nmi_panic;
-
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+extern int unknown_nmi_panic;
+extern int panic_on_unrecovered_nmi;
+extern int panic_on_io_nmi;
+
+/* NMI handler flags */
 #define NMI_FLAG_FIRST	1
 
+/**
+ * enum - NMI types.
+ * @NMI_LOCAL:    Local NMI, CPU-specific NMI generated by the Local APIC.
+ * @NMI_UNKNOWN:  Unknown NMI, the source of the NMI may not be identified.
+ * @NMI_SERR:     System Error NMI, typically triggered by PCI errors.
+ * @NMI_IO_CHECK: I/O Check NMI, related to I/O errors.
+ * @NMI_MAX:      Maximum value for NMI types.
+ *
+ * NMI types are used to categorize NMIs and to dispatch them to the
+ * appropriate handler.
+ */
 enum {
 	NMI_LOCAL=0,
 	NMI_UNKNOWN,
@@ -28,6 +42,7 @@ enum {
 	NMI_MAX
 };
 
+/* NMI handler return values */
 #define NMI_DONE	0
 #define NMI_HANDLED	1
 
@@ -41,6 +56,25 @@ struct nmiaction {
 	const char		*name;
 };
 
+/**
+ * register_nmi_handler - Register a handler for a specific NMI type
+ * @t:    NMI type (e.g. NMI_LOCAL)
+ * @fn:   The NMI handler
+ * @fg:   Flags associated with the NMI handler
+ * @n:    Name of the NMI handler
+ * @init: Optional __init* attributes for struct nmiaction
+ *
+ * Adds the provided handler to the list of handlers for the specified
+ * NMI type. Handlers flagged with NMI_FLAG_FIRST would be executed first.
+ *
+ * Sometimes the source of an NMI can't be reliably determined which
+ * results in an NMI being tagged as "unknown". Register an additional
+ * handler using the NMI type - NMI_UNKNOWN to handle such cases. The
+ * caller would get one last chance to assume responsibility for the
+ * NMI.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
 #define register_nmi_handler(t, fn, fg, n, init...)	\
 ({							\
 	static struct nmiaction init fn##_na = {	\
@@ -54,7 +88,18 @@ struct nmiaction {
 
 int __register_nmi_handler(unsigned int, struct nmiaction *);
 
-void unregister_nmi_handler(unsigned int, const char *);
+/**
+ * unregister_nmi_handler - Unregister a handler for a specific NMI type
+ * @type: NMI type (e.g. NMI_LOCAL)
+ * @name: Name of the NMI handler used during registration
+ *
+ * Removes the handler associated with the specified NMI type from the
+ * NMI handler list. The "name" is used as a lookup key to identify the
+ * handler.
+ */
+void unregister_nmi_handler(unsigned int type, const char *name);
+
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler);
 
 void stop_nmi(void);
 void restart_nmi(void);
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index 1c1b7550fa55..cd94221d8335 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -82,7 +82,7 @@
 #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
 #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern const unsigned char * const x86_nops[];
 #endif
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5..20d754b98f3f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -12,7 +12,6 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 /*
  * Call depth tracking for Intel SKL CPUs to address the RSB underflow
@@ -78,21 +77,21 @@
 #include <asm/asm-offsets.h>
 
 #define CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	$-1, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH_FROM_CALL				\
 	movb	$0xfc, %al;					\
 	shl	$56, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	sarq	$5, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
@@ -177,7 +176,7 @@
 	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
 	lfence;
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions
@@ -198,9 +197,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -271,7 +269,7 @@
  * typically has NO_MELTDOWN).
  *
  * While retbleed_untrain_ret() doesn't clobber anything but requires stack,
- * entry_ibpb() will clobber AX, CX, DX.
+ * write_ibpb() will clobber AX, CX, DX.
  *
  * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
  * where we have a stack but before any RET instruction.
@@ -281,7 +279,7 @@
 	VALIDATE_UNRET_END
 	CALL_UNTRAIN_RET
 	ALTERNATIVE_2 "",						\
-		      "call entry_ibpb", \ibpb_feature,			\
+		      "call write_ibpb", \ibpb_feature,			\
 		     __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
 #endif
 .endm
@@ -329,19 +327,23 @@
 .endm
 
 .macro CLEAR_BRANCH_HISTORY_VMEXIT
-	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT
 .endm
 #else
 #define CLEAR_BRANCH_HISTORY
 #define CLEAR_BRANCH_HISTORY_VMEXIT
 #endif
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
+
+#define ITS_THUNK_SIZE	64
 
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+typedef u8 its_thunk_t[ITS_THUNK_SIZE];
 extern retpoline_thunk_t __x86_indirect_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
+extern its_thunk_t	 __x86_indirect_its_thunk_array[];
 
 #ifdef CONFIG_MITIGATION_RETHUNK
 extern void __x86_return_thunk(void);
@@ -365,12 +367,18 @@ static inline void srso_return_thunk(void) {}
 static inline void srso_alias_return_thunk(void) {}
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_return_thunk(void);
+#else
+static inline void its_return_thunk(void) {}
+#endif
+
 extern void retbleed_return_thunk(void);
 extern void srso_return_thunk(void);
 extern void srso_alias_return_thunk(void);
 
 extern void entry_untrain_ret(void);
-extern void entry_ibpb(void);
+extern void write_ibpb(void);
 
 #ifdef CONFIG_X86_64
 extern void clear_bhb_loop(void);
@@ -388,6 +396,8 @@ extern void call_depth_return_thunk(void);
 		    __stringify(INCREMENT_CALL_DEPTH),		\
 		    X86_FEATURE_CALL_DEPTH)
 
+DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 DECLARE_PER_CPU(u64, __x86_call_count);
 DECLARE_PER_CPU(u64, __x86_ret_count);
@@ -421,19 +431,22 @@ static inline void call_depth_return_thunk(void) {}
 #ifdef CONFIG_X86_64
 
 /*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
+/*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
@@ -511,11 +524,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 		: "memory");
 }
 
-extern u64 x86_pred_cmd;
-
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB);
+	asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)
+			    : ASM_CALL_CONSTRAINT
+			    :: "rax", "rcx", "rdx", "memory");
 }
 
 /* The Intel SPEC CTRL MSR base value cache */
@@ -552,11 +565,13 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
+
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
-DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
 
 extern u16 mds_verw_sel;
 
@@ -596,6 +611,6 @@ static __always_inline void mds_idle_clear_cpu_buffers(void)
 		mds_clear_cpu_buffers();
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 5469d7a7c40f..53ba39ce010c 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -41,10 +41,6 @@ static inline int numa_cpu_node(int cpu)
 }
 #endif	/* CONFIG_NUMA */
 
-#ifdef CONFIG_X86_32
-# include <asm/numa_32.h>
-#endif
-
 #ifdef CONFIG_NUMA
 extern void numa_set_node(int cpu, int node);
 extern void numa_clear_node(int cpu);
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
deleted file mode 100644
index 9c8e9e85be77..000000000000
--- a/arch/x86/include/asm/numa_32.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_NUMA_32_H
-#define _ASM_X86_NUMA_32_H
-
-#ifdef CONFIG_HIGHMEM
-extern void set_highmem_pages_init(void);
-#else
-static inline void set_highmem_pages_init(void)
-{
-}
-#endif
-
-#endif /* _ASM_X86_NUMA_32_H */
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 46d7e06763c9..e0125afa53fb 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -45,7 +45,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/byteorder.h>
 
 /*
@@ -73,6 +73,6 @@ struct orc_entry {
 #endif
 } __packed;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index c9fe207916f4..9265f2fca99a 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -14,7 +14,7 @@
 #include <asm/page_32.h>
 #endif	/* CONFIG_X86_64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct page;
 
@@ -84,7 +84,7 @@ static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits)
 	return __canonical_address(vaddr, vaddr_bits) == vaddr;
 }
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index 580d71aca65a..0c623706cb7e 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -4,7 +4,7 @@
 
 #include <asm/page_32_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
 #ifdef CONFIG_DEBUG_VIRTUAL
@@ -26,6 +26,6 @@ static inline void copy_page(void *to, void *from)
 {
 	memcpy(to, from, PAGE_SIZE);
 }
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PAGE_32_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index faf9cc1c14bb..623f1e9f493e 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -11,8 +11,8 @@
  * a virtual address space of one gigabyte, which limits the
  * amount of physical memory you can use to about 950MB.
  *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G
+ * and CONFIG_HIGHMEM4G options in the kernel configuration.
  */
 #define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
 #define __PAGE_OFFSET		__PAGE_OFFSET_BASE
@@ -63,7 +63,7 @@
  */
 #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * This much address space is reserved for vmalloc() and iomap()
@@ -73,8 +73,7 @@ extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
 extern void find_low_pfn_range(void);
-extern void setup_bootmem_allocator(void);
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PAGE_32_DEFS_H */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d63576608ce7..015d23f3e01f 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -4,7 +4,7 @@
 
 #include <asm/page_64_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -55,13 +55,13 @@ static inline void clear_page(void *page)
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
 			   "=D" (page),
-			   "D" (page)
-			   : "cc", "memory", "rax", "rcx");
+			   "D" (page),
+			   "cc", "memory", "rax", "rcx");
 }
 
 void copy_page(void *to, void *from);
+KCFI_REFERENCE(copy_page);
 
-#ifdef CONFIG_X86_5LEVEL
 /*
  * User space process size.  This is the first address outside the user range.
  * There are a few constraints that determine this:
@@ -92,9 +92,8 @@ static __always_inline unsigned long task_size_max(void)
 
 	return ret;
 }
-#endif	/* CONFIG_X86_5LEVEL */
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 # define __HAVE_ARCH_GATE_AREA 1
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 06ef25411d62..7400dab373fe 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PAGE_64_DEFS_H
 #define _ASM_X86_PAGE_64_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/kaslr.h>
 #endif
 
@@ -41,25 +41,14 @@
 #define __PAGE_OFFSET_BASE_L5	_AC(0xff11000000000000, UL)
 #define __PAGE_OFFSET_BASE_L4	_AC(0xffff888000000000, UL)
 
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 #define __PAGE_OFFSET           page_offset_base
-#else
-#define __PAGE_OFFSET           __PAGE_OFFSET_BASE_L4
-#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
 /* See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. */
 
 #define __PHYSICAL_MASK_SHIFT	52
-
-#ifdef CONFIG_X86_5LEVEL
 #define __VIRTUAL_MASK_SHIFT	(pgtable_l5_enabled() ? 56 : 47)
-/* See task_size_max() in <asm/page_64.h> */
-#else
-#define __VIRTUAL_MASK_SHIFT	47
-#define task_size_max()		((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
-#endif
 
 #define TASK_SIZE_MAX		task_size_max()
 #define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 974688973cf6..018a8d906ca3 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -29,9 +29,7 @@
 #define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
 
 /* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
-				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
-				& ~(CONFIG_PHYSICAL_ALIGN - 1))
+#define LOAD_PHYSICAL_ADDR	__ALIGN_KERNEL_MASK(CONFIG_PHYSICAL_START, CONFIG_PHYSICAL_ALIGN - 1)
 
 #define __START_KERNEL		(__START_KERNEL_map + LOAD_PHYSICAL_ADDR)
 
@@ -43,7 +41,7 @@
 #define IOREMAP_MAX_ORDER       (PMD_SHIFT)
 #endif	/* CONFIG_X86_64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
 extern phys_addr_t physical_mask;
@@ -66,6 +64,6 @@ bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
 
 extern void initmem_init(void);
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif	/* _ASM_X86_PAGE_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 041aff51eb50..b5e59a7ba0d0 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -6,7 +6,7 @@
 
 #include <asm/paravirt_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct mm_struct;
 #endif
 
@@ -15,7 +15,7 @@ struct mm_struct;
 #include <asm/asm.h>
 #include <asm/nospec-branch.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
@@ -91,11 +91,6 @@ static inline void __flush_tlb_multi(const struct cpumask *cpumask,
 	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(mmu.exit_mmap, mm);
@@ -107,6 +102,16 @@ static inline void notify_page_enc_status_changed(unsigned long pfn,
 	PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc);
 }
 
+static __always_inline void arch_safe_halt(void)
+{
+	PVOP_VCALL0(irq.safe_halt);
+}
+
+static inline void halt(void)
+{
+	PVOP_VCALL0(irq.halt);
+}
+
 #ifdef CONFIG_PARAVIRT_XXL
 static inline void load_sp0(unsigned long sp0)
 {
@@ -170,36 +175,24 @@ static inline void __write_cr4(unsigned long x)
 	PVOP_VCALL1(cpu.write_cr4, x);
 }
 
-static __always_inline void arch_safe_halt(void)
-{
-	PVOP_VCALL0(irq.safe_halt);
-}
-
-static inline void halt(void)
-{
-	PVOP_VCALL0(irq.halt);
-}
-
-static inline u64 paravirt_read_msr(unsigned msr)
+static inline u64 paravirt_read_msr(u32 msr)
 {
 	return PVOP_CALL1(u64, cpu.read_msr, msr);
 }
 
-static inline void paravirt_write_msr(unsigned msr,
-				      unsigned low, unsigned high)
+static inline void paravirt_write_msr(u32 msr, u64 val)
 {
-	PVOP_VCALL3(cpu.write_msr, msr, low, high);
+	PVOP_VCALL2(cpu.write_msr, msr, val);
 }
 
-static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
+static inline int paravirt_read_msr_safe(u32 msr, u64 *val)
 {
-	return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
+	return PVOP_CALL2(int, cpu.read_msr_safe, msr, val);
 }
 
-static inline int paravirt_write_msr_safe(unsigned msr,
-					  unsigned low, unsigned high)
+static inline int paravirt_write_msr_safe(u32 msr, u64 val)
 {
-	return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
+	return PVOP_CALL2(int, cpu.write_msr_safe, msr, val);
 }
 
 #define rdmsr(msr, val1, val2)			\
@@ -209,55 +202,46 @@ do {						\
 	val2 = _l >> 32;			\
 } while (0)
 
-#define wrmsr(msr, val1, val2)			\
-do {						\
-	paravirt_write_msr(msr, val1, val2);	\
-} while (0)
+static __always_inline void wrmsr(u32 msr, u32 low, u32 high)
+{
+	paravirt_write_msr(msr, (u64)high << 32 | low);
+}
 
-#define rdmsrl(msr, val)			\
+#define rdmsrq(msr, val)			\
 do {						\
 	val = paravirt_read_msr(msr);		\
 } while (0)
 
-static inline void wrmsrl(unsigned msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
 {
-	wrmsr(msr, (u32)val, (u32)(val>>32));
+	paravirt_write_msr(msr, val);
 }
 
-#define wrmsr_safe(msr, a, b)	paravirt_write_msr_safe(msr, a, b)
+static inline int wrmsrq_safe(u32 msr, u64 val)
+{
+	return paravirt_write_msr_safe(msr, val);
+}
 
 /* rdmsr with exception handling */
 #define rdmsr_safe(msr, a, b)				\
 ({							\
-	int _err;					\
-	u64 _l = paravirt_read_msr_safe(msr, &_err);	\
+	u64 _l;						\
+	int _err = paravirt_read_msr_safe((msr), &_l);	\
 	(*a) = (u32)_l;					\
-	(*b) = _l >> 32;				\
+	(*b) = (u32)(_l >> 32);				\
 	_err;						\
 })
 
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+static __always_inline int rdmsrq_safe(u32 msr, u64 *p)
 {
-	int err;
-
-	*p = paravirt_read_msr_safe(msr, &err);
-	return err;
+	return paravirt_read_msr_safe(msr, p);
 }
 
-static inline unsigned long long paravirt_read_pmc(int counter)
+static __always_inline u64 rdpmc(int counter)
 {
 	return PVOP_CALL1(u64, cpu.read_pmc, counter);
 }
 
-#define rdpmc(counter, low, high)		\
-do {						\
-	u64 _l = paravirt_read_pmc(counter);	\
-	low = (u32)_l;				\
-	high = _l >> 32;			\
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
-
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
@@ -479,8 +463,6 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 	PVOP_VCALL2(mmu.set_p4d, p4dp, val);
 }
 
-#if CONFIG_PGTABLE_LEVELS >= 5
-
 static inline p4d_t __p4d(p4dval_t val)
 {
 	p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
@@ -512,8 +494,6 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
 		set_pgd(pgdp, native_make_pgd(0));			\
 } while (0)
 
-#endif  /* CONFIG_PGTABLE_LEVELS == 5 */
-
 static inline void p4d_clear(p4d_t *p4dp)
 {
 	set_p4d(p4dp, native_make_p4d(0));
@@ -720,7 +700,7 @@ static __always_inline unsigned long arch_local_irq_save(void)
 extern void default_banner(void);
 void native_pv_lock_init(void) __init;
 
-#else  /* __ASSEMBLY__ */
+#else  /* __ASSEMBLER__ */
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
@@ -740,18 +720,18 @@ void native_pv_lock_init(void) __init;
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #else  /* CONFIG_PARAVIRT */
 # define default_banner x86_init_noop
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static inline void native_pv_lock_init(void)
 {
 }
 #endif
 #endif /* !CONFIG_PARAVIRT */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef CONFIG_PARAVIRT_XXL
 static inline void paravirt_enter_mmap(struct mm_struct *mm)
 {
@@ -769,5 +749,5 @@ static inline void paravirt_set_cap(void)
 {
 }
 #endif
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f436..37a8627d8277 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -4,7 +4,7 @@
 
 #ifdef CONFIG_PARAVIRT
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 #include <asm/desc_defs.h>
@@ -91,15 +91,15 @@ struct pv_cpu_ops {
 		      unsigned int *ecx, unsigned int *edx);
 
 	/* Unsafe MSR operations.  These will warn or panic on failure. */
-	u64 (*read_msr)(unsigned int msr);
-	void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+	u64 (*read_msr)(u32 msr);
+	void (*write_msr)(u32 msr, u64 val);
 
 	/*
 	 * Safe MSR operations.
-	 * read sets err to 0 or -EIO.  write returns 0 or -EIO.
+	 * Returns 0 or -EIO.
 	 */
-	u64 (*read_msr_safe)(unsigned int msr, int *err);
-	int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
+	int (*read_msr_safe)(u32 msr, u64 *val);
+	int (*write_msr_safe)(u32 msr, u64 val);
 
 	u64 (*read_pmc)(int counter);
 
@@ -120,10 +120,9 @@ struct pv_irq_ops {
 	struct paravirt_callee_save save_fl;
 	struct paravirt_callee_save irq_disable;
 	struct paravirt_callee_save irq_enable;
-
+#endif
 	void (*safe_halt)(void);
 	void (*halt)(void);
-#endif
 } __no_randomize_layout;
 
 struct pv_mmu_ops {
@@ -134,8 +133,6 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
-	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
-
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
@@ -192,12 +189,10 @@ struct pv_mmu_ops {
 
 	void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval);
 
-#if CONFIG_PGTABLE_LEVELS >= 5
 	struct paravirt_callee_save p4d_val;
 	struct paravirt_callee_save make_p4d;
 
 	void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
-#endif	/* CONFIG_PGTABLE_LEVELS >= 5 */
 
 	struct pv_lazy_ops lazy_mode;
 
@@ -242,9 +237,17 @@ extern struct paravirt_patch_template pv_ops;
 
 #define paravirt_ptr(op)	[paravirt_opptr] "m" (pv_ops.op)
 
-int paravirt_disable_iospace(void);
-
-/* This generates an indirect call based on the operation type number. */
+/*
+ * This generates an indirect call based on the operation type number.
+ *
+ * Since alternatives run after enabling CET/IBT -- the latter setting/clearing
+ * capabilities and the former requiring all capabilities being finalized --
+ * these indirect calls are subject to IBT and the paravirt stubs should have
+ * ENDBR on.
+ *
+ * OTOH since this is effectively a __nocfi indirect call, the paravirt stubs
+ * don't need to bother with CFI prefixes.
+ */
 #define PARAVIRT_CALL					\
 	ANNOTATE_RETPOLINE_SAFE				\
 	"call *%[paravirt_opptr];"
@@ -519,7 +522,7 @@ unsigned long pv_native_read_cr2(void);
 
 #define paravirt_nop	((void *)nop_func)
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define ALT_NOT_XEN	ALT_NOT(X86_FEATURE_XENPV)
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999..b0d03b6c279b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -10,7 +10,7 @@
 # define __percpu_rel
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #ifdef CONFIG_SMP
 # define __percpu		%__percpu_seg:
@@ -20,20 +20,17 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var)  var
-#endif
-
 #else /* !__ASSEMBLY__: */
 
+#include <linux/args.h>
 #include <linux/build_bug.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
 #ifdef CONFIG_SMP
 
+#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
+
 #ifdef CONFIG_CC_HAS_NAMED_AS
 
 #ifdef __CHECKER__
@@ -41,28 +38,23 @@
 # define __seg_fs		__attribute__((address_space(__seg_fs)))
 #endif
 
-#ifdef CONFIG_X86_64
-# define __percpu_seg_override	__seg_gs
-#else
-# define __percpu_seg_override	__seg_fs
-#endif
-
-#define __percpu_prefix		""
+#define __percpu_prefix
+#define __percpu_seg_override	CONCATENATE(__seg_, __percpu_seg)
 
 #else /* !CONFIG_CC_HAS_NAMED_AS: */
 
+#define __percpu_prefix		__force_percpu_prefix
 #define __percpu_seg_override
-#define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
 
 #endif /* CONFIG_CC_HAS_NAMED_AS */
 
-#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset		this_cpu_read(this_cpu_off)
-
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
- *
+ */
+#define __my_cpu_offset		this_cpu_read(this_cpu_off)
+
+/*
  * arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit
  * kernel, because games are played with CONFIG_X86_64 there and
  * sizeof(this_cpu_off) becames 4.
@@ -73,46 +65,43 @@
 	unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off);	\
 									\
 	tcp_ptr__ += (__force unsigned long)(_ptr);			\
-	(typeof(*(_ptr)) __kernel __force *)tcp_ptr__;			\
+	(TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)tcp_ptr__;		\
 })
 #else
-#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; })
+#define arch_raw_cpu_ptr(_ptr)						\
+({									\
+	BUILD_BUG();							\
+	(TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)0;			\
+})
 #endif
 
 #define PER_CPU_VAR(var)	%__percpu_seg:(var)__percpu_rel
 
 #else /* !CONFIG_SMP: */
 
+#define __force_percpu_prefix
+#define __percpu_prefix
 #define __percpu_seg_override
-#define __percpu_prefix		""
-#define __force_percpu_prefix	""
 
 #define PER_CPU_VAR(var)	(var)__percpu_rel
 
 #endif /* CONFIG_SMP */
 
-#define __my_cpu_type(var)	typeof(var) __percpu_seg_override
-#define __my_cpu_ptr(ptr)	(__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr)
-#define __my_cpu_var(var)	(*__my_cpu_ptr(&(var)))
-#define __percpu_arg(x)		__percpu_prefix "%" #x
-#define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
-
-/*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(var) init_per_cpu_var(var)
+#if defined(CONFIG_USE_X86_SEG_SUPPORT) && defined(USE_TYPEOF_UNQUAL)
+# define __my_cpu_type(var)	typeof(var)
+# define __my_cpu_ptr(ptr)	(ptr)
+# define __my_cpu_var(var)	(var)
 
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var)  init_per_cpu__##var
+# define __percpu_qual		__percpu_seg_override
 #else
-# define init_per_cpu_var(var)  var
+# define __my_cpu_type(var)	typeof(var) __percpu_seg_override
+# define __my_cpu_ptr(ptr)	(__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr)
+# define __my_cpu_var(var)	(*__my_cpu_ptr(&(var)))
 #endif
 
+#define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
+#define __percpu_arg(x)		__percpu_prefix "%" #x
+
 /*
  * For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though).
@@ -128,15 +117,10 @@
 #define __pcpu_cast_4(val)	((u32)(((unsigned long) val) & 0xffffffff))
 #define __pcpu_cast_8(val)	((u64)(val))
 
-#define __pcpu_op1_1(op, dst)	op "b " dst
-#define __pcpu_op1_2(op, dst)	op "w " dst
-#define __pcpu_op1_4(op, dst)	op "l " dst
-#define __pcpu_op1_8(op, dst)	op "q " dst
-
-#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
-#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
-#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
-#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
+#define __pcpu_op_1(op)		op "b "
+#define __pcpu_op_2(op)		op "w "
+#define __pcpu_op_4(op)		op "l "
+#define __pcpu_op_8(op)		op "q "
 
 #define __pcpu_reg_1(mod, x)	mod "q" (x)
 #define __pcpu_reg_2(mod, x)	mod "r" (x)
@@ -168,7 +152,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+	asm qual (__pcpu_op_##size("mov")				\
+		  __percpu_arg([var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "m" (__my_cpu_var(_var)));				\
 									\
@@ -180,11 +165,12 @@ do {									\
 	__pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val);	\
 									\
 	if (0) {		                                        \
-		typeof(_var) pto_tmp__;					\
+		TYPEOF_UNQUAL(_var) pto_tmp__;				\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+	asm qual (__pcpu_op_##size("mov") "%[val], "			\
+		  __percpu_arg([var])					\
 	    : [var] "=m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -201,7 +187,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+	asm(__pcpu_op_##size("mov")					\
+	    __force_percpu_arg(a[var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "i" (&(_var)));					\
 									\
@@ -210,7 +197,7 @@ do {									\
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
-	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size(op) __percpu_arg([var])		\
 	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
@@ -219,11 +206,11 @@ do {									\
 	__pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val);	\
 									\
 	if (0) {		                                        \
-		typeof(_var) pto_tmp__;					\
+		TYPEOF_UNQUAL(_var) pto_tmp__;				\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
+	asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var])	\
 	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -240,7 +227,7 @@ do {									\
 			 (val) == (typeof(val))-1)) ? (int)(val) : 0;	\
 									\
 	if (0) {							\
-		typeof(var) pao_tmp__;					\
+		TYPEOF_UNQUAL(var) pao_tmp__;				\
 		pao_tmp__ = (val);					\
 		(void)pao_tmp__;					\
 	}								\
@@ -259,8 +246,8 @@ do {									\
 ({									\
 	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
 									\
-	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
-				     __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("xadd") "%[tmp], "			\
+		  __percpu_arg([var])					\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
@@ -273,7 +260,7 @@ do {									\
  */
 #define raw_percpu_xchg_op(_var, _nval)					\
 ({									\
-	typeof(_var) pxo_old__ = raw_cpu_read(_var);			\
+	TYPEOF_UNQUAL(_var) pxo_old__ = raw_cpu_read(_var);		\
 									\
 	raw_cpu_write(_var, _nval);					\
 									\
@@ -287,7 +274,7 @@ do {									\
  */
 #define this_percpu_xchg_op(_var, _nval)				\
 ({									\
-	typeof(_var) pxo_old__ = this_cpu_read(_var);			\
+	TYPEOF_UNQUAL(_var) pxo_old__ = this_cpu_read(_var);		\
 									\
 	do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval));	\
 									\
@@ -303,8 +290,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
@@ -320,8 +307,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = *pco_oval__;			\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\
@@ -348,15 +335,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -378,17 +364,16 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
 									\
@@ -419,15 +404,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -449,19 +433,19 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 
@@ -582,7 +566,7 @@ do {									\
  * it is accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across CPUs.  The current users include
- * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * current_task and cpu_current_top_of_stack, both of which are
  * actually per-thread variables implemented as per-CPU variables and
  * thus stable for the duration of the respective task.
  */
@@ -617,9 +601,9 @@ do {									\
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifdef CONFIG_SMP
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 0ba8d20f2d1d..70d1d94aca7e 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -141,6 +141,12 @@
 #define PEBS_DATACFG_XMMS	BIT_ULL(2)
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
 #define PEBS_DATACFG_LBR_SHIFT	24
+#define PEBS_DATACFG_CNTR	BIT_ULL(4)
+#define PEBS_DATACFG_CNTR_SHIFT	32
+#define PEBS_DATACFG_CNTR_MASK	GENMASK_ULL(15, 0)
+#define PEBS_DATACFG_FIX_SHIFT	48
+#define PEBS_DATACFG_FIX_MASK	GENMASK_ULL(7, 0)
+#define PEBS_DATACFG_METRICS	BIT_ULL(5)
 
 /* Steal the highest bit of pebs_data_cfg for SW usage */
 #define PEBS_UPDATE_DS_SW	BIT_ULL(63)
@@ -189,6 +195,7 @@ union cpuid10_edx {
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
+#define ARCH_PERFMON_ACR_LEAF			0x2
 
 union cpuid35_eax {
 	struct {
@@ -482,6 +489,15 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
+struct pebs_cntr_header {
+	u32 cntr;
+	u32 fixed;
+	u32 metrics;
+	u32 reserved;
+};
+
+#define INTEL_CNTR_METRICS		0x3
+
 /*
  * AMD Extended Performance Monitoring and Debug cpuid feature detection
  */
@@ -509,6 +525,8 @@ struct pebs_xmm {
 #define IBS_CAPS_FETCHCTLEXTD		(1U<<9)
 #define IBS_CAPS_OPDATA4		(1U<<10)
 #define IBS_CAPS_ZEN4			(1U<<11)
+#define IBS_CAPS_OPLDLAT		(1U<<12)
+#define IBS_CAPS_OPDTLBPGSIZE		(1U<<19)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
@@ -534,8 +552,11 @@ struct pebs_xmm {
  * The lower 7 bits of the current count are random bits
  * preloaded by hardware and ignored in software
  */
+#define IBS_OP_LDLAT_EN		(1ULL<<63)
+#define IBS_OP_LDLAT_THRSH	(0xFULL<<59)
 #define IBS_OP_CUR_CNT		(0xFFF80ULL<<32)
 #define IBS_OP_CUR_CNT_RAND	(0x0007FULL<<32)
+#define IBS_OP_CUR_CNT_EXT_MASK	(0x7FULL<<52)
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd4841231bb9..c88691b15f3c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+#include <asm/cpufeature.h>
+
 #define __HAVE_ARCH_PTE_ALLOC_ONE
 #define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
@@ -30,20 +32,16 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
 /*
- * Flags to use when allocating a user page table page.
- */
-extern gfp_t __userpte_alloc_gfp;
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-/*
- * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
- * both 8k in size and 8k-aligned.  That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned.  That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
  */
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_PTI))
+		return 1;
+	return 0;
+}
 
 /*
  * Allocate and free page tables.
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 7f6ccff0ba72..54690bd4ddbe 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 typedef unsigned long	pteval_t;
@@ -16,24 +16,22 @@ typedef union {
 	pteval_t pte;
 	pteval_t pte_low;
 } pte_t;
-#endif	/* !__ASSEMBLY__ */
-
-#define SHARED_KERNEL_PMD	0
+#endif	/* !__ASSEMBLER__ */
 
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
- * traditional i386 two-level paging structure:
+ * Traditional i386 two-level paging structure:
  */
 
 #define PGDIR_SHIFT	22
 #define PTRS_PER_PGD	1024
 
-
 /*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
+ * The i386 is two-level, so we don't really have any
+ * PMD directory physically:
  */
+#define PTRS_PER_PMD	1
 
 #define PTRS_PER_PTE	1024
 
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 80911349519e..580b09bf6a45 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 typedef u64	pteval_t;
@@ -25,11 +25,9 @@ typedef union {
 	};
 	pmdval_t pmd;
 } pmd_t;
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
-
-#define ARCH_PAGE_TABLE_SYNC_MASK	(SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
+#define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
index a0c1525f1b6f..e12e52ae8083 100644
--- a/arch/x86/include/asm/pgtable-invert.h
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_PGTABLE_INVERT_H
 #define _ASM_PGTABLE_INVERT_H 1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * A clear pte value is special, and doesn't get inverted.
@@ -36,6 +36,6 @@ static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
 	return val;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 593f10aabd45..5ddba366d3b4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -15,7 +15,7 @@
 		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
 	 : (prot))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/spinlock.h>
 #include <asm/x86_init.h>
 #include <asm/pkru.h>
@@ -292,13 +292,6 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
 	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
-#define p4d_leaf p4d_leaf
-static inline bool p4d_leaf(p4d_t p4d)
-{
-	/* No 512 GiB pages yet */
-	return 0;
-}
-
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 #define pmd_leaf pmd_leaf
@@ -973,7 +966,7 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 }
 #endif  /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 
 #ifdef CONFIG_X86_32
@@ -982,7 +975,7 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 # include <asm/pgtable_64.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
 #include <linux/log2.h>
@@ -1233,12 +1226,12 @@ static inline int pgd_none(pgd_t pgd)
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
 #define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern int direct_gbpages;
 void init_mem_mapping(void);
@@ -1472,9 +1465,6 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
 }
 
-#define pgd_leaf	pgd_leaf
-static inline bool pgd_leaf(pgd_t pgd) { return false; }
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages
@@ -1812,6 +1802,6 @@ bool arch_is_platform_page(u64 paddr);
 	WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
 	set_pgd(pgdp, pgd); \
 })
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 7d4ad8907297..b612cc57a4d3 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -13,7 +13,7 @@
  * This file contains the functions and defines necessary to modify and use
  * the i386 page table tree.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/processor.h>
 #include <linux/threads.h>
 #include <asm/paravirt.h>
@@ -45,7 +45,7 @@ do {						\
 	flush_tlb_one_kernel((vaddr));		\
 } while (0)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * This is used to calculate the .brk reservation for initial pagetables.
diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h
index b6355416a15a..921148b42967 100644
--- a/arch/x86/include/asm/pgtable_32_areas.h
+++ b/arch/x86/include/asm/pgtable_32_areas.h
@@ -13,7 +13,7 @@
  */
 #define VMALLOC_OFFSET	(8 * 1024 * 1024)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern bool __vmalloc_start_set; /* set once high_memory is set */
 #endif
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index d1426b64c1b9..f06e5d6a2747 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -5,7 +5,7 @@
 #include <linux/const.h>
 #include <asm/pgtable_64_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * This file contains the functions and defines necessary to modify and use
@@ -41,11 +41,9 @@ static inline void sync_initial_page_table(void) { }
 	pr_err("%s:%d: bad pud %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pud_val(e))
 
-#if CONFIG_PGTABLE_LEVELS >= 5
 #define p4d_ERROR(e)					\
 	pr_err("%s:%d: bad p4d %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), p4d_val(e))
-#endif
 
 #define pgd_ERROR(e)					\
 	pr_err("%s:%d: bad pgd %p(%016lx)\n",		\
@@ -270,7 +268,7 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 
 #include <asm/pgtable-invert.h>
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define l4_index(x)	(((x) >> 39) & 511)
 #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
@@ -291,5 +289,5 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
 	i = i + 1 ;					\
 	.endr
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index ec68f8369bdc..4604f924d8b8 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -4,7 +4,7 @@
 
 #include <asm/sparsemem.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <asm/kaslr.h>
 
@@ -23,7 +23,6 @@ typedef struct { pmdval_t pmd; } pmd_t;
 
 extern unsigned int __pgtable_l5_enabled;
 
-#ifdef CONFIG_X86_5LEVEL
 #ifdef USE_EARLY_PGTABLE_L5
 /*
  * cpu_feature_enabled() is not available in early boot code.
@@ -37,18 +36,10 @@ static inline bool pgtable_l5_enabled(void)
 #define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
 #endif /* USE_EARLY_PGTABLE_L5 */
 
-#else
-#define pgtable_l5_enabled() 0
-#endif /* CONFIG_X86_5LEVEL */
-
 extern unsigned int pgdir_shift;
 extern unsigned int ptrs_per_p4d;
 
-#endif	/* !__ASSEMBLY__ */
-
-#define SHARED_KERNEL_PMD	0
-
-#ifdef CONFIG_X86_5LEVEL
+#endif	/* !__ASSEMBLER__ */
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
@@ -67,17 +58,6 @@ extern unsigned int ptrs_per_p4d;
 
 #define MAX_POSSIBLE_PHYSMEM_BITS	52
 
-#else /* CONFIG_X86_5LEVEL */
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT		39
-#define PTRS_PER_PGD		512
-#define MAX_PTRS_PER_P4D	1
-
-#endif /* CONFIG_X86_5LEVEL */
-
 /*
  * 3rd level page
  */
@@ -130,15 +110,9 @@ extern unsigned int ptrs_per_p4d;
 #define __VMEMMAP_BASE_L4	0xffffea0000000000UL
 #define __VMEMMAP_BASE_L5	0xffd4000000000000UL
 
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 # define VMALLOC_START		vmalloc_base
 # define VMALLOC_SIZE_TB	(pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
 # define VMEMMAP_START		vmemmap_base
-#else
-# define VMALLOC_START		__VMALLOC_BASE_L4
-# define VMALLOC_SIZE_TB	VMALLOC_SIZE_TB_L4
-# define VMEMMAP_START		__VMEMMAP_BASE_L4
-#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
 #ifdef CONFIG_RANDOMIZE_MEMORY
 # define DIRECT_MAP_PHYSMEM_END	direct_map_physmem_end
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c..b74ec5c3643b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -33,6 +33,7 @@
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
+#define _PAGE_BIT_KERNEL_4K	_PAGE_BIT_SOFTW3 /* page must not be converted to large */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
@@ -64,6 +65,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_KERNEL_4K	(_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K)
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 #define _PAGE_PKEY_BIT0	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
 #define _PAGE_PKEY_BIT1	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
@@ -164,7 +166,7 @@
  * to have the WB mode at index 0 (all bits clear). This is the default
  * right now and likely would break too much if changed.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 enum page_cache_mode {
 	_PAGE_CACHE_MODE_WB       = 0,
 	_PAGE_CACHE_MODE_WC       = 1,
@@ -177,7 +179,7 @@ enum page_cache_mode {
 };
 #endif
 
-#define _PAGE_CC		(_AT(pteval_t, cc_mask))
+#define _PAGE_CC		(_AT(pteval_t, cc_get_mask()))
 #define _PAGE_ENC		(_AT(pteval_t, sme_me_mask))
 
 #define _PAGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
@@ -239,7 +241,7 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_IO_NOCACHE	__PAGE_KERNEL_NOCACHE
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __PAGE_KERNEL_ENC	(__PAGE_KERNEL    | _ENC)
 #define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _ENC)
@@ -262,7 +264,7 @@ enum page_cache_mode {
 #define PAGE_KERNEL_IO		__pgprot_mask(__PAGE_KERNEL_IO)
 #define PAGE_KERNEL_IO_NOCACHE	__pgprot_mask(__PAGE_KERNEL_IO_NOCACHE)
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 /*
  * early identity mapping  pte attrib macros.
@@ -281,7 +283,7 @@ enum page_cache_mode {
 # include <asm/pgtable_64_types.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -580,6 +582,6 @@ extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
 					  unsigned long page_flags);
 extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 					    unsigned long numpages);
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 919909d8cb77..578441db09f0 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -4,10 +4,11 @@
 
 #include <asm/rmwcc.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 #include <linux/static_call_types.h>
 
+DECLARE_PER_CPU_CACHE_HOT(int, __preempt_count);
+
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -23,18 +24,18 @@
  */
 static __always_inline int preempt_count(void)
 {
-	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
 {
 	int old, new;
 
-	old = raw_cpu_read_4(pcpu_hot.preempt_count);
+	old = raw_cpu_read_4(__preempt_count);
 	do {
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new));
+	} while (!raw_cpu_try_cmpxchg_4(__preempt_count, &old, new));
 }
 
 /*
@@ -43,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
 #define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \
+	per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
 } while (0)
 
 /*
@@ -57,17 +58,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -76,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, val);
+	raw_cpu_add_4(__preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
+	raw_cpu_add_4(__preempt_count, -val);
 }
 
 /*
@@ -91,7 +92,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
+	return GEN_UNARY_RMWcc("decl", __my_cpu_var(__preempt_count), e,
 			       __percpu_arg([var]));
 }
 
@@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPTION
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90..bde58f6510ac 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -16,7 +16,7 @@ struct vm86;
 #include <uapi/asm/sigcontext.h>
 #include <asm/current.h>
 #include <asm/cpufeatures.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
@@ -60,18 +60,13 @@ struct vm86;
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
-enum tlb_infos {
-	ENTRIES,
-	NR_INFO
-};
-
-extern u16 __read_mostly tlb_lli_4k[NR_INFO];
-extern u16 __read_mostly tlb_lli_2m[NR_INFO];
-extern u16 __read_mostly tlb_lli_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4k[NR_INFO];
-extern u16 __read_mostly tlb_lld_2m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_1g[NR_INFO];
+extern u16 __read_mostly tlb_lli_4k;
+extern u16 __read_mostly tlb_lli_2m;
+extern u16 __read_mostly tlb_lli_4m;
+extern u16 __read_mostly tlb_lld_4k;
+extern u16 __read_mostly tlb_lld_2m;
+extern u16 __read_mostly tlb_lld_4m;
+extern u16 __read_mostly tlb_lld_1g;
 
 /*
  * CPU type and hardware bug flags. Kept separately for each CPU.
@@ -234,7 +229,7 @@ static inline unsigned long long l1tf_pfn_limit(void)
 void init_cpu_devs(void);
 void get_cpu_vendor(struct cpuinfo_x86 *c);
 extern void early_cpu_init(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void identify_secondary_cpu(unsigned int cpu);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 
@@ -420,37 +415,33 @@ struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
 } __aligned(IRQ_STACK_SIZE);
 
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
 #ifdef CONFIG_X86_64
-struct fixed_percpu_data {
-	/*
-	 * GCC hardcodes the stack canary as %gs:40.  Since the
-	 * irq_stack is the object at %gs:0, we reserve the bottom
-	 * 48 bytes of the irq stack for the canary.
-	 *
-	 * Once we are willing to require -mstack-protector-guard-symbol=
-	 * support for x86_64 stackprotector, we can get rid of this.
-	 */
-	char		gs_base[40];
-	unsigned long	stack_canary;
-};
+DECLARE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
+#else
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+#endif
 
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(const unsigned long __percpu_seg_override,
+			  const_cpu_current_top_of_stack);
 
+#ifdef CONFIG_X86_64
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+	return per_cpu_offset(cpu);
+#else
+	return 0;
+#endif
 }
 
 extern asmlinkage void entry_SYSCALL32_ignore(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
 void current_save_fsgs(void);
-#else	/* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif	/* !X86_64 */
+#endif	/* X86_64 */
 
 struct perf_event;
 
@@ -523,15 +514,14 @@ struct thread_struct {
 
 	struct thread_shstk	shstk;
 #endif
-
-	/* Floating point and extended processor state */
-	struct fpu		fpu;
-	/*
-	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
-	 * the end.
-	 */
 };
 
+#ifdef CONFIG_X86_DEBUG_FPU
+extern struct fpu *x86_task_fpu(struct task_struct *task);
+#else
+# define x86_task_fpu(task)	((struct fpu *)((void *)(task) + sizeof(*(task))))
+#endif
+
 extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size);
 
 static inline void arch_thread_struct_whitelist(unsigned long *offset,
@@ -561,9 +551,9 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  entry trampoline.
 	 */
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+		return this_cpu_read_const(const_cpu_current_top_of_stack);
 
-	return this_cpu_read_stable(pcpu_hot.top_of_stack);
+	return this_cpu_read_stable(cpu_current_top_of_stack);
 }
 
 static __always_inline bool on_thread_stack(void)
@@ -668,8 +658,6 @@ static __always_inline void prefetchw(const void *x)
 	.sysenter_cs		= __KERNEL_CS,				  \
 }
 
-#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
-
 #else
 extern unsigned long __top_init_kernel_stack[];
 
@@ -677,8 +665,6 @@ extern unsigned long __top_init_kernel_stack[];
 	.sp	= (unsigned long)&__top_init_kernel_stack,		\
 }
 
-extern unsigned long KSTK_ESP(struct task_struct *task);
-
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -692,6 +678,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 #define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
+#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 /* Get/set a process' ability to use the timestamp counter instruction */
 #define GET_TSC_CTL(adr)	get_tsc_mode((adr))
@@ -746,6 +733,7 @@ void store_cpu_caps(struct cpuinfo_x86 *info);
 
 enum l1tf_mitigations {
 	L1TF_MITIGATION_OFF,
+	L1TF_MITIGATION_AUTO,
 	L1TF_MITIGATION_FLUSH_NOWARN,
 	L1TF_MITIGATION_FLUSH,
 	L1TF_MITIGATION_FLUSH_NOSMT,
@@ -757,6 +745,7 @@ extern enum l1tf_mitigations l1tf_mitigation;
 
 enum mds_mitigations {
 	MDS_MITIGATION_OFF,
+	MDS_MITIGATION_AUTO,
 	MDS_MITIGATION_FULL,
 	MDS_MITIGATION_VMWERV,
 };
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 365798cb4408..5d0dbab85264 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -8,7 +8,7 @@
 
 #ifndef _ASM_X86_PROM_H
 #define _ASM_X86_PROM_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/of.h>
 #include <linux/types.h>
@@ -33,5 +33,5 @@ static inline void x86_flattree_get_config(void) { }
 
 extern char cmd_line[COMMAND_LINE_SIZE];
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 484f4f0131a5..05224a695872 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -15,7 +15,6 @@ void entry_SYSCALL_64(void);
 void entry_SYSCALL_64_safe_stack(void);
 void entry_SYSRETQ_unsafe_stack(void);
 void entry_SYSRETQ_end(void);
-long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
 #ifdef CONFIG_X86_32
@@ -41,6 +40,6 @@ void x86_configure_nx(void);
 
 extern int reboot_force;
 
-long do_arch_prctl_common(int option, unsigned long arg2);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index ab167c96b9ab..88d0a1ab1f77 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PTI_H
 #define _ASM_X86_PTI_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
@@ -11,5 +11,5 @@ extern void pti_finalize(void);
 static inline void pti_check_boottime_disable(void) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5a83fbd9bc0b..50f75467f73d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -6,7 +6,7 @@
 #include <asm/page_types.h>
 #include <uapi/asm/ptrace.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef __i386__
 
 struct pt_regs {
@@ -469,5 +469,5 @@ extern int do_set_thread_area(struct task_struct *p, int idx,
 # define do_set_thread_area_64(p, s, t)	(0)
 #endif
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
index 5528e9325049..2fee5e9f1ccc 100644
--- a/arch/x86/include/asm/purgatory.h
+++ b/arch/x86/include/asm/purgatory.h
@@ -2,10 +2,10 @@
 #ifndef _ASM_X86_PURGATORY_H
 #define _ASM_X86_PURGATORY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/purgatory.h>
 
 extern void purgatory(void);
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 1436226efe3e..b9fece5fc96d 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PVCLOCK_ABI_H
 #define _ASM_X86_PVCLOCK_ABI_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * These structs MUST NOT be changed.
@@ -44,5 +44,5 @@ struct pvclock_wall_clock {
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
 /* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 87e5482acd0d..f607081a022a 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -9,7 +9,7 @@
 #define TH_FLAGS_SME_ACTIVE_BIT		0
 #define TH_FLAGS_SME_ACTIVE		BIT(TH_FLAGS_SME_ACTIVE_BIT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <asm/io.h>
@@ -95,6 +95,6 @@ void reserve_real_mode(void);
 void load_trampoline_pgtable(void);
 void init_real_mode(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
deleted file mode 100644
index e9187ddd3d1f..000000000000
--- a/arch/x86/include/asm/required-features.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#define _ASM_X86_REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CMPXCHG64
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-# define NEED_3DNOW	0
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_MATOM
-# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
-#else
-# define NEED_MOVBE	0
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
-/* Paravirtualized systems may not have PSE or PGE available */
-#define NEED_PSE	0
-#define NEED_PGE	0
-#else
-#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
-#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
-#endif
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	(NEED_MOVBE)
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-#define REQUIRED_MASK8	0
-#define REQUIRED_MASK9	0
-#define REQUIRED_MASK10	0
-#define REQUIRED_MASK11	0
-#define REQUIRED_MASK12	0
-#define REQUIRED_MASK13	0
-#define REQUIRED_MASK14	0
-#define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
-#define REQUIRED_MASK17	0
-#define REQUIRED_MASK18	0
-#define REQUIRED_MASK19	0
-#define REQUIRED_MASK20	0
-#define REQUIRED_MASK21	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 8b1b6ce1e51b..feb93b50e990 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -4,8 +4,12 @@
 
 #ifdef CONFIG_X86_CPU_RESCTRL
 
-#include <linux/sched.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/resctrl_types.h>
+#include <linux/sched.h>
+
+#include <asm/msr.h>
 
 /*
  * This value can never be a valid CLOSID, and is used when mapping a
@@ -40,6 +44,7 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
+extern unsigned int rdt_mon_features;
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
@@ -79,6 +84,21 @@ static inline void resctrl_arch_disable_mon(void)
 	static_branch_dec_cpuslocked(&rdt_enable_key);
 }
 
+static inline bool resctrl_arch_is_llc_occupancy_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_total_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_local_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
@@ -96,8 +116,8 @@ static inline void resctrl_arch_disable_mon(void)
 static inline void __resctrl_sched_in(struct task_struct *tsk)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
-	u32 closid = state->default_closid;
-	u32 rmid = state->default_rmid;
+	u32 closid = READ_ONCE(state->default_closid);
+	u32 rmid = READ_ONCE(state->default_rmid);
 	u32 tmp;
 
 	/*
@@ -132,6 +152,13 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid,
+							    u32 rmid)
+{
+	WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid);
+	WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid);
+}
+
 static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
 						u32 closid, u32 rmid)
 {
@@ -150,7 +177,7 @@ static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
 	return READ_ONCE(tsk->rmid) == rmid;
 }
 
-static inline void resctrl_sched_in(struct task_struct *tsk)
+static inline void resctrl_arch_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
@@ -169,20 +196,22 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
 
 /* x86 can always read an rmid, nothing needs allocating */
 struct rdt_resource;
-static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r,
+					       enum resctrl_event_id evtid)
 {
 	might_sleep();
 	return NULL;
-};
+}
 
-static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
-					     void *ctx) { };
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r,
+					     enum resctrl_event_id evtid,
+					     void *ctx) { }
 
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
 
-static inline void resctrl_sched_in(struct task_struct *tsk) {}
+static inline void resctrl_arch_sched_in(struct task_struct *tsk) {}
 static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
 
 #endif /* CONFIG_X86_CPU_RESCTRL */
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 363266cbcada..3821ee3fae35 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -29,7 +29,7 @@ cc_label:	c = true;						\
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c;								\
-	asm volatile (fullop CC_SET(cc)					\
+	asm_inline volatile (fullop CC_SET(cc)				\
 			: [var] "+m" (_var), CC_OUT(cc) (c)		\
 			: __VA_ARGS__ : clobbers);			\
 	c;								\
diff --git a/arch/x86/include/asm/rqspinlock.h b/arch/x86/include/asm/rqspinlock.h
new file mode 100644
index 000000000000..24a885449ee6
--- /dev/null
+++ b/arch/x86/include/asm/rqspinlock.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_RQSPINLOCK_H
+#define _ASM_X86_RQSPINLOCK_H
+
+#include <asm/paravirt.h>
+
+#ifdef CONFIG_PARAVIRT
+DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
+#define resilient_virt_spin_lock_enabled resilient_virt_spin_lock_enabled
+static __always_inline bool resilient_virt_spin_lock_enabled(void)
+{
+       return static_branch_likely(&virt_spin_lock_key);
+}
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+typedef struct qspinlock rqspinlock_t;
+#else
+typedef struct rqspinlock rqspinlock_t;
+#endif
+extern int resilient_tas_spin_lock(rqspinlock_t *lock);
+
+#define resilient_virt_spin_lock resilient_virt_spin_lock
+static inline int resilient_virt_spin_lock(rqspinlock_t *lock)
+{
+	return resilient_tas_spin_lock(lock);
+}
+
+#endif /* CONFIG_PARAVIRT */
+
+#include <asm-generic/rqspinlock.h>
+
+#endif /* _ASM_X86_RQSPINLOCK_H */
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index 6652ebddfd02..8d983cfd06ea 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -2,6 +2,18 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef __ASSEMBLY__
+
+.macro RUNTIME_CONST_PTR sym reg
+	movq	$0x0123456789abcdef, %\reg
+	1:
+	.pushsection runtime_ptr_\sym, "a"
+	.long	1b - 8 - .
+	.popsection
+.endm
+
+#else /* __ASSEMBLY__ */
+
 #define runtime_const_ptr(sym) ({				\
 	typeof(sym) __ret;					\
 	asm_inline("mov %1,%0\n1:\n"				\
@@ -58,4 +70,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 	}
 }
 
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 9d6411c65920..77d8f49b92bd 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -233,7 +233,7 @@
 #define VDSO_CPUNODE_BITS		12
 #define VDSO_CPUNODE_MASK		0xfff
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* Helper functions to store/load CPU and node numbers */
 
@@ -265,7 +265,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
 		*node = (p >> VDSO_CPUNODE_BITS);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifdef __KERNEL__
 
@@ -286,7 +286,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
  */
 #define XEN_EARLY_IDT_HANDLER_SIZE (8 + ENDBR_INSN_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
@@ -350,7 +350,7 @@ static inline void __loadsegment_fs(unsigned short value)
 #define savesegment(seg, value)				\
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index cc62ef70ccc0..8d9f1c9aaa4c 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_SET_MEMORY_H
 #define _ASM_X86_SET_MEMORY_H
 
-#include <linux/mm.h>
 #include <asm/page.h>
 #include <asm-generic/set_memory.h>
 
@@ -38,7 +37,6 @@ int set_memory_rox(unsigned long addr, int numpages);
  * The caller is required to take care of these.
  */
 
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot);
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
 int _set_memory_wt(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 85f4fde3515c..6324f4c6c545 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -27,7 +27,7 @@
 #define OLD_CL_ADDRESS		0x020	/* Relative to real mode data */
 #define NEW_CL_POINTER		0x228	/* Relative to real mode data */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cache.h>
 
 #include <asm/bootparam.h>
@@ -46,11 +46,13 @@ void setup_bios_corruption_check(void);
 void early_platform_quirks(void);
 
 extern unsigned long saved_video_mode;
+extern unsigned long acpi_realmode_flags;
 
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
 extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp);
 extern void startup_64_setup_gdt_idt(void);
+extern void startup_64_load_idt(void *vc_handler);
 extern void early_setup_idt(void);
 extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
 
@@ -141,7 +143,7 @@ extern bool builtin_cmdline_added __ro_after_init;
 #define builtin_cmdline_added 0
 #endif
 
-#else  /* __ASSEMBLY */
+#else  /* __ASSEMBLER__ */
 
 .macro __RESERVE_BRK name, size
 	.pushsection .bss..brk, "aw"
@@ -153,6 +155,6 @@ SYM_DATA_END(__brk_\name)
 
 #define RESERVE_BRK(name, size) __RESERVE_BRK name, size
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SETUP_H */
diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h
index 77c51111a893..7bb16f843c93 100644
--- a/arch/x86/include/asm/setup_data.h
+++ b/arch/x86/include/asm/setup_data.h
@@ -4,7 +4,7 @@
 
 #include <uapi/asm/setup_data.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct pci_setup_rom {
 	struct setup_data data;
@@ -27,6 +27,6 @@ struct efi_setup_data {
 	u64 reserved[8];
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index dcbccdb280f9..0020d77a0800 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -116,7 +116,7 @@ enum psc_op {
 #define GHCB_MSR_VMPL_REQ		0x016
 #define GHCB_MSR_VMPL_REQ_LEVEL(v)			\
 	/* GHCBData[39:32] */				\
-	(((u64)(v) & GENMASK_ULL(7, 0) << 32) |		\
+	((((u64)(v) & GENMASK_ULL(7, 0)) << 32) |	\
 	/* GHCBDdata[11:0] */				\
 	GHCB_MSR_VMPL_REQ)
 
@@ -212,8 +212,16 @@ struct snp_psc_desc {
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
 /*
- * Error codes related to GHCB input that can be communicated back to the guest
- * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2.
+ * GHCB-defined return codes that are communicated back to the guest via
+ * SW_EXITINFO1.
+ */
+#define GHCB_HV_RESP_NO_ACTION		0
+#define GHCB_HV_RESP_ISSUE_EXCEPTION	1
+#define GHCB_HV_RESP_MALFORMED_INPUT	2
+
+/*
+ * GHCB-defined sub-error codes for malformed input (see above) that are
+ * communicated back to the guest via SW_EXITINFO2[31:0].
  */
 #define GHCB_ERR_NOT_REGISTERED		1
 #define GHCB_ERR_INVALID_USAGE		2
diff --git a/arch/x86/include/asm/sev-internal.h b/arch/x86/include/asm/sev-internal.h
new file mode 100644
index 000000000000..3dfd306d1c9e
--- /dev/null
+++ b/arch/x86/include/asm/sev-internal.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define DR7_RESET_VALUE        0x400
+
+extern struct ghcb boot_ghcb_page;
+extern u64 sev_hv_features;
+extern u64 sev_secrets_pa;
+
+/* #VC handler runtime per-CPU data */
+struct sev_es_runtime_data {
+	struct ghcb ghcb_page;
+
+	/*
+	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
+	 * It is needed when an NMI happens while the #VC handler uses the real
+	 * GHCB, and the NMI handler itself is causing another #VC exception. In
+	 * that case the GHCB content of the first handler needs to be backed up
+	 * and restored.
+	 */
+	struct ghcb backup_ghcb;
+
+	/*
+	 * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
+	 * There is no need for it to be atomic, because nothing is written to
+	 * the GHCB between the read and the write of ghcb_active. So it is safe
+	 * to use it when a nested #VC exception happens before the write.
+	 *
+	 * This is necessary for example in the #VC->NMI->#VC case when the NMI
+	 * happens while the first #VC handler uses the GHCB. When the NMI code
+	 * raises a second #VC handler it might overwrite the contents of the
+	 * GHCB written by the first handler. To avoid this the content of the
+	 * GHCB is saved and restored when the GHCB is detected to be in use
+	 * already.
+	 */
+	bool ghcb_active;
+	bool backup_ghcb_active;
+
+	/*
+	 * Cached DR7 value - write it on DR7 writes and return it on reads.
+	 * That value will never make it to the real hardware DR7 as debugging
+	 * is currently unsupported in SEV-ES guests.
+	 */
+	unsigned long dr7;
+};
+
+struct ghcb_state {
+	struct ghcb *ghcb;
+};
+
+extern struct svsm_ca boot_svsm_ca_page;
+
+struct ghcb *__sev_get_ghcb(struct ghcb_state *state);
+void __sev_put_ghcb(struct ghcb_state *state);
+
+DECLARE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DECLARE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+
+void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+			   unsigned long npages, enum psc_op op);
+
+DECLARE_PER_CPU(struct svsm_ca *, svsm_caa);
+DECLARE_PER_CPU(u64, svsm_caa_pa);
+
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
+
+static __always_inline struct svsm_ca *svsm_get_caa(void)
+{
+	if (sev_cfg.use_cas)
+		return this_cpu_read(svsm_caa);
+	else
+		return boot_svsm_caa;
+}
+
+static __always_inline u64 svsm_get_caa_pa(void)
+{
+	if (sev_cfg.use_cas)
+		return this_cpu_read(svsm_caa_pa);
+	else
+		return boot_svsm_caa_pa;
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+	return native_rdmsrq(MSR_AMD64_SEV_ES_GHCB);
+}
+
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
+{
+	u32 low, high;
+
+	low  = (u32)(val);
+	high = (u32)(val >> 32);
+
+	native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
+}
+
+void snp_register_ghcb_early(unsigned long paddr);
+bool sev_es_negotiate_protocol(void);
+bool sev_es_check_cpu_features(void);
+u64 get_hv_features(void);
+
+const struct snp_cpuid_table *snp_cpuid_get_table(void);
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 1581246491b5..58e028d42e41 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -15,6 +15,7 @@
 #include <asm/sev-common.h>
 #include <asm/coco.h>
 #include <asm/set_memory.h>
+#include <asm/svm.h>
 
 #define GHCB_PROTOCOL_MIN	1ULL
 #define GHCB_PROTOCOL_MAX	2ULL
@@ -83,6 +84,36 @@ extern void vc_no_ghcb(void);
 extern void vc_boot_ghcb(void);
 extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 
+/*
+ * Individual entries of the SNP CPUID table, as defined by the SNP
+ * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
+ */
+struct snp_cpuid_fn {
+	u32 eax_in;
+	u32 ecx_in;
+	u64 xcr0_in;
+	u64 xss_in;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+	u64 __reserved;
+} __packed;
+
+/*
+ * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
+ * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
+ * of 64 entries per CPUID table.
+ */
+#define SNP_CPUID_COUNT_MAX 64
+
+struct snp_cpuid_table {
+	u32 count;
+	u32 __reserved1;
+	u64 __reserved2;
+	struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
+} __packed;
+
 /* PVALIDATE return codes */
 #define PVALIDATE_FAIL_SIZEMISMATCH	6
 
@@ -203,6 +234,9 @@ struct snp_guest_req {
 	unsigned int vmpck_id;
 	u8 msg_version;
 	u8 msg_type;
+
+	struct snp_req_data input;
+	void *certs_data;
 };
 
 /*
@@ -263,9 +297,6 @@ struct snp_msg_desc {
 	struct snp_guest_msg secret_request, secret_response;
 
 	struct snp_secrets_page *secrets;
-	struct snp_req_data input;
-
-	void *certs_data;
 
 	struct aesgcm_ctx *ctx;
 
@@ -384,6 +415,10 @@ struct svsm_call {
 #define SVSM_ATTEST_SERVICES		0
 #define SVSM_ATTEST_SINGLE_SERVICE	1
 
+#define SVSM_VTPM_CALL(x)		((2ULL << 32) | (x))
+#define SVSM_VTPM_QUERY			0
+#define SVSM_VTPM_CMD			1
+
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
 extern u8 snp_vmpl;
@@ -481,9 +516,39 @@ void snp_msg_free(struct snp_msg_desc *mdesc);
 int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
 			   struct snp_guest_request_ioctl *rio);
 
+int snp_svsm_vtpm_send_command(u8 *buffer);
+
 void __init snp_secure_tsc_prepare(void);
 void __init snp_secure_tsc_init(void);
 
+static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
+{
+	ghcb->save.sw_exit_code = 0;
+	__builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt);
+
+/* I/O parameters for CPUID-related helpers */
+struct cpuid_leaf {
+	u32 fn;
+	u32 subfn;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+};
+
+int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf);
+
+void __noreturn sev_es_terminate(unsigned int set, unsigned int reason);
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2);
+
+extern struct ghcb *boot_ghcb;
+
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define snp_vmpl 0
@@ -524,6 +589,7 @@ static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; }
 static inline void snp_msg_free(struct snp_msg_desc *mdesc) { }
 static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
 					 struct snp_guest_request_ioctl *rio) { return -ENODEV; }
+static inline int snp_svsm_vtpm_send_command(u8 *buffer) { return -ENODEV; }
 static inline void __init snp_secure_tsc_prepare(void) { }
 static inline void __init snp_secure_tsc_init(void) { }
 
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index fcbbef484a78..a28ff6b14145 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -106,7 +106,7 @@
 #define TDX_PS_1G	2
 #define TDX_PS_NR	(TDX_PS_1G + 1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler_attributes.h>
 
@@ -177,5 +177,5 @@ static __always_inline u64 hcall_func(u64 exit_reason)
         return exit_reason;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_SHARED_TDX_H */
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 4cb77e004615..ba6f2fe43848 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_SHSTK_H
 #define _ASM_X86_SHSTK_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 struct task_struct;
@@ -37,6 +37,6 @@ static inline int shstk_update_last_frame(unsigned long val) { return 0; }
 static inline bool shstk_is_enabled(void) { return false; }
 #endif /* CONFIG_X86_USER_SHADOW_STACK */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SHSTK_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 4a4043ca6493..c72d46175374 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_SIGNAL_H
 #define _ASM_X86_SIGNAL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/linkage.h>
 
 /* Most things should be clean enough to redefine this at will, if care
@@ -28,9 +28,9 @@ typedef struct {
 #define SA_IA32_ABI	0x02000000u
 #define SA_X32_ABI	0x01000000u
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #include <uapi/asm/signal.h>
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __ARCH_HAS_SA_RESTORER
 
@@ -101,5 +101,5 @@ struct pt_regs;
 
 #endif /* !__i386__ */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_SIGNAL_H */
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index a341c878e977..b8027b63cd7a 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,6 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SIMD_H
+#define _ASM_SIMD_H
 
 #include <asm/fpu/api.h>
+#include <linux/compiler_attributes.h>
+#include <linux/types.h>
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
@@ -10,3 +14,5 @@ static __must_check inline bool may_use_simd(void)
 {
 	return irq_fpu_usable();
 }
+
+#endif	/* _ASM_SIMD_H */
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 2de1e5a75c57..4f84d421d1cf 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -13,7 +13,7 @@
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define ASM_CLAC \
 	ALTERNATIVE "", "clac", X86_FEATURE_SMAP
@@ -21,7 +21,7 @@
 #define ASM_STAC \
 	ALTERNATIVE "", "stac", X86_FEATURE_SMAP
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 static __always_inline void clac(void)
 {
@@ -40,7 +40,8 @@ static __always_inline unsigned long smap_save(void)
 	unsigned long flags;
 
 	asm volatile ("# smap_save\n\t"
-		      ALTERNATIVE("", "pushf; pop %0; " "clac" "\n\t",
+		      ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE
+				  "", "pushf; pop %0; clac",
 				  X86_FEATURE_SMAP)
 		      : "=rm" (flags) : : "memory", "cc");
 
@@ -50,7 +51,8 @@ static __always_inline unsigned long smap_save(void)
 static __always_inline void smap_restore(unsigned long flags)
 {
 	asm volatile ("# smap_restore\n\t"
-		      ALTERNATIVE("", "push %0; popf\n\t",
+		      ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE
+				  "", "push %0; popf",
 				  X86_FEATURE_SMAP)
 		      : : "g" (flags) : "memory", "cc");
 }
@@ -61,6 +63,11 @@ static __always_inline void smap_restore(unsigned long flags)
 #define ASM_STAC \
 	ALTERNATIVE("", "stac", X86_FEATURE_SMAP)
 
-#endif /* __ASSEMBLY__ */
+#define ASM_CLAC_UNSAFE \
+	ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "clac", X86_FEATURE_SMAP)
+#define ASM_STAC_UNSAFE \
+	ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "stac", X86_FEATURE_SMAP)
+
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SMAP_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698f..0c1c68039d6f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -1,12 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_SMP_H
 #define _ASM_X86_SMP_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 
 #include <asm/cpumask.h>
-#include <asm/current.h>
-#include <asm/thread_info.h>
+
+DECLARE_PER_CPU_CACHE_HOT(int, cpu_number);
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
@@ -114,13 +115,12 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-void smp_store_cpu_info(int id);
-
 asmlinkage __visible void smp_reboot_interrupt(void);
 __visible void smp_reschedule_interrupt(struct pt_regs *regs);
 __visible void smp_call_function_interrupt(struct pt_regs *regs);
@@ -133,14 +133,8 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
  * This function is needed by all SMP systems. It must _always_ be valid
  * from the initial startup.
  */
-#define raw_smp_processor_id()  this_cpu_read(pcpu_hot.cpu_number)
-#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
-
-#ifdef CONFIG_X86_32
-extern int safe_smp_processor_id(void);
-#else
-# define safe_smp_processor_id()	smp_processor_id()
-#endif
+#define raw_smp_processor_id()  this_cpu_read(cpu_number)
+#define __smp_processor_id() __this_cpu_read(cpu_number)
 
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
@@ -164,6 +158,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
@@ -175,7 +171,7 @@ extern void nmi_selftest(void);
 extern unsigned int smpboot_control;
 extern unsigned long apic_mmio_base;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* Control bits for startup_64 */
 #define STARTUP_READ_APICID	0x80000000
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 658b690b2ccb..00b7e0398210 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -84,7 +84,7 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
 static __always_inline void __update_spec_ctrl(u64 val)
 {
 	__this_cpu_write(x86_spec_ctrl_current, val);
-	native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+	native_wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 03e7c2d49559..ecda17efa042 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -10,30 +10,19 @@
 #include <linux/irqflags.h>
 #include <linux/jump_label.h>
 
-/*
- * The compiler should not reorder volatile asm statements with respect to each
- * other: they should execute in program order. However GCC 4.9.x and 5.x have
- * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
- * volatile asm. The write functions are not affected since they have memory
- * clobbers preventing reordering. To prevent reads from being reordered with
- * respect to writes, use a dummy memory operand.
- */
-
-#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
-
 void native_write_cr0(unsigned long val);
 
 static inline unsigned long native_read_cr0(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+	asm volatile("mov %%cr0,%0" : "=r" (val));
 	return val;
 }
 
 static __always_inline unsigned long native_read_cr2(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+	asm volatile("mov %%cr2,%0" : "=r" (val));
 	return val;
 }
 
@@ -42,14 +31,14 @@ static __always_inline void native_write_cr2(unsigned long val)
 	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
-static inline unsigned long __native_read_cr3(void)
+static __always_inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+	asm volatile("mov %%cr3,%0" : "=r" (val));
 	return val;
 }
 
-static inline void native_write_cr3(unsigned long val)
+static __always_inline void native_write_cr3(unsigned long val)
 {
 	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
@@ -66,10 +55,10 @@ static inline unsigned long native_read_cr4(void)
 	asm volatile("1: mov %%cr4, %0\n"
 		     "2:\n"
 		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val) : "0" (0), __FORCE_ORDER);
+		     : "=r" (val) : "0" (0));
 #else
 	/* CR4 always exists on x86_64. */
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+	asm volatile("mov %%cr4,%0" : "=r" (val));
 #endif
 	return val;
 }
@@ -176,9 +165,8 @@ static __always_inline void clflush(volatile void *__p)
 
 static inline void clflushopt(volatile void *__p)
 {
-	alternative_io(".byte 0x3e; clflush %0",
-		       ".byte 0x66; clflush %0",
-		       X86_FEATURE_CLFLUSHOPT,
+	alternative_io("ds clflush %0",
+		       "clflushopt %0", X86_FEATURE_CLFLUSHOPT,
 		       "+m" (*(volatile char __force *)__p));
 }
 
@@ -186,14 +174,11 @@ static inline void clwb(volatile void *__p)
 {
 	volatile struct { char x[64]; } *p = __p;
 
-	asm volatile(ALTERNATIVE_2(
-		".byte 0x3e; clflush (%[pax])",
-		".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */
-		X86_FEATURE_CLFLUSHOPT,
-		".byte 0x66, 0x0f, 0xae, 0x30",  /* clwb (%%rax) */
-		X86_FEATURE_CLWB)
-		: [p] "+m" (*p)
-		: [pax] "a" (p));
+	asm_inline volatile(ALTERNATIVE_2(
+		"ds clflush %0",
+		"clflushopt %0", X86_FEATURE_CLFLUSHOPT,
+		"clwb %0", X86_FEATURE_CLWB)
+		: "+m" (*p));
 }
 
 #ifdef CONFIG_X86_USER_SHADOW_STACK
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
deleted file mode 100644
index e0975e9c4f47..000000000000
--- a/arch/x86/include/asm/sta2x11.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
- */
-#ifndef __ASM_STA2X11_H
-#define __ASM_STA2X11_H
-
-#include <linux/pci.h>
-
-/* This needs to be called from the MFD to configure its sub-devices */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
-
-#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f51..cd761b14eb02 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
 /*
  * GCC stack protector support.
  *
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base.  On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary.  On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset.  On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function.  The pattern is called the stack canary
+ * and is a unique value for each task.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
 
 #include <linux/sched.h>
 
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary = get_random_canary();
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
 	current->stack_canary = canary;
-#ifdef CONFIG_X86_64
-	this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
 	this_cpu_write(__stack_chk_guard, canary);
-#endif
 }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 {
-#ifdef CONFIG_X86_64
-	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
 	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
 }
 
 #else	/* STACKPROTECTOR */
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 32c0d981a82a..e9cce169bb4c 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -33,11 +33,11 @@ extern size_t strlen(const char *s);
 static __always_inline void *__memcpy(void *to, const void *from, size_t n)
 {
 	int d0, d1, d2;
-	asm volatile("rep ; movsl\n\t"
+	asm volatile("rep movsl\n\t"
 		     "movl %4,%%ecx\n\t"
 		     "andl $3,%%ecx\n\t"
 		     "jz 1f\n\t"
-		     "rep ; movsb\n\t"
+		     "rep movsb\n\t"
 		     "1:"
 		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
 		     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
@@ -89,7 +89,7 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 	if (n >= 5 * 4) {
 		/* large block: use rep prefix */
 		int ecx;
-		asm volatile("rep ; movsl"
+		asm volatile("rep movsl"
 			     : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
 			     : "0" (n / 4), "1" (edi), "2" (esi)
 			     : "memory"
@@ -165,8 +165,7 @@ extern void *memchr(const void *cs, int c, size_t count);
 static inline void *__memset_generic(void *s, char c, size_t count)
 {
 	int d0, d1;
-	asm volatile("rep\n\t"
-		     "stosb"
+	asm volatile("rep stosb"
 		     : "=&c" (d0), "=&D" (d1)
 		     : "a" (c), "1" (s), "0" (count)
 		     : "memory");
@@ -199,8 +198,7 @@ extern void *memset(void *, int, size_t);
 static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 {
 	int d0, d1;
-	asm volatile("rep\n\t"
-		     "stosw"
+	asm volatile("rep stosw"
 		     : "=&c" (d0), "=&D" (d1)
 		     : "a" (v), "1" (s), "0" (n)
 		     : "memory");
@@ -211,8 +209,7 @@ static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
 {
 	int d0, d1;
-	asm volatile("rep\n\t"
-		     "stosl"
+	asm volatile("rep stosl"
 		     : "=&c" (d0), "=&D" (d1)
 		     : "a" (v), "1" (s), "0" (n)
 		     : "memory");
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 9d0b324eab21..79e9695dc13e 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -21,6 +21,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
 void *__memset(void *s, int c, size_t n);
+KCFI_REFERENCE(__memset);
 
 /*
  * KMSAN needs to instrument as much code as possible. Use C versions of
@@ -70,6 +71,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t count);
 void *__memmove(void *dest, const void *src, size_t count);
+KCFI_REFERENCE(__memmove);
 
 int memcmp(const void *cs, const void *ct, size_t count);
 size_t strlen(const char *s);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d8416b3bf832..e8e5aab06255 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -9,6 +9,7 @@
 
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
+#include <asm/msr.h>
 
 /* image of the saved processor state */
 struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 54df06687d83..b512f9665f78 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -9,6 +9,7 @@
 
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
+#include <asm/msr.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e2fac21471f5..9b7fa99ae951 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -116,6 +116,7 @@ enum {
 	INTERCEPT_INVPCID,
 	INTERCEPT_MCOMMIT,
 	INTERCEPT_TLBSYNC,
+	INTERCEPT_IDLE_HLT = 166,
 };
 
 
@@ -290,10 +291,6 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 #define SVM_SEV_FEAT_ALTERNATE_INJECTION		BIT(4)
 #define SVM_SEV_FEAT_DEBUG_SWAP				BIT(5)
 
-#define SVM_SEV_FEAT_INT_INJ_MODES		\
-	(SVM_SEV_FEAT_RESTRICTED_INJECTION |	\
-	 SVM_SEV_FEAT_ALTERNATE_INJECTION)
-
 struct vmcb_seg {
 	u16 selector;
 	u16 attrib;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 75248546403d..499b1c15cc8b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -52,6 +52,8 @@ do {									\
 } while (0)
 
 #ifdef CONFIG_X86_32
+#include <asm/msr.h>
+
 static inline void refresh_sysenter_cs(struct thread_struct *thread)
 {
 	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
@@ -59,7 +61,7 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 		return;
 
 	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
-	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+	wrmsrq(MSR_IA32_SYSENTER_CS, thread->sysenter_cs);
 }
 #endif
 
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 6d8d6bc183b7..cd21a0405ac5 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -31,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -49,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -66,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
+	asm volatile("lock " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -82,7 +82,7 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -95,7 +95,7 @@ static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -108,7 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
+	return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index b4b16dafd55e..4a1922ec80cf 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -30,7 +30,7 @@
 #define TDX_SUCCESS		0ULL
 #define TDX_RND_NO_ENTROPY	0x8000020300000000ULL
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/asm/mce.h>
 
@@ -58,7 +58,7 @@ void tdx_get_ve_info(struct ve_info *ve);
 
 bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve);
 
-void tdx_safe_halt(void);
+void tdx_halt(void);
 
 bool tdx_early_handle_ve(struct pt_regs *regs);
 
@@ -72,7 +72,7 @@ void __init tdx_dump_td_ctls(u64 td_ctls);
 #else
 
 static inline void tdx_early_init(void) { };
-static inline void tdx_safe_halt(void) { };
+static inline void tdx_halt(void) { };
 
 static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; }
 
@@ -126,5 +126,5 @@ static inline int tdx_enable(void)  { return -ENODEV; }
 static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_TDX_H */
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index ab9e143ec9fe..5337f1be18f6 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -11,11 +11,11 @@
  * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
  * Raise it if needed.
  */
-#define POKE_MAX_OPCODE_SIZE	5
+#define TEXT_POKE_MAX_OPCODE_SIZE	5
 
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
-extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
+extern void text_poke_apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
 
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
@@ -32,17 +32,17 @@ extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u
  * an inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void text_poke_sync(void);
+extern void smp_text_poke_sync_each_cpu(void);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern void *text_poke_copy(void *addr, const void *opcode, size_t len);
 #define text_poke_copy text_poke_copy
 extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok);
 extern void *text_poke_set(void *addr, int c, size_t len);
-extern int poke_int3_handler(struct pt_regs *regs);
-extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
+extern int smp_text_poke_int3_handler(struct pt_regs *regs);
+extern void smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate);
 
-extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate);
-extern void text_poke_finish(void);
+extern void smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate);
+extern void smp_text_poke_batch_finish(void);
 
 #define INT3_INSN_SIZE		1
 #define INT3_INSN_OPCODE	0xCC
@@ -82,7 +82,7 @@ static __always_inline int text_opcode_size(u8 opcode)
 }
 
 union text_poke_insn {
-	u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 text[TEXT_POKE_MAX_OPCODE_SIZE];
 	struct {
 		u8 opcode;
 		s32 disp;
@@ -128,8 +128,8 @@ void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
 }
 
 extern int after_bootmem;
-extern __ro_after_init struct mm_struct *poking_mm;
-extern __ro_after_init unsigned long poking_addr;
+extern __ro_after_init struct mm_struct *text_poke_mm;
+extern __ro_after_init unsigned long text_poke_mm_addr;
 
 #ifndef CONFIG_UML_X86
 static __always_inline
@@ -142,13 +142,14 @@ static __always_inline
 void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
 	/*
-	 * The int3 handler in entry_64.S adds a gap between the
+	 * The INT3 handler in entry_64.S adds a gap between the
 	 * stack where the break point happened, and the saving of
 	 * pt_regs. We can extend the original stack because of
-	 * this gap. See the idtentry macro's create_gap option.
+	 * this gap. See the idtentry macro's X86_TRAP_BP logic.
 	 *
-	 * Similarly entry_32.S will have a gap on the stack for (any) hardware
-	 * exception and pt_regs; see FIXUP_FRAME.
+	 * Similarly, entry_32.S will have a gap on the stack for
+	 * (any) hardware exception and pt_regs; see the
+	 * FIXUP_FRAME macro.
 	 */
 	regs->sp -= sizeof(unsigned long);
 	*(unsigned long *)regs->sp = val;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a55c214f3ba6..9282465eea21 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -54,7 +54,7 @@
  * - this struct should fit entirely inside of one cache line
  * - this struct shares the supervisor stack pages
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct task_struct;
 #include <asm/cpufeature.h>
 #include <linux/atomic.h>
@@ -73,7 +73,7 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #include <asm/asm-offsets.h>
 
@@ -161,7 +161,7 @@ struct thread_info {
  *
  * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * Walks up the stack frames to make sure that the specified object is
@@ -213,7 +213,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #endif
 }
 
-#endif  /* !__ASSEMBLY__ */
+#endif  /* !__ASSEMBLER__ */
 
 /*
  * Thread-synchronous status.
@@ -224,7 +224,7 @@ static inline int arch_within_stack_frames(const void * const stack,
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
 
@@ -242,6 +242,6 @@ static inline int arch_within_stack_frames(const void * const stack,
 
 extern void arch_setup_new_exec(void);
 #define arch_setup_new_exec arch_setup_new_exec
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 77f52bc1578a..866ea78ba156 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,9 @@
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
+#include <linux/kernel.h>
+#include <vdso/bits.h>
+#include <vdso/page.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
@@ -25,4 +28,139 @@ static inline void invlpg(unsigned long addr)
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
 
+enum addr_stride {
+	PTE_STRIDE = 0,
+	PMD_STRIDE = 1
+};
+
+/*
+ * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
+ * of the three. For example:
+ * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
+ * - FLAG_PCID:			    invalidate all TLB entries matching the PCID
+ *
+ * The first is used to invalidate (kernel) mappings at a particular
+ * address across all processes.
+ *
+ * The latter invalidates all TLB entries matching a PCID.
+ */
+#define INVLPGB_FLAG_VA			BIT(0)
+#define INVLPGB_FLAG_PCID		BIT(1)
+#define INVLPGB_FLAG_ASID		BIT(2)
+#define INVLPGB_FLAG_INCLUDE_GLOBAL	BIT(3)
+#define INVLPGB_FLAG_FINAL_ONLY		BIT(4)
+#define INVLPGB_FLAG_INCLUDE_NESTED	BIT(5)
+
+/* The implied mode when all bits are clear: */
+#define INVLPGB_MODE_ALL_NONGLOBALS	0UL
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+/*
+ * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
+ *
+ * The INVLPGB instruction is weakly ordered, and a batch of invalidations can
+ * be done in a parallel fashion.
+ *
+ * The instruction takes the number of extra pages to invalidate, beyond the
+ * first page, while __invlpgb gets the more human readable number of pages to
+ * invalidate.
+ *
+ * The bits in rax[0:2] determine respectively which components of the address
+ * (VA, PCID, ASID) get compared when flushing. If neither bits are set, *any*
+ * address in the specified range matches.
+ *
+ * Since it is desired to only flush TLB entries for the ASID that is executing
+ * the instruction (a host/hypervisor or a guest), the ASID valid bit should
+ * always be set. On a host/hypervisor, the hardware will use the ASID value
+ * specified in EDX[15:0] (which should be 0). On a guest, the hardware will
+ * use the actual ASID value of the guest.
+ *
+ * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from
+ * this CPU have completed.
+ */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride stride, u8 flags)
+{
+	u64 rax = addr | flags | INVLPGB_FLAG_ASID;
+	u32 ecx = (stride << 31) | (nr_pages - 1);
+	u32 edx = (pcid << 16) | asid;
+
+	/* The low bits in rax are for flags. Verify addr is clean. */
+	VM_WARN_ON_ONCE(addr & ~PAGE_MASK);
+
+	/* INVLPGB; supported in binutils >= 2.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xfe" :: "a" (rax), "c" (ecx), "d" (edx));
+}
+
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags)
+{
+	__invlpgb(asid, pcid, 0, 1, 0, flags);
+}
+
+static inline void __tlbsync(void)
+{
+	/*
+	 * TLBSYNC waits for INVLPGB instructions originating on the same CPU
+	 * to have completed. Print a warning if the task has been migrated,
+	 * and might not be waiting on all the INVLPGBs issued during this TLB
+	 * invalidation sequence.
+	 */
+	cant_migrate();
+
+	/* TLBSYNC: supported in binutils >= 0.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
+}
+#else
+/* Some compilers (I'm looking at you clang!) simply can't do DCE */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride s, u8 flags) { }
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags) { }
+static inline void __tlbsync(void) { }
+#endif
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+						unsigned long addr,
+						u16 nr, bool stride)
+{
+	enum addr_stride str = stride ? PMD_STRIDE : PTE_STRIDE;
+	u8 flags = INVLPGB_FLAG_PCID | INVLPGB_FLAG_VA;
+
+	__invlpgb(0, pcid, addr, nr, str, flags);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
+{
+	__invlpgb_all(0, pcid, INVLPGB_FLAG_PCID);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invlpgb_flush_all(void)
+{
+	/*
+	 * TLBSYNC at the end needs to make sure all flushes done on the
+	 * current CPU have been executed system-wide. Therefore, make
+	 * sure nothing gets migrated in-between but disable preemption
+	 * as it is cheaper.
+	 */
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_FLAG_INCLUDE_GLOBAL);
+	__tlbsync();
+}
+
+/* Flush addr, including globals, for all PCIDs. */
+static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
+{
+	__invlpgb(0, 0, addr, nr, PTE_STRIDE, INVLPGB_FLAG_INCLUDE_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invlpgb_flush_all_nonglobals(void)
+{
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_MODE_ALL_NONGLOBALS);
+	__tlbsync();
+}
 #endif /* _ASM_X86_TLB_H */
diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h
index 1ad56eb3e8a8..80aaf64ff25f 100644
--- a/arch/x86/include/asm/tlbbatch.h
+++ b/arch/x86/include/asm/tlbbatch.h
@@ -10,6 +10,11 @@ struct arch_tlbflush_unmap_batch {
 	 * the PFNs being flushed..
 	 */
 	struct cpumask cpumask;
+	/*
+	 * Set if pages were unmapped from any MM, even one that does not
+	 * have active CPUs in its cpumask.
+	 */
+	bool unmapped_pages;
 };
 
 #endif /* _ARCH_X86_TLBBATCH_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 02fc2aa06e9e..e9b81876ebe4 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/sched.h>
 
+#include <asm/barrier.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
@@ -183,6 +184,9 @@ static inline void cr4_init_shadow(void)
 extern unsigned long mmu_cr4_features;
 extern u32 *trampoline_cr4_features;
 
+/* How many pages can be invalidated with one INVLPGB. */
+extern u16 invlpgb_count_max;
+
 extern void initialize_tlbstate_and_flush(void);
 
 /*
@@ -231,6 +235,71 @@ void flush_tlb_one_kernel(unsigned long addr);
 void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info);
 
+static inline bool is_dyn_asid(u16 asid)
+{
+	return asid < TLB_NR_DYN_ASIDS;
+}
+
+static inline bool is_global_asid(u16 asid)
+{
+	return !is_dyn_asid(asid);
+}
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+static inline u16 mm_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return 0;
+
+	asid = smp_load_acquire(&mm->context.global_asid);
+
+	/* mm->context.global_asid is either 0, or a global ASID */
+	VM_WARN_ON_ONCE(asid && is_dyn_asid(asid));
+
+	return asid;
+}
+
+static inline void mm_init_global_asid(struct mm_struct *mm)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		mm->context.global_asid = 0;
+		mm->context.asid_transition = false;
+	}
+}
+
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
+{
+	/*
+	 * Notably flush_tlb_mm_range() -> broadcast_tlb_flush() ->
+	 * finish_asid_transition() needs to observe asid_transition = true
+	 * once it observes global_asid.
+	 */
+	mm->context.asid_transition = true;
+	smp_store_release(&mm->context.global_asid, asid);
+}
+
+static inline void mm_clear_asid_transition(struct mm_struct *mm)
+{
+	WRITE_ONCE(mm->context.asid_transition, false);
+}
+
+static inline bool mm_in_asid_transition(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	return mm && READ_ONCE(mm->context.asid_transition);
+}
+#else
+static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_global_asid(struct mm_struct *mm) { }
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
+static inline void mm_clear_asid_transition(struct mm_struct *mm) { }
+static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
+#endif /* CONFIG_BROADCAST_TLB_FLUSH */
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
@@ -242,7 +311,7 @@ void flush_tlb_multi(const struct cpumask *cpumask,
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
@@ -279,11 +348,11 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 }
 
 static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
-					     struct mm_struct *mm,
-					     unsigned long uaddr)
+		struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	inc_mm_tlb_gen(mm);
 	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	batch->unmapped_pages = true;
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index ec134b719144..6c79ee7c0957 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -229,11 +229,11 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_primary_thread_mask);
 }
+#define topology_is_primary_thread topology_is_primary_thread
 
 #else /* CONFIG_SMP */
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
-static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; }
 #endif /* !CONFIG_SMP */
 
diff --git a/arch/x86/include/asm/trace/common.h b/arch/x86/include/asm/trace/common.h
deleted file mode 100644
index f0f9bcdb74d9..000000000000
--- a/arch/x86/include/asm/trace/common.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_TRACE_COMMON_H
-#define _ASM_TRACE_COMMON_H
-
-#ifdef CONFIG_TRACING
-DECLARE_STATIC_KEY_FALSE(trace_pagefault_key);
-#define trace_pagefault_enabled()			\
-	static_branch_unlikely(&trace_pagefault_key)
-#else
-static inline bool trace_pagefault_enabled(void) { return false; }
-#endif
-
-#endif
diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
deleted file mode 100644
index 6b1e87194809..000000000000
--- a/arch/x86/include/asm/trace/exceptions.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM exceptions
-
-#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PAGE_FAULT_H
-
-#include <linux/tracepoint.h>
-#include <asm/trace/common.h>
-
-extern int trace_pagefault_reg(void);
-extern void trace_pagefault_unreg(void);
-
-DECLARE_EVENT_CLASS(x86_exceptions,
-
-	TP_PROTO(unsigned long address, struct pt_regs *regs,
-		 unsigned long error_code),
-
-	TP_ARGS(address, regs, error_code),
-
-	TP_STRUCT__entry(
-		__field(		unsigned long, address	)
-		__field(		unsigned long, ip	)
-		__field(		unsigned long, error_code )
-	),
-
-	TP_fast_assign(
-		__entry->address = address;
-		__entry->ip = regs->ip;
-		__entry->error_code = error_code;
-	),
-
-	TP_printk("address=%ps ip=%ps error_code=0x%lx",
-		  (void *)__entry->address, (void *)__entry->ip,
-		  __entry->error_code) );
-
-#define DEFINE_PAGE_FAULT_EVENT(name)				\
-DEFINE_EVENT_FN(x86_exceptions, name,				\
-	TP_PROTO(unsigned long address,	struct pt_regs *regs,	\
-		 unsigned long error_code),			\
-	TP_ARGS(address, regs, error_code),			\
-	trace_pagefault_reg, trace_pagefault_unreg);
-
-DEFINE_PAGE_FAULT_EVENT(page_fault_user);
-DEFINE_PAGE_FAULT_EVENT(page_fault_kernel);
-
-#undef TRACE_INCLUDE_PATH
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE exceptions
-#endif /*  _TRACE_PAGE_FAULT_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 4645a6334063..0454d5e60e5d 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -74,11 +74,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
 	TP_ARGS(fpu)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 88e7f0f3bf62..7408bebdfde0 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -6,7 +6,6 @@
 #define _TRACE_IRQ_VECTORS_H
 
 #include <linux/tracepoint.h>
-#include <asm/trace/common.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1f1deaecd364..869b88061801 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -35,8 +35,6 @@ static inline int get_si_code(unsigned long condition)
 		return TRAP_BRKPT;
 }
 
-extern int panic_on_unrecovered_nmi;
-
 void math_emulate(struct math_emu_info *);
 
 bool fault_in_kernel_space(unsigned long address);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 94408a784c8e..4f7f09f50552 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,10 +5,65 @@
 #ifndef _ASM_X86_TSC_H
 #define _ASM_X86_TSC_H
 
+#include <asm/asm.h>
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
 
+/**
+ * rdtsc() - returns the current TSC without ordering constraints
+ *
+ * rdtsc() returns the result of RDTSC as a 64-bit integer.  The
+ * only ordering constraint it supplies is the ordering implied by
+ * "asm volatile": it will put the RDTSC in the place you expect.  The
+ * CPU can and will speculatively execute that RDTSC, though, so the
+ * results can be non-monotonic if compared on different CPUs.
+ */
+static __always_inline u64 rdtsc(void)
+{
+	EAX_EDX_DECLARE_ARGS(val, low, high);
+
+	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
+
+	return EAX_EDX_VAL(val, low, high);
+}
+
+/**
+ * rdtsc_ordered() - read the current TSC in program order
+ *
+ * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
+ * It is ordered like a load to a global in-memory counter.  It should
+ * be impossible to observe non-monotonic rdtsc_unordered() behavior
+ * across multiple CPUs as long as the TSC is synced.
+ */
+static __always_inline u64 rdtsc_ordered(void)
+{
+	EAX_EDX_DECLARE_ARGS(val, low, high);
+
+	/*
+	 * The RDTSC instruction is not ordered relative to memory
+	 * access.  The Intel SDM and the AMD APM are both vague on this
+	 * point, but empirically an RDTSC instruction can be
+	 * speculatively executed before prior loads.  An RDTSC
+	 * immediately after an appropriate barrier appears to be
+	 * ordered as a normal load, that is, it provides the same
+	 * ordering guarantees as reading from a global memory location
+	 * that some other imaginary CPU is updating continuously with a
+	 * time stamp.
+	 *
+	 * Thus, use the preferred barrier on the respective CPU, aiming for
+	 * RDTSCP as the default.
+	 */
+	asm volatile(ALTERNATIVE_2("rdtsc",
+				   "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
+				   "rdtscp", X86_FEATURE_RDTSCP)
+			: EAX_EDX_RET(val, low, high)
+			/* RDTSCP clobbers ECX with MSR_TSC_AUX. */
+			:: "ecx");
+
+	return EAX_EDX_VAL(val, low, high);
+}
+
 /*
  * Standard way to access the cycle counter.
  */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index c52f0133425b..c8a5ae35c871 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -26,8 +26,8 @@ extern unsigned long USER_PTR_MAX;
  */
 static inline unsigned long __untagged_addr(unsigned long addr)
 {
-	asm (ALTERNATIVE("",
-			 "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM)
+	asm_inline (ALTERNATIVE("", "and " __percpu_arg([mask]) ", %[addr]",
+				X86_FEATURE_LAM)
 	     : [addr] "+r" (addr)
 	     : [mask] "m" (__my_cpu_var(tlbstate_untag_mask)));
 
@@ -54,7 +54,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
 #endif
 
 #define valid_user_address(x) \
-	((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
+	likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
 
 /*
  * Masking the user address is an alternative to a conditional
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 85cc57cb6539..8f4579c5a6f8 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -5,7 +5,7 @@
 
 #include "orc_types.h"
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro UNWIND_HINT_END_OF_STACK
 	UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK
@@ -88,6 +88,6 @@
 #define UNWIND_HINT_RESTORE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index d7f6592b74a9..b7253ef3205a 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -18,12 +18,6 @@ struct vdso_image {
 	unsigned long extable_base, extable_len;
 	const void *extable;
 
-	long sym_vvar_start;  /* Negative offset to the vvar area */
-
-	long sym_vvar_page;
-	long sym_pvclock_page;
-	long sym_hvclock_page;
-	long sym_timens_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
@@ -33,17 +27,9 @@ struct vdso_image {
 	long sym_vdso32_rt_sigreturn_landing_pad;
 };
 
-#ifdef CONFIG_X86_64
 extern const struct vdso_image vdso_image_64;
-#endif
-
-#ifdef CONFIG_X86_X32_ABI
 extern const struct vdso_image vdso_image_x32;
-#endif
-
-#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
 extern const struct vdso_image vdso_image_32;
-#endif
 
 extern int __init init_vdso_image(const struct vdso_image *image);
 
diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h
index 2bf9c0e970c3..ff1c11b9fa27 100644
--- a/arch/x86/include/asm/vdso/getrandom.h
+++ b/arch/x86/include/asm/vdso/getrandom.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 
@@ -27,16 +27,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig
 	return ret;
 }
 
-extern struct vdso_rng_data vdso_rng_data
-	__attribute__((visibility("hidden")));
-
-static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void)
-{
-	if (IS_ENABLED(CONFIG_TIME_NS) && __arch_get_vdso_data()->clock_mode == VDSO_CLOCKMODE_TIMENS)
-		return (void *)&vdso_rng_data + ((void *)&timens_page - (void *)__arch_get_vdso_data());
-	return &vdso_rng_data;
-}
-
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 375a34b0f365..73b2e7ee8f0f 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -10,7 +10,7 @@
 #ifndef __ASM_VDSO_GETTIMEOFDAY_H
 #define __ASM_VDSO_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/linux/time.h>
 #include <asm/vgtod.h>
@@ -19,12 +19,6 @@
 #include <asm/pvclock.h>
 #include <clocksource/hyperv_timer.h>
 
-extern struct vdso_data vvar_page
-	__attribute__((visibility("hidden")));
-
-extern struct vdso_data timens_page
-	__attribute__((visibility("hidden")));
-
 #define VDSO_HAS_TIME 1
 
 #define VDSO_HAS_CLOCK_GETRES 1
@@ -59,14 +53,6 @@ extern struct ms_hyperv_tsc_page hvclock_page
 	__attribute__((visibility("hidden")));
 #endif
 
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return &timens_page;
-}
-#endif
-
 #ifndef BUILD_VDSO32
 
 static __always_inline
@@ -250,7 +236,7 @@ static u64 vread_hvclock(void)
 #endif
 
 static inline u64 __arch_get_hw_counter(s32 clock_mode,
-					const struct vdso_data *vd)
+					const struct vdso_time_data *vd)
 {
 	if (likely(clock_mode == VDSO_CLOCKMODE_TSC))
 		return (u64)rdtsc_ordered() & S64_MAX;
@@ -275,12 +261,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return U64_MAX;
 }
 
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
-	return &vvar_page;
-}
-
-static inline bool arch_vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool arch_vdso_clocksource_ok(const struct vdso_clock *vc)
 {
 	return true;
 }
@@ -319,37 +300,37 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
  * declares everything with the MSB/Sign-bit set as invalid. Therefore the
  * effective mask is S64_MAX.
  */
-static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
+static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base)
 {
-	u64 delta = cycles - vd->cycle_last;
+	u64 delta = cycles - vc->cycle_last;
 
 	/*
 	 * Negative motion and deltas which can cause multiplication
 	 * overflow require special treatment. This check covers both as
-	 * negative motion is guaranteed to be greater than @vd::max_cycles
+	 * negative motion is guaranteed to be greater than @vc::max_cycles
 	 * due to unsigned comparison.
 	 *
 	 * Due to the MSB/Sign-bit being used as invalid marker (see
 	 * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that
 	 * case is also unlikely and will also take the unlikely path here.
 	 */
-	if (unlikely(delta > vd->max_cycles)) {
+	if (unlikely(delta > vc->max_cycles)) {
 		/*
 		 * Due to the above mentioned TSC wobbles, filter out
 		 * negative motion.  Per the above masking, the effective
 		 * sign bit is now bit 62.
 		 */
 		if (delta & (1ULL << 62))
-			return base >> vd->shift;
+			return base >> vc->shift;
 
 		/* Handle multiplication overflow gracefully */
-		return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift);
+		return mul_u64_u32_add_u64_shr(delta & S64_MAX, vc->mult, base, vc->shift);
 	}
 
-	return ((delta * vd->mult) + base) >> vd->shift;
+	return ((delta * vc->mult) + base) >> vc->shift;
 }
 #define vdso_calc_ns vdso_calc_ns
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h
index 2cbce97d29ea..7000aeb59aa2 100644
--- a/arch/x86/include/asm/vdso/processor.h
+++ b/arch/x86/include/asm/vdso/processor.h
@@ -5,23 +5,23 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static __always_inline void rep_nop(void)
+/* PAUSE is a good thing to insert into busy-wait loops. */
+static __always_inline void native_pause(void)
 {
-	asm volatile("rep; nop" ::: "memory");
+	asm volatile("pause" ::: "memory");
 }
 
 static __always_inline void cpu_relax(void)
 {
-	rep_nop();
+	native_pause();
 }
 
 struct getcpu_cache;
 
 notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index 37b4a70559a8..4aa311a923f2 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -2,40 +2,21 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#define __VDSO_RND_DATA_OFFSET  640
-#define __VVAR_PAGES	4
+#define __VDSO_PAGES	6
 
 #define VDSO_NR_VCLOCK_PAGES	2
+#define VDSO_VCLOCK_PAGES_START(_b)	((_b) + (__VDSO_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE)
 #define VDSO_PAGE_PVCLOCK_OFFSET	0
 #define VDSO_PAGE_HVCLOCK_OFFSET	1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 #include <asm/vgtod.h>
 
-extern struct vdso_data *vdso_data;
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline
-struct vdso_data *__x86_get_k_vdso_data(void)
-{
-	return vdso_data;
-}
-#define __arch_get_k_vdso_data __x86_get_k_vdso_data
-
-static __always_inline
-struct vdso_rng_data *__x86_get_k_vdso_rng_data(void)
-{
-	return (void *)vdso_data + __VDSO_RND_DATA_OFFSET;
-}
-#define __arch_get_k_vdso_rng_data __x86_get_k_vdso_rng_data
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec3..5d471253c755 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -15,8 +15,6 @@
 #define MODULE_PROC_FAMILY "586TSC "
 #elif defined CONFIG_M586MMX
 #define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,8 +31,6 @@
 #define MODULE_PROC_FAMILY "K6 "
 #elif defined CONFIG_MK7
 #define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f7fd4369b821..8707361b24da 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -580,18 +580,22 @@ enum vm_entry_failure_code {
 /*
  * Exit Qualifications for EPT Violations
  */
-#define EPT_VIOLATION_ACC_READ_BIT	0
-#define EPT_VIOLATION_ACC_WRITE_BIT	1
-#define EPT_VIOLATION_ACC_INSTR_BIT	2
-#define EPT_VIOLATION_RWX_SHIFT		3
-#define EPT_VIOLATION_GVA_IS_VALID_BIT	7
-#define EPT_VIOLATION_GVA_TRANSLATED_BIT 8
-#define EPT_VIOLATION_ACC_READ		(1 << EPT_VIOLATION_ACC_READ_BIT)
-#define EPT_VIOLATION_ACC_WRITE		(1 << EPT_VIOLATION_ACC_WRITE_BIT)
-#define EPT_VIOLATION_ACC_INSTR		(1 << EPT_VIOLATION_ACC_INSTR_BIT)
-#define EPT_VIOLATION_RWX_MASK		(VMX_EPT_RWX_MASK << EPT_VIOLATION_RWX_SHIFT)
-#define EPT_VIOLATION_GVA_IS_VALID	(1 << EPT_VIOLATION_GVA_IS_VALID_BIT)
-#define EPT_VIOLATION_GVA_TRANSLATED	(1 << EPT_VIOLATION_GVA_TRANSLATED_BIT)
+#define EPT_VIOLATION_ACC_READ		BIT(0)
+#define EPT_VIOLATION_ACC_WRITE		BIT(1)
+#define EPT_VIOLATION_ACC_INSTR		BIT(2)
+#define EPT_VIOLATION_PROT_READ		BIT(3)
+#define EPT_VIOLATION_PROT_WRITE	BIT(4)
+#define EPT_VIOLATION_PROT_EXEC		BIT(5)
+#define EPT_VIOLATION_PROT_MASK		(EPT_VIOLATION_PROT_READ  | \
+					 EPT_VIOLATION_PROT_WRITE | \
+					 EPT_VIOLATION_PROT_EXEC)
+#define EPT_VIOLATION_GVA_IS_VALID	BIT(7)
+#define EPT_VIOLATION_GVA_TRANSLATED	BIT(8)
+
+#define EPT_VIOLATION_RWX_TO_PROT(__epte) (((__epte) & VMX_EPT_RWX_MASK) << 3)
+
+static_assert(EPT_VIOLATION_RWX_TO_PROT(VMX_EPT_RWX_MASK) ==
+	      (EPT_VIOLATION_PROT_READ | EPT_VIOLATION_PROT_WRITE | EPT_VIOLATION_PROT_EXEC));
 
 /*
  * Exit Qualifications for NOTIFY VM EXIT
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 213cf5379a5a..36698cc9fb44 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -292,6 +292,7 @@ struct x86_hyper_runtime {
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
+ * @get_nmi_reason		get the reason an NMI was received
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
  * @apic_post_init:		adjust apic if needed
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 97771b9d33af..59a62c3780a2 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -231,14 +231,12 @@ static __always_inline void __xen_stac(void)
 	 * Suppress objtool seeing the STAC/CLAC and getting confused about it
 	 * calling random code with AC=1.
 	 */
-	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
-		     ASM_STAC ::: "memory", "flags");
+	asm volatile(ASM_STAC_UNSAFE ::: "memory", "flags");
 }
 
 static __always_inline void __xen_clac(void)
 {
-	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
-		     ASM_CLAC ::: "memory", "flags");
+	asm volatile(ASM_CLAC_UNSAFE ::: "memory", "flags");
 }
 
 static inline long
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index a9088250770f..c2fc7869b996 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -43,7 +43,7 @@ extern struct start_info *xen_start_info;
 
 static inline uint32_t xen_cpuid_base(void)
 {
-	return hypervisor_cpuid_base(XEN_SIGNATURE, 2);
+	return cpuid_base_hypervisor(XEN_SIGNATURE, 2);
 }
 
 struct pci_dev;
@@ -72,18 +72,10 @@ enum xen_lazy_mode {
 };
 
 DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
-DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
 
 static inline void enter_lazy(enum xen_lazy_mode mode)
 {
-	enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
-
-	if (mode == old_mode) {
-		this_cpu_inc(xen_lazy_nesting);
-		return;
-	}
-
-	BUG_ON(old_mode != XEN_LAZY_NONE);
+	BUG_ON(this_cpu_read(xen_lazy_mode) != XEN_LAZY_NONE);
 
 	this_cpu_write(xen_lazy_mode, mode);
 }
@@ -92,10 +84,7 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
 {
 	BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
 
-	if (this_cpu_read(xen_lazy_nesting) == 0)
-		this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
-	else
-		this_cpu_dec(xen_lazy_nesting);
+	this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
 }
 
 enum xen_lazy_mode xen_get_lazy_mode(void);
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index baca0b00ef76..a078a2b0f032 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -72,7 +72,7 @@
 #endif
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* Explicitly size integers that represent pfns in the public interface
  * with Xen so that on ARM we can have one ABI that works for 32 and 64
  * bit guests. */
@@ -137,7 +137,7 @@ DEFINE_GUEST_HANDLE(xen_ulong_t);
 #define TI_SET_DPL(_ti, _dpl)	((_ti)->flags |= (_dpl))
 #define TI_SET_IF(_ti, _if)	((_ti)->flags |= ((!!(_if))<<2))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct trap_info {
     uint8_t       vector;  /* exception vector                              */
     uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
@@ -186,7 +186,7 @@ struct arch_shared_info {
 	uint32_t wc_sec_hi;
 #endif
 };
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #ifdef CONFIG_X86_32
 #include <asm/xen/interface_32.h>
@@ -196,7 +196,7 @@ struct arch_shared_info {
 
 #include <asm/pvclock-abi.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
@@ -376,7 +376,7 @@ struct xen_pmu_arch {
 	} c;
 };
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 /*
  * Prefix forces emulation of some non-trapping instructions.
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index dc40578abded..74d9768a9cf7 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -44,7 +44,7 @@
  */
 #define __HYPERVISOR_VIRT_START 0xF5800000
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct cpu_user_regs {
     uint32_t ebx;
@@ -85,7 +85,7 @@ typedef struct xen_callback xen_callback_t;
 
 #define XEN_CALLBACK(__cs, __eip)				\
 	((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 
 /*
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index c10f279aae93..38a19edb81a3 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -77,7 +77,7 @@
 #define VGCF_in_syscall  (1<<_VGCF_in_syscall)
 #define VGCF_IN_SYSCALL  VGCF_in_syscall
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct iret_context {
     /* Top of stack (%rsp at point of hypercall). */
@@ -143,7 +143,7 @@ typedef unsigned long xen_callback_t;
 #define XEN_CALLBACK(__cs, __rip)				\
 	((unsigned long)(__rip))
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 
 #endif /* _ASM_X86_XEN_INTERFACE_64_H */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9b82eebd7add..dafbf581c515 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -26,7 +26,7 @@
 #define XLF_5LEVEL_ENABLED		(1<<6)
 #define XLF_MEM_ENCRYPTION		(1<<7)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/screen_info.h>
@@ -210,6 +210,6 @@ enum x86_hardware_subarch {
 	X86_NR_SUBARCHS,
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_BOOTPARAM_H */
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 2f491efe3a12..55bc66867156 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -54,7 +54,7 @@
  */
 #define E820_RESERVED_KERN        128
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 struct e820entry {
 	__u64 addr;	/* start of memory segment */
@@ -76,7 +76,7 @@ struct e820map {
 #define BIOS_ROM_BASE		0xffe00000
 #define BIOS_ROM_END		0xffffffff
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #endif /* _UAPI_ASM_X86_E820_H */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 9e75da97bce0..460306b35a4b 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -559,6 +559,9 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA	(1 << 8)
 
+#define KVM_XEN_MSR_MIN_INDEX			0x40000000u
+#define KVM_XEN_MSR_MAX_INDEX			0x4fffffffu
+
 struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index d62ac5db093b..a82c039d8e6a 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -12,7 +12,7 @@
 /* The size of each LDT entry. */
 #define LDT_ENTRY_SIZE	8
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
  * not to the default values if you still want to do syscalls. This
@@ -44,5 +44,5 @@ struct user_desc {
 #define MODIFY_LDT_CONTENTS_STACK	1
 #define MODIFY_LDT_CONTENTS_CODE	2
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_LDT_H */
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index e7516b402a00..4b8917ca28fe 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_MSR_H
 #define _UAPI_ASM_X86_MSR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
@@ -10,5 +10,5 @@
 #define X86_IOC_RDMSR_REGS	_IOWR('c', 0xA0, __u32[8])
 #define X86_IOC_WRMSR_REGS	_IOWR('c', 0xA1, __u32[8])
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _UAPI_ASM_X86_MSR_H */
diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h
index 16074b9c93bb..5823584dea13 100644
--- a/arch/x86/include/uapi/asm/ptrace-abi.h
+++ b/arch/x86/include/uapi/asm/ptrace-abi.h
@@ -25,7 +25,7 @@
 
 #else /* __i386__ */
 
-#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#if defined(__ASSEMBLER__) || defined(__FRAME_OFFSETS)
 /*
  * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
  * unless syscall needs a complete, fully filled "struct pt_regs".
@@ -57,7 +57,7 @@
 #define EFLAGS 144
 #define RSP 152
 #define SS 160
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* top of stack page */
 #define FRAME_SIZE 168
@@ -87,7 +87,7 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #endif
 
diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h
index 85165c0edafc..e0b5b4f6226b 100644
--- a/arch/x86/include/uapi/asm/ptrace.h
+++ b/arch/x86/include/uapi/asm/ptrace.h
@@ -7,7 +7,7 @@
 #include <asm/processor-flags.h>
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef __i386__
 /* this struct defines the way the registers are stored on the
@@ -81,6 +81,6 @@ struct pt_regs {
 
 
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
index b111b0c18544..50c45ead4e7c 100644
--- a/arch/x86/include/uapi/asm/setup_data.h
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -18,7 +18,7 @@
 #define SETUP_INDIRECT			(1<<31)
 #define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -78,6 +78,6 @@ struct ima_setup_data {
 	__u64 size;
 } __attribute__((packed));
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h
index f777346450ec..1067efabf18b 100644
--- a/arch/x86/include/uapi/asm/signal.h
+++ b/arch/x86/include/uapi/asm/signal.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_SIGNAL_H
 #define _UAPI_ASM_X86_SIGNAL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -16,7 +16,7 @@ struct siginfo;
 typedef unsigned long sigset_t;
 
 #endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #define SIGHUP		 1
@@ -68,7 +68,7 @@ typedef unsigned long sigset_t;
 
 #include <asm-generic/signal-defs.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 
 # ifndef __KERNEL__
@@ -106,6 +106,6 @@ typedef struct sigaltstack {
 	__kernel_size_t ss_size;
 } stack_t;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SIGNAL_H */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 1814b413fd57..ec1321248dac 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
 #define SVM_EXIT_CR14_WRITE_TRAP		0x09e
 #define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
+#define SVM_EXIT_IDLE_HLT      0x0a6
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
@@ -224,6 +225,7 @@
 	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
 	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
+	{ SVM_EXIT_IDLE_HLT,     "idle-halt" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b43eb7e384eb..99a783fd4691 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,8 @@ KCOV_INSTRUMENT_unwind_orc.o				:= n
 KCOV_INSTRUMENT_unwind_frame.o				:= n
 KCOV_INSTRUMENT_unwind_guess.o				:= n
 
+CFLAGS_head32.o := -fno-stack-protector
+CFLAGS_head64.o := -fno-stack-protector
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
 
 obj-y			+= head_$(BITS).o
@@ -139,7 +141,6 @@ obj-$(CONFIG_OF)			+= devicetree.o
 obj-$(CONFIG_UPROBES)			+= uprobes.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
-obj-$(CONFIG_TRACING)			+= tracepoint.o
 obj-$(CONFIG_SCHED_MC_PRIO)		+= itmt.o
 obj-$(CONFIG_X86_UMIP)			+= umip.o
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dae6a73be40e..9fa321a95eb3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -23,6 +23,8 @@
 #include <linux/serial_core.h>
 #include <linux/pgtable.h>
 
+#include <xen/xen.h>
+
 #include <asm/e820/api.h>
 #include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
@@ -1729,6 +1731,15 @@ int __init acpi_mps_check(void)
 {
 #if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE)
 /* mptable code is not built-in*/
+
+	/*
+	 * Xen disables ACPI in PV DomU guests but it still emulates APIC and
+	 * supports SMP. Returning early here ensures that APIC is not disabled
+	 * unnecessarily and the guest is not limited to a single vCPU.
+	 */
+	if (xen_pv_domain() && !xen_initial_domain())
+		return 0;
+
 	if (acpi_disabled || acpi_noirq) {
 		pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n");
 		return 1;
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index d745dd586303..7047124490f6 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -4,6 +4,8 @@
  * Copyright (c) 2016, Intel Corporation.
  */
 
+#include <linux/bitfield.h>
+
 #include <acpi/cppc_acpi.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
@@ -47,7 +49,7 @@ int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
 {
 	int err;
 
-	err = rdmsrl_safe_on_cpu(cpunum, reg->address, val);
+	err = rdmsrq_safe_on_cpu(cpunum, reg->address, val);
 	if (!err) {
 		u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
 				       reg->bit_offset);
@@ -63,7 +65,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 	u64 rd_val;
 	int err;
 
-	err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val);
+	err = rdmsrq_safe_on_cpu(cpunum, reg->address, &rd_val);
 	if (!err) {
 		u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
 				       reg->bit_offset);
@@ -72,7 +74,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 		val &= mask;
 		rd_val &= ~mask;
 		rd_val |= val;
-		err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val);
+		err = wrmsrq_safe_on_cpu(cpunum, reg->address, rd_val);
 	}
 	return err;
 }
@@ -145,11 +147,11 @@ int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
 	int ret;
 
 	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
+		ret = rdmsrq_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
 		if (ret)
 			goto out;
 
-		val = AMD_CPPC_HIGHEST_PERF(val);
+		val = FIELD_GET(AMD_CPPC_HIGHEST_PERF_MASK, val);
 	} else {
 		ret = cppc_get_highest_perf(cpu, &val);
 		if (ret)
@@ -270,7 +272,7 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
 	}
 
 	/* detect if running on heterogeneous design */
-	if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) {
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) {
 		switch (core_type) {
 		case TOPO_CPU_TYPE_UNKNOWN:
 			pr_warn("Undefined core type found for cpu %d\n", cpu);
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 5854f0b8f0f1..8698d66563ed 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -13,9 +13,11 @@
 #include <linux/sched.h>
 
 #include <acpi/processor.h>
-#include <asm/cpuid.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpuid/api.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -47,12 +49,11 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 	/*
 	 * On all recent Intel platforms, ARB_DISABLE is a nop.
 	 * So, set bm_control to zero to indicate that ARB_DISABLE
-	 * is not required while entering C3 type state on
-	 * P4, Core and beyond CPUs
+	 * is not required while entering C3 type state.
 	 */
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
-	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
-			flags->bm_control = 0;
+	    (c->x86 > 15 || (c->x86_vfm >= INTEL_CORE2_MEROM && c->x86_vfm <= INTEL_FAM6_LAST)))
+		flags->bm_control = 0;
 
 	if (c->x86_vendor == X86_VENDOR_CENTAUR) {
 		if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
@@ -205,6 +206,16 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
+
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
index 4e498d28cdc8..aefb9cb583ad 100644
--- a/arch/x86/kernel/acpi/madt_playdead.S
+++ b/arch/x86/kernel/acpi/madt_playdead.S
@@ -14,6 +14,7 @@
  * rsi: PGD of the identity mapping
  */
 SYM_FUNC_START(asm_acpi_mp_play_dead)
+	ANNOTATE_NOENDBR
 	/* Turn off global entries. Following CR3 write will flush them. */
 	movq	%cr4, %rdx
 	andq	$~(X86_CR4_PGE), %rdx
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index d5ef6215583b..f36f28405dcc 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -70,58 +70,6 @@ static void __init free_pgt_page(void *pgt, void *dummy)
 	return memblock_free(pgt, PAGE_SIZE);
 }
 
-/*
- * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at
- * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches
- * to the identity mapping and the function has be present at the same spot in
- * the virtual address space before and after switching page tables.
- */
-static int __init init_transition_pgtable(pgd_t *pgd)
-{
-	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
-	unsigned long vaddr, paddr;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	vaddr = (unsigned long)asm_acpi_mp_play_dead;
-	pgd += pgd_index(vaddr);
-	if (!pgd_present(*pgd)) {
-		p4d = (p4d_t *)alloc_pgt_page(NULL);
-		if (!p4d)
-			return -ENOMEM;
-		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
-	}
-	p4d = p4d_offset(pgd, vaddr);
-	if (!p4d_present(*p4d)) {
-		pud = (pud_t *)alloc_pgt_page(NULL);
-		if (!pud)
-			return -ENOMEM;
-		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
-	}
-	pud = pud_offset(p4d, vaddr);
-	if (!pud_present(*pud)) {
-		pmd = (pmd_t *)alloc_pgt_page(NULL);
-		if (!pmd)
-			return -ENOMEM;
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-	}
-	pmd = pmd_offset(pud, vaddr);
-	if (!pmd_present(*pmd)) {
-		pte = (pte_t *)alloc_pgt_page(NULL);
-		if (!pte)
-			return -ENOMEM;
-		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
-	}
-	pte = pte_offset_kernel(pmd, vaddr);
-
-	paddr = __pa(vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
-
-	return 0;
-}
-
 static int __init acpi_mp_setup_reset(u64 reset_vector)
 {
 	struct x86_mapping_info info = {
@@ -130,6 +78,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		.page_flag      = __PAGE_KERNEL_LARGE_EXEC,
 		.kernpg_flag    = _KERNPG_TABLE_NOENC,
 	};
+	unsigned long mstart, mend;
 	pgd_t *pgd;
 
 	pgd = alloc_pgt_page(NULL);
@@ -137,8 +86,6 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		return -ENOMEM;
 
 	for (int i = 0; i < nr_pfn_mapped; i++) {
-		unsigned long mstart, mend;
-
 		mstart = pfn_mapped[i].start << PAGE_SHIFT;
 		mend   = pfn_mapped[i].end << PAGE_SHIFT;
 		if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
@@ -147,14 +94,24 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		}
 	}
 
-	if (kernel_ident_mapping_init(&info, pgd,
-				      PAGE_ALIGN_DOWN(reset_vector),
-				      PAGE_ALIGN(reset_vector + 1))) {
+	mstart = PAGE_ALIGN_DOWN(reset_vector);
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}
 
-	if (init_transition_pgtable(pgd)) {
+	/*
+	 * Make sure asm_acpi_mp_play_dead() is present in the identity mapping
+	 * at the same place as in the kernel page tables.
+	 * asm_acpi_mp_play_dead() switches to the identity mapping and the
+	 * function must be present at the same spot in the virtual address space
+	 * before and after switching page tables.
+	 */
+	info.offset = __START_KERNEL_map - phys_base;
+	mstart = PAGE_ALIGN_DOWN(__pa(asm_acpi_mp_play_dead));
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 6dfecb27b846..91fa262f0e30 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
 #include <asm/hypervisor.h>
+#include <asm/msr.h>
 #include <asm/smp.h>
 
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b200a193beeb..04f561f75e99 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -17,6 +17,7 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 SYM_FUNC_START(wakeup_long64)
+	ANNOTATE_NOENDBR
 	movq	saved_magic(%rip), %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c71b575bf229..ecfe7b497cad 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1,36 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #define pr_fmt(fmt) "SMP alternatives: " fmt
 
-#include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/mmu_context.h>
 #include <linux/perf_event.h>
-#include <linux/mutex.h>
-#include <linux/list.h>
-#include <linux/stringify.h>
-#include <linux/highmem.h>
-#include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
-#include <linux/stop_machine.h>
-#include <linux/slab.h>
-#include <linux/kdebug.h>
-#include <linux/kprobes.h>
-#include <linux/mmu_context.h>
-#include <linux/bsearch.h>
-#include <linux/sync_core.h>
+#include <linux/execmem.h>
+
 #include <asm/text-patching.h>
-#include <asm/alternative.h>
-#include <asm/sections.h>
-#include <asm/mce.h>
-#include <asm/nmi.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
 #include <asm/insn.h>
-#include <asm/io.h>
-#include <asm/fixmap.h>
-#include <asm/paravirt.h>
-#include <asm/asm-prototypes.h>
-#include <asm/cfi.h>
+#include <asm/ibt.h>
+#include <asm/set_memory.h>
+#include <asm/nmi.h>
 
 int __read_mostly alternatives_patched;
 
@@ -124,6 +105,171 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
 #endif
 };
 
+#ifdef CONFIG_FINEIBT
+static bool cfi_paranoid __ro_after_init;
+#endif
+
+#ifdef CONFIG_MITIGATION_ITS
+
+#ifdef CONFIG_MODULES
+static struct module *its_mod;
+#endif
+static void *its_page;
+static unsigned int its_offset;
+
+/* Initialize a thunk with the "jmp *reg; int3" instructions. */
+static void *its_init_thunk(void *thunk, int reg)
+{
+	u8 *bytes = thunk;
+	int offset = 0;
+	int i = 0;
+
+#ifdef CONFIG_FINEIBT
+	if (cfi_paranoid) {
+		/*
+		 * When ITS uses indirect branch thunk the fineibt_paranoid
+		 * caller sequence doesn't fit in the caller site. So put the
+		 * remaining part of the sequence (<ea> + JNE) into the ITS
+		 * thunk.
+		 */
+		bytes[i++] = 0xea; /* invalid instruction */
+		bytes[i++] = 0x75; /* JNE */
+		bytes[i++] = 0xfd;
+
+		offset = 1;
+	}
+#endif
+
+	if (reg >= 8) {
+		bytes[i++] = 0x41; /* REX.B prefix */
+		reg -= 8;
+	}
+	bytes[i++] = 0xff;
+	bytes[i++] = 0xe0 + reg; /* jmp *reg */
+	bytes[i++] = 0xcc;
+
+	return thunk + offset;
+}
+
+#ifdef CONFIG_MODULES
+void its_init_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	mutex_lock(&text_mutex);
+	its_mod = mod;
+	its_page = NULL;
+}
+
+void its_fini_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	WARN_ON_ONCE(its_mod != mod);
+
+	its_mod = NULL;
+	its_page = NULL;
+	mutex_unlock(&text_mutex);
+
+	for (int i = 0; i < mod->its_num_pages; i++) {
+		void *page = mod->its_page_array[i];
+		execmem_restore_rox(page, PAGE_SIZE);
+	}
+}
+
+void its_free_mod(struct module *mod)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return;
+
+	for (int i = 0; i < mod->its_num_pages; i++) {
+		void *page = mod->its_page_array[i];
+		execmem_free(page);
+	}
+	kfree(mod->its_page_array);
+}
+#endif /* CONFIG_MODULES */
+
+static void *its_alloc(void)
+{
+	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+
+	if (!page)
+		return NULL;
+
+#ifdef CONFIG_MODULES
+	if (its_mod) {
+		void *tmp = krealloc(its_mod->its_page_array,
+				     (its_mod->its_num_pages+1) * sizeof(void *),
+				     GFP_KERNEL);
+		if (!tmp)
+			return NULL;
+
+		its_mod->its_page_array = tmp;
+		its_mod->its_page_array[its_mod->its_num_pages++] = page;
+
+		execmem_make_temp_rw(page, PAGE_SIZE);
+	}
+#endif /* CONFIG_MODULES */
+
+	return no_free_ptr(page);
+}
+
+static void *its_allocate_thunk(int reg)
+{
+	int size = 3 + (reg / 8);
+	void *thunk;
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * The ITS thunk contains an indirect jump and an int3 instruction so
+	 * its size is 3 or 4 bytes depending on the register used. If CFI
+	 * paranoid is used then 3 extra bytes are added in the ITS thunk to
+	 * complete the fineibt_paranoid caller sequence.
+	 */
+	if (cfi_paranoid)
+		size += 3;
+#endif
+
+	if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) {
+		its_page = its_alloc();
+		if (!its_page) {
+			pr_err("ITS page allocation failed\n");
+			return NULL;
+		}
+		memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE);
+		its_offset = 32;
+	}
+
+	/*
+	 * If the indirect branch instruction will be in the lower half
+	 * of a cacheline, then update the offset to reach the upper half.
+	 */
+	if ((its_offset + size - 1) % 64 < 32)
+		its_offset = ((its_offset - 1) | 0x3F) + 33;
+
+	thunk = its_page + its_offset;
+	its_offset += size;
+
+	return its_init_thunk(thunk, reg);
+}
+
+u8 *its_static_thunk(int reg)
+{
+	u8 *thunk = __x86_indirect_its_thunk_array[reg];
+
+#ifdef CONFIG_FINEIBT
+	/* Paranoid thunk starts 2 bytes before */
+	if (cfi_paranoid)
+		return thunk - 2;
+#endif
+	return thunk;
+}
+
+#endif
+
 /*
  * Nomenclature for variable names to simplify and clarify this code and ease
  * any potential staring at it:
@@ -171,13 +317,6 @@ static void add_nop(u8 *buf, unsigned int len)
 		*buf = INT3_INSN_OPCODE;
 }
 
-extern s32 __retpoline_sites[], __retpoline_sites_end[];
-extern s32 __return_sites[], __return_sites_end[];
-extern s32 __cfi_sites[], __cfi_sites_end[];
-extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
-extern s32 __smp_locks[], __smp_locks_end[];
-void text_poke_early(void *addr, const void *opcode, size_t len);
-
 /*
  * Matches NOP and NOPL, not any of the other possible NOPs.
  */
@@ -369,7 +508,7 @@ static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen,
 	}
 }
 
-void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
+void text_poke_apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
 {
 	__apply_relocation(buf, instr, instrlen, repl, repl_len);
 	optimize_nops(instr, buf, instrlen);
@@ -392,10 +531,8 @@ EXPORT_SYMBOL(BUG_func);
  * Rewrite the "call BUG_func" replacement to point to the target of the
  * indirect pv_ops call "call *disp(%ip)".
  */
-static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
-			    struct module *mod)
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
 {
-	u8 *wr_instr = module_writable_address(mod, instr);
 	void *target, *bug = &BUG_func;
 	s32 disp;
 
@@ -405,14 +542,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
 	}
 
 	if (a->instrlen != 6 ||
-	    wr_instr[0] != CALL_RIP_REL_OPCODE ||
-	    wr_instr[1] != CALL_RIP_REL_MODRM) {
+	    instr[0] != CALL_RIP_REL_OPCODE ||
+	    instr[1] != CALL_RIP_REL_MODRM) {
 		pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
 		BUG();
 	}
 
 	/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
-	disp = *(s32 *)(wr_instr + 2);
+	disp = *(s32 *)(instr + 2);
 #ifdef CONFIG_X86_64
 	/* ff 15 00 00 00 00   call   *0x0(%rip) */
 	/* target address is stored at "next instruction + disp". */
@@ -450,8 +587,7 @@ static inline u8 * instr_va(struct alt_instr *i)
  * to refetch changed I$ lines.
  */
 void __init_or_module noinline apply_alternatives(struct alt_instr *start,
-						  struct alt_instr *end,
-						  struct module *mod)
+						  struct alt_instr *end)
 {
 	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *instr, *replacement;
@@ -460,7 +596,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	DPRINTK(ALT, "alt table %px, -> %px", start, end);
 
 	/*
-	 * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+	 * KASAN_SHADOW_START is defined using
 	 * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
 	 * During the process, KASAN becomes confused seeing partial LA57
 	 * conversion and triggers a false-positive out-of-bound report.
@@ -480,7 +616,6 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
-		u8 *wr_instr, *wr_replacement;
 
 		/*
 		 * In case of nested ALTERNATIVE()s the outer alternative might
@@ -494,11 +629,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		}
 
 		instr = instr_va(a);
-		wr_instr = module_writable_address(mod, instr);
-
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		wr_replacement = module_writable_address(mod, replacement);
-
 		BUG_ON(a->instrlen > sizeof(insn_buff));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
 
@@ -509,9 +640,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			memcpy(insn_buff, wr_instr, a->instrlen);
+			memcpy(insn_buff, instr, a->instrlen);
 			optimize_nops(instr, insn_buff, a->instrlen);
-			text_poke_early(wr_instr, insn_buff, a->instrlen);
+			text_poke_early(instr, insn_buff, a->instrlen);
 			continue;
 		}
 
@@ -521,12 +652,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->flags);
 
-		memcpy(insn_buff, wr_replacement, a->replacementlen);
+		memcpy(insn_buff, replacement, a->replacementlen);
 		insn_buff_sz = a->replacementlen;
 
 		if (a->flags & ALT_FLAG_DIRECT_CALL) {
-			insn_buff_sz = alt_replace_call(instr, insn_buff, a,
-							mod);
+			insn_buff_sz = alt_replace_call(instr, insn_buff, a);
 			if (insn_buff_sz < 0)
 				continue;
 		}
@@ -534,13 +664,13 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
 			insn_buff[insn_buff_sz] = 0x90;
 
-		apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
+		text_poke_apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
 
-		DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px:   old_insn: ", instr);
+		DUMP_BYTES(ALT, instr, a->instrlen, "%px:   old_insn: ", instr);
 		DUMP_BYTES(ALT, replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);
 		DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
-		text_poke_early(wr_instr, insn_buff, insn_buff_sz);
+		text_poke_early(instr, insn_buff, insn_buff_sz);
 	}
 
 	kasan_enable_current();
@@ -590,7 +720,8 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 	return i;
 }
 
-static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes,
+			     void *call_dest, void *jmp_dest)
 {
 	u8 op = insn->opcode.bytes[0];
 	int i = 0;
@@ -611,7 +742,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
 	switch (op) {
 	case CALL_INSN_OPCODE:
 		__text_gen_insn(bytes+i, op, addr+i,
-				__x86_indirect_call_thunk_array[reg],
+				call_dest,
 				CALL_INSN_SIZE);
 		i += CALL_INSN_SIZE;
 		break;
@@ -619,7 +750,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8
 	case JMP32_INSN_OPCODE:
 clang_jcc:
 		__text_gen_insn(bytes+i, op, addr+i,
-				__x86_indirect_jump_thunk_array[reg],
+				jmp_dest,
 				JMP32_INSN_SIZE);
 		i += JMP32_INSN_SIZE;
 		break;
@@ -634,6 +765,48 @@ clang_jcc:
 	return i;
 }
 
+static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	return __emit_trampoline(addr, insn, bytes,
+				 __x86_indirect_call_thunk_array[reg],
+				 __x86_indirect_jump_thunk_array[reg]);
+}
+
+#ifdef CONFIG_MITIGATION_ITS
+static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	u8 *thunk = __x86_indirect_its_thunk_array[reg];
+	u8 *tmp = its_allocate_thunk(reg);
+
+	if (tmp)
+		thunk = tmp;
+
+	return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
+/* Check if an indirect branch is at ITS-unsafe address */
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
+		return false;
+
+	/* Indirect branch opcode is 2 or 3 bytes depending on reg */
+	addr += 1 + reg / 8;
+
+	/* Lower-half of the cacheline? */
+	return !(addr & 0x20);
+}
+#else /* CONFIG_MITIGATION_ITS */
+
+#ifdef CONFIG_FINEIBT
+static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
+{
+	return false;
+}
+#endif
+
+#endif /* CONFIG_MITIGATION_ITS */
+
 /*
  * Rewrite the compiler generated retpoline thunk calls.
  *
@@ -708,6 +881,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		bytes[i++] = 0xe8; /* LFENCE */
 	}
 
+#ifdef CONFIG_MITIGATION_ITS
+	/*
+	 * Check if the address of last byte of emitted-indirect is in
+	 * lower-half of the cacheline. Such branches need ITS mitigation.
+	 */
+	if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg))
+		return emit_its_trampoline(addr, insn, reg, bytes);
+#endif
+
 	ret = emit_indirect(op, reg, bytes + i);
 	if (ret < 0)
 		return ret;
@@ -731,20 +913,19 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 /*
  * Generated by 'objtool --retpoline'.
  */
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod)
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op1, op2;
+		u8 *dest;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -752,8 +933,19 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		op2 = insn.opcode.bytes[1];
 
 		switch (op1) {
+		case 0x70 ... 0x7f:	/* Jcc.d8 */
+			/* See cfi_paranoid. */
+			WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+			continue;
+
 		case CALL_INSN_OPCODE:
 		case JMP32_INSN_OPCODE:
+			/* Check for cfi_paranoid + ITS */
+			dest = addr + insn.length + insn.immediate.value;
+			if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) {
+				WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+				continue;
+			}
 			break;
 
 		case 0x0f: /* escape */
@@ -772,15 +964,30 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		len = patch_retpoline(addr, &insn, bytes);
 		if (len == insn.length) {
 			optimize_nops(addr, bytes, len);
-			DUMP_BYTES(RETPOLINE, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RETPOLINE, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
 
 #ifdef CONFIG_MITIGATION_RETHUNK
 
+bool cpu_wants_rethunk(void)
+{
+	return cpu_feature_enabled(X86_FEATURE_RETHUNK);
+}
+
+bool cpu_wants_rethunk_at(void *addr)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return false;
+	if (x86_return_thunk != its_return_thunk)
+		return true;
+
+	return !((unsigned long)addr & 0x20);
+}
+
 /*
  * Rewrite the compiler generated return thunk tail-calls.
  *
@@ -797,7 +1004,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	int i = 0;
 
 	/* Patch the custom return thunks... */
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk_at(addr)) {
 		i = JMP32_INSN_SIZE;
 		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
 	} else {
@@ -810,23 +1017,21 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	return i;
 }
 
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod)
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk())
 		static_call_force_reinit();
 
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -846,41 +1051,59 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 		len = patch_return(addr, &insn, bytes);
 		if (len == insn.length) {
-			DUMP_BYTES(RET, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RET, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
-#else
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
-#endif /* CONFIG_MITIGATION_RETHUNK */
+#else /* !CONFIG_MITIGATION_RETHUNK: */
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* !CONFIG_MITIGATION_RETHUNK */
 
 #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod) { }
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
+#endif /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
-static void poison_cfi(void *addr, void *wr_addr);
+__noendbr bool is_endbr(u32 *val)
+{
+	u32 endbr;
+
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return __is_endbr(endbr);
 
-static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
+Efault:
+	return false;
+}
+
+#ifdef CONFIG_FINEIBT
+
+static __noendbr bool exact_endbr(u32 *val)
 {
-	u32 endbr, poison = gen_endbr_poison();
+	u32 endbr;
 
-	if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr)))
-		return;
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return endbr == gen_endbr();
 
-	if (!is_endbr(endbr)) {
-		WARN_ON_ONCE(warn);
+Efault:
+	return false;
+}
+
+#endif
+
+static void poison_cfi(void *addr);
+
+static void __init_or_module poison_endbr(void *addr)
+{
+	u32 poison = gen_endbr_poison();
+
+	if (WARN_ON_ONCE(!is_endbr(addr)))
 		return;
-	}
 
 	DPRINTK(ENDBR, "ENDBR at: %pS (%px)", addr, addr);
 
@@ -889,7 +1112,7 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
 	 */
 	DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr);
 	DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr);
-	text_poke_early(wr_addr, &poison, 4);
+	text_poke_early(addr, &poison, 4);
 }
 
 /*
@@ -898,36 +1121,39 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
  * Seal the functions for indirect calls by clobbering the ENDBR instructions
  * and the kCFI hash value.
  */
-void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr, wr_addr, true);
+		poison_endbr(addr);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16, wr_addr - 16);
+			poison_cfi(addr - 16);
 	}
 }
 
-#else
+#else /* !CONFIG_X86_KERNEL_IBT: */
 
-void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif /* !CONFIG_X86_KERNEL_IBT */
 
 #ifdef CONFIG_CFI_AUTO_DEFAULT
-#define __CFI_DEFAULT	CFI_AUTO
+# define __CFI_DEFAULT CFI_AUTO
 #elif defined(CONFIG_CFI_CLANG)
-#define __CFI_DEFAULT	CFI_KCFI
+# define __CFI_DEFAULT CFI_KCFI
 #else
-#define __CFI_DEFAULT	CFI_OFF
+# define __CFI_DEFAULT CFI_OFF
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
 
+#ifdef CONFIG_FINEIBT_BHI
+bool cfi_bhi __ro_after_init = false;
+#endif
+
 #ifdef CONFIG_CFI_CLANG
 struct bpf_insn;
 
@@ -935,11 +1161,7 @@ struct bpf_insn;
 extern unsigned int __bpf_prog_runX(const void *ctx,
 				    const struct bpf_insn *insn);
 
-/*
- * Force a reference to the external symbol so the compiler generates
- * __kcfi_typid.
- */
-__ADDRESSABLE(__bpf_prog_runX);
+KCFI_REFERENCE(__bpf_prog_runX);
 
 /* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
 asm (
@@ -956,7 +1178,7 @@ asm (
 /* Must match bpf_callback_t */
 extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
 
-__ADDRESSABLE(__bpf_callback_fn);
+KCFI_REFERENCE(__bpf_callback_fn);
 
 /* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
 asm (
@@ -991,6 +1213,21 @@ u32 cfi_get_func_hash(void *func)
 
 	return hash;
 }
+
+int cfi_get_func_arity(void *func)
+{
+	bhi_thunk *target;
+	s32 disp;
+
+	if (cfi_mode != CFI_FINEIBT && !cfi_bhi)
+		return 0;
+
+	if (get_kernel_nofault(disp, func - 4))
+		return 0;
+
+	target = func + disp;
+	return target - __bhi_args;
+}
 #endif
 
 #ifdef CONFIG_FINEIBT
@@ -1005,7 +1242,7 @@ static u32  cfi_seed __ro_after_init;
 static u32 cfi_rehash(u32 hash)
 {
 	hash ^= cfi_seed;
-	while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+	while (unlikely(__is_endbr(hash) || __is_endbr(-hash))) {
 		bool lsb = hash & 1;
 		hash >>= 1;
 		if (lsb)
@@ -1037,6 +1274,25 @@ static __init int cfi_parse_cmdline(char *str)
 			cfi_mode = CFI_FINEIBT;
 		} else if (!strcmp(str, "norand")) {
 			cfi_rand = false;
+		} else if (!strcmp(str, "warn")) {
+			pr_alert("CFI mismatch non-fatal!\n");
+			cfi_warn = true;
+		} else if (!strcmp(str, "paranoid")) {
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_paranoid = true;
+			} else {
+				pr_err("Ignoring paranoid; depends on fineibt.\n");
+			}
+		} else if (!strcmp(str, "bhi")) {
+#ifdef CONFIG_FINEIBT_BHI
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_bhi = true;
+			} else {
+				pr_err("Ignoring bhi; depends on fineibt.\n");
+			}
+#else
+			pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n");
+#endif
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}
@@ -1054,9 +1310,9 @@ early_param("cfi", cfi_parse_cmdline);
  * __cfi_\func:					__cfi_\func:
  *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
  *	nop					     subl   $0x12345678,%r10d   // 7
- *	nop					     jz     1f			// 2
- *	nop					     ud2			// 2
- *	nop					1:   nop			// 1
+ *	nop					     jne    __cfi_\func+6	// 2
+ *	nop					     nop3			// 3
+ *	nop
  *	nop
  *	nop
  *	nop
@@ -1068,34 +1324,53 @@ early_param("cfi", cfi_parse_cmdline);
  *
  * caller:					caller:
  *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
- *	addl	$-15(%r11),%r10d	 // 4	     sub    $16,%r11		// 4
+ *	addl	$-15(%r11),%r10d	 // 4	     lea    -0x10(%r11),%r11	// 4
  *	je	1f			 // 2	     nop4			// 4
  *	ud2				 // 2
- * 1:	call	__x86_indirect_thunk_r11 // 5	     call   *%r11; nop2;	// 5
+ * 1:	cs call	__x86_indirect_thunk_r11 // 6	     call   *%r11; nop3;	// 6
  *
  */
 
-asm(	".pushsection .rodata			\n"
-	"fineibt_preamble_start:		\n"
-	"	endbr64				\n"
-	"	subl	$0x12345678, %r10d	\n"
-	"	je	fineibt_preamble_end	\n"
-	"	ud2				\n"
-	"	nop				\n"
-	"fineibt_preamble_end:			\n"
+/*
+ * <fineibt_preamble_start>:
+ *  0:   f3 0f 1e fa             endbr64
+ *  4:   41 81 <ea> 78 56 34 12  sub    $0x12345678, %r10d
+ *  b:   75 f9                   jne    6 <fineibt_preamble_start+0x6>
+ *  d:   0f 1f 00                nopl   (%rax)
+ *
+ * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as
+ * (bad) on x86_64 and raises #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_preamble_start:			\n"
+	"	endbr64					\n"
+	"	subl	$0x12345678, %r10d		\n"
+	"fineibt_preamble_bhi:				\n"
+	"	jne	fineibt_preamble_start+6	\n"
+	ASM_NOP3
+	"fineibt_preamble_end:				\n"
 	".popsection\n"
 );
 
 extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_bhi[];
 extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_bhi  (fineibt_preamble_bhi - fineibt_preamble_start)
+#define fineibt_preamble_ud   6
 #define fineibt_preamble_hash 7
 
+/*
+ * <fineibt_caller_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+ *  a:   0f 1f 40 00             nopl   0x0(%rax)
+ */
 asm(	".pushsection .rodata			\n"
 	"fineibt_caller_start:			\n"
 	"	movl	$0x12345678, %r10d	\n"
-	"	sub	$16, %r11		\n"
+	"	lea	-0x10(%r11), %r11	\n"
 	ASM_NOP4
 	"fineibt_caller_end:			\n"
 	".popsection				\n"
@@ -1109,13 +1384,62 @@ extern u8 fineibt_caller_end[];
 
 #define fineibt_caller_jmp (fineibt_caller_size - 2)
 
-static u32 decode_preamble_hash(void *addr)
+/*
+ * Since FineIBT does hash validation on the callee side it is prone to
+ * circumvention attacks where a 'naked' ENDBR instruction exists that
+ * is not part of the fineibt_preamble sequence.
+ *
+ * Notably the x86 entry points must be ENDBR and equally cannot be
+ * fineibt_preamble.
+ *
+ * The fineibt_paranoid caller sequence adds additional caller side
+ * hash validation. This stops such circumvention attacks dead, but at the cost
+ * of adding a load.
+ *
+ * <fineibt_paranoid_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
+ *  a:   4d 8d 5b <f0>           lea    -0x10(%r11), %r11
+ *  e:   75 fd                   jne    d <fineibt_paranoid_start+0xd>
+ * 10:   41 ff d3                call   *%r11
+ * 13:   90                      nop
+ *
+ * Notably LEA does not modify flags and can be reordered with the CMP,
+ * avoiding a dependency. Again, using a non-taken (backwards) branch
+ * for the failure case, abusing LEA's immediate 0xf0 as LOCK prefix for the
+ * Jcc.d8, causing #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_paranoid_start:			\n"
+	"	movl	$0x12345678, %r10d		\n"
+	"	cmpl	-9(%r11), %r10d			\n"
+	"	lea	-0x10(%r11), %r11		\n"
+	"	jne	fineibt_paranoid_start+0xd	\n"
+	"fineibt_paranoid_ind:				\n"
+	"	call	*%r11				\n"
+	"	nop					\n"
+	"fineibt_paranoid_end:				\n"
+	".popsection					\n"
+);
+
+extern u8 fineibt_paranoid_start[];
+extern u8 fineibt_paranoid_ind[];
+extern u8 fineibt_paranoid_end[];
+
+#define fineibt_paranoid_size (fineibt_paranoid_end - fineibt_paranoid_start)
+#define fineibt_paranoid_ind  (fineibt_paranoid_ind - fineibt_paranoid_start)
+#define fineibt_paranoid_ud   0xd
+
+static u32 decode_preamble_hash(void *addr, int *reg)
 {
 	u8 *p = addr;
 
-	/* b8 78 56 34 12          mov    $0x12345678,%eax */
-	if (p[0] == 0xb8)
+	/* b8+reg 78 56 34 12          movl    $0x12345678,\reg */
+	if (p[0] >= 0xb8 && p[0] < 0xc0) {
+		if (reg)
+			*reg = p[0] - 0xb8;
 		return *(u32 *)(addr + 1);
+	}
 
 	return 0; /* invalid hash value */
 }
@@ -1124,11 +1448,11 @@ static u32 decode_caller_hash(void *addr)
 {
 	u8 *p = addr;
 
-	/* 41 ba 78 56 34 12       mov    $0x12345678,%r10d */
+	/* 41 ba 88 a9 cb ed       mov    $(-0x12345678),%r10d */
 	if (p[0] == 0x41 && p[1] == 0xba)
 		return -*(u32 *)(addr + 2);
 
-	/* e8 0c 78 56 34 12	   jmp.d8  +12 */
+	/* e8 0c 88 a9 cb ed	   jmp.d8  +12 */
 	if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
 		return -*(u32 *)(addr + 2);
 
@@ -1136,7 +1460,7 @@ static u32 decode_caller_hash(void *addr)
 }
 
 /* .retpoline_sites */
-static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_disable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
@@ -1148,23 +1472,20 @@ static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, jmp, 2);
+		text_poke_early(addr, jmp, 2);
 	}
 
 	return 0;
 }
 
-static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_enable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Re-enable kCFI, undo what cfi_disable_callers() did.
@@ -1174,126 +1495,230 @@ static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, mov, 2);
+		text_poke_early(addr, mov, 2);
 	}
 
 	return 0;
 }
 
 /* .cfi_sites */
-static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr, NULL);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
 		hash = cfi_rehash(hash);
-		text_poke_early(wr_addr + 1, &hash, 4);
+		text_poke_early(addr + 1, &hash, 4);
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod)
+static void cfi_fineibt_bhi_preamble(void *addr, int arity)
+{
+	if (!arity)
+		return;
+
+	if (!cfi_warn && arity == 1) {
+		/*
+		 * Crazy scheme to allow arity-1 inline:
+		 *
+		 * __cfi_foo:
+		 *  0: f3 0f 1e fa             endbr64
+		 *  4: 41 81 <ea> 78 56 34 12  sub     0x12345678, %r10d
+		 *  b: 49 0f 45 fa             cmovne  %r10, %rdi
+		 *  f: 75 f5                   jne     __cfi_foo+6
+		 * 11: 0f 1f 00                nopl    (%rax)
+		 *
+		 * Code that direct calls to foo()+0, decodes the tail end as:
+		 *
+		 * foo:
+		 *  0: f5                      cmc
+		 *  1: 0f 1f 00                nopl    (%rax)
+		 *
+		 * which clobbers CF, but does not affect anything ABI
+		 * wise.
+		 *
+		 * Notably, this scheme is incompatible with permissive CFI
+		 * because the CMOVcc is unconditional and RDI will have been
+		 * clobbered.
+		 */
+		const u8 magic[9] = {
+			0x49, 0x0f, 0x45, 0xfa,
+			0x75, 0xf5,
+			BYTES_NOP3,
+		};
+
+		text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
+
+		return;
+	}
+
+	text_poke_early(addr + fineibt_preamble_bhi,
+			text_gen_insn(CALL_INSN_OPCODE,
+				      addr + fineibt_preamble_bhi,
+				      __bhi_args[arity]),
+			CALL_INSN_SIZE);
+}
+
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
+		int arity;
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		/*
+		 * When the function doesn't start with ENDBR the compiler will
+		 * have determined there are no indirect calls to it and we
+		 * don't need no CFI either.
+		 */
+		if (!is_endbr(addr + 16))
+			continue;
+
+		hash = decode_preamble_hash(addr, &arity);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
-		text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size);
-		WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678);
-		text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4);
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
+
+		WARN_ONCE(!IS_ENABLED(CONFIG_FINEIBT_BHI) && arity,
+			  "kCFI preamble has wrong register at: %pS %*ph\n",
+			  addr, 5, addr);
+
+		if (cfi_bhi)
+			cfi_fineibt_bhi_preamble(addr, arity);
 	}
 
 	return 0;
 }
 
-static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod)
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr + 16, wr_addr + 16, false);
+		if (!exact_endbr(addr + 16))
+			continue;
+
+		poison_endbr(addr + 16);
 	}
 }
 
 /* .retpoline_sites */
-static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
 			hash = -cfi_rehash(hash);
-			text_poke_early(wr_addr + 2, &hash, 4);
+			text_poke_early(addr + 2, &hash, 4);
 		}
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
+static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes)
+{
+	u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2;
+
+#ifdef CONFIG_MITIGATION_ITS
+	u8 *tmp = its_allocate_thunk(reg);
+	if (tmp)
+		thunk = tmp;
+#endif
+
+	return __emit_trampoline(addr, insn, bytes, thunk, thunk);
+}
+
+static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
+	BUG_ON(fineibt_paranoid_size != 20);
+
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
+		struct insn insn;
+		u8 bytes[20];
 		u32 hash;
+		int ret;
+		u8 op;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-		if (hash) {
-			text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size);
-			WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678);
-			text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4);
+		hash = decode_caller_hash(addr);
+		if (!hash)
+			continue;
+
+		if (!cfi_paranoid) {
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+			/* rely on apply_retpolines() */
+			continue;
+		}
+
+		/* cfi_paranoid */
+		ret = insn_decode_kernel(&insn, addr + fineibt_caller_size);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op != CALL_INSN_OPCODE && op != JMP32_INSN_OPCODE) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
+		memcpy(bytes + fineibt_caller_hash, &hash, 4);
+
+		if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) {
+			emit_paranoid_trampoline(addr + fineibt_caller_size,
+						 &insn, 11, bytes + fineibt_caller_size);
+		} else {
+			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+			if (WARN_ON_ONCE(ret != 3))
+				continue;
 		}
-		/* rely on apply_retpolines() */
+
+		text_poke_early(addr, bytes, fineibt_paranoid_size);
 	}
 
 	return 0;
 }
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
-	bool builtin = mod ? false : true;
 	int ret;
 
 	if (WARN_ONCE(fineibt_preamble_size != 16,
@@ -1302,8 +1727,15 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	if (cfi_mode == CFI_AUTO) {
 		cfi_mode = CFI_KCFI;
-		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) {
+			/*
+			 * FRED has much saner context on exception entry and
+			 * is less easy to take advantage of.
+			 */
+			if (!cpu_feature_enabled(X86_FEATURE_FRED))
+				cfi_paranoid = true;
 			cfi_mode = CFI_FINEIBT;
+		}
 	}
 
 	/*
@@ -1311,7 +1743,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	 * rewrite them. This disables all CFI. If this succeeds but any of the
 	 * later stages fails, we're without CFI.
 	 */
-	ret = cfi_disable_callers(start_retpoline, end_retpoline, mod);
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
 	if (ret)
 		goto err;
 
@@ -1322,11 +1754,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
 		}
 
-		ret = cfi_rand_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
-		ret = cfi_rand_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rand_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 	}
@@ -1338,7 +1770,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_KCFI:
-		ret = cfi_enable_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_enable_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
@@ -1348,20 +1780,23 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	case CFI_FINEIBT:
 		/* place the FineIBT preamble at func()-16 */
-		ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
 		/* rewrite the callers to target func()-16 */
-		ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
 		/* now that nobody targets func()+0, remove ENDBR there */
-		cfi_rewrite_endbr(start_cfi, end_cfi, mod);
+		cfi_rewrite_endbr(start_cfi, end_cfi);
 
-		if (builtin)
-			pr_info("Using FineIBT CFI\n");
+		if (builtin) {
+			pr_info("Using %sFineIBT%s CFI\n",
+				cfi_paranoid ? "paranoid " : "",
+				cfi_bhi ? "+BHI" : "");
+		}
 		return;
 
 	default:
@@ -1377,11 +1812,25 @@ static inline void poison_hash(void *addr)
 	*(u32 *)addr = 0;
 }
 
-static void poison_cfi(void *addr, void *wr_addr)
+static void poison_cfi(void *addr)
 {
+	/*
+	 * Compilers manage to be inconsistent with ENDBR vs __cfi prefixes,
+	 * some (static) functions for which they can determine the address
+	 * is never taken do not get a __cfi prefix, but *DO* get an ENDBR.
+	 *
+	 * As such, these functions will get sealed, but we need to be careful
+	 * to not unconditionally scribble the previous function.
+	 */
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
 		/*
+		 * FineIBT prefix should start with an ENDBR.
+		 */
+		if (!is_endbr(addr))
+			break;
+
+		/*
 		 * __cfi_\func:
 		 *	osp nopl (%rax)
 		 *	subl	$0, %r10d
@@ -1389,17 +1838,23 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	ud2
 		 * 1:	nop
 		 */
-		poison_endbr(addr, wr_addr, false);
-		poison_hash(wr_addr + fineibt_preamble_hash);
+		poison_endbr(addr);
+		poison_hash(addr + fineibt_preamble_hash);
 		break;
 
 	case CFI_KCFI:
 		/*
+		 * kCFI prefix should start with a valid hash.
+		 */
+		if (!decode_preamble_hash(addr, NULL))
+			break;
+
+		/*
 		 * __cfi_\func:
 		 *	movl	$0, %eax
 		 *	.skip	11, 0x90
 		 */
-		poison_hash(wr_addr + 1);
+		poison_hash(addr + 1);
 		break;
 
 	default:
@@ -1407,24 +1862,172 @@ static void poison_cfi(void *addr, void *wr_addr)
 	}
 }
 
-#else
+/*
+ * When regs->ip points to a 0xEA byte in the FineIBT preamble,
+ * return true and fill out target and type.
+ *
+ * We check the preamble by checking for the ENDBR instruction relative to the
+ * 0xEA instruction.
+ */
+static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_preamble_ud;
+	u32 hash;
+
+	if (!exact_endbr((void *)addr))
+		return false;
+
+	*target = addr + fineibt_preamble_size;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	/*
+	 * Since regs->ip points to the middle of an instruction; it cannot
+	 * continue with the normal fixup.
+	 */
+	regs->ip = *target;
+
+	return true;
+
+Efault:
+	return false;
+}
+
+/*
+ * regs->ip points to one of the UD2 in __bhi_args[].
+ */
+static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr;
+	u32 hash;
+
+	if (!cfi_bhi)
+		return false;
+
+	if (regs->ip < (unsigned long)__bhi_args ||
+	    regs->ip >= (unsigned long)__bhi_args_end)
+		return false;
+
+	/*
+	 * Fetch the return address from the stack, this points to the
+	 * FineIBT preamble. Since the CALL instruction is in the 5 last
+	 * bytes of the preamble, the return address is in fact the target
+	 * address.
+	 */
+	__get_kernel_nofault(&addr, regs->sp, unsigned long, Efault);
+	*target = addr;
+
+	addr -= fineibt_preamble_size;
+	if (!exact_endbr((void *)addr))
+		return false;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	/*
+	 * The UD2 sites are constructed with a RET immediately following,
+	 * as such the non-fatal case can use the regular fixup.
+	 */
+	return true;
+
+Efault:
+	return false;
+}
+
+static bool is_paranoid_thunk(unsigned long addr)
+{
+	u32 thunk;
+
+	__get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault);
+	return (thunk & 0x00FFFFFF) == 0xfd75ea;
+
+Efault:
+	return false;
+}
+
+/*
+ * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
+ * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS
+ * thunk.
+ */
+static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_paranoid_ud;
+
+	if (!cfi_paranoid)
+		return false;
+
+	if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) {
+		*target = regs->r11 + fineibt_preamble_size;
+		*type = regs->r10;
+
+		/*
+		 * Since the trapping instruction is the exact, but LOCK prefixed,
+		 * Jcc.d8 that got us here, the normal fixup will work.
+		 */
+		return true;
+	}
+
+	/*
+	 * The cfi_paranoid + ITS thunk combination results in:
+	 *
+	 *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+	 *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
+	 *  a:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+	 *  e:   2e e8 XX XX XX XX	 cs call __x86_indirect_paranoid_thunk_r11
+	 *
+	 * Where the paranoid_thunk looks like:
+	 *
+	 *  1d:  <ea>                    (bad)
+	 *  __x86_indirect_paranoid_thunk_r11:
+	 *  1e:  75 fd                   jne 1d
+	 *  __x86_indirect_its_thunk_r11:
+	 *  20:  41 ff eb                jmp *%r11
+	 *  23:  cc                      int3
+	 *
+	 */
+	if (is_paranoid_thunk(regs->ip)) {
+		*target = regs->r11 + fineibt_preamble_size;
+		*type = regs->r10;
+
+		regs->ip = *target;
+		return true;
+	}
+
+	return false;
+}
+
+bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	if (decode_fineibt_paranoid(regs, target, type))
+		return true;
+
+	if (decode_fineibt_bhi(regs, target, type))
+		return true;
+
+	return decode_fineibt_preamble(regs, target, type);
+}
+
+#else /* !CONFIG_FINEIBT: */
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
 }
 
 #ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr) { }
+static void poison_cfi(void *addr) { }
 #endif
 
-#endif
+#endif /* !CONFIG_FINEIBT */
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 	return __apply_fineibt(start_retpoline, end_retpoline,
-			       start_cfi, end_cfi, mod);
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
 }
 
 #ifdef CONFIG_SMP
@@ -1673,7 +2276,7 @@ __visible noinline void __init __alt_reloc_selftest(void *arg)
 static noinline void __init alt_reloc_selftest(void)
 {
 	/*
-	 * Tests apply_relocation().
+	 * Tests text_poke_apply_relocation().
 	 *
 	 * This has a relative immediate (CALL) in a place other than the first
 	 * instruction and additionally on x86_64 we get a RIP-relative LEA:
@@ -1694,6 +2297,8 @@ static noinline void __init alt_reloc_selftest(void)
 
 void __init alternative_instructions(void)
 {
+	u64 ibt;
+
 	int3_selftest();
 
 	/*
@@ -1720,28 +2325,33 @@ void __init alternative_instructions(void)
 	 */
 	paravirt_set_cap();
 
+	/* Keep CET-IBT disabled until caller/callee are patched */
+	ibt = ibt_save(/*disable*/ true);
+
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
-			__cfi_sites, __cfi_sites_end, NULL);
+			__cfi_sites, __cfi_sites_end, true);
 
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.
 	 */
-	apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL);
-	apply_returns(__return_sites, __return_sites_end, NULL);
-
-	apply_alternatives(__alt_instructions, __alt_instructions_end, NULL);
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
 	/*
-	 * Now all calls are established. Apply the call thunks if
-	 * required.
+	 * Adjust all CALL instructions to point to func()-10, including
+	 * those in .altinstr_replacement.
 	 */
 	callthunks_patch_builtin_calls();
 
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
-	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL);
+	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
+
+	ibt_restore(ibt);
 
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
@@ -1803,76 +2413,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
 	}
 }
 
-typedef struct {
-	struct mm_struct *mm;
-} temp_mm_state_t;
-
-/*
- * Using a temporary mm allows to set temporary mappings that are not accessible
- * by other CPUs. Such mappings are needed to perform sensitive memory writes
- * that override the kernel memory protections (e.g., W^X), without exposing the
- * temporary page-table mappings that are required for these write operations to
- * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
- * mapping is torn down.
- *
- * Context: The temporary mm needs to be used exclusively by a single core. To
- *          harden security IRQs must be disabled while the temporary mm is
- *          loaded, thereby preventing interrupt handler bugs from overriding
- *          the kernel memory protection.
- */
-static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
-{
-	temp_mm_state_t temp_state;
-
-	lockdep_assert_irqs_disabled();
-
-	/*
-	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
-	 * with a stale address space WITHOUT being in lazy mode after
-	 * restoring the previous mm.
-	 */
-	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
-		leave_mm();
-
-	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
-	switch_mm_irqs_off(NULL, mm, current);
-
-	/*
-	 * If breakpoints are enabled, disable them while the temporary mm is
-	 * used. Userspace might set up watchpoints on addresses that are used
-	 * in the temporary mm, which would lead to wrong signals being sent or
-	 * crashes.
-	 *
-	 * Note that breakpoints are not disabled selectively, which also causes
-	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
-	 * undesirable, but still seems reasonable as the code that runs in the
-	 * temporary mm should be short.
-	 */
-	if (hw_breakpoint_active())
-		hw_breakpoint_disable();
-
-	return temp_state;
-}
-
-__ro_after_init struct mm_struct *poking_mm;
-__ro_after_init unsigned long poking_addr;
-
-static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
-{
-	lockdep_assert_irqs_disabled();
-
-	switch_mm_irqs_off(NULL, prev_state.mm, current);
-
-	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
-	cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm));
-
-	/*
-	 * Restore the breakpoints if they were disabled before the temporary mm
-	 * was loaded.
-	 */
-	if (hw_breakpoint_active())
-		hw_breakpoint_restore();
-}
+__ro_after_init struct mm_struct *text_poke_mm;
+__ro_after_init unsigned long text_poke_mm_addr;
 
 static void text_poke_memcpy(void *dst, const void *src, size_t len)
 {
@@ -1892,7 +2434,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
 {
 	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
 	struct page *pages[2] = {NULL};
-	temp_mm_state_t prev;
+	struct mm_struct *prev_mm;
 	unsigned long flags;
 	pte_t pte, *ptep;
 	spinlock_t *ptl;
@@ -1929,7 +2471,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
 	/*
 	 * The lock is not really needed, but this allows to avoid open-coding.
 	 */
-	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
 
 	/*
 	 * This must not fail; preallocated in poking_init().
@@ -1939,21 +2481,21 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
 	local_irq_save(flags);
 
 	pte = mk_pte(pages[0], pgprot);
-	set_pte_at(poking_mm, poking_addr, ptep, pte);
+	set_pte_at(text_poke_mm, text_poke_mm_addr, ptep, pte);
 
 	if (cross_page_boundary) {
 		pte = mk_pte(pages[1], pgprot);
-		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+		set_pte_at(text_poke_mm, text_poke_mm_addr + PAGE_SIZE, ptep + 1, pte);
 	}
 
 	/*
 	 * Loading the temporary mm behaves as a compiler barrier, which
 	 * guarantees that the PTE will be set at the time memcpy() is done.
 	 */
-	prev = use_temporary_mm(poking_mm);
+	prev_mm = use_temporary_mm(text_poke_mm);
 
 	kasan_disable_current();
-	func((u8 *)poking_addr + offset_in_page(addr), src, len);
+	func((u8 *)text_poke_mm_addr + offset_in_page(addr), src, len);
 	kasan_enable_current();
 
 	/*
@@ -1962,22 +2504,22 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
 	 */
 	barrier();
 
-	pte_clear(poking_mm, poking_addr, ptep);
+	pte_clear(text_poke_mm, text_poke_mm_addr, ptep);
 	if (cross_page_boundary)
-		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+		pte_clear(text_poke_mm, text_poke_mm_addr + PAGE_SIZE, ptep + 1);
 
 	/*
 	 * Loading the previous page-table hierarchy requires a serializing
 	 * instruction that already allows the core to see the updated version.
 	 * Xen-PV is assumed to serialize execution in a similar manner.
 	 */
-	unuse_temporary_mm(prev);
+	unuse_temporary_mm(prev_mm);
 
 	/*
 	 * Flushing the TLB might involve IPIs, which would require enabled
 	 * IRQs, but not if the mm is not used, as it is in this point.
 	 */
-	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+	flush_tlb_mm_range(text_poke_mm, text_poke_mm_addr, text_poke_mm_addr +
 			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
 			   PAGE_SHIFT, false);
 
@@ -2113,7 +2655,7 @@ static void do_sync_core(void *info)
 	sync_core();
 }
 
-void text_poke_sync(void)
+void smp_text_poke_sync_each_cpu(void)
 {
 	on_each_cpu(do_sync_core, NULL, 1);
 }
@@ -2123,64 +2665,66 @@ void text_poke_sync(void)
  * this thing. When len == 6 everything is prefixed with 0x0f and we map
  * opcode to Jcc.d8, using len to distinguish.
  */
-struct text_poke_loc {
+struct smp_text_poke_loc {
 	/* addr := _stext + rel_addr */
 	s32 rel_addr;
 	s32 disp;
 	u8 len;
 	u8 opcode;
-	const u8 text[POKE_MAX_OPCODE_SIZE];
-	/* see text_poke_bp_batch() */
+	const u8 text[TEXT_POKE_MAX_OPCODE_SIZE];
+	/* see smp_text_poke_batch_finish() */
 	u8 old;
 };
 
-struct bp_patching_desc {
-	struct text_poke_loc *vec;
+#define TEXT_POKE_ARRAY_MAX (PAGE_SIZE / sizeof(struct smp_text_poke_loc))
+
+static struct smp_text_poke_array {
+	struct smp_text_poke_loc vec[TEXT_POKE_ARRAY_MAX];
 	int nr_entries;
-	atomic_t refs;
-};
+} text_poke_array;
 
-static struct bp_patching_desc bp_desc;
+static DEFINE_PER_CPU(atomic_t, text_poke_array_refs);
 
-static __always_inline
-struct bp_patching_desc *try_get_desc(void)
+/*
+ * These four __always_inline annotations imply noinstr, necessary
+ * due to smp_text_poke_int3_handler() being noinstr:
+ */
+
+static __always_inline bool try_get_text_poke_array(void)
 {
-	struct bp_patching_desc *desc = &bp_desc;
+	atomic_t *refs = this_cpu_ptr(&text_poke_array_refs);
 
-	if (!raw_atomic_inc_not_zero(&desc->refs))
-		return NULL;
+	if (!raw_atomic_inc_not_zero(refs))
+		return false;
 
-	return desc;
+	return true;
 }
 
-static __always_inline void put_desc(void)
+static __always_inline void put_text_poke_array(void)
 {
-	struct bp_patching_desc *desc = &bp_desc;
+	atomic_t *refs = this_cpu_ptr(&text_poke_array_refs);
 
 	smp_mb__before_atomic();
-	raw_atomic_dec(&desc->refs);
+	raw_atomic_dec(refs);
 }
 
-static __always_inline void *text_poke_addr(struct text_poke_loc *tp)
+static __always_inline void *text_poke_addr(const struct smp_text_poke_loc *tpl)
 {
-	return _stext + tp->rel_addr;
+	return _stext + tpl->rel_addr;
 }
 
-static __always_inline int patch_cmp(const void *key, const void *elt)
+static __always_inline int patch_cmp(const void *tpl_a, const void *tpl_b)
 {
-	struct text_poke_loc *tp = (struct text_poke_loc *) elt;
-
-	if (key < text_poke_addr(tp))
+	if (tpl_a < text_poke_addr(tpl_b))
 		return -1;
-	if (key > text_poke_addr(tp))
+	if (tpl_a > text_poke_addr(tpl_b))
 		return 1;
 	return 0;
 }
 
-noinstr int poke_int3_handler(struct pt_regs *regs)
+noinstr int smp_text_poke_int3_handler(struct pt_regs *regs)
 {
-	struct bp_patching_desc *desc;
-	struct text_poke_loc *tp;
+	struct smp_text_poke_loc *tpl;
 	int ret = 0;
 	void *ip;
 
@@ -2189,41 +2733,40 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_desc with non-zero refcount:
+	 * text_poke_array with non-zero refcount:
 	 *
-	 *	bp_desc.refs = 1		INT3
-	 *	WMB				RMB
-	 *	write INT3			if (bp_desc.refs != 0)
+	 *	text_poke_array_refs = 1		INT3
+	 *	WMB			RMB
+	 *	write INT3		if (text_poke_array_refs != 0)
 	 */
 	smp_rmb();
 
-	desc = try_get_desc();
-	if (!desc)
+	if (!try_get_text_poke_array())
 		return 0;
 
 	/*
-	 * Discount the INT3. See text_poke_bp_batch().
+	 * Discount the INT3. See smp_text_poke_batch_finish().
 	 */
 	ip = (void *) regs->ip - INT3_INSN_SIZE;
 
 	/*
 	 * Skip the binary search if there is a single member in the vector.
 	 */
-	if (unlikely(desc->nr_entries > 1)) {
-		tp = __inline_bsearch(ip, desc->vec, desc->nr_entries,
-				      sizeof(struct text_poke_loc),
+	if (unlikely(text_poke_array.nr_entries > 1)) {
+		tpl = __inline_bsearch(ip, text_poke_array.vec, text_poke_array.nr_entries,
+				      sizeof(struct smp_text_poke_loc),
 				      patch_cmp);
-		if (!tp)
+		if (!tpl)
 			goto out_put;
 	} else {
-		tp = desc->vec;
-		if (text_poke_addr(tp) != ip)
+		tpl = text_poke_array.vec;
+		if (text_poke_addr(tpl) != ip)
 			goto out_put;
 	}
 
-	ip += tp->len;
+	ip += tpl->len;
 
-	switch (tp->opcode) {
+	switch (tpl->opcode) {
 	case INT3_INSN_OPCODE:
 		/*
 		 * Someone poked an explicit INT3, they'll want to handle it,
@@ -2236,16 +2779,16 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 		break;
 
 	case CALL_INSN_OPCODE:
-		int3_emulate_call(regs, (long)ip + tp->disp);
+		int3_emulate_call(regs, (long)ip + tpl->disp);
 		break;
 
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		int3_emulate_jmp(regs, (long)ip + tp->disp);
+		int3_emulate_jmp(regs, (long)ip + tpl->disp);
 		break;
 
 	case 0x70 ... 0x7f: /* Jcc */
-		int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp);
+		int3_emulate_jcc(regs, tpl->opcode & 0xf, (long)ip, tpl->disp);
 		break;
 
 	default:
@@ -2255,51 +2798,50 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 	ret = 1;
 
 out_put:
-	put_desc();
+	put_text_poke_array();
 	return ret;
 }
 
-#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
-static struct text_poke_loc tp_vec[TP_VEC_MAX];
-static int tp_vec_nr;
-
 /**
- * text_poke_bp_batch() -- update instructions on live kernel on SMP
- * @tp:			vector of instructions to patch
- * @nr_entries:		number of entries in the vector
+ * smp_text_poke_batch_finish() -- update instructions on live kernel on SMP
+ *
+ * Input state:
+ *  text_poke_array.vec: vector of instructions to patch
+ *  text_poke_array.nr_entries: number of entries in the vector
  *
- * Modify multi-byte instruction by using int3 breakpoint on SMP.
- * We completely avoid stop_machine() here, and achieve the
- * synchronization using int3 breakpoint.
+ * Modify multi-byte instructions by using INT3 breakpoints on SMP.
+ * We completely avoid using stop_machine() here, and achieve the
+ * synchronization using INT3 breakpoints and SMP cross-calls.
  *
  * The way it is done:
  *	- For each entry in the vector:
- *		- add a int3 trap to the address that will be patched
- *	- sync cores
+ *		- add an INT3 trap to the address that will be patched
+ *	- SMP sync all CPUs
  *	- For each entry in the vector:
  *		- update all but the first byte of the patched range
- *	- sync cores
+ *	- SMP sync all CPUs
  *	- For each entry in the vector:
- *		- replace the first byte (int3) by the first byte of
+ *		- replace the first byte (INT3) by the first byte of the
  *		  replacing opcode
- *	- sync cores
+ *	- SMP sync all CPUs
  */
-static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
+void smp_text_poke_batch_finish(void)
 {
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
-	lockdep_assert_held(&text_mutex);
+	if (!text_poke_array.nr_entries)
+		return;
 
-	bp_desc.vec = tp;
-	bp_desc.nr_entries = nr_entries;
+	lockdep_assert_held(&text_mutex);
 
 	/*
-	 * Corresponds to the implicit memory barrier in try_get_desc() to
-	 * ensure reading a non-zero refcount provides up to date bp_desc data.
+	 * Corresponds to the implicit memory barrier in try_get_text_poke_array() to
+	 * ensure reading a non-zero refcount provides up to date text_poke_array data.
 	 */
-	atomic_set_release(&bp_desc.refs, 1);
+	for_each_possible_cpu(i)
+		atomic_set_release(per_cpu_ptr(&text_poke_array_refs, i), 1);
 
 	/*
 	 * Function tracing can enable thousands of places that need to be
@@ -2312,33 +2854,33 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	cond_resched();
 
 	/*
-	 * Corresponding read barrier in int3 notifier for making sure the
-	 * nr_entries and handler are correctly ordered wrt. patching.
+	 * Corresponding read barrier in INT3 notifier for making sure the
+	 * text_poke_array.nr_entries and handler are correctly ordered wrt. patching.
 	 */
 	smp_wmb();
 
 	/*
-	 * First step: add a int3 trap to the address that will be patched.
+	 * First step: add a INT3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++) {
-		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
-		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	for (i = 0; i < text_poke_array.nr_entries; i++) {
+		text_poke_array.vec[i].old = *(u8 *)text_poke_addr(&text_poke_array.vec[i]);
+		text_poke(text_poke_addr(&text_poke_array.vec[i]), &int3, INT3_INSN_SIZE);
 	}
 
-	text_poke_sync();
+	smp_text_poke_sync_each_cpu();
 
 	/*
 	 * Second step: update all but the first byte of the patched range.
 	 */
-	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, };
-		u8 _new[POKE_MAX_OPCODE_SIZE+1];
-		const u8 *new = tp[i].text;
-		int len = tp[i].len;
+	for (do_sync = 0, i = 0; i < text_poke_array.nr_entries; i++) {
+		u8 old[TEXT_POKE_MAX_OPCODE_SIZE+1] = { text_poke_array.vec[i].old, };
+		u8 _new[TEXT_POKE_MAX_OPCODE_SIZE+1];
+		const u8 *new = text_poke_array.vec[i].text;
+		int len = text_poke_array.vec[i].len;
 
 		if (len - INT3_INSN_SIZE > 0) {
 			memcpy(old + INT3_INSN_SIZE,
-			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       text_poke_addr(&text_poke_array.vec[i]) + INT3_INSN_SIZE,
 			       len - INT3_INSN_SIZE);
 
 			if (len == 6) {
@@ -2347,7 +2889,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 				new = _new;
 			}
 
-			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			text_poke(text_poke_addr(&text_poke_array.vec[i]) + INT3_INSN_SIZE,
 				  new + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 
@@ -2378,7 +2920,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 		 * The old instruction is recorded so that the event can be
 		 * processed forwards or backwards.
 		 */
-		perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len);
+		perf_event_text_poke(text_poke_addr(&text_poke_array.vec[i]), old, len, new, len);
 	}
 
 	if (do_sync) {
@@ -2387,63 +2929,79 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 		 * not necessary and we'd be safe even without it. But
 		 * better safe than sorry (plus there's not only Intel).
 		 */
-		text_poke_sync();
+		smp_text_poke_sync_each_cpu();
 	}
 
 	/*
-	 * Third step: replace the first byte (int3) by the first byte of
+	 * Third step: replace the first byte (INT3) by the first byte of the
 	 * replacing opcode.
 	 */
-	for (do_sync = 0, i = 0; i < nr_entries; i++) {
-		u8 byte = tp[i].text[0];
+	for (do_sync = 0, i = 0; i < text_poke_array.nr_entries; i++) {
+		u8 byte = text_poke_array.vec[i].text[0];
 
-		if (tp[i].len == 6)
+		if (text_poke_array.vec[i].len == 6)
 			byte = 0x0f;
 
 		if (byte == INT3_INSN_OPCODE)
 			continue;
 
-		text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE);
+		text_poke(text_poke_addr(&text_poke_array.vec[i]), &byte, INT3_INSN_SIZE);
 		do_sync++;
 	}
 
 	if (do_sync)
-		text_poke_sync();
+		smp_text_poke_sync_each_cpu();
 
 	/*
 	 * Remove and wait for refs to be zero.
+	 *
+	 * Notably, if after step-3 above the INT3 got removed, then the
+	 * smp_text_poke_sync_each_cpu() will have serialized against any running INT3
+	 * handlers and the below spin-wait will not happen.
+	 *
+	 * IOW. unless the replacement instruction is INT3, this case goes
+	 * unused.
 	 */
-	if (!atomic_dec_and_test(&bp_desc.refs))
-		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
+	for_each_possible_cpu(i) {
+		atomic_t *refs = per_cpu_ptr(&text_poke_array_refs, i);
+
+		if (unlikely(!atomic_dec_and_test(refs)))
+			atomic_cond_read_acquire(refs, !VAL);
+	}
+
+	/* They are all completed: */
+	text_poke_array.nr_entries = 0;
 }
 
-static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
-			       const void *opcode, size_t len, const void *emulate)
+static void __smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate)
 {
+	struct smp_text_poke_loc *tpl;
 	struct insn insn;
 	int ret, i = 0;
 
+	tpl = &text_poke_array.vec[text_poke_array.nr_entries++];
+
 	if (len == 6)
 		i = 1;
-	memcpy((void *)tp->text, opcode+i, len-i);
+	memcpy((void *)tpl->text, opcode+i, len-i);
 	if (!emulate)
 		emulate = opcode;
 
 	ret = insn_decode_kernel(&insn, emulate);
 	BUG_ON(ret < 0);
 
-	tp->rel_addr = addr - (void *)_stext;
-	tp->len = len;
-	tp->opcode = insn.opcode.bytes[0];
+	tpl->rel_addr = addr - (void *)_stext;
+	tpl->len = len;
+	tpl->opcode = insn.opcode.bytes[0];
 
 	if (is_jcc32(&insn)) {
 		/*
 		 * Map Jcc.d32 onto Jcc.d8 and use len to distinguish.
 		 */
-		tp->opcode = insn.opcode.bytes[1] - 0x10;
+		tpl->opcode = insn.opcode.bytes[1] - 0x10;
 	}
 
-	switch (tp->opcode) {
+	switch (tpl->opcode) {
 	case RET_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
@@ -2452,14 +3010,14 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 		 * next instruction can be padded with INT3.
 		 */
 		for (i = insn.length; i < len; i++)
-			BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
+			BUG_ON(tpl->text[i] != INT3_INSN_OPCODE);
 		break;
 
 	default:
 		BUG_ON(len != insn.length);
 	}
 
-	switch (tp->opcode) {
+	switch (tpl->opcode) {
 	case INT3_INSN_OPCODE:
 	case RET_INSN_OPCODE:
 		break;
@@ -2468,21 +3026,21 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
 	case 0x70 ... 0x7f: /* Jcc */
-		tp->disp = insn.immediate.value;
+		tpl->disp = insn.immediate.value;
 		break;
 
 	default: /* assume NOP */
 		switch (len) {
 		case 2: /* NOP2 -- emulate as JMP8+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
-			tp->opcode = JMP8_INSN_OPCODE;
-			tp->disp = 0;
+			tpl->opcode = JMP8_INSN_OPCODE;
+			tpl->disp = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
-			tp->opcode = JMP32_INSN_OPCODE;
-			tp->disp = 0;
+			tpl->opcode = JMP32_INSN_OPCODE;
+			tpl->disp = 0;
 			break;
 
 		default: /* unknown instruction */
@@ -2493,51 +3051,50 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 }
 
 /*
- * We hard rely on the tp_vec being ordered; ensure this is so by flushing
+ * We hard rely on the text_poke_array.vec being ordered; ensure this is so by flushing
  * early if needed.
  */
-static bool tp_order_fail(void *addr)
+static bool text_poke_addr_ordered(void *addr)
 {
-	struct text_poke_loc *tp;
+	WARN_ON_ONCE(!addr);
 
-	if (!tp_vec_nr)
-		return false;
-
-	if (!addr) /* force */
-		return true;
-
-	tp = &tp_vec[tp_vec_nr - 1];
-	if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr)
+	if (!text_poke_array.nr_entries)
 		return true;
 
-	return false;
-}
-
-static void text_poke_flush(void *addr)
-{
-	if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) {
-		text_poke_bp_batch(tp_vec, tp_vec_nr);
-		tp_vec_nr = 0;
-	}
-}
+	/*
+	 * If the last current entry's address is higher than the
+	 * new entry's address we'd like to add, then ordering
+	 * is violated and we must first flush all pending patching
+	 * requests:
+	 */
+	if (text_poke_addr(text_poke_array.vec + text_poke_array.nr_entries-1) > addr)
+		return false;
 
-void text_poke_finish(void)
-{
-	text_poke_flush(NULL);
+	return true;
 }
 
-void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
+/**
+ * smp_text_poke_batch_add() -- update instruction on live kernel on SMP, batched
+ * @addr:	address to patch
+ * @opcode:	opcode of new instruction
+ * @len:	length to copy
+ * @emulate:	instruction to be emulated
+ *
+ * Add a new instruction to the current queue of to-be-patched instructions
+ * the kernel maintains. The patching request will not be executed immediately,
+ * but becomes part of an array of patching requests, optimized for batched
+ * execution. All pending patching requests will be executed on the next
+ * smp_text_poke_batch_finish() call.
+ */
+void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	struct text_poke_loc *tp;
-
-	text_poke_flush(addr);
-
-	tp = &tp_vec[tp_vec_nr++];
-	text_poke_loc_init(tp, addr, opcode, len, emulate);
+	if (text_poke_array.nr_entries == TEXT_POKE_ARRAY_MAX || !text_poke_addr_ordered(addr))
+		smp_text_poke_batch_finish();
+	__smp_text_poke_batch_add(addr, opcode, len, emulate);
 }
 
 /**
- * text_poke_bp() -- update instructions on live kernel on SMP
+ * smp_text_poke_single() -- update instruction on live kernel on SMP immediately
  * @addr:	address to patch
  * @opcode:	opcode of new instruction
  * @len:	length to copy
@@ -2545,12 +3102,11 @@ void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const voi
  *
  * Update a single instruction with the vector in the stack, avoiding
  * dynamically allocated memory. This function should be used when it is
- * not possible to allocate memory.
+ * not possible to allocate memory for a vector. The single instruction
+ * is patched in immediately.
  */
-void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
+void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	struct text_poke_loc tp;
-
-	text_poke_loc_init(&tp, addr, opcode, len, emulate);
-	text_poke_bp_batch(&tp, 1);
+	__smp_text_poke_batch_add(addr, opcode, len, emulate);
+	smp_text_poke_batch_finish();
 }
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index c884deca839b..3485d419c2f5 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -39,7 +39,7 @@
 #include <asm/gart.h>
 #include <asm/set_memory.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/x86_init.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 11fac09e3a8c..c1acead6227a 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -13,7 +13,9 @@
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/pci_ids.h>
-#include <asm/amd_nb.h>
+
+#include <asm/amd/nb.h>
+#include <asm/cpuid/api.h>
 
 static u32 *flush_words;
 
@@ -73,7 +75,6 @@ static int amd_cache_northbridges(void)
 	amd_northbridges.nb = nb;
 
 	for (i = 0; i < amd_northbridges.num; i++) {
-		node_to_amd_nb(i)->root = amd_node_get_root(i);
 		node_to_amd_nb(i)->misc = amd_node_get_func(i, 3);
 
 		/*
@@ -92,10 +93,7 @@ static int amd_cache_northbridges(void)
 	if (amd_gart_present())
 		amd_northbridges.flags |= AMD_NB_GART;
 
-	/*
-	 * Check for L3 cache presence.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return 0;
 
 	/*
@@ -143,7 +141,6 @@ bool __init early_is_amd_nb(u32 device)
 
 struct resource *amd_get_mmconfig_range(struct resource *res)
 {
-	u32 address;
 	u64 base, msr;
 	unsigned int segn_busn_bits;
 
@@ -151,13 +148,11 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return NULL;
 
-	/* assume all cpus from fam10h have mmconfig */
-	if (boot_cpu_data.x86 < 0x10)
+	/* Assume CPUs from Fam10h have mmconfig, although not all VMs do */
+	if (boot_cpu_data.x86 < 0x10 ||
+	    rdmsrq_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
 		return NULL;
 
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
 	/* mmconfig is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;
diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index d2ec7fd555c5..a40176b62eb5 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -8,7 +8,8 @@
  * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
  */
 
-#include <asm/amd_node.h>
+#include <linux/debugfs.h>
+#include <asm/amd/node.h>
 
 /*
  * AMD Nodes are a physical collection of I/O devices within an SoC. There can be one
@@ -93,10 +94,14 @@ static struct pci_dev **amd_roots;
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
+static bool smn_exclusive;
 
 #define SMN_INDEX_OFFSET	0x60
 #define SMN_DATA_OFFSET		0x64
 
+#define HSMP_INDEX_OFFSET	0xc4
+#define HSMP_DATA_OFFSET	0xc8
+
 /*
  * SMN accesses may fail in ways that are difficult to detect here in the called
  * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do
@@ -146,6 +151,9 @@ static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, b
 	if (!root)
 		return err;
 
+	if (!smn_exclusive)
+		return err;
+
 	guard(mutex)(&smn_mutex);
 
 	err = pci_write_config_dword(root, i_off, address);
@@ -179,6 +187,93 @@ int __must_check amd_smn_write(u16 node, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(amd_smn_write);
 
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return __amd_smn_rw(HSMP_INDEX_OFFSET, HSMP_DATA_OFFSET, node, address, value, write);
+}
+EXPORT_SYMBOL_GPL(amd_smn_hsmp_rdwr);
+
+static struct dentry *debugfs_dir;
+static u16 debug_node;
+static u32 debug_address;
+
+static ssize_t smn_node_write(struct file *file, const char __user *userbuf,
+			      size_t count, loff_t *ppos)
+{
+	u16 node;
+	int ret;
+
+	ret = kstrtou16_from_user(userbuf, count, 0, &node);
+	if (ret)
+		return ret;
+
+	if (node >= amd_num_nodes())
+		return -ENODEV;
+
+	debug_node = node;
+	return count;
+}
+
+static int smn_node_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_node);
+	return 0;
+}
+
+static ssize_t smn_address_write(struct file *file, const char __user *userbuf,
+				 size_t count, loff_t *ppos)
+{
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &debug_address);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static int smn_address_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_address);
+	return 0;
+}
+
+static int smn_value_show(struct seq_file *m, void *v)
+{
+	u32 val;
+	int ret;
+
+	ret = amd_smn_read(debug_node, debug_address, &val);
+	if (ret)
+		return ret;
+
+	seq_printf(m, "0x%08x\n", val);
+	return 0;
+}
+
+static ssize_t smn_value_write(struct file *file, const char __user *userbuf,
+			       size_t count, loff_t *ppos)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &val);
+	if (ret)
+		return ret;
+
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+	ret = amd_smn_write(debug_node, debug_address, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_node);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_address);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_value);
+
 static int amd_cache_roots(void)
 {
 	u16 node, num_nodes = amd_num_nodes();
@@ -193,6 +288,48 @@ static int amd_cache_roots(void)
 	return 0;
 }
 
+static int reserve_root_config_spaces(void)
+{
+	struct pci_dev *root = NULL;
+	struct pci_bus *bus = NULL;
+
+	while ((bus = pci_find_next_bus(bus))) {
+		/* Root device is Device 0 Function 0 on each Primary Bus. */
+		root = pci_get_slot(bus, 0);
+		if (!root)
+			continue;
+
+		if (root->vendor != PCI_VENDOR_ID_AMD &&
+		    root->vendor != PCI_VENDOR_ID_HYGON)
+			continue;
+
+		pci_dbg(root, "Reserving PCI config space\n");
+
+		/*
+		 * There are a few SMN index/data pairs and other registers
+		 * that shouldn't be accessed by user space.
+		 * So reserve the entire PCI config space for simplicity rather
+		 * than covering specific registers piecemeal.
+		 */
+		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
+			pci_err(root, "Failed to reserve config space\n");
+			return -EEXIST;
+		}
+	}
+
+	smn_exclusive = true;
+	return 0;
+}
+
+static bool enable_dfs;
+
+static int __init amd_smn_enable_dfs(char *str)
+{
+	enable_dfs = true;
+	return 1;
+}
+__setup("amd_smn_debugfs_enable", amd_smn_enable_dfs);
+
 static int __init amd_smn_init(void)
 {
 	int err;
@@ -209,6 +346,18 @@ static int __init amd_smn_init(void)
 	if (err)
 		return err;
 
+	err = reserve_root_config_spaces();
+	if (err)
+		return err;
+
+	if (enable_dfs) {
+		debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir);
+
+		debugfs_create_file("node",	0600, debugfs_dir, NULL, &smn_node_fops);
+		debugfs_create_file("address",	0600, debugfs_dir, NULL, &smn_address_fops);
+		debugfs_create_file("value",	0600, debugfs_dir, NULL, &smn_value_fops);
+	}
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 89c0c8a3fc7e..769321185a08 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -29,7 +29,7 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/x86_init.h>
 #include <linux/crash_dump.h>
 
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 3bf0487cf3b7..52d1808ee360 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -23,8 +23,5 @@ obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
 obj-y				+= apic_flat_64.o
 endif
 
-# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
-
 # For 32bit, probe_32 need to be listed last
 obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e893dc6f11c1..d73ba5a7b623 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -59,6 +59,7 @@
 #include <asm/time.h>
 #include <asm/smp.h>
 #include <asm/mce.h>
+#include <asm/msr.h>
 #include <asm/tsc.h>
 #include <asm/hypervisor.h>
 #include <asm/cpu_device_id.h>
@@ -425,7 +426,7 @@ static int lapic_next_deadline(unsigned long delta,
 	weak_wrmsr_fence();
 
 	tsc = rdtsc();
-	wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
+	wrmsrq(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
 	return 0;
 }
 
@@ -449,7 +450,7 @@ static int lapic_timer_shutdown(struct clock_event_device *evt)
 	 * the timer _and_ zero the counter registers:
 	 */
 	if (v & APIC_LVT_TIMER_TSCDEADLINE)
-		wrmsrl(MSR_IA32_TSC_DEADLINE, 0);
+		wrmsrq(MSR_IA32_TSC_DEADLINE, 0);
 	else
 		apic_write(APIC_TMICT, 0);
 
@@ -1371,8 +1372,6 @@ void __init apic_intr_mode_init(void)
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
@@ -1674,7 +1673,6 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 	topology_register_boot_apic(boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
@@ -1697,7 +1695,7 @@ static bool x2apic_hw_locked(void)
 
 	x86_arch_cap_msr = x86_read_arch_cap_msr();
 	if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) {
-		rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
+		rdmsrq(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
 		return (msr & LEGACY_XAPIC_DISABLED);
 	}
 	return false;
@@ -1710,12 +1708,12 @@ static void __x2apic_disable(void)
 	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return;
 
-	rdmsrl(MSR_IA32_APICBASE, msr);
+	rdmsrq(MSR_IA32_APICBASE, msr);
 	if (!(msr & X2APIC_ENABLE))
 		return;
 	/* Disable xapic and x2apic first and then reenable xapic mode */
-	wrmsrl(MSR_IA32_APICBASE, msr & ~(X2APIC_ENABLE | XAPIC_ENABLE));
-	wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE);
+	wrmsrq(MSR_IA32_APICBASE, msr & ~(X2APIC_ENABLE | XAPIC_ENABLE));
+	wrmsrq(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE);
 	printk_once(KERN_INFO "x2apic disabled\n");
 }
 
@@ -1723,10 +1721,10 @@ static void __x2apic_enable(void)
 {
 	u64 msr;
 
-	rdmsrl(MSR_IA32_APICBASE, msr);
+	rdmsrq(MSR_IA32_APICBASE, msr);
 	if (msr & X2APIC_ENABLE)
 		return;
-	wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE);
+	wrmsrq(MSR_IA32_APICBASE, msr | X2APIC_ENABLE);
 	printk_once(KERN_INFO "x2apic enabled\n");
 }
 
@@ -2014,8 +2012,8 @@ static bool __init detect_init_APIC(void)
 	case X86_VENDOR_HYGON:
 		break;
 	case X86_VENDOR_INTEL:
-		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
-		    (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
+		if ((boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)) ||
+		    boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO)
 			break;
 		goto no_apic;
 	default:
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 16410f087b7a..e272bc7fdc8e 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/pgtable.h>
 
+#include <asm/msr.h>
 #include <asm/numachip/numachip.h>
 #include <asm/numachip/numachip_csr.h>
 
@@ -31,7 +32,7 @@ static u32 numachip1_get_apic_id(u32 x)
 	unsigned int id = (x >> 24) & 0xff;
 
 	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
-		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		rdmsrq(MSR_FAM10H_NODE_ID, value);
 		id |= (value << 2) & 0xff00;
 	}
 
@@ -42,7 +43,7 @@ static u32 numachip2_get_apic_id(u32 x)
 {
 	u64 mcfg;
 
-	rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg);
+	rdmsrq(MSR_FAM10H_MMIO_CONF_BASE, mcfg);
 	return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24);
 }
 
@@ -150,7 +151,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 
 	/* Account for nodes per socket in multi-core-module processors */
 	if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
-		rdmsrl(MSR_FAM10H_NODE_ID, val);
+		rdmsrq(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
deleted file mode 100644
index 9285d500d5b4..000000000000
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
- *
- * Drives the local APIC in "clustered mode".
- */
-#include <linux/cpumask.h>
-#include <linux/dmi.h>
-#include <linux/smp.h>
-
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-
-#include "local.h"
-
-static u32 bigsmp_get_apic_id(u32 x)
-{
-	return (x >> 24) & 0xFF;
-}
-
-static void bigsmp_send_IPI_allbutself(int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void bigsmp_send_IPI_all(int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
-static int dmi_bigsmp; /* can be set by dmi scanners */
-
-static int hp_ht_bigsmp(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
-	dmi_bigsmp = 1;
-
-	return 0;
-}
-
-
-static const struct dmi_system_id bigsmp_dmi_table[] = {
-	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
-		}
-	},
-
-	{ hp_ht_bigsmp, "HP ProLiant DL740",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
-		}
-	},
-	{ } /* NULL entry stops DMI scanning */
-};
-
-static int probe_bigsmp(void)
-{
-	return dmi_check_system(bigsmp_dmi_table);
-}
-
-static struct apic apic_bigsmp __ro_after_init = {
-
-	.name				= "bigsmp",
-	.probe				= probe_bigsmp,
-
-	.dest_mode_logical		= false,
-
-	.disable_esr			= 1,
-
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-
-	.max_apic_id			= 0xFE,
-	.get_apic_id			= bigsmp_get_apic_id,
-
-	.calc_dest_apicid		= apic_default_calc_apicid,
-
-	.send_IPI			= default_send_IPI_single_phys,
-	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
-	.send_IPI_mask_allbutself	= NULL,
-	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
-	.send_IPI_all			= bigsmp_send_IPI_all,
-	.send_IPI_self			= default_send_IPI_self,
-
-	.read				= native_apic_mem_read,
-	.write				= native_apic_mem_write,
-	.eoi				= native_apic_mem_eoi,
-	.icr_read			= native_apic_icr_read,
-	.icr_write			= native_apic_icr_write,
-	.wait_icr_idle			= apic_mem_wait_icr_idle,
-	.safe_wait_icr_idle		= apic_mem_wait_icr_idle_timeout,
-};
-
-bool __init apic_bigsmp_possible(bool cmdline_override)
-{
-	return apic == &apic_bigsmp || !cmdline_override;
-}
-
-void __init apic_bigsmp_force(void)
-{
-	if (apic != &apic_bigsmp)
-		apic_install_driver(&apic_bigsmp);
-}
-
-apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index eebc360ed1bb..5ba2feb2c04c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1486,7 +1486,7 @@ static void __init delay_with_tsc(void)
 	 * 1 GHz == 40 jiffies
 	 */
 	do {
-		rep_nop();
+		native_pause();
 		now = rdtsc();
 	} while ((now - start) < 40000000000ULL / HZ &&	time_before_eq(jiffies, end));
 }
@@ -2225,7 +2225,7 @@ static int mp_irqdomain_create(int ioapic)
 
 	/* Handle device tree enumerated APICs proper */
 	if (cfg->dev) {
-		fn = of_node_to_fwnode(cfg->dev);
+		fn = of_fwnode_handle(cfg->dev);
 	} else {
 		fn = irq_domain_alloc_named_id_fwnode("IO-APIC", mpc_ioapic_id(ioapic));
 		if (!fn)
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b7..98a57cb4aa86 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -3,6 +3,7 @@
 #include <linux/cpumask.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
+#include <linux/string_choices.h>
 
 #include <asm/io_apic.h>
 
@@ -23,7 +24,7 @@ __setup("no_ipi_broadcast=", apic_ipi_shorthand);
 static int __init print_ipi_mode(void)
 {
 	pr_info("IPI shorthand broadcast: %s\n",
-		apic_ipi_shorthand_off ? "disabled" : "enabled");
+		str_disabled_enabled(apic_ipi_shorthand_off));
 	return 0;
 }
 late_initcall(print_ipi_mode);
@@ -287,34 +288,4 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
 	__default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
 	local_irq_restore(flags);
 }
-
-#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(u32 apic_id)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
-			return i;
-	}
-	return -1;
-}
-
-int safe_smp_processor_id(void)
-{
-	u32 apicid;
-	int cpuid;
-
-	if (!boot_cpu_has(X86_FEATURE_APIC))
-		return 0;
-
-	apicid = read_apic_id();
-	if (apicid == BAD_APICID)
-		return 0;
-
-	cpuid = convert_apicid_to_cpu(apicid);
-
-	return cpuid >= 0 ? cpuid : 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 842fe28496be..bdcf609eb283 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -65,17 +65,4 @@ void default_send_IPI_self(int vector);
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
-void x86_32_probe_bigsmp_early(void);
-void x86_32_install_bigsmp(void);
-#else
-static inline void x86_32_probe_bigsmp_early(void) { }
-static inline void x86_32_install_bigsmp(void) { }
-#endif
-
-#ifdef CONFIG_X86_BIGSMP
-bool apic_bigsmp_possible(bool cmdline_selected);
-void apic_bigsmp_force(void);
-#else
-static inline bool apic_bigsmp_possible(bool cmdline_selected) { return false; };
-static inline void apic_bigsmp_force(void) { }
 #endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f75ee345c02d..87bc9e7ca5d6 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -93,35 +93,6 @@ static int __init parse_apic(char *arg)
 }
 early_param("apic", parse_apic);
 
-void __init x86_32_probe_bigsmp_early(void)
-{
-	if (nr_cpu_ids <= 8 || xen_pv_domain())
-		return;
-
-	if (IS_ENABLED(CONFIG_X86_BIGSMP)) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(boot_cpu_apic_version))
-				break;
-			/* P4 and above */
-			fallthrough;
-		case X86_VENDOR_HYGON:
-		case X86_VENDOR_AMD:
-			if (apic_bigsmp_possible(cmdline_apic))
-				return;
-			break;
-		}
-	}
-	pr_info("Limiting to 8 possible CPUs\n");
-	set_nr_cpu_ids(8);
-}
-
-void __init x86_32_install_bigsmp(void)
-{
-	if (nr_cpu_ids > 8 && !xen_pv_domain())
-		apic_bigsmp_force();
-}
-
 void __init x86_32_probe_apic(void)
 {
 	if (!cmdline_apic) {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 736f62812f5c..93069b13d3af 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -799,7 +799,7 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_set_default_host(x86_vector_domain);
+	irq_set_default_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 
@@ -864,7 +864,7 @@ void lapic_offline(void)
 	__vector_cleanup(cl, false);
 
 	irq_matrix_offline(vector_matrix);
-	WARN_ON_ONCE(try_to_del_timer_sync(&cl->timer) < 0);
+	WARN_ON_ONCE(timer_delete_sync_try(&cl->timer) < 0);
 	WARN_ON_ONCE(!hlist_empty(&cl->head));
 
 	unlock_vector_lock();
@@ -888,8 +888,109 @@ static int apic_set_affinity(struct irq_data *irqd,
 	return err ? err : IRQ_SET_MASK_OK;
 }
 
+static void free_moved_vector(struct apic_chip_data *apicd)
+{
+	unsigned int vector = apicd->prev_vector;
+	unsigned int cpu = apicd->prev_cpu;
+	bool managed = apicd->is_managed;
+
+	/*
+	 * Managed interrupts are usually not migrated away
+	 * from an online CPU, but CPU isolation 'managed_irq'
+	 * can make that happen.
+	 * 1) Activation does not take the isolation into account
+	 *    to keep the code simple
+	 * 2) Migration away from an isolated CPU can happen when
+	 *    a non-isolated CPU which is in the calculated
+	 *    affinity mask comes online.
+	 */
+	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
+	irq_matrix_free(vector_matrix, cpu, vector, managed);
+	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
+	hlist_del_init(&apicd->clist);
+	apicd->prev_vector = 0;
+	apicd->move_in_progress = 0;
+}
+
+/*
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
+ */
+static void apic_force_complete_move(struct irq_data *irqd)
+{
+	unsigned int cpu = smp_processor_id();
+	struct apic_chip_data *apicd;
+	unsigned int vector;
+
+	guard(raw_spinlock)(&vector_lock);
+	apicd = apic_chip_data(irqd);
+	if (!apicd)
+		return;
+
+	/*
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
+	 */
+	vector = apicd->prev_vector;
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
+		return;
+
+	/*
+	 * This is tricky. If the cleanup of the old vector has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * All CPUs are stuck in stop machine with interrupts disabled so
+	 * calling __irq_complete_move() would be completely pointless.
+	 *
+	 * 1) The interrupt is in move_in_progress state. That means that we
+	 *    have not seen an interrupt since the io_apic was reprogrammed to
+	 *    the new vector.
+	 *
+	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+	 *    have not been processed yet.
+	 */
+	if (apicd->move_in_progress) {
+		/*
+		 * In theory there is a race:
+		 *
+		 * set_ioapic(new_vector) <-- Interrupt is raised before update
+		 *			      is effective, i.e. it's raised on
+		 *			      the old vector.
+		 *
+		 * So if the target cpu cannot handle that interrupt before
+		 * the old vector is cleaned up, we get a spurious interrupt
+		 * and in the worst case the ioapic irq line becomes stale.
+		 *
+		 * But in case of cpu hotplug this should be a non issue
+		 * because if the affinity update happens right before all
+		 * cpus rendezvous in stop machine, there is no way that the
+		 * interrupt can be blocked on the target cpu because all cpus
+		 * loops first with interrupts enabled in stop machine, so the
+		 * old vector is not yet cleaned up when the interrupt fires.
+		 *
+		 * So the only way to run into this issue is if the delivery
+		 * of the interrupt on the apic/system bus would be delayed
+		 * beyond the point where the target cpu disables interrupts
+		 * in stop machine. I doubt that it can happen, but at least
+		 * there is a theoretical chance. Virtualization might be
+		 * able to expose this, but AFAICT the IOAPIC emulation is not
+		 * as stupid as the real hardware.
+		 *
+		 * Anyway, there is nothing we can do about that at this point
+		 * w/o refactoring the whole fixup_irq() business completely.
+		 * We print at least the irq number and the old vector number,
+		 * so we have the necessary information when a problem in that
+		 * area arises.
+		 */
+		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+			irqd->irq, vector);
+	}
+	free_moved_vector(apicd);
+}
+
 #else
-# define apic_set_affinity	NULL
+# define apic_set_affinity		NULL
+# define apic_force_complete_move	NULL
 #endif
 
 static int apic_retrigger_irq(struct irq_data *irqd)
@@ -923,39 +1024,16 @@ static void x86_vector_msi_compose_msg(struct irq_data *data,
 }
 
 static struct irq_chip lapic_controller = {
-	.name			= "APIC",
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= apic_set_affinity,
-	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
-	.irq_retrigger		= apic_retrigger_irq,
+	.name				= "APIC",
+	.irq_ack			= apic_ack_edge,
+	.irq_set_affinity		= apic_set_affinity,
+	.irq_compose_msi_msg		= x86_vector_msi_compose_msg,
+	.irq_force_complete_move	= apic_force_complete_move,
+	.irq_retrigger			= apic_retrigger_irq,
 };
 
 #ifdef CONFIG_SMP
 
-static void free_moved_vector(struct apic_chip_data *apicd)
-{
-	unsigned int vector = apicd->prev_vector;
-	unsigned int cpu = apicd->prev_cpu;
-	bool managed = apicd->is_managed;
-
-	/*
-	 * Managed interrupts are usually not migrated away
-	 * from an online CPU, but CPU isolation 'managed_irq'
-	 * can make that happen.
-	 * 1) Activation does not take the isolation into account
-	 *    to keep the code simple
-	 * 2) Migration away from an isolated CPU can happen when
-	 *    a non-isolated CPU which is in the calculated
-	 *    affinity mask comes online.
-	 */
-	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
-	irq_matrix_free(vector_matrix, cpu, vector, managed);
-	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
-	hlist_del_init(&apicd->clist);
-	apicd->prev_vector = 0;
-	apicd->move_in_progress = 0;
-}
-
 static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
 {
 	struct apic_chip_data *apicd;
@@ -1068,99 +1146,6 @@ void irq_complete_move(struct irq_cfg *cfg)
 		__vector_schedule_cleanup(apicd);
 }
 
-/*
- * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
- */
-void irq_force_complete_move(struct irq_desc *desc)
-{
-	unsigned int cpu = smp_processor_id();
-	struct apic_chip_data *apicd;
-	struct irq_data *irqd;
-	unsigned int vector;
-
-	/*
-	 * The function is called for all descriptors regardless of which
-	 * irqdomain they belong to. For example if an IRQ is provided by
-	 * an irq_chip as part of a GPIO driver, the chip data for that
-	 * descriptor is specific to the irq_chip in question.
-	 *
-	 * Check first that the chip_data is what we expect
-	 * (apic_chip_data) before touching it any further.
-	 */
-	irqd = irq_domain_get_irq_data(x86_vector_domain,
-				       irq_desc_get_irq(desc));
-	if (!irqd)
-		return;
-
-	raw_spin_lock(&vector_lock);
-	apicd = apic_chip_data(irqd);
-	if (!apicd)
-		goto unlock;
-
-	/*
-	 * If prev_vector is empty or the descriptor is neither currently
-	 * nor previously on the outgoing CPU no action required.
-	 */
-	vector = apicd->prev_vector;
-	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
-		goto unlock;
-
-	/*
-	 * This is tricky. If the cleanup of the old vector has not been
-	 * done yet, then the following setaffinity call will fail with
-	 * -EBUSY. This can leave the interrupt in a stale state.
-	 *
-	 * All CPUs are stuck in stop machine with interrupts disabled so
-	 * calling __irq_complete_move() would be completely pointless.
-	 *
-	 * 1) The interrupt is in move_in_progress state. That means that we
-	 *    have not seen an interrupt since the io_apic was reprogrammed to
-	 *    the new vector.
-	 *
-	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
-	 *    have not been processed yet.
-	 */
-	if (apicd->move_in_progress) {
-		/*
-		 * In theory there is a race:
-		 *
-		 * set_ioapic(new_vector) <-- Interrupt is raised before update
-		 *			      is effective, i.e. it's raised on
-		 *			      the old vector.
-		 *
-		 * So if the target cpu cannot handle that interrupt before
-		 * the old vector is cleaned up, we get a spurious interrupt
-		 * and in the worst case the ioapic irq line becomes stale.
-		 *
-		 * But in case of cpu hotplug this should be a non issue
-		 * because if the affinity update happens right before all
-		 * cpus rendezvous in stop machine, there is no way that the
-		 * interrupt can be blocked on the target cpu because all cpus
-		 * loops first with interrupts enabled in stop machine, so the
-		 * old vector is not yet cleaned up when the interrupt fires.
-		 *
-		 * So the only way to run into this issue is if the delivery
-		 * of the interrupt on the apic/system bus would be delayed
-		 * beyond the point where the target cpu disables interrupts
-		 * in stop machine. I doubt that it can happen, but at least
-		 * there is a theoretical chance. Virtualization might be
-		 * able to expose this, but AFAICT the IOAPIC emulation is not
-		 * as stupid as the real hardware.
-		 *
-		 * Anyway, there is nothing we can do about that at this point
-		 * w/o refactoring the whole fixup_irq() business completely.
-		 * We print at least the irq number and the old vector number,
-		 * so we have the necessary information when a problem in that
-		 * area arises.
-		 */
-		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
-			irqd->irq, vector);
-	}
-	free_moved_vector(apicd);
-unlock:
-	raw_spin_unlock(&vector_lock);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Note, this is not accurate accounting, but at least good enough to
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a98020bf31bb..6259b474073b 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -33,6 +33,14 @@
 
 static void __used common(void)
 {
+	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
+	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
+	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
+	OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
+	OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
+	OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
+	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
+
 	BLANK();
 	OFFSET(TASK_threadsp, task_struct, thread.sp);
 #ifdef CONFIG_STACKPROTECTOR
@@ -107,11 +115,6 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
-	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
-	OFFSET(X86_current_task, pcpu_hot, current_task);
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	OFFSET(X86_call_depth, pcpu_hot, call_depth);
-#endif
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
 	BLANK();
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 2b411cd00a4e..e0a292db97b2 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -12,15 +12,6 @@ void foo(void);
 
 void foo(void)
 {
-	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
-	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
-	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
-	OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
-	OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
-	OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
-	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
-	BLANK();
-
 	OFFSET(PT_EBX, pt_regs, bx);
 	OFFSET(PT_ECX, pt_regs, cx);
 	OFFSET(PT_EDX, pt_regs, dx);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index bb65371ea9df..590b6cd0eac0 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,11 +54,5 @@ int main(void)
 	BLANK();
 #undef ENTRY
 
-	BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
-	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
-	BLANK();
-#endif
 	return 0;
 }
diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 3fed7ae58b60..73274d76ce16 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/acpi.h>
+#include <linux/bitops.h>
 #include <asm/io.h>
 
 #include <linux/mc146818rtc.h>
@@ -20,27 +21,13 @@
 
 int sbf_port __initdata = -1;	/* set via acpi_boot_init() */
 
-static int __init parity(u8 v)
-{
-	int x = 0;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		x ^= (v & 1);
-		v >>= 1;
-	}
-
-	return x;
-}
-
 static void __init sbf_write(u8 v)
 {
 	unsigned long flags;
 
 	if (sbf_port != -1) {
-		v &= ~SBF_PARITY;
-		if (!parity(v))
-			v |= SBF_PARITY;
+		if (!parity8(v))
+			v ^= SBF_PARITY;
 
 		printk(KERN_INFO "Simple Boot Flag at 0x%x set to 0x%x\n",
 			sbf_port, v);
@@ -66,14 +53,14 @@ static u8 __init sbf_read(void)
 	return v;
 }
 
-static int __init sbf_value_valid(u8 v)
+static bool __init sbf_value_valid(u8 v)
 {
 	if (v & SBF_RESERVED)		/* Reserved bits */
-		return 0;
-	if (!parity(v))
-		return 0;
+		return false;
+	if (!parity8(v))
+		return false;
 
-	return 1;
+	return true;
 }
 
 static int __init sbf_init(void)
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8418a892d195..a951333c5995 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -98,11 +98,10 @@ static inline bool within_module_coretext(void *addr)
 #ifdef CONFIG_MODULES
 	struct module *mod;
 
-	preempt_disable();
+	guard(rcu)();
 	mod = __module_address((unsigned long)addr);
 	if (mod && within_module_core((unsigned long)addr, mod))
 		ret = true;
-	preempt_enable();
 #endif
 	return ret;
 }
@@ -186,7 +185,7 @@ static void *patch_dest(void *dest, bool direct)
 	u8 *pad = dest - tsize;
 
 	memcpy(insn_buff, skl_call_thunk_template, tsize);
-	apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
+	text_poke_apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
 
 	/* Already patched? */
 	if (!bcmp(pad, insn_buff, tsize))
@@ -240,21 +239,10 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
 }
 
 static __init_or_module void
-patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
-		     const struct core_text *ct)
-{
-	struct alt_instr *a;
-
-	for (a = start; a < end; a++)
-		patch_call((void *)&a->instr_offset + a->instr_offset, ct);
-}
-
-static __init_or_module void
 callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
 {
 	prdbg("Patching call sites %s\n", ct->name);
 	patch_call_sites(cs->call_start, cs->call_end, ct);
-	patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
 	prdbg("Patching call sites done%s\n", ct->name);
 }
 
@@ -263,8 +251,6 @@ void __init callthunks_patch_builtin_calls(void)
 	struct callthunk_sites cs = {
 		.call_start	= __call_sites,
 		.call_end	= __call_sites_end,
-		.alt_start	= __alt_instructions,
-		.alt_end	= __alt_instructions_end
 	};
 
 	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
@@ -308,7 +294,7 @@ static bool is_callthunk(void *addr)
 	pad = (void *)(dest - tmpl_size);
 
 	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
-	apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
+	text_poke_apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
 
 	return !bcmp(pad, insn_buff, tmpl_size);
 }
@@ -326,7 +312,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
 		return 0;
 
 	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
-	apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
+	text_poke_apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
 
 	memcpy(*pprog, insn_buff, tmpl_size);
 	*pprog += tmpl_size;
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index 303bf74d175b..99444409c026 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -2,6 +2,7 @@
 
 #include <linux/ptrace.h>
 #include <asm/bugs.h>
+#include <asm/msr.h>
 #include <asm/traps.h>
 
 enum cp_error_code {
@@ -55,7 +56,7 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code)
 	 * will be whatever is live in userspace. So read the SSP before enabling
 	 * interrupts so locking the fpregs to do it later is not required.
 	 */
-	rdmsrl(MSR_IA32_PL3_SSP, ssp);
+	rdmsrq(MSR_IA32_PL3_SSP, ssp);
 
 	cond_local_irq_enable(regs);
 
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index e6bf78fac146..77086cf565ec 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -67,16 +67,30 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
  */
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
-	unsigned long target;
+	unsigned long target, addr = regs->ip;
 	u32 type;
 
-	if (!is_cfi_trap(regs->ip))
-		return BUG_TRAP_TYPE_NONE;
+	switch (cfi_mode) {
+	case CFI_KCFI:
+		if (!is_cfi_trap(addr))
+			return BUG_TRAP_TYPE_NONE;
+
+		if (!decode_cfi_insn(regs, &target, &type))
+			return report_cfi_failure_noaddr(regs, addr);
+
+		break;
 
-	if (!decode_cfi_insn(regs, &target, &type))
-		return report_cfi_failure_noaddr(regs, regs->ip);
+	case CFI_FINEIBT:
+		if (!decode_fineibt_insn(regs, &target, &type))
+			return BUG_TRAP_TYPE_NONE;
+
+		break;
+
+	default:
+		return BUG_TRAP_TYPE_NONE;
+	}
 
-	return report_cfi_failure(regs, regs->ip, &target, type);
+	return report_cfi_failure(regs, addr, &target, type);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4efdf5c2efc8..1e26179ff18c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,7 +24,7 @@ obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
-obj-y			+= cpuid-deps.o
+obj-y			+= cpuid-deps.o cpuid_0x2_table.o
 obj-y			+= umwait.o
 obj-y 			+= capflags.o powerflags.o
 
@@ -38,6 +38,9 @@ obj-y					+= intel.o tsx.o
 obj-$(CONFIG_PM)			+= intel_epb.o
 endif
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
+ifeq ($(CONFIG_AMD_NB)$(CONFIG_SYSFS),yy)
+obj-y					+= amd_cache_disable.o
+endif
 obj-$(CONFIG_CPU_SUP_HYGON)		+= hygon.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54194f5995de..93da466dfe2c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,6 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
+#include <asm/amd/fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
@@ -21,6 +22,7 @@
 #include <asm/delay.h>
 #include <asm/debugreg.h>
 #include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/sev.h>
 
 #ifdef CONFIG_X86_64
@@ -29,7 +31,9 @@
 
 #include "cpu.h"
 
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+u16 invlpgb_count_max __ro_after_init;
+
+static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
 {
 	u32 gprs[8] = { 0 };
 	int err;
@@ -47,7 +51,7 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+static inline int wrmsrq_amd_safe(unsigned msr, u64 val)
 {
 	u32 gprs[8] = { 0 };
 
@@ -381,7 +385,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
 			u64 val;
 
-			rdmsrl(MSR_K7_HWCR, val);
+			rdmsrq(MSR_K7_HWCR, val);
 			if (!(val & BIT(24)))
 				pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
 		}
@@ -420,7 +424,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		 * Try to cache the base value so further operations can
 		 * avoid RMW. If that faults, do not enable SSBD.
 		 */
-		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+		if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
 			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
 			setup_force_cpu_cap(X86_FEATURE_SSBD);
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
@@ -470,6 +474,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		case 0x60 ... 0x7f:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
+		case 0x50 ... 0x5f:
+		case 0x90 ... 0xaf:
+		case 0xc0 ... 0xcf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN6);
+			break;
 		default:
 			goto warn;
 		}
@@ -506,7 +515,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
 		/* Check if memory encryption is enabled */
-		rdmsrl(MSR_AMD64_SYSCFG, msr);
+		rdmsrq(MSR_AMD64_SYSCFG, msr);
 		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			goto clear_all;
 
@@ -523,7 +532,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 		if (!sme_me_mask)
 			setup_clear_cpu_cap(X86_FEATURE_SME);
 
-		rdmsrl(MSR_K7_HWCR, msr);
+		rdmsrq(MSR_K7_HWCR, msr);
 		if (!(msr & MSR_K7_HWCR_SMMLOCK))
 			goto clear_sev;
 
@@ -610,7 +619,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
 		if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
 			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
-		else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+		else if (c->x86 >= 0x19 && !wrmsrq_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
 			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
 			setup_force_cpu_cap(X86_FEATURE_SBPB);
 		}
@@ -632,16 +641,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 * (model = 0x14) and later actually support it.
 	 * (AMD Erratum #110, docId: 25759).
 	 */
-	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
-		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+		if (!rdmsrq_amd_safe(0xc001100d, &value)) {
 			value &= ~BIT_64(32);
-			wrmsrl_amd_safe(0xc001100d, value);
+			wrmsrq_amd_safe(0xc001100d, value);
 		}
 	}
 
 	if (!c->x86_model_id[0])
-		strcpy(c->x86_model_id, "Hammer");
+		strscpy(c->x86_model_id, "Hammer");
 
 #ifdef CONFIG_SMP
 	/*
@@ -786,9 +795,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	 * Disable it on the affected CPUs.
 	 */
 	if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
-		if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
+		if (!rdmsrq_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
 			value |= 0x1E;
-			wrmsrl_safe(MSR_F15H_IC_CFG, value);
+			wrmsrq_safe(MSR_F15H_IC_CFG, value);
 		}
 	}
 
@@ -803,6 +812,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static const struct x86_cpu_id erratum_1386_microcode[] = {
 	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e),
 	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052),
+	{}
 };
 
 static void fix_erratum_1386(struct cpuinfo_x86 *c)
@@ -836,9 +846,9 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
 	 * suppresses non-branch predictions.
 	 */
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
-		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+		if (!rdmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
 			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
-			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+			wrmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
 		}
 	}
 #endif
@@ -866,6 +876,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c)
 
 	pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
 	setup_force_cpu_bug(X86_BUG_DIV0);
+
+	/*
+	 * Turn off the Instructions Retired free counter on machines that are
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (c->x86_model < 0x30) {
+		msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
+		clear_cpu_cap(c, X86_FEATURE_IRPERF);
+	}
 }
 
 static bool cpu_has_zenbleed_microcode(void)
@@ -1012,7 +1032,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	init_amd_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_SVM)) {
-		rdmsrl(MSR_VM_CR, vm_cr);
+		rdmsrq(MSR_VM_CR, vm_cr);
 		if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
 			pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
 			clear_cpu_cap(c, X86_FEATURE_SVM);
@@ -1049,13 +1069,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (!cpu_feature_enabled(X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
 
-	/*
-	 * Turn on the Instructions Retired free counter on machines not
-	 * susceptible to erratum #1054 "Instructions Retired Performance
-	 * Counter May Be Inaccurate".
-	 */
-	if (cpu_has(c, X86_FEATURE_IRPERF) &&
-	    (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
+	/* Enable the Instructions Retired free counter */
+	if (cpu_has(c, X86_FEATURE_IRPERF))
 		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 
 	check_null_seg_clears_base(c);
@@ -1073,6 +1088,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
 	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
+	/* Enable Translation Cache Extension */
+	if (cpu_has(c, X86_FEATURE_TCE))
+		msr_set_bit(MSR_EFER, _EFER_TCE);
 }
 
 #ifdef CONFIG_X86_32
@@ -1105,8 +1124,8 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/*
 	 * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
@@ -1119,26 +1138,30 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		/* Erratum 658 */
 		if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
-			tlb_lli_2m[ENTRIES] = 1024;
+			tlb_lli_2m = 1024;
 		} else {
 			cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-			tlb_lli_2m[ENTRIES] = eax & 0xff;
+			tlb_lli_2m = eax & 0xff;
 		}
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
+
+	/* Max number of pages INVLPGB can invalidate in one shot */
+	if (cpu_has(c, X86_FEATURE_INVLPGB))
+		invlpgb_count_max = (cpuid_edx(0x80000008) & 0xffff) + 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {
@@ -1190,7 +1213,7 @@ void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
 	if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
 		return;
 
-	wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+	wrmsrq(amd_msr_dr_addr_masks[dr], mask);
 	per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
 }
 
@@ -1221,3 +1244,56 @@ void amd_check_microcode(void)
 	if (cpu_feature_enabled(X86_FEATURE_ZEN2))
 		on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
+
+static const char * const s5_reset_reason_txt[] = {
+	[0]  = "thermal pin BP_THERMTRIP_L was tripped",
+	[1]  = "power button was pressed for 4 seconds",
+	[2]  = "shutdown pin was tripped",
+	[4]  = "remote ASF power off command was received",
+	[9]  = "internal CPU thermal limit was tripped",
+	[16] = "system reset pin BP_SYS_RST_L was tripped",
+	[17] = "software issued PCI reset",
+	[18] = "software wrote 0x4 to reset control register 0xCF9",
+	[19] = "software wrote 0x6 to reset control register 0xCF9",
+	[20] = "software wrote 0xE to reset control register 0xCF9",
+	[21] = "ACPI power state transition occurred",
+	[22] = "keyboard reset pin KB_RST_L was tripped",
+	[23] = "internal CPU shutdown event occurred",
+	[24] = "system failed to boot before failed boot timer expired",
+	[25] = "hardware watchdog timer expired",
+	[26] = "remote ASF reset command was received",
+	[27] = "an uncorrected error caused a data fabric sync flood event",
+	[29] = "FCH and MP1 failed warm reset handshake",
+	[30] = "a parity error occurred",
+	[31] = "a software sync flood event occurred",
+};
+
+static __init int print_s5_reset_status_mmio(void)
+{
+	unsigned long value;
+	void __iomem *addr;
+	int i;
+
+	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+		return 0;
+
+	addr = ioremap(FCH_PM_BASE + FCH_PM_S5_RESET_STATUS, sizeof(value));
+	if (!addr)
+		return 0;
+
+	value = ioread32(addr);
+	iounmap(addr);
+
+	for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
+		if (!(value & BIT(i)))
+			continue;
+
+		if (s5_reset_reason_txt[i]) {
+			pr_info("x86/amd: Previous system reset reason [0x%08lx]: %s\n",
+				value, s5_reset_reason_txt[i]);
+		}
+	}
+
+	return 0;
+}
+late_initcall(print_s5_reset_status_mmio);
diff --git a/arch/x86/kernel/cpu/amd_cache_disable.c b/arch/x86/kernel/cpu/amd_cache_disable.c
new file mode 100644
index 000000000000..8843b9557aea
--- /dev/null
+++ b/arch/x86/kernel/cpu/amd_cache_disable.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD L3 cache_disable_{0,1} sysfs handling
+ * Documentation/ABI/testing/sysfs-devices-system-cpu
+ */
+
+#include <linux/cacheinfo.h>
+#include <linux/capability.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+
+#include <asm/amd/nb.h>
+
+#include "cpu.h"
+
+/*
+ * L3 cache descriptors
+ */
+static void amd_calc_l3_indices(struct amd_northbridge *nb)
+{
+	struct amd_l3_cache *l3 = &nb->l3_cache;
+	unsigned int sc0, sc1, sc2, sc3;
+	u32 val = 0;
+
+	pci_read_config_dword(nb->misc, 0x1C4, &val);
+
+	/* calculate subcache sizes */
+	l3->subcaches[0] = sc0 = !(val & BIT(0));
+	l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+	if (boot_cpu_data.x86 == 0x15) {
+		l3->subcaches[0] = sc0 += !(val & BIT(1));
+		l3->subcaches[1] = sc1 += !(val & BIT(5));
+	}
+
+	l3->subcaches[2] = sc2 = !(val & BIT(8))  + !(val & BIT(9));
+	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
+}
+
+/*
+ * check whether a slot used for disabling an L3 index is occupied.
+ * @l3: L3 cache descriptor
+ * @slot: slot number (0..1)
+ *
+ * @returns: the disabled index if used or negative value if slot free.
+ */
+static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned int slot)
+{
+	unsigned int reg = 0;
+
+	pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
+
+	/* check whether this slot is activated already */
+	if (reg & (3UL << 30))
+		return reg & 0xfff;
+
+	return -1;
+}
+
+static ssize_t show_cache_disable(struct cacheinfo *ci, char *buf, unsigned int slot)
+{
+	int index;
+	struct amd_northbridge *nb = ci->priv;
+
+	index = amd_get_l3_disable_slot(nb, slot);
+	if (index >= 0)
+		return sysfs_emit(buf, "%d\n", index);
+
+	return sysfs_emit(buf, "FREE\n");
+}
+
+#define SHOW_CACHE_DISABLE(slot)					\
+static ssize_t								\
+cache_disable_##slot##_show(struct device *dev,				\
+			    struct device_attribute *attr, char *buf)	\
+{									\
+	struct cacheinfo *ci = dev_get_drvdata(dev);			\
+	return show_cache_disable(ci, buf, slot);			\
+}
+
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
+				 unsigned int slot, unsigned long idx)
+{
+	int i;
+
+	idx |= BIT(30);
+
+	/*
+	 *  disable index in all 4 subcaches
+	 */
+	for (i = 0; i < 4; i++) {
+		u32 reg = idx | (i << 20);
+
+		if (!nb->l3_cache.subcaches[i])
+			continue;
+
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+
+		/*
+		 * We need to WBINVD on a core on the node containing the L3
+		 * cache which indices we disable therefore a simple wbinvd()
+		 * is not sufficient.
+		 */
+		wbinvd_on_cpu(cpu);
+
+		reg |= BIT(31);
+		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+	}
+}
+
+/*
+ * disable a L3 cache index by using a disable-slot
+ *
+ * @l3:    L3 cache descriptor
+ * @cpu:   A CPU on the node containing the L3 cache
+ * @slot:  slot number (0..1)
+ * @index: index to disable
+ *
+ * @return: 0 on success, error status on failure
+ */
+static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
+				   unsigned int slot, unsigned long index)
+{
+	int ret = 0;
+
+	/*  check if @slot is already used or the index is already disabled */
+	ret = amd_get_l3_disable_slot(nb, slot);
+	if (ret >= 0)
+		return -EEXIST;
+
+	if (index > nb->l3_cache.indices)
+		return -EINVAL;
+
+	/* check whether the other slot has disabled the same index already */
+	if (index == amd_get_l3_disable_slot(nb, !slot))
+		return -EEXIST;
+
+	amd_l3_disable_index(nb, cpu, slot, index);
+
+	return 0;
+}
+
+static ssize_t store_cache_disable(struct cacheinfo *ci, const char *buf,
+				   size_t count, unsigned int slot)
+{
+	struct amd_northbridge *nb = ci->priv;
+	unsigned long val = 0;
+	int cpu, err = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	cpu = cpumask_first(&ci->shared_cpu_map);
+
+	if (kstrtoul(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	err = amd_set_l3_disable_slot(nb, cpu, slot, val);
+	if (err) {
+		if (err == -EEXIST)
+			pr_warn("L3 slot %d in use/index already disabled!\n",
+				   slot);
+		return err;
+	}
+	return count;
+}
+
+#define STORE_CACHE_DISABLE(slot)					\
+static ssize_t								\
+cache_disable_##slot##_store(struct device *dev,			\
+			     struct device_attribute *attr,		\
+			     const char *buf, size_t count)		\
+{									\
+	struct cacheinfo *ci = dev_get_drvdata(dev);			\
+	return store_cache_disable(ci, buf, count, slot);		\
+}
+
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static ssize_t subcaches_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	int cpu = cpumask_first(&ci->shared_cpu_map);
+
+	return sysfs_emit(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t subcaches_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	int cpu = cpumask_first(&ci->shared_cpu_map);
+	unsigned long val;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (kstrtoul(buf, 16, &val) < 0)
+		return -EINVAL;
+
+	if (amd_set_subcaches(cpu, val))
+		return -EINVAL;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(cache_disable_0);
+static DEVICE_ATTR_RW(cache_disable_1);
+static DEVICE_ATTR_RW(subcaches);
+
+static umode_t cache_private_attrs_is_visible(struct kobject *kobj,
+					      struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cacheinfo *ci = dev_get_drvdata(dev);
+	umode_t mode = attr->mode;
+
+	if (!ci->priv)
+		return 0;
+
+	if ((attr == &dev_attr_subcaches.attr) &&
+	    amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		return mode;
+
+	if ((attr == &dev_attr_cache_disable_0.attr ||
+	     attr == &dev_attr_cache_disable_1.attr) &&
+	    amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		return mode;
+
+	return 0;
+}
+
+static struct attribute_group cache_private_group = {
+	.is_visible = cache_private_attrs_is_visible,
+};
+
+static void init_amd_l3_attrs(void)
+{
+	static struct attribute **amd_l3_attrs;
+	int n = 1;
+
+	if (amd_l3_attrs) /* already initialized */
+		return;
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		n += 1;
+
+	amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL);
+	if (!amd_l3_attrs)
+		return;
+
+	n = 0;
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr;
+		amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr;
+	}
+	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+		amd_l3_attrs[n++] = &dev_attr_subcaches.attr;
+
+	cache_private_group.attrs = amd_l3_attrs;
+}
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *ci)
+{
+	struct amd_northbridge *nb = ci->priv;
+
+	if (ci->level < 3 || !nb)
+		return NULL;
+
+	if (nb && nb->l3_cache.indices)
+		init_amd_l3_attrs();
+
+	return &cache_private_group;
+}
+
+struct amd_northbridge *amd_init_l3_cache(int index)
+{
+	struct amd_northbridge *nb;
+	int node;
+
+	/* only for L3, and not in virtualized environments */
+	if (index < 3)
+		return NULL;
+
+	node = topology_amd_node_id(smp_processor_id());
+	nb = node_to_amd_nb(node);
+	if (nb && !nb->l3_cache.indices)
+		amd_calc_l3_indices(nb);
+
+	return nb;
+}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index f642de2ebdac..a315b0627dfb 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -20,6 +20,7 @@
 #include <asm/cpu.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -40,8 +41,8 @@ static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
 
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
+	rdmsrq(MSR_IA32_APERF, aperf);
+	rdmsrq(MSR_IA32_MPERF, mperf);
 
 	this_cpu_write(cpu_samples.aperf, aperf);
 	this_cpu_write(cpu_samples.mperf, mperf);
@@ -99,7 +100,7 @@ static bool __init turbo_disabled(void)
 	u64 misc_en;
 	int err;
 
-	err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+	err = rdmsrq_safe(MSR_IA32_MISC_ENABLE, &misc_en);
 	if (err)
 		return false;
 
@@ -110,11 +111,11 @@ static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 {
 	int err;
 
-	err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+	err = rdmsrq_safe(MSR_ATOM_CORE_RATIOS, base_freq);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+	err = rdmsrq_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
 	if (err)
 		return false;
 
@@ -152,13 +153,13 @@ static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
 	int err, i;
 	u64 msr;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
 	*base_freq = (*base_freq >> 8) & 0xFF;	    /* max P state */
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;
 
@@ -190,17 +191,17 @@ static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int s
 	u32 group_size;
 	int err, i;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
 	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
 	if (err)
 		return false;
 
@@ -220,11 +221,11 @@ static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 	u64 msr;
 	int err;
 
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;
 
@@ -474,8 +475,8 @@ void arch_scale_freq_tick(void)
 	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
 		return;
 
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
+	rdmsrq(MSR_IA32_APERF, aperf);
+	rdmsrq(MSR_IA32_MPERF, mperf);
 	acnt = aperf - s->aperf;
 	mcnt = mperf - s->mperf;
 
@@ -498,7 +499,7 @@ void arch_scale_freq_tick(void)
  */
 #define MAX_SAMPLE_AGE	((unsigned long)HZ / 50)
 
-unsigned int arch_freq_get_on_cpu(int cpu)
+int arch_freq_get_on_cpu(int cpu)
 {
 	struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu);
 	unsigned int seq, freq;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a5d0998d7604..7f94e6a5497d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,21 +34,66 @@
 
 #include "cpu.h"
 
+/*
+ * Speculation Vulnerability Handling
+ *
+ * Each vulnerability is handled with the following functions:
+ *   <vuln>_select_mitigation() -- Selects a mitigation to use.  This should
+ *				   take into account all relevant command line
+ *				   options.
+ *   <vuln>_update_mitigation() -- This is called after all vulnerabilities have
+ *				   selected a mitigation, in case the selection
+ *				   may want to change based on other choices
+ *				   made.  This function is optional.
+ *   <vuln>_apply_mitigation() -- Enable the selected mitigation.
+ *
+ * The compile-time mitigation in all cases should be AUTO.  An explicit
+ * command-line option can override AUTO.  If no such option is
+ * provided, <vuln>_select_mitigation() will override AUTO to the best
+ * mitigation option.
+ */
+
 static void __init spectre_v1_select_mitigation(void);
+static void __init spectre_v1_apply_mitigation(void);
 static void __init spectre_v2_select_mitigation(void);
+static void __init spectre_v2_update_mitigation(void);
+static void __init spectre_v2_apply_mitigation(void);
 static void __init retbleed_select_mitigation(void);
+static void __init retbleed_update_mitigation(void);
+static void __init retbleed_apply_mitigation(void);
 static void __init spectre_v2_user_select_mitigation(void);
+static void __init spectre_v2_user_update_mitigation(void);
+static void __init spectre_v2_user_apply_mitigation(void);
 static void __init ssb_select_mitigation(void);
+static void __init ssb_apply_mitigation(void);
 static void __init l1tf_select_mitigation(void);
+static void __init l1tf_apply_mitigation(void);
 static void __init mds_select_mitigation(void);
-static void __init md_clear_update_mitigation(void);
-static void __init md_clear_select_mitigation(void);
+static void __init mds_update_mitigation(void);
+static void __init mds_apply_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init taa_update_mitigation(void);
+static void __init taa_apply_mitigation(void);
 static void __init mmio_select_mitigation(void);
+static void __init mmio_update_mitigation(void);
+static void __init mmio_apply_mitigation(void);
+static void __init rfds_select_mitigation(void);
+static void __init rfds_update_mitigation(void);
+static void __init rfds_apply_mitigation(void);
 static void __init srbds_select_mitigation(void);
+static void __init srbds_apply_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 static void __init srso_select_mitigation(void);
+static void __init srso_update_mitigation(void);
+static void __init srso_apply_mitigation(void);
 static void __init gds_select_mitigation(void);
+static void __init gds_apply_mitigation(void);
+static void __init bhi_select_mitigation(void);
+static void __init bhi_update_mitigation(void);
+static void __init bhi_apply_mitigation(void);
+static void __init its_select_mitigation(void);
+static void __init its_update_mitigation(void);
+static void __init its_apply_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -59,7 +104,6 @@ DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
 EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
-EXPORT_SYMBOL_GPL(x86_pred_cmd);
 
 static u64 __ro_after_init x86_arch_cap_msr;
 
@@ -67,11 +111,19 @@ static DEFINE_MUTEX(spec_ctrl_mutex);
 
 void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
 
+static void __init set_return_thunk(void *thunk)
+{
+	if (x86_return_thunk != __x86_return_thunk)
+		pr_warn("x86/bugs: return thunk changed\n");
+
+	x86_return_thunk = thunk;
+}
+
 /* Update SPEC_CTRL MSR and its cached copy unconditionally */
 static void update_spec_ctrl(u64 val)
 {
 	this_cpu_write(x86_spec_ctrl_current, val);
-	wrmsrl(MSR_IA32_SPEC_CTRL, val);
+	wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 /*
@@ -90,7 +142,7 @@ void update_spec_ctrl_cond(u64 val)
 	 * forced the update can be delayed until that time.
 	 */
 	if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
-		wrmsrl(MSR_IA32_SPEC_CTRL, val);
+		wrmsrq(MSR_IA32_SPEC_CTRL, val);
 }
 
 noinstr u64 spec_ctrl_current(void)
@@ -113,6 +165,10 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control IBPB on vCPU load */
+DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
+EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
+
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -124,9 +180,13 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
  */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
-/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */
-DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
-EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
+/*
+ * Controls CPU Fill buffer clear before VMenter. This is a subset of
+ * X86_FEATURE_CLEAR_CPU_BUF, and should only be enabled when KVM-only
+ * mitigation is required.
+ */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_vm_clear);
 
 void __init cpu_select_mitigations(void)
 {
@@ -136,7 +196,7 @@ void __init cpu_select_mitigations(void)
 	 * init code as it is not enumerated and depends on the family.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
-		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		rdmsrq(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
 		/*
 		 * Previously running kernel (kexec), may have some controls
@@ -151,30 +211,67 @@ void __init cpu_select_mitigations(void)
 	/* Select the proper CPU mitigations before patching alternatives: */
 	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
-	/*
-	 * retbleed_select_mitigation() relies on the state set by
-	 * spectre_v2_select_mitigation(); specifically it wants to know about
-	 * spectre_v2=ibrs.
-	 */
 	retbleed_select_mitigation();
-	/*
-	 * spectre_v2_user_select_mitigation() relies on the state set by
-	 * retbleed_select_mitigation(); specifically the STIBP selection is
-	 * forced for UNRET or IBPB.
-	 */
 	spectre_v2_user_select_mitigation();
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
-	md_clear_select_mitigation();
+	mds_select_mitigation();
+	taa_select_mitigation();
+	mmio_select_mitigation();
+	rfds_select_mitigation();
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();
+	srso_select_mitigation();
+	gds_select_mitigation();
+	its_select_mitigation();
+	bhi_select_mitigation();
 
 	/*
-	 * srso_select_mitigation() depends and must run after
-	 * retbleed_select_mitigation().
+	 * After mitigations are selected, some may need to update their
+	 * choices.
 	 */
-	srso_select_mitigation();
-	gds_select_mitigation();
+	spectre_v2_update_mitigation();
+	/*
+	 * retbleed_update_mitigation() relies on the state set by
+	 * spectre_v2_update_mitigation(); specifically it wants to know about
+	 * spectre_v2=ibrs.
+	 */
+	retbleed_update_mitigation();
+	/*
+	 * its_update_mitigation() depends on spectre_v2_update_mitigation()
+	 * and retbleed_update_mitigation().
+	 */
+	its_update_mitigation();
+
+	/*
+	 * spectre_v2_user_update_mitigation() depends on
+	 * retbleed_update_mitigation(), specifically the STIBP
+	 * selection is forced for UNRET or IBPB.
+	 */
+	spectre_v2_user_update_mitigation();
+	mds_update_mitigation();
+	taa_update_mitigation();
+	mmio_update_mitigation();
+	rfds_update_mitigation();
+	bhi_update_mitigation();
+	/* srso_update_mitigation() depends on retbleed_update_mitigation(). */
+	srso_update_mitigation();
+
+	spectre_v1_apply_mitigation();
+	spectre_v2_apply_mitigation();
+	retbleed_apply_mitigation();
+	spectre_v2_user_apply_mitigation();
+	ssb_apply_mitigation();
+	l1tf_apply_mitigation();
+	mds_apply_mitigation();
+	taa_apply_mitigation();
+	mmio_apply_mitigation();
+	rfds_apply_mitigation();
+	srbds_apply_mitigation();
+	srso_apply_mitigation();
+	gds_apply_mitigation();
+	its_apply_mitigation();
+	bhi_apply_mitigation();
 }
 
 /*
@@ -224,9 +321,9 @@ static void x86_amd_ssb_disable(void)
 	u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
 
 	if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
-		wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+		wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
 	else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
-		wrmsrl(MSR_AMD64_LS_CFG, msrval);
+		wrmsrq(MSR_AMD64_LS_CFG, msrval);
 }
 
 #undef pr_fmt
@@ -234,7 +331,7 @@ static void x86_amd_ssb_disable(void)
 
 /* Default mitigation for MDS-affected CPUs */
 static enum mds_mitigations mds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_FULL : MDS_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_AUTO : MDS_MITIGATION_OFF;
 static bool mds_nosmt __ro_after_init = false;
 
 static const char * const mds_strings[] = {
@@ -243,6 +340,46 @@ static const char * const mds_strings[] = {
 	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
 };
 
+enum taa_mitigations {
+	TAA_MITIGATION_OFF,
+	TAA_MITIGATION_AUTO,
+	TAA_MITIGATION_UCODE_NEEDED,
+	TAA_MITIGATION_VERW,
+	TAA_MITIGATION_TSX_DISABLED,
+};
+
+/* Default mitigation for TAA-affected CPUs */
+static enum taa_mitigations taa_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_AUTO : TAA_MITIGATION_OFF;
+
+enum mmio_mitigations {
+	MMIO_MITIGATION_OFF,
+	MMIO_MITIGATION_AUTO,
+	MMIO_MITIGATION_UCODE_NEEDED,
+	MMIO_MITIGATION_VERW,
+};
+
+/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
+static enum mmio_mitigations mmio_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ?	MMIO_MITIGATION_AUTO : MMIO_MITIGATION_OFF;
+
+enum rfds_mitigations {
+	RFDS_MITIGATION_OFF,
+	RFDS_MITIGATION_AUTO,
+	RFDS_MITIGATION_VERW,
+	RFDS_MITIGATION_UCODE_NEEDED,
+};
+
+/* Default mitigation for Register File Data Sampling */
+static enum rfds_mitigations rfds_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_AUTO : RFDS_MITIGATION_OFF;
+
+/*
+ * Set if any of MDS/TAA/MMIO/RFDS are going to enable VERW clearing
+ * through X86_FEATURE_CLEAR_CPU_BUF on kernel and guest entry.
+ */
+static bool verw_clear_cpu_buf_mitigation_selected __ro_after_init;
+
 static void __init mds_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
@@ -250,12 +387,37 @@ static void __init mds_select_mitigation(void)
 		return;
 	}
 
+	if (mds_mitigation == MDS_MITIGATION_AUTO)
+		mds_mitigation = MDS_MITIGATION_FULL;
+
+	if (mds_mitigation == MDS_MITIGATION_OFF)
+		return;
+
+	verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init mds_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
+		return;
+
+	/* If TAA, MMIO, or RFDS are being mitigated, MDS gets mitigated too. */
+	if (verw_clear_cpu_buf_mitigation_selected)
+		mds_mitigation = MDS_MITIGATION_FULL;
+
 	if (mds_mitigation == MDS_MITIGATION_FULL) {
 		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
+	}
 
-		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+	pr_info("%s\n", mds_strings[mds_mitigation]);
+}
 
+static void __init mds_apply_mitigation(void)
+{
+	if (mds_mitigation == MDS_MITIGATION_FULL ||
+	    mds_mitigation == MDS_MITIGATION_VMWERV) {
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
 			cpu_smt_disable(false);
@@ -286,16 +448,6 @@ early_param("mds", mds_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"TAA: " fmt
 
-enum taa_mitigations {
-	TAA_MITIGATION_OFF,
-	TAA_MITIGATION_UCODE_NEEDED,
-	TAA_MITIGATION_VERW,
-	TAA_MITIGATION_TSX_DISABLED,
-};
-
-/* Default mitigation for TAA-affected CPUs */
-static enum taa_mitigations taa_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF;
 static bool taa_nosmt __ro_after_init;
 
 static const char * const taa_strings[] = {
@@ -305,6 +457,11 @@ static const char * const taa_strings[] = {
 	[TAA_MITIGATION_TSX_DISABLED]	= "Mitigation: TSX disabled",
 };
 
+static bool __init taa_vulnerable(void)
+{
+	return boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM);
+}
+
 static void __init taa_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_TAA)) {
@@ -318,48 +475,63 @@ static void __init taa_select_mitigation(void)
 		return;
 	}
 
-	if (cpu_mitigations_off()) {
+	if (cpu_mitigations_off())
 		taa_mitigation = TAA_MITIGATION_OFF;
-		return;
-	}
 
-	/*
-	 * TAA mitigation via VERW is turned off if both
-	 * tsx_async_abort=off and mds=off are specified.
-	 */
-	if (taa_mitigation == TAA_MITIGATION_OFF &&
-	    mds_mitigation == MDS_MITIGATION_OFF)
+	/* Microcode will be checked in taa_update_mitigation(). */
+	if (taa_mitigation == TAA_MITIGATION_AUTO)
+		taa_mitigation = TAA_MITIGATION_VERW;
+
+	if (taa_mitigation != TAA_MITIGATION_OFF)
+		verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init taa_update_mitigation(void)
+{
+	if (!taa_vulnerable() || cpu_mitigations_off())
 		return;
 
-	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
+	if (verw_clear_cpu_buf_mitigation_selected)
 		taa_mitigation = TAA_MITIGATION_VERW;
-	else
-		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
 
-	/*
-	 * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
-	 * A microcode update fixes this behavior to clear CPU buffers. It also
-	 * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
-	 * ARCH_CAP_TSX_CTRL_MSR bit.
-	 *
-	 * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
-	 * update is required.
-	 */
-	if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
-	    !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
-		taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+	if (taa_mitigation == TAA_MITIGATION_VERW) {
+		/* Check if the requisite ucode is available. */
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+			taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
 
-	/*
-	 * TSX is enabled, select alternate mitigation for TAA which is
-	 * the same as MDS. Enable MDS static branch to clear CPU buffers.
-	 *
-	 * For guests that can't determine whether the correct microcode is
-	 * present on host, enable the mitigation for UCODE_NEEDED as well.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		/*
+		 * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
+		 * A microcode update fixes this behavior to clear CPU buffers. It also
+		 * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
+		 * ARCH_CAP_TSX_CTRL_MSR bit.
+		 *
+		 * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
+		 * update is required.
+		 */
+		if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
+		   !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
+			taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+	}
 
-	if (taa_nosmt || cpu_mitigations_auto_nosmt())
-		cpu_smt_disable(false);
+	pr_info("%s\n", taa_strings[taa_mitigation]);
+}
+
+static void __init taa_apply_mitigation(void)
+{
+	if (taa_mitigation == TAA_MITIGATION_VERW ||
+	    taa_mitigation == TAA_MITIGATION_UCODE_NEEDED) {
+		/*
+		 * TSX is enabled, select alternate mitigation for TAA which is
+		 * the same as MDS. Enable MDS static branch to clear CPU buffers.
+		 *
+		 * For guests that can't determine whether the correct microcode is
+		 * present on host, enable the mitigation for UCODE_NEEDED as well.
+		 */
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+
+		if (taa_nosmt || cpu_mitigations_auto_nosmt())
+			cpu_smt_disable(false);
+	}
 }
 
 static int __init tsx_async_abort_parse_cmdline(char *str)
@@ -386,15 +558,6 @@ early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"MMIO Stale Data: " fmt
 
-enum mmio_mitigations {
-	MMIO_MITIGATION_OFF,
-	MMIO_MITIGATION_UCODE_NEEDED,
-	MMIO_MITIGATION_VERW,
-};
-
-/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
-static enum mmio_mitigations mmio_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF;
 static bool mmio_nosmt __ro_after_init = false;
 
 static const char * const mmio_strings[] = {
@@ -406,31 +569,67 @@ static const char * const mmio_strings[] = {
 static void __init mmio_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
-	     boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
 	     cpu_mitigations_off()) {
 		mmio_mitigation = MMIO_MITIGATION_OFF;
 		return;
 	}
 
+	/* Microcode will be checked in mmio_update_mitigation(). */
+	if (mmio_mitigation == MMIO_MITIGATION_AUTO)
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return;
 
 	/*
 	 * Enable CPU buffer clear mitigation for host and VMM, if also affected
-	 * by MDS or TAA. Otherwise, enable mitigation for VMM only.
+	 * by MDS or TAA.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
-					      boot_cpu_has(X86_FEATURE_RTM)))
-		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+	if (boot_cpu_has_bug(X86_BUG_MDS) || taa_vulnerable())
+		verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init mmio_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || cpu_mitigations_off())
+		return;
+
+	if (verw_clear_cpu_buf_mitigation_selected)
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+
+	if (mmio_mitigation == MMIO_MITIGATION_VERW) {
+		/*
+		 * Check if the system has the right microcode.
+		 *
+		 * CPU Fill buffer clear mitigation is enumerated by either an explicit
+		 * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
+		 * affected systems.
+		 */
+		if (!((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
+		      (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
+		       boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
+		     !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))))
+			mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
+	}
+
+	pr_info("%s\n", mmio_strings[mmio_mitigation]);
+}
+
+static void __init mmio_apply_mitigation(void)
+{
+	if (mmio_mitigation == MMIO_MITIGATION_OFF)
+		return;
 
 	/*
-	 * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based
-	 * mitigations, disable KVM-only mitigation in that case.
+	 * Only enable the VMM mitigation if the CPU buffer clear mitigation is
+	 * not being used.
 	 */
-	if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
-		static_branch_disable(&mmio_stale_data_clear);
-	else
-		static_branch_enable(&mmio_stale_data_clear);
+	if (verw_clear_cpu_buf_mitigation_selected) {
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		static_branch_disable(&cpu_buf_vm_clear);
+	} else {
+		static_branch_enable(&cpu_buf_vm_clear);
+	}
 
 	/*
 	 * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can
@@ -440,21 +639,6 @@ static void __init mmio_select_mitigation(void)
 	if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
 		static_branch_enable(&mds_idle_clear);
 
-	/*
-	 * Check if the system has the right microcode.
-	 *
-	 * CPU Fill buffer clear mitigation is enumerated by either an explicit
-	 * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
-	 * affected systems.
-	 */
-	if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
-	    (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
-	     boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
-	     !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)))
-		mmio_mitigation = MMIO_MITIGATION_VERW;
-	else
-		mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
-
 	if (mmio_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
 }
@@ -483,35 +667,54 @@ early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
 #undef pr_fmt
 #define pr_fmt(fmt)	"Register File Data Sampling: " fmt
 
-enum rfds_mitigations {
-	RFDS_MITIGATION_OFF,
-	RFDS_MITIGATION_VERW,
-	RFDS_MITIGATION_UCODE_NEEDED,
-};
-
-/* Default mitigation for Register File Data Sampling */
-static enum rfds_mitigations rfds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
-
 static const char * const rfds_strings[] = {
 	[RFDS_MITIGATION_OFF]			= "Vulnerable",
 	[RFDS_MITIGATION_VERW]			= "Mitigation: Clear Register File",
 	[RFDS_MITIGATION_UCODE_NEEDED]		= "Vulnerable: No microcode",
 };
 
+static inline bool __init verw_clears_cpu_reg_file(void)
+{
+	return (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR);
+}
+
 static void __init rfds_select_mitigation(void)
 {
 	if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) {
 		rfds_mitigation = RFDS_MITIGATION_OFF;
 		return;
 	}
+
+	if (rfds_mitigation == RFDS_MITIGATION_AUTO)
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+
 	if (rfds_mitigation == RFDS_MITIGATION_OFF)
 		return;
 
-	if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
+	if (verw_clears_cpu_reg_file())
+		verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init rfds_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off())
+		return;
+
+	if (verw_clear_cpu_buf_mitigation_selected)
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+
+	if (rfds_mitigation == RFDS_MITIGATION_VERW) {
+		if (!verw_clears_cpu_reg_file())
+			rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
+	}
+
+	pr_info("%s\n", rfds_strings[rfds_mitigation]);
+}
+
+static void __init rfds_apply_mitigation(void)
+{
+	if (rfds_mitigation == RFDS_MITIGATION_VERW)
 		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
-	else
-		rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
 }
 
 static __init int rfds_parse_cmdline(char *str)
@@ -532,76 +735,11 @@ static __init int rfds_parse_cmdline(char *str)
 early_param("reg_file_data_sampling", rfds_parse_cmdline);
 
 #undef pr_fmt
-#define pr_fmt(fmt)     "" fmt
-
-static void __init md_clear_update_mitigation(void)
-{
-	if (cpu_mitigations_off())
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
-		goto out;
-
-	/*
-	 * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
-	 * Stale Data mitigation, if necessary.
-	 */
-	if (mds_mitigation == MDS_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_MDS)) {
-		mds_mitigation = MDS_MITIGATION_FULL;
-		mds_select_mitigation();
-	}
-	if (taa_mitigation == TAA_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_TAA)) {
-		taa_mitigation = TAA_MITIGATION_VERW;
-		taa_select_mitigation();
-	}
-	/*
-	 * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear
-	 * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state.
-	 */
-	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
-		mmio_mitigation = MMIO_MITIGATION_VERW;
-		mmio_select_mitigation();
-	}
-	if (rfds_mitigation == RFDS_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_RFDS)) {
-		rfds_mitigation = RFDS_MITIGATION_VERW;
-		rfds_select_mitigation();
-	}
-out:
-	if (boot_cpu_has_bug(X86_BUG_MDS))
-		pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
-	if (boot_cpu_has_bug(X86_BUG_TAA))
-		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
-	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
-		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
-	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
-		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
-	if (boot_cpu_has_bug(X86_BUG_RFDS))
-		pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]);
-}
-
-static void __init md_clear_select_mitigation(void)
-{
-	mds_select_mitigation();
-	taa_select_mitigation();
-	mmio_select_mitigation();
-	rfds_select_mitigation();
-
-	/*
-	 * As these mitigations are inter-related and rely on VERW instruction
-	 * to clear the microarchitural buffers, update and print their status
-	 * after mitigation selection is done for each of these vulnerabilities.
-	 */
-	md_clear_update_mitigation();
-}
-
-#undef pr_fmt
 #define pr_fmt(fmt)	"SRBDS: " fmt
 
 enum srbds_mitigations {
 	SRBDS_MITIGATION_OFF,
+	SRBDS_MITIGATION_AUTO,
 	SRBDS_MITIGATION_UCODE_NEEDED,
 	SRBDS_MITIGATION_FULL,
 	SRBDS_MITIGATION_TSX_OFF,
@@ -609,7 +747,7 @@ enum srbds_mitigations {
 };
 
 static enum srbds_mitigations srbds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_SRBDS) ? SRBDS_MITIGATION_FULL : SRBDS_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_SRBDS) ? SRBDS_MITIGATION_AUTO : SRBDS_MITIGATION_OFF;
 
 static const char * const srbds_strings[] = {
 	[SRBDS_MITIGATION_OFF]		= "Vulnerable",
@@ -641,7 +779,7 @@ void update_srbds_msr(void)
 	if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 
 	switch (srbds_mitigation) {
 	case SRBDS_MITIGATION_OFF:
@@ -655,13 +793,18 @@ void update_srbds_msr(void)
 		break;
 	}
 
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 }
 
 static void __init srbds_select_mitigation(void)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS) || cpu_mitigations_off()) {
+		srbds_mitigation = SRBDS_MITIGATION_OFF;
 		return;
+	}
+
+	if (srbds_mitigation == SRBDS_MITIGATION_AUTO)
+		srbds_mitigation = SRBDS_MITIGATION_FULL;
 
 	/*
 	 * Check to see if this is one of the MDS_NO systems supporting TSX that
@@ -675,13 +818,17 @@ static void __init srbds_select_mitigation(void)
 		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
 	else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
 		srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
-	else if (cpu_mitigations_off() || srbds_off)
+	else if (srbds_off)
 		srbds_mitigation = SRBDS_MITIGATION_OFF;
 
-	update_srbds_msr();
 	pr_info("%s\n", srbds_strings[srbds_mitigation]);
 }
 
+static void __init srbds_apply_mitigation(void)
+{
+	update_srbds_msr();
+}
+
 static int __init srbds_parse_cmdline(char *str)
 {
 	if (!str)
@@ -728,6 +875,7 @@ early_param("l1d_flush", l1d_flush_parse_cmdline);
 
 enum gds_mitigations {
 	GDS_MITIGATION_OFF,
+	GDS_MITIGATION_AUTO,
 	GDS_MITIGATION_UCODE_NEEDED,
 	GDS_MITIGATION_FORCE,
 	GDS_MITIGATION_FULL,
@@ -736,7 +884,7 @@ enum gds_mitigations {
 };
 
 static enum gds_mitigations gds_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_GDS) ? GDS_MITIGATION_FULL : GDS_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_GDS) ? GDS_MITIGATION_AUTO : GDS_MITIGATION_OFF;
 
 static const char * const gds_strings[] = {
 	[GDS_MITIGATION_OFF]		= "Vulnerable",
@@ -761,7 +909,7 @@ void update_gds_msr(void)
 
 	switch (gds_mitigation) {
 	case GDS_MITIGATION_OFF:
-		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 		mcu_ctrl |= GDS_MITG_DIS;
 		break;
 	case GDS_MITIGATION_FULL_LOCKED:
@@ -771,23 +919,24 @@ void update_gds_msr(void)
 		 * CPUs.
 		 */
 	case GDS_MITIGATION_FULL:
-		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 		mcu_ctrl &= ~GDS_MITG_DIS;
 		break;
 	case GDS_MITIGATION_FORCE:
 	case GDS_MITIGATION_UCODE_NEEDED:
 	case GDS_MITIGATION_HYPERVISOR:
+	case GDS_MITIGATION_AUTO:
 		return;
 	}
 
-	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 
 	/*
 	 * Check to make sure that the WRMSR value was not ignored. Writes to
 	 * GDS_MITG_DIS will be ignored if this processor is locked but the boot
 	 * processor was not.
 	 */
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
 	WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
 }
 
@@ -800,33 +949,28 @@ static void __init gds_select_mitigation(void)
 
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
 		gds_mitigation = GDS_MITIGATION_HYPERVISOR;
-		goto out;
+		return;
 	}
 
 	if (cpu_mitigations_off())
 		gds_mitigation = GDS_MITIGATION_OFF;
 	/* Will verify below that mitigation _can_ be disabled */
 
+	if (gds_mitigation == GDS_MITIGATION_AUTO)
+		gds_mitigation = GDS_MITIGATION_FULL;
+
 	/* No microcode */
 	if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) {
-		if (gds_mitigation == GDS_MITIGATION_FORCE) {
-			/*
-			 * This only needs to be done on the boot CPU so do it
-			 * here rather than in update_gds_msr()
-			 */
-			setup_clear_cpu_cap(X86_FEATURE_AVX);
-			pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
-		} else {
+		if (gds_mitigation != GDS_MITIGATION_FORCE)
 			gds_mitigation = GDS_MITIGATION_UCODE_NEEDED;
-		}
-		goto out;
+		return;
 	}
 
 	/* Microcode has mitigation, use it */
 	if (gds_mitigation == GDS_MITIGATION_FORCE)
 		gds_mitigation = GDS_MITIGATION_FULL;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
 	if (mcu_ctrl & GDS_MITG_LOCKED) {
 		if (gds_mitigation == GDS_MITIGATION_OFF)
 			pr_warn("Mitigation locked. Disable failed.\n");
@@ -840,9 +984,25 @@ static void __init gds_select_mitigation(void)
 		 */
 		gds_mitigation = GDS_MITIGATION_FULL_LOCKED;
 	}
+}
+
+static void __init gds_apply_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_GDS))
+		return;
+
+	/* Microcode is present */
+	if (x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)
+		update_gds_msr();
+	else if (gds_mitigation == GDS_MITIGATION_FORCE) {
+		/*
+		 * This only needs to be done on the boot CPU so do it
+		 * here rather than in update_gds_msr()
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_AVX);
+		pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
+	}
 
-	update_gds_msr();
-out:
 	pr_info("%s\n", gds_strings[gds_mitigation]);
 }
 
@@ -903,10 +1063,14 @@ static bool smap_works_speculatively(void)
 
 static void __init spectre_v1_select_mitigation(void)
 {
-	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) {
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off())
 		spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+}
+
+static void __init spectre_v1_apply_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off())
 		return;
-	}
 
 	if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) {
 		/*
@@ -959,8 +1123,20 @@ enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE;
 #undef pr_fmt
 #define pr_fmt(fmt)     "RETBleed: " fmt
 
+enum its_mitigation {
+	ITS_MITIGATION_OFF,
+	ITS_MITIGATION_AUTO,
+	ITS_MITIGATION_VMEXIT_ONLY,
+	ITS_MITIGATION_ALIGNED_THUNKS,
+	ITS_MITIGATION_RETPOLINE_STUFF,
+};
+
+static enum its_mitigation its_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_MITIGATION_AUTO : ITS_MITIGATION_OFF;
+
 enum retbleed_mitigation {
 	RETBLEED_MITIGATION_NONE,
+	RETBLEED_MITIGATION_AUTO,
 	RETBLEED_MITIGATION_UNRET,
 	RETBLEED_MITIGATION_IBPB,
 	RETBLEED_MITIGATION_IBRS,
@@ -968,14 +1144,6 @@ enum retbleed_mitigation {
 	RETBLEED_MITIGATION_STUFF,
 };
 
-enum retbleed_mitigation_cmd {
-	RETBLEED_CMD_OFF,
-	RETBLEED_CMD_AUTO,
-	RETBLEED_CMD_UNRET,
-	RETBLEED_CMD_IBPB,
-	RETBLEED_CMD_STUFF,
-};
-
 static const char * const retbleed_strings[] = {
 	[RETBLEED_MITIGATION_NONE]	= "Vulnerable",
 	[RETBLEED_MITIGATION_UNRET]	= "Mitigation: untrained return thunk",
@@ -986,9 +1154,7 @@ static const char * const retbleed_strings[] = {
 };
 
 static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
-	RETBLEED_MITIGATION_NONE;
-static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_RETBLEED) ? RETBLEED_CMD_AUTO : RETBLEED_CMD_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_RETBLEED) ? RETBLEED_MITIGATION_AUTO : RETBLEED_MITIGATION_NONE;
 
 static int __ro_after_init retbleed_nosmt = false;
 
@@ -1005,15 +1171,15 @@ static int __init retbleed_parse_cmdline(char *str)
 		}
 
 		if (!strcmp(str, "off")) {
-			retbleed_cmd = RETBLEED_CMD_OFF;
+			retbleed_mitigation = RETBLEED_MITIGATION_NONE;
 		} else if (!strcmp(str, "auto")) {
-			retbleed_cmd = RETBLEED_CMD_AUTO;
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
 		} else if (!strcmp(str, "unret")) {
-			retbleed_cmd = RETBLEED_CMD_UNRET;
+			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
 		} else if (!strcmp(str, "ibpb")) {
-			retbleed_cmd = RETBLEED_CMD_IBPB;
+			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
 		} else if (!strcmp(str, "stuff")) {
-			retbleed_cmd = RETBLEED_CMD_STUFF;
+			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
 		} else if (!strcmp(str, "nosmt")) {
 			retbleed_nosmt = true;
 		} else if (!strcmp(str, "force")) {
@@ -1034,77 +1200,122 @@ early_param("retbleed", retbleed_parse_cmdline);
 
 static void __init retbleed_select_mitigation(void)
 {
-	bool mitigate_smt = false;
-
-	if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off())
-		return;
-
-	switch (retbleed_cmd) {
-	case RETBLEED_CMD_OFF:
+	if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off()) {
+		retbleed_mitigation = RETBLEED_MITIGATION_NONE;
 		return;
+	}
 
-	case RETBLEED_CMD_UNRET:
-		if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) {
-			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
-		} else {
+	switch (retbleed_mitigation) {
+	case RETBLEED_MITIGATION_UNRET:
+		if (!IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) {
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
 			pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n");
-			goto do_cmd_auto;
 		}
 		break;
-
-	case RETBLEED_CMD_IBPB:
+	case RETBLEED_MITIGATION_IBPB:
 		if (!boot_cpu_has(X86_FEATURE_IBPB)) {
 			pr_err("WARNING: CPU does not support IBPB.\n");
-			goto do_cmd_auto;
-		} else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
-			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
-		} else {
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+		} else if (!IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
-			goto do_cmd_auto;
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
 		}
 		break;
+	case RETBLEED_MITIGATION_STUFF:
+		if (!IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) {
+			pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n");
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+		} else if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+			pr_err("WARNING: retbleed=stuff only supported for Intel CPUs.\n");
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+		}
+		break;
+	default:
+		break;
+	}
 
-	case RETBLEED_CMD_STUFF:
-		if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) &&
-		    spectre_v2_enabled == SPECTRE_V2_RETPOLINE) {
-			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+	if (retbleed_mitigation != RETBLEED_MITIGATION_AUTO)
+		return;
+
+	/* Intel mitigation selected in retbleed_update_mitigation() */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+		if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY))
+			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+		else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) &&
+			 boot_cpu_has(X86_FEATURE_IBPB))
+			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+		else
+			retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+	}
+}
+
+static void __init retbleed_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off())
+		return;
 
+	if (retbleed_mitigation == RETBLEED_MITIGATION_NONE)
+		goto out;
+
+	/*
+	 * retbleed=stuff is only allowed on Intel.  If stuffing can't be used
+	 * then a different mitigation will be selected below.
+	 *
+	 * its=stuff will also attempt to enable stuffing.
+	 */
+	if (retbleed_mitigation == RETBLEED_MITIGATION_STUFF ||
+	    its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF) {
+		if (spectre_v2_enabled != SPECTRE_V2_RETPOLINE) {
+			pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
+			retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
 		} else {
-			if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))
-				pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
-			else
-				pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n");
+			if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+				pr_info("Retbleed mitigation updated to stuffing\n");
 
-			goto do_cmd_auto;
+			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
 		}
-		break;
-
-do_cmd_auto:
-	case RETBLEED_CMD_AUTO:
-		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-		    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
-			if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY))
-				retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
-			else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) &&
-				 boot_cpu_has(X86_FEATURE_IBPB))
-				retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+	}
+	/*
+	 * Let IBRS trump all on Intel without affecting the effects of the
+	 * retbleed= cmdline option except for call depth based stuffing
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+		switch (spectre_v2_enabled) {
+		case SPECTRE_V2_IBRS:
+			retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
+			break;
+		case SPECTRE_V2_EIBRS:
+		case SPECTRE_V2_EIBRS_RETPOLINE:
+		case SPECTRE_V2_EIBRS_LFENCE:
+			retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
+			break;
+		default:
+			if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+				pr_err(RETBLEED_INTEL_MSG);
 		}
+		/* If nothing has set the mitigation yet, default to NONE. */
+		if (retbleed_mitigation == RETBLEED_MITIGATION_AUTO)
+			retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+	}
+out:
+	pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
+}
 
-		/*
-		 * The Intel mitigation (IBRS or eIBRS) was already selected in
-		 * spectre_v2_select_mitigation().  'retbleed_mitigation' will
-		 * be set accordingly below.
-		 */
 
-		break;
-	}
+static void __init retbleed_apply_mitigation(void)
+{
+	bool mitigate_smt = false;
 
 	switch (retbleed_mitigation) {
+	case RETBLEED_MITIGATION_NONE:
+		return;
+
 	case RETBLEED_MITIGATION_UNRET:
 		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
 		setup_force_cpu_cap(X86_FEATURE_UNRET);
 
-		x86_return_thunk = retbleed_return_thunk;
+		set_return_thunk(retbleed_return_thunk);
 
 		if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
 		    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1127,7 +1338,7 @@ do_cmd_auto:
 		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
 		/*
-		 * There is no need for RSB filling: entry_ibpb() ensures
+		 * There is no need for RSB filling: write_ibpb() ensures
 		 * all predictions, including the RSB, are invalidated,
 		 * regardless of IBPB implementation.
 		 */
@@ -1139,7 +1350,7 @@ do_cmd_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
 		setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
 
-		x86_return_thunk = call_depth_return_thunk;
+		set_return_thunk(call_depth_return_thunk);
 		break;
 
 	default:
@@ -1149,28 +1360,131 @@ do_cmd_auto:
 	if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) &&
 	    (retbleed_nosmt || cpu_mitigations_auto_nosmt()))
 		cpu_smt_disable(false);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "ITS: " fmt
+
+static const char * const its_strings[] = {
+	[ITS_MITIGATION_OFF]			= "Vulnerable",
+	[ITS_MITIGATION_VMEXIT_ONLY]		= "Mitigation: Vulnerable, KVM: Not affected",
+	[ITS_MITIGATION_ALIGNED_THUNKS]		= "Mitigation: Aligned branch/return thunks",
+	[ITS_MITIGATION_RETPOLINE_STUFF]	= "Mitigation: Retpolines, Stuffing RSB",
+};
+
+static int __init its_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) {
+		pr_err("Mitigation disabled at compile time, ignoring option (%s)", str);
+		return 0;
+	}
+
+	if (!strcmp(str, "off")) {
+		its_mitigation = ITS_MITIGATION_OFF;
+	} else if (!strcmp(str, "on")) {
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+	} else if (!strcmp(str, "force")) {
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+		setup_force_cpu_bug(X86_BUG_ITS);
+	} else if (!strcmp(str, "vmexit")) {
+		its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
+	} else if (!strcmp(str, "stuff")) {
+		its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+	} else {
+		pr_err("Ignoring unknown indirect_target_selection option (%s).", str);
+	}
+
+	return 0;
+}
+early_param("indirect_target_selection", its_parse_cmdline);
+
+static void __init its_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) {
+		its_mitigation = ITS_MITIGATION_OFF;
+		return;
+	}
+
+	if (its_mitigation == ITS_MITIGATION_AUTO)
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+
+	if (its_mitigation == ITS_MITIGATION_OFF)
+		return;
+
+	if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ||
+	    !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) {
+		pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) {
+		pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		return;
+	}
+
+	if (its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF &&
+	    !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) {
+		pr_err("RSB stuff mitigation not supported, using default\n");
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+	}
+
+	if (its_mitigation == ITS_MITIGATION_VMEXIT_ONLY &&
+	    !boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY))
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+}
+
+static void __init its_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off())
+		return;
+
+	switch (spectre_v2_enabled) {
+	case SPECTRE_V2_NONE:
+		pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		break;
+	case SPECTRE_V2_RETPOLINE:
+		/* Retpoline+CDT mitigates ITS */
+		if (retbleed_mitigation == RETBLEED_MITIGATION_STUFF)
+			its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+		break;
+	case SPECTRE_V2_LFENCE:
+	case SPECTRE_V2_EIBRS_LFENCE:
+		pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
+		its_mitigation = ITS_MITIGATION_OFF;
+		break;
+	default:
+		break;
+	}
 
 	/*
-	 * Let IBRS trump all on Intel without affecting the effects of the
-	 * retbleed= cmdline option except for call depth based stuffing
+	 * retbleed_update_mitigation() will try to do stuffing if its=stuff.
+	 * If it can't, such as if spectre_v2!=retpoline, then fall back to
+	 * aligned thunks.
 	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
-		switch (spectre_v2_enabled) {
-		case SPECTRE_V2_IBRS:
-			retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
-			break;
-		case SPECTRE_V2_EIBRS:
-		case SPECTRE_V2_EIBRS_RETPOLINE:
-		case SPECTRE_V2_EIBRS_LFENCE:
-			retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
-			break;
-		default:
-			if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
-				pr_err(RETBLEED_INTEL_MSG);
-		}
-	}
+	if (its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF &&
+	    retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+		its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
 
-	pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
+	pr_info("%s\n", its_strings[its_mitigation]);
+}
+
+static void __init its_apply_mitigation(void)
+{
+	/* its=stuff forces retbleed stuffing and is enabled there. */
+	if (its_mitigation != ITS_MITIGATION_ALIGNED_THUNKS)
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_RETPOLINE))
+		setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS);
+
+	setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+	set_return_thunk(its_return_thunk);
 }
 
 #undef pr_fmt
@@ -1250,6 +1564,8 @@ enum spectre_v2_mitigation_cmd {
 	SPECTRE_V2_CMD_IBRS,
 };
 
+static enum spectre_v2_mitigation_cmd spectre_v2_cmd __ro_after_init = SPECTRE_V2_CMD_AUTO;
+
 enum spectre_v2_user_cmd {
 	SPECTRE_V2_USER_CMD_NONE,
 	SPECTRE_V2_USER_CMD_AUTO,
@@ -1288,22 +1604,13 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure)
 		pr_info("spectre_v2_user=%s forced on command line.\n", reason);
 }
 
-static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd;
-
-static enum spectre_v2_user_cmd __init
-spectre_v2_parse_user_cmdline(void)
+static enum spectre_v2_user_cmd __init spectre_v2_parse_user_cmdline(void)
 {
 	char arg[20];
 	int ret, i;
 
-	switch (spectre_v2_cmd) {
-	case SPECTRE_V2_CMD_NONE:
+	if (cpu_mitigations_off() || !IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2))
 		return SPECTRE_V2_USER_CMD_NONE;
-	case SPECTRE_V2_CMD_FORCE:
-		return SPECTRE_V2_USER_CMD_FORCE;
-	default:
-		break;
-	}
 
 	ret = cmdline_find_option(boot_command_line, "spectre_v2_user",
 				  arg, sizeof(arg));
@@ -1318,7 +1625,7 @@ spectre_v2_parse_user_cmdline(void)
 		}
 	}
 
-	pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg);
+	pr_err("Unknown user space protection option (%s). Switching to default\n", arg);
 	return SPECTRE_V2_USER_CMD_AUTO;
 }
 
@@ -1327,65 +1634,72 @@ static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
 	return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS;
 }
 
-static void __init
-spectre_v2_user_select_mitigation(void)
+static void __init spectre_v2_user_select_mitigation(void)
 {
-	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
-	bool smt_possible = IS_ENABLED(CONFIG_SMP);
-	enum spectre_v2_user_cmd cmd;
-
 	if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
 		return;
 
-	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
-	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
-		smt_possible = false;
-
-	cmd = spectre_v2_parse_user_cmdline();
-	switch (cmd) {
+	switch (spectre_v2_parse_user_cmdline()) {
 	case SPECTRE_V2_USER_CMD_NONE:
-		goto set_mode;
+		return;
 	case SPECTRE_V2_USER_CMD_FORCE:
-		mode = SPECTRE_V2_USER_STRICT;
+		spectre_v2_user_ibpb  = SPECTRE_V2_USER_STRICT;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT;
 		break;
 	case SPECTRE_V2_USER_CMD_AUTO:
 	case SPECTRE_V2_USER_CMD_PRCTL:
+		spectre_v2_user_ibpb  = SPECTRE_V2_USER_PRCTL;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
+		break;
 	case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
-		mode = SPECTRE_V2_USER_PRCTL;
+		spectre_v2_user_ibpb  = SPECTRE_V2_USER_STRICT;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
 		break;
 	case SPECTRE_V2_USER_CMD_SECCOMP:
+		if (IS_ENABLED(CONFIG_SECCOMP))
+			spectre_v2_user_ibpb = SPECTRE_V2_USER_SECCOMP;
+		else
+			spectre_v2_user_ibpb = SPECTRE_V2_USER_PRCTL;
+		spectre_v2_user_stibp = spectre_v2_user_ibpb;
+		break;
 	case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
+		spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
 		if (IS_ENABLED(CONFIG_SECCOMP))
-			mode = SPECTRE_V2_USER_SECCOMP;
+			spectre_v2_user_stibp = SPECTRE_V2_USER_SECCOMP;
 		else
-			mode = SPECTRE_V2_USER_PRCTL;
+			spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
 		break;
 	}
 
-	/* Initialize Indirect Branch Prediction Barrier */
-	if (boot_cpu_has(X86_FEATURE_IBPB)) {
-		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+	/*
+	 * At this point, an STIBP mode other than "off" has been set.
+	 * If STIBP support is not being forced, check if STIBP always-on
+	 * is preferred.
+	 */
+	if ((spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+	     spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) &&
+	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+		spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT_PREFERRED;
 
-		spectre_v2_user_ibpb = mode;
-		switch (cmd) {
-		case SPECTRE_V2_USER_CMD_NONE:
-			break;
-		case SPECTRE_V2_USER_CMD_FORCE:
-		case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
-		case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
-			static_branch_enable(&switch_mm_always_ibpb);
-			spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
-			break;
-		case SPECTRE_V2_USER_CMD_PRCTL:
-		case SPECTRE_V2_USER_CMD_AUTO:
-		case SPECTRE_V2_USER_CMD_SECCOMP:
-			static_branch_enable(&switch_mm_cond_ibpb);
-			break;
-		}
+	if (!boot_cpu_has(X86_FEATURE_IBPB))
+		spectre_v2_user_ibpb = SPECTRE_V2_USER_NONE;
 
-		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
-			static_key_enabled(&switch_mm_always_ibpb) ?
-			"always-on" : "conditional");
+	if (!boot_cpu_has(X86_FEATURE_STIBP))
+		spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
+}
+
+static void __init spectre_v2_user_update_mitigation(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
+		return;
+
+	/* The spectre_v2 cmd line can override spectre_v2_user options */
+	if (spectre_v2_cmd == SPECTRE_V2_CMD_NONE) {
+		spectre_v2_user_ibpb = SPECTRE_V2_USER_NONE;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
+	} else if (spectre_v2_cmd == SPECTRE_V2_CMD_FORCE) {
+		spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT;
 	}
 
 	/*
@@ -1401,32 +1715,46 @@ spectre_v2_user_select_mitigation(void)
 	 * so allow for STIBP to be selected in those cases.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
-	    !smt_possible ||
+	    !cpu_smt_possible() ||
 	    (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
-	     !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
+	     !boot_cpu_has(X86_FEATURE_AUTOIBRS))) {
+		spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
 		return;
+	}
 
-	/*
-	 * At this point, an STIBP mode other than "off" has been set.
-	 * If STIBP support is not being forced, check if STIBP always-on
-	 * is preferred.
-	 */
-	if (mode != SPECTRE_V2_USER_STRICT &&
-	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
-		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
-
-	if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
-	    retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
-		if (mode != SPECTRE_V2_USER_STRICT &&
-		    mode != SPECTRE_V2_USER_STRICT_PREFERRED)
+	if (spectre_v2_user_stibp != SPECTRE_V2_USER_NONE &&
+	    (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
+	     retbleed_mitigation == RETBLEED_MITIGATION_IBPB)) {
+		if (spectre_v2_user_stibp != SPECTRE_V2_USER_STRICT &&
+		    spectre_v2_user_stibp != SPECTRE_V2_USER_STRICT_PREFERRED)
 			pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n");
-		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+		spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT_PREFERRED;
 	}
+	pr_info("%s\n", spectre_v2_user_strings[spectre_v2_user_stibp]);
+}
 
-	spectre_v2_user_stibp = mode;
+static void __init spectre_v2_user_apply_mitigation(void)
+{
+	/* Initialize Indirect Branch Prediction Barrier */
+	if (spectre_v2_user_ibpb != SPECTRE_V2_USER_NONE) {
+		static_branch_enable(&switch_vcpu_ibpb);
 
-set_mode:
-	pr_info("%s\n", spectre_v2_user_strings[mode]);
+		switch (spectre_v2_user_ibpb) {
+		case SPECTRE_V2_USER_STRICT:
+			static_branch_enable(&switch_mm_always_ibpb);
+			break;
+		case SPECTRE_V2_USER_PRCTL:
+		case SPECTRE_V2_USER_SECCOMP:
+			static_branch_enable(&switch_mm_cond_ibpb);
+			break;
+		default:
+			break;
+		}
+
+		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
+			static_key_enabled(&switch_mm_always_ibpb) ?
+			"always-on" : "conditional");
+	}
 }
 
 static const char * const spectre_v2_strings[] = {
@@ -1578,51 +1906,54 @@ static void __init spec_ctrl_disable_kernel_rrsba(void)
 	rrsba_disabled = true;
 }
 
-static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+static void __init spectre_v2_select_rsb_mitigation(enum spectre_v2_mitigation mode)
 {
 	/*
-	 * Similar to context switches, there are two types of RSB attacks
-	 * after VM exit:
+	 * WARNING! There are many subtleties to consider when changing *any*
+	 * code related to RSB-related mitigations.  Before doing so, carefully
+	 * read the following document, and update if necessary:
 	 *
-	 * 1) RSB underflow
+	 *   Documentation/admin-guide/hw-vuln/rsb.rst
 	 *
-	 * 2) Poisoned RSB entry
+	 * In an overly simplified nutshell:
 	 *
-	 * When retpoline is enabled, both are mitigated by filling/clearing
-	 * the RSB.
+	 *   - User->user RSB attacks are conditionally mitigated during
+	 *     context switches by cond_mitigation -> write_ibpb().
 	 *
-	 * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
-	 * prediction isolation protections, RSB still needs to be cleared
-	 * because of #2.  Note that SMEP provides no protection here, unlike
-	 * user-space-poisoned RSB entries.
+	 *   - User->kernel and guest->host attacks are mitigated by eIBRS or
+	 *     RSB filling.
 	 *
-	 * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
-	 * bug is present then a LITE version of RSB protection is required,
-	 * just a single call needs to retire before a RET is executed.
+	 *     Though, depending on config, note that other alternative
+	 *     mitigations may end up getting used instead, e.g., IBPB on
+	 *     entry/vmexit, call depth tracking, or return thunks.
 	 */
+
 	switch (mode) {
 	case SPECTRE_V2_NONE:
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_LFENCE:
 	case SPECTRE_V2_EIBRS:
+	case SPECTRE_V2_EIBRS_LFENCE:
+	case SPECTRE_V2_EIBRS_RETPOLINE:
 		if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
-			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 			pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 		}
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_RETPOLINE:
 	case SPECTRE_V2_RETPOLINE:
 	case SPECTRE_V2_LFENCE:
 	case SPECTRE_V2_IBRS:
+		pr_info("Spectre v2 / SpectreRSB: Filling RSB on context switch and VMEXIT\n");
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
-		pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n");
-		return;
-	}
+		break;
 
-	pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
-	dump_stack();
+	default:
+		pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation\n");
+		dump_stack();
+		break;
+	}
 }
 
 /*
@@ -1643,12 +1974,13 @@ static bool __init spec_ctrl_bhi_dis(void)
 
 enum bhi_mitigations {
 	BHI_MITIGATION_OFF,
+	BHI_MITIGATION_AUTO,
 	BHI_MITIGATION_ON,
 	BHI_MITIGATION_VMEXIT_ONLY,
 };
 
 static enum bhi_mitigations bhi_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_AUTO : BHI_MITIGATION_OFF;
 
 static int __init spectre_bhi_parse_cmdline(char *str)
 {
@@ -1670,6 +2002,25 @@ early_param("spectre_bhi", spectre_bhi_parse_cmdline);
 
 static void __init bhi_select_mitigation(void)
 {
+	if (!boot_cpu_has(X86_BUG_BHI) || cpu_mitigations_off())
+		bhi_mitigation = BHI_MITIGATION_OFF;
+
+	if (bhi_mitigation == BHI_MITIGATION_AUTO)
+		bhi_mitigation = BHI_MITIGATION_ON;
+}
+
+static void __init bhi_update_mitigation(void)
+{
+	if (spectre_v2_cmd == SPECTRE_V2_CMD_NONE)
+		bhi_mitigation = BHI_MITIGATION_OFF;
+
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+	     spectre_v2_cmd == SPECTRE_V2_CMD_AUTO)
+		bhi_mitigation = BHI_MITIGATION_OFF;
+}
+
+static void __init bhi_apply_mitigation(void)
+{
 	if (bhi_mitigation == BHI_MITIGATION_OFF)
 		return;
 
@@ -1681,95 +2032,101 @@ static void __init bhi_select_mitigation(void)
 			return;
 	}
 
-	/* Mitigate in hardware if supported */
-	if (spec_ctrl_bhi_dis())
+	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
-	if (!IS_ENABLED(CONFIG_X86_64))
+	/* Mitigate in hardware if supported */
+	if (spec_ctrl_bhi_dis())
 		return;
 
 	if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
 		pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n");
-		setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
 		return;
 	}
 
 	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n");
 	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
-	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
 }
 
 static void __init spectre_v2_select_mitigation(void)
 {
-	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
-	enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+	spectre_v2_cmd = spectre_v2_parse_cmdline();
 
-	/*
-	 * If the CPU is not affected and the command line mode is NONE or AUTO
-	 * then nothing to do.
-	 */
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
-	    (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+	    (spectre_v2_cmd == SPECTRE_V2_CMD_NONE || spectre_v2_cmd == SPECTRE_V2_CMD_AUTO))
 		return;
 
-	switch (cmd) {
+	switch (spectre_v2_cmd) {
 	case SPECTRE_V2_CMD_NONE:
 		return;
 
 	case SPECTRE_V2_CMD_FORCE:
 	case SPECTRE_V2_CMD_AUTO:
 		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
-			mode = SPECTRE_V2_EIBRS;
-			break;
-		}
-
-		if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) &&
-		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
-		    retbleed_cmd != RETBLEED_CMD_OFF &&
-		    retbleed_cmd != RETBLEED_CMD_STUFF &&
-		    boot_cpu_has(X86_FEATURE_IBRS) &&
-		    boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
-			mode = SPECTRE_V2_IBRS;
+			spectre_v2_enabled = SPECTRE_V2_EIBRS;
 			break;
 		}
 
-		mode = spectre_v2_select_retpoline();
+		spectre_v2_enabled = spectre_v2_select_retpoline();
 		break;
 
 	case SPECTRE_V2_CMD_RETPOLINE_LFENCE:
 		pr_err(SPECTRE_V2_LFENCE_MSG);
-		mode = SPECTRE_V2_LFENCE;
+		spectre_v2_enabled = SPECTRE_V2_LFENCE;
 		break;
 
 	case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
-		mode = SPECTRE_V2_RETPOLINE;
+		spectre_v2_enabled = SPECTRE_V2_RETPOLINE;
 		break;
 
 	case SPECTRE_V2_CMD_RETPOLINE:
-		mode = spectre_v2_select_retpoline();
+		spectre_v2_enabled = spectre_v2_select_retpoline();
 		break;
 
 	case SPECTRE_V2_CMD_IBRS:
-		mode = SPECTRE_V2_IBRS;
+		spectre_v2_enabled = SPECTRE_V2_IBRS;
 		break;
 
 	case SPECTRE_V2_CMD_EIBRS:
-		mode = SPECTRE_V2_EIBRS;
+		spectre_v2_enabled = SPECTRE_V2_EIBRS;
 		break;
 
 	case SPECTRE_V2_CMD_EIBRS_LFENCE:
-		mode = SPECTRE_V2_EIBRS_LFENCE;
+		spectre_v2_enabled = SPECTRE_V2_EIBRS_LFENCE;
 		break;
 
 	case SPECTRE_V2_CMD_EIBRS_RETPOLINE:
-		mode = SPECTRE_V2_EIBRS_RETPOLINE;
+		spectre_v2_enabled = SPECTRE_V2_EIBRS_RETPOLINE;
 		break;
 	}
+}
+
+static void __init spectre_v2_update_mitigation(void)
+{
+	if (spectre_v2_cmd == SPECTRE_V2_CMD_AUTO &&
+	    !spectre_v2_in_eibrs_mode(spectre_v2_enabled)) {
+		if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) &&
+		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+		    retbleed_mitigation != RETBLEED_MITIGATION_NONE &&
+		    retbleed_mitigation != RETBLEED_MITIGATION_STUFF &&
+		    boot_cpu_has(X86_FEATURE_IBRS) &&
+		    boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+			spectre_v2_enabled = SPECTRE_V2_IBRS;
+		}
+	}
+
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && !cpu_mitigations_off())
+		pr_info("%s\n", spectre_v2_strings[spectre_v2_enabled]);
+}
 
-	if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
+static void __init spectre_v2_apply_mitigation(void)
+{
+	if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
 		pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
 
-	if (spectre_v2_in_ibrs_mode(mode)) {
+	if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) {
 		if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
 			msr_set_bit(MSR_EFER, _EFER_AUTOIBRS);
 		} else {
@@ -1778,8 +2135,10 @@ static void __init spectre_v2_select_mitigation(void)
 		}
 	}
 
-	switch (mode) {
+	switch (spectre_v2_enabled) {
 	case SPECTRE_V2_NONE:
+		return;
+
 	case SPECTRE_V2_EIBRS:
 		break;
 
@@ -1805,59 +2164,12 @@ static void __init spectre_v2_select_mitigation(void)
 	 * JMPs gets protection against BHI and Intramode-BTI, but RET
 	 * prediction from a non-RSB predictor is still a risk.
 	 */
-	if (mode == SPECTRE_V2_EIBRS_LFENCE ||
-	    mode == SPECTRE_V2_EIBRS_RETPOLINE ||
-	    mode == SPECTRE_V2_RETPOLINE)
+	if (spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE ||
+	    spectre_v2_enabled == SPECTRE_V2_EIBRS_RETPOLINE ||
+	    spectre_v2_enabled == SPECTRE_V2_RETPOLINE)
 		spec_ctrl_disable_kernel_rrsba();
 
-	if (boot_cpu_has(X86_BUG_BHI))
-		bhi_select_mitigation();
-
-	spectre_v2_enabled = mode;
-	pr_info("%s\n", spectre_v2_strings[mode]);
-
-	/*
-	 * If Spectre v2 protection has been enabled, fill the RSB during a
-	 * context switch.  In general there are two types of RSB attacks
-	 * across context switches, for which the CALLs/RETs may be unbalanced.
-	 *
-	 * 1) RSB underflow
-	 *
-	 *    Some Intel parts have "bottomless RSB".  When the RSB is empty,
-	 *    speculated return targets may come from the branch predictor,
-	 *    which could have a user-poisoned BTB or BHB entry.
-	 *
-	 *    AMD has it even worse: *all* returns are speculated from the BTB,
-	 *    regardless of the state of the RSB.
-	 *
-	 *    When IBRS or eIBRS is enabled, the "user -> kernel" attack
-	 *    scenario is mitigated by the IBRS branch prediction isolation
-	 *    properties, so the RSB buffer filling wouldn't be necessary to
-	 *    protect against this type of attack.
-	 *
-	 *    The "user -> user" attack scenario is mitigated by RSB filling.
-	 *
-	 * 2) Poisoned RSB entry
-	 *
-	 *    If the 'next' in-kernel return stack is shorter than 'prev',
-	 *    'next' could be tricked into speculating with a user-poisoned RSB
-	 *    entry.
-	 *
-	 *    The "user -> kernel" attack scenario is mitigated by SMEP and
-	 *    eIBRS.
-	 *
-	 *    The "user -> user" scenario, also known as SpectreBHB, requires
-	 *    RSB clearing.
-	 *
-	 * So to mitigate all cases, unconditionally fill RSB on context
-	 * switches.
-	 *
-	 * FIXME: Is this pointless for retbleed-affected AMD?
-	 */
-	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
-
-	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+	spectre_v2_select_rsb_mitigation(spectre_v2_enabled);
 
 	/*
 	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
@@ -1865,28 +2177,26 @@ static void __init spectre_v2_select_mitigation(void)
 	 * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't
 	 * otherwise enabled.
 	 *
-	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
-	 * the user might select retpoline on the kernel command line and if
-	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
-	 * enable IBRS around firmware calls.
+	 * Use "spectre_v2_enabled" to check Enhanced IBRS instead of
+	 * boot_cpu_has(), because the user might select retpoline on the kernel
+	 * command line and if the CPU supports Enhanced IBRS, kernel might
+	 * un-intentionally not enable IBRS around firmware calls.
 	 */
 	if (boot_cpu_has_bug(X86_BUG_RETBLEED) &&
 	    boot_cpu_has(X86_FEATURE_IBPB) &&
 	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	     boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) {
 
-		if (retbleed_cmd != RETBLEED_CMD_IBPB) {
+		if (retbleed_mitigation != RETBLEED_MITIGATION_IBPB) {
 			setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW);
 			pr_info("Enabling Speculation Barrier for firmware calls\n");
 		}
 
-	} else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
+	} else if (boot_cpu_has(X86_FEATURE_IBRS) &&
+		   !spectre_v2_in_ibrs_mode(spectre_v2_enabled)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
-
-	/* Set up IBPB and STIBP depending on the general spectre V2 command */
-	spectre_v2_cmd = cmd;
 }
 
 static void update_stibp_msr(void * __unused)
@@ -1973,6 +2283,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (mds_mitigation) {
 	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_AUTO:
 	case MDS_MITIGATION_VMWERV:
 		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
 			pr_warn_once(MDS_MSG_SMT);
@@ -1984,6 +2295,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (taa_mitigation) {
 	case TAA_MITIGATION_VERW:
+	case TAA_MITIGATION_AUTO:
 	case TAA_MITIGATION_UCODE_NEEDED:
 		if (sched_smt_active())
 			pr_warn_once(TAA_MSG_SMT);
@@ -1995,6 +2307,7 @@ void cpu_bugs_smt_update(void)
 
 	switch (mmio_mitigation) {
 	case MMIO_MITIGATION_VERW:
+	case MMIO_MITIGATION_AUTO:
 	case MMIO_MITIGATION_UCODE_NEEDED:
 		if (sched_smt_active())
 			pr_warn_once(MMIO_MSG_SMT);
@@ -2072,19 +2385,18 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
 	return cmd;
 }
 
-static enum ssb_mitigation __init __ssb_select_mitigation(void)
+static void __init ssb_select_mitigation(void)
 {
-	enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
 	enum ssb_mitigation_cmd cmd;
 
 	if (!boot_cpu_has(X86_FEATURE_SSBD))
-		return mode;
+		goto out;
 
 	cmd = ssb_parse_cmdline();
 	if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
 	    (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
 	     cmd == SPEC_STORE_BYPASS_CMD_AUTO))
-		return mode;
+		return;
 
 	switch (cmd) {
 	case SPEC_STORE_BYPASS_CMD_SECCOMP:
@@ -2093,28 +2405,35 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		 * enabled.
 		 */
 		if (IS_ENABLED(CONFIG_SECCOMP))
-			mode = SPEC_STORE_BYPASS_SECCOMP;
+			ssb_mode = SPEC_STORE_BYPASS_SECCOMP;
 		else
-			mode = SPEC_STORE_BYPASS_PRCTL;
+			ssb_mode = SPEC_STORE_BYPASS_PRCTL;
 		break;
 	case SPEC_STORE_BYPASS_CMD_ON:
-		mode = SPEC_STORE_BYPASS_DISABLE;
+		ssb_mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
 	case SPEC_STORE_BYPASS_CMD_AUTO:
 	case SPEC_STORE_BYPASS_CMD_PRCTL:
-		mode = SPEC_STORE_BYPASS_PRCTL;
+		ssb_mode = SPEC_STORE_BYPASS_PRCTL;
 		break;
 	case SPEC_STORE_BYPASS_CMD_NONE:
 		break;
 	}
 
+out:
+	if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+		pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+static void __init ssb_apply_mitigation(void)
+{
 	/*
 	 * We have three CPU feature flags that are in play here:
 	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
 	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
 	 *  - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
 	 */
-	if (mode == SPEC_STORE_BYPASS_DISABLE) {
+	if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) {
 		setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
 		/*
 		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
@@ -2128,16 +2447,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 			update_spec_ctrl(x86_spec_ctrl_base);
 		}
 	}
-
-	return mode;
-}
-
-static void ssb_select_mitigation(void)
-{
-	ssb_mode = __ssb_select_mitigation();
-
-	if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
-		pr_info("%s\n", ssb_strings[ssb_mode]);
 }
 
 #undef pr_fmt
@@ -2393,7 +2702,7 @@ EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
 
 /* Default mitigation for L1TF-affected CPUs */
 enum l1tf_mitigations l1tf_mitigation __ro_after_init =
-	IS_ENABLED(CONFIG_MITIGATION_L1TF) ? L1TF_MITIGATION_FLUSH : L1TF_MITIGATION_OFF;
+	IS_ENABLED(CONFIG_MITIGATION_L1TF) ? L1TF_MITIGATION_AUTO : L1TF_MITIGATION_OFF;
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 EXPORT_SYMBOL_GPL(l1tf_mitigation);
 #endif
@@ -2441,22 +2750,33 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
 
 static void __init l1tf_select_mitigation(void)
 {
+	if (!boot_cpu_has_bug(X86_BUG_L1TF) || cpu_mitigations_off()) {
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+		return;
+	}
+
+	if (l1tf_mitigation == L1TF_MITIGATION_AUTO) {
+		if (cpu_mitigations_auto_nosmt())
+			l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+		else
+			l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+	}
+}
+
+static void __init l1tf_apply_mitigation(void)
+{
 	u64 half_pa;
 
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
-	if (cpu_mitigations_off())
-		l1tf_mitigation = L1TF_MITIGATION_OFF;
-	else if (cpu_mitigations_auto_nosmt())
-		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
-
 	override_cache_bits(&boot_cpu_data);
 
 	switch (l1tf_mitigation) {
 	case L1TF_MITIGATION_OFF:
 	case L1TF_MITIGATION_FLUSH_NOWARN:
 	case L1TF_MITIGATION_FLUSH:
+	case L1TF_MITIGATION_AUTO:
 		break;
 	case L1TF_MITIGATION_FLUSH_NOSMT:
 	case L1TF_MITIGATION_FULL:
@@ -2516,20 +2836,14 @@ early_param("l1tf", l1tf_cmdline);
 
 enum srso_mitigation {
 	SRSO_MITIGATION_NONE,
+	SRSO_MITIGATION_AUTO,
 	SRSO_MITIGATION_UCODE_NEEDED,
 	SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED,
 	SRSO_MITIGATION_MICROCODE,
 	SRSO_MITIGATION_SAFE_RET,
 	SRSO_MITIGATION_IBPB,
 	SRSO_MITIGATION_IBPB_ON_VMEXIT,
-};
-
-enum srso_mitigation_cmd {
-	SRSO_CMD_OFF,
-	SRSO_CMD_MICROCODE,
-	SRSO_CMD_SAFE_RET,
-	SRSO_CMD_IBPB,
-	SRSO_CMD_IBPB_ON_VMEXIT,
+	SRSO_MITIGATION_BP_SPEC_REDUCE,
 };
 
 static const char * const srso_strings[] = {
@@ -2539,11 +2853,11 @@ static const char * const srso_strings[] = {
 	[SRSO_MITIGATION_MICROCODE]		= "Vulnerable: Microcode, no safe RET",
 	[SRSO_MITIGATION_SAFE_RET]		= "Mitigation: Safe RET",
 	[SRSO_MITIGATION_IBPB]			= "Mitigation: IBPB",
-	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only"
+	[SRSO_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT only",
+	[SRSO_MITIGATION_BP_SPEC_REDUCE]	= "Mitigation: Reduced Speculation"
 };
 
-static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
-static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET;
+static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_AUTO;
 
 static int __init srso_parse_cmdline(char *str)
 {
@@ -2551,15 +2865,15 @@ static int __init srso_parse_cmdline(char *str)
 		return -EINVAL;
 
 	if (!strcmp(str, "off"))
-		srso_cmd = SRSO_CMD_OFF;
+		srso_mitigation = SRSO_MITIGATION_NONE;
 	else if (!strcmp(str, "microcode"))
-		srso_cmd = SRSO_CMD_MICROCODE;
+		srso_mitigation = SRSO_MITIGATION_MICROCODE;
 	else if (!strcmp(str, "safe-ret"))
-		srso_cmd = SRSO_CMD_SAFE_RET;
+		srso_mitigation = SRSO_MITIGATION_SAFE_RET;
 	else if (!strcmp(str, "ibpb"))
-		srso_cmd = SRSO_CMD_IBPB;
+		srso_mitigation = SRSO_MITIGATION_IBPB;
 	else if (!strcmp(str, "ibpb-vmexit"))
-		srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT;
+		srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 	else
 		pr_err("Ignoring unknown SRSO option (%s).", str);
 
@@ -2571,127 +2885,138 @@ early_param("spec_rstack_overflow", srso_parse_cmdline);
 
 static void __init srso_select_mitigation(void)
 {
-	bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
+	bool has_microcode;
 
-	if (!boot_cpu_has_bug(X86_BUG_SRSO) ||
-	    cpu_mitigations_off() ||
-	    srso_cmd == SRSO_CMD_OFF) {
-		if (boot_cpu_has(X86_FEATURE_SBPB))
-			x86_pred_cmd = PRED_CMD_SBPB;
+	if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off())
+		srso_mitigation = SRSO_MITIGATION_NONE;
+
+	if (srso_mitigation == SRSO_MITIGATION_NONE)
 		return;
-	}
 
+	if (srso_mitigation == SRSO_MITIGATION_AUTO)
+		srso_mitigation = SRSO_MITIGATION_SAFE_RET;
+
+	has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
 	if (has_microcode) {
 		/*
 		 * Zen1/2 with SMT off aren't vulnerable after the right
 		 * IBPB microcode has been applied.
-		 *
-		 * Zen1/2 don't have SBPB, no need to try to enable it here.
 		 */
 		if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
 			setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
+			srso_mitigation = SRSO_MITIGATION_NONE;
 			return;
 		}
-
-		if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
-			srso_mitigation = SRSO_MITIGATION_IBPB;
-			goto out;
-		}
 	} else {
 		pr_warn("IBPB-extending microcode not applied!\n");
 		pr_warn(SRSO_NOTICE);
-
-		/* may be overwritten by SRSO_CMD_SAFE_RET below */
-		srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED;
 	}
 
-	switch (srso_cmd) {
-	case SRSO_CMD_MICROCODE:
-		if (has_microcode) {
-			srso_mitigation = SRSO_MITIGATION_MICROCODE;
-			pr_warn(SRSO_NOTICE);
-		}
-		break;
-
-	case SRSO_CMD_SAFE_RET:
-		if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO))
+	switch (srso_mitigation) {
+	case SRSO_MITIGATION_SAFE_RET:
+		if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO)) {
+			srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 			goto ibpb_on_vmexit;
+		}
 
-		if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
-			/*
-			 * Enable the return thunk for generated code
-			 * like ftrace, static_call, etc.
-			 */
-			setup_force_cpu_cap(X86_FEATURE_RETHUNK);
-			setup_force_cpu_cap(X86_FEATURE_UNRET);
-
-			if (boot_cpu_data.x86 == 0x19) {
-				setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
-				x86_return_thunk = srso_alias_return_thunk;
-			} else {
-				setup_force_cpu_cap(X86_FEATURE_SRSO);
-				x86_return_thunk = srso_return_thunk;
-			}
-			if (has_microcode)
-				srso_mitigation = SRSO_MITIGATION_SAFE_RET;
-			else
-				srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
-		} else {
+		if (!IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
 			pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
+			srso_mitigation = SRSO_MITIGATION_NONE;
 		}
-		break;
 
-	case SRSO_CMD_IBPB:
-		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
-			if (has_microcode) {
-				setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
-				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
-				srso_mitigation = SRSO_MITIGATION_IBPB;
-
-				/*
-				 * IBPB on entry already obviates the need for
-				 * software-based untraining so clear those in case some
-				 * other mitigation like Retbleed has selected them.
-				 */
-				setup_clear_cpu_cap(X86_FEATURE_UNRET);
-				setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
-
-				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
-				 * all predictions, including the RSB, are invalidated,
-				 * regardless of IBPB implementation.
-				 */
-				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
-			}
-		} else {
+		if (!has_microcode)
+			srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
+		break;
+ibpb_on_vmexit:
+	case SRSO_MITIGATION_IBPB_ON_VMEXIT:
+		if (boot_cpu_has(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) {
+			pr_notice("Reducing speculation to address VM/HV SRSO attack vector.\n");
+			srso_mitigation = SRSO_MITIGATION_BP_SPEC_REDUCE;
+			break;
+		}
+		fallthrough;
+	case SRSO_MITIGATION_IBPB:
+		if (!IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+			srso_mitigation = SRSO_MITIGATION_NONE;
 		}
+
+		if (!has_microcode)
+			srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED;
+		break;
+	default:
 		break;
+	}
+}
 
-ibpb_on_vmexit:
-	case SRSO_CMD_IBPB_ON_VMEXIT:
-		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
-			if (has_microcode) {
-				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
-				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
-
-				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
-				 * all predictions, including the RSB, are invalidated,
-				 * regardless of IBPB implementation.
-				 */
-				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
-			}
+static void __init srso_update_mitigation(void)
+{
+	/* If retbleed is using IBPB, that works for SRSO as well */
+	if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB &&
+	    boot_cpu_has(X86_FEATURE_IBPB_BRTYPE))
+		srso_mitigation = SRSO_MITIGATION_IBPB;
+
+	if (boot_cpu_has_bug(X86_BUG_SRSO) &&
+	    !cpu_mitigations_off() &&
+	    !boot_cpu_has(X86_FEATURE_SRSO_NO))
+		pr_info("%s\n", srso_strings[srso_mitigation]);
+}
+
+static void __init srso_apply_mitigation(void)
+{
+	/*
+	 * Clear the feature flag if this mitigation is not selected as that
+	 * feature flag controls the BpSpecReduce MSR bit toggling in KVM.
+	 */
+	if (srso_mitigation != SRSO_MITIGATION_BP_SPEC_REDUCE)
+		setup_clear_cpu_cap(X86_FEATURE_SRSO_BP_SPEC_REDUCE);
+
+	if (srso_mitigation == SRSO_MITIGATION_NONE) {
+		if (boot_cpu_has(X86_FEATURE_SBPB))
+			x86_pred_cmd = PRED_CMD_SBPB;
+		return;
+	}
+
+	switch (srso_mitigation) {
+	case SRSO_MITIGATION_SAFE_RET:
+	case SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED:
+		/*
+		 * Enable the return thunk for generated code
+		 * like ftrace, static_call, etc.
+		 */
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		setup_force_cpu_cap(X86_FEATURE_UNRET);
+
+		if (boot_cpu_data.x86 == 0x19) {
+			setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
+			set_return_thunk(srso_alias_return_thunk);
 		} else {
-			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+			setup_force_cpu_cap(X86_FEATURE_SRSO);
+			set_return_thunk(srso_return_thunk);
 		}
 		break;
+	case SRSO_MITIGATION_IBPB:
+		setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+		/*
+		 * IBPB on entry already obviates the need for
+		 * software-based untraining so clear those in case some
+		 * other mitigation like Retbleed has selected them.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_UNRET);
+		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+		fallthrough;
+	case SRSO_MITIGATION_IBPB_ON_VMEXIT:
+		setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
+		/*
+		 * There is no need for RSB filling: entry_ibpb() ensures
+		 * all predictions, including the RSB, are invalidated,
+		 * regardless of IBPB implementation.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+		break;
 	default:
 		break;
 	}
-
-out:
-	pr_info("%s\n", srso_strings[srso_mitigation]);
 }
 
 #undef pr_fmt
@@ -2786,9 +3111,6 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 
 static ssize_t mmio_stale_data_show_state(char *buf)
 {
-	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
-		return sysfs_emit(buf, "Unknown: No mitigations\n");
-
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
 
@@ -2806,6 +3128,19 @@ static ssize_t rfds_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
 }
 
+static ssize_t old_microcode_show_state(char *buf)
+{
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return sysfs_emit(buf, "Unknown: running under hypervisor");
+
+	return sysfs_emit(buf, "Vulnerable\n");
+}
+
+static ssize_t its_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]);
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -2864,7 +3199,7 @@ static const char *spectre_bhi_state(void)
 		 !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
 		 rrsba_disabled)
 		return "; BHI: Retpoline";
-	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_VMEXIT))
 		return "; BHI: Vulnerable, KVM: SW loop";
 
 	return "; BHI: Vulnerable";
@@ -2973,7 +3308,6 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return srbds_show_state(buf);
 
 	case X86_BUG_MMIO_STALE_DATA:
-	case X86_BUG_MMIO_UNKNOWN:
 		return mmio_stale_data_show_state(buf);
 
 	case X86_BUG_RETBLEED:
@@ -2988,6 +3322,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_RFDS:
 		return rfds_show_state(buf);
 
+	case X86_BUG_OLD_MICROCODE:
+		return old_microcode_show_state(buf);
+
+	case X86_BUG_ITS:
+		return its_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3042,10 +3382,7 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 
 ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
-		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
-	else
-		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
 }
 
 ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
@@ -3067,6 +3404,16 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
 }
+
+ssize_t cpu_show_old_microcode(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_OLD_MICROCODE);
+}
+
+ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
+}
 #endif
 
 void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 6cba85c79d42..981f8b1f0792 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -10,6 +10,7 @@
 #include <asm/cmdline.h>
 #include <asm/traps.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 enum split_lock_detect_state {
 	sld_off = 0,
@@ -95,15 +96,15 @@ static bool split_lock_verify_msr(bool on)
 {
 	u64 ctrl, tmp;
 
-	if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl))
+	if (rdmsrq_safe(MSR_TEST_CTRL, &ctrl))
 		return false;
 	if (on)
 		ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
 	else
 		ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
-	if (wrmsrl_safe(MSR_TEST_CTRL, ctrl))
+	if (wrmsrq_safe(MSR_TEST_CTRL, ctrl))
 		return false;
-	rdmsrl(MSR_TEST_CTRL, tmp);
+	rdmsrq(MSR_TEST_CTRL, tmp);
 	return ctrl == tmp;
 }
 
@@ -137,7 +138,7 @@ static void __init __split_lock_setup(void)
 		return;
 	}
 
-	rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+	rdmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
 
 	if (!split_lock_verify_msr(true)) {
 		pr_info("MSR access failed: Disabled\n");
@@ -145,7 +146,7 @@ static void __init __split_lock_setup(void)
 	}
 
 	/* Restore the MSR to its cached value. */
-	wrmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+	wrmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
 
 	setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
 }
@@ -162,7 +163,7 @@ static void sld_update_msr(bool on)
 	if (on)
 		test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
 
-	wrmsrl(MSR_TEST_CTRL, test_ctrl_val);
+	wrmsrq(MSR_TEST_CTRL, test_ctrl_val);
 }
 
 void split_lock_init(void)
@@ -192,7 +193,33 @@ static void __split_lock_reenable(struct work_struct *work)
 {
 	sld_update_msr(true);
 }
-static DECLARE_DELAYED_WORK(sl_reenable, __split_lock_reenable);
+/*
+ * In order for each CPU to schedule its delayed work independently of the
+ * others, delayed work struct must be per-CPU. This is not required when
+ * sysctl_sld_mitigate is enabled because of the semaphore that limits
+ * the number of simultaneously scheduled delayed works to 1.
+ */
+static DEFINE_PER_CPU(struct delayed_work, sl_reenable);
+
+/*
+ * Per-CPU delayed_work can't be statically initialized properly because
+ * the struct address is unknown. Thus per-CPU delayed_work structures
+ * have to be initialized during kernel initialization and after calling
+ * setup_per_cpu_areas().
+ */
+static int __init setup_split_lock_delayed_work(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct delayed_work *work = per_cpu_ptr(&sl_reenable, cpu);
+
+		INIT_DELAYED_WORK(work, __split_lock_reenable);
+	}
+
+	return 0;
+}
+pure_initcall(setup_split_lock_delayed_work);
 
 /*
  * If a CPU goes offline with pending delayed work to re-enable split lock
@@ -215,13 +242,14 @@ static void split_lock_warn(unsigned long ip)
 {
 	struct delayed_work *work;
 	int cpu;
+	unsigned int saved_sld_mitigate = READ_ONCE(sysctl_sld_mitigate);
 
 	if (!current->reported_split_lock)
 		pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
 				    current->comm, current->pid, ip);
 	current->reported_split_lock = 1;
 
-	if (sysctl_sld_mitigate) {
+	if (saved_sld_mitigate) {
 		/*
 		 * misery factor #1:
 		 * sleep 10ms before trying to execute split lock.
@@ -234,12 +262,10 @@ static void split_lock_warn(unsigned long ip)
 		 */
 		if (down_interruptible(&buslock_sem) == -EINTR)
 			return;
-		work = &sl_reenable_unlock;
-	} else {
-		work = &sl_reenable;
 	}
 
 	cpu = get_cpu();
+	work = saved_sld_mitigate ? &sl_reenable_unlock : per_cpu_ptr(&sl_reenable, cpu);
 	schedule_delayed_work_on(cpu, work, 2);
 
 	/* Disable split lock detection on this CPU to make progress */
@@ -272,7 +298,7 @@ void bus_lock_init(void)
 	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
 		return;
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, val);
 
 	if ((boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
 	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
@@ -286,7 +312,7 @@ void bus_lock_init(void)
 		val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 	}
 
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, val);
 }
 
 bool handle_user_split_lock(struct pt_regs *regs, long error_code)
@@ -350,7 +376,7 @@ static void __init split_lock_setup(struct cpuinfo_x86 *c)
 	 * MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT is.  All CPUs that set
 	 * it have split lock detection.
 	 */
-	rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
+	rdmsrq(MSR_IA32_CORE_CAPS, ia32_core_caps);
 	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
 		goto supported;
 
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172..adfa7e8bb865 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -1,38 +1,28 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- *	Routines to identify caches on Intel CPU.
+ * x86 CPU caches detection and configuration
  *
- *	Changes:
- *	Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
- *	Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
- *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
+ * Previous changes
+ * - Venkatesh Pallipadi:		Cache identification through CPUID(0x4)
+ * - Ashok Raj <ashok.raj@intel.com>:	Work with CPU hotplug infrastructure
+ * - Andi Kleen / Andreas Herrmann:	CPUID(0x4) emulation on AMD
  */
 
-#include <linux/slab.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
-#include <linux/sched.h>
-#include <linux/capability.h>
-#include <linux/sysfs.h>
-#include <linux/pci.h>
 #include <linux/stop_machine.h>
 
-#include <asm/cpufeature.h>
+#include <asm/amd/nb.h>
 #include <asm/cacheinfo.h>
-#include <asm/amd_nb.h>
-#include <asm/smp.h>
+#include <asm/cpufeature.h>
+#include <asm/cpuid/api.h>
 #include <asm/mtrr.h>
+#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 #include "cpu.h"
 
-#define LVL_1_INST	1
-#define LVL_1_DATA	2
-#define LVL_2		3
-#define LVL_3		4
-#define LVL_TRACE	5
-
 /* Shared last level cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
@@ -44,212 +34,127 @@ static cpumask_var_t cpu_cacheinfo_mask;
 /* Kernel controls MTRR and/or PAT MSRs. */
 unsigned int memory_caching_control __ro_after_init;
 
-struct _cache_table {
-	unsigned char descriptor;
-	char cache_type;
-	short size;
-};
-
-#define MB(x)	((x) * 1024)
-
-/* All the cache descriptor types we care about (no TLB or
-   trace cache entries) */
-
-static const struct _cache_table cache_table[] =
-{
-	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x09, LVL_1_INST, 32 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
-	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x0e, LVL_1_DATA, 24 },	/* 6-way set assoc, 64 byte line size */
-	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x23, LVL_3,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x25, LVL_3,      MB(2) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x29, LVL_3,      MB(4) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x2c, LVL_1_DATA, 32 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x30, LVL_1_INST, 32 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x39, LVL_2,      128 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3a, LVL_2,      192 },	/* 6-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3b, LVL_2,      128 },	/* 2-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3c, LVL_2,      256 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3d, LVL_2,      384 },	/* 6-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3e, LVL_2,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x3f, LVL_2,      256 },	/* 2-way set assoc, 64 byte line size */
-	{ 0x41, LVL_2,      128 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x42, LVL_2,      256 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x43, LVL_2,      512 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x44, LVL_2,      MB(1) },	/* 4-way set assoc, 32 byte line size */
-	{ 0x45, LVL_2,      MB(2) },	/* 4-way set assoc, 32 byte line size */
-	{ 0x46, LVL_3,      MB(4) },	/* 4-way set assoc, 64 byte line size */
-	{ 0x47, LVL_3,      MB(8) },	/* 8-way set assoc, 64 byte line size */
-	{ 0x48, LVL_2,      MB(3) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x49, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4a, LVL_3,      MB(6) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4b, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4c, LVL_3,      MB(12) },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4d, LVL_3,      MB(16) },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4e, LVL_2,      MB(6) },	/* 24-way set assoc, 64 byte line size */
-	{ 0x60, LVL_1_DATA, 16 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x68, LVL_1_DATA, 32 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x70, LVL_TRACE,  12 },	/* 8-way set assoc */
-	{ 0x71, LVL_TRACE,  16 },	/* 8-way set assoc */
-	{ 0x72, LVL_TRACE,  32 },	/* 8-way set assoc */
-	{ 0x73, LVL_TRACE,  64 },	/* 8-way set assoc */
-	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
-	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7b, LVL_2,      512 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7c, LVL_2,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7d, LVL_2,      MB(2) },	/* 8-way set assoc, 64 byte line size */
-	{ 0x7f, LVL_2,      512 },	/* 2-way set assoc, 64 byte line size */
-	{ 0x80, LVL_2,      512 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x82, LVL_2,      256 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x83, LVL_2,      512 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x84, LVL_2,      MB(1) },	/* 8-way set assoc, 32 byte line size */
-	{ 0x85, LVL_2,      MB(2) },	/* 8-way set assoc, 32 byte line size */
-	{ 0x86, LVL_2,      512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x87, LVL_2,      MB(1) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd0, LVL_3,      512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd1, LVL_3,      MB(1) },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd2, LVL_3,      MB(2) },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd6, LVL_3,      MB(1) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd7, LVL_3,      MB(2) },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd8, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdc, LVL_3,      MB(2) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdd, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xde, LVL_3,      MB(8) },	/* 12-way set assoc, 64 byte line size */
-	{ 0xe2, LVL_3,      MB(2) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe3, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe4, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
-	{ 0xea, LVL_3,      MB(12) },	/* 24-way set assoc, 64 byte line size */
-	{ 0xeb, LVL_3,      MB(18) },	/* 24-way set assoc, 64 byte line size */
-	{ 0xec, LVL_3,      MB(24) },	/* 24-way set assoc, 64 byte line size */
-	{ 0x00, 0, 0}
-};
-
-
 enum _cache_type {
-	CTYPE_NULL = 0,
-	CTYPE_DATA = 1,
-	CTYPE_INST = 2,
-	CTYPE_UNIFIED = 3
+	CTYPE_NULL	= 0,
+	CTYPE_DATA	= 1,
+	CTYPE_INST	= 2,
+	CTYPE_UNIFIED	= 3
 };
 
 union _cpuid4_leaf_eax {
 	struct {
-		enum _cache_type	type:5;
-		unsigned int		level:3;
-		unsigned int		is_self_initializing:1;
-		unsigned int		is_fully_associative:1;
-		unsigned int		reserved:4;
-		unsigned int		num_threads_sharing:12;
-		unsigned int		num_cores_on_die:6;
+		enum _cache_type	type			:5;
+		unsigned int		level			:3;
+		unsigned int		is_self_initializing	:1;
+		unsigned int		is_fully_associative	:1;
+		unsigned int		reserved		:4;
+		unsigned int		num_threads_sharing	:12;
+		unsigned int		num_cores_on_die	:6;
 	} split;
 	u32 full;
 };
 
 union _cpuid4_leaf_ebx {
 	struct {
-		unsigned int		coherency_line_size:12;
-		unsigned int		physical_line_partition:10;
-		unsigned int		ways_of_associativity:10;
+		unsigned int		coherency_line_size	:12;
+		unsigned int		physical_line_partition	:10;
+		unsigned int		ways_of_associativity	:10;
 	} split;
 	u32 full;
 };
 
 union _cpuid4_leaf_ecx {
 	struct {
-		unsigned int		number_of_sets:32;
+		unsigned int		number_of_sets		:32;
 	} split;
 	u32 full;
 };
 
-struct _cpuid4_info_regs {
+struct _cpuid4_info {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned int id;
 	unsigned long size;
-	struct amd_northbridge *nb;
 };
 
-/* AMD doesn't have CPUID4. Emulate it here to report the same
-   information to the user.  This makes some assumptions about the machine:
-   L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+/* Map CPUID(0x4) EAX.cache_type to <linux/cacheinfo.h> types */
+static const enum cache_type cache_type_map[] = {
+	[CTYPE_NULL]	= CACHE_TYPE_NOCACHE,
+	[CTYPE_DATA]	= CACHE_TYPE_DATA,
+	[CTYPE_INST]	= CACHE_TYPE_INST,
+	[CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
+};
+
+/*
+ * Fallback AMD CPUID(0x4) emulation
+ * AMD CPUs with TOPOEXT can just use CPUID(0x8000001d)
+ *
+ * @AMD_L2_L3_INVALID_ASSOC: cache info for the respective L2/L3 cache should
+ * be determined from CPUID(0x8000001d) instead of CPUID(0x80000006).
+ */
+
+#define AMD_CPUID4_FULLY_ASSOCIATIVE	0xffff
+#define AMD_L2_L3_INVALID_ASSOC		0x9
 
-   In theory the TLBs could be reported as fake type (they are in "dummy").
-   Maybe later */
 union l1_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:8;
-		unsigned assoc:8;
-		unsigned size_in_kb:8;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:8;
+		unsigned assoc		:8;
+		unsigned size_in_kb	:8;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
 union l2_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:4;
-		unsigned assoc:4;
-		unsigned size_in_kb:16;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:4;
+		unsigned assoc		:4;
+		unsigned size_in_kb	:16;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
 union l3_cache {
 	struct {
-		unsigned line_size:8;
-		unsigned lines_per_tag:4;
-		unsigned assoc:4;
-		unsigned res:2;
-		unsigned size_encoded:14;
+		unsigned line_size	:8;
+		unsigned lines_per_tag	:4;
+		unsigned assoc		:4;
+		unsigned res		:2;
+		unsigned size_encoded	:14;
 	};
-	unsigned val;
+	unsigned int val;
 };
 
+/* L2/L3 associativity mapping */
 static const unsigned short assocs[] = {
-	[1] = 1,
-	[2] = 2,
-	[4] = 4,
-	[6] = 8,
-	[8] = 16,
-	[0xa] = 32,
-	[0xb] = 48,
-	[0xc] = 64,
-	[0xd] = 96,
-	[0xe] = 128,
-	[0xf] = 0xffff /* fully associative - no way to show this currently */
+	[1]		= 1,
+	[2]		= 2,
+	[3]		= 3,
+	[4]		= 4,
+	[5]		= 6,
+	[6]		= 8,
+	[8]		= 16,
+	[0xa]		= 32,
+	[0xb]		= 48,
+	[0xc]		= 64,
+	[0xd]		= 96,
+	[0xe]		= 128,
+	[0xf]		= AMD_CPUID4_FULLY_ASSOCIATIVE
 };
 
 static const unsigned char levels[] = { 1, 1, 2, 3 };
-static const unsigned char types[] = { 1, 2, 3, 3 };
-
-static const enum cache_type cache_type_map[] = {
-	[CTYPE_NULL] = CACHE_TYPE_NOCACHE,
-	[CTYPE_DATA] = CACHE_TYPE_DATA,
-	[CTYPE_INST] = CACHE_TYPE_INST,
-	[CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
-};
+static const unsigned char types[]  = { 1, 2, 3, 3 };
 
-static void
-amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
-		     union _cpuid4_leaf_ebx *ebx,
-		     union _cpuid4_leaf_ecx *ecx)
+static void legacy_amd_cpuid4(int index, union _cpuid4_leaf_eax *eax,
+			      union _cpuid4_leaf_ebx *ebx, union _cpuid4_leaf_ecx *ecx)
 {
-	unsigned dummy;
-	unsigned line_size, lines_per_tag, assoc, size_in_kb;
-	union l1_cache l1i, l1d;
+	unsigned int dummy, line_size, lines_per_tag, assoc, size_in_kb;
+	union l1_cache l1i, l1d, *l1;
 	union l2_cache l2;
 	union l3_cache l3;
-	union l1_cache *l1 = &l1d;
 
 	eax->full = 0;
 	ebx->full = 0;
@@ -258,430 +163,155 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
 	cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val);
 
-	switch (leaf) {
+	l1 = &l1d;
+	switch (index) {
 	case 1:
 		l1 = &l1i;
 		fallthrough;
 	case 0:
 		if (!l1->val)
 			return;
-		assoc = assocs[l1->assoc];
-		line_size = l1->line_size;
-		lines_per_tag = l1->lines_per_tag;
-		size_in_kb = l1->size_in_kb;
+
+		assoc		= (l1->assoc == 0xff) ? AMD_CPUID4_FULLY_ASSOCIATIVE : l1->assoc;
+		line_size	= l1->line_size;
+		lines_per_tag	= l1->lines_per_tag;
+		size_in_kb	= l1->size_in_kb;
 		break;
 	case 2:
-		if (!l2.val)
+		if (!l2.assoc || l2.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
-		assoc = assocs[l2.assoc];
-		line_size = l2.line_size;
-		lines_per_tag = l2.lines_per_tag;
-		/* cpu_data has errata corrections for K7 applied */
-		size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
+
+		/* Use x86_cache_size as it might have K7 errata fixes */
+		assoc		= assocs[l2.assoc];
+		line_size	= l2.line_size;
+		lines_per_tag	= l2.lines_per_tag;
+		size_in_kb	= __this_cpu_read(cpu_info.x86_cache_size);
 		break;
 	case 3:
-		if (!l3.val)
+		if (!l3.assoc || l3.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
-		assoc = assocs[l3.assoc];
-		line_size = l3.line_size;
-		lines_per_tag = l3.lines_per_tag;
-		size_in_kb = l3.size_encoded * 512;
+
+		assoc		= assocs[l3.assoc];
+		line_size	= l3.line_size;
+		lines_per_tag	= l3.lines_per_tag;
+		size_in_kb	= l3.size_encoded * 512;
 		if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
-			size_in_kb = size_in_kb >> 1;
-			assoc = assoc >> 1;
+			size_in_kb	= size_in_kb >> 1;
+			assoc		= assoc >> 1;
 		}
 		break;
 	default:
 		return;
 	}
 
-	eax->split.is_self_initializing = 1;
-	eax->split.type = types[leaf];
-	eax->split.level = levels[leaf];
-	eax->split.num_threads_sharing = 0;
-	eax->split.num_cores_on_die = topology_num_cores_per_package();
-
+	eax->split.is_self_initializing		= 1;
+	eax->split.type				= types[index];
+	eax->split.level			= levels[index];
+	eax->split.num_threads_sharing		= 0;
+	eax->split.num_cores_on_die		= topology_num_cores_per_package();
 
-	if (assoc == 0xffff)
+	if (assoc == AMD_CPUID4_FULLY_ASSOCIATIVE)
 		eax->split.is_fully_associative = 1;
-	ebx->split.coherency_line_size = line_size - 1;
-	ebx->split.ways_of_associativity = assoc - 1;
-	ebx->split.physical_line_partition = lines_per_tag - 1;
-	ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
-		(ebx->split.ways_of_associativity + 1) - 1;
-}
-
-#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
-
-/*
- * L3 cache descriptors
- */
-static void amd_calc_l3_indices(struct amd_northbridge *nb)
-{
-	struct amd_l3_cache *l3 = &nb->l3_cache;
-	unsigned int sc0, sc1, sc2, sc3;
-	u32 val = 0;
-
-	pci_read_config_dword(nb->misc, 0x1C4, &val);
-
-	/* calculate subcache sizes */
-	l3->subcaches[0] = sc0 = !(val & BIT(0));
-	l3->subcaches[1] = sc1 = !(val & BIT(4));
-
-	if (boot_cpu_data.x86 == 0x15) {
-		l3->subcaches[0] = sc0 += !(val & BIT(1));
-		l3->subcaches[1] = sc1 += !(val & BIT(5));
-	}
-
-	l3->subcaches[2] = sc2 = !(val & BIT(8))  + !(val & BIT(9));
-	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
-
-	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
-}
-
-/*
- * check whether a slot used for disabling an L3 index is occupied.
- * @l3: L3 cache descriptor
- * @slot: slot number (0..1)
- *
- * @returns: the disabled index if used or negative value if slot free.
- */
-static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
-{
-	unsigned int reg = 0;
-
-	pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
-
-	/* check whether this slot is activated already */
-	if (reg & (3UL << 30))
-		return reg & 0xfff;
-
-	return -1;
-}
-
-static ssize_t show_cache_disable(struct cacheinfo *this_leaf, char *buf,
-				  unsigned int slot)
-{
-	int index;
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	index = amd_get_l3_disable_slot(nb, slot);
-	if (index >= 0)
-		return sprintf(buf, "%d\n", index);
-
-	return sprintf(buf, "FREE\n");
-}
-
-#define SHOW_CACHE_DISABLE(slot)					\
-static ssize_t								\
-cache_disable_##slot##_show(struct device *dev,				\
-			    struct device_attribute *attr, char *buf)	\
-{									\
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);		\
-	return show_cache_disable(this_leaf, buf, slot);		\
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
-				 unsigned slot, unsigned long idx)
-{
-	int i;
-
-	idx |= BIT(30);
-
-	/*
-	 *  disable index in all 4 subcaches
-	 */
-	for (i = 0; i < 4; i++) {
-		u32 reg = idx | (i << 20);
-
-		if (!nb->l3_cache.subcaches[i])
-			continue;
-
-		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
-
-		/*
-		 * We need to WBINVD on a core on the node containing the L3
-		 * cache which indices we disable therefore a simple wbinvd()
-		 * is not sufficient.
-		 */
-		wbinvd_on_cpu(cpu);
-
-		reg |= BIT(31);
-		pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
-	}
-}
-
-/*
- * disable a L3 cache index by using a disable-slot
- *
- * @l3:    L3 cache descriptor
- * @cpu:   A CPU on the node containing the L3 cache
- * @slot:  slot number (0..1)
- * @index: index to disable
- *
- * @return: 0 on success, error status on failure
- */
-static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
-			    unsigned slot, unsigned long index)
-{
-	int ret = 0;
-
-	/*  check if @slot is already used or the index is already disabled */
-	ret = amd_get_l3_disable_slot(nb, slot);
-	if (ret >= 0)
-		return -EEXIST;
-
-	if (index > nb->l3_cache.indices)
-		return -EINVAL;
-
-	/* check whether the other slot has disabled the same index already */
-	if (index == amd_get_l3_disable_slot(nb, !slot))
-		return -EEXIST;
-
-	amd_l3_disable_index(nb, cpu, slot, index);
-
-	return 0;
-}
 
-static ssize_t store_cache_disable(struct cacheinfo *this_leaf,
-				   const char *buf, size_t count,
-				   unsigned int slot)
-{
-	unsigned long val = 0;
-	int cpu, err = 0;
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	cpu = cpumask_first(&this_leaf->shared_cpu_map);
-
-	if (kstrtoul(buf, 10, &val) < 0)
-		return -EINVAL;
-
-	err = amd_set_l3_disable_slot(nb, cpu, slot, val);
-	if (err) {
-		if (err == -EEXIST)
-			pr_warn("L3 slot %d in use/index already disabled!\n",
-				   slot);
-		return err;
-	}
-	return count;
-}
-
-#define STORE_CACHE_DISABLE(slot)					\
-static ssize_t								\
-cache_disable_##slot##_store(struct device *dev,			\
-			     struct device_attribute *attr,		\
-			     const char *buf, size_t count)		\
-{									\
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);		\
-	return store_cache_disable(this_leaf, buf, count, slot);	\
-}
-STORE_CACHE_DISABLE(0)
-STORE_CACHE_DISABLE(1)
-
-static ssize_t subcaches_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
-	int cpu = cpumask_first(&this_leaf->shared_cpu_map);
-
-	return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
-}
-
-static ssize_t subcaches_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
-{
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
-	int cpu = cpumask_first(&this_leaf->shared_cpu_map);
-	unsigned long val;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	if (kstrtoul(buf, 16, &val) < 0)
-		return -EINVAL;
-
-	if (amd_set_subcaches(cpu, val))
-		return -EINVAL;
-
-	return count;
+	ebx->split.coherency_line_size		= line_size - 1;
+	ebx->split.ways_of_associativity	= assoc - 1;
+	ebx->split.physical_line_partition	= lines_per_tag - 1;
+	ecx->split.number_of_sets		= (size_in_kb * 1024) / line_size /
+		(ebx->split.ways_of_associativity + 1) - 1;
 }
 
-static DEVICE_ATTR_RW(cache_disable_0);
-static DEVICE_ATTR_RW(cache_disable_1);
-static DEVICE_ATTR_RW(subcaches);
-
-static umode_t
-cache_private_attrs_is_visible(struct kobject *kobj,
-			       struct attribute *attr, int unused)
+static int cpuid4_info_fill_done(struct _cpuid4_info *id4, union _cpuid4_leaf_eax eax,
+				 union _cpuid4_leaf_ebx ebx, union _cpuid4_leaf_ecx ecx)
 {
-	struct device *dev = kobj_to_dev(kobj);
-	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
-	umode_t mode = attr->mode;
-
-	if (!this_leaf->priv)
-		return 0;
-
-	if ((attr == &dev_attr_subcaches.attr) &&
-	    amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
-		return mode;
+	if (eax.split.type == CTYPE_NULL)
+		return -EIO;
 
-	if ((attr == &dev_attr_cache_disable_0.attr ||
-	     attr == &dev_attr_cache_disable_1.attr) &&
-	    amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
-		return mode;
+	id4->eax = eax;
+	id4->ebx = ebx;
+	id4->ecx = ecx;
+	id4->size = (ecx.split.number_of_sets          + 1) *
+		    (ebx.split.coherency_line_size     + 1) *
+		    (ebx.split.physical_line_partition + 1) *
+		    (ebx.split.ways_of_associativity   + 1);
 
 	return 0;
 }
 
-static struct attribute_group cache_private_group = {
-	.is_visible = cache_private_attrs_is_visible,
-};
-
-static void init_amd_l3_attrs(void)
+static int amd_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	int n = 1;
-	static struct attribute **amd_l3_attrs;
-
-	if (amd_l3_attrs) /* already initialized */
-		return;
-
-	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
-		n += 2;
-	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
-		n += 1;
-
-	amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL);
-	if (!amd_l3_attrs)
-		return;
-
-	n = 0;
-	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
-		amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr;
-		amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr;
-	}
-	if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
-		amd_l3_attrs[n++] = &dev_attr_subcaches.attr;
-
-	cache_private_group.attrs = amd_l3_attrs;
-}
-
-const struct attribute_group *
-cache_get_priv_group(struct cacheinfo *this_leaf)
-{
-	struct amd_northbridge *nb = this_leaf->priv;
-
-	if (this_leaf->level < 3 || !nb)
-		return NULL;
+	union _cpuid4_leaf_eax eax;
+	union _cpuid4_leaf_ebx ebx;
+	union _cpuid4_leaf_ecx ecx;
+	u32 ignored;
 
-	if (nb && nb->l3_cache.indices)
-		init_amd_l3_attrs();
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT) || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &ignored);
+	else
+		legacy_amd_cpuid4(index, &eax, &ebx, &ecx);
 
-	return &cache_private_group;
+	return cpuid4_info_fill_done(id4, eax, ebx, ecx);
 }
 
-static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
+static int intel_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	int node;
+	union _cpuid4_leaf_eax eax;
+	union _cpuid4_leaf_ebx ebx;
+	union _cpuid4_leaf_ecx ecx;
+	u32 ignored;
 
-	/* only for L3, and not in virtualized environments */
-	if (index < 3)
-		return;
+	cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &ignored);
 
-	node = topology_amd_node_id(smp_processor_id());
-	this_leaf->nb = node_to_amd_nb(node);
-	if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
-		amd_calc_l3_indices(this_leaf->nb);
+	return cpuid4_info_fill_done(id4, eax, ebx, ecx);
 }
-#else
-#define amd_init_l3_cache(x, y)
-#endif  /* CONFIG_AMD_NB && CONFIG_SYSFS */
 
-static int
-cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
+static int fill_cpuid4_info(int index, struct _cpuid4_info *id4)
 {
-	union _cpuid4_leaf_eax	eax;
-	union _cpuid4_leaf_ebx	ebx;
-	union _cpuid4_leaf_ecx	ecx;
-	unsigned		edx;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		if (boot_cpu_has(X86_FEATURE_TOPOEXT))
-			cpuid_count(0x8000001d, index, &eax.full,
-				    &ebx.full, &ecx.full, &edx);
-		else
-			amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_init_l3_cache(this_leaf, index);
-	} else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
-		cpuid_count(0x8000001d, index, &eax.full,
-			    &ebx.full, &ecx.full, &edx);
-		amd_init_l3_cache(this_leaf, index);
-	} else {
-		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
-	}
+	u8 cpu_vendor = boot_cpu_data.x86_vendor;
 
-	if (eax.split.type == CTYPE_NULL)
-		return -EIO; /* better error ? */
-
-	this_leaf->eax = eax;
-	this_leaf->ebx = ebx;
-	this_leaf->ecx = ecx;
-	this_leaf->size = (ecx.split.number_of_sets          + 1) *
-			  (ebx.split.coherency_line_size     + 1) *
-			  (ebx.split.physical_line_partition + 1) *
-			  (ebx.split.ways_of_associativity   + 1);
-	return 0;
+	return (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON) ?
+		amd_fill_cpuid4_info(index, id4) :
+		intel_fill_cpuid4_info(index, id4);
 }
 
 static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 {
-	unsigned int		eax, ebx, ecx, edx, op;
-	union _cpuid4_leaf_eax	cache_eax;
-	int 			i = -1;
-
-	if (c->x86_vendor == X86_VENDOR_AMD ||
-	    c->x86_vendor == X86_VENDOR_HYGON)
-		op = 0x8000001d;
-	else
-		op = 4;
+	unsigned int eax, ebx, ecx, edx, op;
+	union _cpuid4_leaf_eax cache_eax;
+	int i = -1;
 
+	/* Do a CPUID(op) loop to calculate num_cache_leaves */
+	op = (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) ? 0x8000001d : 4;
 	do {
 		++i;
-		/* Do cpuid(op) loop to find out num_cache_leaves */
 		cpuid_count(op, i, &eax, &ebx, &ecx, &edx);
 		cache_eax.full = eax;
 	} while (cache_eax.split.type != CTYPE_NULL);
 	return i;
 }
 
+/*
+ * AMD/Hygon CPUs may have multiple LLCs if L3 caches exist.
+ */
+
 void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
 {
-	/*
-	 * We may have multiple LLCs if L3 caches exist, so check if we
-	 * have an L3 cache by looking at the L3 cache CPUID leaf.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return;
 
 	if (c->x86 < 0x17) {
-		/* LLC is at the node level. */
+		/* Pre-Zen: LLC is at the node level */
 		c->topo.llc_id = die_id;
 	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
-		 * LLC is at the core complex level.
-		 * Core complex ID is ApicId[3] for these processors.
+		 * Family 17h up to 1F models: LLC is at the core
+		 * complex level.  Core complex ID is ApicId[3].
 		 */
 		c->topo.llc_id = c->topo.apicid >> 3;
 	} else {
 		/*
-		 * LLC ID is calculated from the number of threads sharing the
-		 * cache.
-		 * */
+		 * Newer families: LLC ID is calculated from the number
+		 * of threads sharing the L3 cache.
+		 */
 		u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
 		u32 llc_index = find_num_cache_leaves(c) - 1;
 
@@ -690,25 +320,21 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
 			num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
 
 		if (num_sharing_cache) {
-			int bits = get_count_order(num_sharing_cache);
+			int index_msb = get_count_order(num_sharing_cache);
 
-			c->topo.llc_id = c->topo.apicid >> bits;
+			c->topo.llc_id = c->topo.apicid >> index_msb;
 		}
 	}
 }
 
 void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 {
-	/*
-	 * We may have multiple LLCs if L3 caches exist, so check if we
-	 * have an L3 cache by looking at the L3 cache CPUID leaf.
-	 */
-	if (!cpuid_edx(0x80000006))
+	if (!cpuid_amd_hygon_has_l3_cache())
 		return;
 
 	/*
-	 * LLC is at the core complex level.
-	 * Core complex ID is ApicId[3] for these processors.
+	 * Hygons are similar to AMD Family 17h up to 1F models: LLC is
+	 * at the core complex level.  Core complex ID is ApicId[3].
 	 */
 	c->topo.llc_id = c->topo.apicid >> 3;
 }
@@ -717,14 +343,10 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT))
 		ci->num_leaves = find_num_cache_leaves(c);
-	} else if (c->extended_cpuid_level >= 0x80000006) {
-		if (cpuid_edx(0x80000006) & 0xf000)
-			ci->num_leaves = 4;
-		else
-			ci->num_leaves = 3;
-	}
+	else if (c->extended_cpuid_level >= 0x80000006)
+		ci->num_leaves = (cpuid_edx(0x80000006) & 0xf000) ? 4 : 3;
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
@@ -734,156 +356,131 @@ void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 	ci->num_leaves = find_num_cache_leaves(c);
 }
 
-void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+static void intel_cacheinfo_done(struct cpuinfo_x86 *c, unsigned int l3,
+				 unsigned int l2, unsigned int l1i, unsigned int l1d)
 {
-	/* Cache sizes */
-	unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
-	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
-	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
-	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+	/*
+	 * If llc_id is still unset, then cpuid_level < 4, which implies
+	 * that the only possibility left is SMT.  Since CPUID(0x2) doesn't
+	 * specify any shared caches and SMT shares all caches, we can
+	 * unconditionally set LLC ID to the package ID so that all
+	 * threads share it.
+	 */
+	if (c->topo.llc_id == BAD_APICID)
+		c->topo.llc_id = c->topo.pkg_id;
 
-	if (c->cpuid_level > 3) {
-		/*
-		 * There should be at least one leaf. A non-zero value means
-		 * that the number of leaves has been initialized.
-		 */
-		if (!ci->num_leaves)
-			ci->num_leaves = find_num_cache_leaves(c);
+	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : l1i + l1d);
 
-		/*
-		 * Whenever possible use cpuid(4), deterministic cache
-		 * parameters cpuid leaf to find the cache details
-		 */
-		for (i = 0; i < ci->num_leaves; i++) {
-			struct _cpuid4_info_regs this_leaf = {};
-			int retval;
+	if (!l2)
+		cpu_detect_cache_sizes(c);
+}
 
-			retval = cpuid4_cache_lookup_regs(i, &this_leaf);
-			if (retval < 0)
-				continue;
+/*
+ * Legacy Intel CPUID(0x2) path if CPUID(0x4) is not available.
+ */
+static void intel_cacheinfo_0x2(struct cpuinfo_x86 *c)
+{
+	unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
+	const struct leaf_0x2_table *desc;
+	union leaf_0x2_regs regs;
+	u8 *ptr;
 
-			switch (this_leaf.eax.split.level) {
-			case 1:
-				if (this_leaf.eax.split.type == CTYPE_DATA)
-					new_l1d = this_leaf.size/1024;
-				else if (this_leaf.eax.split.type == CTYPE_INST)
-					new_l1i = this_leaf.size/1024;
-				break;
-			case 2:
-				new_l2 = this_leaf.size/1024;
-				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-				index_msb = get_count_order(num_threads_sharing);
-				l2_id = c->topo.apicid & ~((1 << index_msb) - 1);
-				break;
-			case 3:
-				new_l3 = this_leaf.size/1024;
-				num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
-				index_msb = get_count_order(num_threads_sharing);
-				l3_id = c->topo.apicid & ~((1 << index_msb) - 1);
-				break;
-			default:
-				break;
-			}
+	if (c->cpuid_level < 2)
+		return;
+
+	cpuid_leaf_0x2(&regs);
+	for_each_cpuid_0x2_desc(regs, ptr, desc) {
+		switch (desc->c_type) {
+		case CACHE_L1_INST:	l1i += desc->c_size; break;
+		case CACHE_L1_DATA:	l1d += desc->c_size; break;
+		case CACHE_L2:		l2  += desc->c_size; break;
+		case CACHE_L3:		l3  += desc->c_size; break;
 		}
 	}
+
+	intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+}
+
+static unsigned int calc_cache_topo_id(struct cpuinfo_x86 *c, const struct _cpuid4_info *id4)
+{
+	unsigned int num_threads_sharing;
+	int index_msb;
+
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
+	index_msb = get_count_order(num_threads_sharing);
+	return c->topo.apicid & ~((1 << index_msb) - 1);
+}
+
+static bool intel_cacheinfo_0x4(struct cpuinfo_x86 *c)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+	unsigned int l2_id = BAD_APICID, l3_id = BAD_APICID;
+	unsigned int l1d = 0, l1i = 0, l2 = 0, l3 = 0;
+
+	if (c->cpuid_level < 4)
+		return false;
+
 	/*
-	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
-	 * trace cache
+	 * There should be at least one leaf. A non-zero value means
+	 * that the number of leaves has been previously initialized.
 	 */
-	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
-		/* supports eax=2  call */
-		int j, n;
-		unsigned int regs[4];
-		unsigned char *dp = (unsigned char *)regs;
-		int only_trace = 0;
-
-		if (ci->num_leaves && c->x86 == 15)
-			only_trace = 1;
-
-		/* Number of times to iterate */
-		n = cpuid_eax(2) & 0xFF;
-
-		for (i = 0 ; i < n ; i++) {
-			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
-
-			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
-				if (regs[j] & (1 << 31))
-					regs[j] = 0;
-
-			/* Byte 0 is level count, not a descriptor */
-			for (j = 1 ; j < 16 ; j++) {
-				unsigned char des = dp[j];
-				unsigned char k = 0;
-
-				/* look up this descriptor in the table */
-				while (cache_table[k].descriptor != 0) {
-					if (cache_table[k].descriptor == des) {
-						if (only_trace && cache_table[k].cache_type != LVL_TRACE)
-							break;
-						switch (cache_table[k].cache_type) {
-						case LVL_1_INST:
-							l1i += cache_table[k].size;
-							break;
-						case LVL_1_DATA:
-							l1d += cache_table[k].size;
-							break;
-						case LVL_2:
-							l2 += cache_table[k].size;
-							break;
-						case LVL_3:
-							l3 += cache_table[k].size;
-							break;
-						}
-
-						break;
-					}
-
-					k++;
-				}
-			}
-		}
-	}
+	if (!ci->num_leaves)
+		ci->num_leaves = find_num_cache_leaves(c);
 
-	if (new_l1d)
-		l1d = new_l1d;
+	if (!ci->num_leaves)
+		return false;
 
-	if (new_l1i)
-		l1i = new_l1i;
+	for (int i = 0; i < ci->num_leaves; i++) {
+		struct _cpuid4_info id4 = {};
+		int ret;
 
-	if (new_l2) {
-		l2 = new_l2;
-		c->topo.llc_id = l2_id;
-		c->topo.l2c_id = l2_id;
-	}
+		ret = intel_fill_cpuid4_info(i, &id4);
+		if (ret < 0)
+			continue;
 
-	if (new_l3) {
-		l3 = new_l3;
-		c->topo.llc_id = l3_id;
+		switch (id4.eax.split.level) {
+		case 1:
+			if (id4.eax.split.type == CTYPE_DATA)
+				l1d = id4.size / 1024;
+			else if (id4.eax.split.type == CTYPE_INST)
+				l1i = id4.size / 1024;
+			break;
+		case 2:
+			l2 = id4.size / 1024;
+			l2_id = calc_cache_topo_id(c, &id4);
+			break;
+		case 3:
+			l3 = id4.size / 1024;
+			l3_id = calc_cache_topo_id(c, &id4);
+			break;
+		default:
+			break;
+		}
 	}
 
-	/*
-	 * If llc_id is not yet set, this means cpuid_level < 4 which in
-	 * turns means that the only possibility is SMT (as indicated in
-	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
-	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
-	 * c->topo.pkg_id.
-	 */
-	if (c->topo.llc_id == BAD_APICID)
-		c->topo.llc_id = c->topo.pkg_id;
+	c->topo.l2c_id = l2_id;
+	c->topo.llc_id = (l3_id == BAD_APICID) ? l2_id : l3_id;
+	intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+	return true;
+}
 
-	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+{
+	/* Don't use CPUID(0x2) if CPUID(0x4) is supported. */
+	if (intel_cacheinfo_0x4(c))
+		return;
 
-	if (!l2)
-		cpu_detect_cache_sizes(c);
+	intel_cacheinfo_0x2(c);
 }
 
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, AMD/Hygon
+ */
 static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
-				    struct _cpuid4_info_regs *base)
+				    const struct _cpuid4_info *id4)
 {
 	struct cpu_cacheinfo *this_cpu_ci;
-	struct cacheinfo *this_leaf;
+	struct cacheinfo *ci;
 	int i, sibling;
 
 	/*
@@ -895,18 +492,18 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 			this_cpu_ci = get_cpu_cacheinfo(i);
 			if (!this_cpu_ci->info_list)
 				continue;
-			this_leaf = this_cpu_ci->info_list + index;
+
+			ci = this_cpu_ci->info_list + index;
 			for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
 				if (!cpu_online(sibling))
 					continue;
-				cpumask_set_cpu(sibling,
-						&this_leaf->shared_cpu_map);
+				cpumask_set_cpu(sibling, &ci->shared_cpu_map);
 			}
 		}
 	} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
-		nshared = base->eax.split.num_threads_sharing + 1;
+		nshared = id4->eax.split.num_threads_sharing + 1;
 		apicid = cpu_data(cpu).topo.apicid;
 		first = apicid - (apicid % nshared);
 		last = first + nshared - 1;
@@ -920,14 +517,13 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 			if ((apicid < first) || (apicid > last))
 				continue;
 
-			this_leaf = this_cpu_ci->info_list + index;
+			ci = this_cpu_ci->info_list + index;
 
 			for_each_online_cpu(sibling) {
 				apicid = cpu_data(sibling).topo.apicid;
 				if ((apicid < first) || (apicid > last))
 					continue;
-				cpumask_set_cpu(sibling,
-						&this_leaf->shared_cpu_map);
+				cpumask_set_cpu(sibling, &ci->shared_cpu_map);
 			}
 		}
 	} else
@@ -936,25 +532,27 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 	return 1;
 }
 
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, Intel + fallback AMD/Hygon
+ */
 static void __cache_cpumap_setup(unsigned int cpu, int index,
-				 struct _cpuid4_info_regs *base)
+				 const struct _cpuid4_info *id4)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf, *sibling_leaf;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct cacheinfo *ci, *sibling_ci;
 	unsigned long num_threads_sharing;
 	int index_msb, i;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor == X86_VENDOR_AMD ||
-	    c->x86_vendor == X86_VENDOR_HYGON) {
-		if (__cache_amd_cpumap_setup(cpu, index, base))
+	if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
+		if (__cache_amd_cpumap_setup(cpu, index, id4))
 			return;
 	}
 
-	this_leaf = this_cpu_ci->info_list + index;
-	num_threads_sharing = 1 + base->eax.split.num_threads_sharing;
+	ci = this_cpu_ci->info_list + index;
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
 
-	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+	cpumask_set_cpu(cpu, &ci->shared_cpu_map);
 	if (num_threads_sharing == 1)
 		return;
 
@@ -964,30 +562,29 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 		if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) {
 			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
 
+			/* Skip if itself or no cacheinfo */
 			if (i == cpu || !sib_cpu_ci->info_list)
-				continue;/* skip if itself or no cacheinfo */
-			sibling_leaf = sib_cpu_ci->info_list + index;
-			cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
-			cpumask_set_cpu(cpu, &sibling_leaf->shared_cpu_map);
+				continue;
+
+			sibling_ci = sib_cpu_ci->info_list + index;
+			cpumask_set_cpu(i, &ci->shared_cpu_map);
+			cpumask_set_cpu(cpu, &sibling_ci->shared_cpu_map);
 		}
 }
 
-static void ci_leaf_init(struct cacheinfo *this_leaf,
-			 struct _cpuid4_info_regs *base)
+static void ci_info_init(struct cacheinfo *ci, const struct _cpuid4_info *id4,
+			 struct amd_northbridge *nb)
 {
-	this_leaf->id = base->id;
-	this_leaf->attributes = CACHE_ID;
-	this_leaf->level = base->eax.split.level;
-	this_leaf->type = cache_type_map[base->eax.split.type];
-	this_leaf->coherency_line_size =
-				base->ebx.split.coherency_line_size + 1;
-	this_leaf->ways_of_associativity =
-				base->ebx.split.ways_of_associativity + 1;
-	this_leaf->size = base->size;
-	this_leaf->number_of_sets = base->ecx.split.number_of_sets + 1;
-	this_leaf->physical_line_partition =
-				base->ebx.split.physical_line_partition + 1;
-	this_leaf->priv = base->nb;
+	ci->id				= id4->id;
+	ci->attributes			= CACHE_ID;
+	ci->level			= id4->eax.split.level;
+	ci->type			= cache_type_map[id4->eax.split.type];
+	ci->coherency_line_size		= id4->ebx.split.coherency_line_size + 1;
+	ci->ways_of_associativity	= id4->ebx.split.ways_of_associativity + 1;
+	ci->size			= id4->size;
+	ci->number_of_sets		= id4->ecx.split.number_of_sets + 1;
+	ci->physical_line_partition	= id4->ebx.split.physical_line_partition + 1;
+	ci->priv			= nb;
 }
 
 int init_cache_level(unsigned int cpu)
@@ -1002,38 +599,45 @@ int init_cache_level(unsigned int cpu)
 }
 
 /*
- * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * The max shared threads number comes from CPUID(0x4) EAX[25-14] with input
  * ECX as cache index. Then right shift apicid by the number's order to get
  * cache id for this cache node.
  */
-static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+static void get_cache_id(int cpu, struct _cpuid4_info *id4)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	unsigned long num_threads_sharing;
 	int index_msb;
 
-	num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+	num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
 	index_msb = get_count_order(num_threads_sharing);
-	id4_regs->id = c->topo.apicid >> index_msb;
+	id4->id = c->topo.apicid >> index_msb;
 }
 
 int populate_cache_leaves(unsigned int cpu)
 {
-	unsigned int idx, ret;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-	struct _cpuid4_info_regs id4_regs = {};
+	struct cacheinfo *ci = this_cpu_ci->info_list;
+	u8 cpu_vendor = boot_cpu_data.x86_vendor;
+	struct amd_northbridge *nb = NULL;
+	struct _cpuid4_info id4 = {};
+	int idx, ret;
 
 	for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) {
-		ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
+		ret = fill_cpuid4_info(idx, &id4);
 		if (ret)
 			return ret;
-		get_cache_id(cpu, &id4_regs);
-		ci_leaf_init(this_leaf++, &id4_regs);
-		__cache_cpumap_setup(cpu, idx, &id4_regs);
+
+		get_cache_id(cpu, &id4);
+
+		if (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON)
+			nb = amd_init_l3_cache(idx);
+
+		ci_info_init(ci++, &id4, nb);
+		__cache_cpumap_setup(cpu, idx, &id4);
 	}
-	this_cpu_ci->cpu_map_populated = true;
 
+	this_cpu_ci->cpu_map_populated = true;
 	return 0;
 }
 
@@ -1049,31 +653,33 @@ int populate_cache_leaves(unsigned int cpu)
 static unsigned long saved_cr4;
 static DEFINE_RAW_SPINLOCK(cache_disable_lock);
 
+/*
+ * Cache flushing is the most time-consuming step when programming the
+ * MTRRs.  On many Intel CPUs without known erratas, it can be skipped
+ * if the CPU declares cache self-snooping support.
+ */
+static void maybe_flush_caches(void)
+{
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
+}
+
 void cache_disable(void) __acquires(cache_disable_lock)
 {
 	unsigned long cr0;
 
 	/*
-	 * Note that this is not ideal
-	 * since the cache is only flushed/disabled for this CPU while the
-	 * MTRRs are changed, but changing this requires more invasive
-	 * changes to the way the kernel boots
+	 * This is not ideal since the cache is only flushed/disabled
+	 * for this CPU while the MTRRs are changed, but changing this
+	 * requires more invasive changes to the way the kernel boots.
 	 */
-
 	raw_spin_lock(&cache_disable_lock);
 
 	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
 	cr0 = read_cr0() | X86_CR0_CD;
 	write_cr0(cr0);
 
-	/*
-	 * Cache flushing is the most time-consuming step when programming
-	 * the MTRRs. Fortunately, as per the Intel Software Development
-	 * Manual, we can skip it if the processor supports cache self-
-	 * snooping.
-	 */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
+	maybe_flush_caches();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (cpu_feature_enabled(X86_FEATURE_PGE)) {
@@ -1088,9 +694,7 @@ void cache_disable(void) __acquires(cache_disable_lock)
 	if (cpu_feature_enabled(X86_FEATURE_MTRR))
 		mtrr_disable();
 
-	/* Again, only flush caches if we have to. */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
+	maybe_flush_caches();
 }
 
 void cache_enable(void) __releases(cache_disable_lock)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2..8feb8fd2957a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -29,7 +29,7 @@
 
 #include <asm/alternative.h>
 #include <asm/cmdline.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/perf_event.h>
 #include <asm/mmu_context.h>
 #include <asm/doublefault.h>
@@ -148,7 +148,7 @@ static void ppin_init(struct cpuinfo_x86 *c)
 	 */
 	info = (struct ppin_info *)id->driver_data;
 
-	if (rdmsrl_safe(info->msr_ppin_ctl, &val))
+	if (rdmsrq_safe(info->msr_ppin_ctl, &val))
 		goto clear_ppin;
 
 	if ((val & 3UL) == 1UL) {
@@ -158,13 +158,13 @@ static void ppin_init(struct cpuinfo_x86 *c)
 
 	/* If PPIN is disabled, try to enable */
 	if (!(val & 2UL)) {
-		wrmsrl_safe(info->msr_ppin_ctl,  val | 2UL);
-		rdmsrl_safe(info->msr_ppin_ctl, &val);
+		wrmsrq_safe(info->msr_ppin_ctl,  val | 2UL);
+		rdmsrq_safe(info->msr_ppin_ctl, &val);
 	}
 
 	/* Is the enable bit set? */
 	if (val & 2UL) {
-		c->ppin = __rdmsr(info->msr_ppin);
+		c->ppin = native_rdmsrq(info->msr_ppin);
 		set_cpu_cap(c, info->feature);
 		return;
 	}
@@ -242,6 +242,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 #endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
+SYM_PIC_ALIAS(gdt_page);
 
 #ifdef CONFIG_X86_64
 static int __init x86_nopcid_setup(char *s)
@@ -321,7 +322,7 @@ static int __init cachesize_setup(char *str)
 __setup("cachesize=", cachesize_setup);
 
 /* Probe for the CPUID instruction */
-bool have_cpuid_p(void)
+bool cpuid_feature(void)
 {
 	return flag_is_changeable_p(X86_EFLAGS_ID);
 }
@@ -562,9 +563,9 @@ __noendbr u64 ibt_save(bool disable)
 	u64 msr = 0;
 
 	if (cpu_feature_enabled(X86_FEATURE_IBT)) {
-		rdmsrl(MSR_IA32_S_CET, msr);
+		rdmsrq(MSR_IA32_S_CET, msr);
 		if (disable)
-			wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
+			wrmsrq(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
 	}
 
 	return msr;
@@ -575,10 +576,10 @@ __noendbr void ibt_restore(u64 save)
 	u64 msr;
 
 	if (cpu_feature_enabled(X86_FEATURE_IBT)) {
-		rdmsrl(MSR_IA32_S_CET, msr);
+		rdmsrq(MSR_IA32_S_CET, msr);
 		msr &= ~CET_ENDBR_EN;
 		msr |= (save & CET_ENDBR_EN);
-		wrmsrl(MSR_IA32_S_CET, msr);
+		wrmsrq(MSR_IA32_S_CET, msr);
 	}
 }
 
@@ -602,15 +603,15 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_USER_SHSTK);
 
 	if (kernel_ibt)
-		wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN);
+		wrmsrq(MSR_IA32_S_CET, CET_ENDBR_EN);
 	else
-		wrmsrl(MSR_IA32_S_CET, 0);
+		wrmsrq(MSR_IA32_S_CET, 0);
 
 	cr4_set_bits(X86_CR4_CET);
 
 	if (kernel_ibt && ibt_selftest()) {
 		pr_err("IBT selftest: Failed!\n");
-		wrmsrl(MSR_IA32_S_CET, 0);
+		wrmsrq(MSR_IA32_S_CET, 0);
 		setup_clear_cpu_cap(X86_FEATURE_IBT);
 	}
 }
@@ -621,8 +622,8 @@ __noendbr void cet_disable(void)
 	      cpu_feature_enabled(X86_FEATURE_SHSTK)))
 		return;
 
-	wrmsrl(MSR_IA32_S_CET, 0);
-	wrmsrl(MSR_IA32_U_CET, 0);
+	wrmsrq(MSR_IA32_S_CET, 0);
+	wrmsrq(MSR_IA32_U_CET, 0);
 }
 
 /*
@@ -667,8 +668,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 		if (!warn)
 			continue;
 
-		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
-			x86_cap_flag(df->feature), df->level);
+		pr_warn("CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+			x86_cap_flags[df->feature], df->level);
 	}
 }
 
@@ -751,9 +752,9 @@ void __init switch_gdt_and_percpu_base(int cpu)
 	 * No need to load %gs. It is already correct.
 	 *
 	 * Writing %gs on 64bit would zero GSBASE which would make any per
-	 * CPU operation up to the point of the wrmsrl() fault.
+	 * CPU operation up to the point of the wrmsrq() fault.
 	 *
-	 * Set GSBASE to the new offset. Until the wrmsrl() happens the
+	 * Set GSBASE to the new offset. Until the wrmsrq() happens the
 	 * early mapping is still valid. That means the GSBASE update will
 	 * lose any prior per CPU data which was not copied over in
 	 * setup_per_cpu_areas().
@@ -761,7 +762,7 @@ void __init switch_gdt_and_percpu_base(int cpu)
 	 * This works even with stackprotector enabled because the
 	 * per CPU stack canary is 0 in both per CPU areas.
 	 */
-	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+	wrmsrq(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #else
 	/*
 	 * %fs is already set to __KERNEL_PERCPU, but after switching GDT
@@ -846,13 +847,13 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 	c->x86_cache_size = l2size;
 }
 
-u16 __read_mostly tlb_lli_4k[NR_INFO];
-u16 __read_mostly tlb_lli_2m[NR_INFO];
-u16 __read_mostly tlb_lli_4m[NR_INFO];
-u16 __read_mostly tlb_lld_4k[NR_INFO];
-u16 __read_mostly tlb_lld_2m[NR_INFO];
-u16 __read_mostly tlb_lld_4m[NR_INFO];
-u16 __read_mostly tlb_lld_1g[NR_INFO];
+u16 __read_mostly tlb_lli_4k;
+u16 __read_mostly tlb_lli_2m;
+u16 __read_mostly tlb_lli_4m;
+u16 __read_mostly tlb_lld_4k;
+u16 __read_mostly tlb_lld_2m;
+u16 __read_mostly tlb_lld_4m;
+u16 __read_mostly tlb_lld_1g;
 
 static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 {
@@ -860,12 +861,10 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		this_cpu->c_detect_tlb(c);
 
 	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
-		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
-		tlb_lli_4m[ENTRIES]);
+		tlb_lli_4k, tlb_lli_2m, tlb_lli_4m);
 
 	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
-		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
-		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
+		tlb_lld_4k, tlb_lld_2m, tlb_lld_4m, tlb_lld_1g);
 }
 
 void get_cpu_vendor(struct cpuinfo_x86 *c)
@@ -1007,17 +1006,18 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
-	/* AMD-defined flags: level 0x80000001 */
+	/*
+	 * Check if extended CPUID leaves are implemented: Max extended
+	 * CPUID leaf must be in the 0x80000001-0x8000ffff range.
+	 */
 	eax = cpuid_eax(0x80000000);
-	c->extended_cpuid_level = eax;
+	c->extended_cpuid_level = ((eax & 0xffff0000) == 0x80000000) ? eax : 0;
 
-	if ((eax & 0xffff0000) == 0x80000000) {
-		if (eax >= 0x80000001) {
-			cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+	if (c->extended_cpuid_level >= 0x80000001) {
+		cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
 
-			c->x86_capability[CPUID_8000_0001_ECX] = ecx;
-			c->x86_capability[CPUID_8000_0001_EDX] = edx;
-		}
+		c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+		c->x86_capability[CPUID_8000_0001_EDX] = edx;
 	}
 
 	if (c->extended_cpuid_level >= 0x80000007) {
@@ -1164,7 +1164,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 
 	VULNWL_INTEL(INTEL_CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
+	VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID2,NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
 	VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(INTEL_ATOM_GOLDMONT,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
@@ -1205,6 +1205,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define VULNBL_INTEL_STEPS(vfm, max_stepping, issues)		   \
 	X86_MATCH_VFM_STEPS(vfm, X86_STEP_MIN, max_stepping, issues)
 
+#define VULNBL_INTEL_TYPE(vfm, cpu_type, issues)	\
+	X86_MATCH_VFM_CPU_TYPE(vfm, INTEL_CPU_TYPE_##cpu_type, issues)
+
 #define VULNBL_AMD(family, blacklist)		\
 	VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
 
@@ -1226,6 +1229,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define GDS		BIT(6)
 /* CPU is affected by Register File Data Sampling */
 #define RFDS		BIT(7)
+/* CPU is affected by Indirect Target Selection */
+#define ITS		BIT(8)
+/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
+#define ITS_NATIVE_ONLY	BIT(9)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1237,25 +1244,28 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_G,	     X86_STEP_MAX,	SRBDS),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_X,	     X86_STEP_MAX,	MMIO),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,		      0x5,	MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,		      0xb,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,		      0xc,	MMIO | RETBLEED | GDS | SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
 	VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L,	     X86_STEP_MAX,	RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_D,	     X86_STEP_MAX,	MMIO | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ICELAKE_X,	     X86_STEP_MAX,	MMIO | GDS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L,	     X86_STEP_MAX,	GDS),
-	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_D,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_ICELAKE_X,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED | ITS),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_LAKEFIELD,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE,	     X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
+	VULNBL_INTEL_TYPE(INTEL_ALDERLAKE,		     ATOM,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L,	     X86_STEP_MAX,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE,	     X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE,		     ATOM,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P,	     X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S,	     X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT,     X86_STEP_MAX,	RFDS),
@@ -1287,7 +1297,7 @@ u64 x86_read_arch_cap_msr(void)
 	u64 x86_arch_cap_msr = 0;
 
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
+		rdmsrq(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
 
 	return x86_arch_cap_msr;
 }
@@ -1317,10 +1327,78 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
 	return cpu_matches(cpu_vuln_blacklist, RFDS);
 }
 
+static bool __init vulnerable_to_its(u64 x86_arch_cap_msr)
+{
+	/* The "immunity" bit trumps everything else: */
+	if (x86_arch_cap_msr & ARCH_CAP_ITS_NO)
+		return false;
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	/* None of the affected CPUs have BHI_CTRL */
+	if (boot_cpu_has(X86_FEATURE_BHI_CTRL))
+		return false;
+
+	/*
+	 * If a VMM did not expose ITS_NO, assume that a guest could
+	 * be running on a vulnerable hardware or may migrate to such
+	 * hardware.
+	 */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
+
+	if (cpu_matches(cpu_vuln_blacklist, ITS))
+		return true;
+
+	return false;
+}
+
+static struct x86_cpu_id cpu_latest_microcode[] = {
+#include "microcode/intel-ucode-defs.h"
+	{}
+};
+
+static bool __init cpu_has_old_microcode(void)
+{
+	const struct x86_cpu_id *m = x86_match_cpu(cpu_latest_microcode);
+
+	/* Give unknown CPUs a pass: */
+	if (!m) {
+		/* Intel CPUs should be in the list. Warn if not: */
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+			pr_info("x86/CPU: Model not found in latest microcode list\n");
+		return false;
+	}
+
+	/*
+	 * Hosts usually lie to guests with a super high microcode
+	 * version. Just ignore what hosts tell guests:
+	 */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return false;
+
+	/* Consider all debug microcode to be old: */
+	if (boot_cpu_data.microcode & BIT(31))
+		return true;
+
+	/* Give new microcode a pass: */
+	if (boot_cpu_data.microcode >= m->driver_data)
+		return false;
+
+	/* Uh oh, too old: */
+	return true;
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
 
+	if (cpu_has_old_microcode()) {
+		pr_warn("x86/CPU: Running old microcode\n");
+		setup_force_cpu_bug(X86_BUG_OLD_MICROCODE);
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
+
 	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
 	if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
 	    !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO))
@@ -1331,8 +1409,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 
-	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2)) {
 		setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+		setup_force_cpu_bug(X86_BUG_SPECTRE_V2_USER);
+	}
 
 	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
 	    !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) &&
@@ -1399,15 +1479,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	 * Affected CPU list is generally enough to enumerate the vulnerability,
 	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
 	 * not want the guest to enumerate the bug.
-	 *
-	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
-	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
 	 */
 	if (!arch_cap_mmio_immune(x86_arch_cap_msr)) {
 		if (cpu_matches(cpu_vuln_blacklist, MMIO))
 			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
-		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
-			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
 	}
 
 	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
@@ -1436,9 +1511,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (vulnerable_to_rfds(x86_arch_cap_msr))
 		setup_force_cpu_bug(X86_BUG_RFDS);
 
-	/* When virtualized, eIBRS could be hidden, assume vulnerable */
-	if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
-	    !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+	/*
+	 * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with
+	 * BHI_NO still need to use the BHI mitigation to prevent Intra-mode
+	 * attacks.  When virtualized, eIBRS could be hidden, assume vulnerable.
+	 */
+	if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
 	    (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
 	     boot_cpu_has(X86_FEATURE_HYPERVISOR)))
 		setup_force_cpu_bug(X86_BUG_BHI);
@@ -1446,6 +1524,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
 		setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
 
+	if (vulnerable_to_its(x86_arch_cap_msr)) {
+		setup_force_cpu_bug(X86_BUG_ITS);
+		if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY))
+			setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
+	}
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
@@ -1479,15 +1563,96 @@ static void detect_nopl(void)
 #endif
 }
 
+static inline bool parse_set_clear_cpuid(char *arg, bool set)
+{
+	char *opt;
+	int taint = 0;
+
+	while (arg) {
+		bool found __maybe_unused = false;
+		unsigned int bit;
+
+		opt = strsep(&arg, ",");
+
+		/*
+		 * Handle naked numbers first for feature flags which don't
+		 * have names. It doesn't make sense for a bug not to have a
+		 * name so don't handle bug flags here.
+		 */
+		if (!kstrtouint(opt, 10, &bit)) {
+			if (bit < NCAPINTS * 32) {
+
+				if (set) {
+					pr_warn("setcpuid: force-enabling CPU feature flag:");
+					setup_force_cpu_cap(bit);
+				} else {
+					pr_warn("clearcpuid: force-disabling CPU feature flag:");
+					setup_clear_cpu_cap(bit);
+				}
+				/* empty-string, i.e., ""-defined feature flags */
+				if (!x86_cap_flags[bit])
+					pr_cont(" %d:%d\n", bit >> 5, bit & 31);
+				else
+					pr_cont(" %s\n", x86_cap_flags[bit]);
+
+				taint++;
+			}
+			/*
+			 * The assumption is that there are no feature names with only
+			 * numbers in the name thus go to the next argument.
+			 */
+			continue;
+		}
+
+		for (bit = 0; bit < 32 * (NCAPINTS + NBUGINTS); bit++) {
+			const char *flag;
+			const char *kind;
+
+			if (bit < 32 * NCAPINTS) {
+				flag = x86_cap_flags[bit];
+				kind = "feature";
+			} else {
+				kind = "bug";
+				flag = x86_bug_flags[bit - (32 * NCAPINTS)];
+			}
+
+			if (!flag)
+				continue;
+
+			if (strcmp(flag, opt))
+				continue;
+
+			if (set) {
+				pr_warn("setcpuid: force-enabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_force_cpu_cap(bit);
+			} else {
+				pr_warn("clearcpuid: force-disabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_clear_cpu_cap(bit);
+			}
+			taint++;
+			found = true;
+			break;
+		}
+
+		if (!found)
+			pr_warn("%s: unknown CPU flag: %s", set ? "setcpuid" : "clearcpuid", opt);
+	}
+
+	return taint;
+}
+
+
 /*
  * We parse cpu parameters early because fpu__init_system() is executed
  * before parse_early_param().
  */
 static void __init cpu_parse_early_param(void)
 {
+	bool cpuid_taint = false;
 	char arg[128];
-	char *argptr = arg, *opt;
-	int arglen, taint = 0;
+	int arglen;
 
 #ifdef CONFIG_X86_32
 	if (cmdline_find_option_bool(boot_command_line, "no387"))
@@ -1519,61 +1684,17 @@ static void __init cpu_parse_early_param(void)
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
-
-	pr_info("Clearing CPUID bits:");
-
-	while (argptr) {
-		bool found __maybe_unused = false;
-		unsigned int bit;
-
-		opt = strsep(&argptr, ",");
-
-		/*
-		 * Handle naked numbers first for feature flags which don't
-		 * have names.
-		 */
-		if (!kstrtouint(opt, 10, &bit)) {
-			if (bit < NCAPINTS * 32) {
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, false);
 
-				/* empty-string, i.e., ""-defined feature flags */
-				if (!x86_cap_flags[bit])
-					pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit));
-				else
-					pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
+	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, true);
 
-				setup_clear_cpu_cap(bit);
-				taint++;
-			}
-			/*
-			 * The assumption is that there are no feature names with only
-			 * numbers in the name thus go to the next argument.
-			 */
-			continue;
-		}
-
-		for (bit = 0; bit < 32 * NCAPINTS; bit++) {
-			if (!x86_cap_flag(bit))
-				continue;
-
-			if (strcmp(x86_cap_flag(bit), opt))
-				continue;
-
-			pr_cont(" %s", opt);
-			setup_clear_cpu_cap(bit);
-			taint++;
-			found = true;
-			break;
-		}
-
-		if (!found)
-			pr_cont(" (unknown: %s)", opt);
-	}
-	pr_cont("\n");
-
-	if (taint)
+	if (cpuid_taint) {
+		pr_warn("!!! setcpuid=/clearcpuid= in use, this is for TESTING ONLY, may break things horribly. Tainting kernel.\n");
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
 }
 
 /*
@@ -1590,11 +1711,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
 	c->extended_cpuid_level = 0;
 
-	if (!have_cpuid_p())
+	if (!cpuid_feature())
 		identify_cpu_without_cpuid(c);
 
 	/* cyrix could have cpuid enabled via c_identify()*/
-	if (have_cpuid_p()) {
+	if (cpuid_feature()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
 		intel_unlock_cpuid_leafs(c);
@@ -1610,6 +1731,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 		c->cpu_index = 0;
 		filter_cpuid_features(c, false);
+		check_cpufeature_deps(c);
 
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
@@ -1708,11 +1830,11 @@ static bool detect_null_seg_behavior(void)
 	 */
 
 	unsigned long old_base, tmp;
-	rdmsrl(MSR_FS_BASE, old_base);
-	wrmsrl(MSR_FS_BASE, 1);
+	rdmsrq(MSR_FS_BASE, old_base);
+	wrmsrq(MSR_FS_BASE, 1);
 	loadsegment(fs, 0);
-	rdmsrl(MSR_FS_BASE, tmp);
-	wrmsrl(MSR_FS_BASE, old_base);
+	rdmsrq(MSR_FS_BASE, tmp);
+	wrmsrq(MSR_FS_BASE, old_base);
 	return tmp == 0;
 }
 
@@ -1753,11 +1875,11 @@ static void generic_identify(struct cpuinfo_x86 *c)
 {
 	c->extended_cpuid_level = 0;
 
-	if (!have_cpuid_p())
+	if (!cpuid_feature())
 		identify_cpu_without_cpuid(c);
 
 	/* cyrix could have cpuid enabled via c_identify()*/
-	if (!have_cpuid_p())
+	if (!cpuid_feature())
 		return;
 
 	cpu_detect(c);
@@ -1870,6 +1992,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	/* Filter out anything that depends on CPUID levels we don't have */
 	filter_cpuid_features(c, true);
 
+	/* Check for unmet dependencies based on the CPUID dependency table */
+	check_cpufeature_deps(c);
+
 	/* If the model name is still unset, do table lookup. */
 	if (!c->x86_model_id[0]) {
 		const char *p;
@@ -1938,9 +2063,9 @@ void enable_sep_cpu(void)
 	 */
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
-	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
+	wrmsrq(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1);
+	wrmsrq(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
+	wrmsrq(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32);
 
 	put_cpu();
 }
@@ -1962,9 +2087,15 @@ static __init void identify_boot_cpu(void)
 	lkgs_init();
 }
 
-void identify_secondary_cpu(struct cpuinfo_x86 *c)
+void identify_secondary_cpu(unsigned int cpu)
 {
-	BUG_ON(c == &boot_cpu_data);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
+		*c = boot_cpu_data;
+	c->cpu_index = cpu;
+
 	identify_cpu(c);
 #ifdef CONFIG_X86_32
 	enable_sep_cpu();
@@ -1975,6 +2106,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 		update_gds_msr();
 
 	tsx_ap_init();
+	c->initialized = true;
 }
 
 void print_cpu_info(struct cpuinfo_x86 *c)
@@ -2005,29 +2137,42 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 }
 
 /*
- * clearcpuid= was already parsed in cpu_parse_early_param().  This dummy
- * function prevents it from becoming an environment variable for init.
+ * clearcpuid= and setcpuid= were already parsed in cpu_parse_early_param().
+ * These dummy functions prevent them from becoming an environment variable for
+ * init.
  */
+
 static __init int setup_clearcpuid(char *arg)
 {
 	return 1;
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
-DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
-	.current_task	= &init_task,
-	.preempt_count	= INIT_PREEMPT_COUNT,
-	.top_of_stack	= TOP_OF_INIT_STACK,
-};
-EXPORT_PER_CPU_SYMBOL(pcpu_hot);
-EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
+static __init int setup_setcpuid(char *arg)
+{
+	return 1;
+}
+__setup("setcpuid=", setup_setcpuid);
+
+DEFINE_PER_CPU_CACHE_HOT(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+EXPORT_PER_CPU_SYMBOL(const_current_task);
+
+DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
-		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
+/*
+ * Note: Do not make this dependant on CONFIG_MITIGATION_CALL_DEPTH_TRACKING
+ * so that this space is reserved in the hot cache section even when the
+ * mitigation is disabled.
+ */
+DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
 
-static void wrmsrl_cstar(unsigned long val)
+static void wrmsrq_cstar(unsigned long val)
 {
 	/*
 	 * Intel CPUs do not support 32-bit SYSCALL. Writing to MSR_CSTAR
@@ -2035,37 +2180,37 @@ static void wrmsrl_cstar(unsigned long val)
 	 * guest. Avoid the pointless write on all Intel CPUs.
 	 */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
-		wrmsrl(MSR_CSTAR, val);
+		wrmsrq(MSR_CSTAR, val);
 }
 
 static inline void idt_syscall_init(void)
 {
-	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	wrmsrq(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 	if (ia32_enabled()) {
-		wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+		wrmsrq_cstar((unsigned long)entry_SYSCALL_compat);
 		/*
 		 * This only works on Intel CPUs.
 		 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
 		 * This does not cause SYSENTER to jump to the wrong location, because
 		 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 		 */
-		wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-		wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+		wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+		wrmsrq_safe(MSR_IA32_SYSENTER_ESP,
 			    (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
-		wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+		wrmsrq_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 	} else {
-		wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
-		wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
-		wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-		wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+		wrmsrq_cstar((unsigned long)entry_SYSCALL32_ignore);
+		wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+		wrmsrq_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+		wrmsrq_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
 	}
 
 	/*
 	 * Flags to clear on syscall; clear as much as possible
 	 * to minimize user space-kernel interference.
 	 */
-	wrmsrl(MSR_SYSCALL_MASK,
+	wrmsrq(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_CF|X86_EFLAGS_PF|X86_EFLAGS_AF|
 	       X86_EFLAGS_ZF|X86_EFLAGS_SF|X86_EFLAGS_TF|
 	       X86_EFLAGS_IF|X86_EFLAGS_DF|X86_EFLAGS_OF|
@@ -2089,18 +2234,15 @@ void syscall_init(void)
 	if (!cpu_feature_enabled(X86_FEATURE_FRED))
 		idt_syscall_init();
 }
-
-#else	/* CONFIG_X86_64 */
+#endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
 #ifndef CONFIG_SMP
 EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * Clear all 6 debug registers:
  */
@@ -2137,7 +2279,7 @@ static inline void setup_getcpu(int cpu)
 	struct desc_struct d = { };
 
 	if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID))
-		wrmsr(MSR_TSC_AUX, cpudata, 0);
+		wrmsrq(MSR_TSC_AUX, cpudata);
 
 	/* Store CPU and node number in limit. */
 	d.limit0 = cpudata;
@@ -2252,8 +2394,8 @@ void cpu_init(void)
 		memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
 		syscall_init();
 
-		wrmsrl(MSR_FS_BASE, 0);
-		wrmsrl(MSR_KERNEL_GS_BASE, 0);
+		wrmsrq(MSR_FS_BASE, 0);
+		wrmsrq(MSR_KERNEL_GS_BASE, 0);
 		barrier();
 
 		x2apic_setup();
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1beccefbaff9..bc38b2d56f26 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -33,14 +33,6 @@ struct cpu_dev {
 #endif
 };
 
-struct _tlb_table {
-	unsigned char descriptor;
-	char tlb_type;
-	unsigned int entries;
-	/* unsigned int ways; */
-	char info[128];
-};
-
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
 	__section(".x86_cpu_dev.init") = \
@@ -83,6 +75,15 @@ extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
 void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id);
 void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);
 
+#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
+struct amd_northbridge *amd_init_l3_cache(int index);
+#else
+static inline struct amd_northbridge *amd_init_l3_cache(int index)
+{
+	return NULL;
+}
+#endif
+
 unsigned int aperfmperf_get_khz(int cpu);
 void cpu_select_mitigations(void);
 
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index df838e3bdbe0..46efcbd6afa4 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -28,6 +28,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_PKU,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_MPX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_XGETBV1,			X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_APX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_CMOV,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMX,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMXEXT,			X86_FEATURE_MMX       },
@@ -82,8 +83,12 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_XFD,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
+	{ X86_FEATURE_AMX_FP16,			X86_FEATURE_AMX_TILE  },
+	{ X86_FEATURE_AMX_BF16,			X86_FEATURE_AMX_TILE  },
+	{ X86_FEATURE_AMX_INT8,			X86_FEATURE_AMX_TILE  },
 	{ X86_FEATURE_SHSTK,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_FRED,			X86_FEATURE_LKGS      },
+	{ X86_FEATURE_SPEC_CTRL_SSBD,		X86_FEATURE_SPEC_CTRL },
 	{}
 };
 
@@ -147,3 +152,38 @@ void setup_clear_cpu_cap(unsigned int feature)
 {
 	do_clear_cpu_cap(NULL, feature);
 }
+
+/*
+ * Return the feature "name" if available, otherwise return
+ * the X86_FEATURE_* numerals to make it easier to identify
+ * the feature.
+ */
+static const char *x86_feature_name(unsigned int feature, char *buf)
+{
+	if (x86_cap_flags[feature])
+		return x86_cap_flags[feature];
+
+	snprintf(buf, 16, "%d*32+%2d", feature / 32, feature % 32);
+
+	return buf;
+}
+
+void check_cpufeature_deps(struct cpuinfo_x86 *c)
+{
+	char feature_buf[16], depends_buf[16];
+	const struct cpuid_dep *d;
+
+	for (d = cpuid_deps; d->feature; d++) {
+		if (cpu_has(c, d->feature) && !cpu_has(c, d->depends)) {
+			/*
+			 * Only warn about the first unmet dependency on the
+			 * first CPU where it is encountered to avoid spamming
+			 * the kernel log.
+			 */
+			pr_warn_once("x86 CPU feature dependency check failure: CPU%d has '%s' enabled but '%s' disabled. Kernel might be fine, but no guarantees.\n",
+				     smp_processor_id(),
+				     x86_feature_name(d->feature, feature_buf),
+				     x86_feature_name(d->depends, depends_buf));
+		}
+	}
+}
diff --git a/arch/x86/kernel/cpu/cpuid_0x2_table.c b/arch/x86/kernel/cpu/cpuid_0x2_table.c
new file mode 100644
index 000000000000..89bc8db5e9c6
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpuid_0x2_table.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/sizes.h>
+
+#include <asm/cpuid/types.h>
+
+#include "cpu.h"
+
+#define CACHE_ENTRY(_desc, _type, _size)	\
+	[_desc] = {				\
+		.c_type = (_type),		\
+		.c_size = (_size) / SZ_1K,	\
+	}
+
+#define TLB_ENTRY(_desc, _type, _entries)	\
+	[_desc] = {				\
+		.t_type = (_type),		\
+		.entries = (_entries),		\
+	}
+
+const struct leaf_0x2_table cpuid_0x2_table[256] = {
+	CACHE_ENTRY(0x06, CACHE_L1_INST,	SZ_8K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x08, CACHE_L1_INST,	SZ_16K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x09, CACHE_L1_INST,	SZ_32K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x0a, CACHE_L1_DATA,	SZ_8K	),	/* 2 way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x0c, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x0d, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x0e, CACHE_L1_DATA,	SZ_24K	),	/* 6-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x21, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x22, CACHE_L3,		SZ_512K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x23, CACHE_L3,		SZ_1M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x25, CACHE_L3,		SZ_2M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x29, CACHE_L3,		SZ_4M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x2c, CACHE_L1_DATA,	SZ_32K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x30, CACHE_L1_INST,	SZ_32K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x39, CACHE_L2,		SZ_128K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3a, CACHE_L2,		SZ_192K	),	/* 6-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3b, CACHE_L2,		SZ_128K	),	/* 2-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3c, CACHE_L2,		SZ_256K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3d, CACHE_L2,		SZ_384K	),	/* 6-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3e, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x3f, CACHE_L2,		SZ_256K	),	/* 2-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x41, CACHE_L2,		SZ_128K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x42, CACHE_L2,		SZ_256K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x43, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x44, CACHE_L2,		SZ_1M	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x45, CACHE_L2,		SZ_2M	),	/* 4-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x46, CACHE_L3,		SZ_4M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x47, CACHE_L3,		SZ_8M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x48, CACHE_L2,		SZ_3M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x49, CACHE_L3,		SZ_4M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4a, CACHE_L3,		SZ_6M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4b, CACHE_L3,		SZ_8M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4c, CACHE_L3,		SZ_12M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4d, CACHE_L3,		SZ_16M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x4e, CACHE_L2,		SZ_6M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x60, CACHE_L1_DATA,	SZ_16K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x66, CACHE_L1_DATA,	SZ_8K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x67, CACHE_L1_DATA,	SZ_16K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x68, CACHE_L1_DATA,	SZ_32K	),	/* 4-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x78, CACHE_L2,		SZ_1M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x79, CACHE_L2,		SZ_128K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7a, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7b, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7c, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, sectored cache, 64 byte line size */
+	CACHE_ENTRY(0x7d, CACHE_L2,		SZ_2M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x7f, CACHE_L2,		SZ_512K	),	/* 2-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x80, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x82, CACHE_L2,		SZ_256K	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x83, CACHE_L2,		SZ_512K	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x84, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x85, CACHE_L2,		SZ_2M	),	/* 8-way set assoc, 32 byte line size */
+	CACHE_ENTRY(0x86, CACHE_L2,		SZ_512K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0x87, CACHE_L2,		SZ_1M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd0, CACHE_L3,		SZ_512K	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd1, CACHE_L3,		SZ_1M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd2, CACHE_L3,		SZ_2M	),	/* 4-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd6, CACHE_L3,		SZ_1M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd7, CACHE_L3,		SZ_2M	),	/* 8-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xd8, CACHE_L3,		SZ_4M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xdc, CACHE_L3,		SZ_2M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xdd, CACHE_L3,		SZ_4M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xde, CACHE_L3,		SZ_8M	),	/* 12-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe2, CACHE_L3,		SZ_2M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe3, CACHE_L3,		SZ_4M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xe4, CACHE_L3,		SZ_8M	),	/* 16-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xea, CACHE_L3,		SZ_12M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xeb, CACHE_L3,		SZ_18M	),	/* 24-way set assoc, 64 byte line size */
+	CACHE_ENTRY(0xec, CACHE_L3,		SZ_24M	),	/* 24-way set assoc, 64 byte line size */
+
+	TLB_ENTRY(  0x01, TLB_INST_4K,		32	),	/* TLB_INST 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0x02, TLB_INST_4M,		2	),	/* TLB_INST 4 MByte pages, full associative */
+	TLB_ENTRY(  0x03, TLB_DATA_4K,		64	),	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0x04, TLB_DATA_4M,		8	),	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x05, TLB_DATA_4M,		32	),	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x0b, TLB_INST_4M,		4	),	/* TLB_INST 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x4f, TLB_INST_4K,		32	),	/* TLB_INST 4 KByte pages */
+	TLB_ENTRY(  0x50, TLB_INST_ALL,		64	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x51, TLB_INST_ALL,		128	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x52, TLB_INST_ALL,		256	),	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	TLB_ENTRY(  0x55, TLB_INST_2M_4M,	7	),	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	TLB_ENTRY(  0x56, TLB_DATA0_4M,		16	),	/* TLB_DATA0 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x57, TLB_DATA0_4K,		16	),	/* TLB_DATA0 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0x59, TLB_DATA0_4K,		16	),	/* TLB_DATA0 4 KByte pages, fully associative */
+	TLB_ENTRY(  0x5a, TLB_DATA0_2M_4M,	32	),	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+	TLB_ENTRY(  0x5b, TLB_DATA_4K_4M,	64	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x5c, TLB_DATA_4K_4M,	128	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x5d, TLB_DATA_4K_4M,	256	),	/* TLB_DATA 4 KByte and 4 MByte pages */
+	TLB_ENTRY(  0x61, TLB_INST_4K,		48	),	/* TLB_INST 4 KByte pages, full associative */
+	TLB_ENTRY(  0x63, TLB_DATA_1G_2M_4M,	4	),	/* TLB_DATA 1 GByte pages, 4-way set associative
+								 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+	TLB_ENTRY(  0x6b, TLB_DATA_4K,		256	),	/* TLB_DATA 4 KByte pages, 8-way associative */
+	TLB_ENTRY(  0x6c, TLB_DATA_2M_4M,	128	),	/* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+	TLB_ENTRY(  0x6d, TLB_DATA_1G,		16	),	/* TLB_DATA 1 GByte pages, fully associative */
+	TLB_ENTRY(  0x76, TLB_INST_2M_4M,	8	),	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	TLB_ENTRY(  0xb0, TLB_INST_4K,		128	),	/* TLB_INST 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb1, TLB_INST_2M_4M,	4	),	/* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+	TLB_ENTRY(  0xb2, TLB_INST_4K,		64	),	/* TLB_INST 4KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb3, TLB_DATA_4K,		128	),	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	TLB_ENTRY(  0xb4, TLB_DATA_4K,		256	),	/* TLB_DATA 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0xb5, TLB_INST_4K,		64	),	/* TLB_INST 4 KByte pages, 8-way set associative */
+	TLB_ENTRY(  0xb6, TLB_INST_4K,		128	),	/* TLB_INST 4 KByte pages, 8-way set associative */
+	TLB_ENTRY(  0xba, TLB_DATA_4K,		64	),	/* TLB_DATA 4 KByte pages, 4-way associative */
+	TLB_ENTRY(  0xc0, TLB_DATA_4K_4M,	8	),	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+	TLB_ENTRY(  0xc1, STLB_4K_2M,		1024	),	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
+	TLB_ENTRY(  0xc2, TLB_DATA_2M_4M,	16	),	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+	TLB_ENTRY(  0xca, STLB_4K,		512	),	/* STLB 4 KByte pages, 4-way associative */
+};
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1..dfec2c61e354 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index cacfd3f6abef..1976fef2dfe5 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -16,8 +16,8 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	if (!c->initialized)
 		return 0;
 
-	seq_printf(m, "initial_apicid:      %x\n", c->topo.initial_apicid);
-	seq_printf(m, "apicid:              %x\n", c->topo.apicid);
+	seq_printf(m, "initial_apicid:	    0x%x\n", c->topo.initial_apicid);
+	seq_printf(m, "apicid:		    0x%x\n", c->topo.apicid);
 	seq_printf(m, "pkg_id:              %u\n", c->topo.pkg_id);
 	seq_printf(m, "die_id:              %u\n", c->topo.die_id);
 	seq_printf(m, "cu_id:               %u\n", c->topo.cu_id);
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 4a4118784c13..d69757246bde 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -4,6 +4,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/msr-index.h>
+#include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/vmx.h>
 
@@ -118,7 +119,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 	bool enable_vmx;
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
+	if (rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr)) {
 		clear_cpu_cap(c, X86_FEATURE_VMX);
 		clear_cpu_cap(c, X86_FEATURE_SGX);
 		return;
@@ -165,7 +166,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
 			msr |= FEAT_CTL_SGX_LC_ENABLED;
 	}
 
-	wrmsrl(MSR_IA32_FEAT_CTL, msr);
+	wrmsrq(MSR_IA32_FEAT_CTL, msr);
 
 update_caps:
 	set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index c5191b06f9f2..2154f12766fb 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -15,6 +15,7 @@
 #include <asm/cacheinfo.h>
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -96,7 +97,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 		u64 val;
 
-		rdmsrl(MSR_K7_HWCR, val);
+		rdmsrq(MSR_K7_HWCR, val);
 		if (!(val & BIT(24)))
 			pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
 	}
@@ -110,7 +111,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 		 * Try to cache the base value so further operations can
 		 * avoid RMW. If that faults, do not enable SSBD.
 		 */
-		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+		if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
 			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
 			setup_force_cpu_cap(X86_FEATURE_SSBD);
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
@@ -194,7 +195,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
 	init_hygon_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_SVM)) {
-		rdmsrl(MSR_VM_CR, vm_cr);
+		rdmsrq(MSR_VM_CR, vm_cr);
 		if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
 			pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
 			clear_cpu_cap(c, X86_FEATURE_SVM);
@@ -240,26 +241,26 @@ static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-		tlb_lli_2m[ENTRIES] = eax & 0xff;
+		tlb_lli_2m = eax & 0xff;
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev hygon_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc3..076eaa41b8c8 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,40 +1,33 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/pgtable.h>
 
-#include <linux/string.h>
 #include <linux/bitops.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/thread_info.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/minmax.h>
+#include <linux/smp.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_64
+#include <linux/topology.h>
+#endif
 
-#include <asm/cpufeature.h>
-#include <asm/msr.h>
 #include <asm/bugs.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu.h>
+#include <asm/cpuid/api.h>
+#include <asm/hwcap2.h>
 #include <asm/intel-family.h>
 #include <asm/microcode.h>
-#include <asm/hwcap2.h>
-#include <asm/elf.h>
-#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
+#include <asm/resctrl.h>
 #include <asm/thermal.h>
-
-#ifdef CONFIG_X86_64
-#include <linux/topology.h>
-#endif
+#include <asm/uaccess.h>
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#endif
-
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
@@ -166,7 +159,7 @@ static void detect_tme_early(struct cpuinfo_x86 *c)
 	u64 tme_activate;
 	int keyid_bits;
 
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+	rdmsrq(MSR_IA32_TME_ACTIVATE, tme_activate);
 
 	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
 		pr_info_once("x86/tme: not enabled by BIOS\n");
@@ -195,7 +188,7 @@ void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return;
 
-	if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd))
+	if (c->x86_vfm < INTEL_PENTIUM_M_DOTHAN)
 		return;
 
 	/*
@@ -210,10 +203,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
 
-	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
-		(c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-
 	if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
 		c->microcode = intel_get_microcode_revision();
 
@@ -256,8 +245,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 #endif
 
 	/* CPUID workaround for 0F33/0F34 CPU */
-	if (c->x86 == 0xF && c->x86_model == 0x3
-	    && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
+	if (c->x86_vfm == INTEL_P4_PRESCOTT &&
+	    (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
 		c->x86_phys_bits = 36;
 
 	/*
@@ -266,10 +255,16 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 *
 	 * It is also reliable across cores and sockets. (but not across
 	 * cabinets - we turn it off in that case explicitly.)
+	 *
+	 * Use a model-specific check for some older CPUs that have invariant
+	 * TSC but may not report it architecturally via 8000_0007.
 	 */
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_WILLAMETTE) ||
+		   (c->x86_vfm >= INTEL_CORE_YONAH  && c->x86_vfm <= INTEL_IVYBRIDGE)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
@@ -298,12 +293,19 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		clear_cpu_cap(c, X86_FEATURE_PAT);
 
 	/*
-	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
-	 * clear the fast string and enhanced fast string CPU capabilities.
+	 * Modern CPUs are generally expected to have a sane fast string
+	 * implementation. However, BIOSes typically have a knob to tweak
+	 * the architectural MISC_ENABLE.FAST_STRING enable bit.
+	 *
+	 * Adhere to the preference and program the Linux-defined fast
+	 * string flag and enhanced fast string capabilities accordingly.
 	 */
-	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+	if (c->x86_vfm >= INTEL_PENTIUM_M_DOTHAN) {
+		rdmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
+		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
+			/* X86_FEATURE_ERMS is set based on CPUID */
+			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+		} else {
 			pr_info("Disabled fast string operations\n");
 			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
@@ -350,9 +352,7 @@ static void bsp_init_intel(struct cpuinfo_x86 *c)
 int ppro_with_ram_bug(void)
 {
 	/* Uses data from early_cpu_detect now */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model == 1 &&
+	if (boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO &&
 	    boot_cpu_data.x86_stepping < 8) {
 		pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n");
 		return 1;
@@ -369,9 +369,8 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
 	/*
 	 * Mask B, Pentium, but not Pentium MMX
 	 */
-	if (c->x86 == 5 &&
-	    c->x86_stepping >= 1 && c->x86_stepping <= 4 &&
-	    c->x86_model <= 3) {
+	if (c->x86_vfm >= INTEL_FAM5_START && c->x86_vfm < INTEL_PENTIUM_MMX &&
+	    c->x86_stepping >= 1 && c->x86_stepping <= 4) {
 		/*
 		 * Remember we have B step Pentia with bugs
 		 */
@@ -398,7 +397,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * The Quark is also family 5, but does not have the same bug.
 	 */
 	clear_cpu_bug(c, X86_BUG_F00F);
-	if (c->x86 == 5 && c->x86_model < 9) {
+	if (c->x86_vfm >= INTEL_FAM5_START && c->x86_vfm < INTEL_QUARK_X1000) {
 		static int f00f_workaround_enabled;
 
 		set_cpu_bug(c, X86_BUG_F00F);
@@ -413,7 +412,8 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
 	 * model 3 mask 3
 	 */
-	if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633)
+	if ((c->x86_vfm == INTEL_PENTIUM_II_KLAMATH && c->x86_stepping < 3) ||
+	    c->x86_vfm < INTEL_PENTIUM_II_KLAMATH)
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
@@ -431,7 +431,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * P4 Xeon erratum 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
-	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) {
+	if (c->x86_vfm == INTEL_P4_WILLAMETTE && c->x86_stepping == 1) {
 		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
 				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) {
 			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
@@ -445,27 +445,20 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * integrated APIC (see 11AP erratum in "Pentium Processor
 	 * Specification Update").
 	 */
-	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+	if (boot_cpu_has(X86_FEATURE_APIC) && c->x86_vfm == INTEL_PENTIUM_75 &&
 	    (c->x86_stepping < 0x6 || c->x86_stepping == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
-
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	/*
-	 * Set up the preferred alignment for movsl bulk memory moves
+	 * MOVSL bulk memory moves can be slow when source and dest are not
+	 * both 8-byte aligned. PII/PIII only like MOVSL with 8-byte alignment.
+	 *
+	 * Set the preferred alignment for Pentium Pro and newer processors, as
+	 * it has only been tested on these.
 	 */
-	switch (c->x86) {
-	case 4:		/* 486: untested */
-		break;
-	case 5:		/* Old Pentia: untested */
-		break;
-	case 6:		/* PII/PIII only like movsl with 8-byte alignment */
-		movsl_mask.mask = 7;
-		break;
-	case 15:	/* P4 is OK down to 8-byte alignment */
+	if (c->x86_vfm >= INTEL_PENTIUM_PRO)
 		movsl_mask.mask = 7;
-		break;
-	}
 #endif
 
 	intel_smp_check(c);
@@ -497,7 +490,7 @@ static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
 
-	if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+	if (!rdmsrq_safe(MSR_PLATFORM_INFO, &msr)) {
 		if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
 			set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
 	}
@@ -507,7 +500,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 {
 	u64 msr;
 
-	if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+	if (rdmsrq_safe(MSR_MISC_FEATURES_ENABLES, &msr))
 		return;
 
 	/* Clear all MISC features */
@@ -518,9 +511,28 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 	probe_xeon_phi_r3mwait(c);
 
 	msr = this_cpu_read(msr_misc_features_shadow);
-	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+	wrmsrq(MSR_MISC_FEATURES_ENABLES, msr);
 }
 
+/*
+ * This is a list of Intel CPUs that are known to suffer from downclocking when
+ * ZMM registers (512-bit vectors) are used.  On these CPUs, when the kernel
+ * executes SIMD-optimized code such as cryptography functions or CRCs, it
+ * should prefer 256-bit (YMM) code to 512-bit (ZMM) code.
+ */
+static const struct x86_cpu_id zmm_exclusion_list[] = {
+	X86_MATCH_VFM(INTEL_SKYLAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_X,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_D,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_L,		0),
+	X86_MATCH_VFM(INTEL_ICELAKE_NNPI,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	0),
+	X86_MATCH_VFM(INTEL_TIGERLAKE,		0),
+	/* Allow Rocket Lake and later, and Sapphire Rapids and later. */
+	{},
+};
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	early_init_intel(c);
@@ -563,8 +575,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 #else
 	/*
 	 * Names for the Pentium II/Celeron processors
@@ -601,6 +611,9 @@ static void init_intel(struct cpuinfo_x86 *c)
 	}
 #endif
 
+	if (x86_match_cpu(zmm_exclusion_list))
+		set_cpu_cap(c, X86_FEATURE_PREFER_YMM);
+
 	/* Work around errata */
 	srat_detect_node(c);
 
@@ -622,191 +635,90 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 * to determine which, so we use a boottime override
 	 * for the 512kb model, and assume 256 otherwise.
 	 */
-	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
+	if (c->x86_vfm == INTEL_PENTIUM_III_TUALATIN && size == 0)
 		size = 256;
 
 	/*
 	 * Intel Quark SoC X1000 contains a 4-way set associative
 	 * 16K cache with a 16 byte cache line and 256 lines per tag
 	 */
-	if ((c->x86 == 5) && (c->x86_model == 9))
+	if (c->x86_vfm == INTEL_QUARK_X1000)
 		size = 16;
 	return size;
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
-
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
-
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
-
-#define TLB_DATA_1G	0x16
-
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
-
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
-
-static const struct _tlb_table intel_tlb_table[] = {
-	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
-	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
-	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages" },
-	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
-	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
-	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
-	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
-	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
-	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
-	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
-	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
-	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
-	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
-	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
-	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
-	{ 0xc2, TLB_DATA_2M_4M,		16,	" TLB_DATA 2 MByte/4MByte pages, 4-way associative" },
-	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
-	{ 0x00, 0, 0 }
-};
-
-static void intel_tlb_lookup(const unsigned char desc)
+static void intel_tlb_lookup(const struct leaf_0x2_table *desc)
 {
-	unsigned char k;
-	if (desc == 0)
-		return;
+	short entries = desc->entries;
 
-	/* look up this descriptor in the table */
-	for (k = 0; intel_tlb_table[k].descriptor != desc &&
-	     intel_tlb_table[k].descriptor != 0; k++)
-		;
-
-	if (intel_tlb_table[k].tlb_type == 0)
-		return;
-
-	switch (intel_tlb_table[k].tlb_type) {
+	switch (desc->t_type) {
 	case STLB_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case STLB_4K_2M:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_INST_ALL:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
 		break;
 	case TLB_INST_4M:
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_2M_4M:
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_DATA_4K:
 	case TLB_DATA0_4K:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case TLB_DATA_4M:
 	case TLB_DATA0_4M:
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_2M_4M:
 	case TLB_DATA0_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_4K_4M:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
+	case TLB_DATA_1G_2M_4M:
+		tlb_lld_2m = max(tlb_lld_2m, TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_4m = max(tlb_lld_4m, TLB_0x63_2M_4M_ENTRIES);
+		fallthrough;
 	case TLB_DATA_1G:
-		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_1g = max(tlb_lld_1g, entries);
 		break;
 	}
 }
 
 static void intel_detect_tlb(struct cpuinfo_x86 *c)
 {
-	int i, j, n;
-	unsigned int regs[4];
-	unsigned char *desc = (unsigned char *)regs;
+	const struct leaf_0x2_table *desc;
+	union leaf_0x2_regs regs;
+	u8 *ptr;
 
 	if (c->cpuid_level < 2)
 		return;
 
-	/* Number of times to iterate */
-	n = cpuid_eax(2) & 0xFF;
-
-	for (i = 0 ; i < n ; i++) {
-		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
-
-		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
-			if (regs[j] & (1 << 31))
-				regs[j] = 0;
-
-		/* Byte 0 is level count, not a descriptor */
-		for (j = 1 ; j < 16 ; j++)
-			intel_tlb_lookup(desc[j]);
-	}
+	cpuid_leaf_0x2(&regs);
+	for_each_cpuid_0x2_desc(regs, ptr, desc)
+		intel_tlb_lookup(desc);
 }
 
 static const struct cpu_dev intel_cpu_dev = {
@@ -873,34 +785,3 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
-
-#define X86_HYBRID_CPU_TYPE_ID_SHIFT	24
-
-/**
- * get_this_hybrid_cpu_type() - Get the type of this hybrid CPU
- *
- * Returns the CPU type [31:24] (i.e., Atom or Core) of a CPU in
- * a hybrid processor. If the processor is not hybrid, returns 0.
- */
-u8 get_this_hybrid_cpu_type(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
-}
-
-/**
- * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
- *
- * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
- * If the processor is not hybrid, returns 0.
- */
-u32 get_this_hybrid_cpu_native_id(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) &
-	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
-}
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 30b1d63b97f3..bc7671f920a7 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -79,7 +79,7 @@ static int intel_epb_save(void)
 {
 	u64 epb;
 
-	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
 	/*
 	 * Ensure that saved_epb will always be nonzero after this write even if
 	 * the EPB value read from the MSR is 0.
@@ -94,7 +94,7 @@ static void intel_epb_restore(void)
 	u64 val = this_cpu_read(saved_epb);
 	u64 epb;
 
-	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
 	if (val) {
 		val &= EPB_MASK;
 	} else {
@@ -111,7 +111,7 @@ static void intel_epb_restore(void)
 			pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
 		}
 	}
-	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+	wrmsrq(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
 }
 
 static struct syscore_ops intel_epb_syscore_ops = {
@@ -135,7 +135,7 @@ static ssize_t energy_perf_bias_show(struct device *dev,
 	u64 epb;
 	int ret;
 
-	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
 	if (ret < 0)
 		return ret;
 
@@ -157,11 +157,11 @@ static ssize_t energy_perf_bias_store(struct device *dev,
 	else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
 		return -EINVAL;
 
-	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
 	if (ret < 0)
 		return ret;
 
-	ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+	ret = wrmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
 			    (epb & ~EPB_MASK) | val);
 	if (ret < 0)
 		return ret;
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 4f3c65429f82..6af1e8baeb0f 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -6,6 +6,34 @@
 #include <linux/slab.h>
 
 /**
+ * x86_match_vendor_cpu_type - helper function to match the hardware defined
+ *                             cpu-type for a single entry in the x86_cpu_id
+ *                             table. Note, this function does not match the
+ *                             generic cpu-types TOPO_CPU_TYPE_EFFICIENCY and
+ *                             TOPO_CPU_TYPE_PERFORMANCE.
+ * @c: Pointer to the cpuinfo_x86 structure of the CPU to match.
+ * @m: Pointer to the x86_cpu_id entry to match against.
+ *
+ * Return: true if the cpu-type matches, false otherwise.
+ */
+static bool x86_match_vendor_cpu_type(struct cpuinfo_x86 *c, const struct x86_cpu_id *m)
+{
+	if (m->type == X86_CPU_TYPE_ANY)
+		return true;
+
+	/* Hybrid CPUs are special, they are assumed to match all cpu-types */
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		return true;
+
+	if (c->x86_vendor == X86_VENDOR_INTEL)
+		return m->type == c->topo.intel_type;
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		return m->type == c->topo.amd_type;
+
+	return false;
+}
+
+/**
  * x86_match_cpu - match current CPU against an array of x86_cpu_ids
  * @match: Pointer to array of x86_cpu_ids. Last entry terminated with
  *         {}.
@@ -50,6 +78,8 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
+		if (!x86_match_vendor_cpu_type(c, m))
+			continue;
 		return m;
 	}
 	return NULL;
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 1075a90141da..9d852c3b2cb5 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -662,12 +662,12 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 		return;
 	}
 
-	rdmsrl(MSR_K7_HWCR, hwcr);
+	rdmsrq(MSR_K7_HWCR, hwcr);
 
 	/* McStatusWrEn has to be set */
 	need_toggle = !(hwcr & BIT(18));
 	if (need_toggle)
-		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+		wrmsrq(MSR_K7_HWCR, hwcr | BIT(18));
 
 	/* Clear CntP bit safely */
 	for (i = 0; i < num_msrs; i++)
@@ -675,7 +675,7 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 
 	/* restore old settings */
 	if (need_toggle)
-		wrmsrl(MSR_K7_HWCR, hwcr);
+		wrmsrq(MSR_K7_HWCR, hwcr);
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
@@ -805,12 +805,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 	}
 
 	if (mce_flags.smca) {
-		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
+		rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
 
 		if (m->status & MCI_STATUS_SYNDV) {
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
+			rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
 		}
 	}
 
@@ -834,16 +834,16 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc)
 {
 	u64 status, addr = 0;
 
-	rdmsrl(msr_stat, status);
+	rdmsrq(msr_stat, status);
 	if (!(status & MCI_STATUS_VAL))
 		return false;
 
 	if (status & MCI_STATUS_ADDRV)
-		rdmsrl(msr_addr, addr);
+		rdmsrq(msr_addr, addr);
 
 	__log_error(bank, status, addr, misc);
 
-	wrmsrl(msr_stat, 0);
+	wrmsrq(msr_stat, 0);
 
 	return status & MCI_STATUS_DEFERRED;
 }
@@ -862,7 +862,7 @@ static bool _log_error_deferred(unsigned int bank, u32 misc)
 		return true;
 
 	/* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */
-	wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
+	wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
 	return true;
 }
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 0dc00c9894c7..e9b3c5d4a52e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -121,7 +121,7 @@ void mce_prep_record_common(struct mce *m)
 {
 	m->cpuid	= cpuid_eax(1);
 	m->cpuvendor	= boot_cpu_data.x86_vendor;
-	m->mcgcap	= __rdmsr(MSR_IA32_MCG_CAP);
+	m->mcgcap	= native_rdmsrq(MSR_IA32_MCG_CAP);
 	/* need the internal __ version to avoid deadlocks */
 	m->time		= __ktime_get_real_seconds();
 }
@@ -388,9 +388,9 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 }
 
 /* MSR access wrappers used for error injection */
-noinstr u64 mce_rdmsrl(u32 msr)
+noinstr u64 mce_rdmsrq(u32 msr)
 {
-	DECLARE_ARGS(val, low, high);
+	EAX_EDX_DECLARE_ARGS(val, low, high);
 
 	if (__this_cpu_read(injectm.finished)) {
 		int offset;
@@ -423,7 +423,7 @@ noinstr u64 mce_rdmsrl(u32 msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static noinstr void mce_wrmsrl(u32 msr, u64 v)
+static noinstr void mce_wrmsrq(u32 msr, u64 v)
 {
 	u32 low, high;
 
@@ -444,7 +444,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
 	low  = (u32)v;
 	high = (u32)(v >> 32);
 
-	/* See comment in mce_rdmsrl() */
+	/* See comment in mce_rdmsrq() */
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
@@ -468,7 +468,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 	instrumentation_end();
 
 	m = &err->m;
-	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+	m->mcgstatus = mce_rdmsrq(MSR_IA32_MCG_STATUS);
 	if (regs) {
 		/*
 		 * Get the address of the instruction at the time of
@@ -488,7 +488,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
 		}
 		/* Use accurate RIP reporting if available. */
 		if (mca_cfg.rip_msr)
-			m->ip = mce_rdmsrl(mca_cfg.rip_msr);
+			m->ip = mce_rdmsrq(mca_cfg.rip_msr);
 	}
 }
 
@@ -584,6 +584,28 @@ bool mce_is_correctable(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_correctable);
 
+/*
+ * Notify the user(s) about new machine check events.
+ * Can be called from interrupt context, but not from machine check/NMI
+ * context.
+ */
+static bool mce_notify_irq(void)
+{
+	/* Not more than two messages every minute */
+	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
+
+	if (test_and_clear_bit(0, &mce_need_notify)) {
+		mce_work_trigger();
+
+		if (__ratelimit(&ratelimit))
+			pr_info(HW_ERR "Machine check events logged\n");
+
+		return true;
+	}
+
+	return false;
+}
+
 static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
 			      void *data)
 {
@@ -662,10 +684,10 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 	struct mce *m = &err->m;
 
 	if (m->status & MCI_STATUS_MISCV)
-		m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
+		m->misc = mce_rdmsrq(mca_msr_reg(i, MCA_MISC));
 
 	if (m->status & MCI_STATUS_ADDRV) {
-		m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR));
+		m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
 
 		/*
 		 * Mask the reported address by the reported granularity.
@@ -680,12 +702,12 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
 	}
 
 	if (mce_flags.smca) {
-		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+		m->ipid = mce_rdmsrq(MSR_AMD64_SMCA_MCx_IPID(i));
 
 		if (m->status & MCI_STATUS_SYNDV) {
-			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
-			err->vendor.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i));
-			err->vendor.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i));
+			m->synd = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND(i));
+			err->vendor.amd.synd1 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(i));
+			err->vendor.amd.synd2 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(i));
 		}
 	}
 }
@@ -731,7 +753,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		m->bank = i;
 
 		barrier();
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 
 		/*
 		 * Update storm tracking here, before checking for the
@@ -807,7 +829,7 @@ clear_it:
 		/*
 		 * Clear state for this bank.
 		 */
-		mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 
 	/*
@@ -865,8 +887,8 @@ quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
  */
 static noinstr bool quirk_skylake_repmov(void)
 {
-	u64 mcgstatus   = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-	u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE);
+	u64 mcgstatus   = mce_rdmsrq(MSR_IA32_MCG_STATUS);
+	u64 misc_enable = mce_rdmsrq(MSR_IA32_MISC_ENABLE);
 	u64 mc1_status;
 
 	/*
@@ -877,7 +899,7 @@ static noinstr bool quirk_skylake_repmov(void)
 	    !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING))
 		return false;
 
-	mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1));
+	mc1_status = mce_rdmsrq(MSR_IA32_MCx_STATUS(1));
 
 	/* Check for a software-recoverable data fetch error. */
 	if ((mc1_status &
@@ -888,8 +910,8 @@ static noinstr bool quirk_skylake_repmov(void)
 	      MCI_STATUS_ADDRV | MCI_STATUS_MISCV |
 	      MCI_STATUS_AR | MCI_STATUS_S)) {
 		misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-		mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0);
+		mce_wrmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
+		mce_wrmsrq(MSR_IA32_MCx_STATUS(1), 0);
 
 		instrumentation_begin();
 		pr_err_once("Erratum detected, disable fast string copy instructions.\n");
@@ -933,7 +955,7 @@ static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, un
 	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1252,7 +1274,7 @@ static __always_inline void mce_clear_state(unsigned long *toclear)
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		if (arch_test_bit(i, toclear))
-			mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+			mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1276,7 +1298,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
-		mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS);
+		mcgstatus = native_rdmsrq(MSR_IA32_MCG_STATUS);
 
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
 			if (mcgstatus & MCG_STATUS_LMCES)
@@ -1284,7 +1306,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 		}
 
 		if (mcgstatus & MCG_STATUS_RIPV) {
-			__wrmsr(MSR_IA32_MCG_STATUS, 0, 0);
+			native_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 			return true;
 		}
 	}
@@ -1313,7 +1335,7 @@ __mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs,
 		m->addr = 0;
 		m->bank = i;
 
-		m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+		m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
 		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
@@ -1671,7 +1693,7 @@ out:
 	instrumentation_end();
 
 clear:
-	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+	mce_wrmsrq(MSR_IA32_MCG_STATUS, 0);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1764,36 +1786,14 @@ void mce_timer_kick(bool storm)
 		__this_cpu_write(mce_next_interval, check_interval * HZ);
 }
 
-/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+/* Must not be called in IRQ context where timer_delete_sync() can deadlock */
 static void mce_timer_delete_all(void)
 {
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		del_timer_sync(&per_cpu(mce_timer, cpu));
-}
-
-/*
- * Notify the user(s) about new machine check events.
- * Can be called from interrupt context, but not from machine check/NMI
- * context.
- */
-bool mce_notify_irq(void)
-{
-	/* Not more than two messages every minute */
-	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
-
-	if (test_and_clear_bit(0, &mce_need_notify)) {
-		mce_work_trigger();
-
-		if (__ratelimit(&ratelimit))
-			pr_info(HW_ERR "Machine check events logged\n");
-
-		return true;
-	}
-	return false;
+		timer_delete_sync(&per_cpu(mce_timer, cpu));
 }
-EXPORT_SYMBOL_GPL(mce_notify_irq);
 
 static void __mcheck_cpu_mce_banks_init(void)
 {
@@ -1822,7 +1822,7 @@ static void __mcheck_cpu_cap_init(void)
 	u64 cap;
 	u8 b;
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
 
@@ -1863,7 +1863,7 @@ static void __mcheck_cpu_init_generic(void)
 
 	cr4_set_bits(X86_CR4_MCE);
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 	if (cap & MCG_CTL_P)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 }
@@ -1878,8 +1878,8 @@ static void __mcheck_cpu_init_clear_banks(void)
 
 		if (!b->init)
 			continue;
-		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+		wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+		wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
 	}
 }
 
@@ -1905,7 +1905,7 @@ static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
-		rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
+		rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
 		b->init = !!msrval;
 	}
 }
@@ -2436,7 +2436,7 @@ static void mce_disable_error_reporting(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), 0);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), 0);
 	}
 	return;
 }
@@ -2786,7 +2786,7 @@ static void mce_reenable_cpu(void)
 		struct mce_bank *b = &mce_banks[i];
 
 		if (b->init)
-			wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+			wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
 	}
 }
 
@@ -2820,7 +2820,7 @@ static int mce_cpu_pre_down(unsigned int cpu)
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
 
 	mce_disable_cpu();
-	del_timer_sync(t);
+	timer_delete_sync(t);
 	mce_threshold_remove_device(cpu);
 	mce_device_remove(cpu);
 	return 0;
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 313fe682db33..d02c4f556cd0 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -24,10 +24,11 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>
 
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/apic.h>
 #include <asm/irq_vectors.h>
 #include <asm/mce.h>
+#include <asm/msr.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 
@@ -229,7 +230,6 @@ static int raise_local(void)
 	} else if (m->status) {
 		pr_info("Starting machine check poll CPU %d\n", cpu);
 		raise_poll(m);
-		mce_notify_irq();
 		pr_info("Machine check poll done on CPU %d\n", cpu);
 	} else
 		m->finished = 0;
@@ -476,27 +476,27 @@ static void prepare_msrs(void *info)
 	struct mce m = *(struct mce *)info;
 	u8 b = m.bank;
 
-	wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
+	wrmsrq(MSR_IA32_MCG_STATUS, m.mcgstatus);
 
 	if (boot_cpu_has(X86_FEATURE_SMCA)) {
 		if (m.inject_flags == DFR_INT_INJ) {
-			wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
-			wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
+			wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
+			wrmsrq(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
 		} else {
-			wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
-			wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
+			wrmsrq(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
+			wrmsrq(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
 		}
 
-		wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
+		wrmsrq(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
 
 		if (m.misc)
-			wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
+			wrmsrq(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
 	} else {
-		wrmsrl(MSR_IA32_MCx_STATUS(b), m.status);
-		wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr);
+		wrmsrq(MSR_IA32_MCx_STATUS(b), m.status);
+		wrmsrq(MSR_IA32_MCx_ADDR(b), m.addr);
 
 		if (m.misc)
-			wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
+			wrmsrq(MSR_IA32_MCx_MISC(b), m.misc);
 	}
 }
 
@@ -590,7 +590,7 @@ static int inj_bank_set(void *data, u64 val)
 	u64 cap;
 
 	/* Get bank count on target CPU so we can handle non-uniform values. */
-	rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+	rdmsrq_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
 	n_banks = cap & MCG_BANKCNT_MASK;
 
 	if (val >= n_banks) {
@@ -614,7 +614,7 @@ static int inj_bank_set(void *data, u64 val)
 	if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
 		u64 ipid;
 
-		if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
+		if (rdmsrq_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
 			pr_err("Error reading IPID on CPU%d\n", m->extcpu);
 			return -EINVAL;
 		}
@@ -742,15 +742,15 @@ static void check_hw_inj_possible(void)
 		u64 status = MCI_STATUS_VAL, ipid;
 
 		/* Check whether bank is populated */
-		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+		rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
 		if (!ipid)
 			continue;
 
 		toggle_hw_mce_inject(cpu, true);
 
-		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
-		rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
-		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0);
+		wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), status);
+		rdmsrq_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+		wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), 0);
 
 		if (!status) {
 			hw_injection_possible = false;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f863df0ff42c..efcf21e9552e 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -94,7 +94,7 @@ static bool cmci_supported(int *banks)
 	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return false;
 
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	rdmsrq(MSR_IA32_MCG_CAP, cap);
 	*banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK);
 	return !!(cap & MCG_CMCI_P);
 }
@@ -106,7 +106,7 @@ static bool lmce_supported(void)
 	if (mca_cfg.lmce_disabled)
 		return false;
 
-	rdmsrl(MSR_IA32_MCG_CAP, tmp);
+	rdmsrq(MSR_IA32_MCG_CAP, tmp);
 
 	/*
 	 * LMCE depends on recovery support in the processor. Hence both
@@ -123,7 +123,7 @@ static bool lmce_supported(void)
 	 * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally
 	 * locks the MSR in the event that it wasn't already locked by BIOS.
 	 */
-	rdmsrl(MSR_IA32_FEAT_CTL, tmp);
+	rdmsrq(MSR_IA32_FEAT_CTL, tmp);
 	if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED)))
 		return false;
 
@@ -141,9 +141,9 @@ static void cmci_set_threshold(int bank, int thresh)
 	u64 val;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val | thresh);
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
@@ -184,7 +184,7 @@ static bool cmci_skip_bank(int bank, u64 *val)
 	if (test_bit(bank, mce_banks_ce_disabled))
 		return true;
 
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), *val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), *val);
 
 	/* Already owned by someone else? */
 	if (*val & MCI_CTL2_CMCI_EN) {
@@ -232,8 +232,8 @@ static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_w
 	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
 
 	val |= MCI_CTL2_CMCI_EN;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 
 	/* If the enable bit did not stick, this bank should be polled. */
 	if (!(val & MCI_CTL2_CMCI_EN)) {
@@ -324,9 +324,9 @@ static void __cmci_disable_bank(int bank)
 
 	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
 		return;
-	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_EN;
-	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
 	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
 
 	if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
@@ -430,10 +430,10 @@ void intel_init_lmce(void)
 	if (!lmce_supported())
 		return;
 
-	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
 
 	if (!(val & MCG_EXT_CTL_LMCE_EN))
-		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+		wrmsrq(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
 }
 
 void intel_clear_lmce(void)
@@ -443,9 +443,9 @@ void intel_clear_lmce(void)
 	if (!lmce_supported())
 		return;
 
-	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
 	val &= ~MCG_EXT_CTL_LMCE_EN;
-	wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+	wrmsrq(MSR_IA32_MCG_EXT_CTL, val);
 }
 
 /*
@@ -460,10 +460,10 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
 	case INTEL_SANDYBRIDGE_X:
 	case INTEL_IVYBRIDGE_X:
 	case INTEL_HASWELL_X:
-		if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control))
+		if (rdmsrq_safe(MSR_ERROR_CONTROL, &error_control))
 			return;
 		error_control |= 2;
-		wrmsrl_safe(MSR_ERROR_CONTROL, error_control);
+		wrmsrq_safe(MSR_ERROR_CONTROL, error_control);
 		break;
 	}
 }
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 95a504ece43e..b5ba598e54cb 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -312,7 +312,7 @@ static __always_inline void pentium_machine_check(struct pt_regs *regs) {}
 static __always_inline void winchip_machine_check(struct pt_regs *regs) {}
 #endif
 
-noinstr u64 mce_rdmsrl(u32 msr);
+noinstr u64 mce_rdmsrq(u32 msr);
 
 static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
 {
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index dac4d64dfb2a..2235a7477436 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs)
 	copy_user  = is_copy_from_user(regs);
 	instrumentation_end();
 
-	switch (fixup_type) {
-	case EX_TYPE_UACCESS:
-		if (!copy_user)
-			return IN_KERNEL;
-		m->kflags |= MCE_IN_KERNEL_COPYIN;
-		fallthrough;
+	if (copy_user) {
+		m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV;
+		return IN_KERNEL_RECOV;
+	}
 
+	switch (fixup_type) {
 	case EX_TYPE_FAULT_MCE_SAFE:
 	case EX_TYPE_DEFAULT_MCE_SAFE:
 		m->kflags |= MCE_IN_KERNEL_RECOV;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a5dac7f3c0a0..097e39327942 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -23,14 +23,18 @@
 
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
+#include <linux/bsearch.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 
+#include <crypto/sha2.h>
+
 #include <asm/microcode.h>
 #include <asm/processor.h>
+#include <asm/cmdline.h>
 #include <asm/setup.h>
 #include <asm/cpu.h>
 #include <asm/msr.h>
@@ -145,6 +149,115 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static bool sha_check = true;
+
+struct patch_digest {
+	u32 patch_id;
+	u8 sha256[SHA256_DIGEST_SIZE];
+};
+
+#include "amd_shas.c"
+
+static int cmp_id(const void *key, const void *elem)
+{
+	struct patch_digest *pd = (struct patch_digest *)elem;
+	u32 patch_id = *(u32 *)key;
+
+	if (patch_id == pd->patch_id)
+		return 0;
+	else if (patch_id < pd->patch_id)
+		return -1;
+	else
+		return 1;
+}
+
+static bool need_sha_check(u32 cur_rev)
+{
+	switch (cur_rev >> 8) {
+	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x80082: return cur_rev <= 0x800820f; break;
+	case 0x83010: return cur_rev <= 0x830107c; break;
+	case 0x86001: return cur_rev <= 0x860010e; break;
+	case 0x86081: return cur_rev <= 0x8608108; break;
+	case 0x87010: return cur_rev <= 0x8701034; break;
+	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0010: return cur_rev <= 0xa00107a; break;
+	case 0xa0011: return cur_rev <= 0xa0011da; break;
+	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa0082: return cur_rev <= 0xa00820e; break;
+	case 0xa1011: return cur_rev <= 0xa101153; break;
+	case 0xa1012: return cur_rev <= 0xa10124e; break;
+	case 0xa1081: return cur_rev <= 0xa108109; break;
+	case 0xa2010: return cur_rev <= 0xa20102f; break;
+	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa4041: return cur_rev <= 0xa404109; break;
+	case 0xa5000: return cur_rev <= 0xa500013; break;
+	case 0xa6012: return cur_rev <= 0xa60120a; break;
+	case 0xa7041: return cur_rev <= 0xa704109; break;
+	case 0xa7052: return cur_rev <= 0xa705208; break;
+	case 0xa7080: return cur_rev <= 0xa708009; break;
+	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa001: return cur_rev <= 0xaa00116; break;
+	case 0xaa002: return cur_rev <= 0xaa00218; break;
+	case 0xb0021: return cur_rev <= 0xb002146; break;
+	case 0xb1010: return cur_rev <= 0xb101046; break;
+	case 0xb2040: return cur_rev <= 0xb204031; break;
+	case 0xb4040: return cur_rev <= 0xb404031; break;
+	case 0xb6000: return cur_rev <= 0xb600031; break;
+	case 0xb7000: return cur_rev <= 0xb700031; break;
+	default: break;
+	}
+
+	pr_info("You should not be seeing this. Please send the following couple of lines to x86-<at>-kernel.org\n");
+	pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev);
+	return true;
+}
+
+static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
+{
+	struct patch_digest *pd = NULL;
+	u8 digest[SHA256_DIGEST_SIZE];
+	int i;
+
+	if (x86_family(bsp_cpuid_1_eax) < 0x17)
+		return true;
+
+	if (!need_sha_check(cur_rev))
+		return true;
+
+	if (!sha_check)
+		return true;
+
+	pd = bsearch(&patch_id, phashes, ARRAY_SIZE(phashes), sizeof(struct patch_digest), cmp_id);
+	if (!pd) {
+		pr_err("No sha256 digest for patch ID: 0x%x found\n", patch_id);
+		return false;
+	}
+
+	sha256(data, len, digest);
+
+	if (memcmp(digest, pd->sha256, sizeof(digest))) {
+		pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
+
+		for (i = 0; i < SHA256_DIGEST_SIZE; i++)
+			pr_cont("0x%x ", digest[i]);
+		pr_info("\n");
+
+		return false;
+	}
+
+	return true;
+}
+
+static u32 get_patch_level(void)
+{
+	u32 rev, dummy __always_unused;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	return rev;
+}
+
 static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val)
 {
 	union zen_patch_rev p;
@@ -246,8 +359,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
  * On success, @sh_psize returns the patch size according to the section header,
  * to the caller.
  */
-static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
+static bool __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
 {
 	u32 p_type, p_size;
 	const u32 *hdr;
@@ -484,12 +596,15 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 	}
 }
 
-static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
+static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
+				  unsigned int psize)
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
-	u32 rev, dummy;
 
-	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
+	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
+		return false;
+
+	native_wrmsrq(MSR_AMD64_PATCH_LOADER, p_addr);
 
 	if (x86_family(bsp_cpuid_1_eax) == 0x17) {
 		unsigned long p_addr_end = p_addr + psize - 1;
@@ -505,47 +620,13 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	}
 
 	/* verify patch application was successful */
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	if (rev != mc->hdr.patch_id)
+	*cur_rev = get_patch_level();
+	if (*cur_rev != mc->hdr.patch_id)
 		return false;
 
 	return true;
 }
 
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- *
- * Returns true if container found (sets @desc), false otherwise.
- */
-static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
-{
-	struct cont_desc desc = { 0 };
-	struct microcode_amd *mc;
-
-	scan_containers(ucode, size, &desc);
-
-	mc = desc.mc;
-	if (!mc)
-		return false;
-
-	/*
-	 * Allow application of the same revision to pick up SMT-specific
-	 * changes even if the revision of the other SMT thread is already
-	 * up-to-date.
-	 */
-	if (old_rev > mc->hdr.patch_id)
-		return false;
-
-	return __apply_microcode_amd(mc, desc.psize);
-}
-
 static bool get_builtin_microcode(struct cpio_data *cp)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
@@ -583,14 +664,35 @@ static bool __init find_blobs_in_containers(struct cpio_data *ret)
 	return found;
 }
 
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
 void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
+	struct cont_desc desc = { };
+	struct microcode_amd *mc;
 	struct cpio_data cp = { };
-	u32 dummy;
+	char buf[4];
+	u32 rev;
+
+	if (cmdline_find_option(boot_command_line, "microcode.amd_sha_check", buf, 4)) {
+		if (!strncmp(buf, "off", 3)) {
+			sha_check = false;
+			pr_warn_once("It is a very very bad idea to disable the blobs SHA check!\n");
+			add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+		}
+	}
 
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
+	rev = get_patch_level();
+	ed->old_rev = rev;
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -598,37 +700,23 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (!find_blobs_in_containers(&cp))
 		return;
 
-	if (early_apply_microcode(ed->old_rev, cp.data, cp.size))
-		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
-}
-
-static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
-
-static int __init save_microcode_in_initrd(void)
-{
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-	struct cont_desc desc = { 0 };
-	enum ucode_state ret;
-	struct cpio_data cp;
-
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
-		return 0;
-
-	if (!find_blobs_in_containers(&cp))
-		return -EINVAL;
-
 	scan_containers(cp.data, cp.size, &desc);
-	if (!desc.mc)
-		return -EINVAL;
 
-	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret > UCODE_UPDATED)
-		return -EINVAL;
+	mc = desc.mc;
+	if (!mc)
+		return;
 
-	return 0;
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (ed->old_rev > mc->hdr.patch_id)
+		return;
+
+	if (__apply_microcode_amd(mc, &rev, desc.psize))
+		ed->new_rev = rev;
 }
-early_initcall(save_microcode_in_initrd);
 
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
 					 struct ucode_patch *n,
@@ -729,14 +817,9 @@ static void free_cache(void)
 static struct ucode_patch *find_patch(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u32 rev, dummy __always_unused;
 	u16 equiv_id = 0;
 
-	/* fetch rev if not populated yet: */
-	if (!uci->cpu_sig.rev) {
-		rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-		uci->cpu_sig.rev = rev;
-	}
+	uci->cpu_sig.rev = get_patch_level();
 
 	if (x86_family(bsp_cpuid_1_eax) < 0x17) {
 		equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
@@ -759,22 +842,20 @@ void reload_ucode_amd(unsigned int cpu)
 
 	mc = p->data;
 
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
+	rev = get_patch_level();
 	if (rev < mc->hdr.patch_id) {
-		if (__apply_microcode_amd(mc, p->size))
-			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
+		if (__apply_microcode_amd(mc, &rev, p->size))
+			pr_info_once("reload revision: 0x%08x\n", rev);
 	}
 }
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct ucode_patch *p;
 
 	csig->sig = cpuid_eax(0x00000001);
-	csig->rev = c->microcode;
+	csig->rev = get_patch_level();
 
 	/*
 	 * a patch could have been loaded early, set uci->mc so that
@@ -815,7 +896,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 		goto out;
 	}
 
-	if (!__apply_microcode_amd(mc_amd, p->size)) {
+	if (!__apply_microcode_amd(mc_amd, &rev, p->size)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;
@@ -937,8 +1018,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 }
 
 /* Scan the blob in @data and add microcode patches to the cache. */
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
-					     size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	u8 *fw = (u8 *)data;
 	size_t offset;
@@ -996,7 +1076,7 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	if (ret != UCODE_OK)
 		return ret;
 
-	for_each_node(nid) {
+	for_each_node_with_cpus(nid) {
 		cpu = cpumask_first(cpumask_of_node(nid));
 		c = &cpu_data(cpu);
 
@@ -1013,6 +1093,34 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	return ret;
 }
 
+static int __init save_microcode_in_initrd(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct cont_desc desc = { 0 };
+	unsigned int cpuid_1_eax;
+	enum ucode_state ret;
+	struct cpio_data cp;
+
+	if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+		return 0;
+
+	cpuid_1_eax = native_cpuid_eax(1);
+
+	if (!find_blobs_in_containers(&cp))
+		return -EINVAL;
+
+	scan_containers(cp.data, cp.size, &desc);
+	if (!desc.mc)
+		return -EINVAL;
+
+	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+	if (ret > UCODE_UPDATED)
+		return -EINVAL;
+
+	return 0;
+}
+early_initcall(save_microcode_in_initrd);
+
 /*
  * AMD microcode firmware naming convention, up to family 15h they are in
  * the legacy file:
@@ -1067,11 +1175,18 @@ static void microcode_fini_cpu_amd(int cpu)
 	uci->mc = NULL;
 }
 
+static void finalize_late_load_amd(int result)
+{
+	if (result)
+		cleanup();
+}
+
 static struct microcode_ops microcode_amd_ops = {
 	.request_microcode_fw	= request_microcode_amd,
 	.collect_cpu_info	= collect_cpu_info_amd,
 	.apply_microcode	= apply_microcode_amd,
 	.microcode_fini_cpu	= microcode_fini_cpu_amd,
+	.finalize_late_load	= finalize_late_load_amd,
 	.nmi_safe		= true,
 };
 
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
new file mode 100644
index 000000000000..2a1655b1fdd8
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -0,0 +1,444 @@
+/* Keep 'em sorted. */
+static const struct patch_digest phashes[] = {
+ { 0x8001227, {
+		0x99,0xc0,0x9b,0x2b,0xcc,0x9f,0x52,0x1b,
+		0x1a,0x5f,0x1d,0x83,0xa1,0x6c,0xc4,0x46,
+		0xe2,0x6c,0xda,0x73,0xfb,0x2d,0x23,0xa8,
+		0x77,0xdc,0x15,0x31,0x33,0x4a,0x46,0x18,
+	}
+ },
+ { 0x8001250, {
+		0xc0,0x0b,0x6b,0x19,0xfd,0x5c,0x39,0x60,
+		0xd5,0xc3,0x57,0x46,0x54,0xe4,0xd1,0xaa,
+		0xa8,0xf7,0x1f,0xa8,0x6a,0x60,0x3e,0xe3,
+		0x27,0x39,0x8e,0x53,0x30,0xf8,0x49,0x19,
+	}
+ },
+ { 0x800126e, {
+		0xf3,0x8b,0x2b,0xb6,0x34,0xe3,0xc8,0x2c,
+		0xef,0xec,0x63,0x6d,0xc8,0x76,0x77,0xb3,
+		0x25,0x5a,0xb7,0x52,0x8c,0x83,0x26,0xe6,
+		0x4c,0xbe,0xbf,0xe9,0x7d,0x22,0x6a,0x43,
+	}
+ },
+ { 0x800126f, {
+		0x2b,0x5a,0xf2,0x9c,0xdd,0xd2,0x7f,0xec,
+		0xec,0x96,0x09,0x57,0xb0,0x96,0x29,0x8b,
+		0x2e,0x26,0x91,0xf0,0x49,0x33,0x42,0x18,
+		0xdd,0x4b,0x65,0x5a,0xd4,0x15,0x3d,0x33,
+	}
+ },
+ { 0x800820d, {
+		0x68,0x98,0x83,0xcd,0x22,0x0d,0xdd,0x59,
+		0x73,0x2c,0x5b,0x37,0x1f,0x84,0x0e,0x67,
+		0x96,0x43,0x83,0x0c,0x46,0x44,0xab,0x7c,
+		0x7b,0x65,0x9e,0x57,0xb5,0x90,0x4b,0x0e,
+	}
+ },
+ { 0x8301025, {
+		0xe4,0x7d,0xdb,0x1e,0x14,0xb4,0x5e,0x36,
+		0x8f,0x3e,0x48,0x88,0x3c,0x6d,0x76,0xa1,
+		0x59,0xc6,0xc0,0x72,0x42,0xdf,0x6c,0x30,
+		0x6f,0x0b,0x28,0x16,0x61,0xfc,0x79,0x77,
+	}
+ },
+ { 0x8301055, {
+		0x81,0x7b,0x99,0x1b,0xae,0x2d,0x4f,0x9a,
+		0xef,0x13,0xce,0xb5,0x10,0xaf,0x6a,0xea,
+		0xe5,0xb0,0x64,0x98,0x10,0x68,0x34,0x3b,
+		0x9d,0x7a,0xd6,0x22,0x77,0x5f,0xb3,0x5b,
+	}
+ },
+ { 0x8301072, {
+		0xcf,0x76,0xa7,0x1a,0x49,0xdf,0x2a,0x5e,
+		0x9e,0x40,0x70,0xe5,0xdd,0x8a,0xa8,0x28,
+		0x20,0xdc,0x91,0xd8,0x2c,0xa6,0xa0,0xb1,
+		0x2d,0x22,0x26,0x94,0x4b,0x40,0x85,0x30,
+	}
+ },
+ { 0x830107a, {
+		0x2a,0x65,0x8c,0x1a,0x5e,0x07,0x21,0x72,
+		0xdf,0x90,0xa6,0x51,0x37,0xd3,0x4b,0x34,
+		0xc4,0xda,0x03,0xe1,0x8a,0x6c,0xfb,0x20,
+		0x04,0xb2,0x81,0x05,0xd4,0x87,0xf4,0x0a,
+	}
+ },
+ { 0x830107b, {
+		0xb3,0x43,0x13,0x63,0x56,0xc1,0x39,0xad,
+		0x10,0xa6,0x2b,0xcc,0x02,0xe6,0x76,0x2a,
+		0x1e,0x39,0x58,0x3e,0x23,0x6e,0xa4,0x04,
+		0x95,0xea,0xf9,0x6d,0xc2,0x8a,0x13,0x19,
+	}
+ },
+ { 0x830107c, {
+		0x21,0x64,0xde,0xfb,0x9f,0x68,0x96,0x47,
+		0x70,0x5c,0xe2,0x8f,0x18,0x52,0x6a,0xac,
+		0xa4,0xd2,0x2e,0xe0,0xde,0x68,0x66,0xc3,
+		0xeb,0x1e,0xd3,0x3f,0xbc,0x51,0x1d,0x38,
+	}
+ },
+ { 0x860010d, {
+		0x86,0xb6,0x15,0x83,0xbc,0x3b,0x9c,0xe0,
+		0xb3,0xef,0x1d,0x99,0x84,0x35,0x15,0xf7,
+		0x7c,0x2a,0xc6,0x42,0xdb,0x73,0x07,0x5c,
+		0x7d,0xc3,0x02,0xb5,0x43,0x06,0x5e,0xf8,
+	}
+ },
+ { 0x8608108, {
+		0x14,0xfe,0x57,0x86,0x49,0xc8,0x68,0xe2,
+		0x11,0xa3,0xcb,0x6e,0xff,0x6e,0xd5,0x38,
+		0xfe,0x89,0x1a,0xe0,0x67,0xbf,0xc4,0xcc,
+		0x1b,0x9f,0x84,0x77,0x2b,0x9f,0xaa,0xbd,
+	}
+ },
+ { 0x8701034, {
+		0xc3,0x14,0x09,0xa8,0x9c,0x3f,0x8d,0x83,
+		0x9b,0x4c,0xa5,0xb7,0x64,0x8b,0x91,0x5d,
+		0x85,0x6a,0x39,0x26,0x1e,0x14,0x41,0xa8,
+		0x75,0xea,0xa6,0xf9,0xc9,0xd1,0xea,0x2b,
+	}
+ },
+ { 0x8a00008, {
+		0xd7,0x2a,0x93,0xdc,0x05,0x2f,0xa5,0x6e,
+		0x0c,0x61,0x2c,0x07,0x9f,0x38,0xe9,0x8e,
+		0xef,0x7d,0x2a,0x05,0x4d,0x56,0xaf,0x72,
+		0xe7,0x56,0x47,0x6e,0x60,0x27,0xd5,0x8c,
+	}
+ },
+ { 0x8a0000a, {
+		0x73,0x31,0x26,0x22,0xd4,0xf9,0xee,0x3c,
+		0x07,0x06,0xe7,0xb9,0xad,0xd8,0x72,0x44,
+		0x33,0x31,0xaa,0x7d,0xc3,0x67,0x0e,0xdb,
+		0x47,0xb5,0xaa,0xbc,0xf5,0xbb,0xd9,0x20,
+	}
+ },
+ { 0xa00104c, {
+		0x3c,0x8a,0xfe,0x04,0x62,0xd8,0x6d,0xbe,
+		0xa7,0x14,0x28,0x64,0x75,0xc0,0xa3,0x76,
+		0xb7,0x92,0x0b,0x97,0x0a,0x8e,0x9c,0x5b,
+		0x1b,0xc8,0x9d,0x3a,0x1e,0x81,0x3d,0x3b,
+	}
+ },
+ { 0xa00104e, {
+		0xc4,0x35,0x82,0x67,0xd2,0x86,0xe5,0xb2,
+		0xfd,0x69,0x12,0x38,0xc8,0x77,0xba,0xe0,
+		0x70,0xf9,0x77,0x89,0x10,0xa6,0x74,0x4e,
+		0x56,0x58,0x13,0xf5,0x84,0x70,0x28,0x0b,
+	}
+ },
+ { 0xa001053, {
+		0x92,0x0e,0xf4,0x69,0x10,0x3b,0xf9,0x9d,
+		0x31,0x1b,0xa6,0x99,0x08,0x7d,0xd7,0x25,
+		0x7e,0x1e,0x89,0xba,0x35,0x8d,0xac,0xcb,
+		0x3a,0xb4,0xdf,0x58,0x12,0xcf,0xc0,0xc3,
+	}
+ },
+ { 0xa001058, {
+		0x33,0x7d,0xa9,0xb5,0x4e,0x62,0x13,0x36,
+		0xef,0x66,0xc9,0xbd,0x0a,0xa6,0x3b,0x19,
+		0xcb,0xf5,0xc2,0xc3,0x55,0x47,0x20,0xec,
+		0x1f,0x7b,0xa1,0x44,0x0e,0x8e,0xa4,0xb2,
+	}
+ },
+ { 0xa001075, {
+		0x39,0x02,0x82,0xd0,0x7c,0x26,0x43,0xe9,
+		0x26,0xa3,0xd9,0x96,0xf7,0x30,0x13,0x0a,
+		0x8a,0x0e,0xac,0xe7,0x1d,0xdc,0xe2,0x0f,
+		0xcb,0x9e,0x8d,0xbc,0xd2,0xa2,0x44,0xe0,
+	}
+ },
+ { 0xa001078, {
+		0x2d,0x67,0xc7,0x35,0xca,0xef,0x2f,0x25,
+		0x4c,0x45,0x93,0x3f,0x36,0x01,0x8c,0xce,
+		0xa8,0x5b,0x07,0xd3,0xc1,0x35,0x3c,0x04,
+		0x20,0xa2,0xfc,0xdc,0xe6,0xce,0x26,0x3e,
+	}
+ },
+ { 0xa001079, {
+		0x43,0xe2,0x05,0x9c,0xfd,0xb7,0x5b,0xeb,
+		0x5b,0xe9,0xeb,0x3b,0x96,0xf4,0xe4,0x93,
+		0x73,0x45,0x3e,0xac,0x8d,0x3b,0xe4,0xdb,
+		0x10,0x31,0xc1,0xe4,0xa2,0xd0,0x5a,0x8a,
+	}
+ },
+ { 0xa00107a, {
+		0x5f,0x92,0xca,0xff,0xc3,0x59,0x22,0x5f,
+		0x02,0xa0,0x91,0x3b,0x4a,0x45,0x10,0xfd,
+		0x19,0xe1,0x8a,0x6d,0x9a,0x92,0xc1,0x3f,
+		0x75,0x78,0xac,0x78,0x03,0x1d,0xdb,0x18,
+	}
+ },
+ { 0xa001143, {
+		0x56,0xca,0xf7,0x43,0x8a,0x4c,0x46,0x80,
+		0xec,0xde,0xe5,0x9c,0x50,0x84,0x9a,0x42,
+		0x27,0xe5,0x51,0x84,0x8f,0x19,0xc0,0x8d,
+		0x0c,0x25,0xb4,0xb0,0x8f,0x10,0xf3,0xf8,
+	}
+ },
+ { 0xa001144, {
+		0x42,0xd5,0x9b,0xa7,0xd6,0x15,0x29,0x41,
+		0x61,0xc4,0x72,0x3f,0xf3,0x06,0x78,0x4b,
+		0x65,0xf3,0x0e,0xfa,0x9c,0x87,0xde,0x25,
+		0xbd,0xb3,0x9a,0xf4,0x75,0x13,0x53,0xdc,
+	}
+ },
+ { 0xa00115d, {
+		0xd4,0xc4,0x49,0x36,0x89,0x0b,0x47,0xdd,
+		0xfb,0x2f,0x88,0x3b,0x5f,0xf2,0x8e,0x75,
+		0xc6,0x6c,0x37,0x5a,0x90,0x25,0x94,0x3e,
+		0x36,0x9c,0xae,0x02,0x38,0x6c,0xf5,0x05,
+	}
+ },
+ { 0xa001173, {
+		0x28,0xbb,0x9b,0xd1,0xa0,0xa0,0x7e,0x3a,
+		0x59,0x20,0xc0,0xa9,0xb2,0x5c,0xc3,0x35,
+		0x53,0x89,0xe1,0x4c,0x93,0x2f,0x1d,0xc3,
+		0xe5,0xf7,0xf3,0xc8,0x9b,0x61,0xaa,0x9e,
+	}
+ },
+ { 0xa0011a8, {
+		0x97,0xc6,0x16,0x65,0x99,0xa4,0x85,0x3b,
+		0xf6,0xce,0xaa,0x49,0x4a,0x3a,0xc5,0xb6,
+		0x78,0x25,0xbc,0x53,0xaf,0x5d,0xcf,0xf4,
+		0x23,0x12,0xbb,0xb1,0xbc,0x8a,0x02,0x2e,
+	}
+ },
+ { 0xa0011ce, {
+		0xcf,0x1c,0x90,0xa3,0x85,0x0a,0xbf,0x71,
+		0x94,0x0e,0x80,0x86,0x85,0x4f,0xd7,0x86,
+		0xae,0x38,0x23,0x28,0x2b,0x35,0x9b,0x4e,
+		0xfe,0xb8,0xcd,0x3d,0x3d,0x39,0xc9,0x6a,
+	}
+ },
+ { 0xa0011d1, {
+		0xdf,0x0e,0xca,0xde,0xf6,0xce,0x5c,0x1e,
+		0x4c,0xec,0xd7,0x71,0x83,0xcc,0xa8,0x09,
+		0xc7,0xc5,0xfe,0xb2,0xf7,0x05,0xd2,0xc5,
+		0x12,0xdd,0xe4,0xf3,0x92,0x1c,0x3d,0xb8,
+	}
+ },
+ { 0xa0011d3, {
+		0x91,0xe6,0x10,0xd7,0x57,0xb0,0x95,0x0b,
+		0x9a,0x24,0xee,0xf7,0xcf,0x56,0xc1,0xa6,
+		0x4a,0x52,0x7d,0x5f,0x9f,0xdf,0xf6,0x00,
+		0x65,0xf7,0xea,0xe8,0x2a,0x88,0xe2,0x26,
+	}
+ },
+ { 0xa0011d5, {
+		0xed,0x69,0x89,0xf4,0xeb,0x64,0xc2,0x13,
+		0xe0,0x51,0x1f,0x03,0x26,0x52,0x7d,0xb7,
+		0x93,0x5d,0x65,0xca,0xb8,0x12,0x1d,0x62,
+		0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
+	}
+ },
+ { 0xa001223, {
+		0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
+		0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
+		0x83,0x75,0x94,0xdd,0xeb,0x7e,0xb7,0x15,
+		0x8e,0x3b,0x50,0x29,0x8a,0x9c,0xcc,0x45,
+	}
+ },
+ { 0xa001224, {
+		0x0e,0x0c,0xdf,0xb4,0x89,0xee,0x35,0x25,
+		0xdd,0x9e,0xdb,0xc0,0x69,0x83,0x0a,0xad,
+		0x26,0xa9,0xaa,0x9d,0xfc,0x3c,0xea,0xf9,
+		0x6c,0xdc,0xd5,0x6d,0x8b,0x6e,0x85,0x4a,
+	}
+ },
+ { 0xa001227, {
+		0xab,0xc6,0x00,0x69,0x4b,0x50,0x87,0xad,
+		0x5f,0x0e,0x8b,0xea,0x57,0x38,0xce,0x1d,
+		0x0f,0x75,0x26,0x02,0xf6,0xd6,0x96,0xe9,
+		0x87,0xb9,0xd6,0x20,0x27,0x7c,0xd2,0xe0,
+	}
+ },
+ { 0xa001229, {
+		0x7f,0x49,0x49,0x48,0x46,0xa5,0x50,0xa6,
+		0x28,0x89,0x98,0xe2,0x9e,0xb4,0x7f,0x75,
+		0x33,0xa7,0x04,0x02,0xe4,0x82,0xbf,0xb4,
+		0xa5,0x3a,0xba,0x24,0x8d,0x31,0x10,0x1d,
+	}
+ },
+ { 0xa00122e, {
+		0x56,0x94,0xa9,0x5d,0x06,0x68,0xfe,0xaf,
+		0xdf,0x7a,0xff,0x2d,0xdf,0x74,0x0f,0x15,
+		0x66,0xfb,0x00,0xb5,0x51,0x97,0x9b,0xfa,
+		0xcb,0x79,0x85,0x46,0x25,0xb4,0xd2,0x10,
+	}
+ },
+ { 0xa001231, {
+		0x0b,0x46,0xa5,0xfc,0x18,0x15,0xa0,0x9e,
+		0xa6,0xdc,0xb7,0xff,0x17,0xf7,0x30,0x64,
+		0xd4,0xda,0x9e,0x1b,0xc3,0xfc,0x02,0x3b,
+		0xe2,0xc6,0x0e,0x41,0x54,0xb5,0x18,0xdd,
+	}
+ },
+ { 0xa001234, {
+		0x88,0x8d,0xed,0xab,0xb5,0xbd,0x4e,0xf7,
+		0x7f,0xd4,0x0e,0x95,0x34,0x91,0xff,0xcc,
+		0xfb,0x2a,0xcd,0xf7,0xd5,0xdb,0x4c,0x9b,
+		0xd6,0x2e,0x73,0x50,0x8f,0x83,0x79,0x1a,
+	}
+ },
+ { 0xa001236, {
+		0x3d,0x30,0x00,0xb9,0x71,0xba,0x87,0x78,
+		0xa8,0x43,0x55,0xc4,0x26,0x59,0xcf,0x9d,
+		0x93,0xce,0x64,0x0e,0x8b,0x72,0x11,0x8b,
+		0xa3,0x8f,0x51,0xe9,0xca,0x98,0xaa,0x25,
+	}
+ },
+ { 0xa001238, {
+		0x72,0xf7,0x4b,0x0c,0x7d,0x58,0x65,0xcc,
+		0x00,0xcc,0x57,0x16,0x68,0x16,0xf8,0x2a,
+		0x1b,0xb3,0x8b,0xe1,0xb6,0x83,0x8c,0x7e,
+		0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
+	}
+ },
+ { 0xa00820c, {
+		0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
+		0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
+		0xf1,0x8c,0x88,0x45,0xd7,0x82,0x80,0xd1,
+		0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
+	}
+ },
+ { 0xa10113e, {
+		0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
+		0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
+		0x15,0xe3,0x3f,0x4b,0x1d,0x0d,0x0a,0xd5,
+		0xfa,0x90,0xc4,0xed,0x9d,0x90,0xaf,0x53,
+	}
+ },
+ { 0xa101144, {
+		0xb3,0x0b,0x26,0x9a,0xf8,0x7c,0x02,0x26,
+		0x35,0x84,0x53,0xa4,0xd3,0x2c,0x7c,0x09,
+		0x68,0x7b,0x96,0xb6,0x93,0xef,0xde,0xbc,
+		0xfd,0x4b,0x15,0xd2,0x81,0xd3,0x51,0x47,
+	}
+ },
+ { 0xa101148, {
+		0x20,0xd5,0x6f,0x40,0x4a,0xf6,0x48,0x90,
+		0xc2,0x93,0x9a,0xc2,0xfd,0xac,0xef,0x4f,
+		0xfa,0xc0,0x3d,0x92,0x3c,0x6d,0x01,0x08,
+		0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
+	}
+ },
+ { 0xa10123e, {
+		0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
+		0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
+		0x1d,0x13,0x53,0x63,0xfe,0x42,0x6f,0xfc,
+		0x19,0x0f,0xf1,0xfc,0xa7,0xdd,0x89,0x1b,
+	}
+ },
+ { 0xa101244, {
+		0x71,0x56,0xb5,0x9f,0x21,0xbf,0xb3,0x3c,
+		0x8c,0xd7,0x36,0xd0,0x34,0x52,0x1b,0xb1,
+		0x46,0x2f,0x04,0xf0,0x37,0xd8,0x1e,0x72,
+		0x24,0xa2,0x80,0x84,0x83,0x65,0x84,0xc0,
+	}
+ },
+ { 0xa101248, {
+		0xed,0x3b,0x95,0xa6,0x68,0xa7,0x77,0x3e,
+		0xfc,0x17,0x26,0xe2,0x7b,0xd5,0x56,0x22,
+		0x2c,0x1d,0xef,0xeb,0x56,0xdd,0xba,0x6e,
+		0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
+	}
+ },
+ { 0xa108108, {
+		0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
+		0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
+		0xf5,0xd4,0x3f,0x7b,0x14,0xd5,0x60,0x2c,
+		0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
+	}
+ },
+ { 0xa20102d, {
+		0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
+		0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
+		0x8b,0x89,0x2f,0xb5,0xbb,0x82,0xef,0x23,
+		0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
+	}
+ },
+ { 0xa201210, {
+		0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
+		0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
+		0x6d,0x3d,0x0e,0x6b,0xa7,0xac,0xe3,0x68,
+		0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
+	}
+ },
+ { 0xa404107, {
+		0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
+		0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
+		0x8b,0x0d,0x9f,0xf9,0x3a,0xdf,0xc6,0x81,
+		0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
+	}
+ },
+ { 0xa500011, {
+		0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
+		0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
+		0xd7,0x5b,0x65,0x3a,0x7d,0xab,0xdf,0xa2,
+		0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
+	}
+ },
+ { 0xa601209, {
+		0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
+		0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
+		0x15,0x86,0xcc,0x5d,0x97,0x0f,0xc0,0x46,
+		0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
+	}
+ },
+ { 0xa704107, {
+		0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
+		0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
+		0x2a,0xad,0x8e,0x6b,0xea,0x9b,0xb7,0xc2,
+		0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
+	}
+ },
+ { 0xa705206, {
+		0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
+		0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
+		0x67,0x6f,0x04,0x18,0xae,0x20,0x87,0x4b,
+		0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
+	}
+ },
+ { 0xa708007, {
+		0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
+		0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
+		0x07,0xaa,0x3a,0xe0,0x57,0x13,0x72,0x80,
+		0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
+	}
+ },
+ { 0xa70c005, {
+		0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
+		0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
+		0x1f,0x1f,0xf1,0x97,0xeb,0xfe,0x56,0x55,
+		0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
+	}
+ },
+ { 0xaa00116, {
+		0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
+		0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
+		0xfe,0x1d,0x5e,0x65,0xc7,0xaa,0x92,0x4d,
+		0x91,0xee,0x76,0xbb,0x4c,0x66,0x78,0xc9,
+	}
+ },
+ { 0xaa00212, {
+		0xbd,0x57,0x5d,0x0a,0x0a,0x30,0xc1,0x75,
+		0x95,0x58,0x5e,0x93,0x02,0x28,0x43,0x71,
+		0xed,0x42,0x29,0xc8,0xec,0x34,0x2b,0xb2,
+		0x1a,0x65,0x4b,0xfe,0x07,0x0f,0x34,0xa1,
+	}
+ },
+ { 0xaa00213, {
+		0xed,0x58,0xb7,0x76,0x81,0x7f,0xd9,0x3a,
+		0x1a,0xff,0x8b,0x34,0xb8,0x4a,0x99,0x0f,
+		0x28,0x49,0x6c,0x56,0x2b,0xdc,0xb7,0xed,
+		0x96,0xd5,0x9d,0xc1,0x7a,0xd4,0x51,0x9b,
+	}
+ },
+ { 0xaa00215, {
+		0x55,0xd3,0x28,0xcb,0x87,0xa9,0x32,0xe9,
+		0x4e,0x85,0x4b,0x7c,0x6b,0xd5,0x7c,0xd4,
+		0x1b,0x51,0x71,0x3a,0x0e,0x0b,0xdc,0x9b,
+		0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
+	}
+ },
+};
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b3658d11e7b6..fe50eb5b7c4a 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -37,12 +37,13 @@
 #include <asm/perf_event.h>
 #include <asm/processor.h>
 #include <asm/cmdline.h>
+#include <asm/msr.h>
 #include <asm/setup.h>
 
 #include "internal.h"
 
-static struct microcode_ops	*microcode_ops;
-bool dis_ucode_ldr = true;
+static struct microcode_ops *microcode_ops;
+static bool dis_ucode_ldr = false;
 
 bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
 module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
@@ -84,6 +85,9 @@ static bool amd_check_current_patch_level(void)
 	u32 lvl, dummy, i;
 	u32 *levels;
 
+	if (x86_cpuid_vendor() != X86_VENDOR_AMD)
+		return false;
+
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
 
 	levels = final_levels;
@@ -95,27 +99,29 @@ static bool amd_check_current_patch_level(void)
 	return false;
 }
 
-static bool __init check_loader_disabled_bsp(void)
+bool __init microcode_loader_disabled(void)
 {
-	static const char *__dis_opt_str = "dis_ucode_ldr";
-	const char *cmdline = boot_command_line;
-	const char *option  = __dis_opt_str;
+	if (dis_ucode_ldr)
+		return true;
 
 	/*
-	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
-	 * completely accurate as xen pv guests don't see that CPUID bit set but
-	 * that's good enough as they don't land on the BSP path anyway.
+	 * Disable when:
+	 *
+	 * 1) The CPU does not support CPUID.
+	 *
+	 * 2) Bit 31 in CPUID[1]:ECX is clear
+	 *    The bit is reserved for hypervisor use. This is still not
+	 *    completely accurate as XEN PV guests don't see that CPUID bit
+	 *    set, but that's good enough as they don't land on the BSP
+	 *    path anyway.
+	 *
+	 * 3) Certain AMD patch levels are not allowed to be
+	 *    overwritten.
 	 */
-	if (native_cpuid_ecx(1) & BIT(31))
-		return true;
-
-	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
-		if (amd_check_current_patch_level())
-			return true;
-	}
-
-	if (cmdline_find_option_bool(cmdline, option) <= 0)
-		dis_ucode_ldr = false;
+	if (!cpuid_feature() ||
+	    native_cpuid_ecx(1) & BIT(31) ||
+	    amd_check_current_patch_level())
+		dis_ucode_ldr = true;
 
 	return dis_ucode_ldr;
 }
@@ -125,7 +131,10 @@ void __init load_ucode_bsp(void)
 	unsigned int cpuid_1_eax;
 	bool intel = true;
 
-	if (!have_cpuid_p())
+	if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0)
+		dis_ucode_ldr = true;
+
+	if (microcode_loader_disabled())
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
@@ -146,9 +155,6 @@ void __init load_ucode_bsp(void)
 		return;
 	}
 
-	if (check_loader_disabled_bsp())
-		return;
-
 	if (intel)
 		load_ucode_intel_bsp(&early_data);
 	else
@@ -159,6 +165,11 @@ void load_ucode_ap(void)
 {
 	unsigned int cpuid_1_eax;
 
+	/*
+	 * Can't use microcode_loader_disabled() here - .init section
+	 * hell. It doesn't have to either - the BSP variant must've
+	 * parsed cmdline already anyway.
+	 */
 	if (dis_ucode_ldr)
 		return;
 
@@ -686,6 +697,8 @@ static int load_late_locked(void)
 		return load_late_stop_cpus(true);
 	case UCODE_NFOUND:
 		return -ENOENT;
+	case UCODE_OK:
+		return 0;
 	default:
 		return -EBADFD;
 	}
@@ -810,7 +823,7 @@ static int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	int error;
 
-	if (dis_ucode_ldr)
+	if (microcode_loader_disabled())
 		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h b/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h
new file mode 100644
index 000000000000..cb6e601701ab
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h
@@ -0,0 +1,150 @@
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x03, .steppings = 0x0004, .driver_data = 0x2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x05, .steppings = 0x0001, .driver_data = 0x45 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x05, .steppings = 0x0002, .driver_data = 0x40 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x05, .steppings = 0x0004, .driver_data = 0x2c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x05, .steppings = 0x0008, .driver_data = 0x10 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x06, .steppings = 0x0001, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x06, .steppings = 0x0020, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x06, .steppings = 0x0400, .driver_data = 0xd },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x06, .steppings = 0x2000, .driver_data = 0x7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x07, .steppings = 0x0002, .driver_data = 0x14 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x07, .steppings = 0x0004, .driver_data = 0x38 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x07, .steppings = 0x0008, .driver_data = 0x2e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x08, .steppings = 0x0002, .driver_data = 0x11 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x08, .steppings = 0x0008, .driver_data = 0x8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x08, .steppings = 0x0040, .driver_data = 0xc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x08, .steppings = 0x0400, .driver_data = 0x5 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x09, .steppings = 0x0020, .driver_data = 0x47 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0a, .steppings = 0x0001, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0a, .steppings = 0x0002, .driver_data = 0x1 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0b, .steppings = 0x0002, .driver_data = 0x1d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0b, .steppings = 0x0010, .driver_data = 0x2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0d, .steppings = 0x0040, .driver_data = 0x18 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0e, .steppings = 0x0100, .driver_data = 0x39 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0e, .steppings = 0x1000, .driver_data = 0x59 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x0004, .driver_data = 0x5d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x0040, .driver_data = 0xd2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x0080, .driver_data = 0x6b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x0400, .driver_data = 0x95 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x0800, .driver_data = 0xbc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x0f, .steppings = 0x2000, .driver_data = 0xa4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x16, .steppings = 0x0002, .driver_data = 0x44 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x17, .steppings = 0x0040, .driver_data = 0x60f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x17, .steppings = 0x0080, .driver_data = 0x70a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x17, .steppings = 0x0400, .driver_data = 0xa0b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1a, .steppings = 0x0010, .driver_data = 0x12 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1a, .steppings = 0x0020, .driver_data = 0x1d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1c, .steppings = 0x0004, .driver_data = 0x219 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1c, .steppings = 0x0400, .driver_data = 0x107 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1d, .steppings = 0x0002, .driver_data = 0x29 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x1e, .steppings = 0x0020, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x25, .steppings = 0x0004, .driver_data = 0x11 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x25, .steppings = 0x0020, .driver_data = 0x7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x26, .steppings = 0x0002, .driver_data = 0x105 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2a, .steppings = 0x0080, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2c, .steppings = 0x0004, .driver_data = 0x1f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2d, .steppings = 0x0040, .driver_data = 0x621 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2d, .steppings = 0x0080, .driver_data = 0x71a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2e, .steppings = 0x0040, .driver_data = 0xd },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x2f, .steppings = 0x0004, .driver_data = 0x3b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x37, .steppings = 0x0100, .driver_data = 0x838 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x37, .steppings = 0x0200, .driver_data = 0x90d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3a, .steppings = 0x0200, .driver_data = 0x21 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3c, .steppings = 0x0008, .driver_data = 0x28 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3d, .steppings = 0x0010, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3e, .steppings = 0x0010, .driver_data = 0x42e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3e, .steppings = 0x0040, .driver_data = 0x600 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3e, .steppings = 0x0080, .driver_data = 0x715 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3f, .steppings = 0x0004, .driver_data = 0x49 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x3f, .steppings = 0x0010, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x45, .steppings = 0x0002, .driver_data = 0x26 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x46, .steppings = 0x0002, .driver_data = 0x1c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x47, .steppings = 0x0002, .driver_data = 0x22 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x4c, .steppings = 0x0008, .driver_data = 0x368 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x4c, .steppings = 0x0010, .driver_data = 0x411 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x4d, .steppings = 0x0100, .driver_data = 0x12d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x4e, .steppings = 0x0008, .driver_data = 0xf0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0008, .driver_data = 0x1000191 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0010, .driver_data = 0x2007006 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0020, .driver_data = 0x3000010 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0040, .driver_data = 0x4003605 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0080, .driver_data = 0x5003707 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x55, .steppings = 0x0800, .driver_data = 0x7002904 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x56, .steppings = 0x0004, .driver_data = 0x1c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x56, .steppings = 0x0008, .driver_data = 0x700001c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x56, .steppings = 0x0010, .driver_data = 0xf00001a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x56, .steppings = 0x0020, .driver_data = 0xe000015 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x5c, .steppings = 0x0004, .driver_data = 0x14 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x5c, .steppings = 0x0200, .driver_data = 0x48 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x5c, .steppings = 0x0400, .driver_data = 0x28 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x5e, .steppings = 0x0008, .driver_data = 0xf0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x5f, .steppings = 0x0002, .driver_data = 0x3e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x66, .steppings = 0x0008, .driver_data = 0x2a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x6a, .steppings = 0x0020, .driver_data = 0xc0002f0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x6a, .steppings = 0x0040, .driver_data = 0xd0003e7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x6c, .steppings = 0x0002, .driver_data = 0x10002b0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x7a, .steppings = 0x0002, .driver_data = 0x42 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x7a, .steppings = 0x0100, .driver_data = 0x24 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x7e, .steppings = 0x0020, .driver_data = 0xc6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8a, .steppings = 0x0002, .driver_data = 0x33 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8c, .steppings = 0x0002, .driver_data = 0xb8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8c, .steppings = 0x0004, .driver_data = 0x38 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8d, .steppings = 0x0002, .driver_data = 0x52 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8e, .steppings = 0x0200, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8e, .steppings = 0x0400, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8e, .steppings = 0x0800, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8e, .steppings = 0x1000, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8f, .steppings = 0x0100, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8f, .steppings = 0x0080, .driver_data = 0x2b000603 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8f, .steppings = 0x0040, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8f, .steppings = 0x0020, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x8f, .steppings = 0x0010, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x96, .steppings = 0x0002, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x97, .steppings = 0x0004, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x97, .steppings = 0x0020, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xbf, .steppings = 0x0004, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xbf, .steppings = 0x0020, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9a, .steppings = 0x0008, .driver_data = 0x435 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9a, .steppings = 0x0010, .driver_data = 0x435 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9c, .steppings = 0x0001, .driver_data = 0x24000026 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9e, .steppings = 0x0200, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9e, .steppings = 0x0400, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9e, .steppings = 0x0800, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9e, .steppings = 0x1000, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0x9e, .steppings = 0x2000, .driver_data = 0x100 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa5, .steppings = 0x0004, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa5, .steppings = 0x0008, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa5, .steppings = 0x0020, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa6, .steppings = 0x0001, .driver_data = 0xfe },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa6, .steppings = 0x0002, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xa7, .steppings = 0x0002, .driver_data = 0x62 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xaa, .steppings = 0x0010, .driver_data = 0x20 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xb7, .steppings = 0x0002, .driver_data = 0x12b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xba, .steppings = 0x0004, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xba, .steppings = 0x0008, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xba, .steppings = 0x0100, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xbe, .steppings = 0x0001, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xcf, .steppings = 0x0004, .driver_data = 0x21000283 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6,  .model = 0xcf, .steppings = 0x0002, .driver_data = 0x21000283 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x00, .steppings = 0x0080, .driver_data = 0x12 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x00, .steppings = 0x0400, .driver_data = 0x15 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x01, .steppings = 0x0004, .driver_data = 0x2e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x02, .steppings = 0x0010, .driver_data = 0x21 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x02, .steppings = 0x0020, .driver_data = 0x2c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x02, .steppings = 0x0040, .driver_data = 0x10 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x02, .steppings = 0x0080, .driver_data = 0x39 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x02, .steppings = 0x0200, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x03, .steppings = 0x0004, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x03, .steppings = 0x0008, .driver_data = 0xc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x03, .steppings = 0x0010, .driver_data = 0x17 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0002, .driver_data = 0x17 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0008, .driver_data = 0x5 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0010, .driver_data = 0x6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0080, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0100, .driver_data = 0xe },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0200, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x04, .steppings = 0x0400, .driver_data = 0x4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x06, .steppings = 0x0004, .driver_data = 0xf },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x06, .steppings = 0x0010, .driver_data = 0x4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x06, .steppings = 0x0020, .driver_data = 0x8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf,  .model = 0x06, .steppings = 0x0100, .driver_data = 0x9 },
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index f3d534807d91..371ca6eac00e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -74,7 +74,7 @@ void intel_collect_cpu_info(struct cpu_signature *sig)
 	sig->pf = 0;
 	sig->rev = intel_get_microcode_revision();
 
-	if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) {
+	if (IFM(x86_family(sig->sig), x86_model(sig->sig)) >= INTEL_PENTIUM_III_DESCHUTES) {
 		unsigned int val[2];
 
 		/* get processor flags from MSR 0x17 */
@@ -320,7 +320,7 @@ static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
 	}
 
 	/* write microcode via MSR 0x79 */
-	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+	native_wrmsrq(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
 	rev = intel_get_microcode_revision();
 	if (rev != mc->hdr.rev)
@@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void)
 	if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
 		return 0;
 
-	if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
 	uci.mc = get_microcode_blob(&uci, true);
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 21776c529fa9..50a9702ae4e2 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -94,20 +94,17 @@ static inline unsigned int x86_cpuid_family(void)
 	return x86_family(eax);
 }
 
-extern bool dis_ucode_ldr;
 extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
 void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
-int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
 static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
 static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
 static inline void exit_amd_microcode(void) { }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index f285757618fc..c78f860419d6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,11 +30,10 @@
 #include <asm/reboot.h>
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
 #include <asm/svm.h>
 
-/* Is Linux running as the root partition? */
-bool hv_root_partition;
 /* Is Linux running on nested Microsoft Hypervisor */
 bool hv_nested;
 struct ms_hyperv_info ms_hyperv;
@@ -72,7 +71,7 @@ u64 hv_get_non_nested_msr(unsigned int reg)
 	if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
 		hv_ivm_msr_read(reg, &value);
 	else
-		rdmsrl(reg, value);
+		rdmsrq(reg, value);
 	return value;
 }
 EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
@@ -84,9 +83,9 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value)
 
 		/* Write proxy bit via wrmsl instruction */
 		if (hv_is_sint_msr(reg))
-			wrmsrl(reg, value | 1 << 20);
+			wrmsrq(reg, value | 1 << 20);
 	} else {
-		wrmsrl(reg, value);
+		wrmsrq(reg, value);
 	}
 }
 EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
@@ -109,6 +108,7 @@ void hv_set_msr(unsigned int reg, u64 value)
 }
 EXPORT_SYMBOL_GPL(hv_set_msr);
 
+static void (*mshv_handler)(void);
 static void (*vmbus_handler)(void);
 static void (*hv_stimer0_handler)(void);
 static void (*hv_kexec_handler)(void);
@@ -119,6 +119,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	inc_irq_stat(irq_hv_callback_count);
+	if (mshv_handler)
+		mshv_handler();
+
 	if (vmbus_handler)
 		vmbus_handler();
 
@@ -128,6 +131,11 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
+void hv_setup_mshv_handler(void (*handler)(void))
+{
+	mshv_handler = handler;
+}
+
 void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;
@@ -338,7 +346,7 @@ static unsigned long hv_get_tsc_khz(void)
 {
 	unsigned long freq;
 
-	rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+	rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
 
 	return freq / 1000;
 }
@@ -422,6 +430,7 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
 
 static void __init ms_hyperv_init_platform(void)
 {
@@ -436,13 +445,15 @@ static void __init ms_hyperv_init_platform(void)
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
 	ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES);
+	ms_hyperv.ext_features = cpuid_ecx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
 	hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS);
 
-	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
-		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+	pr_info("Hyper-V: privilege flags low %#x, high %#x, ext %#x, hints %#x, misc %#x\n",
+		ms_hyperv.features, ms_hyperv.priv_high,
+		ms_hyperv.ext_features, ms_hyperv.hints,
 		ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -451,25 +462,7 @@ static void __init ms_hyperv_init_platform(void)
 	pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
 		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
 
-	/*
-	 * Check CPU management privilege.
-	 *
-	 * To mirror what Windows does we should extract CPU management
-	 * features and use the ReservedIdentityBit to detect if Linux is the
-	 * root partition. But that requires negotiating CPU management
-	 * interface (a process to be finalized). For now, use the privilege
-	 * flag as the indicator for running as root.
-	 *
-	 * Hyper-V should never specify running as root and as a Confidential
-	 * VM. But to protect against a compromised/malicious Hyper-V trying
-	 * to exploit root behavior to expose Confidential VM memory, ignore
-	 * the root partition setting if also a Confidential VM.
-	 */
-	if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) &&
-	    !(ms_hyperv.priv_high & HV_ISOLATION)) {
-		hv_root_partition = true;
-		pr_info("Hyper-V: running as root partition\n");
-	}
+	hv_identify_partition_type();
 
 	if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) {
 		hv_nested = true;
@@ -549,7 +542,7 @@ static void __init ms_hyperv_init_platform(void)
 		 */
 		u64	hv_lapic_frequency;
 
-		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
+		rdmsrq(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
 		lapic_timer_period = hv_lapic_frequency;
 		pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
@@ -582,7 +575,7 @@ static void __init ms_hyperv_init_platform(void)
 		 * setting of this MSR bit should happen before init_intel()
 		 * is called.
 		 */
-		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
+		wrmsrq(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 	}
 
@@ -618,7 +611,7 @@ static void __init ms_hyperv_init_platform(void)
 
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
-	if (hv_root_partition ||
+	if (hv_root_partition() ||
 	    (!ms_hyperv.paravisor_present && hv_isolation_type_snp()))
 		smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus;
 # endif
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 2fdfda2b60e4..8c18327eb10b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -9,9 +9,11 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/cc_platform.h>
+#include <linux/string_choices.h>
 #include <asm/processor-flags.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
 #include <asm/tlbflush.h>
@@ -591,7 +593,7 @@ static void get_fixed_ranges(mtrr_type *frs)
 
 void mtrr_save_fixed_ranges(void *info)
 {
-	if (boot_cpu_has(X86_FEATURE_MTRR))
+	if (mtrr_state.have_fixed)
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 }
 
@@ -646,10 +648,10 @@ static void __init print_mtrr_state(void)
 	pr_info("MTRR default type: %s\n",
 		mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
-		pr_info("MTRR fixed ranges %sabled:\n",
-			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
-			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
-			 "en" : "dis");
+		pr_info("MTRR fixed ranges %s:\n",
+			str_enabled_disabled(
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)));
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -661,8 +663,8 @@ static void __init print_mtrr_state(void)
 		/* tail */
 		print_fixed_last();
 	}
-	pr_info("MTRR variable ranges %sabled:\n",
-		mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
+	pr_info("MTRR variable ranges %s:\n",
+		str_enabled_disabled(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED));
 	high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {
@@ -1025,8 +1027,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size,
 	 * For Intel PPro stepping <= 7
 	 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF
 	 */
-	if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model == 1 &&
+	if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO &&
 	    boot_cpu_data.x86_stepping <= 7) {
 		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
 			pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index a5c506f6da7f..4049235b1bfe 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -99,7 +99,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	char *ptr;
 	char line[LINE_SIZE];
 	int length;
-	size_t linelen;
 
 	memset(line, 0, LINE_SIZE);
 
@@ -108,9 +107,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	if (length < 0)
 		return length;
 
-	linelen = strlen(line);
-	ptr = line + linelen - 1;
-	if (linelen && *ptr == '\n')
+	ptr = line + length - 1;
+	if (length && *ptr == '\n')
 		*ptr = '\0';
 
 	if (!strncmp(line, "disable=", 8)) {
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 41ed01f46bd9..6571d432cbe3 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -86,9 +86,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
 	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = arch_freq_get_on_cpu(cpu);
+		int freq = arch_freq_get_on_cpu(cpu);
 
-		seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000));
+		if (freq < 0)
+			seq_puts(m, "cpu MHz\t\t: Unknown\n");
+		else
+			seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000));
 	}
 
 	/* Cache size */
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 4a06c37b9cf1..d8a04b195da2 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -1,4 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= ctrlmondata.o
+obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
+
+# To allow define_trace.h's recursive include:
 CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 3d1735ed8d1f..7109cbfcad4f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,6 +22,7 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/cpu_device_id.h>
+#include <asm/msr.h>
 #include <asm/resctrl.h>
 #include "internal.h"
 
@@ -44,12 +45,6 @@ static DEFINE_MUTEX(domain_list_lock);
 DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 /*
- * Used to store the max resource name width and max resource data width
- * to display the schemata in a tabular format
- */
-int max_name_width, max_data_width;
-
-/*
  * Global boolean for rdt_alloc which is true if any
  * resource allocation is enabled.
  */
@@ -62,19 +57,16 @@ static void mba_wrmsr_amd(struct msr_param *m);
 #define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)
 #define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains)
 
-struct rdt_hw_resource rdt_resources_all[] = {
+struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_L3] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.mon_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L3),
 			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),
-			.parse_ctrlval		= parse_cbm,
-			.format_str		= "%d=%0*x",
-			.fflags			= RFTYPE_RES_CACHE,
+			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
 		},
 		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -82,13 +74,10 @@ struct rdt_hw_resource rdt_resources_all[] = {
 	[RDT_RESOURCE_L2] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
 			.ctrl_scope		= RESCTRL_L2_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
-			.parse_ctrlval		= parse_cbm,
-			.format_str		= "%d=%0*x",
-			.fflags			= RFTYPE_RES_CACHE,
+			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
 		},
 		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -96,25 +85,19 @@ struct rdt_hw_resource rdt_resources_all[] = {
 	[RDT_RESOURCE_MBA] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_MBA,
 			.name			= "MB",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
-			.parse_ctrlval		= parse_bw,
-			.format_str		= "%d=%*u",
-			.fflags			= RFTYPE_RES_MB,
+			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
 		},
 	},
 	[RDT_RESOURCE_SMBA] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_SMBA,
 			.name			= "SMBA",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
-			.parse_ctrlval		= parse_bw,
-			.format_str		= "%d=%*u",
-			.fflags			= RFTYPE_RES_MB,
+			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
 		},
 	},
 };
@@ -127,6 +110,14 @@ u32 resctrl_arch_system_num_rmid_idx(void)
 	return r->num_rmid;
 }
 
+struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l)
+{
+	if (l >= RDT_NUM_RESOURCES)
+		return NULL;
+
+	return &rdt_resources_all[l].r_resctrl;
+}
+
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
  * as they do not have CPUID enumeration support for Cache allocation.
@@ -151,17 +142,16 @@ static inline void cache_alloc_hsw_probe(void)
 	struct rdt_resource *r  = &hw_res->r_resctrl;
 	u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0;
 
-	if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
+	if (wrmsrq_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
 		return;
 
-	rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
+	rdmsrq(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
 
 	/* If all the bits were set in MSR, return success */
 	if (l3_cbm_0 != max_cbm)
 		return;
 
 	hw_res->num_closid = 4;
-	r->default_ctrl = max_cbm;
 	r->cache.cbm_len = 20;
 	r->cache.shareable_bits = 0xc0000;
 	r->cache.min_cbm_bits = 2;
@@ -171,21 +161,6 @@ static inline void cache_alloc_hsw_probe(void)
 	rdt_alloc_capable = true;
 }
 
-bool is_mba_sc(struct rdt_resource *r)
-{
-	if (!r)
-		return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc;
-
-	/*
-	 * The software controller support is only applicable to MBA resource.
-	 * Make sure to check for resource type.
-	 */
-	if (r->rid != RDT_RESOURCE_MBA)
-		return false;
-
-	return r->membw.mba_sc;
-}
-
 /*
  * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
  * exposed to user interface and the h/w understandable delay values.
@@ -217,7 +192,7 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
 	hw_res->num_closid = edx.split.cos_max + 1;
 	max_delay = eax.split.max_delay + 1;
-	r->default_ctrl = MAX_MBA_BW;
+	r->membw.max_bw = MAX_MBA_BW;
 	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
@@ -228,16 +203,12 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 			return false;
 		r->membw.arch_needs_linear = false;
 	}
-	r->data_width = 3;
 
 	if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA))
 		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
 	else
 		r->membw.throttle_mode = THREAD_THROTTLE_MAX;
 
-	resctrl_file_fflags_init("thread_throttle_mode",
-				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
-
 	r->alloc_capable = true;
 
 	return true;
@@ -256,7 +227,7 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 
 	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
 	hw_res->num_closid = edx + 1;
-	r->default_ctrl = 1 << eax;
+	r->membw.max_bw = 1 << eax;
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
@@ -269,8 +240,6 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED;
 	r->membw.min_bw = 0;
 	r->membw.bw_gran = 1;
-	/* Max value is 2048, Data width should be 4 in decimal */
-	r->data_width = 4;
 
 	r->alloc_capable = true;
 
@@ -283,14 +252,13 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 	union cpuid_0x10_1_eax eax;
 	union cpuid_0x10_x_ecx ecx;
 	union cpuid_0x10_x_edx edx;
-	u32 ebx;
+	u32 ebx, default_ctrl;
 
 	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full);
 	hw_res->num_closid = edx.split.cos_max + 1;
 	r->cache.cbm_len = eax.split.cbm_len + 1;
-	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
-	r->cache.shareable_bits = ebx & r->default_ctrl;
-	r->data_width = (r->cache.cbm_len + 3) / 4;
+	default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->cache.shareable_bits = ebx & default_ctrl;
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;
 	r->alloc_capable = true;
@@ -323,7 +291,7 @@ static void mba_wrmsr_amd(struct msr_param *m)
 	unsigned int i;
 
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
+		wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
 }
 
 /*
@@ -337,7 +305,7 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 		return MAX_MBA_BW - bw;
 
 	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
-	return r->default_ctrl;
+	return MAX_MBA_BW;
 }
 
 static void mba_wrmsr_intel(struct msr_param *m)
@@ -348,7 +316,7 @@ static void mba_wrmsr_intel(struct msr_param *m)
 
 	/*  Write the delay values for mba. */
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
+		wrmsrq(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
 }
 
 static void cat_wrmsr(struct msr_param *m)
@@ -358,37 +326,7 @@ static void cat_wrmsr(struct msr_param *m)
 	unsigned int i;
 
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
-}
-
-struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r)
-{
-	struct rdt_ctrl_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
-}
-
-struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r)
-{
-	struct rdt_mon_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
+		wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
 }
 
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
@@ -405,36 +343,6 @@ void rdt_ctrl_update(void *arg)
 	hw_res->msr_update(m);
 }
 
-/*
- * rdt_find_domain - Search for a domain id in a resource domain list.
- *
- * Search the domain list to find the domain id. If the domain id is
- * found, return the domain. NULL otherwise.  If the domain id is not
- * found (and NULL returned) then the first domain with id bigger than
- * the input id can be returned to the caller via @pos.
- */
-struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
-				       struct list_head **pos)
-{
-	struct rdt_domain_hdr *d;
-	struct list_head *l;
-
-	list_for_each(l, h) {
-		d = list_entry(l, struct rdt_domain_hdr, list);
-		/* When id is found, return its domain. */
-		if (id == d->id)
-			return d;
-		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
-			break;
-	}
-
-	if (pos)
-		*pos = l;
-
-	return NULL;
-}
-
 static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
@@ -446,7 +354,7 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
 	 * For Memory Allocation: Set b/w requested to 100%
 	 */
 	for (i = 0; i < hw_res->num_closid; i++, dc++)
-		*dc = r->default_ctrl;
+		*dc = resctrl_get_default_ctrl(r);
 }
 
 static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
@@ -494,13 +402,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
 	size_t tsize;
 
-	if (is_mbm_total_enabled()) {
+	if (resctrl_arch_is_mbm_total_enabled()) {
 		tsize = sizeof(*hw_dom->arch_mbm_total);
 		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_total)
 			return -ENOMEM;
 	}
-	if (is_mbm_local_enabled()) {
+	if (resctrl_arch_is_mbm_local_enabled()) {
 		tsize = sizeof(*hw_dom->arch_mbm_local);
 		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_local) {
@@ -545,7 +453,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos);
+	hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos);
 	if (hdr) {
 		if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
 			return;
@@ -600,7 +508,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->mon_domains, id, &add_pos);
+	hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos);
 	if (hdr) {
 		if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
 			return;
@@ -665,7 +573,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->ctrl_domains, id, NULL);
+	hdr = resctrl_find_domain(&r->ctrl_domains, id, NULL);
 	if (!hdr) {
 		pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n",
 			id, cpu, r->name);
@@ -711,7 +619,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->mon_domains, id, NULL);
+	hdr = resctrl_find_domain(&r->mon_domains, id, NULL);
 	if (!hdr) {
 		pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n",
 			id, cpu, r->name);
@@ -786,20 +694,6 @@ static int resctrl_arch_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-/*
- * Choose a width for the resource name and resource data based on the
- * resource that has widest name and cbm.
- */
-static __init void rdt_init_padding(void)
-{
-	struct rdt_resource *r;
-
-	for_each_alloc_capable_rdt_resource(r) {
-		if (r->data_width > max_data_width)
-			max_data_width = r->data_width;
-	}
-}
-
 enum {
 	RDT_FLAG_CMT,
 	RDT_FLAG_MBM_TOTAL,
@@ -825,7 +719,7 @@ struct rdt_options {
 	bool	force_off, force_on;
 };
 
-static struct rdt_options rdt_options[]  __initdata = {
+static struct rdt_options rdt_options[]  __ro_after_init = {
 	RDT_OPT(RDT_FLAG_CMT,	    "cmt",	X86_FEATURE_CQM_OCCUP_LLC),
 	RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL),
 	RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL),
@@ -865,7 +759,7 @@ static int __init set_rdt_options(char *str)
 }
 __setup("rdt", set_rdt_options);
 
-bool __init rdt_cpu_has(int flag)
+bool rdt_cpu_has(int flag)
 {
 	bool ret = boot_cpu_has(flag);
 	struct rdt_options *o;
@@ -885,6 +779,21 @@ bool __init rdt_cpu_has(int flag)
 	return ret;
 }
 
+bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
+{
+	if (!rdt_cpu_has(X86_FEATURE_BMEC))
+		return false;
+
+	switch (evt) {
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		return rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL);
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL);
+	default:
+		return false;
+	}
+}
+
 static __init bool get_mem_config(void)
 {
 	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA];
@@ -963,11 +872,6 @@ static __init bool get_rdt_mon_resources(void)
 	if (!rdt_mon_features)
 		return false;
 
-	if (is_mbm_local_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (is_mbm_total_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-
 	return !rdt_get_mon_l3_config(r);
 }
 
@@ -1086,10 +990,14 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 	}
 }
 
-static int __init resctrl_late_init(void)
+static int __init resctrl_arch_late_init(void)
 {
 	struct rdt_resource *r;
-	int state, ret;
+	int state, ret, i;
+
+	/* for_each_rdt_resource() requires all rid to be initialised. */
+	for (i = 0; i < RDT_NUM_RESOURCES; i++)
+		rdt_resources_all[i].r_resctrl.rid = i;
 
 	/*
 	 * Initialize functions(or definitions) that are different
@@ -1102,8 +1010,6 @@ static int __init resctrl_late_init(void)
 	if (!get_rdt_resources())
 		return -ENODEV;
 
-	rdt_init_padding();
-
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
 				  resctrl_arch_online_cpu,
@@ -1111,7 +1017,7 @@ static int __init resctrl_late_init(void)
 	if (state < 0)
 		return state;
 
-	ret = rdtgroup_init();
+	ret = resctrl_init();
 	if (ret) {
 		cpuhp_remove_state(state);
 		return ret;
@@ -1127,18 +1033,13 @@ static int __init resctrl_late_init(void)
 	return 0;
 }
 
-late_initcall(resctrl_late_init);
+late_initcall(resctrl_arch_late_init);
 
-static void __exit resctrl_exit(void)
+static void __exit resctrl_arch_exit(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-
 	cpuhp_remove_state(rdt_online);
 
-	rdtgroup_exit();
-
-	if (r->mon_capable)
-		rdt_put_mon_l3_config();
+	resctrl_exit();
 }
 
-__exitcall(resctrl_exit);
+__exitcall(resctrl_arch_exit);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 536351159cc2..1189c0df4ad7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -16,273 +16,15 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/cpu.h>
-#include <linux/kernfs.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
 
 #include "internal.h"
 
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and max bandwidth values specified by the
- * hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
-	int ret;
-	u32 bw;
-
-	/*
-	 * Only linear delay values is supported for current Intel SKUs.
-	 */
-	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
-		rdt_last_cmd_puts("No support for non-linear MB domains\n");
-		return false;
-	}
-
-	ret = kstrtou32(buf, 10, &bw);
-	if (ret) {
-		rdt_last_cmd_printf("Invalid MB value %s\n", buf);
-		return false;
-	}
-
-	/* Nothing else to do if software controller is enabled. */
-	if (is_mba_sc(r)) {
-		*data = bw;
-		return true;
-	}
-
-	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
-		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
-				    bw, r->membw.min_bw, r->default_ctrl);
-		return false;
-	}
-
-	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
-	return true;
-}
-
-int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_ctrl_domain *d)
-{
-	struct resctrl_staged_config *cfg;
-	u32 closid = data->rdtgrp->closid;
-	struct rdt_resource *r = s->res;
-	u32 bw_val;
-
-	cfg = &d->staged_config[s->conf_type];
-	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
-		return -EINVAL;
-	}
-
-	if (!bw_validate(data->buf, &bw_val, r))
-		return -EINVAL;
-
-	if (is_mba_sc(r)) {
-		d->mbps_val[closid] = bw_val;
-		return 0;
-	}
-
-	cfg->new_ctrl = bw_val;
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * Check whether a cache bit mask is valid.
- * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
- *   - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
- *   - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
- *
- * Haswell does not support a non-contiguous 1s value and additionally
- * requires at least two bits set.
- * AMD allows non-contiguous bitmasks.
- */
-static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
-	unsigned long first_bit, zero_bit, val;
-	unsigned int cbm_len = r->cache.cbm_len;
-	int ret;
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret) {
-		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
-		return false;
-	}
-
-	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > r->default_ctrl) {
-		rdt_last_cmd_puts("Mask out of range\n");
-		return false;
-	}
-
-	first_bit = find_first_bit(&val, cbm_len);
-	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
-	/* Are non-contiguous bitmasks allowed? */
-	if (!r->cache.arch_has_sparse_bitmasks &&
-	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
-		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
-		return false;
-	}
-
-	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
-				    r->cache.min_cbm_bits);
-		return false;
-	}
-
-	*data = val;
-	return true;
-}
-
-/*
- * Read one cache bit mask (hex). Check that it is valid for the current
- * resource type.
- */
-int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_ctrl_domain *d)
-{
-	struct rdtgroup *rdtgrp = data->rdtgrp;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	u32 cbm_val;
-
-	cfg = &d->staged_config[s->conf_type];
-	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
-		return -EINVAL;
-	}
-
-	/*
-	 * Cannot set up more than one pseudo-locked region in a cache
-	 * hierarchy.
-	 */
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
-	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
-		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
-		return -EINVAL;
-	}
-
-	if (!cbm_validate(data->buf, &cbm_val, r))
-		return -EINVAL;
-
-	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
-	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
-		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * The CBM may not overlap with the CBM of another closid if
-	 * either is exclusive.
-	 */
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
-		rdt_last_cmd_puts("Overlaps with exclusive group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
-		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			rdt_last_cmd_puts("Overlaps with other group\n");
-			return -EINVAL;
-		}
-	}
-
-	cfg->new_ctrl = cbm_val;
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * For each domain in this resource we expect to find a series of:
- *	id=mask
- * separated by ";". The "id" is in decimal, and must match one of
- * the "id"s for this resource.
- */
-static int parse_line(char *line, struct resctrl_schema *s,
-		      struct rdtgroup *rdtgrp)
-{
-	enum resctrl_conf_type t = s->conf_type;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	struct rdt_parse_data data;
-	struct rdt_ctrl_domain *d;
-	char *dom = NULL, *id;
-	unsigned long dom_id;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
-	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
-		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
-		return -EINVAL;
-	}
-
-next:
-	if (!line || line[0] == '\0')
-		return 0;
-	dom = strsep(&line, ";");
-	id = strsep(&dom, "=");
-	if (!dom || kstrtoul(id, 10, &dom_id)) {
-		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
-		return -EINVAL;
-	}
-	dom = strim(dom);
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		if (d->hdr.id == dom_id) {
-			data.buf = dom;
-			data.rdtgrp = rdtgrp;
-			if (r->parse_ctrlval(&data, s, d))
-				return -EINVAL;
-			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
-				cfg = &d->staged_config[t];
-				/*
-				 * In pseudo-locking setup mode and just
-				 * parsed a valid CBM that should be
-				 * pseudo-locked. Only one locked region per
-				 * resource group and domain so just do
-				 * the required initialization for single
-				 * region and return.
-				 */
-				rdtgrp->plr->s = s;
-				rdtgrp->plr->d = d;
-				rdtgrp->plr->cbm = cfg->new_ctrl;
-				d->plr = rdtgrp->plr;
-				return 0;
-			}
-			goto next;
-		}
-	}
-	return -EINVAL;
-}
-
-static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
-{
-	switch (type) {
-	default:
-	case CDP_NONE:
-		return closid;
-	case CDP_CODE:
-		return closid * 2 + 1;
-	case CDP_DATA:
-		return closid * 2;
-	}
-}
-
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
 	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	u32 idx = get_config_index(closid, t);
+	u32 idx = resctrl_get_config_index(closid, t);
 	struct msr_param msr_param;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
@@ -319,7 +61,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 			if (!cfg->have_new_ctrl)
 				continue;
 
-			idx = get_config_index(closid, t);
+			idx = resctrl_get_config_index(closid, t);
 			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
 				continue;
 			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
@@ -341,357 +83,11 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	return 0;
 }
 
-static int rdtgroup_parse_resource(char *resname, char *tok,
-				   struct rdtgroup *rdtgrp)
-{
-	struct resctrl_schema *s;
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
-			return parse_line(tok, s, rdtgrp);
-	}
-	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
-	return -EINVAL;
-}
-
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off)
-{
-	struct resctrl_schema *s;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	char *tok, *resname;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	/*
-	 * No changes to pseudo-locked region allowed. It has to be removed
-	 * and re-created instead.
-	 */
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
-		goto out;
-	}
-
-	rdt_staged_configs_clear();
-
-	while ((tok = strsep(&buf, "\n")) != NULL) {
-		resname = strim(strsep(&tok, ":"));
-		if (!tok) {
-			rdt_last_cmd_puts("Missing ':'\n");
-			ret = -EINVAL;
-			goto out;
-		}
-		if (tok[0] == '\0') {
-			rdt_last_cmd_printf("Missing '%s' value\n", resname);
-			ret = -EINVAL;
-			goto out;
-		}
-		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
-		if (ret)
-			goto out;
-	}
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-
-		/*
-		 * Writes to mba_sc resources update the software controller,
-		 * not the control MSR.
-		 */
-		if (is_mba_sc(r))
-			continue;
-
-		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
-		if (ret)
-			goto out;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		/*
-		 * If pseudo-locking fails we keep the resource group in
-		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
-		 * active and updated for just the domain the pseudo-locked
-		 * region was requested for.
-		 */
-		ret = rdtgroup_pseudo_lock_create(rdtgrp);
-	}
-
-out:
-	rdt_staged_configs_clear();
-	rdtgroup_kn_unlock(of->kn);
-	return ret ?: nbytes;
-}
-
 u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type type)
 {
 	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
-	u32 idx = get_config_index(closid, type);
+	u32 idx = resctrl_get_config_index(closid, type);
 
 	return hw_dom->ctrl_val[idx];
 }
-
-static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
-{
-	struct rdt_resource *r = schema->res;
-	struct rdt_ctrl_domain *dom;
-	bool sep = false;
-	u32 ctrl_val;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
-		if (sep)
-			seq_puts(s, ";");
-
-		if (is_mba_sc(r))
-			ctrl_val = dom->mbps_val[closid];
-		else
-			ctrl_val = resctrl_arch_get_config(r, dom, closid,
-							   schema->conf_type);
-
-		seq_printf(s, r->format_str, dom->hdr.id, max_data_width,
-			   ctrl_val);
-		sep = true;
-	}
-	seq_puts(s, "\n");
-}
-
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
-			   struct seq_file *s, void *v)
-{
-	struct resctrl_schema *schema;
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-	u32 closid;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			list_for_each_entry(schema, &resctrl_schema_all, list) {
-				seq_printf(s, "%s:uninitialized\n", schema->name);
-			}
-		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			if (!rdtgrp->plr->d) {
-				rdt_last_cmd_clear();
-				rdt_last_cmd_puts("Cache domain offline\n");
-				ret = -ENODEV;
-			} else {
-				seq_printf(s, "%s:%d=%x\n",
-					   rdtgrp->plr->s->res->name,
-					   rdtgrp->plr->d->hdr.id,
-					   rdtgrp->plr->cbm);
-			}
-		} else {
-			closid = rdtgrp->closid;
-			list_for_each_entry(schema, &resctrl_schema_all, list) {
-				if (closid < schema->num_closid)
-					show_doms(s, schema, closid);
-			}
-		}
-	} else {
-		ret = -ENOENT;
-	}
-	rdtgroup_kn_unlock(of->kn);
-	return ret;
-}
-
-static int smp_mon_event_count(void *arg)
-{
-	mon_event_count(arg);
-
-	return 0;
-}
-
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
-				      char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	if (!strcmp(buf, "mbm_local_bytes")) {
-		if (is_mbm_local_enabled())
-			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-		else
-			ret = -EINVAL;
-	} else if (!strcmp(buf, "mbm_total_bytes")) {
-		if (is_mbm_total_enabled())
-			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-		else
-			ret = -EINVAL;
-	} else {
-		ret = -EINVAL;
-	}
-
-	if (ret)
-		rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
-
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret ?: nbytes;
-}
-
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
-				 struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-
-	if (rdtgrp) {
-		switch (rdtgrp->mba_mbps_event) {
-		case QOS_L3_MBM_LOCAL_EVENT_ID:
-			seq_puts(s, "mbm_local_bytes\n");
-			break;
-		case QOS_L3_MBM_TOTAL_EVENT_ID:
-			seq_puts(s, "mbm_total_bytes\n");
-			break;
-		default:
-			pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
-			ret = -EINVAL;
-			break;
-		}
-	} else {
-		ret = -ENOENT;
-	}
-
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first)
-{
-	int cpu;
-
-	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	/*
-	 * Setup the parameters to pass to mon_event_count() to read the data.
-	 */
-	rr->rgrp = rdtgrp;
-	rr->evtid = evtid;
-	rr->r = r;
-	rr->d = d;
-	rr->first = first;
-	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
-	if (IS_ERR(rr->arch_mon_ctx)) {
-		rr->err = -EINVAL;
-		return;
-	}
-
-	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
-
-	/*
-	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
-	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
-	 * MPAM's resctrl_arch_rmid_read() is unable to read the
-	 * counters on some platforms if its called in IRQ context.
-	 */
-	if (tick_nohz_full_cpu(cpu))
-		smp_call_function_any(cpumask, mon_event_count, rr, 1);
-	else
-		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
-
-	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
-}
-
-int rdtgroup_mondata_show(struct seq_file *m, void *arg)
-{
-	struct kernfs_open_file *of = m->private;
-	struct rdt_domain_hdr *hdr;
-	struct rmid_read rr = {0};
-	struct rdt_mon_domain *d;
-	u32 resid, evtid, domid;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	union mon_data_bits md;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	md.priv = of->kn->priv;
-	resid = md.u.rid;
-	domid = md.u.domid;
-	evtid = md.u.evtid;
-	r = &rdt_resources_all[resid].r_resctrl;
-
-	if (md.u.sum) {
-		/*
-		 * This file requires summing across all domains that share
-		 * the L3 cache id that was provided in the "domid" field of the
-		 * mon_data_bits union. Search all domains in the resource for
-		 * one that matches this cache id.
-		 */
-		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
-				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
-				goto checkresult;
-			}
-		}
-		ret = -ENOENT;
-		goto out;
-	} else {
-		/*
-		 * This file provides data from a single domain. Search
-		 * the resource to find the domain with "domid".
-		 */
-		hdr = rdt_find_domain(&r->mon_domains, domid, NULL);
-		if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
-			ret = -ENOENT;
-			goto out;
-		}
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
-		mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
-	}
-
-checkresult:
-
-	if (rr.err == -EIO)
-		seq_puts(m, "Error\n");
-	else if (rr.err == -EINVAL)
-		seq_puts(m, "Unavailable\n");
-	else
-		seq_printf(m, "%llu\n", rr.val);
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-	return ret;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 20c898f09b7e..5e3c41b36437 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -3,28 +3,21 @@
 #define _ASM_X86_RESCTRL_INTERNAL_H
 
 #include <linux/resctrl.h>
-#include <linux/sched.h>
-#include <linux/kernfs.h>
-#include <linux/fs_context.h>
-#include <linux/jump_label.h>
-#include <linux/tick.h>
-
-#include <asm/resctrl.h>
 
 #define L3_QOS_CDP_ENABLE		0x01ULL
 
 #define L2_QOS_CDP_ENABLE		0x01ULL
 
-#define CQM_LIMBOCHECK_INTERVAL	1000
-
 #define MBM_CNTR_WIDTH_BASE		24
-#define MBM_OVERFLOW_INTERVAL		1000
-#define MAX_MBA_BW			100u
+
 #define MBA_IS_LINEAR			0x4
+
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
+
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
+
 /*
  * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
  * data to be returned. The counter width is discovered from the hardware
@@ -32,343 +25,6 @@
  */
 #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
-/* Reads to Local DRAM Memory */
-#define READS_TO_LOCAL_MEM		BIT(0)
-
-/* Reads to Remote DRAM Memory */
-#define READS_TO_REMOTE_MEM		BIT(1)
-
-/* Non-Temporal Writes to Local Memory */
-#define NON_TEMP_WRITE_TO_LOCAL_MEM	BIT(2)
-
-/* Non-Temporal Writes to Remote Memory */
-#define NON_TEMP_WRITE_TO_REMOTE_MEM	BIT(3)
-
-/* Reads to Local Memory the system identifies as "Slow Memory" */
-#define READS_TO_LOCAL_S_MEM		BIT(4)
-
-/* Reads to Remote Memory the system identifies as "Slow Memory" */
-#define READS_TO_REMOTE_S_MEM		BIT(5)
-
-/* Dirty Victims to All Types of Memory */
-#define DIRTY_VICTIMS_TO_ALL_MEM	BIT(6)
-
-/* Max event bits supported */
-#define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
-
-/**
- * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
- *			        aren't marked nohz_full
- * @mask:	The mask to pick a CPU from.
- * @exclude_cpu:The CPU to avoid picking.
- *
- * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
- * CPUs that don't use nohz_full, these are preferred. Pass
- * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
- *
- * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
- */
-static inline unsigned int
-cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
-{
-	unsigned int cpu, hk_cpu;
-
-	if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
-		cpu = cpumask_any(mask);
-	else
-		cpu = cpumask_any_but(mask, exclude_cpu);
-
-	/* Only continue if tick_nohz_full_mask has been initialized. */
-	if (!tick_nohz_full_enabled())
-		return cpu;
-
-	/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
-	if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
-		return cpu;
-
-	/* Try to find a CPU that isn't nohz_full to use in preference */
-	hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
-	if (hk_cpu == exclude_cpu)
-		hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
-
-	if (hk_cpu < nr_cpu_ids)
-		cpu = hk_cpu;
-
-	return cpu;
-}
-
-struct rdt_fs_context {
-	struct kernfs_fs_context	kfc;
-	bool				enable_cdpl2;
-	bool				enable_cdpl3;
-	bool				enable_mba_mbps;
-	bool				enable_debug;
-};
-
-static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
-{
-	struct kernfs_fs_context *kfc = fc->fs_private;
-
-	return container_of(kfc, struct rdt_fs_context, kfc);
-}
-
-/**
- * struct mon_evt - Entry in the event list of a resource
- * @evtid:		event id
- * @name:		name of the event
- * @configurable:	true if the event is configurable
- * @list:		entry in &rdt_resource->evt_list
- */
-struct mon_evt {
-	enum resctrl_event_id	evtid;
-	char			*name;
-	bool			configurable;
-	struct list_head	list;
-};
-
-/**
- * union mon_data_bits - Monitoring details for each event file.
- * @priv:              Used to store monitoring event data in @u
- *                     as kernfs private data.
- * @u.rid:             Resource id associated with the event file.
- * @u.evtid:           Event id associated with the event file.
- * @u.sum:             Set when event must be summed across multiple
- *                     domains.
- * @u.domid:           When @u.sum is zero this is the domain to which
- *                     the event file belongs. When @sum is one this
- *                     is the id of the L3 cache that all domains to be
- *                     summed share.
- * @u:                 Name of the bit fields struct.
- */
-union mon_data_bits {
-	void *priv;
-	struct {
-		unsigned int rid		: 10;
-		enum resctrl_event_id evtid	: 7;
-		unsigned int sum		: 1;
-		unsigned int domid		: 14;
-	} u;
-};
-
-/**
- * struct rmid_read - Data passed across smp_call*() to read event count.
- * @rgrp:  Resource group for which the counter is being read. If it is a parent
- *	   resource group then its event count is summed with the count from all
- *	   its child resource groups.
- * @r:	   Resource describing the properties of the event being read.
- * @d:	   Domain that the counter should be read from. If NULL then sum all
- *	   domains in @r sharing L3 @ci.id
- * @evtid: Which monitor event to read.
- * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
- * @err:   Error encountered when reading counter.
- * @val:   Returned value of event counter. If @rgrp is a parent resource group,
- *	   @val includes the sum of event counts from its child resource groups.
- *	   If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
- *	   (summed across child resource groups if @rgrp is a parent resource group).
- * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
- */
-struct rmid_read {
-	struct rdtgroup		*rgrp;
-	struct rdt_resource	*r;
-	struct rdt_mon_domain	*d;
-	enum resctrl_event_id	evtid;
-	bool			first;
-	struct cacheinfo	*ci;
-	int			err;
-	u64			val;
-	void			*arch_mon_ctx;
-};
-
-extern unsigned int rdt_mon_features;
-extern struct list_head resctrl_schema_all;
-extern bool resctrl_mounted;
-
-enum rdt_group_type {
-	RDTCTRL_GROUP = 0,
-	RDTMON_GROUP,
-	RDT_NUM_GROUP,
-};
-
-/**
- * enum rdtgrp_mode - Mode of a RDT resource group
- * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
- * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
- * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
- * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
- *                          allowed AND the allocations are Cache Pseudo-Locked
- * @RDT_NUM_MODES: Total number of modes
- *
- * The mode of a resource group enables control over the allowed overlap
- * between allocations associated with different resource groups (classes
- * of service). User is able to modify the mode of a resource group by
- * writing to the "mode" resctrl file associated with the resource group.
- *
- * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
- * writing the appropriate text to the "mode" file. A resource group enters
- * "pseudo-locked" mode after the schemata is written while the resource
- * group is in "pseudo-locksetup" mode.
- */
-enum rdtgrp_mode {
-	RDT_MODE_SHAREABLE = 0,
-	RDT_MODE_EXCLUSIVE,
-	RDT_MODE_PSEUDO_LOCKSETUP,
-	RDT_MODE_PSEUDO_LOCKED,
-
-	/* Must be last */
-	RDT_NUM_MODES,
-};
-
-/**
- * struct mongroup - store mon group's data in resctrl fs.
- * @mon_data_kn:		kernfs node for the mon_data directory
- * @parent:			parent rdtgrp
- * @crdtgrp_list:		child rdtgroup node list
- * @rmid:			rmid for this rdtgroup
- */
-struct mongroup {
-	struct kernfs_node	*mon_data_kn;
-	struct rdtgroup		*parent;
-	struct list_head	crdtgrp_list;
-	u32			rmid;
-};
-
-/**
- * struct pseudo_lock_region - pseudo-lock region information
- * @s:			Resctrl schema for the resource to which this
- *			pseudo-locked region belongs
- * @d:			RDT domain to which this pseudo-locked region
- *			belongs
- * @cbm:		bitmask of the pseudo-locked region
- * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
- *			completion
- * @thread_done:	variable used by waitqueue to test if pseudo-locking
- *			thread completed
- * @cpu:		core associated with the cache on which the setup code
- *			will be run
- * @line_size:		size of the cache lines
- * @size:		size of pseudo-locked region in bytes
- * @kmem:		the kernel memory associated with pseudo-locked region
- * @minor:		minor number of character device associated with this
- *			region
- * @debugfs_dir:	pointer to this region's directory in the debugfs
- *			filesystem
- * @pm_reqs:		Power management QoS requests related to this region
- */
-struct pseudo_lock_region {
-	struct resctrl_schema	*s;
-	struct rdt_ctrl_domain	*d;
-	u32			cbm;
-	wait_queue_head_t	lock_thread_wq;
-	int			thread_done;
-	int			cpu;
-	unsigned int		line_size;
-	unsigned int		size;
-	void			*kmem;
-	unsigned int		minor;
-	struct dentry		*debugfs_dir;
-	struct list_head	pm_reqs;
-};
-
-/**
- * struct rdtgroup - store rdtgroup's data in resctrl file system.
- * @kn:				kernfs node
- * @rdtgroup_list:		linked list for all rdtgroups
- * @closid:			closid for this rdtgroup
- * @cpu_mask:			CPUs assigned to this rdtgroup
- * @flags:			status bits
- * @waitcount:			how many cpus expect to find this
- *				group when they acquire rdtgroup_mutex
- * @type:			indicates type of this rdtgroup - either
- *				monitor only or ctrl_mon group
- * @mon:			mongroup related data
- * @mode:			mode of resource group
- * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
- * @plr:			pseudo-locked region
- */
-struct rdtgroup {
-	struct kernfs_node		*kn;
-	struct list_head		rdtgroup_list;
-	u32				closid;
-	struct cpumask			cpu_mask;
-	int				flags;
-	atomic_t			waitcount;
-	enum rdt_group_type		type;
-	struct mongroup			mon;
-	enum rdtgrp_mode		mode;
-	enum resctrl_event_id		mba_mbps_event;
-	struct pseudo_lock_region	*plr;
-};
-
-/* rdtgroup.flags */
-#define	RDT_DELETED		1
-
-/* rftype.flags */
-#define RFTYPE_FLAGS_CPUS_LIST	1
-
-/*
- * Define the file type flags for base and info directories.
- */
-#define RFTYPE_INFO			BIT(0)
-#define RFTYPE_BASE			BIT(1)
-#define RFTYPE_CTRL			BIT(4)
-#define RFTYPE_MON			BIT(5)
-#define RFTYPE_TOP			BIT(6)
-#define RFTYPE_RES_CACHE		BIT(8)
-#define RFTYPE_RES_MB			BIT(9)
-#define RFTYPE_DEBUG			BIT(10)
-#define RFTYPE_CTRL_INFO		(RFTYPE_INFO | RFTYPE_CTRL)
-#define RFTYPE_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
-#define RFTYPE_TOP_INFO			(RFTYPE_INFO | RFTYPE_TOP)
-#define RFTYPE_CTRL_BASE		(RFTYPE_BASE | RFTYPE_CTRL)
-#define RFTYPE_MON_BASE			(RFTYPE_BASE | RFTYPE_MON)
-
-/* List of all resource groups */
-extern struct list_head rdt_all_groups;
-
-extern int max_name_width, max_data_width;
-
-int __init rdtgroup_init(void);
-void __exit rdtgroup_exit(void);
-
-/**
- * struct rftype - describe each file in the resctrl file system
- * @name:	File name
- * @mode:	Access mode
- * @kf_ops:	File operations
- * @flags:	File specific RFTYPE_FLAGS_* flags
- * @fflags:	File specific RFTYPE_* flags
- * @seq_show:	Show content of the file
- * @write:	Write to the file
- */
-struct rftype {
-	char			*name;
-	umode_t			mode;
-	const struct kernfs_ops	*kf_ops;
-	unsigned long		flags;
-	unsigned long		fflags;
-
-	int (*seq_show)(struct kernfs_open_file *of,
-			struct seq_file *sf, void *v);
-	/*
-	 * write() is the generic write callback which maps directly to
-	 * kernfs write operation and overrides all other operations.
-	 * Maximum write size is determined by ->max_write_len.
-	 */
-	ssize_t (*write)(struct kernfs_open_file *of,
-			 char *buf, size_t nbytes, loff_t off);
-};
-
-/**
- * struct mbm_state - status for each MBM counter in each domain
- * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
- * @prev_bw:	The most recent bandwidth in MBps
- */
-struct mbm_state {
-	u64	prev_bw_bytes;
-	u32	prev_bw;
-};
-
 /**
  * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s
  *			   return value.
@@ -433,37 +89,6 @@ struct msr_param {
 	u32			high;
 };
 
-static inline bool is_llc_occupancy_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
-}
-
-static inline bool is_mbm_total_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
-}
-
-static inline bool is_mbm_local_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
-}
-
-static inline bool is_mbm_enabled(void)
-{
-	return (is_mbm_total_enabled() || is_mbm_local_enabled());
-}
-
-static inline bool is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-struct rdt_parse_data {
-	struct rdtgroup		*rdtgrp;
-	char			*buf;
-};
-
 /**
  * struct rdt_hw_resource - arch private attributes of a resctrl resource
  * @r_resctrl:		Attributes of the resource used directly by resctrl.
@@ -476,8 +101,6 @@ struct rdt_parse_data {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
- * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
- *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -491,7 +114,6 @@ struct rdt_hw_resource {
 	void			(*msr_update)(struct msr_param *m);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
-	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
@@ -500,66 +122,10 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 	return container_of(r, struct rdt_hw_resource, r_resctrl);
 }
 
-int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_ctrl_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_ctrl_domain *d);
-
-extern struct mutex rdtgroup_mutex;
-
 extern struct rdt_hw_resource rdt_resources_all[];
-extern struct rdtgroup rdtgroup_default;
-extern struct dentry *debugfs_resctrl;
-extern enum resctrl_event_id mba_mbps_default_event;
-
-enum resctrl_res_level {
-	RDT_RESOURCE_L3,
-	RDT_RESOURCE_L2,
-	RDT_RESOURCE_MBA,
-	RDT_RESOURCE_SMBA,
-
-	/* Must be the last */
-	RDT_NUM_RESOURCES,
-};
-
-static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
-
-	hw_res++;
-	return &hw_res->r_resctrl;
-}
-
-static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
-{
-	return rdt_resources_all[l].cdp_enabled;
-}
-
-int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 
 void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
 
-/*
- * To return the common struct rdt_resource, which is contained in struct
- * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
- */
-#define for_each_rdt_resource(r)					      \
-	for (r = &rdt_resources_all[0].r_resctrl;			      \
-	     r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl;	      \
-	     r = resctrl_inc(r))
-
-#define for_each_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable || r->mon_capable)
-
-#define for_each_alloc_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable)
-
-#define for_each_mon_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->mon_capable)
-
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
 	struct {
@@ -593,69 +159,14 @@ union cpuid_0x10_x_edx {
 	unsigned int full;
 };
 
-void rdt_last_cmd_clear(void);
-void rdt_last_cmd_puts(const char *s);
-__printf(1, 2)
-void rdt_last_cmd_printf(const char *fmt, ...);
-
 void rdt_ctrl_update(void *arg);
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
-void rdtgroup_kn_unlock(struct kernfs_node *kn);
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
-			     umode_t mask);
-struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
-				       struct list_head **pos);
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off);
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
-			   struct seq_file *s, void *v);
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
-				      char *buf, size_t nbytes, loff_t off);
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
-				 struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
-			   unsigned long cbm, int closid, bool exclusive);
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
-				  unsigned long cbm);
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
-int rdtgroup_tasks_assigned(struct rdtgroup *r);
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
-int rdt_pseudo_lock_init(void);
-void rdt_pseudo_lock_release(void);
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
-struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r);
-int closids_supported(void);
-void closid_free(int closid);
-int alloc_rmid(u32 closid);
-void free_rmid(u32 closid, u32 rmid);
+
 int rdt_get_mon_l3_config(struct rdt_resource *r);
-void __exit rdt_put_mon_l3_config(void);
-bool __init rdt_cpu_has(int flag);
-void mon_event_count(void *info);
-int rdtgroup_mondata_show(struct seq_file *m, void *arg);
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first);
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
-				unsigned long delay_ms,
-				int exclude_cpu);
-void mbm_handle_overflow(struct work_struct *work);
+
+bool rdt_cpu_has(int flag);
+
 void __init intel_rdt_mbm_apply_quirk(void);
-bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-			     int exclude_cpu);
-void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_mon_domain *d);
-void __check_limbo(struct rdt_mon_domain *d, bool force_free);
+
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void resctrl_file_fflags_init(const char *config, unsigned long fflags);
-void rdt_staged_configs_clear(void);
-bool closid_allocated(unsigned int closid);
-int resctrl_find_cleanest_closid(void);
+
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 94a1d9780461..c261558276cd 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -18,62 +18,12 @@
 #define pr_fmt(fmt)	"resctrl: " fmt
 
 #include <linux/cpu.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <linux/slab.h>
+#include <linux/resctrl.h>
 
 #include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 
 #include "internal.h"
-#include "trace.h"
-
-/**
- * struct rmid_entry - dirty tracking for all RMID.
- * @closid:	The CLOSID for this entry.
- * @rmid:	The RMID for this entry.
- * @busy:	The number of domains with cached data using this RMID.
- * @list:	Member of the rmid_free_lru list when busy == 0.
- *
- * Depending on the architecture the correct monitor is accessed using
- * both @closid and @rmid, or @rmid only.
- *
- * Take the rdtgroup_mutex when accessing.
- */
-struct rmid_entry {
-	u32				closid;
-	u32				rmid;
-	int				busy;
-	struct list_head		list;
-};
-
-/*
- * @rmid_free_lru - A least recently used list of free RMIDs
- *     These RMIDs are guaranteed to have an occupancy less than the
- *     threshold occupancy
- */
-static LIST_HEAD(rmid_free_lru);
-
-/*
- * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
- *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
- *     Indexed by CLOSID. Protected by rdtgroup_mutex.
- */
-static u32 *closid_num_dirty_rmid;
-
-/*
- * @rmid_limbo_count - count of currently unused but (potentially)
- *     dirty RMIDs.
- *     This counts RMIDs that no one is currently using but that
- *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
- *     change the threshold occupancy value.
- */
-static unsigned int rmid_limbo_count;
-
-/*
- * @rmid_entry - The entry in the limbo and free lists.
- */
-static struct rmid_entry	*rmid_ptrs;
 
 /*
  * Global boolean for rdt_monitor which is true if any
@@ -86,23 +36,12 @@ bool rdt_mon_capable;
  */
 unsigned int rdt_mon_features;
 
-/*
- * This is the threshold cache occupancy in bytes at which we will consider an
- * RMID available for re-allocation.
- */
-unsigned int resctrl_rmid_realloc_threshold;
-
-/*
- * This is the maximum value for the reallocation threshold, in bytes.
- */
-unsigned int resctrl_rmid_realloc_limit;
-
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
 static int snc_nodes_per_l3_cache = 1;
 
 /*
- * The correction factor table is documented in Documentation/arch/x86/resctrl.rst.
+ * The correction factor table is documented in Documentation/filesystems/resctrl.rst.
  * If rmid > rmid threshold, MBM total and local values should be multiplied
  * by the correction factor.
  *
@@ -151,6 +90,7 @@ static const struct mbm_correction_factor_table {
 };
 
 static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX;
+
 static u64 mbm_cf __read_mostly;
 
 static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
@@ -163,33 +103,6 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
 }
 
 /*
- * x86 and arm64 differ in their handling of monitoring.
- * x86's RMID are independent numbers, there is only one source of traffic
- * with an RMID value of '1'.
- * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
- * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
- * value is no longer unique.
- * To account for this, resctrl uses an index. On x86 this is just the RMID,
- * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
- *
- * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
- * must accept an attempt to read every index.
- */
-static inline struct rmid_entry *__rmid_entry(u32 idx)
-{
-	struct rmid_entry *entry;
-	u32 closid, rmid;
-
-	entry = &rmid_ptrs[idx];
-	resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
-
-	WARN_ON_ONCE(entry->closid != closid);
-	WARN_ON_ONCE(entry->rmid != rmid);
-
-	return entry;
-}
-
-/*
  * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by
  * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is
  * needed. The physical RMID is the same as the logical RMID.
@@ -238,7 +151,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
 	 * are error bits.
 	 */
 	wrmsr(MSR_IA32_QM_EVTSEL, eventid, prmid);
-	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+	rdmsrq(MSR_IA32_QM_CTR, msr_val);
 
 	if (msr_val & RMID_VAL_ERROR)
 		return -EIO;
@@ -260,12 +173,11 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 		return &hw_dom->arch_mbm_total[rmid];
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
 		return &hw_dom->arch_mbm_local[rmid];
+	default:
+		/* Never expect to get here */
+		WARN_ON_ONCE(1);
+		return NULL;
 	}
-
-	/* Never expect to get here */
-	WARN_ON_ONCE(1);
-
-	return NULL;
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
@@ -295,11 +207,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
-	if (is_mbm_total_enabled())
+	if (resctrl_arch_is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
 		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
 
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		memset(hw_dom->arch_mbm_local, 0,
 		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
 }
@@ -346,749 +258,6 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 	return 0;
 }
 
-static void limbo_release_entry(struct rmid_entry *entry)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	rmid_limbo_count--;
-	list_add_tail(&entry->list, &rmid_free_lru);
-
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		closid_num_dirty_rmid[entry->closid]--;
-}
-
-/*
- * Check the RMIDs that are marked as busy for this domain. If the
- * reported LLC occupancy is below the threshold clear the busy bit and
- * decrement the count. If the busy count gets to zero on an RMID, we
- * free the RMID
- */
-void __check_limbo(struct rdt_mon_domain *d, bool force_free)
-{
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	struct rmid_entry *entry;
-	u32 idx, cur_idx = 1;
-	void *arch_mon_ctx;
-	bool rmid_dirty;
-	u64 val = 0;
-
-	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
-	if (IS_ERR(arch_mon_ctx)) {
-		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-				    PTR_ERR(arch_mon_ctx));
-		return;
-	}
-
-	/*
-	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
-	 * are marked as busy for occupancy < threshold. If the occupancy
-	 * is less than the threshold decrement the busy counter of the
-	 * RMID and move it to the free list when the counter reaches 0.
-	 */
-	for (;;) {
-		idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
-		if (idx >= idx_limit)
-			break;
-
-		entry = __rmid_entry(idx);
-		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val,
-					   arch_mon_ctx)) {
-			rmid_dirty = true;
-		} else {
-			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
-
-			/*
-			 * x86's CLOSID and RMID are independent numbers, so the entry's
-			 * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
-			 * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
-			 * used to select the configuration. It is thus necessary to track both
-			 * CLOSID and RMID because there may be dependencies between them
-			 * on some architectures.
-			 */
-			trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
-		}
-
-		if (force_free || !rmid_dirty) {
-			clear_bit(idx, d->rmid_busy_llc);
-			if (!--entry->busy)
-				limbo_release_entry(entry);
-		}
-		cur_idx = idx + 1;
-	}
-
-	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
-}
-
-bool has_busy_rmid(struct rdt_mon_domain *d)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-
-	return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
-}
-
-static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
-{
-	struct rmid_entry *itr;
-	u32 itr_idx, cmp_idx;
-
-	if (list_empty(&rmid_free_lru))
-		return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
-
-	list_for_each_entry(itr, &rmid_free_lru, list) {
-		/*
-		 * Get the index of this free RMID, and the index it would need
-		 * to be if it were used with this CLOSID.
-		 * If the CLOSID is irrelevant on this architecture, the two
-		 * index values are always the same on every entry and thus the
-		 * very first entry will be returned.
-		 */
-		itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
-		cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
-
-		if (itr_idx == cmp_idx)
-			return itr;
-	}
-
-	return ERR_PTR(-ENOSPC);
-}
-
-/**
- * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
- *                                  RMID are clean, or the CLOSID that has
- *                                  the most clean RMID.
- *
- * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
- * may not be able to allocate clean RMID. To avoid this the allocator will
- * choose the CLOSID with the most clean RMID.
- *
- * When the CLOSID and RMID are independent numbers, the first free CLOSID will
- * be returned.
- */
-int resctrl_find_cleanest_closid(void)
-{
-	u32 cleanest_closid = ~0;
-	int i = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		return -EIO;
-
-	for (i = 0; i < closids_supported(); i++) {
-		int num_dirty;
-
-		if (closid_allocated(i))
-			continue;
-
-		num_dirty = closid_num_dirty_rmid[i];
-		if (num_dirty == 0)
-			return i;
-
-		if (cleanest_closid == ~0)
-			cleanest_closid = i;
-
-		if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
-			cleanest_closid = i;
-	}
-
-	if (cleanest_closid == ~0)
-		return -ENOSPC;
-
-	return cleanest_closid;
-}
-
-/*
- * For MPAM the RMID value is not unique, and has to be considered with
- * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
- * allows all domains to be managed by a single free list.
- * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
- */
-int alloc_rmid(u32 closid)
-{
-	struct rmid_entry *entry;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	entry = resctrl_find_free_rmid(closid);
-	if (IS_ERR(entry))
-		return PTR_ERR(entry);
-
-	list_del(&entry->list);
-	return entry->rmid;
-}
-
-static void add_rmid_to_limbo(struct rmid_entry *entry)
-{
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_mon_domain *d;
-	u32 idx;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
-
-	entry->busy = 0;
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		/*
-		 * For the first limbo RMID in the domain,
-		 * setup up the limbo worker.
-		 */
-		if (!has_busy_rmid(d))
-			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
-						RESCTRL_PICK_ANY_CPU);
-		set_bit(idx, d->rmid_busy_llc);
-		entry->busy++;
-	}
-
-	rmid_limbo_count++;
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		closid_num_dirty_rmid[entry->closid]++;
-}
-
-void free_rmid(u32 closid, u32 rmid)
-{
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct rmid_entry *entry;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/*
-	 * Do not allow the default rmid to be free'd. Comparing by index
-	 * allows architectures that ignore the closid parameter to avoid an
-	 * unnecessary check.
-	 */
-	if (!resctrl_arch_mon_capable() ||
-	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
-						RESCTRL_RESERVED_RMID))
-		return;
-
-	entry = __rmid_entry(idx);
-
-	if (is_llc_occupancy_enabled())
-		add_rmid_to_limbo(entry);
-	else
-		list_add_tail(&entry->list, &rmid_free_lru);
-}
-
-static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
-				       u32 rmid, enum resctrl_event_id evtid)
-{
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-
-	switch (evtid) {
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[idx];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[idx];
-	default:
-		return NULL;
-	}
-}
-
-static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
-	int cpu = smp_processor_id();
-	struct rdt_mon_domain *d;
-	struct mbm_state *m;
-	int err, ret;
-	u64 tval = 0;
-
-	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
-		if (m)
-			memset(m, 0, sizeof(struct mbm_state));
-		return 0;
-	}
-
-	if (rr->d) {
-		/* Reading a single domain, must be on a CPU in that domain. */
-		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
-			return -EINVAL;
-		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
-						 rr->evtid, &tval, rr->arch_mon_ctx);
-		if (rr->err)
-			return rr->err;
-
-		rr->val += tval;
-
-		return 0;
-	}
-
-	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
-		return -EINVAL;
-
-	/*
-	 * Legacy files must report the sum of an event across all
-	 * domains that share the same L3 cache instance.
-	 * Report success if a read from any domain succeeds, -EINVAL
-	 * (translated to "Unavailable" for user space) if reading from
-	 * all domains fail for any reason.
-	 */
-	ret = -EINVAL;
-	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
-			continue;
-		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
-					     rr->evtid, &tval, rr->arch_mon_ctx);
-		if (!err) {
-			rr->val += tval;
-			ret = 0;
-		}
-	}
-
-	if (ret)
-		rr->err = ret;
-
-	return ret;
-}
-
-/*
- * mbm_bw_count() - Update bw count from values previously read by
- *		    __mon_event_count().
- * @closid:	The closid used to identify the cached mbm_state.
- * @rmid:	The rmid used to identify the cached mbm_state.
- * @rr:		The struct rmid_read populated by __mon_event_count().
- *
- * Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps. The chunks value previously read by
- * __mon_event_count() is compared with the chunks value from the previous
- * invocation. This must be called once per second to maintain values in MBps.
- */
-static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
-	u64 cur_bw, bytes, cur_bytes;
-	struct mbm_state *m;
-
-	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
-	if (WARN_ON_ONCE(!m))
-		return;
-
-	cur_bytes = rr->val;
-	bytes = cur_bytes - m->prev_bw_bytes;
-	m->prev_bw_bytes = cur_bytes;
-
-	cur_bw = bytes / SZ_1M;
-
-	m->prev_bw = cur_bw;
-}
-
-/*
- * This is scheduled by mon_event_read() to read the CQM/MBM counters
- * on a domain.
- */
-void mon_event_count(void *info)
-{
-	struct rdtgroup *rdtgrp, *entry;
-	struct rmid_read *rr = info;
-	struct list_head *head;
-	int ret;
-
-	rdtgrp = rr->rgrp;
-
-	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
-
-	/*
-	 * For Ctrl groups read data from child monitor groups and
-	 * add them together. Count events which are read successfully.
-	 * Discard the rmid_read's reporting errors.
-	 */
-	head = &rdtgrp->mon.crdtgrp_list;
-
-	if (rdtgrp->type == RDTCTRL_GROUP) {
-		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->closid, entry->mon.rmid,
-					      rr) == 0)
-				ret = 0;
-		}
-	}
-
-	/*
-	 * __mon_event_count() calls for newly created monitor groups may
-	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
-	 * Discard error if any of the monitor event reads succeeded.
-	 */
-	if (ret == 0)
-		rr->err = 0;
-}
-
-/*
- * Feedback loop for MBA software controller (mba_sc)
- *
- * mba_sc is a feedback loop where we periodically read MBM counters and
- * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
- * that:
- *
- *   current bandwidth(cur_bw) < user specified bandwidth(user_bw)
- *
- * This uses the MBM counters to measure the bandwidth and MBA throttle
- * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
- * fact that resctrl rdtgroups have both monitoring and control.
- *
- * The frequency of the checks is 1s and we just tag along the MBM overflow
- * timer. Having 1s interval makes the calculation of bandwidth simpler.
- *
- * Although MBA's goal is to restrict the bandwidth to a maximum, there may
- * be a need to increase the bandwidth to avoid unnecessarily restricting
- * the L2 <-> L3 traffic.
- *
- * Since MBA controls the L2 external bandwidth where as MBM measures the
- * L3 external bandwidth the following sequence could lead to such a
- * situation.
- *
- * Consider an rdtgroup which had high L3 <-> memory traffic in initial
- * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
- * after some time rdtgroup has mostly L2 <-> L3 traffic.
- *
- * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
- * throttle MSRs already have low percentage values.  To avoid
- * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
- */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
-{
-	u32 closid, rmid, cur_msr_val, new_msr_val;
-	struct mbm_state *pmbm_data, *cmbm_data;
-	struct rdt_ctrl_domain *dom_mba;
-	enum resctrl_event_id evt_id;
-	struct rdt_resource *r_mba;
-	struct list_head *head;
-	struct rdtgroup *entry;
-	u32 cur_bw, user_bw;
-
-	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
-	evt_id = rgrp->mba_mbps_event;
-
-	closid = rgrp->closid;
-	rmid = rgrp->mon.rmid;
-	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
-	if (WARN_ON_ONCE(!pmbm_data))
-		return;
-
-	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
-	if (!dom_mba) {
-		pr_warn_once("Failure to get domain for MBA update\n");
-		return;
-	}
-
-	cur_bw = pmbm_data->prev_bw;
-	user_bw = dom_mba->mbps_val[closid];
-
-	/* MBA resource doesn't support CDP */
-	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
-
-	/*
-	 * For Ctrl groups read data from child monitor groups.
-	 */
-	head = &rgrp->mon.crdtgrp_list;
-	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
-		if (WARN_ON_ONCE(!cmbm_data))
-			return;
-		cur_bw += cmbm_data->prev_bw;
-	}
-
-	/*
-	 * Scale up/down the bandwidth linearly for the ctrl group.  The
-	 * bandwidth step is the bandwidth granularity specified by the
-	 * hardware.
-	 * Always increase throttling if current bandwidth is above the
-	 * target set by user.
-	 * But avoid thrashing up and down on every poll by checking
-	 * whether a decrease in throttling is likely to push the group
-	 * back over target. E.g. if currently throttling to 30% of bandwidth
-	 * on a system with 10% granularity steps, check whether moving to
-	 * 40% would go past the limit by multiplying current bandwidth by
-	 * "(30 + 10) / 30".
-	 */
-	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
-		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
-	} else if (cur_msr_val < MAX_MBA_BW &&
-		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
-		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
-	} else {
-		return;
-	}
-
-	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-}
-
-static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
-				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
-{
-	struct rmid_read rr = {0};
-
-	rr.r = r;
-	rr.d = d;
-	rr.evtid = evtid;
-	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-	if (IS_ERR(rr.arch_mon_ctx)) {
-		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-				    PTR_ERR(rr.arch_mon_ctx));
-		return;
-	}
-
-	__mon_event_count(closid, rmid, &rr);
-
-	/*
-	 * If the software controller is enabled, compute the
-	 * bandwidth for this event id.
-	 */
-	if (is_mba_sc(NULL))
-		mbm_bw_count(closid, rmid, &rr);
-
-	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-}
-
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
-{
-	/*
-	 * This is protected from concurrent reads from user as both
-	 * the user and overflow handler hold the global mutex.
-	 */
-	if (is_mbm_total_enabled())
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	if (is_mbm_local_enabled())
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-/*
- * Handler to scan the limbo list and move the RMIDs
- * to free list whose occupancy < threshold_occupancy.
- */
-void cqm_handle_limbo(struct work_struct *work)
-{
-	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	struct rdt_mon_domain *d;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
-
-	__check_limbo(d, false);
-
-	if (has_busy_rmid(d)) {
-		d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
-							   RESCTRL_PICK_ANY_CPU);
-		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
-					 delay);
-	}
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-/**
- * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
- *                             domain.
- * @dom:           The domain the limbo handler should run for.
- * @delay_ms:      How far in the future the handler should run.
- * @exclude_cpu:   Which CPU the handler should not run on,
- *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-			     int exclude_cpu)
-{
-	unsigned long delay = msecs_to_jiffies(delay_ms);
-	int cpu;
-
-	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
-	dom->cqm_work_cpu = cpu;
-
-	if (cpu < nr_cpu_ids)
-		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
-}
-
-void mbm_handle_overflow(struct work_struct *work)
-{
-	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
-	struct rdtgroup *prgrp, *crgrp;
-	struct rdt_mon_domain *d;
-	struct list_head *head;
-	struct rdt_resource *r;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	/*
-	 * If the filesystem has been unmounted this work no longer needs to
-	 * run.
-	 */
-	if (!resctrl_mounted || !resctrl_arch_mon_capable())
-		goto out_unlock;
-
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
-
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
-
-		if (is_mba_sc(NULL))
-			update_mba_bw(prgrp, d);
-	}
-
-	/*
-	 * Re-check for housekeeping CPUs. This allows the overflow handler to
-	 * move off a nohz_full CPU quickly.
-	 */
-	d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
-						   RESCTRL_PICK_ANY_CPU);
-	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-/**
- * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
- *                                domain.
- * @dom:           The domain the overflow handler should run for.
- * @delay_ms:      How far in the future the handler should run.
- * @exclude_cpu:   Which CPU the handler should not run on,
- *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-				int exclude_cpu)
-{
-	unsigned long delay = msecs_to_jiffies(delay_ms);
-	int cpu;
-
-	/*
-	 * When a domain comes online there is no guarantee the filesystem is
-	 * mounted. If not, there is no need to catch counter overflow.
-	 */
-	if (!resctrl_mounted || !resctrl_arch_mon_capable())
-		return;
-	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
-	dom->mbm_work_cpu = cpu;
-
-	if (cpu < nr_cpu_ids)
-		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
-}
-
-static int dom_data_init(struct rdt_resource *r)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	struct rmid_entry *entry = NULL;
-	int err = 0, i;
-	u32 idx;
-
-	mutex_lock(&rdtgroup_mutex);
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		u32 *tmp;
-
-		/*
-		 * If the architecture hasn't provided a sanitised value here,
-		 * this may result in larger arrays than necessary. Resctrl will
-		 * use a smaller system wide value based on the resources in
-		 * use.
-		 */
-		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
-		if (!tmp) {
-			err = -ENOMEM;
-			goto out_unlock;
-		}
-
-		closid_num_dirty_rmid = tmp;
-	}
-
-	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs) {
-		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-			kfree(closid_num_dirty_rmid);
-			closid_num_dirty_rmid = NULL;
-		}
-		err = -ENOMEM;
-		goto out_unlock;
-	}
-
-	for (i = 0; i < idx_limit; i++) {
-		entry = &rmid_ptrs[i];
-		INIT_LIST_HEAD(&entry->list);
-
-		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
-		list_add_tail(&entry->list, &rmid_free_lru);
-	}
-
-	/*
-	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
-	 * are always allocated. These are used for the rdtgroup_default
-	 * control group, which will be setup later in rdtgroup_init().
-	 */
-	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
-					   RESCTRL_RESERVED_RMID);
-	entry = __rmid_entry(idx);
-	list_del(&entry->list);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-static void __exit dom_data_exit(void)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		kfree(closid_num_dirty_rmid);
-		closid_num_dirty_rmid = NULL;
-	}
-
-	kfree(rmid_ptrs);
-	rmid_ptrs = NULL;
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static struct mon_evt llc_occupancy_event = {
-	.name		= "llc_occupancy",
-	.evtid		= QOS_L3_OCCUP_EVENT_ID,
-};
-
-static struct mon_evt mbm_total_event = {
-	.name		= "mbm_total_bytes",
-	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
-};
-
-static struct mon_evt mbm_local_event = {
-	.name		= "mbm_local_bytes",
-	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
-};
-
-/*
- * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
- */
-static void l3_mon_evt_init(struct rdt_resource *r)
-{
-	INIT_LIST_HEAD(&r->evt_list);
-
-	if (is_llc_occupancy_enabled())
-		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (is_mbm_total_enabled())
-		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (is_mbm_local_enabled())
-		list_add_tail(&mbm_local_event.list, &r->evt_list);
-}
-
 /*
  * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
  * which indicates that RMIDs are configured in legacy mode.
@@ -1177,7 +346,6 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int threshold;
-	int ret;
 
 	snc_nodes_per_l3_cache = snc_get_config();
 
@@ -1207,41 +375,19 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 */
 	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
-	ret = dom_data_init(r);
-	if (ret)
-		return ret;
-
 	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
 		u32 eax, ebx, ecx, edx;
 
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
-		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
-
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-			mbm_total_event.configurable = true;
-			resctrl_file_fflags_init("mbm_total_bytes_config",
-						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-		}
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-			mbm_local_event.configurable = true;
-			resctrl_file_fflags_init("mbm_local_bytes_config",
-						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-		}
+		r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
-	l3_mon_evt_init(r);
-
 	r->mon_capable = true;
 
 	return 0;
 }
 
-void __exit rdt_put_mon_l3_config(void)
-{
-	dom_data_exit();
-}
-
 void __init intel_rdt_mbm_apply_quirk(void)
 {
 	int cf_index;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 42cc162f7fc9..de580eca3363 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -11,26 +11,22 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheflush.h>
 #include <linux/cpu.h>
-#include <linux/cpumask.h>
-#include <linux/debugfs.h>
-#include <linux/kthread.h>
-#include <linux/mman.h>
 #include <linux/perf_event.h>
 #include <linux/pm_qos.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
+#include <linux/resctrl.h>
 
-#include <asm/cacheflush.h>
 #include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
 #include <asm/perf_event.h>
+#include <asm/msr.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
-#include "trace.h"
+
+#include "pseudo_lock_trace.h"
 
 /*
  * The bits needed to disable hardware prefetching varies based on the
@@ -38,30 +34,9 @@
  */
 static u64 prefetch_disable_bits;
 
-/*
- * Major number assigned to and shared by all devices exposing
- * pseudo-locked regions.
- */
-static unsigned int pseudo_lock_major;
-static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
-
-static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
-{
-	const struct rdtgroup *rdtgrp;
-
-	rdtgrp = dev_get_drvdata(dev);
-	if (mode)
-		*mode = 0600;
-	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
-}
-
-static const struct class pseudo_lock_class = {
-	.name = "pseudo_lock",
-	.devnode = pseudo_lock_devnode,
-};
-
 /**
- * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ * resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported
+ *                                          platforms
  * @void: It takes no parameters.
  *
  * Capture the list of platforms that have been validated to support
@@ -75,14 +50,16 @@ static const struct class pseudo_lock_class = {
  * in the SDM.
  *
  * When adding a platform here also add support for its cache events to
- * measure_cycles_perf_fn()
+ * resctrl_arch_measure_l*_residency()
  *
  * Return:
  * If platform is supported, the bits to disable hardware prefetchers, 0
  * if platform is not supported.
  */
-static u64 get_prefetch_disable_bits(void)
+u64 resctrl_arch_get_prefetch_disable_bits(void)
 {
+	prefetch_disable_bits = 0;
+
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
 		return 0;
@@ -98,7 +75,8 @@ static u64 get_prefetch_disable_bits(void)
 		 * 3    DCU IP Prefetcher Disable (R/W)
 		 * 63:4 Reserved
 		 */
-		return 0xF;
+		prefetch_disable_bits = 0xF;
+		break;
 	case INTEL_ATOM_GOLDMONT:
 	case INTEL_ATOM_GOLDMONT_PLUS:
 		/*
@@ -109,307 +87,16 @@ static u64 get_prefetch_disable_bits(void)
 		 * 2     DCU Hardware Prefetcher Disable (R/W)
 		 * 63:3  Reserved
 		 */
-		return 0x5;
-	}
-
-	return 0;
-}
-
-/**
- * pseudo_lock_minor_get - Obtain available minor number
- * @minor: Pointer to where new minor number will be stored
- *
- * A bitmask is used to track available minor numbers. Here the next free
- * minor number is marked as unavailable and returned.
- *
- * Return: 0 on success, <0 on failure.
- */
-static int pseudo_lock_minor_get(unsigned int *minor)
-{
-	unsigned long first_bit;
-
-	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
-
-	if (first_bit == MINORBITS)
-		return -ENOSPC;
-
-	__clear_bit(first_bit, &pseudo_lock_minor_avail);
-	*minor = first_bit;
-
-	return 0;
-}
-
-/**
- * pseudo_lock_minor_release - Return minor number to available
- * @minor: The minor number made available
- */
-static void pseudo_lock_minor_release(unsigned int minor)
-{
-	__set_bit(minor, &pseudo_lock_minor_avail);
-}
-
-/**
- * region_find_by_minor - Locate a pseudo-lock region by inode minor number
- * @minor: The minor number of the device representing pseudo-locked region
- *
- * When the character device is accessed we need to determine which
- * pseudo-locked region it belongs to. This is done by matching the minor
- * number of the device to the pseudo-locked region it belongs.
- *
- * Minor numbers are assigned at the time a pseudo-locked region is associated
- * with a cache instance.
- *
- * Return: On success return pointer to resource group owning the pseudo-locked
- *         region, NULL on failure.
- */
-static struct rdtgroup *region_find_by_minor(unsigned int minor)
-{
-	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
-
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
-			rdtgrp_match = rdtgrp;
-			break;
-		}
-	}
-	return rdtgrp_match;
-}
-
-/**
- * struct pseudo_lock_pm_req - A power management QoS request list entry
- * @list:	Entry within the @pm_reqs list for a pseudo-locked region
- * @req:	PM QoS request
- */
-struct pseudo_lock_pm_req {
-	struct list_head list;
-	struct dev_pm_qos_request req;
-};
-
-static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
-{
-	struct pseudo_lock_pm_req *pm_req, *next;
-
-	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
-		dev_pm_qos_remove_request(&pm_req->req);
-		list_del(&pm_req->list);
-		kfree(pm_req);
-	}
-}
-
-/**
- * pseudo_lock_cstates_constrain - Restrict cores from entering C6
- * @plr: Pseudo-locked region
- *
- * To prevent the cache from being affected by power management entering
- * C6 has to be avoided. This is accomplished by requesting a latency
- * requirement lower than lowest C6 exit latency of all supported
- * platforms as found in the cpuidle state tables in the intel_idle driver.
- * At this time it is possible to do so with a single latency requirement
- * for all supported platforms.
- *
- * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
- * the ACPI latencies need to be considered while keeping in mind that C2
- * may be set to map to deeper sleep states. In this case the latency
- * requirement needs to prevent entering C2 also.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
-{
-	struct pseudo_lock_pm_req *pm_req;
-	int cpu;
-	int ret;
-
-	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
-		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
-		if (!pm_req) {
-			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
-			ret = -ENOMEM;
-			goto out_err;
-		}
-		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-					     &pm_req->req,
-					     DEV_PM_QOS_RESUME_LATENCY,
-					     30);
-		if (ret < 0) {
-			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
-					    cpu);
-			kfree(pm_req);
-			ret = -1;
-			goto out_err;
-		}
-		list_add(&pm_req->list, &plr->pm_reqs);
-	}
-
-	return 0;
-
-out_err:
-	pseudo_lock_cstates_relax(plr);
-	return ret;
-}
-
-/**
- * pseudo_lock_region_clear - Reset pseudo-lock region data
- * @plr: pseudo-lock region
- *
- * All content of the pseudo-locked region is reset - any memory allocated
- * freed.
- *
- * Return: void
- */
-static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
-{
-	plr->size = 0;
-	plr->line_size = 0;
-	kfree(plr->kmem);
-	plr->kmem = NULL;
-	plr->s = NULL;
-	if (plr->d)
-		plr->d->plr = NULL;
-	plr->d = NULL;
-	plr->cbm = 0;
-	plr->debugfs_dir = NULL;
-}
-
-/**
- * pseudo_lock_region_init - Initialize pseudo-lock region information
- * @plr: pseudo-lock region
- *
- * Called after user provided a schemata to be pseudo-locked. From the
- * schemata the &struct pseudo_lock_region is on entry already initialized
- * with the resource, domain, and capacity bitmask. Here the information
- * required for pseudo-locking is deduced from this data and &struct
- * pseudo_lock_region initialized further. This information includes:
- * - size in bytes of the region to be pseudo-locked
- * - cache line size to know the stride with which data needs to be accessed
- *   to be pseudo-locked
- * - a cpu associated with the cache instance on which the pseudo-locking
- *   flow can be executed
- *
- * Return: 0 on success, <0 on failure. Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
-{
-	enum resctrl_scope scope = plr->s->res->ctrl_scope;
-	struct cacheinfo *ci;
-	int ret;
-
-	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
-		return -ENODEV;
-
-	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
-
-	if (!cpu_online(plr->cpu)) {
-		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
-				    plr->cpu);
-		ret = -ENODEV;
-		goto out_region;
-	}
-
-	ci = get_cpu_cacheinfo_level(plr->cpu, scope);
-	if (ci) {
-		plr->line_size = ci->coherency_line_size;
-		plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
-		return 0;
-	}
-
-	ret = -1;
-	rdt_last_cmd_puts("Unable to determine cache line size\n");
-out_region:
-	pseudo_lock_region_clear(plr);
-	return ret;
-}
-
-/**
- * pseudo_lock_init - Initialize a pseudo-lock region
- * @rdtgrp: resource group to which new pseudo-locked region will belong
- *
- * A pseudo-locked region is associated with a resource group. When this
- * association is created the pseudo-locked region is initialized. The
- * details of the pseudo-locked region are not known at this time so only
- * allocation is done and association established.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_init(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr;
-
-	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
-	if (!plr)
-		return -ENOMEM;
-
-	init_waitqueue_head(&plr->lock_thread_wq);
-	INIT_LIST_HEAD(&plr->pm_reqs);
-	rdtgrp->plr = plr;
-	return 0;
-}
-
-/**
- * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
- * @plr: pseudo-lock region
- *
- * Initialize the details required to set up the pseudo-locked region and
- * allocate the contiguous memory that will be pseudo-locked to the cache.
- *
- * Return: 0 on success, <0 on failure.  Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
-{
-	int ret;
-
-	ret = pseudo_lock_region_init(plr);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * We do not yet support contiguous regions larger than
-	 * KMALLOC_MAX_SIZE.
-	 */
-	if (plr->size > KMALLOC_MAX_SIZE) {
-		rdt_last_cmd_puts("Requested region exceeds maximum size\n");
-		ret = -E2BIG;
-		goto out_region;
-	}
-
-	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
-	if (!plr->kmem) {
-		rdt_last_cmd_puts("Unable to allocate memory\n");
-		ret = -ENOMEM;
-		goto out_region;
+		prefetch_disable_bits = 0x5;
+		break;
 	}
 
-	ret = 0;
-	goto out;
-out_region:
-	pseudo_lock_region_clear(plr);
-out:
-	return ret;
-}
-
-/**
- * pseudo_lock_free - Free a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-locked region belonged
- *
- * The pseudo-locked region's resources have already been released, or not
- * yet created at this point. Now it can be freed and disassociated from the
- * resource group.
- *
- * Return: void
- */
-static void pseudo_lock_free(struct rdtgroup *rdtgrp)
-{
-	pseudo_lock_region_clear(rdtgrp->plr);
-	kfree(rdtgrp->plr);
-	rdtgrp->plr = NULL;
+	return prefetch_disable_bits;
 }
 
 /**
- * pseudo_lock_fn - Load kernel memory into cache
- * @_rdtgrp: resource group to which pseudo-lock region belongs
+ * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache
+ * @_plr: the pseudo-lock region descriptor
  *
  * This is the core pseudo-locking flow.
  *
@@ -426,10 +113,9 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp)
  *
  * Return: 0. Waiter on waitqueue will be woken on completion.
  */
-static int pseudo_lock_fn(void *_rdtgrp)
+int resctrl_arch_pseudo_lock_fn(void *_plr)
 {
-	struct rdtgroup *rdtgrp = _rdtgrp;
-	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct pseudo_lock_region *plr = _plr;
 	u32 rmid_p, closid_p;
 	unsigned long i;
 	u64 saved_msr;
@@ -476,8 +162,8 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	 * the buffer and evict pseudo-locked memory read earlier from the
 	 * cache.
 	 */
-	saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
-	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	saved_msr = native_rdmsrq(MSR_MISC_FEATURE_CONTROL);
+	native_wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 	closid_p = this_cpu_read(pqr_state.cur_closid);
 	rmid_p = this_cpu_read(pqr_state.cur_rmid);
 	mem_r = plr->kmem;
@@ -489,7 +175,8 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	 * pseudo-locked followed by reading of kernel memory to load it
 	 * into the cache.
 	 */
-	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+	native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
+
 	/*
 	 * Cache was flushed earlier. Now access kernel memory to read it
 	 * into cache region associated with just activated plr->closid.
@@ -525,10 +212,10 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	 * Critical section end: restore closid with capacity bitmask that
 	 * does not overlap with pseudo-locked region.
 	 */
-	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
+	native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
 
 	/* Re-enable the hardware prefetcher(s) */
-	wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, saved_msr);
 	local_irq_enable();
 
 	plr->thread_done = 1;
@@ -537,342 +224,8 @@ static int pseudo_lock_fn(void *_rdtgrp)
 }
 
 /**
- * rdtgroup_monitor_in_progress - Test if monitoring in progress
- * @rdtgrp: resource group being queried
- *
- * Return: 1 if monitor groups have been created for this resource
- * group, 0 otherwise.
- */
-static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
-{
-	return !list_empty(&rdtgrp->mon.crdtgrp_list);
-}
-
-/**
- * rdtgroup_locksetup_user_restrict - Restrict user access to group
- * @rdtgrp: resource group needing access restricted
- *
- * A resource group used for cache pseudo-locking cannot have cpus or tasks
- * assigned to it. This is communicated to the user by restricting access
- * to all the files that can be used to make such changes.
- *
- * Permissions restored with rdtgroup_locksetup_user_restore()
- *
- * Return: 0 on success, <0 on failure. If a failure occurs during the
- * restriction of access an attempt will be made to restore permissions but
- * the state of the mode of these files will be uncertain when a failure
- * occurs.
- */
-static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
-	if (ret)
-		goto err_tasks;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
-	if (ret)
-		goto err_cpus;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
-		if (ret)
-			goto err_cpus_list;
-	}
-
-	ret = 0;
-	goto out;
-
-err_cpus_list:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
-err_cpus:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
-err_tasks:
-	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_user_restore - Restore user access to group
- * @rdtgrp: resource group needing access restored
- *
- * Restore all file access previously removed using
- * rdtgroup_locksetup_user_restrict()
- *
- * Return: 0 on success, <0 on failure.  If a failure occurs during the
- * restoration of access an attempt will be made to restrict permissions
- * again but the state of the mode of these files will be uncertain when
- * a failure occurs.
- */
-static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
-	if (ret)
-		goto err_tasks;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
-	if (ret)
-		goto err_cpus;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
-		if (ret)
-			goto err_cpus_list;
-	}
-
-	ret = 0;
-	goto out;
-
-err_cpus_list:
-	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
-err_cpus:
-	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
-err_tasks:
-	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_enter - Resource group enters locksetup mode
- * @rdtgrp: resource group requested to enter locksetup mode
- *
- * A resource group enters locksetup mode to reflect that it would be used
- * to represent a pseudo-locked region and is in the process of being set
- * up to do so. A resource group used for a pseudo-locked region would
- * lose the closid associated with it so we cannot allow it to have any
- * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
- * future. Monitoring of a pseudo-locked region is not allowed either.
- *
- * The above and more restrictions on a pseudo-locked region are checked
- * for and enforced before the resource group enters the locksetup mode.
- *
- * Returns: 0 if the resource group successfully entered locksetup mode, <0
- * on failure. On failure the last_cmd_status buffer is updated with text to
- * communicate details of failure to the user.
- */
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	/*
-	 * The default resource group can neither be removed nor lose the
-	 * default closid associated with it.
-	 */
-	if (rdtgrp == &rdtgroup_default) {
-		rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Cache Pseudo-locking not supported when CDP is enabled.
-	 *
-	 * Some things to consider if you would like to enable this
-	 * support (using L3 CDP as example):
-	 * - When CDP is enabled two separate resources are exposed,
-	 *   L3DATA and L3CODE, but they are actually on the same cache.
-	 *   The implication for pseudo-locking is that if a
-	 *   pseudo-locked region is created on a domain of one
-	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
-	 *   be created on that same domain of the other resource
-	 *   (eg. L3DATA). This is because the creation of a
-	 *   pseudo-locked region involves a call to wbinvd that will
-	 *   affect all cache allocations on particular domain.
-	 * - Considering the previous, it may be possible to only
-	 *   expose one of the CDP resources to pseudo-locking and
-	 *   hide the other. For example, we could consider to only
-	 *   expose L3DATA and since the L3 cache is unified it is
-	 *   still possible to place instructions there are execute it.
-	 * - If only one region is exposed to pseudo-locking we should
-	 *   still keep in mind that availability of a portion of cache
-	 *   for pseudo-locking should take into account both resources.
-	 *   Similarly, if a pseudo-locked region is created in one
-	 *   resource, the portion of cache used by it should be made
-	 *   unavailable to all future allocations from both resources.
-	 */
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
-	    resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
-		rdt_last_cmd_puts("CDP enabled\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Not knowing the bits to disable prefetching implies that this
-	 * platform does not support Cache Pseudo-Locking.
-	 */
-	prefetch_disable_bits = get_prefetch_disable_bits();
-	if (prefetch_disable_bits == 0) {
-		rdt_last_cmd_puts("Pseudo-locking not supported\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_monitor_in_progress(rdtgrp)) {
-		rdt_last_cmd_puts("Monitoring in progress\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_tasks_assigned(rdtgrp)) {
-		rdt_last_cmd_puts("Tasks assigned to resource group\n");
-		return -EINVAL;
-	}
-
-	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
-		rdt_last_cmd_puts("CPUs assigned to resource group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
-		rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
-		return -EIO;
-	}
-
-	ret = pseudo_lock_init(rdtgrp);
-	if (ret) {
-		rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
-		goto out_release;
-	}
-
-	/*
-	 * If this system is capable of monitoring a rmid would have been
-	 * allocated when the control group was created. This is not needed
-	 * anymore when this group would be used for pseudo-locking. This
-	 * is safe to call on platforms not capable of monitoring.
-	 */
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-	ret = 0;
-	goto out;
-
-out_release:
-	rdtgroup_locksetup_user_restore(rdtgrp);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_exit - resource group exist locksetup mode
- * @rdtgrp: resource group
- *
- * When a resource group exits locksetup mode the earlier restrictions are
- * lifted.
- *
- * Return: 0 on success, <0 on failure
- */
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = alloc_rmid(rdtgrp->closid);
-		if (ret < 0) {
-			rdt_last_cmd_puts("Out of RMIDs\n");
-			return ret;
-		}
-		rdtgrp->mon.rmid = ret;
-	}
-
-	ret = rdtgroup_locksetup_user_restore(rdtgrp);
-	if (ret) {
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-		return ret;
-	}
-
-	pseudo_lock_free(rdtgrp);
-	return 0;
-}
-
-/**
- * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
- * @d: RDT domain
- * @cbm: CBM to test
- *
- * @d represents a cache instance and @cbm a capacity bitmask that is
- * considered for it. Determine if @cbm overlaps with any existing
- * pseudo-locked region on @d.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: true if @cbm overlaps with pseudo-locked region on @d, false
- * otherwise.
- */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
-{
-	unsigned int cbm_len;
-	unsigned long cbm_b;
-
-	if (d->plr) {
-		cbm_len = d->plr->s->res->cache.cbm_len;
-		cbm_b = d->plr->cbm;
-		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
-			return true;
-	}
-	return false;
-}
-
-/**
- * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
- * @d: RDT domain under test
- *
- * The setup of a pseudo-locked region affects all cache instances within
- * the hierarchy of the region. It is thus essential to know if any
- * pseudo-locked regions exist within a cache hierarchy to prevent any
- * attempts to create new pseudo-locked regions in the same hierarchy.
- *
- * Return: true if a pseudo-locked region exists in the hierarchy of @d or
- *         if it is not possible to test due to memory allocation issue,
- *         false otherwise.
- */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
-{
-	struct rdt_ctrl_domain *d_i;
-	cpumask_var_t cpu_with_psl;
-	struct rdt_resource *r;
-	bool ret = false;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
-		return true;
-
-	/*
-	 * First determine which cpus have pseudo-locked regions
-	 * associated with them.
-	 */
-	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
-			if (d_i->plr)
-				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->hdr.cpu_mask);
-		}
-	}
-
-	/*
-	 * Next test if new pseudo-locked region would intersect with
-	 * existing region.
-	 */
-	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
-		ret = true;
-
-	free_cpumask_var(cpu_with_psl);
-	return ret;
-}
-
-/**
- * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * resctrl_arch_measure_cycles_lat_fn - Measure cycle latency to read
+ *                                      pseudo-locked memory
  * @_plr: pseudo-lock region to measure
  *
  * There is no deterministic way to test if a memory region is cached. One
@@ -885,7 +238,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
  *
  * Return: 0. Waiter on waitqueue will be woken on completion.
  */
-static int measure_cycles_lat_fn(void *_plr)
+int resctrl_arch_measure_cycles_lat_fn(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	u32 saved_low, saved_high;
@@ -898,7 +251,7 @@ static int measure_cycles_lat_fn(void *_plr)
 	 * Disable hardware prefetchers.
 	 */
 	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
-	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 	mem_r = READ_ONCE(plr->kmem);
 	/*
 	 * Dummy execute of the time measurement to load the needed
@@ -994,7 +347,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * Disable hardware prefetchers.
 	 */
 	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
-	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
 
 	/* Initialize rest of local variables */
 	/*
@@ -1012,8 +365,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * used in L1 cache, second to capture accurate value that does not
 	 * include cache misses incurred because of instruction loads.
 	 */
-	rdpmcl(hit_pmcnum, hits_before);
-	rdpmcl(miss_pmcnum, miss_before);
+	hits_before = rdpmc(hit_pmcnum);
+	miss_before = rdpmc(miss_pmcnum);
 	/*
 	 * From SDM: Performing back-to-back fast reads are not guaranteed
 	 * to be monotonic.
@@ -1021,8 +374,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * before proceeding.
 	 */
 	rmb();
-	rdpmcl(hit_pmcnum, hits_before);
-	rdpmcl(miss_pmcnum, miss_before);
+	hits_before = rdpmc(hit_pmcnum);
+	miss_before = rdpmc(miss_pmcnum);
 	/*
 	 * Use LFENCE to ensure all previous instructions are retired
 	 * before proceeding.
@@ -1044,8 +397,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 * before proceeding.
 	 */
 	rmb();
-	rdpmcl(hit_pmcnum, hits_after);
-	rdpmcl(miss_pmcnum, miss_after);
+	hits_after = rdpmc(hit_pmcnum);
+	miss_after = rdpmc(miss_pmcnum);
 	/*
 	 * Use LFENCE to ensure all previous instructions are retired
 	 * before proceeding.
@@ -1069,7 +422,7 @@ out:
 	return 0;
 }
 
-static int measure_l2_residency(void *_plr)
+int resctrl_arch_measure_l2_residency(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	struct residency_counts counts = {0};
@@ -1107,7 +460,7 @@ out:
 	return 0;
 }
 
-static int measure_l3_residency(void *_plr)
+int resctrl_arch_measure_l3_residency(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	struct residency_counts counts = {0};
@@ -1162,428 +515,3 @@ out:
 	wake_up_interruptible(&plr->lock_thread_wq);
 	return 0;
 }
-
-/**
- * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
- * @rdtgrp: Resource group to which the pseudo-locked region belongs.
- * @sel: Selector of which measurement to perform on a pseudo-locked region.
- *
- * The measurement of latency to access a pseudo-locked region should be
- * done from a cpu that is associated with that pseudo-locked region.
- * Determine which cpu is associated with this region and start a thread on
- * that cpu to perform the measurement, wait for that thread to complete.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-	struct task_struct *thread;
-	unsigned int cpu;
-	int ret = -1;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	if (rdtgrp->flags & RDT_DELETED) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	if (!plr->d) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
-	if (!cpu_online(cpu)) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	plr->cpu = cpu;
-
-	if (sel == 1)
-		thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr,
-					    cpu, "pseudo_lock_measure/%u");
-	else if (sel == 2)
-		thread = kthread_run_on_cpu(measure_l2_residency, plr,
-					    cpu, "pseudo_lock_measure/%u");
-	else if (sel == 3)
-		thread = kthread_run_on_cpu(measure_l3_residency, plr,
-					    cpu, "pseudo_lock_measure/%u");
-	else
-		goto out;
-
-	if (IS_ERR(thread)) {
-		ret = PTR_ERR(thread);
-		goto out;
-	}
-
-	ret = wait_event_interruptible(plr->lock_thread_wq,
-				       plr->thread_done == 1);
-	if (ret < 0)
-		goto out;
-
-	ret = 0;
-
-out:
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return ret;
-}
-
-static ssize_t pseudo_lock_measure_trigger(struct file *file,
-					   const char __user *user_buf,
-					   size_t count, loff_t *ppos)
-{
-	struct rdtgroup *rdtgrp = file->private_data;
-	size_t buf_size;
-	char buf[32];
-	int ret;
-	int sel;
-
-	buf_size = min(count, (sizeof(buf) - 1));
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	ret = kstrtoint(buf, 10, &sel);
-	if (ret == 0) {
-		if (sel != 1 && sel != 2 && sel != 3)
-			return -EINVAL;
-		ret = debugfs_file_get(file->f_path.dentry);
-		if (ret)
-			return ret;
-		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
-		if (ret == 0)
-			ret = count;
-		debugfs_file_put(file->f_path.dentry);
-	}
-
-	return ret;
-}
-
-static const struct file_operations pseudo_measure_fops = {
-	.write = pseudo_lock_measure_trigger,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-/**
- * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-lock region belongs
- *
- * Called when a resource group in the pseudo-locksetup mode receives a
- * valid schemata that should be pseudo-locked. Since the resource group is
- * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
- * allocated and initialized with the essential information. If a failure
- * occurs the resource group remains in the pseudo-locksetup mode with the
- * &struct pseudo_lock_region associated with it, but cleared from all
- * information and ready for the user to re-attempt pseudo-locking by
- * writing the schemata again.
- *
- * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
- * on failure. Descriptive error will be written to last_cmd_status buffer.
- */
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-	struct task_struct *thread;
-	unsigned int new_minor;
-	struct device *dev;
-	int ret;
-
-	ret = pseudo_lock_region_alloc(plr);
-	if (ret < 0)
-		return ret;
-
-	ret = pseudo_lock_cstates_constrain(plr);
-	if (ret < 0) {
-		ret = -EINVAL;
-		goto out_region;
-	}
-
-	plr->thread_done = 0;
-
-	thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp,
-				    plr->cpu, "pseudo_lock/%u");
-	if (IS_ERR(thread)) {
-		ret = PTR_ERR(thread);
-		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
-		goto out_cstates;
-	}
-
-	ret = wait_event_interruptible(plr->lock_thread_wq,
-				       plr->thread_done == 1);
-	if (ret < 0) {
-		/*
-		 * If the thread does not get on the CPU for whatever
-		 * reason and the process which sets up the region is
-		 * interrupted then this will leave the thread in runnable
-		 * state and once it gets on the CPU it will dereference
-		 * the cleared, but not freed, plr struct resulting in an
-		 * empty pseudo-locking loop.
-		 */
-		rdt_last_cmd_puts("Locking thread interrupted\n");
-		goto out_cstates;
-	}
-
-	ret = pseudo_lock_minor_get(&new_minor);
-	if (ret < 0) {
-		rdt_last_cmd_puts("Unable to obtain a new minor number\n");
-		goto out_cstates;
-	}
-
-	/*
-	 * Unlock access but do not release the reference. The
-	 * pseudo-locked region will still be here on return.
-	 *
-	 * The mutex has to be released temporarily to avoid a potential
-	 * deadlock with the mm->mmap_lock which is obtained in the
-	 * device_create() and debugfs_create_dir() callpath below as well as
-	 * before the mmap() callback is called.
-	 */
-	mutex_unlock(&rdtgroup_mutex);
-
-	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-						      debugfs_resctrl);
-		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
-			debugfs_create_file("pseudo_lock_measure", 0200,
-					    plr->debugfs_dir, rdtgrp,
-					    &pseudo_measure_fops);
-	}
-
-	dev = device_create(&pseudo_lock_class, NULL,
-			    MKDEV(pseudo_lock_major, new_minor),
-			    rdtgrp, "%s", rdtgrp->kn->name);
-
-	mutex_lock(&rdtgroup_mutex);
-
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
-		rdt_last_cmd_printf("Failed to create character device: %d\n",
-				    ret);
-		goto out_debugfs;
-	}
-
-	/* We released the mutex - check if group was removed while we did so */
-	if (rdtgrp->flags & RDT_DELETED) {
-		ret = -ENODEV;
-		goto out_device;
-	}
-
-	plr->minor = new_minor;
-
-	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
-	closid_free(rdtgrp->closid);
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
-
-	ret = 0;
-	goto out;
-
-out_device:
-	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
-out_debugfs:
-	debugfs_remove_recursive(plr->debugfs_dir);
-	pseudo_lock_minor_release(new_minor);
-out_cstates:
-	pseudo_lock_cstates_relax(plr);
-out_region:
-	pseudo_lock_region_clear(plr);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
- * @rdtgrp: resource group to which the pseudo-locked region belongs
- *
- * The removal of a pseudo-locked region can be initiated when the resource
- * group is removed from user space via a "rmdir" from userspace or the
- * unmount of the resctrl filesystem. On removal the resource group does
- * not go back to pseudo-locksetup mode before it is removed, instead it is
- * removed directly. There is thus asymmetry with the creation where the
- * &struct pseudo_lock_region is removed here while it was not created in
- * rdtgroup_pseudo_lock_create().
- *
- * Return: void
- */
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		/*
-		 * Default group cannot be a pseudo-locked region so we can
-		 * free closid here.
-		 */
-		closid_free(rdtgrp->closid);
-		goto free;
-	}
-
-	pseudo_lock_cstates_relax(plr);
-	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
-	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
-	pseudo_lock_minor_release(plr->minor);
-
-free:
-	pseudo_lock_free(rdtgrp);
-}
-
-static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
-{
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgrp = region_find_by_minor(iminor(inode));
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	filp->private_data = rdtgrp;
-	atomic_inc(&rdtgrp->waitcount);
-	/* Perform a non-seekable open - llseek is not supported */
-	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-
-	mutex_unlock(&rdtgroup_mutex);
-
-	return 0;
-}
-
-static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
-{
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-	rdtgrp = filp->private_data;
-	WARN_ON(!rdtgrp);
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-	filp->private_data = NULL;
-	atomic_dec(&rdtgrp->waitcount);
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
-{
-	/* Not supported */
-	return -EINVAL;
-}
-
-static const struct vm_operations_struct pseudo_mmap_ops = {
-	.mremap = pseudo_lock_dev_mremap,
-};
-
-static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	unsigned long vsize = vma->vm_end - vma->vm_start;
-	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
-	struct pseudo_lock_region *plr;
-	struct rdtgroup *rdtgrp;
-	unsigned long physical;
-	unsigned long psize;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgrp = filp->private_data;
-	WARN_ON(!rdtgrp);
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	plr = rdtgrp->plr;
-
-	if (!plr->d) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	/*
-	 * Task is required to run with affinity to the cpus associated
-	 * with the pseudo-locked region. If this is not the case the task
-	 * may be scheduled elsewhere and invalidate entries in the
-	 * pseudo-locked region.
-	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EINVAL;
-	}
-
-	physical = __pa(plr->kmem) >> PAGE_SHIFT;
-	psize = plr->size - off;
-
-	if (off > plr->size) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENOSPC;
-	}
-
-	/*
-	 * Ensure changes are carried directly to the memory being mapped,
-	 * do not allow copy-on-write mapping.
-	 */
-	if (!(vma->vm_flags & VM_SHARED)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EINVAL;
-	}
-
-	if (vsize > psize) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENOSPC;
-	}
-
-	memset(plr->kmem + off, 0, vsize);
-
-	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
-			    vsize, vma->vm_page_prot)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EAGAIN;
-	}
-	vma->vm_ops = &pseudo_mmap_ops;
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static const struct file_operations pseudo_lock_dev_fops = {
-	.owner =	THIS_MODULE,
-	.read =		NULL,
-	.write =	NULL,
-	.open =		pseudo_lock_dev_open,
-	.release =	pseudo_lock_dev_release,
-	.mmap =		pseudo_lock_dev_mmap,
-};
-
-int rdt_pseudo_lock_init(void)
-{
-	int ret;
-
-	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
-	if (ret < 0)
-		return ret;
-
-	pseudo_lock_major = ret;
-
-	ret = class_register(&pseudo_lock_class);
-	if (ret) {
-		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
-		return ret;
-	}
-
-	return 0;
-}
-
-void rdt_pseudo_lock_release(void)
-{
-	class_unregister(&pseudo_lock_class);
-	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
-	pseudo_lock_major = 0;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/trace.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
index 2a506316b303..7c8aef08010f 100644
--- a/arch/x86/kernel/cpu/resctrl/trace.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
@@ -2,8 +2,8 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM resctrl
 
-#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_RESCTRL_H
+#if !defined(_X86_RESCTRL_PSEUDO_LOCK_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _X86_RESCTRL_PSEUDO_LOCK_TRACE_H
 
 #include <linux/tracepoint.h>
 
@@ -35,25 +35,11 @@ TRACE_EVENT(pseudo_lock_l3,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l3_hits, __entry->l3_miss));
 
-TRACE_EVENT(mon_llc_occupancy_limbo,
-	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
-	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
-	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
-			     __field(u32, mon_hw_id)
-			     __field(int, domain_id)
-			     __field(u64, llc_occupancy_bytes)),
-	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
-			   __entry->mon_hw_id = mon_hw_id;
-			   __entry->domain_id = domain_id;
-			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
-	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
-		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
-		      __entry->llc_occupancy_bytes)
-	   );
-
-#endif /* _TRACE_RESCTRL_H */
+#endif /* _X86_RESCTRL_PSEUDO_LOCK_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace
+
+#define TRACE_INCLUDE_FILE pseudo_lock_trace
+
 #include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6419e04d8a7b..885026468440 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -18,6 +18,7 @@
 #include <linux/fs_parser.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
+#include <linux/resctrl.h>
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
 #include <linux/sched/signal.h>
@@ -28,333 +29,28 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-
-/* Mutex to protect rdtgroup access. */
-DEFINE_MUTEX(rdtgroup_mutex);
-
-static struct kernfs_root *rdt_root;
-struct rdtgroup rdtgroup_default;
-LIST_HEAD(rdt_all_groups);
-
-/* list of entries for the schemata file */
-LIST_HEAD(resctrl_schema_all);
-
-/* The filesystem can only be mounted once. */
-bool resctrl_mounted;
-
-/* Kernel fs node for "info" directory under root */
-static struct kernfs_node *kn_info;
-
-/* Kernel fs node for "mon_groups" directory under root */
-static struct kernfs_node *kn_mongrp;
-
-/* Kernel fs node for "mon_data" directory under root */
-static struct kernfs_node *kn_mondata;
-
-static struct seq_buf last_cmd_status;
-static char last_cmd_status_buf[512];
-
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
-static void rdtgroup_destroy_root(void);
-
-struct dentry *debugfs_resctrl;
-
-/*
- * Memory bandwidth monitoring event to use for the default CTRL_MON group
- * and each new CTRL_MON group created by the user.  Only relevant when
- * the filesystem is mounted with the "mba_MBps" option so it does not
- * matter that it remains uninitialized on systems that do not support
- * the "mba_MBps" option.
- */
-enum resctrl_event_id mba_mbps_default_event;
-
-static bool resctrl_debug;
-
-void rdt_last_cmd_clear(void)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_clear(&last_cmd_status);
-}
-
-void rdt_last_cmd_puts(const char *s)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_puts(&last_cmd_status, s);
-}
-
-void rdt_last_cmd_printf(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_vprintf(&last_cmd_status, fmt, ap);
-	va_end(ap);
-}
-
-void rdt_staged_configs_clear(void)
-{
-	struct rdt_ctrl_domain *dom;
-	struct rdt_resource *r;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
-			memset(dom->staged_config, 0, sizeof(dom->staged_config));
-	}
-}
-
-/*
- * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
- * we can keep a bitmap of free CLOSIDs in a single integer.
- *
- * Using a global CLOSID across all resources has some advantages and
- * some drawbacks:
- * + We can simply set current's closid to assign a task to a resource
- *   group.
- * + Context switch code can avoid extra memory references deciding which
- *   CLOSID to load into the PQR_ASSOC MSR
- * - We give up some options in configuring resource groups across multi-socket
- *   systems.
- * - Our choices on how to configure each resource become progressively more
- *   limited as the number of resources grows.
- */
-static unsigned long closid_free_map;
-static int closid_free_map_len;
-
-int closids_supported(void)
-{
-	return closid_free_map_len;
-}
-
-static void closid_init(void)
-{
-	struct resctrl_schema *s;
-	u32 rdt_min_closid = 32;
-
-	/* Compute rdt_min_closid across all resources */
-	list_for_each_entry(s, &resctrl_schema_all, list)
-		rdt_min_closid = min(rdt_min_closid, s->num_closid);
-
-	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
-
-	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
-	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
-	closid_free_map_len = rdt_min_closid;
-}
-
-static int closid_alloc(void)
-{
-	int cleanest_closid;
-	u32 closid;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		cleanest_closid = resctrl_find_cleanest_closid();
-		if (cleanest_closid < 0)
-			return cleanest_closid;
-		closid = cleanest_closid;
-	} else {
-		closid = ffs(closid_free_map);
-		if (closid == 0)
-			return -ENOSPC;
-		closid--;
-	}
-	__clear_bit(closid, &closid_free_map);
-
-	return closid;
-}
-
-void closid_free(int closid)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	__set_bit(closid, &closid_free_map);
-}
-
-/**
- * closid_allocated - test if provided closid is in use
- * @closid: closid to be tested
- *
- * Return: true if @closid is currently associated with a resource group,
- * false if @closid is free
- */
-bool closid_allocated(unsigned int closid)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	return !test_bit(closid, &closid_free_map);
-}
-
-/**
- * rdtgroup_mode_by_closid - Return mode of resource group with closid
- * @closid: closid if the resource group
- *
- * Each resource group is associated with a @closid. Here the mode
- * of a resource group can be queried by searching for it using its closid.
- *
- * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
- */
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
-{
-	struct rdtgroup *rdtgrp;
-
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (rdtgrp->closid == closid)
-			return rdtgrp->mode;
-	}
-
-	return RDT_NUM_MODES;
-}
-
-static const char * const rdt_mode_str[] = {
-	[RDT_MODE_SHAREABLE]		= "shareable",
-	[RDT_MODE_EXCLUSIVE]		= "exclusive",
-	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
-	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
-};
-
-/**
- * rdtgroup_mode_str - Return the string representation of mode
- * @mode: the resource group mode as &enum rdtgroup_mode
- *
- * Return: string representation of valid mode, "unknown" otherwise
- */
-static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
-{
-	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
-		return "unknown";
-
-	return rdt_mode_str[mode];
-}
-
-/* set uid and gid of rdtgroup dirs and files to that of the creator */
-static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
-{
-	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
-				.ia_uid = current_fsuid(),
-				.ia_gid = current_fsgid(), };
-
-	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
-	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
-		return 0;
-
-	return kernfs_setattr(kn, &iattr);
-}
-
-static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
-{
-	struct kernfs_node *kn;
-	int ret;
-
-	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-				  0, rft->kf_ops, rft, NULL, NULL);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
-{
-	struct kernfs_open_file *of = m->private;
-	struct rftype *rft = of->kn->priv;
-
-	if (rft->seq_show)
-		return rft->seq_show(of, m, arg);
-	return 0;
-}
-
-static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
-				   size_t nbytes, loff_t off)
-{
-	struct rftype *rft = of->kn->priv;
-
-	if (rft->write)
-		return rft->write(of, buf, nbytes, off);
-
-	return -EINVAL;
-}
-
-static const struct kernfs_ops rdtgroup_kf_single_ops = {
-	.atomic_write_len	= PAGE_SIZE,
-	.write			= rdtgroup_file_write,
-	.seq_show		= rdtgroup_seqfile_show,
-};
-
-static const struct kernfs_ops kf_mondata_ops = {
-	.atomic_write_len	= PAGE_SIZE,
-	.seq_show		= rdtgroup_mondata_show,
-};
 
-static bool is_cpu_list(struct kernfs_open_file *of)
-{
-	struct rftype *rft = of->kn->priv;
-
-	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
-}
-
-static int rdtgroup_cpus_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	struct cpumask *mask;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-
-	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			if (!rdtgrp->plr->d) {
-				rdt_last_cmd_clear();
-				rdt_last_cmd_puts("Cache domain offline\n");
-				ret = -ENODEV;
-			} else {
-				mask = &rdtgrp->plr->d->hdr.cpu_mask;
-				seq_printf(s, is_cpu_list(of) ?
-					   "%*pbl\n" : "%*pb\n",
-					   cpumask_pr_args(mask));
-			}
-		} else {
-			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-				   cpumask_pr_args(&rdtgrp->cpu_mask));
-		}
-	} else {
-		ret = -ENOENT;
-	}
-	rdtgroup_kn_unlock(of->kn);
+DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
-	return ret;
-}
+DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 /*
- * This is safe against resctrl_sched_in() called from __switch_to()
+ * This is safe against resctrl_arch_sched_in() called from __switch_to()
  * because __switch_to() is executed with interrupts disabled. A local call
  * from update_closid_rmid() is protected against __switch_to() because
  * preemption is disabled.
  */
-static void update_cpu_closid_rmid(void *info)
+void resctrl_arch_sync_cpu_closid_rmid(void *info)
 {
-	struct rdtgroup *r = info;
+	struct resctrl_cpu_defaults *r = info;
 
 	if (r) {
 		this_cpu_write(pqr_state.default_closid, r->closid);
-		this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
+		this_cpu_write(pqr_state.default_rmid, r->rmid);
 	}
 
 	/*
@@ -362,1201 +58,9 @@ static void update_cpu_closid_rmid(void *info)
 	 * executing task might have its own closid selected. Just reuse
 	 * the context switch code.
 	 */
-	resctrl_sched_in(current);
-}
-
-/*
- * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
- *
- * Per task closids/rmids must have been set up before calling this function.
- */
-static void
-update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
-{
-	on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1);
-}
-
-static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
-			  cpumask_var_t tmpmask)
-{
-	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
-	struct list_head *head;
-
-	/* Check whether cpus belong to parent ctrl group */
-	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
-		return -EINVAL;
-	}
-
-	/* Check whether cpus are dropped from this group */
-	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (!cpumask_empty(tmpmask)) {
-		/* Give any dropped cpus to parent rdtgroup */
-		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
-		update_closid_rmid(tmpmask, prgrp);
-	}
-
-	/*
-	 * If we added cpus, remove them from previous group that owned them
-	 * and update per-cpu rmid
-	 */
-	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-			if (crgrp == rdtgrp)
-				continue;
-			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
-				       tmpmask);
-		}
-		update_closid_rmid(tmpmask, rdtgrp);
-	}
-
-	/* Done pushing/pulling - update this group with new mask */
-	cpumask_copy(&rdtgrp->cpu_mask, newmask);
-
-	return 0;
-}
-
-static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
-{
-	struct rdtgroup *crgrp;
-
-	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
-	/* update the child mon group masks as well*/
-	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
-		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
+	resctrl_arch_sched_in(current);
 }
 
-static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
-			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
-{
-	struct rdtgroup *r, *crgrp;
-	struct list_head *head;
-
-	/* Check whether cpus are dropped from this group */
-	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (!cpumask_empty(tmpmask)) {
-		/* Can't drop from default group */
-		if (rdtgrp == &rdtgroup_default) {
-			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
-			return -EINVAL;
-		}
-
-		/* Give any dropped cpus to rdtgroup_default */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, tmpmask);
-		update_closid_rmid(tmpmask, &rdtgroup_default);
-	}
-
-	/*
-	 * If we added cpus, remove them from previous group and
-	 * the prev group's child groups that owned them
-	 * and update per-cpu closid/rmid.
-	 */
-	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
-			if (r == rdtgrp)
-				continue;
-			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
-			if (!cpumask_empty(tmpmask1))
-				cpumask_rdtgrp_clear(r, tmpmask1);
-		}
-		update_closid_rmid(tmpmask, rdtgrp);
-	}
-
-	/* Done pushing/pulling - update this group with new mask */
-	cpumask_copy(&rdtgrp->cpu_mask, newmask);
-
-	/*
-	 * Clear child mon group masks since there is a new parent mask
-	 * now and update the rmid for the cpus the child lost.
-	 */
-	head = &rdtgrp->mon.crdtgrp_list;
-	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
-		update_closid_rmid(tmpmask, rdtgrp);
-		cpumask_clear(&crgrp->cpu_mask);
-	}
-
-	return 0;
-}
-
-static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
-				   char *buf, size_t nbytes, loff_t off)
-{
-	cpumask_var_t tmpmask, newmask, tmpmask1;
-	struct rdtgroup *rdtgrp;
-	int ret;
-
-	if (!buf)
-		return -EINVAL;
-
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		return -ENOMEM;
-	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
-		free_cpumask_var(tmpmask);
-		return -ENOMEM;
-	}
-	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
-		free_cpumask_var(tmpmask);
-		free_cpumask_var(newmask);
-		return -ENOMEM;
-	}
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		ret = -ENOENT;
-		goto unlock;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
-	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto unlock;
-	}
-
-	if (is_cpu_list(of))
-		ret = cpulist_parse(buf, newmask);
-	else
-		ret = cpumask_parse(buf, newmask);
-
-	if (ret) {
-		rdt_last_cmd_puts("Bad CPU list/mask\n");
-		goto unlock;
-	}
-
-	/* check that user didn't specify any offline cpus */
-	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
-	if (!cpumask_empty(tmpmask)) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Can only assign online CPUs\n");
-		goto unlock;
-	}
-
-	if (rdtgrp->type == RDTCTRL_GROUP)
-		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
-	else if (rdtgrp->type == RDTMON_GROUP)
-		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
-	else
-		ret = -EINVAL;
-
-unlock:
-	rdtgroup_kn_unlock(of->kn);
-	free_cpumask_var(tmpmask);
-	free_cpumask_var(newmask);
-	free_cpumask_var(tmpmask1);
-
-	return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_remove - the helper to remove resource group safely
- * @rdtgrp: resource group to remove
- *
- * On resource group creation via a mkdir, an extra kernfs_node reference is
- * taken to ensure that the rdtgroup structure remains accessible for the
- * rdtgroup_kn_unlock() calls where it is removed.
- *
- * Drop the extra reference here, then free the rdtgroup structure.
- *
- * Return: void
- */
-static void rdtgroup_remove(struct rdtgroup *rdtgrp)
-{
-	kernfs_put(rdtgrp->kn);
-	kfree(rdtgrp);
-}
-
-static void _update_task_closid_rmid(void *task)
-{
-	/*
-	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
-	 * Otherwise, the MSR is updated when the task is scheduled in.
-	 */
-	if (task == current)
-		resctrl_sched_in(task);
-}
-
-static void update_task_closid_rmid(struct task_struct *t)
-{
-	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
-		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
-	else
-		_update_task_closid_rmid(t);
-}
-
-static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
-{
-	u32 closid, rmid = rdtgrp->mon.rmid;
-
-	if (rdtgrp->type == RDTCTRL_GROUP)
-		closid = rdtgrp->closid;
-	else if (rdtgrp->type == RDTMON_GROUP)
-		closid = rdtgrp->mon.parent->closid;
-	else
-		return false;
-
-	return resctrl_arch_match_closid(tsk, closid) &&
-	       resctrl_arch_match_rmid(tsk, closid, rmid);
-}
-
-static int __rdtgroup_move_task(struct task_struct *tsk,
-				struct rdtgroup *rdtgrp)
-{
-	/* If the task is already in rdtgrp, no need to move the task. */
-	if (task_in_rdtgroup(tsk, rdtgrp))
-		return 0;
-
-	/*
-	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
-	 * updated by them.
-	 *
-	 * For ctrl_mon groups, move both closid and rmid.
-	 * For monitor groups, can move the tasks only from
-	 * their parent CTRL group.
-	 */
-	if (rdtgrp->type == RDTMON_GROUP &&
-	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
-		rdt_last_cmd_puts("Can't move task to different control group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgrp->type == RDTMON_GROUP)
-		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
-					     rdtgrp->mon.rmid);
-	else
-		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
-					     rdtgrp->mon.rmid);
-
-	/*
-	 * Ensure the task's closid and rmid are written before determining if
-	 * the task is current that will decide if it will be interrupted.
-	 * This pairs with the full barrier between the rq->curr update and
-	 * resctrl_sched_in() during context switch.
-	 */
-	smp_mb();
-
-	/*
-	 * By now, the task's closid and rmid are set. If the task is current
-	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
-	 * group go into effect. If the task is not current, the MSR will be
-	 * updated when the task is scheduled in.
-	 */
-	update_task_closid_rmid(tsk);
-
-	return 0;
-}
-
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
-		resctrl_arch_match_closid(t, r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
-		resctrl_arch_match_rmid(t, r->mon.parent->closid,
-					r->mon.rmid));
-}
-
-/**
- * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
- * @r: Resource group
- *
- * Return: 1 if tasks have been assigned to @r, 0 otherwise
- */
-int rdtgroup_tasks_assigned(struct rdtgroup *r)
-{
-	struct task_struct *p, *t;
-	int ret = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	rcu_read_lock();
-	for_each_process_thread(p, t) {
-		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
-			ret = 1;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int rdtgroup_task_write_permission(struct task_struct *task,
-					  struct kernfs_open_file *of)
-{
-	const struct cred *tcred = get_task_cred(task);
-	const struct cred *cred = current_cred();
-	int ret = 0;
-
-	/*
-	 * Even if we're attaching all tasks in the thread group, we only
-	 * need to check permissions on one of them.
-	 */
-	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
-	    !uid_eq(cred->euid, tcred->uid) &&
-	    !uid_eq(cred->euid, tcred->suid)) {
-		rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
-		ret = -EPERM;
-	}
-
-	put_cred(tcred);
-	return ret;
-}
-
-static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
-			      struct kernfs_open_file *of)
-{
-	struct task_struct *tsk;
-	int ret;
-
-	rcu_read_lock();
-	if (pid) {
-		tsk = find_task_by_vpid(pid);
-		if (!tsk) {
-			rcu_read_unlock();
-			rdt_last_cmd_printf("No task %d\n", pid);
-			return -ESRCH;
-		}
-	} else {
-		tsk = current;
-	}
-
-	get_task_struct(tsk);
-	rcu_read_unlock();
-
-	ret = rdtgroup_task_write_permission(tsk, of);
-	if (!ret)
-		ret = __rdtgroup_move_task(tsk, rdtgrp);
-
-	put_task_struct(tsk);
-	return ret;
-}
-
-static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
-				    char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	char *pid_str;
-	int ret = 0;
-	pid_t pid;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
-	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto unlock;
-	}
-
-	while (buf && buf[0] != '\0' && buf[0] != '\n') {
-		pid_str = strim(strsep(&buf, ","));
-
-		if (kstrtoint(pid_str, 0, &pid)) {
-			rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
-			ret = -EINVAL;
-			break;
-		}
-
-		if (pid < 0) {
-			rdt_last_cmd_printf("Invalid pid %d\n", pid);
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = rdtgroup_move_task(pid, rdtgrp, of);
-		if (ret) {
-			rdt_last_cmd_printf("Error while processing task %d\n", pid);
-			break;
-		}
-	}
-
-unlock:
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret ?: nbytes;
-}
-
-static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
-{
-	struct task_struct *p, *t;
-	pid_t pid;
-
-	rcu_read_lock();
-	for_each_process_thread(p, t) {
-		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
-			pid = task_pid_vnr(t);
-			if (pid)
-				seq_printf(s, "%d\n", pid);
-		}
-	}
-	rcu_read_unlock();
-}
-
-static int rdtgroup_tasks_show(struct kernfs_open_file *of,
-			       struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		show_rdt_tasks(rdtgrp, s);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-static int rdtgroup_closid_show(struct kernfs_open_file *of,
-				struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		seq_printf(s, "%u\n", rdtgrp->closid);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-static int rdtgroup_rmid_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		seq_printf(s, "%u\n", rdtgrp->mon.rmid);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-#ifdef CONFIG_PROC_CPU_RESCTRL
-
-/*
- * A task can only be part of one resctrl control group and of one monitor
- * group which is associated to that control group.
- *
- * 1)   res:
- *      mon:
- *
- *    resctrl is not available.
- *
- * 2)   res:/
- *      mon:
- *
- *    Task is part of the root resctrl control group, and it is not associated
- *    to any monitor group.
- *
- * 3)  res:/
- *     mon:mon0
- *
- *    Task is part of the root resctrl control group and monitor group mon0.
- *
- * 4)  res:group0
- *     mon:
- *
- *    Task is part of resctrl control group group0, and it is not associated
- *    to any monitor group.
- *
- * 5) res:group0
- *    mon:mon1
- *
- *    Task is part of resctrl control group group0 and monitor group mon1.
- */
-int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
-		      struct pid *pid, struct task_struct *tsk)
-{
-	struct rdtgroup *rdtg;
-	int ret = 0;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	/* Return empty if resctrl has not been mounted. */
-	if (!resctrl_mounted) {
-		seq_puts(s, "res:\nmon:\n");
-		goto unlock;
-	}
-
-	list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
-		struct rdtgroup *crg;
-
-		/*
-		 * Task information is only relevant for shareable
-		 * and exclusive groups.
-		 */
-		if (rdtg->mode != RDT_MODE_SHAREABLE &&
-		    rdtg->mode != RDT_MODE_EXCLUSIVE)
-			continue;
-
-		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
-			continue;
-
-		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
-			   rdtg->kn->name);
-		seq_puts(s, "mon:");
-		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
-				    mon.crdtgrp_list) {
-			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
-						     crg->mon.rmid))
-				continue;
-			seq_printf(s, "%s", crg->kn->name);
-			break;
-		}
-		seq_putc(s, '\n');
-		goto unlock;
-	}
-	/*
-	 * The above search should succeed. Otherwise return
-	 * with an error.
-	 */
-	ret = -ENOENT;
-unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return ret;
-}
-#endif
-
-static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
-				    struct seq_file *seq, void *v)
-{
-	int len;
-
-	mutex_lock(&rdtgroup_mutex);
-	len = seq_buf_used(&last_cmd_status);
-	if (len)
-		seq_printf(seq, "%.*s", len, last_cmd_status_buf);
-	else
-		seq_puts(seq, "ok\n");
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static int rdt_num_closids_show(struct kernfs_open_file *of,
-				struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-
-	seq_printf(seq, "%u\n", s->num_closid);
-	return 0;
-}
-
-static int rdt_default_ctrl_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%x\n", r->default_ctrl);
-	return 0;
-}
-
-static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
-	return 0;
-}
-
-static int rdt_shareable_bits_show(struct kernfs_open_file *of,
-				   struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%x\n", r->cache.shareable_bits);
-	return 0;
-}
-
-/*
- * rdt_bit_usage_show - Display current usage of resources
- *
- * A domain is a shared resource that can now be allocated differently. Here
- * we display the current regions of the domain as an annotated bitmask.
- * For each domain of this resource its allocation bitmask
- * is annotated as below to indicate the current usage of the corresponding bit:
- *   0 - currently unused
- *   X - currently available for sharing and used by software and hardware
- *   H - currently used by hardware only but available for software use
- *   S - currently used and shareable by software only
- *   E - currently used exclusively by one resource group
- *   P - currently pseudo-locked by one resource group
- */
-static int rdt_bit_usage_show(struct kernfs_open_file *of,
-			      struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	/*
-	 * Use unsigned long even though only 32 bits are used to ensure
-	 * test_bit() is used safely.
-	 */
-	unsigned long sw_shareable = 0, hw_shareable = 0;
-	unsigned long exclusive = 0, pseudo_locked = 0;
-	struct rdt_resource *r = s->res;
-	struct rdt_ctrl_domain *dom;
-	int i, hwb, swb, excl, psl;
-	enum rdtgrp_mode mode;
-	bool sep = false;
-	u32 ctrl_val;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-	hw_shareable = r->cache.shareable_bits;
-	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
-		if (sep)
-			seq_putc(seq, ';');
-		sw_shareable = 0;
-		exclusive = 0;
-		seq_printf(seq, "%d=", dom->hdr.id);
-		for (i = 0; i < closids_supported(); i++) {
-			if (!closid_allocated(i))
-				continue;
-			ctrl_val = resctrl_arch_get_config(r, dom, i,
-							   s->conf_type);
-			mode = rdtgroup_mode_by_closid(i);
-			switch (mode) {
-			case RDT_MODE_SHAREABLE:
-				sw_shareable |= ctrl_val;
-				break;
-			case RDT_MODE_EXCLUSIVE:
-				exclusive |= ctrl_val;
-				break;
-			case RDT_MODE_PSEUDO_LOCKSETUP:
-			/*
-			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
-			 * here but not included since the CBM
-			 * associated with this CLOSID in this mode
-			 * is not initialized and no task or cpu can be
-			 * assigned this CLOSID.
-			 */
-				break;
-			case RDT_MODE_PSEUDO_LOCKED:
-			case RDT_NUM_MODES:
-				WARN(1,
-				     "invalid mode for closid %d\n", i);
-				break;
-			}
-		}
-		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
-			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
-			hwb = test_bit(i, &hw_shareable);
-			swb = test_bit(i, &sw_shareable);
-			excl = test_bit(i, &exclusive);
-			psl = test_bit(i, &pseudo_locked);
-			if (hwb && swb)
-				seq_putc(seq, 'X');
-			else if (hwb && !swb)
-				seq_putc(seq, 'H');
-			else if (!hwb && swb)
-				seq_putc(seq, 'S');
-			else if (excl)
-				seq_putc(seq, 'E');
-			else if (psl)
-				seq_putc(seq, 'P');
-			else /* Unused bits remain */
-				seq_putc(seq, '0');
-		}
-		sep = true;
-	}
-	seq_putc(seq, '\n');
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return 0;
-}
-
-static int rdt_min_bw_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.min_bw);
-	return 0;
-}
-
-static int rdt_num_rmids_show(struct kernfs_open_file *of,
-			      struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-
-	seq_printf(seq, "%d\n", r->num_rmid);
-
-	return 0;
-}
-
-static int rdt_mon_features_show(struct kernfs_open_file *of,
-				 struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-	struct mon_evt *mevt;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
-		seq_printf(seq, "%s\n", mevt->name);
-		if (mevt->configurable)
-			seq_printf(seq, "%s_config\n", mevt->name);
-	}
-
-	return 0;
-}
-
-static int rdt_bw_gran_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.bw_gran);
-	return 0;
-}
-
-static int rdt_delay_linear_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.delay_linear);
-	return 0;
-}
-
-static int max_threshold_occ_show(struct kernfs_open_file *of,
-				  struct seq_file *seq, void *v)
-{
-	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
-
-	return 0;
-}
-
-static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
-					 struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
-		seq_puts(seq, "per-thread\n");
-	else
-		seq_puts(seq, "max\n");
-
-	return 0;
-}
-
-static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
-				       char *buf, size_t nbytes, loff_t off)
-{
-	unsigned int bytes;
-	int ret;
-
-	ret = kstrtouint(buf, 0, &bytes);
-	if (ret)
-		return ret;
-
-	if (bytes > resctrl_rmid_realloc_limit)
-		return -EINVAL;
-
-	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
-
-	return nbytes;
-}
-
-/*
- * rdtgroup_mode_show - Display mode of this resource group
- */
-static int rdtgroup_mode_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
-
-	rdtgroup_kn_unlock(of->kn);
-	return 0;
-}
-
-static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
-{
-	switch (my_type) {
-	case CDP_CODE:
-		return CDP_DATA;
-	case CDP_DATA:
-		return CDP_CODE;
-	default:
-	case CDP_NONE:
-		return CDP_NONE;
-	}
-}
-
-static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
-					struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = of->kn->parent->priv;
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
-
-	return 0;
-}
-
-/**
- * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
- * @r: Resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @type: CDP type of @r.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Checks if provided @cbm intended to be used for @closid on domain
- * @d overlaps with any other closids or other hardware usage associated
- * with this domain. If @exclusive is true then only overlaps with
- * resource groups in exclusive mode will be considered. If @exclusive
- * is false then overlaps with any resource group or hardware entities
- * will be considered.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: false if CBM does not overlap, true if it does.
- */
-static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
-				    unsigned long cbm, int closid,
-				    enum resctrl_conf_type type, bool exclusive)
-{
-	enum rdtgrp_mode mode;
-	unsigned long ctrl_b;
-	int i;
-
-	/* Check for any overlap with regions used by hardware directly */
-	if (!exclusive) {
-		ctrl_b = r->cache.shareable_bits;
-		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
-			return true;
-	}
-
-	/* Check for overlap with other resource groups */
-	for (i = 0; i < closids_supported(); i++) {
-		ctrl_b = resctrl_arch_get_config(r, d, i, type);
-		mode = rdtgroup_mode_by_closid(i);
-		if (closid_allocated(i) && i != closid &&
-		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
-			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
-				if (exclusive) {
-					if (mode == RDT_MODE_EXCLUSIVE)
-						return true;
-					continue;
-				}
-				return true;
-			}
-		}
-	}
-
-	return false;
-}
-
-/**
- * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
- * @s: Schema for the resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Resources that can be allocated using a CBM can use the CBM to control
- * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
- * for overlap. Overlap test is not limited to the specific resource for
- * which the CBM is intended though - when dealing with CDP resources that
- * share the underlying hardware the overlap check should be performed on
- * the CDP resource sharing the hardware also.
- *
- * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
- * overlap test.
- *
- * Return: true if CBM overlap detected, false if there is no overlap
- */
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
-			   unsigned long cbm, int closid, bool exclusive)
-{
-	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
-	struct rdt_resource *r = s->res;
-
-	if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
-				    exclusive))
-		return true;
-
-	if (!resctrl_arch_get_cdp_enabled(r->rid))
-		return false;
-	return  __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
-}
-
-/**
- * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
- * @rdtgrp: Resource group identified through its closid.
- *
- * An exclusive resource group implies that there should be no sharing of
- * its allocated resources. At the time this group is considered to be
- * exclusive this test can determine if its current schemata supports this
- * setting by testing for overlap with all other resource groups.
- *
- * Return: true if resource group can be exclusive, false if there is overlap
- * with allocations of other resource groups and thus this resource group
- * cannot be exclusive.
- */
-static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
-{
-	int closid = rdtgrp->closid;
-	struct rdt_ctrl_domain *d;
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	bool has_cache = false;
-	u32 ctrl;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
-			continue;
-		has_cache = true;
-		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-			ctrl = resctrl_arch_get_config(r, d, closid,
-						       s->conf_type);
-			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
-				rdt_last_cmd_puts("Schemata overlaps\n");
-				return false;
-			}
-		}
-	}
-
-	if (!has_cache) {
-		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
-		return false;
-	}
-
-	return true;
-}
-
-/*
- * rdtgroup_mode_write - Modify the resource group's mode
- */
-static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
-				   char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	enum rdtgrp_mode mode;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	rdt_last_cmd_clear();
-
-	mode = rdtgrp->mode;
-
-	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
-	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
-	    (!strcmp(buf, "pseudo-locksetup") &&
-	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
-	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
-		goto out;
-
-	if (mode == RDT_MODE_PSEUDO_LOCKED) {
-		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (!strcmp(buf, "shareable")) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			ret = rdtgroup_locksetup_exit(rdtgrp);
-			if (ret)
-				goto out;
-		}
-		rdtgrp->mode = RDT_MODE_SHAREABLE;
-	} else if (!strcmp(buf, "exclusive")) {
-		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
-			ret = -EINVAL;
-			goto out;
-		}
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			ret = rdtgroup_locksetup_exit(rdtgrp);
-			if (ret)
-				goto out;
-		}
-		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
-	} else if (!strcmp(buf, "pseudo-locksetup")) {
-		ret = rdtgroup_locksetup_enter(rdtgrp);
-		if (ret)
-			goto out;
-		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
-	} else {
-		rdt_last_cmd_puts("Unknown or unsupported mode\n");
-		ret = -EINVAL;
-	}
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-	return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_cbm_to_size - Translate CBM to size in bytes
- * @r: RDT resource to which @d belongs.
- * @d: RDT domain instance.
- * @cbm: bitmask for which the size should be computed.
- *
- * The bitmask provided associated with the RDT domain instance @d will be
- * translated into how many bytes it represents. The size in bytes is
- * computed by first dividing the total cache size by the CBM length to
- * determine how many bytes each bit in the bitmask represents. The result
- * is multiplied with the number of bits set in the bitmask.
- *
- * @cbm is unsigned long, even if only 32 bits are used to make the
- * bitmap functions work correctly.
- */
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
-				  struct rdt_ctrl_domain *d, unsigned long cbm)
-{
-	unsigned int size = 0;
-	struct cacheinfo *ci;
-	int num_b;
-
-	if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
-		return size;
-
-	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
-	ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
-	if (ci)
-		size = ci->size / r->cache.cbm_len * num_b;
-
-	return size;
-}
-
-/*
- * rdtgroup_size_show - Display size in bytes of allocated regions
- *
- * The "size" file mirrors the layout of the "schemata" file, printing the
- * size in bytes of each region instead of the capacity bitmask.
- */
-static int rdtgroup_size_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct resctrl_schema *schema;
-	enum resctrl_conf_type type;
-	struct rdt_ctrl_domain *d;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	unsigned int size;
-	int ret = 0;
-	u32 closid;
-	bool sep;
-	u32 ctrl;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		if (!rdtgrp->plr->d) {
-			rdt_last_cmd_clear();
-			rdt_last_cmd_puts("Cache domain offline\n");
-			ret = -ENODEV;
-		} else {
-			seq_printf(s, "%*s:", max_name_width,
-				   rdtgrp->plr->s->name);
-			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
-						    rdtgrp->plr->d,
-						    rdtgrp->plr->cbm);
-			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
-		}
-		goto out;
-	}
-
-	closid = rdtgrp->closid;
-
-	list_for_each_entry(schema, &resctrl_schema_all, list) {
-		r = schema->res;
-		type = schema->conf_type;
-		sep = false;
-		seq_printf(s, "%*s:", max_name_width, schema->name);
-		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-			if (sep)
-				seq_putc(s, ';');
-			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-				size = 0;
-			} else {
-				if (is_mba_sc(r))
-					ctrl = d->mbps_val[closid];
-				else
-					ctrl = resctrl_arch_get_config(r, d,
-								       closid,
-								       type);
-				if (r->rid == RDT_RESOURCE_MBA ||
-				    r->rid == RDT_RESOURCE_SMBA)
-					size = ctrl;
-				else
-					size = rdtgroup_cbm_to_size(r, d, ctrl);
-			}
-			seq_printf(s, "%d=%u", d->hdr.id, size);
-			sep = true;
-		}
-		seq_putc(s, '\n');
-	}
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-struct mon_config_info {
-	u32 evtid;
-	u32 mon_config;
-};
-
 #define INVALID_CONFIG_INDEX   UINT_MAX
 
 /**
@@ -1581,681 +85,48 @@ static inline unsigned int mon_event_config_index_get(u32 evtid)
 	}
 }
 
-static void mon_event_config_read(void *info)
+void resctrl_arch_mon_event_config_read(void *_config_info)
 {
-	struct mon_config_info *mon_info = info;
+	struct resctrl_mon_config_info *config_info = _config_info;
 	unsigned int index;
 	u64 msrval;
 
-	index = mon_event_config_index_get(mon_info->evtid);
+	index = mon_event_config_index_get(config_info->evtid);
 	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
 	}
-	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
+	rdmsrq(MSR_IA32_EVT_CFG_BASE + index, msrval);
 
 	/* Report only the valid event configuration bits */
-	mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
-}
-
-static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info)
-{
-	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
+	config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
 }
 
-static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
+void resctrl_arch_mon_event_config_write(void *_config_info)
 {
-	struct mon_config_info mon_info;
-	struct rdt_mon_domain *dom;
-	bool sep = false;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
-		if (sep)
-			seq_puts(s, ";");
-
-		memset(&mon_info, 0, sizeof(struct mon_config_info));
-		mon_info.evtid = evtid;
-		mondata_config_read(dom, &mon_info);
-
-		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
-		sep = true;
-	}
-	seq_puts(s, "\n");
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return 0;
-}
-
-static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
-				       struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-
-	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	return 0;
-}
-
-static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
-				       struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-
-	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
-
-	return 0;
-}
-
-static void mon_event_config_write(void *info)
-{
-	struct mon_config_info *mon_info = info;
+	struct resctrl_mon_config_info *config_info = _config_info;
 	unsigned int index;
 
-	index = mon_event_config_index_get(mon_info->evtid);
+	index = mon_event_config_index_get(config_info->evtid);
 	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
-		return;
-	}
-	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
-}
-
-static void mbm_config_write_domain(struct rdt_resource *r,
-				    struct rdt_mon_domain *d, u32 evtid, u32 val)
-{
-	struct mon_config_info mon_info = {0};
-
-	/*
-	 * Read the current config value first. If both are the same then
-	 * no need to write it again.
-	 */
-	mon_info.evtid = evtid;
-	mondata_config_read(d, &mon_info);
-	if (mon_info.mon_config == val)
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
-
-	mon_info.mon_config = val;
-
-	/*
-	 * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
-	 * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
-	 * are scoped at the domain level. Writing any of these MSRs
-	 * on one CPU is observed by all the CPUs in the domain.
-	 */
-	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write,
-			      &mon_info, 1);
-
-	/*
-	 * When an Event Configuration is changed, the bandwidth counters
-	 * for all RMIDs and Events will be cleared by the hardware. The
-	 * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
-	 * every RMID on the next read to any event for every RMID.
-	 * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
-	 * cleared while it is tracked by the hardware. Clear the
-	 * mbm_local and mbm_total counts for all the RMIDs.
-	 */
-	resctrl_arch_reset_rmid_all(r, d);
-}
-
-static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	char *dom_str = NULL, *id_str;
-	unsigned long dom_id, val;
-	struct rdt_mon_domain *d;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-next:
-	if (!tok || tok[0] == '\0')
-		return 0;
-
-	/* Start processing the strings for each domain */
-	dom_str = strim(strsep(&tok, ";"));
-	id_str = strsep(&dom_str, "=");
-
-	if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
-		rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
-		return -EINVAL;
-	}
-
-	if (!dom_str || kstrtoul(dom_str, 16, &val)) {
-		rdt_last_cmd_puts("Non-numeric event configuration value\n");
-		return -EINVAL;
 	}
-
-	/* Value from user cannot be more than the supported set of events */
-	if ((val & hw_res->mbm_cfg_mask) != val) {
-		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
-				    hw_res->mbm_cfg_mask);
-		return -EINVAL;
-	}
-
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		if (d->hdr.id == dom_id) {
-			mbm_config_write_domain(r, d, evtid, val);
-			goto next;
-		}
-	}
-
-	return -EINVAL;
-}
-
-static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
-					    char *buf, size_t nbytes,
-					    loff_t off)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-	int ret;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	buf[nbytes - 1] = '\0';
-
-	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return ret ?: nbytes;
-}
-
-static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
-					    char *buf, size_t nbytes,
-					    loff_t off)
-{
-	struct rdt_resource *r = of->kn->parent->priv;
-	int ret;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	buf[nbytes - 1] = '\0';
-
-	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return ret ?: nbytes;
-}
-
-/* rdtgroup information files for one cache resource. */
-static struct rftype res_common_files[] = {
-	{
-		.name		= "last_cmd_status",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_last_cmd_status_show,
-		.fflags		= RFTYPE_TOP_INFO,
-	},
-	{
-		.name		= "num_closids",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_num_closids_show,
-		.fflags		= RFTYPE_CTRL_INFO,
-	},
-	{
-		.name		= "mon_features",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_mon_features_show,
-		.fflags		= RFTYPE_MON_INFO,
-	},
-	{
-		.name		= "num_rmids",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_num_rmids_show,
-		.fflags		= RFTYPE_MON_INFO,
-	},
-	{
-		.name		= "cbm_mask",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_default_ctrl_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "min_cbm_bits",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_min_cbm_bits_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "shareable_bits",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_shareable_bits_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "bit_usage",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_bit_usage_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "min_bandwidth",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_min_bw_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	{
-		.name		= "bandwidth_gran",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_bw_gran_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	{
-		.name		= "delay_linear",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_delay_linear_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	/*
-	 * Platform specific which (if any) capabilities are provided by
-	 * thread_throttle_mode. Defer "fflags" initialization to platform
-	 * discovery.
-	 */
-	{
-		.name		= "thread_throttle_mode",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_thread_throttle_mode_show,
-	},
-	{
-		.name		= "max_threshold_occupancy",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= max_threshold_occ_write,
-		.seq_show	= max_threshold_occ_show,
-		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "mbm_total_bytes_config",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= mbm_total_bytes_config_show,
-		.write		= mbm_total_bytes_config_write,
-	},
-	{
-		.name		= "mbm_local_bytes_config",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= mbm_local_bytes_config_show,
-		.write		= mbm_local_bytes_config_write,
-	},
-	{
-		.name		= "cpus",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "cpus_list",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-		.flags		= RFTYPE_FLAGS_CPUS_LIST,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "tasks",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_tasks_write,
-		.seq_show	= rdtgroup_tasks_show,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "mon_hw_id",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_rmid_show,
-		.fflags		= RFTYPE_MON_BASE | RFTYPE_DEBUG,
-	},
-	{
-		.name		= "schemata",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_schemata_write,
-		.seq_show	= rdtgroup_schemata_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "mba_MBps_event",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_mba_mbps_event_write,
-		.seq_show	= rdtgroup_mba_mbps_event_show,
-	},
-	{
-		.name		= "mode",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_mode_write,
-		.seq_show	= rdtgroup_mode_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "size",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_size_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "sparse_masks",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_has_sparse_bitmasks_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "ctrl_hw_id",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_closid_show,
-		.fflags		= RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
-	},
-
-};
-
-static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
-{
-	struct rftype *rfts, *rft;
-	int ret, len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	if (resctrl_debug)
-		fflags |= RFTYPE_DEBUG;
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
-			ret = rdtgroup_add_file(kn, rft);
-			if (ret)
-				goto error;
-		}
-	}
-
-	return 0;
-error:
-	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
-	while (--rft >= rfts) {
-		if ((fflags & rft->fflags) == rft->fflags)
-			kernfs_remove_by_name(kn, rft->name);
-	}
-	return ret;
-}
-
-static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
-{
-	struct rftype *rfts, *rft;
-	int len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (!strcmp(rft->name, name))
-			return rft;
-	}
-
-	return NULL;
-}
-
-void resctrl_file_fflags_init(const char *config, unsigned long fflags)
-{
-	struct rftype *rft;
-
-	rft = rdtgroup_get_rftype_by_name(config);
-	if (rft)
-		rft->fflags = fflags;
-}
-
-/**
- * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- *
- * The permissions of named resctrl file, directory, or link are modified
- * to not allow read, write, or execute by any user.
- *
- * WARNING: This function is intended to communicate to the user that the
- * resctrl file has been locked down - that it is not relevant to the
- * particular state the system finds itself in. It should not be relied
- * on to protect from user access because after the file's permissions
- * are restricted the user can still change the permissions using chmod
- * from the command line.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
-{
-	struct iattr iattr = {.ia_valid = ATTR_MODE,};
-	struct kernfs_node *kn;
-	int ret = 0;
-
-	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
-	if (!kn)
-		return -ENOENT;
-
-	switch (kernfs_type(kn)) {
-	case KERNFS_DIR:
-		iattr.ia_mode = S_IFDIR;
-		break;
-	case KERNFS_FILE:
-		iattr.ia_mode = S_IFREG;
-		break;
-	case KERNFS_LINK:
-		iattr.ia_mode = S_IFLNK;
-		break;
-	}
-
-	ret = kernfs_setattr(kn, &iattr);
-	kernfs_put(kn);
-	return ret;
-}
-
-/**
- * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- * @mask: Mask of permissions that should be restored
- *
- * Restore the permissions of the named file. If @name is a directory the
- * permissions of its parent will be used.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
-			     umode_t mask)
-{
-	struct iattr iattr = {.ia_valid = ATTR_MODE,};
-	struct kernfs_node *kn, *parent;
-	struct rftype *rfts, *rft;
-	int ret, len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (!strcmp(rft->name, name))
-			iattr.ia_mode = rft->mode & mask;
-	}
-
-	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
-	if (!kn)
-		return -ENOENT;
-
-	switch (kernfs_type(kn)) {
-	case KERNFS_DIR:
-		parent = kernfs_get_parent(kn);
-		if (parent) {
-			iattr.ia_mode |= parent->mode;
-			kernfs_put(parent);
-		}
-		iattr.ia_mode |= S_IFDIR;
-		break;
-	case KERNFS_FILE:
-		iattr.ia_mode |= S_IFREG;
-		break;
-	case KERNFS_LINK:
-		iattr.ia_mode |= S_IFLNK;
-		break;
-	}
-
-	ret = kernfs_setattr(kn, &iattr);
-	kernfs_put(kn);
-	return ret;
-}
-
-static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
-				      unsigned long fflags)
-{
-	struct kernfs_node *kn_subdir;
-	int ret;
-
-	kn_subdir = kernfs_create_dir(kn_info, name,
-				      kn_info->mode, priv);
-	if (IS_ERR(kn_subdir))
-		return PTR_ERR(kn_subdir);
-
-	ret = rdtgroup_kn_set_ugid(kn_subdir);
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_add_files(kn_subdir, fflags);
-	if (!ret)
-		kernfs_activate(kn_subdir);
-
-	return ret;
-}
-
-static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
-{
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	unsigned long fflags;
-	char name[32];
-	int ret;
-
-	/* create the directory */
-	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
-	if (IS_ERR(kn_info))
-		return PTR_ERR(kn_info);
-
-	ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
-	if (ret)
-		goto out_destroy;
-
-	/* loop over enabled controls, these are all alloc_capable */
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		fflags = r->fflags | RFTYPE_CTRL_INFO;
-		ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
-		if (ret)
-			goto out_destroy;
-	}
-
-	for_each_mon_capable_rdt_resource(r) {
-		fflags = r->fflags | RFTYPE_MON_INFO;
-		sprintf(name, "%s_MON", r->name);
-		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
-		if (ret)
-			goto out_destroy;
-	}
-
-	ret = rdtgroup_kn_set_ugid(kn_info);
-	if (ret)
-		goto out_destroy;
-
-	kernfs_activate(kn_info);
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn_info);
-	return ret;
-}
-
-static int
-mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
-		    char *name, struct kernfs_node **dest_kn)
-{
-	struct kernfs_node *kn;
-	int ret;
-
-	/* create the directory */
-	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
-
-	if (dest_kn)
-		*dest_kn = kn;
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret)
-		goto out_destroy;
-
-	kernfs_activate(kn);
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
+	wrmsrq(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config);
 }
 
 static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+	wrmsrq(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
 static void l2_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
-}
-
-static inline bool is_mba_linear(void)
-{
-	return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear;
+	wrmsrq(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
 static int set_cache_qos_cfg(int level, bool enable)
@@ -2313,76 +184,6 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
 		l3_qos_cfg_update(&hw_res->cdp_enabled);
 }
 
-static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	int cpu = cpumask_any(&d->hdr.cpu_mask);
-	int i;
-
-	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
-				   GFP_KERNEL, cpu_to_node(cpu));
-	if (!d->mbps_val)
-		return -ENOMEM;
-
-	for (i = 0; i < num_closid; i++)
-		d->mbps_val[i] = MBA_MAX_MBPS;
-
-	return 0;
-}
-
-static void mba_sc_domain_destroy(struct rdt_resource *r,
-				  struct rdt_ctrl_domain *d)
-{
-	kfree(d->mbps_val);
-	d->mbps_val = NULL;
-}
-
-/*
- * MBA software controller is supported only if
- * MBM is supported and MBA is in linear scale,
- * and the MBM monitor scope is the same as MBA
- * control scope.
- */
-static bool supports_mba_mbps(void)
-{
-	struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
-
-	return (is_mbm_enabled() &&
-		r->alloc_capable && is_mba_linear() &&
-		r->ctrl_scope == rmbm->mon_scope);
-}
-
-/*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
- */
-static int set_mba_sc(bool mba_sc)
-{
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	struct rdt_ctrl_domain *d;
-	unsigned long fflags;
-	int i;
-
-	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
-		return -EINVAL;
-
-	r->membw.mba_sc = mba_sc;
-
-	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		for (i = 0; i < num_closid; i++)
-			d->mbps_val[i] = MBA_MAX_MBPS;
-	}
-
-	fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
-	resctrl_file_fflags_init("mba_MBps_event", fflags);
-
-	return 0;
-}
-
 static int cdp_enable(int level)
 {
 	struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
@@ -2423,407 +224,12 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
 	return 0;
 }
 
-/*
- * We don't allow rdtgroup directories to be created anywhere
- * except the root directory. Thus when looking for the rdtgroup
- * structure for a kernfs node we are either looking at a directory,
- * in which case the rdtgroup structure is pointed at by the "priv"
- * field, otherwise we have a file, and need only look to the parent
- * to find the rdtgroup.
- */
-static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
-{
-	if (kernfs_type(kn) == KERNFS_DIR) {
-		/*
-		 * All the resource directories use "kn->priv"
-		 * to point to the "struct rdtgroup" for the
-		 * resource. "info" and its subdirectories don't
-		 * have rdtgroup structures, so return NULL here.
-		 */
-		if (kn == kn_info || kn->parent == kn_info)
-			return NULL;
-		else
-			return kn->priv;
-	} else {
-		return kn->parent->priv;
-	}
-}
-
-static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
-	atomic_inc(&rdtgrp->waitcount);
-	kernfs_break_active_protection(kn);
-}
-
-static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
-	    (rdtgrp->flags & RDT_DELETED)) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-		kernfs_unbreak_active_protection(kn);
-		rdtgroup_remove(rdtgrp);
-	} else {
-		kernfs_unbreak_active_protection(kn);
-	}
-}
-
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
-{
-	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
-	if (!rdtgrp)
-		return NULL;
-
-	rdtgroup_kn_get(rdtgrp, kn);
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	/* Was this group deleted while we waited? */
-	if (rdtgrp->flags & RDT_DELETED)
-		return NULL;
-
-	return rdtgrp;
-}
-
-void rdtgroup_kn_unlock(struct kernfs_node *kn)
-{
-	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
-	if (!rdtgrp)
-		return;
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	rdtgroup_kn_put(rdtgrp, kn);
-}
-
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
-			     struct rdtgroup *prgrp,
-			     struct kernfs_node **mon_data_kn);
-
-static void rdt_disable_ctx(void)
-{
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-	set_mba_sc(false);
-
-	resctrl_debug = false;
-}
-
-static int rdt_enable_ctx(struct rdt_fs_context *ctx)
-{
-	int ret = 0;
-
-	if (ctx->enable_cdpl2) {
-		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
-		if (ret)
-			goto out_done;
-	}
-
-	if (ctx->enable_cdpl3) {
-		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
-		if (ret)
-			goto out_cdpl2;
-	}
-
-	if (ctx->enable_mba_mbps) {
-		ret = set_mba_sc(true);
-		if (ret)
-			goto out_cdpl3;
-	}
-
-	if (ctx->enable_debug)
-		resctrl_debug = true;
-
-	return 0;
-
-out_cdpl3:
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
-out_cdpl2:
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-out_done:
-	return ret;
-}
-
-static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
-{
-	struct resctrl_schema *s;
-	const char *suffix = "";
-	int ret, cl;
-
-	s = kzalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	s->res = r;
-	s->num_closid = resctrl_arch_get_num_closid(r);
-	if (resctrl_arch_get_cdp_enabled(r->rid))
-		s->num_closid /= 2;
-
-	s->conf_type = type;
-	switch (type) {
-	case CDP_CODE:
-		suffix = "CODE";
-		break;
-	case CDP_DATA:
-		suffix = "DATA";
-		break;
-	case CDP_NONE:
-		suffix = "";
-		break;
-	}
-
-	ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
-	if (ret >= sizeof(s->name)) {
-		kfree(s);
-		return -EINVAL;
-	}
-
-	cl = strlen(s->name);
-
-	/*
-	 * If CDP is supported by this resource, but not enabled,
-	 * include the suffix. This ensures the tabular format of the
-	 * schemata file does not change between mounts of the filesystem.
-	 */
-	if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
-		cl += 4;
-
-	if (cl > max_name_width)
-		max_name_width = cl;
-
-	INIT_LIST_HEAD(&s->list);
-	list_add(&s->list, &resctrl_schema_all);
-
-	return 0;
-}
-
-static int schemata_list_create(void)
-{
-	struct rdt_resource *r;
-	int ret = 0;
-
-	for_each_alloc_capable_rdt_resource(r) {
-		if (resctrl_arch_get_cdp_enabled(r->rid)) {
-			ret = schemata_list_add(r, CDP_CODE);
-			if (ret)
-				break;
-
-			ret = schemata_list_add(r, CDP_DATA);
-		} else {
-			ret = schemata_list_add(r, CDP_NONE);
-		}
-
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
-static void schemata_list_destroy(void)
-{
-	struct resctrl_schema *s, *tmp;
-
-	list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
-		list_del(&s->list);
-		kfree(s);
-	}
-}
-
-static int rdt_get_tree(struct fs_context *fc)
-{
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-	unsigned long flags = RFTYPE_CTRL_BASE;
-	struct rdt_mon_domain *dom;
-	struct rdt_resource *r;
-	int ret;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-	/*
-	 * resctrl file system can only be mounted once.
-	 */
-	if (resctrl_mounted) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = rdtgroup_setup_root(ctx);
-	if (ret)
-		goto out;
-
-	ret = rdt_enable_ctx(ctx);
-	if (ret)
-		goto out_root;
-
-	ret = schemata_list_create();
-	if (ret) {
-		schemata_list_destroy();
-		goto out_ctx;
-	}
-
-	closid_init();
-
-	if (resctrl_arch_mon_capable())
-		flags |= RFTYPE_MON;
-
-	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
-	if (ret)
-		goto out_schemata_free;
-
-	kernfs_activate(rdtgroup_default.kn);
-
-	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
-	if (ret < 0)
-		goto out_schemata_free;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = mongroup_create_dir(rdtgroup_default.kn,
-					  &rdtgroup_default, "mon_groups",
-					  &kn_mongrp);
-		if (ret < 0)
-			goto out_info;
-
-		ret = mkdir_mondata_all(rdtgroup_default.kn,
-					&rdtgroup_default, &kn_mondata);
-		if (ret < 0)
-			goto out_mongrp;
-		rdtgroup_default.mon.mon_data_kn = kn_mondata;
-	}
-
-	ret = rdt_pseudo_lock_init();
-	if (ret)
-		goto out_mondata;
-
-	ret = kernfs_get_tree(fc);
-	if (ret < 0)
-		goto out_psl;
-
-	if (resctrl_arch_alloc_capable())
-		resctrl_arch_enable_alloc();
-	if (resctrl_arch_mon_capable())
-		resctrl_arch_enable_mon();
-
-	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
-		resctrl_mounted = true;
-
-	if (is_mbm_enabled()) {
-		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-		list_for_each_entry(dom, &r->mon_domains, hdr.list)
-			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
-						   RESCTRL_PICK_ANY_CPU);
-	}
-
-	goto out;
-
-out_psl:
-	rdt_pseudo_lock_release();
-out_mondata:
-	if (resctrl_arch_mon_capable())
-		kernfs_remove(kn_mondata);
-out_mongrp:
-	if (resctrl_arch_mon_capable())
-		kernfs_remove(kn_mongrp);
-out_info:
-	kernfs_remove(kn_info);
-out_schemata_free:
-	schemata_list_destroy();
-out_ctx:
-	rdt_disable_ctx();
-out_root:
-	rdtgroup_destroy_root();
-out:
-	rdt_last_cmd_clear();
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return ret;
-}
-
-enum rdt_param {
-	Opt_cdp,
-	Opt_cdpl2,
-	Opt_mba_mbps,
-	Opt_debug,
-	nr__rdt_params
-};
-
-static const struct fs_parameter_spec rdt_fs_parameters[] = {
-	fsparam_flag("cdp",		Opt_cdp),
-	fsparam_flag("cdpl2",		Opt_cdpl2),
-	fsparam_flag("mba_MBps",	Opt_mba_mbps),
-	fsparam_flag("debug",		Opt_debug),
-	{}
-};
-
-static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
-{
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-	struct fs_parse_result result;
-	const char *msg;
-	int opt;
-
-	opt = fs_parse(fc, rdt_fs_parameters, param, &result);
-	if (opt < 0)
-		return opt;
-
-	switch (opt) {
-	case Opt_cdp:
-		ctx->enable_cdpl3 = true;
-		return 0;
-	case Opt_cdpl2:
-		ctx->enable_cdpl2 = true;
-		return 0;
-	case Opt_mba_mbps:
-		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
-		if (!supports_mba_mbps())
-			return invalfc(fc, msg);
-		ctx->enable_mba_mbps = true;
-		return 0;
-	case Opt_debug:
-		ctx->enable_debug = true;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-static void rdt_fs_context_free(struct fs_context *fc)
+bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 {
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-
-	kernfs_free_fs_context(fc);
-	kfree(ctx);
+	return rdt_resources_all[l].cdp_enabled;
 }
 
-static const struct fs_context_operations rdt_fs_context_ops = {
-	.free		= rdt_fs_context_free,
-	.parse_param	= rdt_parse_param,
-	.get_tree	= rdt_get_tree,
-};
-
-static int rdt_init_fs_context(struct fs_context *fc)
-{
-	struct rdt_fs_context *ctx;
-
-	ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
-
-	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
-	fc->fs_private = &ctx->kfc;
-	fc->ops = &rdt_fs_context_ops;
-	put_user_ns(fc->user_ns);
-	fc->user_ns = get_user_ns(&init_user_ns);
-	fc->global = true;
-	return 0;
-}
-
-static int reset_all_ctrls(struct rdt_resource *r)
+void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_ctrl_domain *hw_dom;
@@ -2847,1400 +253,10 @@ static int reset_all_ctrls(struct rdt_resource *r)
 		hw_dom = resctrl_to_arch_ctrl_dom(d);
 
 		for (i = 0; i < hw_res->num_closid; i++)
-			hw_dom->ctrl_val[i] = r->default_ctrl;
+			hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r);
 		msr_param.dom = d;
 		smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	return 0;
-}
-
-/*
- * Move tasks from one to the other group. If @from is NULL, then all tasks
- * in the systems are moved unconditionally (used for teardown).
- *
- * If @mask is not NULL the cpus on which moved tasks are running are set
- * in that mask so the update smp function call is restricted to affected
- * cpus.
- */
-static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
-				 struct cpumask *mask)
-{
-	struct task_struct *p, *t;
-
-	read_lock(&tasklist_lock);
-	for_each_process_thread(p, t) {
-		if (!from || is_closid_match(t, from) ||
-		    is_rmid_match(t, from)) {
-			resctrl_arch_set_closid_rmid(t, to->closid,
-						     to->mon.rmid);
-
-			/*
-			 * Order the closid/rmid stores above before the loads
-			 * in task_curr(). This pairs with the full barrier
-			 * between the rq->curr update and resctrl_sched_in()
-			 * during context switch.
-			 */
-			smp_mb();
-
-			/*
-			 * If the task is on a CPU, set the CPU in the mask.
-			 * The detection is inaccurate as tasks might move or
-			 * schedule before the smp function call takes place.
-			 * In such a case the function call is pointless, but
-			 * there is no other side effect.
-			 */
-			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
-				cpumask_set_cpu(task_cpu(t), mask);
-		}
-	}
-	read_unlock(&tasklist_lock);
-}
-
-static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
-{
-	struct rdtgroup *sentry, *stmp;
-	struct list_head *head;
-
-	head = &rdtgrp->mon.crdtgrp_list;
-	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
-		free_rmid(sentry->closid, sentry->mon.rmid);
-		list_del(&sentry->mon.crdtgrp_list);
-
-		if (atomic_read(&sentry->waitcount) != 0)
-			sentry->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(sentry);
-	}
-}
-
-/*
- * Forcibly remove all of subdirectories under root.
- */
-static void rmdir_all_sub(void)
-{
-	struct rdtgroup *rdtgrp, *tmp;
-
-	/* Move all tasks to the default resource group */
-	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
-
-	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
-		/* Free any child rmids */
-		free_all_child_rdtgrp(rdtgrp);
-
-		/* Remove each rdtgroup other than root */
-		if (rdtgrp == &rdtgroup_default)
-			continue;
-
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-
-		/*
-		 * Give any CPUs back to the default group. We cannot copy
-		 * cpu_online_mask because a CPU might have executed the
-		 * offline callback already, but is still marked online.
-		 */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-		kernfs_remove(rdtgrp->kn);
-		list_del(&rdtgrp->rdtgroup_list);
-
-		if (atomic_read(&rdtgrp->waitcount) != 0)
-			rdtgrp->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(rdtgrp);
-	}
-	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
-	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
-
-	kernfs_remove(kn_info);
-	kernfs_remove(kn_mongrp);
-	kernfs_remove(kn_mondata);
-}
-
-static void rdt_kill_sb(struct super_block *sb)
-{
-	struct rdt_resource *r;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_disable_ctx();
-
-	/*Put everything back to default values. */
-	for_each_alloc_capable_rdt_resource(r)
-		reset_all_ctrls(r);
-	rmdir_all_sub();
-	rdt_pseudo_lock_release();
-	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
-	schemata_list_destroy();
-	rdtgroup_destroy_root();
-	if (resctrl_arch_alloc_capable())
-		resctrl_arch_disable_alloc();
-	if (resctrl_arch_mon_capable())
-		resctrl_arch_disable_mon();
-	resctrl_mounted = false;
-	kernfs_kill_sb(sb);
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-static struct file_system_type rdt_fs_type = {
-	.name			= "resctrl",
-	.init_fs_context	= rdt_init_fs_context,
-	.parameters		= rdt_fs_parameters,
-	.kill_sb		= rdt_kill_sb,
-};
-
-static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
-		       void *priv)
-{
-	struct kernfs_node *kn;
-	int ret = 0;
-
-	kn = __kernfs_create_file(parent_kn, name, 0444,
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
-				  &kf_mondata_ops, priv, NULL, NULL);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
-	}
-
-	return ret;
-}
-
-static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname)
-{
-	struct kernfs_node *kn;
-
-	kn = kernfs_find_and_get(pkn, name);
-	if (!kn)
-		return;
-	kernfs_put(kn);
-
-	if (kn->dir.subdirs <= 1)
-		kernfs_remove(kn);
-	else
-		kernfs_remove_by_name(kn, subname);
-}
-
-/*
- * Remove all subdirectories of mon_data of ctrl_mon groups
- * and monitor groups for the given domain.
- * Remove files and directories containing "sum" of domain data
- * when last domain being summed is removed.
- */
-static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
-{
-	struct rdtgroup *prgrp, *crgrp;
-	char subname[32];
-	bool snc_mode;
-	char name[32];
-
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
-	if (snc_mode)
-		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
-
-		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
-			mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname);
-	}
-}
-
-static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
-			     struct rdt_resource *r, struct rdtgroup *prgrp,
-			     bool do_sum)
-{
-	struct rmid_read rr = {0};
-	union mon_data_bits priv;
-	struct mon_evt *mevt;
-	int ret;
-
-	if (WARN_ON(list_empty(&r->evt_list)))
-		return -EPERM;
-
-	priv.u.rid = r->rid;
-	priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
-	priv.u.sum = do_sum;
-	list_for_each_entry(mevt, &r->evt_list, list) {
-		priv.u.evtid = mevt->evtid;
-		ret = mon_addfile(kn, mevt->name, priv.priv);
-		if (ret)
-			return ret;
-
-		if (!do_sum && is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
-	}
-
-	return 0;
-}
-
-static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
-				struct rdt_mon_domain *d,
-				struct rdt_resource *r, struct rdtgroup *prgrp)
-{
-	struct kernfs_node *kn, *ckn;
-	char name[32];
-	bool snc_mode;
-	int ret = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
-	kn = kernfs_find_and_get(parent_kn, name);
-	if (kn) {
-		/*
-		 * rdtgroup_mutex will prevent this directory from being
-		 * removed. No need to keep this hold.
-		 */
-		kernfs_put(kn);
-	} else {
-		kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
-		if (IS_ERR(kn))
-			return PTR_ERR(kn);
-
-		ret = rdtgroup_kn_set_ugid(kn);
-		if (ret)
-			goto out_destroy;
-		ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
-		if (ret)
-			goto out_destroy;
-	}
-
-	if (snc_mode) {
-		sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
-		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
-		if (IS_ERR(ckn)) {
-			ret = -EINVAL;
-			goto out_destroy;
-		}
-
-		ret = rdtgroup_kn_set_ugid(ckn);
-		if (ret)
-			goto out_destroy;
-
-		ret = mon_add_all_files(ckn, d, r, prgrp, false);
-		if (ret)
-			goto out_destroy;
-	}
-
-	kernfs_activate(kn);
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
-}
-
-/*
- * Add all subdirectories of mon_data for "ctrl_mon" groups
- * and "monitor" groups with given domain id.
- */
-static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
-{
-	struct kernfs_node *parent_kn;
-	struct rdtgroup *prgrp, *crgrp;
-	struct list_head *head;
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		parent_kn = prgrp->mon.mon_data_kn;
-		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
-
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-			parent_kn = crgrp->mon.mon_data_kn;
-			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
-		}
-	}
-}
-
-static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
-				       struct rdt_resource *r,
-				       struct rdtgroup *prgrp)
-{
-	struct rdt_mon_domain *dom;
-	int ret;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
-		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
- * This creates a directory mon_data which contains the monitored data.
- *
- * mon_data has one directory for each domain which are named
- * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
- * with L3 domain looks as below:
- * ./mon_data:
- * mon_L3_00
- * mon_L3_01
- * mon_L3_02
- * ...
- *
- * Each domain directory has one file per event:
- * ./mon_L3_00/:
- * llc_occupancy
- *
- */
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
-			     struct rdtgroup *prgrp,
-			     struct kernfs_node **dest_kn)
-{
-	struct rdt_resource *r;
-	struct kernfs_node *kn;
-	int ret;
-
-	/*
-	 * Create the mon_data directory first.
-	 */
-	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
-	if (ret)
-		return ret;
-
-	if (dest_kn)
-		*dest_kn = kn;
-
-	/*
-	 * Create the subdirectories for each domain. Note that all events
-	 * in a domain like L3 are grouped into a resource whose domain is L3
-	 */
-	for_each_mon_capable_rdt_resource(r) {
-		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
-		if (ret)
-			goto out_destroy;
-	}
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
-}
-
-/**
- * cbm_ensure_valid - Enforce validity on provided CBM
- * @_val:	Candidate CBM
- * @r:		RDT resource to which the CBM belongs
- *
- * The provided CBM represents all cache portions available for use. This
- * may be represented by a bitmap that does not consist of contiguous ones
- * and thus be an invalid CBM.
- * Here the provided CBM is forced to be a valid CBM by only considering
- * the first set of contiguous bits as valid and clearing all bits.
- * The intention here is to provide a valid default CBM with which a new
- * resource group is initialized. The user can follow this with a
- * modification to the CBM if the default does not satisfy the
- * requirements.
- */
-static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
-{
-	unsigned int cbm_len = r->cache.cbm_len;
-	unsigned long first_bit, zero_bit;
-	unsigned long val = _val;
-
-	if (!val)
-		return 0;
-
-	first_bit = find_first_bit(&val, cbm_len);
-	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
-	/* Clear any remaining bits to ensure contiguous region */
-	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
-	return (u32)val;
-}
-
-/*
- * Initialize cache resources per RDT domain
- *
- * Set the RDT domain up to start off with all usable allocations. That is,
- * all shareable and unused bits. All-zero CBM is invalid.
- */
-static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
-				 u32 closid)
-{
-	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
-	enum resctrl_conf_type t = s->conf_type;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	u32 used_b = 0, unused_b = 0;
-	unsigned long tmp_cbm;
-	enum rdtgrp_mode mode;
-	u32 peer_ctl, ctrl_val;
-	int i;
-
-	cfg = &d->staged_config[t];
-	cfg->have_new_ctrl = false;
-	cfg->new_ctrl = r->cache.shareable_bits;
-	used_b = r->cache.shareable_bits;
-	for (i = 0; i < closids_supported(); i++) {
-		if (closid_allocated(i) && i != closid) {
-			mode = rdtgroup_mode_by_closid(i);
-			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
-				/*
-				 * ctrl values for locksetup aren't relevant
-				 * until the schemata is written, and the mode
-				 * becomes RDT_MODE_PSEUDO_LOCKED.
-				 */
-				continue;
-			/*
-			 * If CDP is active include peer domain's
-			 * usage to ensure there is no overlap
-			 * with an exclusive group.
-			 */
-			if (resctrl_arch_get_cdp_enabled(r->rid))
-				peer_ctl = resctrl_arch_get_config(r, d, i,
-								   peer_type);
-			else
-				peer_ctl = 0;
-			ctrl_val = resctrl_arch_get_config(r, d, i,
-							   s->conf_type);
-			used_b |= ctrl_val | peer_ctl;
-			if (mode == RDT_MODE_SHAREABLE)
-				cfg->new_ctrl |= ctrl_val | peer_ctl;
-		}
-	}
-	if (d->plr && d->plr->cbm > 0)
-		used_b |= d->plr->cbm;
-	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
-	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
-	cfg->new_ctrl |= unused_b;
-	/*
-	 * Force the initial CBM to be valid, user can
-	 * modify the CBM based on system availability.
-	 */
-	cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
-	/*
-	 * Assign the u32 CBM to an unsigned long to ensure that
-	 * bitmap_weight() does not access out-of-bound memory.
-	 */
-	tmp_cbm = cfg->new_ctrl;
-	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
-		return -ENOSPC;
-	}
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * Initialize cache resources with default values.
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations.
- *
- * If there are no more shareable bits available on any domain then
- * the entire allocation will fail.
- */
-static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
-{
-	struct rdt_ctrl_domain *d;
-	int ret;
-
-	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
-		ret = __init_one_rdt_domain(d, s, closid);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
-}
-
-/* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
-{
-	struct resctrl_staged_config *cfg;
-	struct rdt_ctrl_domain *d;
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		if (is_mba_sc(r)) {
-			d->mbps_val[closid] = MBA_MAX_MBPS;
-			continue;
-		}
-
-		cfg = &d->staged_config[CDP_NONE];
-		cfg->new_ctrl = r->default_ctrl;
-		cfg->have_new_ctrl = true;
-	}
-}
-
-/* Initialize the RDT group's allocations. */
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
-{
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	int ret = 0;
-
-	rdt_staged_configs_clear();
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA ||
-		    r->rid == RDT_RESOURCE_SMBA) {
-			rdtgroup_init_mba(r, rdtgrp->closid);
-			if (is_mba_sc(r))
-				continue;
-		} else {
-			ret = rdtgroup_init_cat(s, rdtgrp->closid);
-			if (ret < 0)
-				goto out;
-		}
-
-		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
-		if (ret < 0) {
-			rdt_last_cmd_puts("Failed to initialize allocations\n");
-			goto out;
-		}
-
-	}
-
-	rdtgrp->mode = RDT_MODE_SHAREABLE;
-
-out:
-	rdt_staged_configs_clear();
-	return ret;
-}
-
-static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	if (!resctrl_arch_mon_capable())
-		return 0;
-
-	ret = alloc_rmid(rdtgrp->closid);
-	if (ret < 0) {
-		rdt_last_cmd_puts("Out of RMIDs\n");
-		return ret;
-	}
-	rdtgrp->mon.rmid = ret;
-
-	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs subdir error\n");
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
-{
-	if (resctrl_arch_mon_capable())
-		free_rmid(rgrp->closid, rgrp->mon.rmid);
-}
-
-static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
-			     const char *name, umode_t mode,
-			     enum rdt_group_type rtype, struct rdtgroup **r)
-{
-	struct rdtgroup *prdtgrp, *rdtgrp;
-	unsigned long files = 0;
-	struct kernfs_node *kn;
-	int ret;
-
-	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
-	if (!prdtgrp) {
-		ret = -ENODEV;
-		goto out_unlock;
-	}
-
-	if (rtype == RDTMON_GROUP &&
-	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto out_unlock;
-	}
-
-	/* allocate the rdtgroup. */
-	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
-	if (!rdtgrp) {
-		ret = -ENOSPC;
-		rdt_last_cmd_puts("Kernel out of memory\n");
-		goto out_unlock;
-	}
-	*r = rdtgrp;
-	rdtgrp->mon.parent = prdtgrp;
-	rdtgrp->type = rtype;
-	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);
-
-	/* kernfs creates the directory for rdtgrp */
-	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
-	if (IS_ERR(kn)) {
-		ret = PTR_ERR(kn);
-		rdt_last_cmd_puts("kernfs create error\n");
-		goto out_free_rgrp;
-	}
-	rdtgrp->kn = kn;
-
-	/*
-	 * kernfs_remove() will drop the reference count on "kn" which
-	 * will free it. But we still need it to stick around for the
-	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
-	 * which will be dropped by kernfs_put() in rdtgroup_remove().
-	 */
-	kernfs_get(kn);
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs perm error\n");
-		goto out_destroy;
-	}
-
-	if (rtype == RDTCTRL_GROUP) {
-		files = RFTYPE_BASE | RFTYPE_CTRL;
-		if (resctrl_arch_mon_capable())
-			files |= RFTYPE_MON;
-	} else {
-		files = RFTYPE_BASE | RFTYPE_MON;
-	}
-
-	ret = rdtgroup_add_files(kn, files);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs fill error\n");
-		goto out_destroy;
-	}
-
-	/*
-	 * The caller unlocks the parent_kn upon success.
-	 */
-	return 0;
-
-out_destroy:
-	kernfs_put(rdtgrp->kn);
-	kernfs_remove(rdtgrp->kn);
-out_free_rgrp:
-	kfree(rdtgrp);
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
-{
-	kernfs_remove(rgrp->kn);
-	rdtgroup_remove(rgrp);
-}
-
-/*
- * Create a monitor group under "mon_groups" directory of a control
- * and monitor group(ctrl_mon). This is a resource group
- * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
- */
-static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
-			      const char *name, umode_t mode)
-{
-	struct rdtgroup *rdtgrp, *prgrp;
-	int ret;
-
-	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
-	if (ret)
-		return ret;
-
-	prgrp = rdtgrp->mon.parent;
-	rdtgrp->closid = prgrp->closid;
-
-	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
-	if (ret) {
-		mkdir_rdt_prepare_clean(rdtgrp);
-		goto out_unlock;
-	}
-
-	kernfs_activate(rdtgrp->kn);
-
-	/*
-	 * Add the rdtgrp to the list of rdtgrps the parent
-	 * ctrl_mon group has to track.
-	 */
-	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
-
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-/*
- * These are rdtgroups created under the root directory. Can be used
- * to allocate and monitor resources.
- */
-static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
-				   const char *name, umode_t mode)
-{
-	struct rdtgroup *rdtgrp;
-	struct kernfs_node *kn;
-	u32 closid;
-	int ret;
-
-	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
-	if (ret)
-		return ret;
-
-	kn = rdtgrp->kn;
-	ret = closid_alloc();
-	if (ret < 0) {
-		rdt_last_cmd_puts("Out of CLOSIDs\n");
-		goto out_common_fail;
-	}
-	closid = ret;
-	ret = 0;
-
-	rdtgrp->closid = closid;
-
-	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
-	if (ret)
-		goto out_closid_free;
-
-	kernfs_activate(rdtgrp->kn);
-
-	ret = rdtgroup_init_alloc(rdtgrp);
-	if (ret < 0)
-		goto out_rmid_free;
-
-	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
-
-	if (resctrl_arch_mon_capable()) {
-		/*
-		 * Create an empty mon_groups directory to hold the subset
-		 * of tasks and cpus to monitor.
-		 */
-		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
-		if (ret) {
-			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_del_list;
-		}
-		if (is_mba_sc(NULL))
-			rdtgrp->mba_mbps_event = mba_mbps_default_event;
-	}
-
-	goto out_unlock;
-
-out_del_list:
-	list_del(&rdtgrp->rdtgroup_list);
-out_rmid_free:
-	mkdir_rdt_prepare_rmid_free(rdtgrp);
-out_closid_free:
-	closid_free(closid);
-out_common_fail:
-	mkdir_rdt_prepare_clean(rdtgrp);
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- *   This makes sure "mon_groups" directory always has a ctrl_mon group
- *   as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
-	return (!strcmp(kn->name, "mon_groups") &&
-		strcmp(name, "mon_groups"));
-}
-
-static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
-			  umode_t mode)
-{
-	/* Do not accept '\n' to avoid unparsable situation. */
-	if (strchr(name, '\n'))
-		return -EINVAL;
-
-	/*
-	 * If the parent directory is the root directory and RDT
-	 * allocation is supported, add a control and monitoring
-	 * subdirectory
-	 */
-	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
-		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
-
-	/*
-	 * If RDT monitoring is supported and the parent directory is a valid
-	 * "mon_groups" directory, add a monitoring subdirectory.
-	 */
-	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
-		return rdtgroup_mkdir_mon(parent_kn, name, mode);
-
-	return -EPERM;
-}
-
-static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
-	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
-	int cpu;
-
-	/* Give any tasks back to the parent group */
-	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
-
-	/* Update per cpu rmid of the moved CPUs first */
-	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
-	/*
-	 * Update the MSR on moved CPUs and CPUs which have moved
-	 * task running on them.
-	 */
-	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
-	update_closid_rmid(tmpmask, NULL);
-
-	rdtgrp->flags = RDT_DELETED;
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-	/*
-	 * Remove the rdtgrp from the parent ctrl_mon group's list
-	 */
-	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
-	list_del(&rdtgrp->mon.crdtgrp_list);
-
-	kernfs_remove(rdtgrp->kn);
-
-	return 0;
-}
-
-static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
-{
-	rdtgrp->flags = RDT_DELETED;
-	list_del(&rdtgrp->rdtgroup_list);
-
-	kernfs_remove(rdtgrp->kn);
-	return 0;
-}
-
-static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
-	int cpu;
-
-	/* Give any tasks back to the default group */
-	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
-
-	/* Give any CPUs back to the default group */
-	cpumask_or(&rdtgroup_default.cpu_mask,
-		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
-	/* Update per cpu closid and rmid of the moved CPUs first */
-	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
-		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
-		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
-	}
-
-	/*
-	 * Update the MSR on moved CPUs and CPUs which have moved
-	 * task running on them.
-	 */
-	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
-	update_closid_rmid(tmpmask, NULL);
-
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-	closid_free(rdtgrp->closid);
-
-	rdtgroup_ctrl_remove(rdtgrp);
-
-	/*
-	 * Free all the child monitor group rmids.
-	 */
-	free_all_child_rdtgrp(rdtgrp);
-
-	return 0;
-}
-
-static int rdtgroup_rmdir(struct kernfs_node *kn)
-{
-	struct kernfs_node *parent_kn = kn->parent;
-	struct rdtgroup *rdtgrp;
-	cpumask_var_t tmpmask;
-	int ret = 0;
-
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		return -ENOMEM;
-
-	rdtgrp = rdtgroup_kn_lock_live(kn);
-	if (!rdtgrp) {
-		ret = -EPERM;
-		goto out;
-	}
-
-	/*
-	 * If the rdtgroup is a ctrl_mon group and parent directory
-	 * is the root directory, remove the ctrl_mon group.
-	 *
-	 * If the rdtgroup is a mon group and parent directory
-	 * is a valid "mon_groups" directory, remove the mon group.
-	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
-	    rdtgrp != &rdtgroup_default) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			ret = rdtgroup_ctrl_remove(rdtgrp);
-		} else {
-			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
-		}
-	} else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name)) {
-		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
-	} else {
-		ret = -EPERM;
-	}
-
-out:
-	rdtgroup_kn_unlock(kn);
-	free_cpumask_var(tmpmask);
-	return ret;
-}
-
-/**
- * mongrp_reparent() - replace parent CTRL_MON group of a MON group
- * @rdtgrp:		the MON group whose parent should be replaced
- * @new_prdtgrp:	replacement parent CTRL_MON group for @rdtgrp
- * @cpus:		cpumask provided by the caller for use during this call
- *
- * Replaces the parent CTRL_MON group for a MON group, resulting in all member
- * tasks' CLOSID immediately changing to that of the new parent group.
- * Monitoring data for the group is unaffected by this operation.
- */
-static void mongrp_reparent(struct rdtgroup *rdtgrp,
-			    struct rdtgroup *new_prdtgrp,
-			    cpumask_var_t cpus)
-{
-	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
-
-	WARN_ON(rdtgrp->type != RDTMON_GROUP);
-	WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);
-
-	/* Nothing to do when simply renaming a MON group. */
-	if (prdtgrp == new_prdtgrp)
-		return;
-
-	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
-	list_move_tail(&rdtgrp->mon.crdtgrp_list,
-		       &new_prdtgrp->mon.crdtgrp_list);
-
-	rdtgrp->mon.parent = new_prdtgrp;
-	rdtgrp->closid = new_prdtgrp->closid;
-
-	/* Propagate updated closid to all tasks in this group. */
-	rdt_move_group_tasks(rdtgrp, rdtgrp, cpus);
-
-	update_closid_rmid(cpus, NULL);
-}
-
-static int rdtgroup_rename(struct kernfs_node *kn,
-			   struct kernfs_node *new_parent, const char *new_name)
-{
-	struct rdtgroup *new_prdtgrp;
-	struct rdtgroup *rdtgrp;
-	cpumask_var_t tmpmask;
-	int ret;
-
-	rdtgrp = kernfs_to_rdtgroup(kn);
-	new_prdtgrp = kernfs_to_rdtgroup(new_parent);
-	if (!rdtgrp || !new_prdtgrp)
-		return -ENOENT;
-
-	/* Release both kernfs active_refs before obtaining rdtgroup mutex. */
-	rdtgroup_kn_get(rdtgrp, kn);
-	rdtgroup_kn_get(new_prdtgrp, new_parent);
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	/*
-	 * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
-	 * either kernfs_node is a file.
-	 */
-	if (kernfs_type(kn) != KERNFS_DIR ||
-	    kernfs_type(new_parent) != KERNFS_DIR) {
-		rdt_last_cmd_puts("Source and destination must be directories");
-		ret = -EPERM;
-		goto out;
-	}
-
-	if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	if (rdtgrp->type != RDTMON_GROUP || !kn->parent ||
-	    !is_mon_groups(kn->parent, kn->name)) {
-		rdt_last_cmd_puts("Source must be a MON group\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	if (!is_mon_groups(new_parent, new_name)) {
-		rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	/*
-	 * If the MON group is monitoring CPUs, the CPUs must be assigned to the
-	 * current parent CTRL_MON group and therefore cannot be assigned to
-	 * the new parent, making the move illegal.
-	 */
-	if (!cpumask_empty(&rdtgrp->cpu_mask) &&
-	    rdtgrp->mon.parent != new_prdtgrp) {
-		rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	/*
-	 * Allocate the cpumask for use in mongrp_reparent() to avoid the
-	 * possibility of failing to allocate it after kernfs_rename() has
-	 * succeeded.
-	 */
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/*
-	 * Perform all input validation and allocations needed to ensure
-	 * mongrp_reparent() will succeed before calling kernfs_rename(),
-	 * otherwise it would be necessary to revert this call if
-	 * mongrp_reparent() failed.
-	 */
-	ret = kernfs_rename(kn, new_parent, new_name);
-	if (!ret)
-		mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);
-
-	free_cpumask_var(tmpmask);
-
-out:
-	mutex_unlock(&rdtgroup_mutex);
-	rdtgroup_kn_put(rdtgrp, kn);
-	rdtgroup_kn_put(new_prdtgrp, new_parent);
-	return ret;
-}
-
-static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
-{
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
-		seq_puts(seq, ",cdp");
-
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
-		seq_puts(seq, ",cdpl2");
-
-	if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
-		seq_puts(seq, ",mba_MBps");
-
-	if (resctrl_debug)
-		seq_puts(seq, ",debug");
-
-	return 0;
-}
-
-static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
-	.mkdir		= rdtgroup_mkdir,
-	.rmdir		= rdtgroup_rmdir,
-	.rename		= rdtgroup_rename,
-	.show_options	= rdtgroup_show_options,
-};
-
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
-{
-	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
-				      KERNFS_ROOT_CREATE_DEACTIVATED |
-				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
-				      &rdtgroup_default);
-	if (IS_ERR(rdt_root))
-		return PTR_ERR(rdt_root);
-
-	ctx->kfc.root = rdt_root;
-	rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
-
-	return 0;
-}
-
-static void rdtgroup_destroy_root(void)
-{
-	kernfs_destroy_root(rdt_root);
-	rdtgroup_default.kn = NULL;
-}
-
-static void __init rdtgroup_setup_default(void)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
-	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
-	rdtgroup_default.type = RDTCTRL_GROUP;
-	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
-
-	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static void domain_destroy_mon_state(struct rdt_mon_domain *d)
-{
-	bitmap_free(d->rmid_busy_llc);
-	kfree(d->mbm_total);
-	kfree(d->mbm_local);
-}
-
-void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
-		mba_sc_domain_destroy(r, d);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	/*
-	 * If resctrl is mounted, remove all the
-	 * per domain monitor data directories.
-	 */
-	if (resctrl_mounted && resctrl_arch_mon_capable())
-		rmdir_mondata_subdir_allrdtgrp(r, d);
-
-	if (is_mbm_enabled())
-		cancel_delayed_work(&d->mbm_over);
-	if (is_llc_occupancy_enabled() && has_busy_rmid(d)) {
-		/*
-		 * When a package is going down, forcefully
-		 * decrement rmid->ebusy. There is no way to know
-		 * that the L3 was flushed and hence may lead to
-		 * incorrect counts in rare scenarios, but leaving
-		 * the RMID as busy creates RMID leaks if the
-		 * package never comes back.
-		 */
-		__check_limbo(d, true);
-		cancel_delayed_work(&d->cqm_limbo);
-	}
-
-	domain_destroy_mon_state(d);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	size_t tsize;
-
-	if (is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
-		if (!d->rmid_busy_llc)
-			return -ENOMEM;
-	}
-	if (is_mbm_total_enabled()) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
-			return -ENOMEM;
-		}
-	}
-	if (is_mbm_local_enabled()) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
-			return -ENOMEM;
-		}
-	}
-
-	return 0;
-}
-
-int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	int err = 0;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
-		/* RDT_RESOURCE_MBA is never mon_capable */
-		err = mba_sc_domain_allocate(r, d);
-	}
-
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	int err;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	err = domain_setup_mon_state(r, d);
-	if (err)
-		goto out_unlock;
-
-	if (is_mbm_enabled()) {
-		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
-		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
-					   RESCTRL_PICK_ANY_CPU);
-	}
-
-	if (is_llc_occupancy_enabled())
-		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
-
-	/*
-	 * If the filesystem is not mounted then only the default resource group
-	 * exists. Creation of its directories is deferred until mount time
-	 * by rdt_get_tree() calling mkdir_mondata_all().
-	 * If resctrl is mounted, add per domain monitor data directories.
-	 */
-	if (resctrl_mounted && resctrl_arch_mon_capable())
-		mkdir_mondata_subdir_allrdtgrp(r, d);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-void resctrl_online_cpu(unsigned int cpu)
-{
-	mutex_lock(&rdtgroup_mutex);
-	/* The CPU is set in default rdtgroup after online. */
-	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
-{
-	struct rdtgroup *cr;
-
-	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
-			break;
-	}
-}
-
-void resctrl_offline_cpu(unsigned int cpu)
-{
-	struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_mon_domain *d;
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
-			clear_childcpus(rdtgrp, cpu);
-			break;
-		}
-	}
-
-	if (!l3->mon_capable)
-		goto out_unlock;
-
-	d = get_mon_domain_from_cpu(cpu, l3);
-	if (d) {
-		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
-			cancel_delayed_work(&d->mbm_over);
-			mbm_setup_overflow_handler(d, 0, cpu);
-		}
-		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
-		    has_busy_rmid(d)) {
-			cancel_delayed_work(&d->cqm_limbo);
-			cqm_setup_limbo_handler(d, 0, cpu);
-		}
-	}
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-/*
- * rdtgroup_init - rdtgroup initialization
- *
- * Setup resctrl file system including set up root, create mount point,
- * register rdtgroup filesystem, and initialize files under root directory.
- *
- * Return: 0 on success or -errno
- */
-int __init rdtgroup_init(void)
-{
-	int ret = 0;
-
-	seq_buf_init(&last_cmd_status, last_cmd_status_buf,
-		     sizeof(last_cmd_status_buf));
-
-	rdtgroup_setup_default();
-
-	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
-	if (ret)
-		return ret;
-
-	ret = register_filesystem(&rdt_fs_type);
-	if (ret)
-		goto cleanup_mountpoint;
-
-	/*
-	 * Adding the resctrl debugfs directory here may not be ideal since
-	 * it would let the resctrl debugfs directory appear on the debugfs
-	 * filesystem before the resctrl filesystem is mounted.
-	 * It may also be ok since that would enable debugging of RDT before
-	 * resctrl is mounted.
-	 * The reason why the debugfs directory is created here and not in
-	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
-	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
-	 * (the lockdep class of inode->i_rwsem). Other filesystem
-	 * interactions (eg. SyS_getdents) have the lock ordering:
-	 * &sb->s_type->i_mutex_key --> &mm->mmap_lock
-	 * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
-	 * is taken, thus creating dependency:
-	 * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
-	 * issues considering the other two lock dependencies.
-	 * By creating the debugfs directory here we avoid a dependency
-	 * that may cause deadlock (even though file operations cannot
-	 * occur until the filesystem is mounted, but I do not know how to
-	 * tell lockdep that).
-	 */
-	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
-
-	return 0;
-
-cleanup_mountpoint:
-	sysfs_remove_mount_point(fs_kobj, "resctrl");
-
-	return ret;
-}
-
-void __exit rdtgroup_exit(void)
-{
-	debugfs_remove_recursive(debugfs_resctrl);
-	unregister_filesystem(&rdt_fs_type);
-	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	return;
 }
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 16f3ca30626a..dbf6d71bdf18 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,		CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,			CPUID_ECX,  3, 0x00000006, 0 },
 	{ X86_FEATURE_INTEL_PPIN,		CPUID_EBX,  0, 0x00000007, 1 },
+	{ X86_FEATURE_APX,			CPUID_EDX, 21, 0x00000007, 1 },
 	{ X86_FEATURE_RRSBA_CTRL,		CPUID_EDX,  2, 0x00000007, 2 },
 	{ X86_FEATURE_BHI_CTRL,			CPUID_EDX,  4, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,			CPUID_EDX,  1, 0x0000000f, 0 },
@@ -53,7 +54,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_PERFMON_V2,		CPUID_EAX,  0, 0x80000022, 0 },
 	{ X86_FEATURE_AMD_LBR_V2,		CPUID_EAX,  1, 0x80000022, 0 },
 	{ X86_FEATURE_AMD_LBR_PMC_FREEZE,	CPUID_EAX,  2, 0x80000022, 0 },
-	{ X86_FEATURE_AMD_HETEROGENEOUS_CORES,	CPUID_EAX, 30, 0x80000026, 0 },
+	{ X86_FEATURE_AMD_HTR_CORES,		CPUID_EAX, 30, 0x80000026, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 22b65a5f5ec6..7f8d1e11dbee 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -150,13 +150,15 @@ int __init sgx_drv_init(void)
 	u64 xfrm_mask;
 	int ret;
 
-	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC))
+	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) {
+		pr_info("SGX disabled: SGX launch control CPU feature is not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
+	}
 
 	cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx);
 
 	if (!(eax & 1))  {
-		pr_err("SGX disabled: SGX1 instruction support not available.\n");
+		pr_info("SGX disabled: SGX1 instruction support not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
 	}
 
@@ -173,8 +175,10 @@ int __init sgx_drv_init(void)
 	}
 
 	ret = misc_register(&sgx_dev_enclave);
-	if (ret)
+	if (ret) {
+		pr_info("SGX disabled: Unable to register the /dev/sgx_enclave driver (%d).\n", ret);
 		return ret;
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index b65ab214bdf5..776a20172867 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -64,6 +64,13 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	struct file *backing;
 	long ret;
 
+	/*
+	 * ECREATE would detect this too, but checking here also ensures
+	 * that the 'encl_size' calculations below can never overflow.
+	 */
+	if (!is_power_of_2(secs->size))
+		return -EINVAL;
+
 	va_page = sgx_encl_grow(encl, true);
 	if (IS_ERR(va_page))
 		return PTR_ERR(va_page);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8ce352fc72ac..6722b2fc82cf 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/vmalloc.h>
+#include <asm/msr.h>
 #include <asm/sgx.h>
 #include "driver.h"
 #include "encl.h"
@@ -871,7 +872,7 @@ void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
 	WARN_ON_ONCE(preemptible());
 
 	for (i = 0; i < 4; i++)
-		wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
+		wrmsrq(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
 }
 
 const struct file_operations sgx_provision_fops = {
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 01456236a6dd..e35ccdc84910 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -30,6 +30,7 @@
 #include <asm/hypervisor.h>
 #include <asm/io_apic.h>
 #include <asm/mpspec.h>
+#include <asm/msr.h>
 #include <asm/smp.h>
 
 #include "cpu.h"
@@ -154,7 +155,7 @@ static __init bool check_for_real_bsp(u32 apic_id)
 	 * kernel must rely on the firmware enumeration order.
 	 */
 	if (has_apic_base) {
-		rdmsrl(MSR_IA32_APICBASE, msr);
+		rdmsrq(MSR_IA32_APICBASE, msr);
 		is_bsp = !!(msr & MSR_IA32_APICBASE_BSP);
 	}
 
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 03b3c9c3a45e..843b1655ab45 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -3,6 +3,7 @@
 
 #include <asm/apic.h>
 #include <asm/memtype.h>
+#include <asm/msr.h>
 #include <asm/processor.h>
 
 #include "cpu.h"
@@ -133,7 +134,7 @@ static void parse_fam10h_node_id(struct topo_scan *tscan)
 	if (!boot_cpu_has(X86_FEATURE_NODEID_MSR))
 		return;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, nid.msr);
+	rdmsrq(MSR_FAM10H_NODE_ID, nid.msr);
 	store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id);
 	tscan->c->topo.llc_id = nid.node_id;
 }
@@ -160,7 +161,7 @@ static void topoext_fixup(struct topo_scan *tscan)
 	if (msr_set_bit(0xc0011005, 54) <= 0)
 		return;
 
-	rdmsrl(0xc0011005, msrval);
+	rdmsrq(0xc0011005, msrval);
 	if (msrval & BIT_64(54)) {
 		set_cpu_cap(c, X86_FEATURE_TOPOEXT);
 		pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
@@ -182,7 +183,7 @@ static void parse_topology_amd(struct topo_scan *tscan)
 	if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
 		has_topoext = cpu_parse_topology_ext(tscan);
 
-	if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES))
+	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES))
 		tscan->c->topo.cpu_type = cpuid_ebx(0x80000026);
 
 	if (!has_topoext && !parse_8000_0008(tscan))
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index b31ee4f1657a..49782724a943 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -12,6 +12,7 @@
 
 #include <asm/cmdline.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
@@ -24,7 +25,7 @@ static void tsx_disable(void)
 {
 	u64 tsx;
 
-	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+	rdmsrq(MSR_IA32_TSX_CTRL, tsx);
 
 	/* Force all transactions to immediately abort */
 	tsx |= TSX_CTRL_RTM_DISABLE;
@@ -37,14 +38,14 @@ static void tsx_disable(void)
 	 */
 	tsx |= TSX_CTRL_CPUID_CLEAR;
 
-	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+	wrmsrq(MSR_IA32_TSX_CTRL, tsx);
 }
 
 static void tsx_enable(void)
 {
 	u64 tsx;
 
-	rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+	rdmsrq(MSR_IA32_TSX_CTRL, tsx);
 
 	/* Enable the RTM feature in the cpu */
 	tsx &= ~TSX_CTRL_RTM_DISABLE;
@@ -56,7 +57,7 @@ static void tsx_enable(void)
 	 */
 	tsx &= ~TSX_CTRL_CPUID_CLEAR;
 
-	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+	wrmsrq(MSR_IA32_TSX_CTRL, tsx);
 }
 
 static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
@@ -115,13 +116,13 @@ static void tsx_clear_cpuid(void)
 	 */
 	if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) &&
 	    boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
-		rdmsrl(MSR_TSX_FORCE_ABORT, msr);
+		rdmsrq(MSR_TSX_FORCE_ABORT, msr);
 		msr |= MSR_TFA_TSX_CPUID_CLEAR;
-		wrmsrl(MSR_TSX_FORCE_ABORT, msr);
+		wrmsrq(MSR_TSX_FORCE_ABORT, msr);
 	} else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) {
-		rdmsrl(MSR_IA32_TSX_CTRL, msr);
+		rdmsrq(MSR_IA32_TSX_CTRL, msr);
 		msr |= TSX_CTRL_CPUID_CLEAR;
-		wrmsrl(MSR_IA32_TSX_CTRL, msr);
+		wrmsrq(MSR_IA32_TSX_CTRL, msr);
 	}
 }
 
@@ -146,11 +147,11 @@ static void tsx_dev_mode_disable(void)
 	    !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL))
 		return;
 
-	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+	rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
 
 	if (mcu_opt_ctrl & RTM_ALLOW) {
 		mcu_opt_ctrl &= ~RTM_ALLOW;
-		wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+		wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
 		setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT);
 	}
 }
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 2293efd6ffa6..933fcd7ff250 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -33,7 +33,7 @@ static DEFINE_MUTEX(umwait_lock);
 static void umwait_update_control_msr(void * unused)
 {
 	lockdep_assert_irqs_disabled();
-	wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+	wrmsrq(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached));
 }
 
 /*
@@ -71,7 +71,7 @@ static int umwait_cpu_offline(unsigned int cpu)
 	 * the original control MSR value in umwait_init(). So there
 	 * is no race condition here.
 	 */
-	wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0);
+	wrmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
 
 	return 0;
 }
@@ -214,7 +214,7 @@ static int __init umwait_init(void)
 	 * changed. This is the only place where orig_umwait_control_cached
 	 * is modified.
 	 */
-	rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
+	rdmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
 
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
 				umwait_cpu_online, umwait_cpu_offline);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 00189cdeb775..cb3f900c46fc 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/clocksource.h>
 #include <linux/cpu.h>
+#include <linux/efi.h>
 #include <linux/reboot.h>
 #include <linux/static_call.h>
 #include <asm/div64.h>
@@ -429,6 +430,9 @@ static void __init vmware_platform_setup(void)
 		pr_warn("Failed to get TSC freq from the hypervisor\n");
 	}
 
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !efi_enabled(EFI_BOOT))
+		x86_init.mpparse.find_mptable = mpparse_find_mptable;
+
 	vmware_paravirt_ops_setup();
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 90eba7eb5335..89b1c8a70fe8 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -4,6 +4,7 @@
 
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/msr.h>
 
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 340af8155658..0be61c45400c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -140,7 +140,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	x86_platform.guest.enc_kexec_begin();
 	x86_platform.guest.enc_kexec_finish();
 
-	crash_save_cpu(regs, safe_smp_processor_id());
+	crash_save_cpu(regs, smp_processor_id());
 }
 
 #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0..dd8748c45529 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index a7d562697e50..71ee20102a8a 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -23,8 +23,6 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-int panic_on_unrecovered_nmi;
-int panic_on_io_nmi;
 static int die_counter;
 
 static struct pt_regs exec_summary_regs;
@@ -195,6 +193,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
+	stack = stack ?: get_stack_pointer(task, regs);
 	regs = unwind_get_entry_regs(&state, &partial);
 
 	/*
@@ -213,9 +212,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - hardirq stack
 	 * - entry stack
 	 */
-	for (stack = stack ?: get_stack_pointer(task, regs);
-	     stack;
-	     stack = stack_info.next_sp) {
+	for (; stack; stack = stack_info.next_sp) {
 		const char *stack_name;
 
 		stack = PTR_ALIGN(stack, sizeof(long));
@@ -395,18 +392,13 @@ NOKPROBE_SYMBOL(oops_end);
 
 static void __die_header(const char *str, struct pt_regs *regs, long err)
 {
-	const char *pr = "";
-
 	/* Save the regs of the first oops for the executive summary later. */
 	if (!die_counter)
 		exec_summary_regs = *regs;
 
-	if (IS_ENABLED(CONFIG_PREEMPTION))
-		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
-
 	printk(KERN_DEFAULT
-	       "Oops: %s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff,
-	       ++die_counter, pr,
+	       "Oops: %s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff,
+	       ++die_counter,
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
 	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b4905d5173fd..722fd712e1cf 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
@@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index f05339fee778..6c5defd6569a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin;
 
 	/*
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 82b96ed9890a..9920122018a0 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -28,18 +28,13 @@
  *   the first 128 E820 memory entries in boot_params.e820_table and the remaining
  *   (if any) entries of the SETUP_E820_EXT nodes. We use this to:
  *
- *       - inform the user about the firmware's notion of memory layout
- *         via /sys/firmware/memmap
- *
  *       - the hibernation code uses it to generate a kernel-independent CRC32
  *         checksum of the physical memory layout of a system.
  *
  * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version
  *   passed to us by the bootloader - the major difference between
- *   e820_table_firmware[] and this one is that, the latter marks the setup_data
- *   list created by the EFI boot stub as reserved, so that kexec can reuse the
- *   setup_data information in the second kernel. Besides, e820_table_kexec[]
- *   might also be modified by the kexec itself to fake a mptable.
+ *   e820_table_firmware[] and this one is that e820_table_kexec[]
+ *   might be modified by the kexec itself to fake an mptable.
  *   We use this to:
  *
  *       - kexec, which is a bootloader in disguise, uses the original E820
@@ -47,6 +42,11 @@
  *         can have a restricted E820 map while the kexec()-ed kexec-kernel
  *         can have access to full memory - etc.
  *
+ *         Export the memory layout via /sys/firmware/memmap. kexec-tools uses
+ *         the entries to create an E820 table for the kexec kernel.
+ *
+ *         kexec_file_load in-kernel code uses the table for the kexec kernel.
+ *
  * - 'e820_table': this is the main E820 table that is massaged by the
  *   low level x86 platform code, or modified by boot parameters, before
  *   passed on to higher level MM layers.
@@ -187,8 +187,7 @@ void __init e820__range_add(u64 start, u64 size, enum e820_type type)
 static void __init e820_print_type(enum e820_type type)
 {
 	switch (type) {
-	case E820_TYPE_RAM:		/* Fall through: */
-	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
+	case E820_TYPE_RAM:		pr_cont("usable");			break;
 	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
 	case E820_TYPE_SOFT_RESERVED:	pr_cont("soft reserved");		break;
 	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
@@ -754,22 +753,21 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
 void __init e820__register_nosave_regions(unsigned long limit_pfn)
 {
 	int i;
-	unsigned long pfn = 0;
+	u64 last_addr = 0;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
 		struct e820_entry *entry = &e820_table->entries[i];
 
-		if (pfn < PFN_UP(entry->addr))
-			register_nosave_region(pfn, PFN_UP(entry->addr));
-
-		pfn = PFN_DOWN(entry->addr + entry->size);
+		if (entry->type != E820_TYPE_RAM)
+			continue;
 
-		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
-			register_nosave_region(PFN_UP(entry->addr), pfn);
+		if (last_addr < entry->addr)
+			register_nosave_region(PFN_DOWN(last_addr), PFN_UP(entry->addr));
 
-		if (pfn >= limit_pfn)
-			break;
+		last_addr = entry->addr + entry->size;
 	}
+
+	register_nosave_region(PFN_DOWN(last_addr), limit_pfn);
 }
 
 #ifdef CONFIG_ACPI
@@ -991,60 +989,6 @@ static int __init parse_memmap_opt(char *str)
 early_param("memmap", parse_memmap_opt);
 
 /*
- * Reserve all entries from the bootloader's extensible data nodes list,
- * because if present we are going to use it later on to fetch e820
- * entries from it:
- */
-void __init e820__reserve_setup_data(void)
-{
-	struct setup_indirect *indirect;
-	struct setup_data *data;
-	u64 pa_data, pa_next;
-	u32 len;
-
-	pa_data = boot_params.hdr.setup_data;
-	if (!pa_data)
-		return;
-
-	while (pa_data) {
-		data = early_memremap(pa_data, sizeof(*data));
-		if (!data) {
-			pr_warn("e820: failed to memremap setup_data entry\n");
-			return;
-		}
-
-		len = sizeof(*data);
-		pa_next = data->next;
-
-		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-
-		if (data->type == SETUP_INDIRECT) {
-			len += data->len;
-			early_memunmap(data, sizeof(*data));
-			data = early_memremap(pa_data, len);
-			if (!data) {
-				pr_warn("e820: failed to memremap indirect setup_data\n");
-				return;
-			}
-
-			indirect = (struct setup_indirect *)data->data;
-
-			if (indirect->type != SETUP_INDIRECT)
-				e820__range_update(indirect->addr, indirect->len,
-						   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
-		}
-
-		pa_data = pa_next;
-		early_memunmap(data, len);
-	}
-
-	e820__update_table(e820_table);
-
-	pr_info("extended physical RAM map:\n");
-	e820__print_table("reserve setup_data");
-}
-
-/*
  * Called after parse_early_param(), after early parameters (such as mem=)
  * have been processed, in which case we already have an E820 table filled in
  * via the parameter callback function(s), but it's not sorted and printed yet:
@@ -1063,7 +1007,6 @@ void __init e820__finish_early_params(void)
 static const char *__init e820_type_to_string(struct e820_entry *entry)
 {
 	switch (entry->type) {
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		return "System RAM";
 	case E820_TYPE_ACPI:		return "ACPI Tables";
 	case E820_TYPE_NVS:		return "ACPI Non-volatile Storage";
@@ -1079,7 +1022,6 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
 static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 {
 	switch (entry->type) {
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		return IORESOURCE_SYSTEM_RAM;
 	case E820_TYPE_ACPI:		/* Fall-through: */
 	case E820_TYPE_NVS:		/* Fall-through: */
@@ -1101,7 +1043,6 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
 	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
 	case E820_TYPE_SOFT_RESERVED:	return IORES_DESC_SOFT_RESERVED;
-	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
 	default:			return IORES_DESC_NONE;
@@ -1124,7 +1065,6 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 	case E820_TYPE_PRAM:
 	case E820_TYPE_PMEM:
 		return false;
-	case E820_TYPE_RESERVED_KERN:
 	case E820_TYPE_RAM:
 	case E820_TYPE_ACPI:
 	case E820_TYPE_NVS:
@@ -1176,9 +1116,9 @@ void __init e820__reserve_resources(void)
 		res++;
 	}
 
-	/* Expose the bootloader-provided memory layout to the sysfs. */
-	for (i = 0; i < e820_table_firmware->nr_entries; i++) {
-		struct e820_entry *entry = e820_table_firmware->entries + i;
+	/* Expose the kexec e820 table to the sysfs. */
+	for (i = 0; i < e820_table_kexec->nr_entries; i++) {
+		struct e820_entry *entry = e820_table_kexec->entries + i;
 
 		firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry));
 	}
@@ -1302,6 +1242,36 @@ void __init e820__memblock_setup(void)
 	int i;
 	u64 end;
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/*
+	 * Memory used by the kernel cannot be hot-removed because Linux
+	 * cannot migrate the kernel pages. When memory hotplug is
+	 * enabled, we should prevent memblock from allocating memory
+	 * for the kernel.
+	 *
+	 * ACPI SRAT records all hotpluggable memory ranges. But before
+	 * SRAT is parsed, we don't know about it.
+	 *
+	 * The kernel image is loaded into memory at very early time. We
+	 * cannot prevent this anyway. So on NUMA system, we set any
+	 * node the kernel resides in as un-hotpluggable.
+	 *
+	 * Since on modern servers, one node could have double-digit
+	 * gigabytes memory, we can assume the memory around the kernel
+	 * image is also un-hotpluggable. So before SRAT is parsed, just
+	 * allocate memory near the kernel image to try the best to keep
+	 * the kernel away from hotpluggable memory.
+	 */
+	if (movable_node_is_enabled())
+		memblock_set_bottom_up(true);
+#endif
+
+	/*
+	 * At this point only the first megabyte is mapped for sure, the
+	 * rest of the memory cannot be used for memblock resizing
+	 */
+	memblock_set_current_limit(ISA_END_ADDRESS);
+
 	/*
 	 * The bootstrap memblock region count maximum is 128 entries
 	 * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
@@ -1323,12 +1293,20 @@ void __init e820__memblock_setup(void)
 		if (entry->type == E820_TYPE_SOFT_RESERVED)
 			memblock_reserve(entry->addr, entry->size);
 
-		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
+		if (entry->type != E820_TYPE_RAM)
 			continue;
 
 		memblock_add(entry->addr, entry->size);
 	}
 
+	/*
+	 * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+	 * to even less without it.
+	 * Discard memory after max_pfn - the actual limit detected at runtime.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		memblock_remove(PFN_PHYS(max_pfn), -1);
+
 	/* Throw away partial pages: */
 	memblock_trim_memory(PAGE_SIZE);
 
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 44f937015e1e..cba75306e5b6 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/console.h>
 #include <linux/kernel.h>
+#include <linux/kexec.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/screen_info.h>
@@ -19,6 +20,7 @@
 #include <linux/usb/ehci_def.h>
 #include <linux/usb/xhci-dbgp.h>
 #include <asm/pci_x86.h>
+#include <linux/static_call.h>
 
 /* Simple VGA output */
 #define VGABASE		(__ISA_IO_base + 0xb8000)
@@ -94,26 +96,28 @@ static unsigned long early_serial_base = 0x3f8;  /* ttyS0 */
 #define DLL             0       /*  Divisor Latch Low         */
 #define DLH             1       /*  Divisor latch High        */
 
-static unsigned int io_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int io_serial_in(unsigned long addr, int offset)
 {
 	return inb(addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_in);
 
-static void io_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void io_serial_out(unsigned long addr, int offset, int value)
 {
 	outb(value, addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_out);
 
-static unsigned int (*serial_in)(unsigned long addr, int offset) = io_serial_in;
-static void (*serial_out)(unsigned long addr, int offset, int value) = io_serial_out;
+DEFINE_STATIC_CALL(serial_in, io_serial_in);
+DEFINE_STATIC_CALL(serial_out, io_serial_out);
 
 static int early_serial_putc(unsigned char ch)
 {
 	unsigned timeout = 0xffff;
 
-	while ((serial_in(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
+	while ((static_call(serial_in)(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
 		cpu_relax();
-	serial_out(early_serial_base, TXR, ch);
+	static_call(serial_out)(early_serial_base, TXR, ch);
 	return timeout ? 0 : -1;
 }
 
@@ -131,16 +135,21 @@ static __init void early_serial_hw_init(unsigned divisor)
 {
 	unsigned char c;
 
-	serial_out(early_serial_base, LCR, 0x3);	/* 8n1 */
-	serial_out(early_serial_base, IER, 0);	/* no interrupt */
-	serial_out(early_serial_base, FCR, 0);	/* no fifo */
-	serial_out(early_serial_base, MCR, 0x3);	/* DTR + RTS */
+	static_call(serial_out)(early_serial_base, LCR, 0x3);	/* 8n1 */
+	static_call(serial_out)(early_serial_base, IER, 0);	/* no interrupt */
+	static_call(serial_out)(early_serial_base, FCR, 0);	/* no fifo */
+	static_call(serial_out)(early_serial_base, MCR, 0x3);	/* DTR + RTS */
 
-	c = serial_in(early_serial_base, LCR);
-	serial_out(early_serial_base, LCR, c | DLAB);
-	serial_out(early_serial_base, DLL, divisor & 0xff);
-	serial_out(early_serial_base, DLH, (divisor >> 8) & 0xff);
-	serial_out(early_serial_base, LCR, c & ~DLAB);
+	c = static_call(serial_in)(early_serial_base, LCR);
+	static_call(serial_out)(early_serial_base, LCR, c | DLAB);
+	static_call(serial_out)(early_serial_base, DLL, divisor & 0xff);
+	static_call(serial_out)(early_serial_base, DLH, (divisor >> 8) & 0xff);
+	static_call(serial_out)(early_serial_base, LCR, c & ~DLAB);
+
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_X86_64)
+	if (static_call_query(serial_in) == io_serial_in)
+		kexec_debug_8250_port = early_serial_base;
+#endif
 }
 
 #define DEFAULT_BAUD 9600
@@ -183,30 +192,66 @@ static __init void early_serial_init(char *s)
 	/* Convert from baud to divisor value */
 	divisor = 115200 / baud;
 
-	/* These will always be IO based ports */
-	serial_in = io_serial_in;
-	serial_out = io_serial_out;
-
 	/* Set up the HW */
 	early_serial_hw_init(divisor);
 }
 
-#ifdef CONFIG_PCI
-static void mem32_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	writel(value, vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_out);
 
-static unsigned int mem32_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	return readl(vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_in);
 
 /*
+ * early_mmio_serial_init() - Initialize MMIO-based early serial console.
+ * @s: MMIO-based serial specification.
+ */
+static __init void early_mmio_serial_init(char *s)
+{
+	unsigned long baudrate;
+	unsigned long membase;
+	char *e;
+
+	if (*s == ',')
+		s++;
+
+	if (!strncmp(s, "0x", 2)) {
+		/* NB: only 32-bit addresses are supported. */
+		membase = simple_strtoul(s, &e, 16);
+		early_serial_base = (unsigned long)early_ioremap(membase, PAGE_SIZE);
+
+		static_call_update(serial_in, mem32_serial_in);
+		static_call_update(serial_out, mem32_serial_out);
+
+		s += strcspn(s, ",");
+		if (*s == ',')
+			s++;
+	}
+
+	if (!strncmp(s, "nocfg", 5)) {
+		baudrate = 0;
+	} else {
+		baudrate = simple_strtoul(s, &e, 0);
+		if (baudrate == 0 || s == e)
+			baudrate = DEFAULT_BAUD;
+	}
+
+	if (baudrate)
+		early_serial_hw_init(115200 / baudrate);
+}
+
+#ifdef CONFIG_PCI
+/*
  * early_pci_serial_init()
  *
  * This function is invoked when the early_printk param starts with "pciserial"
@@ -278,18 +323,19 @@ static __init void early_pci_serial_init(char *s)
 	 */
 	if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
 		/* it is IO mapped */
-		serial_in = io_serial_in;
-		serial_out = io_serial_out;
 		early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
 		write_pci_config(bus, slot, func, PCI_COMMAND,
 				 cmdreg|PCI_COMMAND_IO);
 	} else {
 		/* It is memory mapped - assume 32-bit alignment */
-		serial_in = mem32_serial_in;
-		serial_out = mem32_serial_out;
+		static_call_update(serial_in, mem32_serial_in);
+		static_call_update(serial_out, mem32_serial_out);
 		/* WARNING! assuming the address is always in the first 4G */
 		early_serial_base =
 			(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_X86_64)
+		kexec_debug_8250_mmio32 = bar0 & PCI_BASE_ADDRESS_MEM_MASK;
+#endif
 		write_pci_config(bus, slot, func, PCI_COMMAND,
 				 cmdreg|PCI_COMMAND_MEMORY);
 	}
@@ -352,6 +398,11 @@ static int __init setup_early_printk(char *buf)
 	keep = (strstr(buf, "keep") != NULL);
 
 	while (*buf != '\0') {
+		if (!strncmp(buf, "mmio32", 6)) {
+			buf += 6;
+			early_mmio_serial_init(buf);
+			early_console_register(&early_serial_console, keep);
+		}
 		if (!strncmp(buf, "serial", 6)) {
 			buf += 6;
 			early_serial_init(buf);
@@ -365,9 +416,9 @@ static int __init setup_early_printk(char *buf)
 		}
 #ifdef CONFIG_PCI
 		if (!strncmp(buf, "pciserial", 9)) {
-			early_pci_serial_init(buf + 9);
+			buf += 9; /* Keep from match the above "pciserial" */
+			early_pci_serial_init(buf);
 			early_console_register(&early_serial_console, keep);
-			buf += 9; /* Keep from match the above "serial" */
 		}
 #endif
 		if (!strncmp(buf, "vga", 3) &&
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
index f6d856bd50bc..10d0a720659c 100644
--- a/arch/x86/kernel/fpu/context.h
+++ b/arch/x86/kernel/fpu/context.h
@@ -53,7 +53,7 @@ static inline void fpregs_activate(struct fpu *fpu)
 /* Internal helper for switch_fpu_return() and signal frame setup */
 static inline void fpregs_restore_userregs(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int cpu = smp_processor_id();
 
 	if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER)))
@@ -67,7 +67,7 @@ static inline void fpregs_restore_userregs(void)
 		 * If PKRU is enabled, then the PKRU value is already
 		 * correct because it was either set in switch_to() or in
 		 * flush_thread(). So it is excluded because it might be
-		 * not up to date in current->thread.fpu.xsave state.
+		 * not up to date in current->thread.fpu->xsave state.
 		 *
 		 * XFD state is handled in restore_fpregs_from_fpstate().
 		 */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1209c7aebb21..ea138583dd92 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -11,6 +11,7 @@
 #include <asm/fpu/sched.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
+#include <asm/msr.h>
 #include <asm/traps.h>
 #include <asm/irq_regs.h>
 
@@ -43,14 +44,27 @@ struct fpu_state_config fpu_user_cfg __ro_after_init;
  */
 struct fpstate init_fpstate __ro_after_init;
 
-/* Track in-kernel FPU usage */
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
+/*
+ * Track FPU initialization and kernel-mode usage. 'true' means the FPU is
+ * initialized and is not currently being used by the kernel:
+ */
+DEFINE_PER_CPU(bool, kernel_fpu_allowed);
 
 /*
  * Track which context is using the FPU on the CPU:
  */
 DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
 
+#ifdef CONFIG_X86_DEBUG_FPU
+struct fpu *x86_task_fpu(struct task_struct *task)
+{
+	if (WARN_ON_ONCE(task->flags & PF_KTHREAD))
+		return NULL;
+
+	return (void *)task + sizeof(*task);
+}
+#endif
+
 /*
  * Can we use the FPU in kernel mode with the
  * whole "kernel_fpu_begin/end()" sequence?
@@ -60,8 +74,18 @@ bool irq_fpu_usable(void)
 	if (WARN_ON_ONCE(in_nmi()))
 		return false;
 
-	/* In kernel FPU usage already active? */
-	if (this_cpu_read(in_kernel_fpu))
+	/*
+	 * Return false in the following cases:
+	 *
+	 * - FPU is not yet initialized. This can happen only when the call is
+	 *   coming from CPU onlining, for example for microcode checksumming.
+	 * - The kernel is already using the FPU, either because of explicit
+	 *   nesting (which should never be done), or because of implicit
+	 *   nesting when a hardirq interrupted a kernel-mode FPU section.
+	 *
+	 * The single boolean check below handles both cases:
+	 */
+	if (!this_cpu_read(kernel_fpu_allowed))
 		return false;
 
 	/*
@@ -195,7 +219,7 @@ void fpu_reset_from_exception_fixup(void)
 #if IS_ENABLED(CONFIG_KVM)
 static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
 
-static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
+static void fpu_lock_guest_permissions(void)
 {
 	struct fpu_state_perm *fpuperm;
 	u64 perm;
@@ -204,15 +228,13 @@ static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
 		return;
 
 	spin_lock_irq(&current->sighand->siglock);
-	fpuperm = &current->group_leader->thread.fpu.guest_perm;
+	fpuperm = &x86_task_fpu(current->group_leader)->guest_perm;
 	perm = fpuperm->__state_perm;
 
 	/* First fpstate allocation locks down permissions. */
 	WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED);
 
 	spin_unlock_irq(&current->sighand->siglock);
-
-	gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
 }
 
 bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
@@ -220,7 +242,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	struct fpstate *fpstate;
 	unsigned int size;
 
-	size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+	size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
 	fpstate = vzalloc(size);
 	if (!fpstate)
 		return false;
@@ -232,8 +254,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	fpstate->is_guest	= true;
 
 	gfpu->fpstate		= fpstate;
-	gfpu->xfeatures		= fpu_user_cfg.default_features;
-	gfpu->perm		= fpu_user_cfg.default_features;
+	gfpu->xfeatures		= fpu_kernel_cfg.default_features;
 
 	/*
 	 * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
@@ -248,7 +269,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size))
 		gfpu->uabi_size = fpu_user_cfg.default_size;
 
-	fpu_init_guest_permissions(gfpu);
+	fpu_lock_guest_permissions();
 
 	return true;
 }
@@ -256,16 +277,16 @@ EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
 
 void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
 {
-	struct fpstate *fps = gfpu->fpstate;
+	struct fpstate *fpstate = gfpu->fpstate;
 
-	if (!fps)
+	if (!fpstate)
 		return;
 
-	if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
+	if (WARN_ON_ONCE(!fpstate->is_valloc || !fpstate->is_guest || fpstate->in_use))
 		return;
 
 	gfpu->fpstate = NULL;
-	vfree(fps);
+	vfree(fpstate);
 }
 EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
 
@@ -316,12 +337,12 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
  */
 void fpu_sync_guest_vmexit_xfd_state(void)
 {
-	struct fpstate *fps = current->thread.fpu.fpstate;
+	struct fpstate *fpstate = x86_task_fpu(current)->fpstate;
 
 	lockdep_assert_irqs_disabled();
 	if (fpu_state_size_dynamic()) {
-		rdmsrl(MSR_IA32_XFD, fps->xfd);
-		__this_cpu_write(xfd_state, fps->xfd);
+		rdmsrq(MSR_IA32_XFD, fpstate->xfd);
+		__this_cpu_write(xfd_state, fpstate->xfd);
 	}
 }
 EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
@@ -330,7 +351,7 @@ EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
 int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 {
 	struct fpstate *guest_fps = guest_fpu->fpstate;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *cur_fps = fpu->fpstate;
 
 	fpregs_lock();
@@ -420,17 +441,19 @@ EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
 
 void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON_FPU(!irq_fpu_usable());
-	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
 
-	this_cpu_write(in_kernel_fpu, true);
+	/* Toggle kernel_fpu_allowed to false: */
+	WARN_ON_FPU(!this_cpu_read(kernel_fpu_allowed));
+	this_cpu_write(kernel_fpu_allowed, false);
 
 	if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) &&
 	    !test_thread_flag(TIF_NEED_FPU_LOAD)) {
 		set_thread_flag(TIF_NEED_FPU_LOAD);
-		save_fpregs_to_fpstate(&current->thread.fpu);
+		save_fpregs_to_fpstate(x86_task_fpu(current));
 	}
 	__cpu_invalidate_fpregs_state();
 
@@ -445,10 +468,12 @@ EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
 
 void kernel_fpu_end(void)
 {
-	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+	/* Toggle kernel_fpu_allowed back to true: */
+	WARN_ON_FPU(this_cpu_read(kernel_fpu_allowed));
+	this_cpu_write(kernel_fpu_allowed, true);
 
-	this_cpu_write(in_kernel_fpu, false);
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
@@ -458,7 +483,7 @@ EXPORT_SYMBOL_GPL(kernel_fpu_end);
  */
 void fpu_sync_fpstate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu);
+	WARN_ON_FPU(fpu != x86_task_fpu(current));
 
 	fpregs_lock();
 	trace_x86_fpu_before_save(fpu);
@@ -499,7 +524,7 @@ static inline void fpstate_init_fstate(struct fpstate *fpstate)
 /*
  * Used in two places:
  * 1) Early boot to setup init_fpstate for non XSAVE systems
- * 2) fpu_init_fpstate_user() which is invoked from KVM
+ * 2) fpu_alloc_guest_fpstate() which is invoked from KVM
  */
 void fpstate_init_user(struct fpstate *fpstate)
 {
@@ -543,7 +568,7 @@ void fpstate_reset(struct fpu *fpu)
 static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 {
 	if (fpu_state_size_dynamic()) {
-		struct fpu *src_fpu = &current->group_leader->thread.fpu;
+		struct fpu *src_fpu = x86_task_fpu(current->group_leader);
 
 		spin_lock_irq(&current->sighand->siglock);
 		/* Fork also inherits the permissions of the parent */
@@ -563,7 +588,7 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
 	if (!ssp)
 		return 0;
 
-	xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave,
+	xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave,
 				XFEATURE_CET_USER);
 
 	/*
@@ -584,8 +609,16 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
 int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	      unsigned long ssp)
 {
-	struct fpu *src_fpu = &current->thread.fpu;
-	struct fpu *dst_fpu = &dst->thread.fpu;
+	/*
+	 * We allocate the new FPU structure right after the end of the task struct.
+	 * task allocation size already took this into account.
+	 *
+	 * This is safe because task_struct size is a multiple of cacheline size,
+	 * thus x86_task_fpu() will always be cacheline aligned as well.
+	 */
+	struct fpu *dst_fpu = (void *)dst + sizeof(*dst);
+
+	BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0);
 
 	/* The new task's FPU state cannot be valid in the hardware. */
 	dst_fpu->last_cpu = -1;
@@ -648,19 +681,22 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	if (update_fpu_shstk(dst, ssp))
 		return 1;
 
-	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
 
 	return 0;
 }
 
 /*
- * Whitelist the FPU register state embedded into task_struct for hardened
- * usercopy.
+ * While struct fpu is no longer part of struct thread_struct, it is still
+ * allocated after struct task_struct in the "task_struct" kmem cache. But
+ * since FPU is expected to be part of struct thread_struct, we have to
+ * adjust for it here.
  */
 void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
 {
-	*offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
+	/* The allocation follows struct task_struct. */
+	*offset = sizeof(struct task_struct) - offsetof(struct task_struct, thread);
+	*offset += offsetof(struct fpu, __fpstate.regs);
 	*size = fpu_kernel_cfg.default_size;
 }
 
@@ -673,11 +709,18 @@ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
  * a state-restore is coming: either an explicit one,
  * or a reschedule.
  */
-void fpu__drop(struct fpu *fpu)
+void fpu__drop(struct task_struct *tsk)
 {
+	struct fpu *fpu;
+
+	if (test_tsk_thread_flag(tsk, TIF_NEED_FPU_LOAD))
+		return;
+
+	fpu = x86_task_fpu(tsk);
+
 	preempt_disable();
 
-	if (fpu == &current->thread.fpu) {
+	if (fpu == x86_task_fpu(current)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
@@ -709,9 +752,9 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
 /*
  * Reset current->fpu memory state to the init values.
  */
-static void fpu_reset_fpregs(void)
+static void fpu_reset_fpstate_regs(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	fpregs_lock();
 	__fpu_invalidate_fpregs_state(fpu);
@@ -740,11 +783,11 @@ static void fpu_reset_fpregs(void)
  */
 void fpu__clear_user_states(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu);
+	WARN_ON_FPU(fpu != x86_task_fpu(current));
 
 	fpregs_lock();
 	if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
-		fpu_reset_fpregs();
+		fpu_reset_fpstate_regs();
 		fpregs_unlock();
 		return;
 	}
@@ -773,8 +816,8 @@ void fpu__clear_user_states(struct fpu *fpu)
 
 void fpu_flush_thread(void)
 {
-	fpstate_reset(&current->thread.fpu);
-	fpu_reset_fpregs();
+	fpstate_reset(x86_task_fpu(current));
+	fpu_reset_fpstate_regs();
 }
 /*
  * Load FPU context before returning to userspace.
@@ -814,7 +857,7 @@ void fpregs_lock_and_load(void)
  */
 void fpregs_assert_state_consistent(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		return;
@@ -826,7 +869,7 @@ EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
 
 void fpregs_mark_activate(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	fpregs_activate(fpu);
 	fpu->last_cpu = smp_processor_id();
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 998a08f17e33..99db41bf9fa6 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -38,7 +38,7 @@ static void fpu__init_cpu_generic(void)
 	/* Flush out any pending x87 state: */
 #ifdef CONFIG_MATH_EMULATION
 	if (!boot_cpu_has(X86_FEATURE_FPU))
-		fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+		;
 	else
 #endif
 		asm volatile ("fninit");
@@ -51,6 +51,9 @@ void fpu__init_cpu(void)
 {
 	fpu__init_cpu_generic();
 	fpu__init_cpu_xstate();
+
+	/* Start allowing kernel-mode FPU: */
+	this_cpu_write(kernel_fpu_allowed, true);
 }
 
 static bool __init fpu__probe_without_cpuid(void)
@@ -73,6 +76,8 @@ static bool __init fpu__probe_without_cpuid(void)
 
 static void __init fpu__init_system_early_generic(void)
 {
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+
 	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
 	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
 		if (fpu__probe_without_cpuid())
@@ -94,7 +99,6 @@ static void __init fpu__init_system_early_generic(void)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu;
-EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
@@ -150,11 +154,13 @@ static void __init fpu__init_task_struct_size(void)
 {
 	int task_size = sizeof(struct task_struct);
 
+	task_size += sizeof(struct fpu);
+
 	/*
 	 * Subtract off the static size of the register state.
 	 * It potentially has a bunch of padding.
 	 */
-	task_size -= sizeof(current->thread.fpu.__fpstate.regs);
+	task_size -= sizeof(union fpregs_state);
 
 	/*
 	 * Add back the dynamically-calculated register state
@@ -164,14 +170,9 @@ static void __init fpu__init_task_struct_size(void)
 
 	/*
 	 * We dynamically size 'struct fpu', so we require that
-	 * it be at the end of 'thread_struct' and that
-	 * 'thread_struct' be at the end of 'task_struct'.  If
-	 * you hit a compile error here, check the structure to
-	 * see if something got added to the end.
+	 * 'state' be at the end of 'it:
 	 */
 	CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate);
-	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
-	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
 
 	arch_task_struct_size = task_size;
 }
@@ -204,7 +205,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	fpu_kernel_cfg.default_size = size;
 	fpu_user_cfg.max_size = size;
 	fpu_user_cfg.default_size = size;
-	fpstate_reset(&current->thread.fpu);
 }
 
 /*
@@ -213,7 +213,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  */
 void __init fpu__init_system(void)
 {
-	fpstate_reset(&current->thread.fpu);
 	fpu__init_system_early_generic();
 
 	/*
diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
index dbdb31f55fc7..975de070c9c9 100644
--- a/arch/x86/kernel/fpu/internal.h
+++ b/arch/x86/kernel/fpu/internal.h
@@ -18,7 +18,7 @@ static __always_inline __pure bool use_fxsr(void)
 #ifdef CONFIG_X86_DEBUG_FPU
 # define WARN_ON_FPU(x) WARN_ON_ONCE(x)
 #else
-# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+# define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; })
 #endif
 
 /* Used in init.c */
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 887b0b8e21e3..0986c2200adc 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -45,7 +45,7 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r
  */
 static void sync_fpstate(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu)
+	if (fpu == x86_task_fpu(current))
 		fpu_sync_fpstate(fpu);
 }
 
@@ -63,7 +63,7 @@ static void fpu_force_restore(struct fpu *fpu)
 	 * Only stopped child tasks can be used to modify the FPU
 	 * state in the fpstate buffer:
 	 */
-	WARN_ON_FPU(fpu == &current->thread.fpu);
+	WARN_ON_FPU(fpu == x86_task_fpu(current));
 
 	__fpu_invalidate_fpregs_state(fpu);
 }
@@ -71,7 +71,7 @@ static void fpu_force_restore(struct fpu *fpu)
 int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 		struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 
 	if (!cpu_feature_enabled(X86_FEATURE_FXSR))
 		return -ENODEV;
@@ -91,7 +91,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 		unsigned int pos, unsigned int count,
 		const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct fxregs_state newstate;
 	int ret;
 
@@ -133,7 +133,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 	if (!cpu_feature_enabled(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
-	sync_fpstate(&target->thread.fpu);
+	sync_fpstate(x86_task_fpu(target));
 
 	copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE);
 	return 0;
@@ -143,7 +143,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 		  unsigned int pos, unsigned int count,
 		  const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct xregs_state *tmpbuf = NULL;
 	int ret;
 
@@ -187,7 +187,7 @@ int ssp_active(struct task_struct *target, const struct user_regset *regset)
 int ssp_get(struct task_struct *target, const struct user_regset *regset,
 	    struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct cet_user_state *cetregs;
 
 	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
@@ -214,7 +214,7 @@ int ssp_set(struct task_struct *target, const struct user_regset *regset,
 	    unsigned int pos, unsigned int count,
 	    const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct xregs_state *xsave = &fpu->fpstate->regs.xsave;
 	struct cet_user_state *cetregs;
 	unsigned long user_ssp;
@@ -368,7 +368,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env,
 void
 convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 {
-	__convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave);
+	__convert_from_fxsr(env, tsk, &x86_task_fpu(tsk)->fpstate->regs.fxsave);
 }
 
 void convert_to_fxsr(struct fxregs_state *fxsave,
@@ -401,7 +401,7 @@ void convert_to_fxsr(struct fxregs_state *fxsave,
 int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	       struct membuf to)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct user_i387_ia32_struct env;
 	struct fxregs_state fxsave, *fx;
 
@@ -433,7 +433,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	       unsigned int pos, unsigned int count,
 	       const void *kbuf, const void __user *ubuf)
 {
-	struct fpu *fpu = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct user_i387_ia32_struct env;
 	int ret;
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 8f62e0666dea..c3ec2512f2bb 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -27,19 +27,14 @@
 static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 					    struct _fpx_sw_bytes *fx_sw)
 {
-	int min_xstate_size = sizeof(struct fxregs_state) +
-			      sizeof(struct xstate_header);
 	void __user *fpstate = fxbuf;
 	unsigned int magic2;
 
 	if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
 		return false;
 
-	/* Check for the first magic field and other error scenarios. */
-	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
-	    fx_sw->xstate_size < min_xstate_size ||
-	    fx_sw->xstate_size > current->thread.fpu.fpstate->user_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
+	/* Check for the first magic field */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1)
 		goto setfx;
 
 	/*
@@ -48,13 +43,13 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
+	if (__get_user(magic2, (__u32 __user *)(fpstate + x86_task_fpu(current)->fpstate->user_size)))
 		return false;
 
 	if (likely(magic2 == FP_XSTATE_MAGIC2))
 		return true;
 setfx:
-	trace_x86_fpu_xstate_check_failed(&current->thread.fpu);
+	trace_x86_fpu_xstate_check_failed(x86_task_fpu(current));
 
 	/* Set the parameters for fx only state */
 	fx_sw->magic1 = 0;
@@ -69,13 +64,13 @@ setfx:
 static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
 {
 	if (use_fxsr()) {
-		struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave;
+		struct xregs_state *xsave = &x86_task_fpu(tsk)->fpstate->regs.xsave;
 		struct user_i387_ia32_struct env;
 		struct _fpstate_32 __user *fp = buf;
 
 		fpregs_lock();
 		if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-			fxsave(&tsk->thread.fpu.fpstate->regs.fxsave);
+			fxsave(&x86_task_fpu(tsk)->fpstate->regs.fxsave);
 		fpregs_unlock();
 
 		convert_from_fxsr(&env, tsk);
@@ -119,7 +114,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 {
 	struct xregs_state __user *x = buf;
 	struct _fpx_sw_bytes sw_bytes = {};
-	u32 xfeatures;
 	int err;
 
 	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
@@ -133,12 +127,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 			  (__u32 __user *)(buf + fpstate->user_size));
 
 	/*
-	 * Read the xfeatures which we copied (directly from the cpu or
-	 * from the state in task struct) to the user buffers.
-	 */
-	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
-
-	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
 	 * vector while saving the state to the user context. This will
 	 * enable us capturing any changes(during sigreturn) to
@@ -149,9 +137,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	 * header as well as change any contents in the memory layout.
 	 * xrestore as part of sigreturn will capture all the changes.
 	 */
-	xfeatures |= XFEATURE_MASK_FPSSE;
-
-	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+	err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE);
 
 	return !err;
 }
@@ -189,7 +175,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pk
 bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru)
 {
 	struct task_struct *tsk = current;
-	struct fpstate *fpstate = tsk->thread.fpu.fpstate;
+	struct fpstate *fpstate = x86_task_fpu(tsk)->fpstate;
 	bool ia32_fxstate = (buf != buf_fx);
 	int ret;
 
@@ -277,7 +263,7 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
  */
 static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int ret;
 
 	/* Restore enabled features only. */
@@ -337,7 +323,7 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 			      bool ia32_fxstate)
 {
 	struct task_struct *tsk = current;
-	struct fpu *fpu = &tsk->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(tsk);
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
@@ -457,7 +443,7 @@ static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate)
  */
 bool fpu__restore_sig(void __user *buf, int ia32_frame)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	void __user *buf_fx = buf;
 	bool ia32_fxstate = false;
 	bool success = false;
@@ -504,7 +490,7 @@ unsigned long
 fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
 		     unsigned long *buf_fx, unsigned long *size)
 {
-	unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate);
+	unsigned long frame_size = xstate_sigframe_size(x86_task_fpu(current)->fpstate);
 
 	*buf_fx = sp = round_down(sp - frame_size, 64);
 	if (ia32_frame && use_fxsr()) {
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 27417b685c1d..9aa9ac8399ae 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -14,13 +14,15 @@
 #include <linux/proc_fs.h>
 #include <linux/vmalloc.h>
 #include <linux/coredump.h>
+#include <linux/sort.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/xcr.h>
 
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
+#include <asm/msr.h>
 #include <asm/tlbflush.h>
 #include <asm/prctl.h>
 #include <asm/elf.h>
@@ -62,6 +64,7 @@ static const char *xfeature_names[] =
 	"unknown xstate feature",
 	"AMX Tile config",
 	"AMX Tile data",
+	"APX registers",
 	"unknown xstate feature",
 };
 
@@ -80,6 +83,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
 	[XFEATURE_CET_USER]			= X86_FEATURE_SHSTK,
 	[XFEATURE_XTILE_CFG]			= X86_FEATURE_AMX_TILE,
 	[XFEATURE_XTILE_DATA]			= X86_FEATURE_AMX_TILE,
+	[XFEATURE_APX]				= X86_FEATURE_APX,
 };
 
 static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
@@ -88,6 +92,31 @@ static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
 
+/*
+ * Ordering of xstate components in uncompacted format:  The xfeature
+ * number does not necessarily indicate its position in the XSAVE buffer.
+ * This array defines the traversal order of xstate features.
+ */
+static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init =
+	{ [ 0 ... XFEATURE_MAX - 1] = -1};
+
+static inline unsigned int next_xfeature_order(unsigned int i, u64 mask)
+{
+	for (; xfeature_uncompact_order[i] != -1; i++) {
+		if (mask & BIT_ULL(xfeature_uncompact_order[i]))
+			break;
+	}
+
+	return i;
+}
+
+/* Iterate xstate features in uncompacted order: */
+#define for_each_extended_xfeature_in_order(i, mask)	\
+	for (i = 0;					\
+	     i = next_xfeature_order(i, mask),		\
+	     xfeature_uncompact_order[i] != -1;		\
+	     i++)
+
 #define XSTATE_FLAG_SUPERVISOR	BIT(0)
 #define XSTATE_FLAG_ALIGNED64	BIT(1)
 
@@ -199,7 +228,7 @@ void fpu__init_cpu_xstate(void)
 	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
 	 */
 	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+		wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
 				     xfeatures_mask_independent());
 	}
 }
@@ -209,16 +238,20 @@ static bool xfeature_enabled(enum xfeature xfeature)
 	return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
 }
 
+static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2)
+{
+	return  xstate_offsets[*(unsigned int *)xfeature1] -
+		xstate_offsets[*(unsigned int *)xfeature2];
+}
+
 /*
  * Record the offsets and sizes of various xstates contained
- * in the XSAVE state memory layout.
+ * in the XSAVE state memory layout. Also, create an ordered
+ * list of xfeatures for handling out-of-order offsets.
  */
 static void __init setup_xstate_cache(void)
 {
-	u32 eax, ebx, ecx, edx, i;
-	/* start at the beginning of the "extended state" */
-	unsigned int last_good_offset = offsetof(struct xregs_state,
-						 extended_state_area);
+	u32 eax, ebx, ecx, edx, xfeature, i = 0;
 	/*
 	 * The FP xstates and SSE xstates are legacy states. They are always
 	 * in the fixed offsets in the xsave area in either compacted form
@@ -232,39 +265,30 @@ static void __init setup_xstate_cache(void)
 	xstate_sizes[XFEATURE_SSE]	= sizeof_field(struct fxregs_state,
 						       xmm_space);
 
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx);
+	for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) {
+		cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx);
 
-		xstate_sizes[i] = eax;
-		xstate_flags[i] = ecx;
+		xstate_sizes[xfeature] = eax;
+		xstate_flags[xfeature] = ecx;
 
 		/*
 		 * If an xfeature is supervisor state, the offset in EBX is
 		 * invalid, leave it to -1.
 		 */
-		if (xfeature_is_supervisor(i))
+		if (xfeature_is_supervisor(xfeature))
 			continue;
 
-		xstate_offsets[i] = ebx;
+		xstate_offsets[xfeature] = ebx;
 
-		/*
-		 * In our xstate size checks, we assume that the highest-numbered
-		 * xstate feature has the highest offset in the buffer.  Ensure
-		 * it does.
-		 */
-		WARN_ONCE(last_good_offset > xstate_offsets[i],
-			  "x86/fpu: misordered xstate at %d\n", last_good_offset);
-
-		last_good_offset = xstate_offsets[i];
+		/* Populate the list of xfeatures before sorting */
+		xfeature_uncompact_order[i++] = xfeature;
 	}
-}
 
-static void __init print_xstate_feature(u64 xstate_mask)
-{
-	const char *feature_name;
-
-	if (cpu_has_xfeatures(xstate_mask, &feature_name))
-		pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
+	/*
+	 * Sort xfeatures by their offsets to support out-of-order
+	 * offsets in the uncompacted format.
+	 */
+	sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL);
 }
 
 /*
@@ -272,19 +296,15 @@ static void __init print_xstate_feature(u64 xstate_mask)
  */
 static void __init print_xstate_features(void)
 {
-	print_xstate_feature(XFEATURE_MASK_FP);
-	print_xstate_feature(XFEATURE_MASK_SSE);
-	print_xstate_feature(XFEATURE_MASK_YMM);
-	print_xstate_feature(XFEATURE_MASK_BNDREGS);
-	print_xstate_feature(XFEATURE_MASK_BNDCSR);
-	print_xstate_feature(XFEATURE_MASK_OPMASK);
-	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
-	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
-	print_xstate_feature(XFEATURE_MASK_PKRU);
-	print_xstate_feature(XFEATURE_MASK_PASID);
-	print_xstate_feature(XFEATURE_MASK_CET_USER);
-	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
-	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
+	int i;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = BIT_ULL(i);
+		const char *name;
+
+		if (cpu_has_xfeatures(mask, &name))
+			pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name);
+	}
 }
 
 /*
@@ -352,7 +372,8 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
 	 XFEATURE_MASK_BNDCSR |			\
 	 XFEATURE_MASK_PASID |			\
 	 XFEATURE_MASK_CET_USER |		\
-	 XFEATURE_MASK_XTILE)
+	 XFEATURE_MASK_XTILE |			\
+	 XFEATURE_MASK_APX)
 
 /*
  * setup the xstate image representing the init state
@@ -552,6 +573,7 @@ static bool __init check_xstate_against_struct(int nr)
 	case XFEATURE_PASID:	  return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
 	case XFEATURE_XTILE_CFG:  return XCHECK_SZ(sz, nr, struct xtile_cfg);
 	case XFEATURE_CET_USER:	  return XCHECK_SZ(sz, nr, struct cet_user_state);
+	case XFEATURE_APX:        return XCHECK_SZ(sz, nr, struct apx_state);
 	case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
 	default:
 		XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
@@ -564,13 +586,20 @@ static bool __init check_xstate_against_struct(int nr)
 static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
 {
 	unsigned int topmost = fls64(xfeatures) -  1;
-	unsigned int offset = xstate_offsets[topmost];
+	unsigned int offset, i;
 
 	if (topmost <= XFEATURE_SSE)
 		return sizeof(struct xregs_state);
 
-	if (compacted)
+	if (compacted) {
 		offset = xfeature_get_offset(xfeatures, topmost);
+	} else {
+		/* Walk through the xfeature order to pick the last */
+		for_each_extended_xfeature_in_order(i, xfeatures)
+			topmost = xfeature_uncompact_order[i];
+		offset = xstate_offsets[topmost];
+	}
+
 	return offset + xstate_sizes[topmost];
 }
 
@@ -651,7 +680,7 @@ static unsigned int __init get_xsave_compacted_size(void)
 		return get_compacted_size();
 
 	/* Disable independent features. */
-	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor());
 
 	/*
 	 * Ask the hardware what size is required of the buffer.
@@ -660,7 +689,7 @@ static unsigned int __init get_xsave_compacted_size(void)
 	size = get_compacted_size();
 
 	/* Re-enable independent features so XSAVES will work on them again. */
-	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+	wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
 
 	return size;
 }
@@ -723,6 +752,8 @@ static int __init init_xstate_size(void)
  */
 static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
 {
+	pr_info("x86/fpu: XSAVE disabled\n");
+
 	fpu_kernel_cfg.max_features = 0;
 	cr4_clear_bits(X86_CR4_OSXSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
@@ -739,7 +770,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
 	 */
 	init_fpstate.xfd = 0;
 
-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 }
 
 /*
@@ -787,6 +818,17 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX &&
+	    fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) {
+		/*
+		 * This is a problematic CPU configuration where two
+		 * conflicting state components are both enumerated.
+		 */
+		pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n",
+		       fpu_kernel_cfg.max_features);
+		goto out_disable;
+	}
+
 	fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
 					      XFEATURE_MASK_INDEPENDENT;
 
@@ -846,9 +888,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	if (err)
 		goto out_disable;
 
-	/* Reset the state for the current task */
-	fpstate_reset(&current->thread.fpu);
-
 	/*
 	 * Update info used for ptrace frames; use standard-format size and no
 	 * supervisor xstates:
@@ -864,7 +903,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
 
 	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
-		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n",
 			sizeof(init_fpstate.regs), init_fpstate.size);
 		goto out_disable;
 	}
@@ -876,7 +915,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	 * xfeatures mask.
 	 */
 	if (xfeatures != fpu_kernel_cfg.max_features) {
-		pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
+		pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n",
 		       xfeatures, fpu_kernel_cfg.max_features);
 		goto out_disable;
 	}
@@ -916,12 +955,12 @@ void fpu__resume_cpu(void)
 	 * of XSAVES and MSR_IA32_XSS.
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+		wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
 				     xfeatures_mask_independent());
 	}
 
 	if (fpu_state_size_dynamic())
-		wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+		wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
 }
 
 /*
@@ -1083,10 +1122,9 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
 	struct xregs_state *xinit = &init_fpstate.regs.xsave;
 	struct xregs_state *xsave = &fpstate->regs.xsave;
+	unsigned int zerofrom, i, xfeature;
 	struct xstate_header header;
-	unsigned int zerofrom;
 	u64 mask;
-	int i;
 
 	memset(&header, 0, sizeof(header));
 	header.xfeatures = xsave->header.xfeatures;
@@ -1155,15 +1193,16 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	mask = header.xfeatures;
 
-	for_each_extended_xfeature(i, mask) {
+	for_each_extended_xfeature_in_order(i, mask) {
+		xfeature = xfeature_uncompact_order[i];
 		/*
 		 * If there was a feature or alignment gap, zero the space
 		 * in the destination buffer.
 		 */
-		if (zerofrom < xstate_offsets[i])
-			membuf_zero(&to, xstate_offsets[i] - zerofrom);
+		if (zerofrom < xstate_offsets[xfeature])
+			membuf_zero(&to, xstate_offsets[xfeature] - zerofrom);
 
-		if (i == XFEATURE_PKRU) {
+		if (xfeature == XFEATURE_PKRU) {
 			struct pkru_state pkru = {0};
 			/*
 			 * PKRU is not necessarily up to date in the
@@ -1173,14 +1212,14 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
 			membuf_write(&to,
-				     __raw_xsave_addr(xsave, i),
-				     xstate_sizes[i]);
+				     __raw_xsave_addr(xsave, xfeature),
+				     xstate_sizes[xfeature]);
 		}
 		/*
 		 * Keep track of the last copied state in the non-compacted
 		 * target buffer for gap zeroing.
 		 */
-		zerofrom = xstate_offsets[i] + xstate_sizes[i];
+		zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature];
 	}
 
 out:
@@ -1203,8 +1242,8 @@ out:
 void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 			     enum xstate_copy_mode copy_mode)
 {
-	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
-				  tsk->thread.fpu.fpstate->user_xfeatures,
+	__copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+				  x86_task_fpu(tsk)->fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }
 
@@ -1344,7 +1383,7 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u
 int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+	return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru);
 }
 
 static bool validate_independent_components(u64 mask)
@@ -1410,9 +1449,9 @@ void xrstors(struct xregs_state *xstate, u64 mask)
 }
 
 #if IS_ENABLED(CONFIG_KVM)
-void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature)
 {
-	void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+	void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature);
 
 	if (addr)
 		memset(addr, 0, xstate_sizes[xfeature]);
@@ -1438,7 +1477,7 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
 	  * The XFD MSR does not match fpstate->xfd. That's invalid when
 	  * the passed in fpstate is current's fpstate.
 	  */
-	if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+	if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd)
 		return false;
 
 	/*
@@ -1515,7 +1554,7 @@ void fpstate_free(struct fpu *fpu)
 static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 			   unsigned int usize, struct fpu_guest *guest_fpu)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *curfps, *newfps = NULL;
 	unsigned int fpsize;
 	bool in_use;
@@ -1608,7 +1647,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 	 * AVX512.
 	 */
 	bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	u64 mask;
@@ -1618,16 +1657,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 	if ((permitted & requested) == requested)
 		return 0;
 
-	/* Calculate the resulting kernel state size */
+	/*
+	 * Calculate the resulting kernel state size.  Note, @permitted also
+	 * contains supervisor xfeatures even though supervisor are always
+	 * permitted for kernel and guest FPUs, and never permitted for user
+	 * FPUs.
+	 */
 	mask = permitted | requested;
-	/* Take supervisor states into account on the host */
-	if (!guest)
-		mask |= xfeatures_mask_supervisor();
 	ksize = xstate_calculate_size(mask, compacted);
 
-	/* Calculate the resulting user state size */
-	mask &= XFEATURE_MASK_USER_SUPPORTED;
-	usize = xstate_calculate_size(mask, false);
+	/*
+	 * Calculate the resulting user state size.  Take care not to clobber
+	 * the supervisor xfeatures in the new mask!
+	 */
+	usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false);
 
 	if (!guest) {
 		ret = validate_sigaltstack(usize);
@@ -1711,7 +1754,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
 		return -EPERM;
 	}
 
-	fpu = &current->group_leader->thread.fpu;
+	fpu = x86_task_fpu(current->group_leader);
 	perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
 	ksize = perm->__state_size;
 	usize = perm->__user_state_size;
@@ -1816,7 +1859,7 @@ long fpu_xstate_prctl(int option, unsigned long arg2)
  */
 static void avx512_status(struct seq_file *m, struct task_struct *task)
 {
-	unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+	unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
 	long delta;
 
 	if (!timestamp) {
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index aa16f1a1bbcf..52ce19289989 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -5,6 +5,7 @@
 #include <asm/cpufeature.h>
 #include <asm/fpu/xstate.h>
 #include <asm/fpu/xcr.h>
+#include <asm/msr.h>
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(u64, xfd_state);
@@ -22,7 +23,7 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
 
 static inline u64 xstate_get_group_perm(bool guest)
 {
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 
 	/* Pairs with WRITE_ONCE() in xstate_request_perm() */
@@ -69,21 +70,31 @@ static inline u64 xfeatures_mask_independent(void)
 	return fpu_kernel_cfg.independent_features;
 }
 
+static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask)
+{
+	u64 xfeatures;
+	int err;
+
+	/* Read the xfeatures value already saved in the user buffer */
+	err  = __get_user(xfeatures, &xbuf->header.xfeatures);
+	xfeatures |= mask;
+	err |= __put_user(xfeatures, &xbuf->header.xfeatures);
+
+	return err;
+}
+
 /*
  * Update the value of PKRU register that was already pushed onto the signal frame.
  */
-static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
-	u64 xstate_bv;
 	int err;
 
 	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
 		return 0;
 
 	/* Mark PKRU as in-use so that it is restored correctly. */
-	xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
-
-	err =  __put_user(xstate_bv, &buf->header.xfeatures);
+	err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU);
 	if (err)
 		return err;
 
@@ -94,30 +105,33 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 /* XSAVE/XRSTOR wrapper functions */
 
 #ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
+#define REX_SUFFIX	"64"
 #else
-#define REX_PREFIX
+#define REX_SUFFIX
 #endif
 
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVEC		".byte " REX_PREFIX "0x0f,0xc7,0x27"
-#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+#define XSAVE		"xsave" REX_SUFFIX " %[xa]"
+#define XSAVEOPT	"xsaveopt" REX_SUFFIX " %[xa]"
+#define XSAVEC		"xsavec" REX_SUFFIX " %[xa]"
+#define XSAVES		"xsaves" REX_SUFFIX " %[xa]"
+#define XRSTOR		"xrstor" REX_SUFFIX " %[xa]"
+#define XRSTORS		"xrstors" REX_SUFFIX " %[xa]"
 
 /*
  * After this @err contains 0 on success or the trap number when the
  * operation raises an exception.
+ *
+ * The [xa] input parameter below represents the struct xregs_state pointer
+ * and the asm symbolic name for the argument used in the XSAVE/XRSTOR insns
+ * above.
  */
 #define XSTATE_OP(op, st, lmask, hmask, err)				\
 	asm volatile("1:" op "\n\t"					\
 		     "xor %[err], %[err]\n"				\
-		     "2:\n\t"						\
+		     "2:\n"						\
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE)	\
 		     : [err] "=a" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -137,12 +151,12 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
 				   XSAVEC,   X86_FEATURE_XSAVEC,	\
 				   XSAVES,   X86_FEATURE_XSAVES)	\
-		     "\n"						\
+		     "\n\t"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
 		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -156,7 +170,7 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 		     "3:\n"						\
 		     _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE)	\
 		     :							\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)
@@ -168,7 +182,7 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs
 #ifdef CONFIG_X86_64
 static inline void xfd_set_state(u64 xfd)
 {
-	wrmsrl(MSR_IA32_XFD, xfd);
+	wrmsrq(MSR_IA32_XFD, xfd);
 	__this_cpu_write(xfd_state, xfd);
 }
 
@@ -285,7 +299,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
 	 * internally, e.g. PKRU. That's user space ABI and also required
 	 * to allow the signal handler to modify PKRU.
 	 */
-	struct fpstate *fpstate = current->thread.fpu.fpstate;
+	struct fpstate *fpstate = x86_task_fpu(current)->fpstate;
 	u64 mask = fpstate->user_xfeatures;
 	u32 lmask;
 	u32 hmask;
@@ -304,7 +318,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
 	clac();
 
 	if (!err)
-		err = update_pkru_in_sigframe(buf, mask, pkru);
+		err = update_pkru_in_sigframe(buf, pkru);
 
 	return err;
 }
@@ -319,7 +333,7 @@ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64
 	u32 hmask = mask >> 32;
 	int err;
 
-	xfd_validate_state(current->thread.fpu.fpstate, mask, true);
+	xfd_validate_state(x86_task_fpu(current)->fpstate, mask, true);
 
 	stac();
 	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c
index 5e2cd1004980..816187da3a47 100644
--- a/arch/x86/kernel/fred.c
+++ b/arch/x86/kernel/fred.c
@@ -3,6 +3,7 @@
 
 #include <asm/desc.h>
 #include <asm/fred.h>
+#include <asm/msr.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 
@@ -43,23 +44,23 @@ void cpu_init_fred_exceptions(void)
 	 */
 	loadsegment(ss, __KERNEL_DS);
 
-	wrmsrl(MSR_IA32_FRED_CONFIG,
+	wrmsrq(MSR_IA32_FRED_CONFIG,
 	       /* Reserve for CALL emulation */
 	       FRED_CONFIG_REDZONE |
 	       FRED_CONFIG_INT_STKLVL(0) |
 	       FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user));
 
-	wrmsrl(MSR_IA32_FRED_STKLVLS, 0);
+	wrmsrq(MSR_IA32_FRED_STKLVLS, 0);
 
 	/*
 	 * Ater a CPU offline/online cycle, the FRED RSP0 MSR should be
 	 * resynchronized with its per-CPU cache.
 	 */
-	wrmsrl(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0));
+	wrmsrq(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0));
 
-	wrmsrl(MSR_IA32_FRED_RSP1, 0);
-	wrmsrl(MSR_IA32_FRED_RSP2, 0);
-	wrmsrl(MSR_IA32_FRED_RSP3, 0);
+	wrmsrq(MSR_IA32_FRED_RSP1, 0);
+	wrmsrq(MSR_IA32_FRED_RSP2, 0);
+	wrmsrq(MSR_IA32_FRED_RSP3, 0);
 
 	/* Enable FRED */
 	cr4_set_bits(X86_CR4_FRED);
@@ -79,14 +80,14 @@ void cpu_init_fred_rsps(void)
 	 * (remember that user space faults are always taken on stack level 0)
 	 * is to avoid overflowing the kernel stack.
 	 */
-	wrmsrl(MSR_IA32_FRED_STKLVLS,
+	wrmsrq(MSR_IA32_FRED_STKLVLS,
 	       FRED_STKLVL(X86_TRAP_DB,  FRED_DB_STACK_LEVEL) |
 	       FRED_STKLVL(X86_TRAP_NMI, FRED_NMI_STACK_LEVEL) |
 	       FRED_STKLVL(X86_TRAP_MC,  FRED_MC_STACK_LEVEL) |
 	       FRED_STKLVL(X86_TRAP_DF,  FRED_DF_STACK_LEVEL));
 
 	/* The FRED equivalents to IST stacks... */
-	wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
-	wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
-	wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
+	wrmsrq(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
+	wrmsrq(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
+	wrmsrq(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 166bc0ea3bdf..252e82bcfd2f 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -55,10 +55,10 @@ void ftrace_arch_code_modify_post_process(void)
 {
 	/*
 	 * ftrace_make_{call,nop}() may be called during
-	 * module load, and we need to finish the text_poke_queue()
+	 * module load, and we need to finish the smp_text_poke_batch_add()
 	 * that they do, here.
 	 */
-	text_poke_finish();
+	smp_text_poke_batch_finish();
 	ftrace_poke_late = 0;
 	mutex_unlock(&text_mutex);
 }
@@ -118,13 +118,10 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
 		return ret;
 
 	/* replace the text with the new text */
-	if (ftrace_poke_late) {
-		text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
-	} else {
-		mutex_lock(&text_mutex);
-		text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
-		mutex_unlock(&text_mutex);
-	}
+	if (ftrace_poke_late)
+		smp_text_poke_batch_add((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
+	else
+		text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
@@ -189,11 +186,11 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 	ip = (unsigned long)(&ftrace_call);
 	new = ftrace_call_replace(ip, (unsigned long)func);
-	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 
 	ip = (unsigned long)(&ftrace_regs_call);
 	new = ftrace_call_replace(ip, (unsigned long)func);
-	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 
 	return 0;
 }
@@ -250,10 +247,10 @@ void ftrace_replace_code(int enable)
 			break;
 		}
 
-		text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
+		smp_text_poke_batch_add((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
 		ftrace_update_record(rec, enable);
 	}
-	text_poke_finish();
+	smp_text_poke_batch_finish();
 }
 
 void arch_ftrace_update_code(int command)
@@ -321,7 +318,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
 	union ftrace_op_code_union op_ptr;
-	void *ret;
+	int ret;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		start_offset = (unsigned long)ftrace_regs_caller;
@@ -352,15 +349,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = text_poke_copy(trampoline, (void *)start_offset, size);
-	if (WARN_ON(!ret))
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0))
 		goto fail;
 
 	ip = trampoline + size;
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk_at(ip))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
-		text_poke_copy(ip, retq, sizeof(retq));
+		memcpy(ip, retq, sizeof(retq));
 
 	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -368,7 +365,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		ip = trampoline + (jmp_offset - start_offset);
 		if (WARN_ON(*(char *)ip != 0x75))
 			goto fail;
-		if (!text_poke_copy(ip, x86_nops[2], 2))
+		ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
+		if (ret < 0)
 			goto fail;
 	}
 
@@ -381,7 +379,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 */
 
 	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
-	text_poke_copy(ptr, &ops, sizeof(unsigned long));
+	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -397,7 +395,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	op_ptr.offset = offset;
 
 	/* put in the new offset to the ftrace_ops */
-	text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
 
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
@@ -407,9 +405,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the depth accounting before the call already.
 	 */
 	dest = ftrace_ops_get_func(ops);
-	text_poke_copy_locked(trampoline + call_offset,
-	      text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
-	      CALL_INSN_SIZE, false);
+	memcpy(trampoline + call_offset,
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
@@ -494,7 +492,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 	mutex_lock(&text_mutex);
 	/* Do a safe modify in case the trampoline is executing */
 	new = ftrace_call_replace(ip, (unsigned long)func);
-	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 	mutex_unlock(&text_mutex);
 }
 
@@ -588,7 +586,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func)
 	const char *new;
 
 	new = ftrace_jmp_replace(ip, (unsigned long)func);
-	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+	smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index d51647228596..367da3638167 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -146,12 +146,14 @@ SYM_FUNC_END(ftrace_stub_graph)
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
 SYM_FUNC_START(ftrace_caller)
+	ANNOTATE_NOENDBR
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
@@ -197,6 +199,7 @@ SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
 SYM_FUNC_START(ftrace_regs_caller)
+	ANNOTATE_NOENDBR
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
@@ -310,6 +313,7 @@ SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 
 SYM_FUNC_START(ftrace_stub_direct_tramp)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub_direct_tramp)
@@ -317,6 +321,7 @@ SYM_FUNC_END(ftrace_stub_direct_tramp)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 
 	cmpq $ftrace_stub, ftrace_trace_function
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index de001b2146ab..375f2d7f1762 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void)
 	*ptr = (unsigned long)ptep + PAGE_OFFSET;
 
 #ifdef CONFIG_MICROCODE_INITRD32
-	/* Running on a hypervisor? */
-	if (native_cpuid_ecx(1) & BIT(31))
-		return;
-
 	params = (struct boot_params *)__pa_nodebug(&boot_params);
 	if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image)
 		return;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 22c9ba305ac1..533fcf5636fc 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -5,8 +5,6 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
-#define DISABLE_BRANCH_PROFILING
-
 /* cpu_feature_enabled() cannot be used this early */
 #define USE_EARLY_PGTABLE_L5
 
@@ -49,234 +47,22 @@
  * Manage page tables very early on.
  */
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
-static unsigned int __initdata next_early_pgt;
+unsigned int __initdata next_early_pgt;
+SYM_PIC_ALIAS(next_early_pgt);
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
-#ifdef CONFIG_X86_5LEVEL
 unsigned int __pgtable_l5_enabled __ro_after_init;
 unsigned int pgdir_shift __ro_after_init = 39;
 EXPORT_SYMBOL(pgdir_shift);
 unsigned int ptrs_per_p4d __ro_after_init = 1;
 EXPORT_SYMBOL(ptrs_per_p4d);
-#endif
 
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4;
 EXPORT_SYMBOL(page_offset_base);
 unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4;
 EXPORT_SYMBOL(vmalloc_base);
 unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
 EXPORT_SYMBOL(vmemmap_base);
-#endif
-
-static inline bool check_la57_support(void)
-{
-	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
-		return false;
-
-	/*
-	 * 5-level paging is detected and enabled at kernel decompression
-	 * stage. Only check if it has been enabled there.
-	 */
-	if (!(native_read_cr4() & X86_CR4_LA57))
-		return false;
-
-	RIP_REL_REF(__pgtable_l5_enabled)	= 1;
-	RIP_REL_REF(pgdir_shift)		= 48;
-	RIP_REL_REF(ptrs_per_p4d)		= 512;
-	RIP_REL_REF(page_offset_base)		= __PAGE_OFFSET_BASE_L5;
-	RIP_REL_REF(vmalloc_base)		= __VMALLOC_BASE_L5;
-	RIP_REL_REF(vmemmap_base)		= __VMEMMAP_BASE_L5;
-
-	return true;
-}
-
-static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
-						    pmdval_t *pmd,
-						    unsigned long p2v_offset)
-{
-	unsigned long paddr, paddr_end;
-	int i;
-
-	/* Encrypt the kernel and related (if SME is active) */
-	sme_encrypt_kernel(bp);
-
-	/*
-	 * Clear the memory encryption mask from the .bss..decrypted section.
-	 * The bss section will be memset to zero later in the initialization so
-	 * there is no need to zero it after changing the memory encryption
-	 * attribute.
-	 */
-	if (sme_get_me_mask()) {
-		paddr = (unsigned long)&RIP_REL_REF(__start_bss_decrypted);
-		paddr_end = (unsigned long)&RIP_REL_REF(__end_bss_decrypted);
-
-		for (; paddr < paddr_end; paddr += PMD_SIZE) {
-			/*
-			 * On SNP, transition the page to shared in the RMP table so that
-			 * it is consistent with the page table attribute change.
-			 *
-			 * __start_bss_decrypted has a virtual address in the high range
-			 * mapping (kernel .text). PVALIDATE, by way of
-			 * early_snp_set_memory_shared(), requires a valid virtual
-			 * address but the kernel is currently running off of the identity
-			 * mapping so use the PA to get a *currently* valid virtual address.
-			 */
-			early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
-
-			i = pmd_index(paddr - p2v_offset);
-			pmd[i] -= sme_get_me_mask();
-		}
-	}
-
-	/*
-	 * Return the SME encryption mask (if SME is active) to be used as a
-	 * modifier for the initial pgdir entry programmed into CR3.
-	 */
-	return sme_get_me_mask();
-}
-
-/* Code in __startup_64() can be relocated during execution, but the compiler
- * doesn't have to generate PC-relative relocations when accessing globals from
- * that function. Clang actually does not generate them, which leads to
- * boot-time crashes. To work around this problem, every global pointer must
- * be accessed using RIP_REL_REF(). Kernel virtual addresses can be determined
- * by subtracting p2v_offset from the RIP-relative address.
- */
-unsigned long __head __startup_64(unsigned long p2v_offset,
-				  struct boot_params *bp)
-{
-	pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
-	unsigned long physaddr = (unsigned long)&RIP_REL_REF(_text);
-	unsigned long va_text, va_end;
-	unsigned long pgtable_flags;
-	unsigned long load_delta;
-	pgdval_t *pgd;
-	p4dval_t *p4d;
-	pudval_t *pud;
-	pmdval_t *pmd, pmd_entry;
-	bool la57;
-	int i;
-
-	la57 = check_la57_support();
-
-	/* Is the address too large? */
-	if (physaddr >> MAX_PHYSMEM_BITS)
-		for (;;);
-
-	/*
-	 * Compute the delta between the address I am compiled to run at
-	 * and the address I am actually running at.
-	 */
-	load_delta = __START_KERNEL_map + p2v_offset;
-	RIP_REL_REF(phys_base) = load_delta;
-
-	/* Is the address not 2M aligned? */
-	if (load_delta & ~PMD_MASK)
-		for (;;);
-
-	va_text = physaddr - p2v_offset;
-	va_end  = (unsigned long)&RIP_REL_REF(_end) - p2v_offset;
-
-	/* Include the SME encryption mask in the fixup value */
-	load_delta += sme_get_me_mask();
-
-	/* Fixup the physical addresses in the page table */
-
-	pgd = &RIP_REL_REF(early_top_pgt)->pgd;
-	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
-
-	if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) {
-		p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
-		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
-
-		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
-	}
-
-	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
-	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta;
-
-	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
-		RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta;
-
-	/*
-	 * Set up the identity mapping for the switchover.  These
-	 * entries should *NOT* have the global bit set!  This also
-	 * creates a bunch of nonsense entries but that is fine --
-	 * it avoids problems around wraparound.
-	 */
-
-	pud = &early_pgts[0]->pmd;
-	pmd = &early_pgts[1]->pmd;
-	RIP_REL_REF(next_early_pgt) = 2;
-
-	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
-
-	if (la57) {
-		p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd;
-
-		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
-		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
-
-		i = physaddr >> P4D_SHIFT;
-		p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
-		p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
-	} else {
-		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
-		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
-	}
-
-	i = physaddr >> PUD_SHIFT;
-	pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
-	pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
-
-	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
-	/* Filter out unsupported __PAGE_KERNEL_* bits: */
-	pmd_entry &= RIP_REL_REF(__supported_pte_mask);
-	pmd_entry += sme_get_me_mask();
-	pmd_entry +=  physaddr;
-
-	for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
-		int idx = i + (physaddr >> PMD_SHIFT);
-
-		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
-	}
-
-	/*
-	 * Fixup the kernel text+data virtual addresses. Note that
-	 * we might write invalid pmds, when the kernel is relocated
-	 * cleanup_highmap() fixes this up along with the mappings
-	 * beyond _end.
-	 *
-	 * Only the region occupied by the kernel image has so far
-	 * been checked against the table of usable memory regions
-	 * provided by the firmware, so invalidate pages outside that
-	 * region. A page table entry that maps to a reserved area of
-	 * memory would allow processor speculation into that area,
-	 * and on some hardware (particularly the UV platform) even
-	 * speculative access to some reserved areas is caught as an
-	 * error, causing the BIOS to halt the system.
-	 */
-
-	pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd;
-
-	/* invalidate pages before the kernel image */
-	for (i = 0; i < pmd_index(va_text); i++)
-		pmd[i] &= ~_PAGE_PRESENT;
-
-	/* fixup pages that are part of the kernel image */
-	for (; i <= pmd_index(va_end); i++)
-		if (pmd[i] & _PAGE_PRESENT)
-			pmd[i] += load_delta;
-
-	/* invalidate pages after the kernel image */
-	for (; i < PTRS_PER_PMD; i++)
-		pmd[i] &= ~_PAGE_PRESENT;
-
-	return sme_postprocess_startup(bp, pmd, p2v_offset);
-}
 
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
@@ -451,6 +237,12 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
+	if (pgtable_l5_enabled()) {
+		page_offset_base	= __PAGE_OFFSET_BASE_L5;
+		vmalloc_base		= __VMALLOC_BASE_L5;
+		vmemmap_base		= __VMEMMAP_BASE_L5;
+	}
+
 	clear_bss();
 
 	/*
@@ -515,41 +307,6 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data)
 	start_kernel();
 }
 
-/*
- * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
- * used until the idt_table takes over. On the boot CPU this happens in
- * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
- * this happens in the functions called from head_64.S.
- *
- * The idt_table can't be used that early because all the code modifying it is
- * in idt.c and can be instrumented by tracing or KASAN, which both don't work
- * during early CPU bringup. Also the idt_table has the runtime vectors
- * configured which require certain CPU state to be setup already (like TSS),
- * which also hasn't happened yet in early CPU bringup.
- */
-static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
-
-/* This may run while still in the direct mapping */
-static void __head startup_64_load_idt(void *vc_handler)
-{
-	struct desc_ptr desc = {
-		.address = (unsigned long)&RIP_REL_REF(bringup_idt_table),
-		.size    = sizeof(bringup_idt_table) - 1,
-	};
-	struct idt_data data;
-	gate_desc idt_desc;
-
-	/* @vc_handler is set only for a VMM Communication Exception */
-	if (vc_handler) {
-		init_idt_data(&data, X86_TRAP_VC, vc_handler);
-		idt_init_desc(&idt_desc, &data);
-		native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
-	}
-
-	native_load_idt(&desc);
-}
-
-/* This is used when running on kernel addresses */
 void early_setup_idt(void)
 {
 	void *handler = NULL;
@@ -561,30 +318,3 @@ void early_setup_idt(void)
 
 	startup_64_load_idt(handler);
 }
-
-/*
- * Setup boot CPU state needed before kernel switches to virtual addresses.
- */
-void __head startup_64_setup_gdt_idt(void)
-{
-	struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
-	void *handler = NULL;
-
-	struct desc_ptr startup_gdt_descr = {
-		.address = (unsigned long)&RIP_REL_REF(*gdt),
-		.size    = GDT_SIZE - 1,
-	};
-
-	/* Load GDT */
-	native_load_gdt(&startup_gdt_descr);
-
-	/* New GDT is live - reload data segment registers */
-	asm volatile("movl %%eax, %%ds\n"
-		     "movl %%eax, %%ss\n"
-		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
-		handler = &RIP_REL_REF(vc_no_ghcb);
-
-	startup_64_load_idt(handler);
-}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 2e42056d2306..76743dfad6ab 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -86,7 +86,7 @@ SYM_CODE_START(startup_32)
 	movl $pa(__bss_stop),%ecx
 	subl %edi,%ecx
 	shrl $2,%ecx
-	rep ; stosl
+	rep stosl
 /*
  * Copy bootup parameters out of the way.
  * Note: %esi still has the pointer to the real-mode data.
@@ -98,15 +98,13 @@ SYM_CODE_START(startup_32)
 	movl $pa(boot_params),%edi
 	movl $(PARAM_SIZE/4),%ecx
 	cld
-	rep
-	movsl
+	rep movsl
 	movl pa(boot_params) + NEW_CL_POINTER,%esi
 	andl %esi,%esi
 	jz 1f			# No command line
 	movl $pa(boot_command_line),%edi
 	movl $(COMMAND_LINE_SIZE/4),%ecx
-	rep
-	movsl
+	rep movsl
 1:
 
 #ifdef CONFIG_OLPC
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 31345e0ba006..3e9b3a3bd039 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -61,11 +61,14 @@ SYM_CODE_START_NOALIGN(startup_64)
 	/* Set up the stack for verify_cpu() */
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Setup GSBASE to allow stack canary access for C code */
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
 	movl	$MSR_GS_BASE, %ecx
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movl	%edx, %eax
-	shrq	$32,  %rdx
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	call	startup_64_setup_gdt_idt
@@ -319,7 +322,7 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	 *
 	 * RDX contains the per-cpu offset
 	 */
-	movq	pcpu_hot + X86_current_task(%rdx), %rax
+	movq	current_task(%rdx), %rax
 	movq	TASK_threadsp(%rax), %rsp
 
 	/*
@@ -359,17 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data. If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
 	movl	%edx, %eax
 	shrq	$32, %rdx
 	wrmsr
@@ -435,7 +433,7 @@ SYM_CODE_START(soft_restart_cpu)
 	UNWIND_HINT_END_OF_STACK
 
 	/* Find the idle task stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
+	movq	PER_CPU_VAR(current_task), %rcx
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
@@ -575,6 +573,7 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb)
 	/* Pure iret required here - don't use INTERRUPT_RETURN */
 	iretq
 SYM_CODE_END(vc_no_ghcb)
+SYM_PIC_ALIAS(vc_no_ghcb);
 #endif
 
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
@@ -606,10 +605,12 @@ SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	.fill	PTI_USER_PGD_FILL,8,0
 SYM_DATA_END(early_top_pgt)
+SYM_PIC_ALIAS(early_top_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
 SYM_DATA_END(early_dynamic_pgts)
+SYM_PIC_ALIAS(early_dynamic_pgts);
 
 SYM_DATA(early_recursion_flag, .long 0)
 
@@ -648,12 +649,11 @@ SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
 SYM_DATA_END(init_top_pgt)
 #endif
 
-#ifdef CONFIG_X86_5LEVEL
 SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 SYM_DATA_END(level4_kernel_pgt)
-#endif
+SYM_PIC_ALIAS(level4_kernel_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
@@ -661,6 +661,7 @@ SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
 	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 SYM_DATA_END(level3_kernel_pgt)
+SYM_PIC_ALIAS(level3_kernel_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
 	/*
@@ -678,6 +679,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE)
 SYM_DATA_END(level2_kernel_pgt)
+SYM_PIC_ALIAS(level2_kernel_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
 	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
@@ -690,6 +692,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
 	/* 6 MB reserved space + a 2MB hole */
 	.fill	4,8,0
 SYM_DATA_END(level2_fixmap_pgt)
+SYM_PIC_ALIAS(level2_fixmap_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
 	.rept (FIXMAP_PMD_NUM)
@@ -705,6 +708,7 @@ SYM_DATA(smpboot_control,		.long 0)
 	.align 16
 /* This must match the first entry in level2_kernel_pgt */
 SYM_DATA(phys_base, .quad 0x0)
+SYM_PIC_ALIAS(phys_base);
 EXPORT_SYMBOL(phys_base)
 
 #include "../xen/xen-head.S"
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7f4b2966e15c..d6387dde3ff9 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -7,11 +7,12 @@
 #include <linux/cpu.h>
 #include <linux/irq.h>
 
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
 #include <asm/mwait.h>
+#include <asm/msr.h>
 
 #undef  pr_fmt
 #define pr_fmt(fmt) "hpet: " fmt
@@ -970,7 +971,7 @@ static bool __init hpet_is_pc10_damaged(void)
 		return false;
 
 	/* Check whether PC10 is enabled in PKG C-state limit */
-	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+	rdmsrq(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
 	if ((pcfg & 0xF) < 8)
 		return false;
 
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 80e262bb627f..cb9852ad6098 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -46,7 +46,8 @@ bool __init pit_timer_init(void)
 		 * VMMs otherwise steal CPU time just to pointlessly waggle
 		 * the (masked) IRQ.
 		 */
-		clockevent_i8253_disable();
+		scoped_guard(irq)
+			clockevent_i8253_disable();
 		return false;
 	}
 	clockevent_i8253_init(true);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index c20d1832c481..2bade73f49e3 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -23,6 +23,7 @@
 #include <asm/desc.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
+#include <asm/io_apic.h>
 
 /*
  * This is the 'legacy' 8259A Programmable Interrupt Controller,
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index e2fab3ceb09f..6290dd120f5e 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -144,7 +144,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * Update the sequence number to force a TSS update on return to
 	 * user mode.
 	 */
-	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
+	iobm->sequence = atomic64_inc_return(&io_bitmap_sequence);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc304..81f9b78e0f7b 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,12 +25,19 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
+DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+EXPORT_PER_CPU_SYMBOL(__softirq_pending);
+
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
+
 atomic_t irq_err_count;
 
 /*
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index dc1049c01f9b..c7a5d2960d57 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -29,12 +29,9 @@
 int sysctl_panic_on_stackoverflow __read_mostly;
 
 /* Debugging check for stack overflow: is there less than 1KB free? */
-static int check_stack_overflow(void)
+static bool check_stack_overflow(void)
 {
-	long sp;
-
-	__asm__ __volatile__("andl %%esp,%0" :
-			     "=r" (sp) : "0" (THREAD_SIZE - 1));
+	unsigned long sp = current_stack_pointer & (THREAD_SIZE - 1);
 
 	return sp < (sizeof(struct thread_info) + STACK_WARN);
 }
@@ -48,18 +45,19 @@ static void print_stack_overflow(void)
 }
 
 #else
-static inline int check_stack_overflow(void) { return 0; }
+static inline bool check_stack_overflow(void) { return false; }
 static inline void print_stack_overflow(void) { }
 #endif
 
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+
 static void call_on_stack(void *func, void *stack)
 {
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=b" (stack)
-		     : "0" (stack),
-		       [thunk_target] "D"(func)
+		     "movl %[sp], %%esp"
+		     : [sp] "+b" (stack)
+		     : [thunk_target] "D" (func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
@@ -68,13 +66,13 @@ static inline void *current_stack(void)
 	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
-static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
+static inline bool execute_on_irq_stack(bool overflow, struct irq_desc *desc)
 {
 	struct irq_stack *curstk, *irqstk;
-	u32 *isp, *prev_esp, arg1;
+	u32 *isp, *prev_esp;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -83,7 +81,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	 * current stack (which is the irq stack already after all)
 	 */
 	if (unlikely(curstk == irqstk))
-		return 0;
+		return false;
 
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
@@ -94,14 +92,13 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
 
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=a" (arg1), "=b" (isp)
-		     :  "0" (desc),   "1" (isp),
-			[thunk_target] "D" (desc->handle_irq)
-		     : "memory", "cc", "ecx");
-	return 1;
+		     "movl %[sp], %%esp"
+		     : "+a" (desc), [sp] "+b" (isp)
+		     : [thunk_target] "D" (desc->handle_irq)
+		     : "memory", "cc", "edx", "ecx");
+	return true;
 }
 
 /*
@@ -112,7 +109,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	struct page *ph, *ps;
 
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 
 	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
@@ -124,8 +121,8 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 		return -ENOMEM;
 	}
 
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph);
-	per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps);
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
 	return 0;
 }
 
@@ -135,7 +132,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
@@ -150,7 +147,7 @@ void do_softirq_own_stack(void)
 
 void __handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	int overflow = check_stack_overflow();
+	bool overflow = check_stack_overflow();
 
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
 		if (unlikely(overflow))
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ade0043ce56e..ca78dce39361 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,8 +26,8 @@
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
+DEFINE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
 DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_VMAP_STACK
 /*
@@ -51,7 +51,7 @@ static int map_irq_stack(unsigned int cpu)
 		return -ENOMEM;
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -64,14 +64,14 @@ static int map_irq_stack(unsigned int cpu)
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif
 
 int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 	return map_irq_stack(cpu);
 }
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 7f542a7799cb..fdabd5dda154 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -9,6 +9,7 @@
  */
 .pushsection .noinstr.text, "ax"
 SYM_FUNC_START(native_save_fl)
+	ENDBR
 	pushf
 	pop %_ASM_AX
 	RET
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index cd8ed1edbf9e..9e9a591a5fec 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -49,7 +49,7 @@ static uint32_t jailhouse_cpuid_base(void)
 	    !boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return 0;
 
-	return hypervisor_cpuid_base("Jailhouse\0\0\0", 0);
+	return cpuid_base_hypervisor("Jailhouse\0\0\0", 0);
 }
 
 static uint32_t __init jailhouse_detect(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index f5b8ef02d172..a7949a54a0ff 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -102,7 +102,7 @@ __jump_label_transform(struct jump_entry *entry,
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
+	smp_text_poke_single((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
 }
 
 static void __ref jump_label_transform(struct jump_entry *entry,
@@ -135,7 +135,7 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 
 	mutex_lock(&text_mutex);
 	jlp = __jump_label_patch(entry, type);
-	text_poke_queue((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
+	smp_text_poke_batch_add((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
 	mutex_unlock(&text_mutex);
 	return true;
 }
@@ -143,6 +143,6 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 void arch_jump_label_transform_apply(void)
 {
 	mutex_lock(&text_mutex);
-	text_poke_finish();
+	smp_text_poke_batch_finish();
 	mutex_unlock(&text_mutex);
 }
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 9c9faa1634fb..102641fd2172 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -655,7 +655,7 @@ void kgdb_arch_late(void)
 		if (breakinfo[i].pev)
 			continue;
 		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL);
-		if (IS_ERR((void * __force)breakinfo[i].pev)) {
+		if (IS_ERR_PCPU(breakinfo[i].pev)) {
 			printk(KERN_ERR "kgdb: Could not allocate hw"
 			       "breakpoints\nDisabling the kernel debugger\n");
 			breakinfo[i].pev = NULL;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 72e6a45e7ec2..47cb8eb138ba 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -373,16 +373,7 @@ out:
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	u32 insn;
-
-	/*
-	 * Since 'addr' is not guaranteed to be safe to access, use
-	 * copy_from_kernel_nofault() to read the instruction:
-	 */
-	if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
-		return NULL;
-
-	if (is_endbr(insn)) {
+	if (is_endbr((u32 *)addr)) {
 		*on_func_entry = !offset || offset == 4;
 		if (*on_func_entry)
 			offset = 4;
@@ -817,7 +808,7 @@ void arch_arm_kprobe(struct kprobe *p)
 	u8 int3 = INT3_INSN_OPCODE;
 
 	text_poke(p->addr, &int3, 1);
-	text_poke_sync();
+	smp_text_poke_sync_each_cpu();
 	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
@@ -827,7 +818,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 
 	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
-	text_poke_sync();
+	smp_text_poke_sync_each_cpu();
 }
 
 void arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 36d6809c6c9e..0aabd4c4e2c4 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -488,7 +488,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
 		insn_buff[0] = JMP32_INSN_OPCODE;
 		*(s32 *)(&insn_buff[1]) = rel;
 
-		text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
+		smp_text_poke_single(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
 
 		list_del_init(&op->list);
 	}
@@ -513,11 +513,11 @@ void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
 
 	text_poke(addr, new, INT3_INSN_SIZE);
-	text_poke_sync();
+	smp_text_poke_sync_each_cpu();
 	text_poke(addr + INT3_INSN_SIZE,
 		  new + INT3_INSN_SIZE,
 		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
-	text_poke_sync();
+	smp_text_poke_sync_each_cpu();
 
 	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7a422a6c5983..921c1c783bc1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -40,6 +40,7 @@
 #include <asm/mtrr.h>
 #include <asm/tlb.h>
 #include <asm/cpuidle_haltpoll.h>
+#include <asm/msr.h>
 #include <asm/ptrace.h>
 #include <asm/reboot.h>
 #include <asm/svm.h>
@@ -301,7 +302,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 		token = __this_cpu_read(apf_reason.token);
 		kvm_async_pf_task_wake(token);
 		__this_cpu_write(apf_reason.token, 0);
-		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
+		wrmsrq(MSR_KVM_ASYNC_PF_ACK, 1);
 	}
 
 	set_irq_regs(old_regs);
@@ -327,7 +328,7 @@ static void kvm_register_steal_time(void)
 	if (!has_steal_clock)
 		return;
 
-	wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
+	wrmsrq(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
 	pr_debug("stealtime: cpu %d, msr %llx\n", cpu,
 		(unsigned long long) slow_virt_to_phys(st));
 }
@@ -361,9 +362,9 @@ static void kvm_guest_cpu_init(void)
 		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
 			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 
-		wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
+		wrmsrq(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
 
-		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+		wrmsrq(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(async_pf_enabled, true);
 		pr_debug("setup async PF for cpu %d\n", smp_processor_id());
 	}
@@ -376,7 +377,7 @@ static void kvm_guest_cpu_init(void)
 		__this_cpu_write(kvm_apic_eoi, 0);
 		pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
 			| KVM_MSR_ENABLED;
-		wrmsrl(MSR_KVM_PV_EOI_EN, pa);
+		wrmsrq(MSR_KVM_PV_EOI_EN, pa);
 	}
 
 	if (has_steal_clock)
@@ -388,7 +389,7 @@ static void kvm_pv_disable_apf(void)
 	if (!__this_cpu_read(async_pf_enabled))
 		return;
 
-	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
+	wrmsrq(MSR_KVM_ASYNC_PF_EN, 0);
 	__this_cpu_write(async_pf_enabled, false);
 
 	pr_debug("disable async PF for cpu %d\n", smp_processor_id());
@@ -399,7 +400,7 @@ static void kvm_disable_steal_time(void)
 	if (!has_steal_clock)
 		return;
 
-	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+	wrmsrq(MSR_KVM_STEAL_TIME, 0);
 }
 
 static u64 kvm_steal_clock(int cpu)
@@ -451,9 +452,9 @@ static void kvm_guest_cpu_offline(bool shutdown)
 {
 	kvm_disable_steal_time();
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
-		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+		wrmsrq(MSR_KVM_PV_EOI_EN, 0);
 	if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
-		wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0);
+		wrmsrq(MSR_KVM_MIGRATION_CONTROL, 0);
 	kvm_pv_disable_apf();
 	if (!shutdown)
 		apf_task_wake_all();
@@ -615,7 +616,7 @@ static int __init setup_efi_kvm_sev_migration(void)
 	}
 
 	pr_info("%s : live migration enabled in EFI\n", __func__);
-	wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
+	wrmsrq(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
 
 	return 1;
 }
@@ -728,7 +729,7 @@ static int kvm_suspend(void)
 
 #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
 	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
-		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+		rdmsrq(MSR_KVM_POLL_CONTROL, val);
 	has_guest_poll = !(val & 1);
 #endif
 	return 0;
@@ -740,7 +741,7 @@ static void kvm_resume(void)
 
 #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
 	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
-		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+		wrmsrq(MSR_KVM_POLL_CONTROL, 0);
 #endif
 }
 
@@ -838,7 +839,6 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	if (pv_tlb_flush_supported()) {
 		pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
-		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
 
@@ -875,7 +875,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
 		return 0;	/* So we don't blow up on old processors */
 
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return hypervisor_cpuid_base(KVM_SIGNATURE, 0);
+		return cpuid_base_hypervisor(KVM_SIGNATURE, 0);
 
 	return 0;
 }
@@ -976,7 +976,7 @@ static void __init kvm_init_platform(void)
 		 * If not booted using EFI, enable Live migration support.
 		 */
 		if (!efi_enabled(EFI_BOOT))
-			wrmsrl(MSR_KVM_MIGRATION_CONTROL,
+			wrmsrq(MSR_KVM_MIGRATION_CONTROL,
 			       KVM_MIGRATION_READY);
 	}
 	kvmclock_init();
@@ -1125,12 +1125,12 @@ out:
 
 static void kvm_disable_host_haltpoll(void *i)
 {
-	wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+	wrmsrq(MSR_KVM_POLL_CONTROL, 0);
 }
 
 static void kvm_enable_host_haltpoll(void *i)
 {
-	wrmsrl(MSR_KVM_POLL_CONTROL, 1);
+	wrmsrq(MSR_KVM_POLL_CONTROL, 1);
 }
 
 void arch_haltpoll_enable(unsigned int cpu)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 5b2c15214a6b..ca0a49eeac4a 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -60,7 +60,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
  */
 static void kvm_get_wallclock(struct timespec64 *now)
 {
-	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+	wrmsrq(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
 	preempt_disable();
 	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
 	preempt_enable();
@@ -173,7 +173,7 @@ static void kvm_register_clock(char *txt)
 		return;
 
 	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
-	wrmsrl(msr_kvm_system_time, pa);
+	wrmsrq(msr_kvm_system_time, pa);
 	pr_debug("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
 }
 
@@ -196,7 +196,7 @@ static void kvm_setup_secondary_clock(void)
 void kvmclock_disable(void)
 {
 	if (msr_kvm_system_time)
-		native_write_msr(msr_kvm_system_time, 0, 0);
+		native_write_msr(msr_kvm_system_time, 0);
 }
 
 static void __init kvmclock_init_mem(void)
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 80265162aeff..1f325304c4a8 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
 	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						    PGD_ALLOCATION_ORDER);
+						    pgd_allocation_order());
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a68f5a0a9f37..949c9e4bfad2 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -76,6 +76,19 @@ map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
 static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
 #endif
 
+static int map_mmio_serial(struct x86_mapping_info *info, pgd_t *level4p)
+{
+	unsigned long mstart, mend;
+
+	if (!kexec_debug_8250_mmio32)
+		return 0;
+
+	mstart = kexec_debug_8250_mmio32 & PAGE_MASK;
+	mend = (kexec_debug_8250_mmio32 + PAGE_SIZE + 23) & PAGE_MASK;
+	pr_info("Map PCI serial at %lx - %lx\n", mstart, mend);
+	return kernel_ident_mapping_init(info, level4p, mstart, mend);
+}
+
 #ifdef CONFIG_KEXEC_FILE
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 		&kexec_bzImage64_ops,
@@ -285,6 +298,10 @@ static int init_pgtable(struct kimage *image, unsigned long control_page)
 	if (result)
 		return result;
 
+	result = map_mmio_serial(&info, image->arch.pgd);
+	if (result)
+		return result;
+
 	/*
 	 * This must be last because the intermediate page table pages it
 	 * allocates will not be control pages and may overlap the image.
@@ -304,6 +321,24 @@ static void load_segments(void)
 		);
 }
 
+static void prepare_debug_idt(unsigned long control_page, unsigned long vec_ofs)
+{
+	gate_desc idtentry = { 0 };
+	int i;
+
+	idtentry.bits.p		= 1;
+	idtentry.bits.type	= GATE_TRAP;
+	idtentry.segment	= __KERNEL_CS;
+	idtentry.offset_low	= (control_page & 0xFFFF) + vec_ofs;
+	idtentry.offset_middle	= (control_page >> 16) & 0xFFFF;
+	idtentry.offset_high	= control_page >> 32;
+
+	for (i = 0; i < 16; i++) {
+		kexec_debug_idt[i] = idtentry;
+		idtentry.offset_low += KEXEC_DEBUG_EXC_HANDLER_SIZE;
+	}
+}
+
 int machine_kexec_prepare(struct kimage *image)
 {
 	void *control_page = page_address(image->control_code_page);
@@ -321,6 +356,9 @@ int machine_kexec_prepare(struct kimage *image)
 	if (image->type == KEXEC_TYPE_DEFAULT)
 		kexec_pa_swap_page = page_to_pfn(image->swap_page) << PAGE_SHIFT;
 
+	prepare_debug_idt((unsigned long)__pa(control_page),
+			  (unsigned long)kexec_debug_exc_vectors - reloc_start);
+
 	__memcpy(control_page, __relocate_kernel_start, reloc_end - reloc_start);
 
 	set_memory_rox((unsigned long)control_page, 1);
@@ -396,16 +434,10 @@ void __nocfi machine_kexec(struct kimage *image)
 	 * with from a table in memory.  At no other time is the
 	 * descriptor table in memory accessed.
 	 *
-	 * I take advantage of this here by force loading the
-	 * segments, before I zap the gdt with an invalid value.
+	 * Take advantage of this here by force loading the segments,
+	 * before the GDT is zapped with an invalid value.
 	 */
 	load_segments();
-	/*
-	 * The gdt & idt are now invalid.
-	 * If you want to load them you must set up your own idt & gdt.
-	 */
-	native_idt_invalidate();
-	native_gdt_invalidate();
 
 	/* now call it */
 	image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 1f54eedc3015..ef6104e7cc72 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -97,7 +97,7 @@ static void get_fam10h_pci_mmconf_base(void)
 
 	/* SYS_CFG */
 	address = MSR_AMD64_SYSCFG;
-	rdmsrl(address, val);
+	rdmsrq(address, val);
 
 	/* TOP_MEM2 is not enabled? */
 	if (!(val & (1<<21))) {
@@ -105,7 +105,7 @@ static void get_fam10h_pci_mmconf_base(void)
 	} else {
 		/* TOP_MEM2 */
 		address = MSR_K8_TOP_MEM2;
-		rdmsrl(address, val);
+		rdmsrq(address, val);
 		tom2 = max(val & 0xffffff800000ULL, 1ULL << 32);
 	}
 
@@ -177,7 +177,7 @@ void fam10h_check_enable_mmcfg(void)
 		return;
 
 	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, val);
+	rdmsrq(address, val);
 
 	/* try to make sure that AP's setting is identical to BSP setting */
 	if (val & FAM10H_MMIO_CONF_ENABLE) {
@@ -212,7 +212,7 @@ void fam10h_check_enable_mmcfg(void)
 	     (FAM10H_MMIO_CONF_BUSRANGE_MASK<<FAM10H_MMIO_CONF_BUSRANGE_SHIFT));
 	val |= fam10h_pci_mmconf_base | (8 << FAM10H_MMIO_CONF_BUSRANGE_SHIFT) |
 	       FAM10H_MMIO_CONF_ENABLE;
-	wrmsrl(address, val);
+	wrmsrq(address, val);
 }
 
 static int __init set_check_enable_amd_mmconf(const struct dmi_system_id *d)
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c00..0ffbae902e2f 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 #include <linux/memory.h>
+#include <linux/stackprotector.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -130,6 +131,20 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 				goto overflow;
 			size = 4;
 			break;
+#if defined(CONFIG_STACKPROTECTOR) && \
+    defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+		case R_X86_64_REX_GOTPCRELX: {
+			static unsigned long __percpu *const addr = &__stack_chk_guard;
+
+			if (sym->st_value != (u64)addr) {
+				pr_err("%s: Unsupported GOTPCREL relocation\n", me->name);
+				return -ENOEXEC;
+			}
+
+			val = (u64)&addr + rel[i].r_addend;
+			fallthrough;
+		}
+#endif
 		case R_X86_64_PC32:
 		case R_X86_64_PLT32:
 			val -= (u64)loc;
@@ -146,21 +161,18 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 		}
 
 		if (apply) {
-			void *wr_loc = module_writable_address(me, loc);
-
-			if (memcmp(wr_loc, &zero, size)) {
+			if (memcmp(loc, &zero, size)) {
 				pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
 				       (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			write(wr_loc, &val, size);
+			write(loc, &val, size);
 		} else {
 			if (memcmp(loc, &val, size)) {
 				pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
 					(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			/* FIXME: needs care for ROX module allocations */
 			write(loc, &zero, size);
 		}
 	}
@@ -194,7 +206,7 @@ static int write_relocate_add(Elf64_Shdr *sechdrs,
 				   write, apply);
 
 	if (!early) {
-		text_poke_sync();
+		smp_text_poke_sync_each_cpu();
 		mutex_unlock(&text_mutex);
 	}
 
@@ -227,7 +239,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s, *alt = NULL,
+	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
 		*orc = NULL, *orc_ip = NULL,
 		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
 		*calls = NULL, *cfi = NULL;
@@ -236,6 +248,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -252,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 			ibt_endbr = s;
 	}
 
+	its_init_mod(me);
+
 	if (retpolines || cfi) {
 		void *rseg = NULL, *cseg = NULL;
 		unsigned int rsize = 0, csize = 0;
@@ -266,60 +282,36 @@ int module_finalize(const Elf_Ehdr *hdr,
 			csize = cfi->sh_size;
 		}
 
-		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
+		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
 	}
 	if (retpolines) {
 		void *rseg = (void *)retpolines->sh_addr;
-		apply_retpolines(rseg, rseg + retpolines->sh_size, me);
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
 	}
+
+	its_fini_mod(me);
+
 	if (returns) {
 		void *rseg = (void *)returns->sh_addr;
-		apply_returns(rseg, rseg + returns->sh_size, me);
-	}
-	if (alt) {
-		/* patch .altinstructions */
-		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size, me);
+		apply_returns(rseg, rseg + returns->sh_size);
 	}
-	if (calls || alt) {
+	if (calls) {
 		struct callthunk_sites cs = {};
 
-		if (calls) {
-			cs.call_start = (void *)calls->sh_addr;
-			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
-		}
-
-		if (alt) {
-			cs.alt_start = (void *)alt->sh_addr;
-			cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
-		}
+		cs.call_start = (void *)calls->sh_addr;
+		cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 
 		callthunks_patch_module_calls(&cs, me);
 	}
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
-		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
+		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
 	}
-
-	if (orc && orc_ip)
-		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
-				   (void *)orc->sh_addr, orc->sh_size);
-
-	return 0;
-}
-
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *me)
-{
-	const Elf_Shdr *s, *locks = NULL;
-	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks = s;
-	}
-
 	if (locks) {
 		void *lseg = (void *)locks->sh_addr;
 		void *text = me->mem[MOD_TEXT].base;
@@ -329,10 +321,15 @@ int module_post_finalize(const Elf_Ehdr *hdr,
 					    text, text_end);
 	}
 
+	if (orc && orc_ip)
+		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+				   (void *)orc->sh_addr, orc->sh_size);
+
 	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
 	alternatives_smp_module_del(mod);
+	its_free_mod(mod);
 }
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ed163c8c8604..be93ec7255bf 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -40,32 +40,29 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
 
+/*
+ * An emergency handler can be set in any context including NMI
+ */
 struct nmi_desc {
 	raw_spinlock_t lock;
+	nmi_handler_t emerg_handler;
 	struct list_head head;
 };
 
-static struct nmi_desc nmi_desc[NMI_MAX] = 
-{
-	{
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
-		.head = LIST_HEAD_INIT(nmi_desc[0].head),
-	},
-	{
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
-		.head = LIST_HEAD_INIT(nmi_desc[1].head),
-	},
-	{
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock),
-		.head = LIST_HEAD_INIT(nmi_desc[2].head),
-	},
-	{
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock),
-		.head = LIST_HEAD_INIT(nmi_desc[3].head),
-	},
+#define NMI_DESC_INIT(type) { \
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[type].lock), \
+	.head = LIST_HEAD_INIT(nmi_desc[type].head), \
+}
 
+static struct nmi_desc nmi_desc[NMI_MAX] = {
+	NMI_DESC_INIT(NMI_LOCAL),
+	NMI_DESC_INIT(NMI_UNKNOWN),
+	NMI_DESC_INIT(NMI_SERR),
+	NMI_DESC_INIT(NMI_IO_CHECK),
 };
 
+#define nmi_to_desc(type) (&nmi_desc[type])
+
 struct nmi_stats {
 	unsigned int normal;
 	unsigned int unknown;
@@ -87,6 +84,9 @@ static DEFINE_PER_CPU(struct nmi_stats, nmi_stats);
 static int ignore_nmis __read_mostly;
 
 int unknown_nmi_panic;
+int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
+
 /*
  * Prevent NMI reason port (0x61) being accessed simultaneously, can
  * only be used in NMI handler.
@@ -100,8 +100,6 @@ static int __init setup_unknown_nmi_panic(char *str)
 }
 __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
-#define nmi_to_desc(type) (&nmi_desc[type])
-
 static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
 
 static int __init nmi_warning_debugfs(void)
@@ -121,20 +119,33 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
 
 	action->max_duration = duration;
 
-	remainder_ns = do_div(duration, (1000 * 1000));
-	decimal_msecs = remainder_ns / 1000;
+	/* Convert duration from nsec to msec */
+	remainder_ns = do_div(duration, NSEC_PER_MSEC);
+	decimal_msecs = remainder_ns / NSEC_PER_USEC;
 
-	printk_ratelimited(KERN_INFO
-		"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
-		action->handler, duration, decimal_msecs);
+	pr_info_ratelimited("INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+			    action->handler, duration, decimal_msecs);
 }
 
 static int nmi_handle(unsigned int type, struct pt_regs *regs)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
+	nmi_handler_t ehandler;
 	struct nmiaction *a;
 	int handled=0;
 
+	/*
+	 * Call the emergency handler, if set
+	 *
+	 * In the case of crash_nmi_callback() emergency handler, it will
+	 * return in the case of the crashing CPU to enable it to complete
+	 * other necessary crashing actions ASAP. Other handlers in the
+	 * linked list won't need to be run.
+	 */
+	ehandler = desc->emerg_handler;
+	if (ehandler)
+		return ehandler(type, regs);
+
 	rcu_read_lock();
 
 	/*
@@ -224,6 +235,31 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 }
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
+/**
+ * set_emergency_nmi_handler - Set emergency handler
+ * @type:    NMI type
+ * @handler: the emergency handler to be stored
+ *
+ * Set an emergency NMI handler which, if set, will preempt all the other
+ * handlers in the linked list. If a NULL handler is passed in, it will clear
+ * it. It is expected that concurrent calls to this function will not happen
+ * or the system is screwed beyond repair.
+ */
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+
+	if (WARN_ON_ONCE(desc->emerg_handler == handler))
+		return;
+	desc->emerg_handler = handler;
+
+	/*
+	 * Ensure the emergency handler is visible to other CPUs before
+	 * function return
+	 */
+	smp_wmb();
+}
+
 static void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
@@ -291,10 +327,9 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 	int handled;
 
 	/*
-	 * Use 'false' as back-to-back NMIs are dealt with one level up.
-	 * Of course this makes having multiple 'unknown' handlers useless
-	 * as only the first one is ever run (unless it can actually determine
-	 * if it caused the NMI)
+	 * As a last resort, let the "unknown" handlers make a
+	 * best-effort attempt to figure out if they can claim
+	 * responsibility for this Unknown NMI.
 	 */
 	handled = nmi_handle(NMI_UNKNOWN, regs);
 	if (handled) {
@@ -324,17 +359,18 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 	bool b2b = false;
 
 	/*
-	 * CPU-specific NMI must be processed before non-CPU-specific
-	 * NMI, otherwise we may lose it, because the CPU-specific
-	 * NMI can not be detected/processed on other CPUs.
-	 */
-
-	/*
-	 * Back-to-back NMIs are interesting because they can either
-	 * be two NMI or more than two NMIs (any thing over two is dropped
-	 * due to NMI being edge-triggered).  If this is the second half
-	 * of the back-to-back NMI, assume we dropped things and process
-	 * more handlers.  Otherwise reset the 'swallow' NMI behaviour
+	 * Back-to-back NMIs are detected by comparing the RIP of the
+	 * current NMI with that of the previous NMI. If it is the same,
+	 * it is assumed that the CPU did not have a chance to jump back
+	 * into a non-NMI context and execute code in between the two
+	 * NMIs.
+	 *
+	 * They are interesting because even if there are more than two,
+	 * only a maximum of two can be detected (anything over two is
+	 * dropped due to NMI being edge-triggered). If this is the
+	 * second half of the back-to-back NMI, assume we dropped things
+	 * and process more handlers. Otherwise, reset the 'swallow' NMI
+	 * behavior.
 	 */
 	if (regs->ip == __this_cpu_read(last_nmi_rip))
 		b2b = true;
@@ -348,6 +384,11 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 	if (microcode_nmi_handler_enabled() && microcode_nmi_handler())
 		goto out;
 
+	/*
+	 * CPU-specific NMI must be processed before non-CPU-specific
+	 * NMI, otherwise we may lose it, because the CPU-specific
+	 * NMI can not be detected/processed on other CPUs.
+	 */
 	handled = nmi_handle(NMI_LOCAL, regs);
 	__this_cpu_add(nmi_stats.normal, handled);
 	if (handled) {
@@ -384,13 +425,14 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
 			pci_serr_error(reason, regs);
 		else if (reason & NMI_REASON_IOCHK)
 			io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
+
 		/*
 		 * Reassert NMI in case it became active
 		 * meanwhile as it's edge-triggered:
 		 */
-		reassert_nmi();
-#endif
+		if (IS_ENABLED(CONFIG_X86_32))
+			reassert_nmi();
+
 		__this_cpu_add(nmi_stats.external, 1);
 		raw_spin_unlock(&nmi_reason_lock);
 		goto out;
@@ -709,4 +751,3 @@ void local_touch_nmi(void)
 {
 	__this_cpu_write(last_nmi_rip, 0);
 }
-EXPORT_SYMBOL_GPL(local_touch_nmi);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e93a8545c74d..a010e9d062bf 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * arch/x86/kernel/nmi-selftest.c
- *
  * Testsuite for NMI: IPIs
  *
  * Started by Don Zickus:
@@ -30,7 +28,6 @@ static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __initdata;
 
 static int __initdata testcase_total;
 static int __initdata testcase_successes;
-static int __initdata expected_testcase_failures;
 static int __initdata unexpected_testcase_failures;
 static int __initdata unexpected_testcase_unknowns;
 
@@ -120,26 +117,22 @@ static void __init dotest(void (*testcase_fn)(void), int expected)
 		unexpected_testcase_failures++;
 
 		if (nmi_fail == FAILURE)
-			printk(KERN_CONT "FAILED |");
+			pr_cont("FAILED |");
 		else if (nmi_fail == TIMEOUT)
-			printk(KERN_CONT "TIMEOUT|");
+			pr_cont("TIMEOUT|");
 		else
-			printk(KERN_CONT "ERROR  |");
+			pr_cont("ERROR  |");
 		dump_stack();
 	} else {
 		testcase_successes++;
-		printk(KERN_CONT "  ok  |");
+		pr_cont("  ok  |");
 	}
-	testcase_total++;
+	pr_cont("\n");
 
+	testcase_total++;
 	reset_nmi();
 }
 
-static inline void __init print_testname(const char *testname)
-{
-	printk("%12s:", testname);
-}
-
 void __init nmi_selftest(void)
 {
 	init_nmi_testsuite();
@@ -147,38 +140,25 @@ void __init nmi_selftest(void)
         /*
 	 * Run the testsuite:
 	 */
-	printk("----------------\n");
-	printk("| NMI testsuite:\n");
-	printk("--------------------\n");
+	pr_info("----------------\n");
+	pr_info("| NMI testsuite:\n");
+	pr_info("--------------------\n");
 
-	print_testname("remote IPI");
+	pr_info("%12s:", "remote IPI");
 	dotest(remote_ipi, SUCCESS);
-	printk(KERN_CONT "\n");
-	print_testname("local IPI");
+
+	pr_info("%12s:", "local IPI");
 	dotest(local_ipi, SUCCESS);
-	printk(KERN_CONT "\n");
 
 	cleanup_nmi_testsuite();
 
+	pr_info("--------------------\n");
 	if (unexpected_testcase_failures) {
-		printk("--------------------\n");
-		printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
+		pr_info("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
 			unexpected_testcase_failures, testcase_total);
-		printk("-----------------------------------------------------------------\n");
-	} else if (expected_testcase_failures && testcase_successes) {
-		printk("--------------------\n");
-		printk("%3d out of %3d testcases failed, as expected. |\n",
-			expected_testcase_failures, testcase_total);
-		printk("----------------------------------------------------\n");
-	} else if (expected_testcase_failures && !testcase_successes) {
-		printk("--------------------\n");
-		printk("All %3d testcases failed, as expected. |\n",
-			expected_testcase_failures);
-		printk("----------------------------------------\n");
 	} else {
-		printk("--------------------\n");
-		printk("Good, all %3d testcases passed! |\n",
+		pr_info("Good, all %3d testcases passed! |\n",
 			testcase_successes);
-		printk("---------------------------------\n");
 	}
+	pr_info("-----------------------------------------------------------------\n");
 }
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a67..ab3e172dcc69 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -33,6 +33,7 @@
 #include <asm/tlb.h>
 #include <asm/io_bitmap.h>
 #include <asm/gsseg.h>
+#include <asm/msr.h>
 
 /* stub always returning 0. */
 DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text);
@@ -59,21 +60,6 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
-#ifndef CONFIG_PT_RECLAIM
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -90,24 +76,9 @@ void paravirt_set_sched_clock(u64 (*func)(void))
 	static_call_update(pv_sched_clock, func);
 }
 
-/* These are in entry.S */
-static struct resource reserve_ioports = {
-	.start = 0,
-	.end = IO_SPACE_LIMIT,
-	.name = "paravirt-ioport",
-	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
-
-/*
- * Reserve the whole legacy IO space to prevent any legacy drivers
- * from wasting time probing for their hardware.  This is a fairly
- * brute-force approach to disabling all non-virtual drivers.
- *
- * Note that this must be called very early to have any effect.
- */
-int paravirt_disable_iospace(void)
+static noinstr void pv_native_safe_halt(void)
 {
-	return request_resource(&ioport_resource, &reserve_ioports);
+	native_safe_halt();
 }
 
 #ifdef CONFIG_PARAVIRT_XXL
@@ -116,6 +87,16 @@ static noinstr void pv_native_write_cr2(unsigned long val)
 	native_write_cr2(val);
 }
 
+static noinstr unsigned long pv_native_read_cr3(void)
+{
+	return __native_read_cr3();
+}
+
+static noinstr void pv_native_write_cr3(unsigned long cr3)
+{
+	native_write_cr3(cr3);
+}
+
 static noinstr unsigned long pv_native_get_debugreg(int regno)
 {
 	return native_get_debugreg(regno);
@@ -125,11 +106,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
 {
 	native_set_debugreg(regno, val);
 }
-
-static noinstr void pv_native_safe_halt(void)
-{
-	native_safe_halt();
-}
 #endif
 
 struct pv_info pv_info = {
@@ -186,16 +162,17 @@ struct paravirt_patch_template pv_ops = {
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(pv_native_save_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
+#endif /* CONFIG_PARAVIRT_XXL */
+
+	/* Irq HLT ops. */
 	.irq.safe_halt		= pv_native_safe_halt,
 	.irq.halt		= native_halt,
-#endif /* CONFIG_PARAVIRT_XXL */
 
 	/* Mmu ops. */
 	.mmu.flush_tlb_user	= native_flush_tlb_local,
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
-	.mmu.tlb_remove_table	= native_tlb_remove_table,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
@@ -203,8 +180,8 @@ struct paravirt_patch_template pv_ops = {
 #ifdef CONFIG_PARAVIRT_XXL
 	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
 	.mmu.write_cr2		= pv_native_write_cr2,
-	.mmu.read_cr3		= __native_read_cr3,
-	.mmu.write_cr3		= native_write_cr3,
+	.mmu.read_cr3		= pv_native_read_cr3,
+	.mmu.write_cr3		= pv_native_write_cr3,
 
 	.mmu.pgd_alloc		= __paravirt_pgd_alloc,
 	.mmu.pgd_free		= paravirt_nop,
@@ -234,12 +211,10 @@ struct paravirt_patch_template pv_ops = {
 
 	.mmu.set_p4d		= native_set_p4d,
 
-#if CONFIG_PGTABLE_LEVELS >= 5
 	.mmu.p4d_val		= PTE_IDENT,
 	.mmu.make_p4d		= PTE_IDENT,
 
 	.mmu.set_pgd		= native_set_pgd,
-#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
 
 	.mmu.pte_val		= PTE_IDENT,
 	.mmu.pgd_val		= PTE_IDENT,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254..c1d2dac72b9c 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -30,7 +30,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/entry-common.h>
 #include <asm/cpu.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/apic.h>
 #include <linux/uaccess.h>
 #include <asm/mwait.h>
@@ -52,6 +52,7 @@
 #include <asm/unwind.h>
 #include <asm/tdx.h>
 #include <asm/mmu_context.h>
+#include <asm/msr.h>
 #include <asm/shstk.h>
 
 #include "process.h"
@@ -93,12 +94,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst, src, arch_task_struct_size);
+	/* fpu_clone() will initialize the "dst_fpu" memory */
+	memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(*dst), 0);
+
 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif
-	/* Drop the copied pointer to current's fpstate */
-	dst->thread.fpu.fpstate = NULL;
 
 	return 0;
 }
@@ -106,8 +107,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 #ifdef CONFIG_X86_64
 void arch_release_task_struct(struct task_struct *tsk)
 {
-	if (fpu_state_size_dynamic())
-		fpstate_free(&tsk->thread.fpu);
+	if (fpu_state_size_dynamic() && !(tsk->flags & (PF_KTHREAD | PF_USER_WORKER)))
+		fpstate_free(x86_task_fpu(tsk));
 }
 #endif
 
@@ -117,7 +118,6 @@ void arch_release_task_struct(struct task_struct *tsk)
 void exit_thread(struct task_struct *tsk)
 {
 	struct thread_struct *t = &tsk->thread;
-	struct fpu *fpu = &t->fpu;
 
 	if (test_thread_flag(TIF_IO_BITMAP))
 		io_bitmap_exit(tsk);
@@ -125,7 +125,7 @@ void exit_thread(struct task_struct *tsk)
 	free_vm86(t);
 
 	shstk_free(tsk);
-	fpu__drop(fpu);
+	fpu__drop(tsk);
 }
 
 static int set_new_tls(struct task_struct *p, unsigned long tls)
@@ -339,7 +339,7 @@ static void set_cpuid_faulting(bool on)
 	msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
 	msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
 	this_cpu_write(msr_misc_features_shadow, msrval);
-	wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
+	wrmsrq(MSR_MISC_FEATURES_ENABLES, msrval);
 }
 
 static void disable_cpuid(void)
@@ -556,7 +556,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
 
 	if (!static_cpu_has(X86_FEATURE_ZEN)) {
 		msr |= ssbd_tif_to_amd_ls_cfg(tifn);
-		wrmsrl(MSR_AMD64_LS_CFG, msr);
+		wrmsrq(MSR_AMD64_LS_CFG, msr);
 		return;
 	}
 
@@ -573,7 +573,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
 		raw_spin_lock(&st->shared_state->lock);
 		/* First sibling enables SSBD: */
 		if (!st->shared_state->disable_state)
-			wrmsrl(MSR_AMD64_LS_CFG, msr);
+			wrmsrq(MSR_AMD64_LS_CFG, msr);
 		st->shared_state->disable_state++;
 		raw_spin_unlock(&st->shared_state->lock);
 	} else {
@@ -583,7 +583,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
 		raw_spin_lock(&st->shared_state->lock);
 		st->shared_state->disable_state--;
 		if (!st->shared_state->disable_state)
-			wrmsrl(MSR_AMD64_LS_CFG, msr);
+			wrmsrq(MSR_AMD64_LS_CFG, msr);
 		raw_spin_unlock(&st->shared_state->lock);
 	}
 }
@@ -592,7 +592,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
 {
 	u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
 
-	wrmsrl(MSR_AMD64_LS_CFG, msr);
+	wrmsrq(MSR_AMD64_LS_CFG, msr);
 }
 #endif
 
@@ -602,7 +602,7 @@ static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
 	 * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
 	 * so ssbd_tif_to_spec_ctrl() just works.
 	 */
-	wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+	wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
 }
 
 /*
@@ -705,11 +705,11 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 	    arch_has_block_step()) {
 		unsigned long debugctl, msk;
 
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 		debugctl &= ~DEBUGCTLMSR_BTF;
 		msk = tifn & _TIF_BLOCKSTEP;
 		debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
 	if ((tifp ^ tifn) & _TIF_NOTSC)
@@ -902,13 +902,10 @@ static __init bool prefer_mwait_c1_over_halt(void)
 static __cpuidle void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
-		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
-			mb(); /* quirk */
-			clflush((void *)&current_thread_info()->flags);
-			mb(); /* quirk */
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 		if (!need_resched()) {
 			__sti_mwait(0, 0);
 			raw_local_irq_disable();
@@ -934,7 +931,7 @@ void __init select_idle_routine(void)
 		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
-		static_call_update(x86_idle, tdx_safe_halt);
+		static_call_update(x86_idle, tdx_halt);
 	} else {
 		static_call_update(x86_idle, default_idle);
 	}
@@ -1043,7 +1040,7 @@ unsigned long __get_wchan(struct task_struct *p)
 	return addr;
 }
 
-long do_arch_prctl_common(int option, unsigned long arg2)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
 	switch (option) {
 	case ARCH_GET_CPUID:
@@ -1058,5 +1055,13 @@ long do_arch_prctl_common(int option, unsigned long arg2)
 		return fpu_xstate_prctl(option, arg2);
 	}
 
+	if (!in_ia32_syscall())
+		return do_arch_prctl_64(current, option, arg2);
+
 	return -EINVAL;
 }
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+	return -ENOSYS;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0917c7f25720..a10e180cbf23 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -160,8 +160,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_p, cpu);
+	switch_fpu(prev_p, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -190,13 +189,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0 and pcpu_hot.top_of_stack.  This changes
+	 * Reload esp0 and cpu_current_top_of_stack.  This changes
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
 	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
-	this_cpu_write(pcpu_hot.top_of_stack,
+	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
 
@@ -206,17 +205,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	raw_cpu_write(pcpu_hot.current_task, next_p);
-
-	switch_fpu_finish(next_p);
+	raw_cpu_write(current_task, next_p);
 
 	/* Load the Intel cache allocation PQR MSR. */
-	resctrl_sched_in(next_p);
+	resctrl_arch_sched_in(next_p);
 
 	return prev_p;
 }
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 226472332a70..8d6cf25127aa 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -57,6 +57,7 @@
 #include <asm/unistd.h>
 #include <asm/fsgsbase.h>
 #include <asm/fred.h>
+#include <asm/msr.h>
 #ifdef CONFIG_IA32_EMULATION
 /* Not included via unistd.h */
 #include <asm/unistd_32_ia32.h>
@@ -95,8 +96,8 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 		return;
 
 	if (mode == SHOW_REGS_USER) {
-		rdmsrl(MSR_FS_BASE, fs);
-		rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+		rdmsrq(MSR_FS_BASE, fs);
+		rdmsrq(MSR_KERNEL_GS_BASE, shadowgs);
 		printk("%sFS:  %016lx GS:  %016lx\n",
 		       log_lvl, fs, shadowgs);
 		return;
@@ -107,9 +108,9 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 	asm("movl %%fs,%0" : "=r" (fsindex));
 	asm("movl %%gs,%0" : "=r" (gsindex));
 
-	rdmsrl(MSR_FS_BASE, fs);
-	rdmsrl(MSR_GS_BASE, gs);
-	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+	rdmsrq(MSR_FS_BASE, fs);
+	rdmsrq(MSR_GS_BASE, gs);
+	rdmsrq(MSR_KERNEL_GS_BASE, shadowgs);
 
 	cr0 = read_cr0();
 	cr2 = read_cr2();
@@ -195,7 +196,7 @@ static noinstr unsigned long __rdgsbase_inactive(void)
 		native_swapgs();
 	} else {
 		instrumentation_begin();
-		rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+		rdmsrq(MSR_KERNEL_GS_BASE, gsbase);
 		instrumentation_end();
 	}
 
@@ -221,7 +222,7 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase)
 		native_swapgs();
 	} else {
 		instrumentation_begin();
-		wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+		wrmsrq(MSR_KERNEL_GS_BASE, gsbase);
 		instrumentation_end();
 	}
 }
@@ -353,7 +354,7 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
 		} else {
 			if (prev_index != next_index)
 				loadseg(which, next_index);
-			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+			wrmsrq(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
 			       next_base);
 		}
 	} else {
@@ -463,7 +464,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void)
 		gsbase = __rdgsbase_inactive();
 		local_irq_restore(flags);
 	} else {
-		rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+		rdmsrq(MSR_KERNEL_GS_BASE, gsbase);
 	}
 
 	return gsbase;
@@ -478,7 +479,7 @@ void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
 		__wrgsbase_inactive(gsbase);
 		local_irq_restore(flags);
 	} else {
-		wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+		wrmsrq(MSR_KERNEL_GS_BASE, gsbase);
 	}
 }
 
@@ -614,10 +615,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
-		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
+		     this_cpu_read(hardirq_stack_inuse));
 
-	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_p, cpu);
+	switch_fpu(prev_p, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -668,10 +668,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	raw_cpu_write(pcpu_hot.current_task, next_p);
-	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
-
-	switch_fpu_finish(next_p);
+	raw_cpu_write(current_task, next_p);
+	raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
 	update_task_stack(next_p);
@@ -707,7 +705,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	}
 
 	/* Load the Intel cache allocation PQR MSR. */
-	resctrl_sched_in(next_p);
+	resctrl_arch_sched_in(next_p);
 
 	return prev_p;
 }
@@ -942,7 +940,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	case ARCH_MAP_VDSO_X32:
 		return prctl_map_vdso(&vdso_image_x32, arg2);
 # endif
-# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+# ifdef CONFIG_IA32_EMULATION
 	case ARCH_MAP_VDSO_32:
 		return prctl_map_vdso(&vdso_image_32, arg2);
 # endif
@@ -979,26 +977,3 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 
 	return ret;
 }
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	long ret;
-
-	ret = do_arch_prctl_64(current, option, arg2);
-	if (ret == -EINVAL)
-		ret = do_arch_prctl_common(option, arg2);
-
-	return ret;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
-#endif
-
-unsigned long KSTK_ESP(struct task_struct *task)
-{
-	return task_pt_regs(task)->sp;
-}
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 6d0df6a58873..a92f18db9610 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -10,6 +10,8 @@
 #include <asm/setup.h>
 #include <asm/mce.h>
 
+#include <linux/platform_data/x86/apple.h>
+
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
 static void quirk_intel_irqbalance(struct pci_dev *dev)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index dc1dd3f3e67f..964f6b0a3d68 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -921,20 +921,16 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 		return;
 
 	/* Make a note of crashing cpu. Will be used in NMI callback. */
-	crashing_cpu = safe_smp_processor_id();
+	crashing_cpu = smp_processor_id();
 
 	shootdown_callback = callback;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
-				 NMI_FLAG_FIRST, "crash"))
-		return;		/* Return what? */
+
 	/*
-	 * Ensure the new callback function is set before sending
-	 * out the NMI
+	 * Set emergency handler to preempt other handlers.
 	 */
-	wmb();
+	set_emergency_nmi_handler(NMI_LOCAL, crash_nmi_callback);
 
 	apic_send_IPI_allbutself(NMI_VECTOR);
 
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index b7c0f142d026..4679ac0a03eb 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -27,7 +27,7 @@ static void cs5530a_warm_reset(struct pci_dev *dev)
 static void cs5536_warm_reset(struct pci_dev *dev)
 {
 	/* writing 1 to the LSB of this MSR causes a hard reset */
-	wrmsrl(MSR_DIVIL_SOFT_RESET, 1ULL);
+	wrmsrq(MSR_DIVIL_SOFT_RESET, 1ULL);
 	udelay(50); /* shouldn't get here but be safe and spin a while */
 }
 
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index c7c4b1917336..57276f134d12 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -263,17 +263,17 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 
 	movl	%edx, %edi
 	movl    $1024, %ecx
-	rep ; movsl
+	rep movsl
 
 	movl	%ebp, %edi
 	movl	%eax, %esi
 	movl	$1024, %ecx
-	rep ; movsl
+	rep movsl
 
 	movl	%eax, %edi
 	movl	%edx, %esi
 	movl	$1024, %ecx
-	rep ; movsl
+	rep movsl
 
 	lea	PAGE_SIZE(%ebp), %esi
 	jmp     0b
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index b44d8863e57f..ea604f4d0b52 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -39,6 +39,23 @@ SYM_DATA(kexec_va_control_page, .quad 0)
 SYM_DATA(kexec_pa_table_page, .quad 0)
 SYM_DATA(kexec_pa_swap_page, .quad 0)
 SYM_DATA_LOCAL(pa_backup_pages_map, .quad 0)
+SYM_DATA(kexec_debug_8250_mmio32, .quad 0)
+SYM_DATA(kexec_debug_8250_port, .word 0)
+
+	.balign 16
+SYM_DATA_START_LOCAL(kexec_debug_gdt)
+	.word   kexec_debug_gdt_end - kexec_debug_gdt - 1
+	.long   0
+	.word   0
+	.quad   0x00cf9a000000ffff      /* __KERNEL32_CS */
+	.quad   0x00af9a000000ffff      /* __KERNEL_CS */
+	.quad   0x00cf92000000ffff      /* __KERNEL_DS */
+SYM_DATA_END_LABEL(kexec_debug_gdt, SYM_L_LOCAL, kexec_debug_gdt_end)
+
+	.balign 8
+SYM_DATA_START(kexec_debug_idt)
+	.skip 0x100, 0x00
+SYM_DATA_END(kexec_debug_idt)
 
 	.section .text..relocate_kernel,"ax";
 	.code64
@@ -62,8 +79,13 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
 	pushq %r15
 	pushf
 
-	/* zero out flags, and disable interrupts */
-	pushq $0
+	/* Invalidate GDT/IDT, zero out flags */
+	pushq	$0
+	pushq	$0
+
+	lidt	(%rsp)
+	lgdt	(%rsp)
+	addq	$8, %rsp
 	popfq
 
 	/* Switch to the identity mapped page tables */
@@ -116,6 +138,28 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	/* store the start address on the stack */
 	pushq   %rdx
 
+	/* Create a GDTR (16 bits limit, 64 bits addr) on stack */
+	leaq	kexec_debug_gdt(%rip), %rax
+	pushq	%rax
+	pushw	(%rax)
+
+	/* Load the GDT, put the stack back */
+	lgdt	(%rsp)
+	addq	$10, %rsp
+
+	/* Test that we can load segments */
+	movq	%ds, %rax
+	movq	%rax, %ds
+
+	/* Now an IDTR on the stack to load the IDT the kernel created */
+	leaq	kexec_debug_idt(%rip), %rsi
+	pushq	%rsi
+	pushw	$0xff
+	lidt	(%rsp)
+	addq	$10, %rsp
+
+	//int3
+
 	/*
 	 * Clear X86_CR4_CET (if it was set) such that we can clear CR0_WP
 	 * below.
@@ -319,20 +363,20 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	/* copy source page to swap page */
 	movq	kexec_pa_swap_page(%rip), %rdi
 	movl	$512, %ecx
-	rep ; movsq
+	rep movsq
 
 	/* copy destination page to source page */
 	movq	%rax, %rdi
 	movq	%rdx, %rsi
 	movl	$512, %ecx
-	rep ; movsq
+	rep movsq
 
 	/* copy swap page to destination page */
 	movq	%rdx, %rdi
 	movq	kexec_pa_swap_page(%rip), %rsi
 .Lnoswap:
 	movl	$512, %ecx
-	rep ; movsq
+	rep movsq
 
 	lea	PAGE_SIZE(%rax), %rsi
 	jmp	.Lloop
@@ -341,3 +385,222 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	ret
 	int3
 SYM_CODE_END(swap_pages)
+
+/*
+ * Generic 'print character' routine
+ *  - %al: Character to be printed (may clobber %rax)
+ *  - %rdx: MMIO address or port.
+ */
+#define XMTRDY          0x20
+
+#define TXR             0       /*  Transmit register (WRITE) */
+#define LSR             5       /*  Line Status               */
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_char_8250)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	addw	$LSR, %dx
+	xchg	%al, %ah
+.Lxmtrdy_loop:
+	inb	%dx, %al
+	testb	$XMTRDY, %al
+	jnz	.Lready
+	pause
+	jmp .Lxmtrdy_loop
+
+.Lready:
+	subw	$LSR, %dx
+	xchg	%al, %ah
+	outb	%al, %dx
+pr_char_null:
+	ANNOTATE_NOENDBR
+
+	ANNOTATE_UNRET_SAFE
+	ret
+SYM_CODE_END(pr_char_8250)
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_char_8250_mmio32)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+.Lxmtrdy_loop_mmio:
+	movb	(LSR*4)(%rdx), %ah
+	testb	$XMTRDY, %ah
+	jnz	.Lready_mmio
+	pause
+	jmp .Lxmtrdy_loop_mmio
+
+.Lready_mmio:
+	movb	%al, (%rdx)
+	ANNOTATE_UNRET_SAFE
+	ret
+SYM_CODE_END(pr_char_8250_mmio32)
+
+/*
+ * Load pr_char function pointer into %rsi and load %rdx with whatever
+ * that function wants to see there (typically port/MMIO address).
+ */
+.macro pr_setup
+	leaq	pr_char_8250(%rip), %rsi
+	movw	kexec_debug_8250_port(%rip), %dx
+	testw	%dx, %dx
+	jnz	1f
+
+	leaq	pr_char_8250_mmio32(%rip), %rsi
+	movq	kexec_debug_8250_mmio32(%rip), %rdx
+	testq	%rdx, %rdx
+	jnz	1f
+
+	leaq	pr_char_null(%rip), %rsi
+1:
+.endm
+
+/* Print the nybble in %bl, clobber %rax */
+SYM_CODE_START_LOCAL_NOALIGN(pr_nybble)
+	UNWIND_HINT_FUNC
+	movb	%bl, %al
+	nop
+	andb	$0x0f, %al
+	addb	$0x30, %al
+	cmpb	$0x3a, %al
+	jb	1f
+	addb	$('a' - '0' - 10), %al
+	ANNOTATE_RETPOLINE_SAFE
+1:	jmp	*%rsi
+SYM_CODE_END(pr_nybble)
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_qword)
+	UNWIND_HINT_FUNC
+	movq	$16, %rcx
+1:	rolq	$4, %rbx
+	call	pr_nybble
+	loop	1b
+	movb	$'\n', %al
+	ANNOTATE_RETPOLINE_SAFE
+	jmp	*%rsi
+SYM_CODE_END(pr_qword)
+
+.macro print_reg a, b, c, d, r
+	movb	$\a, %al
+	ANNOTATE_RETPOLINE_SAFE
+	call	*%rsi
+	movb	$\b, %al
+	ANNOTATE_RETPOLINE_SAFE
+	call	*%rsi
+	movb	$\c, %al
+	ANNOTATE_RETPOLINE_SAFE
+	call	*%rsi
+	movb	$\d, %al
+	ANNOTATE_RETPOLINE_SAFE
+	call	*%rsi
+	movq	\r, %rbx
+	call	pr_qword
+.endm
+
+SYM_CODE_START_NOALIGN(kexec_debug_exc_vectors)
+	/* Each of these is 6 bytes. */
+.macro vec_err exc
+	UNWIND_HINT_ENTRY
+	. = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+	nop
+	nop
+	pushq	$\exc
+	jmp	exc_handler
+.endm
+
+.macro vec_noerr exc
+	UNWIND_HINT_ENTRY
+	. = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+	pushq	$0
+	pushq	$\exc
+	jmp	exc_handler
+.endm
+
+	ANNOTATE_NOENDBR
+	vec_noerr  0 // #DE
+	vec_noerr  1 // #DB
+	vec_noerr  2 // #NMI
+	vec_noerr  3 // #BP
+	vec_noerr  4 // #OF
+	vec_noerr  5 // #BR
+	vec_noerr  6 // #UD
+	vec_noerr  7 // #NM
+	vec_err    8 // #DF
+	vec_noerr  9
+	vec_err   10 // #TS
+	vec_err   11 // #NP
+	vec_err   12 // #SS
+	vec_err   13 // #GP
+	vec_err   14 // #PF
+	vec_noerr 15
+SYM_CODE_END(kexec_debug_exc_vectors)
+
+SYM_CODE_START_LOCAL_NOALIGN(exc_handler)
+	/* No need for RET mitigations during kexec */
+	VALIDATE_UNRET_END
+
+	pushq	%rax
+	pushq	%rbx
+	pushq	%rcx
+	pushq	%rdx
+	pushq	%rsi
+
+	/* Stack frame */
+#define EXC_SS		0x58 /* Architectural... */
+#define EXC_RSP		0x50
+#define EXC_EFLAGS	0x48
+#define EXC_CS		0x40
+#define EXC_RIP		0x38
+#define EXC_ERRORCODE	0x30 /* Either architectural or zero pushed by handler */
+#define EXC_EXCEPTION	0x28 /* Pushed by handler entry point */
+#define EXC_RAX		0x20 /* Pushed just above in exc_handler */
+#define EXC_RBX		0x18
+#define EXC_RCX		0x10
+#define EXC_RDX		0x08
+#define EXC_RSI		0x00
+
+	/* Set up %rdx/%rsi for debug output */
+	pr_setup
+
+	/* rip and exception info */
+	print_reg 'E', 'x', 'c', ':', EXC_EXCEPTION(%rsp)
+	print_reg 'E', 'r', 'r', ':', EXC_ERRORCODE(%rsp)
+	print_reg 'r', 'i', 'p', ':', EXC_RIP(%rsp)
+	print_reg 'r', 's', 'p', ':', EXC_RSP(%rsp)
+
+	/* We spilled these to the stack */
+	print_reg 'r', 'a', 'x', ':', EXC_RAX(%rsp)
+	print_reg 'r', 'b', 'x', ':', EXC_RBX(%rsp)
+	print_reg 'r', 'c', 'x', ':', EXC_RCX(%rsp)
+	print_reg 'r', 'd', 'x', ':', EXC_RDX(%rsp)
+	print_reg 'r', 's', 'i', ':', EXC_RSI(%rsp)
+
+	/* Other registers untouched */
+	print_reg 'r', 'd', 'i', ':', %rdi
+	print_reg 'r', '8', ' ', ':', %r8
+	print_reg 'r', '9', ' ', ':', %r9
+	print_reg 'r', '1', '0', ':', %r10
+	print_reg 'r', '1', '1', ':', %r11
+	print_reg 'r', '1', '2', ':', %r12
+	print_reg 'r', '1', '3', ':', %r13
+	print_reg 'r', '1', '4', ':', %r14
+	print_reg 'r', '1', '5', ':', %r15
+	print_reg 'c', 'r', '2', ':', %cr2
+
+	/* Only return from INT3 */
+	cmpq	$3, EXC_EXCEPTION(%rsp)
+	jne	.Ldie
+
+	popq	%rsi
+	popq	%rdx
+	popq	%rcx
+	popq	%rbx
+	popq	%rax
+
+	addq	$16, %rsp
+	iretq
+
+.Ldie:
+	hlt
+	jmp	.Ldie
+
+SYM_CODE_END(exc_handler)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cebee310e200..7d9ed79a93c0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -11,6 +11,7 @@
 #include <linux/crash_dump.h>
 #include <linux/dma-map-ops.h>
 #include <linux/efi.h>
+#include <linux/hugetlb.h>
 #include <linux/ima.h>
 #include <linux/init_ohci1394_dma.h>
 #include <linux/initrd.h>
@@ -18,21 +19,19 @@
 #include <linux/memblock.h>
 #include <linux/panic_notifier.h>
 #include <linux/pci.h>
+#include <linux/random.h>
 #include <linux/root_dev.h>
-#include <linux/hugetlb.h>
-#include <linux/tboot.h>
-#include <linux/usb/xhci-dbgp.h>
 #include <linux/static_call.h>
 #include <linux/swiotlb.h>
-#include <linux/random.h>
+#include <linux/tboot.h>
+#include <linux/usb/xhci-dbgp.h>
+#include <linux/vmalloc.h>
 
 #include <uapi/linux/mount.h>
 
 #include <xen/xen.h>
 
 #include <asm/apic.h>
-#include <asm/efi.h>
-#include <asm/numa.h>
 #include <asm/bios_ebda.h>
 #include <asm/bugs.h>
 #include <asm/cacheinfo.h>
@@ -47,15 +46,16 @@
 #include <asm/mce.h>
 #include <asm/memtype.h>
 #include <asm/mtrr.h>
-#include <asm/realmode.h>
+#include <asm/nmi.h>
+#include <asm/numa.h>
 #include <asm/olpc_ofw.h>
 #include <asm/pci-direct.h>
 #include <asm/prom.h>
 #include <asm/proto.h>
+#include <asm/realmode.h>
 #include <asm/thermal.h>
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
-#include <linux/vmalloc.h>
 
 /*
  * max_low_pfn_mapped: highest directly mapped pfn < 4 GB
@@ -131,6 +131,7 @@ struct ist_info ist_info;
 
 struct cpuinfo_x86 boot_cpu_data __read_mostly;
 EXPORT_SYMBOL(boot_cpu_data);
+SYM_PIC_ALIAS(boot_cpu_data);
 
 #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
 __visible unsigned long mmu_cr4_features __ro_after_init;
@@ -146,6 +147,67 @@ static size_t ima_kexec_buffer_size;
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */
 int bootloader_type, bootloader_version;
 
+static const struct ctl_table x86_sysctl_table[] = {
+	{
+		.procname       = "unknown_nmi_panic",
+		.data           = &unknown_nmi_panic,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_type",
+		.data		= &bootloader_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_version",
+		.data		= &bootloader_version,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "io_delay_type",
+		.data		= &io_delay_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#if defined(CONFIG_ACPI_SLEEP)
+	{
+		.procname	= "acpi_video_flags",
+		.data		= &acpi_realmode_flags,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+#endif
+};
+
+static int __init init_x86_sysctl(void)
+{
+	register_sysctl_init("kernel", x86_sysctl_table);
+	return 0;
+}
+arch_initcall(init_x86_sysctl);
+
 /*
  * Setup options
  */
@@ -429,6 +491,46 @@ static void __init parse_setup_data(void)
 	}
 }
 
+/*
+ * Translate the fields of 'struct boot_param' into global variables
+ * representing these parameters.
+ */
+static void __init parse_boot_params(void)
+{
+	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
+	screen_info = boot_params.screen_info;
+	edid_info = boot_params.edid_info;
+#ifdef CONFIG_X86_32
+	apm_info.bios = boot_params.apm_bios_info;
+	ist_info = boot_params.ist_info;
+#endif
+	saved_video_mode = boot_params.hdr.vid_mode;
+	bootloader_type = boot_params.hdr.type_of_loader;
+	if ((bootloader_type >> 4) == 0xe) {
+		bootloader_type &= 0xf;
+		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+	}
+	bootloader_version  = bootloader_type & 0xf;
+	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
+
+#ifdef CONFIG_BLK_DEV_RAM
+	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
+#endif
+#ifdef CONFIG_EFI
+	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+		     EFI32_LOADER_SIGNATURE, 4)) {
+		set_bit(EFI_BOOT, &efi.flags);
+	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+		     EFI64_LOADER_SIGNATURE, 4)) {
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
+	}
+#endif
+
+	if (!boot_params.hdr.root_flags)
+		root_mountflags &= ~MS_RDONLY;
+}
+
 static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_indirect *indirect;
@@ -472,14 +574,13 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long crash_base, crash_size, low_size = 0;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
@@ -490,8 +591,7 @@ static void __init arch_reserve_crashkernel(void)
 		return;
 	}
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static struct resource standard_io_resources[] = {
@@ -527,6 +627,23 @@ void __init reserve_standard_io_resources(void)
 
 }
 
+static void __init setup_kernel_resources(void)
+{
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext)-1;
+	rodata_resource.start = __pa_symbol(__start_rodata);
+	rodata_resource.end = __pa_symbol(__end_rodata)-1;
+	data_resource.start = __pa_symbol(_sdata);
+	data_resource.end = __pa_symbol(_edata)-1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop)-1;
+
+	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &rodata_resource);
+	insert_resource(&iomem_resource, &data_resource);
+	insert_resource(&iomem_resource, &bss_resource);
+}
+
 static bool __init snb_gfx_workaround_needed(void)
 {
 #ifdef CONFIG_PCI
@@ -789,35 +906,7 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_olpc_ofw_pgd();
 
-	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
-	screen_info = boot_params.screen_info;
-	edid_info = boot_params.edid_info;
-#ifdef CONFIG_X86_32
-	apm_info.bios = boot_params.apm_bios_info;
-	ist_info = boot_params.ist_info;
-#endif
-	saved_video_mode = boot_params.hdr.vid_mode;
-	bootloader_type = boot_params.hdr.type_of_loader;
-	if ((bootloader_type >> 4) == 0xe) {
-		bootloader_type &= 0xf;
-		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
-	}
-	bootloader_version  = bootloader_type & 0xf;
-	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
-
-#ifdef CONFIG_BLK_DEV_RAM
-	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
-#endif
-#ifdef CONFIG_EFI
-	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     EFI32_LOADER_SIGNATURE, 4)) {
-		set_bit(EFI_BOOT, &efi.flags);
-	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     EFI64_LOADER_SIGNATURE, 4)) {
-		set_bit(EFI_BOOT, &efi.flags);
-		set_bit(EFI_64BIT, &efi.flags);
-	}
-#endif
+	parse_boot_params();
 
 	x86_init.oem.arch_setup();
 
@@ -841,19 +930,8 @@ void __init setup_arch(char **cmdline_p)
 
 	copy_edd();
 
-	if (!boot_params.hdr.root_flags)
-		root_mountflags &= ~MS_RDONLY;
 	setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end);
 
-	code_resource.start = __pa_symbol(_text);
-	code_resource.end = __pa_symbol(_etext)-1;
-	rodata_resource.start = __pa_symbol(__start_rodata);
-	rodata_resource.end = __pa_symbol(__end_rodata)-1;
-	data_resource.start = __pa_symbol(_sdata);
-	data_resource.end = __pa_symbol(_edata)-1;
-	bss_resource.start = __pa_symbol(__bss_start);
-	bss_resource.end = __pa_symbol(__bss_stop)-1;
-
 	/*
 	 * x86_configure_nx() is called before parse_early_param() to detect
 	 * whether hardware doesn't support NX (so that the early EHCI debug
@@ -866,30 +944,6 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_memblock_x86_reserve_range();
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-	/*
-	 * Memory used by the kernel cannot be hot-removed because Linux
-	 * cannot migrate the kernel pages. When memory hotplug is
-	 * enabled, we should prevent memblock from allocating memory
-	 * for the kernel.
-	 *
-	 * ACPI SRAT records all hotpluggable memory ranges. But before
-	 * SRAT is parsed, we don't know about it.
-	 *
-	 * The kernel image is loaded into memory at very early time. We
-	 * cannot prevent this anyway. So on NUMA system, we set any
-	 * node the kernel resides in as un-hotpluggable.
-	 *
-	 * Since on modern servers, one node could have double-digit
-	 * gigabytes memory, we can assume the memory around the kernel
-	 * image is also un-hotpluggable. So before SRAT is parsed, just
-	 * allocate memory near the kernel image to try the best to keep
-	 * the kernel away from hotpluggable memory.
-	 */
-	if (movable_node_is_enabled())
-		memblock_set_bottom_up(true);
-#endif
-
 	x86_report_nx();
 
 	apic_setup_apic_calls();
@@ -901,7 +955,6 @@ void __init setup_arch(char **cmdline_p)
 		setup_clear_cpu_cap(X86_FEATURE_APIC);
 	}
 
-	e820__reserve_setup_data();
 	e820__finish_early_params();
 
 	if (efi_enabled(EFI_BOOT))
@@ -921,11 +974,11 @@ void __init setup_arch(char **cmdline_p)
 	tsc_early_init();
 	x86_init.resources.probe_roms();
 
-	/* after parse_early_param, so could debug it */
-	insert_resource(&iomem_resource, &code_resource);
-	insert_resource(&iomem_resource, &rodata_resource);
-	insert_resource(&iomem_resource, &data_resource);
-	insert_resource(&iomem_resource, &bss_resource);
+	/*
+	 * Add resources for kernel text and data to the iomem_resource.
+	 * Do it after parse_early_param, so it can be debugged.
+	 */
+	setup_kernel_resources();
 
 	e820_add_kernel_range();
 	trim_bios_range();
@@ -972,8 +1025,6 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = e820__end_of_low_ram_pfn();
 	else
 		max_low_pfn = max_pfn;
-
-	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
 	/* Find and reserve MPTABLE area */
@@ -990,7 +1041,6 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
 	/*
@@ -1108,8 +1158,10 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
-	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+	if (boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+		hugetlb_bootmem_alloc();
+	}
 
 	/*
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7..bfa48e7a32a2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,13 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
+DEFINE_PER_CPU_CACHE_HOT(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
 
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
-	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
 EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
@@ -169,7 +164,7 @@ void __init setup_per_cpu_areas(void)
 	for_each_possible_cpu(cpu) {
 		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
-		per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
+		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 059685612362..2ddf23387c7e 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -173,8 +173,8 @@ static int shstk_setup(void)
 		return PTR_ERR((void *)addr);
 
 	fpregs_lock_and_load();
-	wrmsrl(MSR_IA32_PL3_SSP, addr + size);
-	wrmsrl(MSR_IA32_U_CET, CET_SHSTK_EN);
+	wrmsrq(MSR_IA32_PL3_SSP, addr + size);
+	wrmsrq(MSR_IA32_U_CET, CET_SHSTK_EN);
 	fpregs_unlock();
 
 	shstk->base = addr;
@@ -239,7 +239,7 @@ static unsigned long get_user_shstk_addr(void)
 
 	fpregs_lock_and_load();
 
-	rdmsrl(MSR_IA32_PL3_SSP, ssp);
+	rdmsrq(MSR_IA32_PL3_SSP, ssp);
 
 	fpregs_unlock();
 
@@ -372,7 +372,7 @@ int setup_signal_shadow_stack(struct ksignal *ksig)
 		return -EFAULT;
 
 	fpregs_lock_and_load();
-	wrmsrl(MSR_IA32_PL3_SSP, ssp);
+	wrmsrq(MSR_IA32_PL3_SSP, ssp);
 	fpregs_unlock();
 
 	return 0;
@@ -396,7 +396,7 @@ int restore_signal_shadow_stack(void)
 		return err;
 
 	fpregs_lock_and_load();
-	wrmsrl(MSR_IA32_PL3_SSP, ssp);
+	wrmsrq(MSR_IA32_PL3_SSP, ssp);
 	fpregs_unlock();
 
 	return 0;
@@ -460,7 +460,7 @@ static int wrss_control(bool enable)
 		return 0;
 
 	fpregs_lock_and_load();
-	rdmsrl(MSR_IA32_U_CET, msrval);
+	rdmsrq(MSR_IA32_U_CET, msrval);
 
 	if (enable) {
 		features_set(ARCH_SHSTK_WRSS);
@@ -473,7 +473,7 @@ static int wrss_control(bool enable)
 		msrval &= ~CET_WRSS_EN;
 	}
 
-	wrmsrl(MSR_IA32_U_CET, msrval);
+	wrmsrq(MSR_IA32_U_CET, msrval);
 
 unlock:
 	fpregs_unlock();
@@ -492,8 +492,8 @@ static int shstk_disable(void)
 
 	fpregs_lock_and_load();
 	/* Disable WRSS too when disabling shadow stack */
-	wrmsrl(MSR_IA32_U_CET, 0);
-	wrmsrl(MSR_IA32_PL3_SSP, 0);
+	wrmsrq(MSR_IA32_U_CET, 0);
+	wrmsrq(MSR_IA32_PL3_SSP, 0);
 	fpregs_unlock();
 
 	shstk_free(current);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 5f441039b572..2404233336ab 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -255,7 +255,7 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 
 	if (v8086_mode(regs))
 		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
@@ -423,14 +423,14 @@ bool sigaltstack_size_valid(size_t ss_size)
 	if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
 		return true;
 
-	fsize += current->group_leader->thread.fpu.perm.__user_state_size;
+	fsize += x86_task_fpu(current->group_leader)->perm.__user_state_size;
 	if (likely(ss_size > fsize))
 		return true;
 
 	if (strict_sigaltstack_size)
 		return ss_size > fsize;
 
-	mask = current->group_leader->thread.fpu.perm.__state_perm;
+	mask = x86_task_fpu(current->group_leader)->perm.__state_perm;
 	if (mask & XFEATURE_MASK_USER_DYNAMIC)
 		return ss_size > fsize;
 
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index ef654530bf5a..98123ff10506 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -33,25 +33,55 @@
 #include <asm/smap.h>
 #include <asm/gsseg.h>
 
+/*
+ * The first GDT descriptor is reserved as 'NULL descriptor'.  As bits 0
+ * and 1 of a segment selector, i.e., the RPL bits, are NOT used to index
+ * GDT, selector values 0~3 all point to the NULL descriptor, thus values
+ * 0, 1, 2 and 3 are all valid NULL selector values.
+ *
+ * However IRET zeros ES, FS, GS, and DS segment registers if any of them
+ * is found to have any nonzero NULL selector value, which can be used by
+ * userspace in pre-FRED systems to spot any interrupt/exception by loading
+ * a nonzero NULL selector and waiting for it to become zero.  Before FRED
+ * there was nothing software could do to prevent such an information leak.
+ *
+ * ERETU, the only legit instruction to return to userspace from kernel
+ * under FRED, by design does NOT zero any segment register to avoid this
+ * problem behavior.
+ *
+ * As such, leave NULL selector values 0~3 unchanged.
+ */
+static inline u16 fixup_rpl(u16 sel)
+{
+	return sel <= 3 ? sel : sel | 3;
+}
+
 #ifdef CONFIG_IA32_EMULATION
 #include <asm/unistd_32_ia32.h>
 
 static inline void reload_segments(struct sigcontext_32 *sc)
 {
-	unsigned int cur;
+	u16 cur;
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
 	savesegment(gs, cur);
-	if ((sc->gs | 0x03) != cur)
-		load_gs_index(sc->gs | 0x03);
+	if (fixup_rpl(sc->gs) != cur)
+		load_gs_index(fixup_rpl(sc->gs));
 	savesegment(fs, cur);
-	if ((sc->fs | 0x03) != cur)
-		loadsegment(fs, sc->fs | 0x03);
+	if (fixup_rpl(sc->fs) != cur)
+		loadsegment(fs, fixup_rpl(sc->fs));
+
 	savesegment(ds, cur);
-	if ((sc->ds | 0x03) != cur)
-		loadsegment(ds, sc->ds | 0x03);
+	if (fixup_rpl(sc->ds) != cur)
+		loadsegment(ds, fixup_rpl(sc->ds));
 	savesegment(es, cur);
-	if ((sc->es | 0x03) != cur)
-		loadsegment(es, sc->es | 0x03);
+	if (fixup_rpl(sc->es) != cur)
+		loadsegment(es, fixup_rpl(sc->es));
 }
 
 #define sigset32_t			compat_sigset_t
@@ -105,18 +135,12 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs,
 	regs->orig_ax = -1;
 
 #ifdef CONFIG_IA32_EMULATION
-	/*
-	 * Reload fs and gs if they have changed in the signal
-	 * handler.  This does not handle long fs/gs base changes in
-	 * the handler, but does not clobber them at least in the
-	 * normal case.
-	 */
 	reload_segments(&sc);
 #else
-	loadsegment(gs, sc.gs);
-	regs->fs = sc.fs;
-	regs->es = sc.es;
-	regs->ds = sc.ds;
+	loadsegment(gs, fixup_rpl(sc.gs));
+	regs->fs = fixup_rpl(sc.fs);
+	regs->es = fixup_rpl(sc.es);
+	regs->ds = fixup_rpl(sc.ds);
 #endif
 
 	return fpu__restore_sig(compat_ptr(sc.fpstate), 1);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f09..b90d872aa0c8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -64,7 +64,7 @@
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/desc.h>
 #include <asm/nmi.h>
 #include <asm/irq.h>
@@ -190,7 +190,7 @@ static void ap_starting(void)
 	apic_ap_setup();
 
 	/* Save the processor parameters. */
-	smp_store_cpu_info(cpuid);
+	identify_secondary_cpu(cpuid);
 
 	/*
 	 * The topology information must be up to date before
@@ -215,7 +215,7 @@ static void ap_calibrate_delay(void)
 {
 	/*
 	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
-	 * smp_store_cpu_info() stored a value that is close but not as
+	 * identify_secondary_cpu() stored a value that is close but not as
 	 * accurate as the value just calculated.
 	 *
 	 * As this is invoked after the TSC synchronization check,
@@ -229,7 +229,7 @@ static void ap_calibrate_delay(void)
 /*
  * Activate a secondary processor.
  */
-static void notrace start_secondary(void *unused)
+static void notrace __noendbr start_secondary(void *unused)
 {
 	/*
 	 * Don't put *anything* except direct CPU state initialization
@@ -314,26 +314,7 @@ static void notrace start_secondary(void *unused)
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
-
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	/* Copy boot_cpu_data only on the first bringup */
-	if (!c->initialized)
-		*c = boot_cpu_data;
-	c->cpu_index = id;
-	/*
-	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up an AP.
-	 */
-	identify_secondary_cpu(c);
-	c->initialized = true;
-}
+ANNOTATE_NOENDBR_SYM(start_secondary);
 
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -654,10 +635,9 @@ static void impress_friends(void)
  * But that slows boot and resume on modern processors, which include
  * many cores and don't require that delay.
  *
- * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
- * Modern processor families are quirked to remove the delay entirely.
+ * Cmdline "cpu_init_udelay=" is available to override this delay.
  */
-#define UDELAY_10MS_DEFAULT 10000
+#define UDELAY_10MS_LEGACY 10000
 
 static unsigned int init_udelay = UINT_MAX;
 
@@ -669,21 +649,21 @@ static int __init cpu_init_udelay(char *str)
 }
 early_param("cpu_init_udelay", cpu_init_udelay);
 
-static void __init smp_quirk_init_udelay(void)
+static void __init smp_set_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
 	if (init_udelay != UINT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
-	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON && boot_cpu_data.x86 >= 0x18) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD   && boot_cpu_data.x86 >= 0xF)) {
 		init_udelay = 0;
 		return;
 	}
 	/* else, use legacy delay */
-	init_udelay = UDELAY_10MS_DEFAULT;
+	init_udelay = UDELAY_10MS_LEGACY;
 }
 
 /*
@@ -841,7 +821,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(pcpu_hot.current_task, cpu) = idle;
+	per_cpu(current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
@@ -851,7 +831,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
+	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #endif
 	return 0;
 }
@@ -1094,7 +1074,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	uv_system_init();
 
-	smp_quirk_init_udelay();
+	smp_set_init_udelay();
 
 	speculative_store_bypass_ht_init();
 
@@ -1208,6 +1188,12 @@ void cpu_disable_common(void)
 
 	remove_siblinginfo(cpu);
 
+	/*
+	 * Stop allowing kernel-mode FPU. This is needed so that if the CPU is
+	 * brought online again, the initial state is not allowed:
+	 */
+	this_cpu_write(kernel_fpu_allowed, false);
+
 	/* It's now safe to remove this processor from the online map */
 	lock_vector_lock();
 	remove_cpu_from_maps(cpu);
@@ -1262,43 +1248,9 @@ void play_dead_common(void)
  * We need to flush the caches before going to sleep, lest we have
  * dirty data in our caches when we come back up.
  */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1319,7 +1271,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1391,9 +1343,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 9e51242ed125..378c388d1b31 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 		break;
 
 	case RET:
-		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		if (cpu_wants_rethunk_at(insn))
 			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
@@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 	case JCC:
 		if (!func) {
 			func = __static_call_return;
-			if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			if (cpu_wants_rethunk())
 				func = x86_return_thunk;
 		}
 
@@ -108,7 +108,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 	if (system_state == SYSTEM_BOOTING || modinit)
 		return text_poke_early(insn, code, size);
 
-	text_poke_bp(insn, code, size, emulate);
+	smp_text_poke_single(insn, code, size, emulate);
 }
 
 static void __static_call_validate(u8 *insn, bool tail, bool tramp)
@@ -158,7 +158,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	mutex_lock(&text_mutex);
 
-	if (tramp) {
+	if (tramp && !site) {
 		__static_call_validate(tramp, true, true);
 		__static_call_transform(tramp, __sc_insn(!func, true), func, false);
 	}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 4c1bcb6053fc..46b8f1f16676 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -200,8 +200,7 @@ static int tboot_setup_sleep(void)
 	tboot->num_mac_regions = 0;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
-		if ((e820_table->entries[i].type != E820_TYPE_RAM)
-		 && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN))
+		if (e820_table->entries[i].type != E820_TYPE_RAM)
 			continue;
 
 		add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size);
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
index b8e7abe00b06..708d61743d15 100644
--- a/arch/x86/kernel/trace_clock.c
+++ b/arch/x86/kernel/trace_clock.c
@@ -4,7 +4,7 @@
  */
 #include <asm/trace_clock.h>
 #include <asm/barrier.h>
-#include <asm/msr.h>
+#include <asm/tsc.h>
 
 /*
  * trace_clock_x86_tsc(): A clock that is just the cycle counter.
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
deleted file mode 100644
index 03ae1caaa878..000000000000
--- a/arch/x86/kernel/tracepoint.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com>
- */
-#include <linux/jump_label.h>
-#include <linux/atomic.h>
-
-#include <asm/trace/exceptions.h>
-
-DEFINE_STATIC_KEY_FALSE(trace_pagefault_key);
-
-int trace_pagefault_reg(void)
-{
-	static_branch_inc(&trace_pagefault_key);
-	return 0;
-}
-
-void trace_pagefault_unreg(void)
-{
-	static_branch_dec(&trace_pagefault_key);
-}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2dbadf347b5f..94c0236963c6 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -68,6 +68,7 @@
 #include <asm/vdso.h>
 #include <asm/tdx.h>
 #include <asm/cfi.h>
+#include <asm/msr.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -94,10 +95,20 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
 
 /*
  * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
- * If it's a UD1, get the ModRM byte to pass along to UBSan.
+ * If it's a UD1, further decode to determine its use:
+ *
+ * FineIBT:      ea                      (bad)
+ * FineIBT:      f0 75 f9                lock jne . - 6
+ * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
+ * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
+ * static_call:  0f b9 cc                ud1    %esp,%ecx
+ *
+ * Notably UBSAN uses EAX, static_call uses ECX.
  */
-__always_inline int decode_bug(unsigned long addr, u32 *imm)
+__always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 {
+	unsigned long start = addr;
+	bool lock = false;
 	u8 v;
 
 	if (addr < TASK_SIZE_MAX)
@@ -106,28 +117,67 @@ __always_inline int decode_bug(unsigned long addr, u32 *imm)
 	v = *(u8 *)(addr++);
 	if (v == INSN_ASOP)
 		v = *(u8 *)(addr++);
-	if (v != OPCODE_ESCAPE)
+
+	if (v == INSN_LOCK) {
+		lock = true;
+		v = *(u8 *)(addr++);
+	}
+
+	switch (v) {
+	case 0x70 ... 0x7f: /* Jcc.d8 */
+		addr += 1; /* d8 */
+		*len = addr - start;
+		WARN_ON_ONCE(!lock);
+		return BUG_LOCK;
+
+	case 0xea:
+		*len = addr - start;
+		return BUG_EA;
+
+	case OPCODE_ESCAPE:
+		break;
+
+	default:
 		return BUG_NONE;
+	}
 
 	v = *(u8 *)(addr++);
-	if (v == SECOND_BYTE_OPCODE_UD2)
+	if (v == SECOND_BYTE_OPCODE_UD2) {
+		*len = addr - start;
 		return BUG_UD2;
+	}
 
-	if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1)
+	if (v != SECOND_BYTE_OPCODE_UD1)
 		return BUG_NONE;
 
-	/* Retrieve the immediate (type value) for the UBSAN UD1 */
-	v = *(u8 *)(addr++);
-	if (X86_MODRM_RM(v) == 4)
-		addr++;
-
 	*imm = 0;
-	if (X86_MODRM_MOD(v) == 1)
-		*imm = *(u8 *)addr;
-	else if (X86_MODRM_MOD(v) == 2)
-		*imm = *(u32 *)addr;
-	else
-		WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v));
+	v = *(u8 *)(addr++);		/* ModRM */
+
+	if (X86_MODRM_MOD(v) != 3 && X86_MODRM_RM(v) == 4)
+		addr++;			/* SIB */
+
+	/* Decode immediate, if present */
+	switch (X86_MODRM_MOD(v)) {
+	case 0: if (X86_MODRM_RM(v) == 5)
+			addr += 4; /* RIP + disp32 */
+		break;
+
+	case 1: *imm = *(s8 *)addr;
+		addr += 1;
+		break;
+
+	case 2: *imm = *(s32 *)addr;
+		addr += 4;
+		break;
+
+	case 3: break;
+	}
+
+	/* record instruction length */
+	*len = addr - start;
+
+	if (X86_MODRM_REG(v) == 0)	/* EAX */
+		return BUG_UD1_UBSAN;
 
 	return BUG_UD1;
 }
@@ -257,11 +307,12 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 
 static noinstr bool handle_bug(struct pt_regs *regs)
 {
+	unsigned long addr = regs->ip;
 	bool handled = false;
-	int ud_type;
-	u32 imm;
+	int ud_type, ud_len;
+	s32 ud_imm;
 
-	ud_type = decode_bug(regs->ip, &imm);
+	ud_type = decode_bug(addr, &ud_imm, &ud_len);
 	if (ud_type == BUG_NONE)
 		return handled;
 
@@ -281,15 +332,47 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (ud_type == BUG_UD2) {
-		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
-		    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
-			regs->ip += LEN_UD2;
+
+	switch (ud_type) {
+	case BUG_UD2:
+		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+			handled = true;
+			break;
+		}
+		fallthrough;
+
+	case BUG_EA:
+	case BUG_LOCK:
+		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 			handled = true;
+			break;
+		}
+		break;
+
+	case BUG_UD1_UBSAN:
+		if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
+			pr_crit("%s at %pS\n",
+				report_ubsan_failure(regs, ud_imm),
+				(void *)regs->ip);
 		}
-	} else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
-		pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip);
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * When continuing, and regs->ip hasn't changed, move it to the next
+	 * instruction. When not continuing execution, restore the instruction
+	 * pointer.
+	 */
+	if (handled) {
+		if (regs->ip == addr)
+			regs->ip += ud_len;
+	} else {
+		regs->ip = addr;
 	}
+
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();
 	instrumentation_end();
@@ -380,6 +463,21 @@ __visible void __noreturn handle_stack_overflow(struct pt_regs *regs,
 #endif
 
 /*
+ * Prevent the compiler and/or objtool from marking the !CONFIG_X86_ESPFIX64
+ * version of exc_double_fault() as noreturn.  Otherwise the noreturn mismatch
+ * between configs triggers objtool warnings.
+ *
+ * This is a temporary hack until we have compiler or plugin support for
+ * annotating noreturns.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+#define always_true() true
+#else
+bool always_true(void);
+bool __weak always_true(void) { return true; }
+#endif
+
+/*
  * Runs on an IST stack for x86_64 and on a special task stack for x86_32.
  *
  * On x86_64, this is more or less a normal kernel entry.  Notwithstanding the
@@ -514,7 +612,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 
 	pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
 	die("double fault", regs, error_code);
-	panic("Machine halted.");
+	if (always_true())
+		panic("Machine halted.");
 	instrumentation_end();
 }
 
@@ -651,7 +750,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (current->pasid_activated)
 		return false;
 
-	wrmsrl(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
+	wrmsrq(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
 	current->pasid_activated = 1;
 
 	return true;
@@ -784,16 +883,16 @@ static void do_int3_user(struct pt_regs *regs)
 DEFINE_IDTENTRY_RAW(exc_int3)
 {
 	/*
-	 * poke_int3_handler() is completely self contained code; it does (and
+	 * smp_text_poke_int3_handler() is completely self contained code; it does (and
 	 * must) *NOT* call out to anything, lest it hits upon yet another
 	 * INT3.
 	 */
-	if (poke_int3_handler(regs))
+	if (smp_text_poke_int3_handler(regs))
 		return;
 
 	/*
 	 * irqentry_enter_from_user_mode() uses static_branch_{,un}likely()
-	 * and therefore can trigger INT3, hence poke_int3_handler() must
+	 * and therefore can trigger INT3, hence smp_text_poke_int3_handler() must
 	 * be done before. If the entry came from kernel mode, then use
 	 * nmi_enter() because the INT3 could have been hit in any context
 	 * including NMI.
@@ -1022,9 +1121,9 @@ static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6)
 		 */
 		unsigned long debugctl;
 
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 		debugctl |= DEBUGCTLMSR_BTF;
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	}
 
 	/*
@@ -1197,7 +1296,7 @@ DEFINE_IDTENTRY_RAW(exc_debug)
 static void math_error(struct pt_regs *regs, int trapnr)
 {
 	struct task_struct *task = current;
-	struct fpu *fpu = &task->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(task);
 	int si_code;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
@@ -1288,11 +1387,11 @@ static bool handle_xfd_event(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD))
 		return false;
 
-	rdmsrl(MSR_IA32_XFD_ERR, xfd_err);
+	rdmsrq(MSR_IA32_XFD_ERR, xfd_err);
 	if (!xfd_err)
 		return false;
 
-	wrmsrl(MSR_IA32_XFD_ERR, 0);
+	wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/* Die if that happens in kernel space */
 	if (WARN_ON(!user_mode(regs)))
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 34dec0b72ea8..87e749106dda 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -16,7 +16,7 @@
 #include <linux/static_key.h>
 #include <linux/static_call.h>
 
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/hpet.h>
 #include <asm/timer.h>
 #include <asm/vgtod.h>
@@ -29,6 +29,7 @@
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
 #include <asm/i8259.h>
+#include <asm/msr.h>
 #include <asm/topology.h>
 #include <asm/uv/uv.h>
 #include <asm/sev.h>
@@ -959,7 +960,7 @@ static unsigned long long cyc2ns_suspend;
 
 void tsc_save_sched_clock_state(void)
 {
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	cyc2ns_suspend = sched_clock();
@@ -979,7 +980,7 @@ void tsc_restore_sched_clock_state(void)
 	unsigned long flags;
 	int cpu;
 
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	local_irq_save(flags);
@@ -1098,7 +1099,7 @@ static void __init detect_art(void)
 	if (art_base_clk.denominator < ART_MIN_DENOMINATOR)
 		return;
 
-	rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset);
+	rdmsrq(MSR_IA32_TSC_ADJUST, art_base_clk.offset);
 
 	/* Make this sticky over multiple CPU init calls */
 	setup_force_cpu_cap(X86_FEATURE_ART);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index deeb02825670..48e6cc1cb017 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -152,7 +152,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&freq_desc_byt),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&freq_desc_tng),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&freq_desc_cht),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&freq_desc_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&freq_desc_ann),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,	&freq_desc_lgm),
 	{}
 };
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 4334033658ed..ec3aa340d351 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <asm/msr.h>
 #include <asm/tsc.h>
 
 struct tsc_adjust {
@@ -65,12 +66,12 @@ void tsc_verify_tsc_adjust(bool resume)
 
 	adj->nextcheck = jiffies + HZ;
 
-	rdmsrl(MSR_IA32_TSC_ADJUST, curval);
+	rdmsrq(MSR_IA32_TSC_ADJUST, curval);
 	if (adj->adjusted == curval)
 		return;
 
 	/* Restore the original value */
-	wrmsrl(MSR_IA32_TSC_ADJUST, adj->adjusted);
+	wrmsrq(MSR_IA32_TSC_ADJUST, adj->adjusted);
 
 	if (!adj->warned || resume) {
 		pr_warn(FW_BUG "TSC ADJUST differs: CPU%u %lld --> %lld. Restoring\n",
@@ -142,7 +143,7 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 		if (likely(!tsc_async_resets)) {
 			pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n",
 				cpu, bootval);
-			wrmsrl(MSR_IA32_TSC_ADJUST, 0);
+			wrmsrq(MSR_IA32_TSC_ADJUST, 0);
 			bootval = 0;
 		} else {
 			pr_info("TSC ADJUST: CPU%u: %lld NOT forced to 0\n",
@@ -165,7 +166,7 @@ bool __init tsc_store_and_check_tsc_adjust(bool bootcpu)
 	if (check_tsc_unstable())
 		return false;
 
-	rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
+	rdmsrq(MSR_IA32_TSC_ADJUST, bootval);
 	cur->bootval = bootval;
 	cur->nextcheck = jiffies + HZ;
 	tsc_sanitize_first_cpu(cur, bootval, smp_processor_id(), bootcpu);
@@ -187,7 +188,7 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
 	if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
 		return false;
 
-	rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
+	rdmsrq(MSR_IA32_TSC_ADJUST, bootval);
 	cur->bootval = bootval;
 	cur->nextcheck = jiffies + HZ;
 	cur->warned = false;
@@ -229,7 +230,7 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
 	 */
 	if (bootval != ref->adjusted) {
 		cur->adjusted = ref->adjusted;
-		wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted);
+		wrmsrq(MSR_IA32_TSC_ADJUST, ref->adjusted);
 	}
 	/*
 	 * We have the TSCs forced to be in sync on this package. Skip sync
@@ -518,7 +519,7 @@ retry:
 	pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n",
 		cpu, cur_max_warp, cur->adjusted);
 
-	wrmsrl(MSR_IA32_TSC_ADJUST, cur->adjusted);
+	wrmsrq(MSR_IA32_TSC_ADJUST, cur->adjusted);
 	goto retry;
 
 }
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index d4705a348a80..977ee75e047c 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -476,7 +476,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	/* Don't let modules unload while we're reading their ORC data. */
-	preempt_disable();
+	guard(rcu)();
 
 	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
@@ -669,14 +669,12 @@ bool unwind_next_frame(struct unwind_state *state)
 		goto err;
 	}
 
-	preempt_enable();
 	return true;
 
 err:
 	state->error = true;
 
 the_end:
-	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5a952c5ea66b..6d383839e839 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,19 +357,23 @@ void *arch_uprobe_trampoline(unsigned long *psize)
 	return &insn;
 }
 
-static unsigned long trampoline_check_ip(void)
+static unsigned long trampoline_check_ip(unsigned long tramp)
 {
-	unsigned long tramp = uprobe_get_trampoline_vaddr();
-
 	return tramp + (uretprobe_syscall_check - uretprobe_trampoline_entry);
 }
 
 SYSCALL_DEFINE0(uretprobe)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	unsigned long err, ip, sp, r11_cx_ax[3];
+	unsigned long err, ip, sp, r11_cx_ax[3], tramp;
+
+	/* If there's no trampoline, we are called from wrong place. */
+	tramp = uprobe_get_trampoline_vaddr();
+	if (unlikely(tramp == UPROBE_NO_TRAMPOLINE_VADDR))
+		goto sigill;
 
-	if (regs->ip != trampoline_check_ip())
+	/* Make sure the ip matches the only allowed sys_uretprobe caller. */
+	if (unlikely(regs->ip != trampoline_check_ip(tramp)))
 		goto sigill;
 
 	err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
@@ -836,6 +840,11 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	insn_byte_t p;
 	int i;
 
+	/* x86_nops[insn->length]; same as jmp with .offs = 0 */
+	if (insn->length <= ASM_NOP_MAX &&
+	    !memcmp(insn->kaddr, x86_nops[insn->length], insn->length))
+		goto setup;
+
 	switch (opc1) {
 	case 0xeb:	/* jmp 8 */
 	case 0xe9:	/* jmp 32 */
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 1258a5872d12..37ad43792452 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -29,8 +29,12 @@
  */
 
 #include <asm/cpufeatures.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/msr-index.h>
 
+#define SSE_MASK	\
+	(REQUIRED_MASK0 & ((1<<(X86_FEATURE_XMM & 31)) | (1<<(X86_FEATURE_XMM2 & 31))))
+
 SYM_FUNC_START_LOCAL(verify_cpu)
 	pushf				# Save caller passed flags
 	push	$0			# Kill any dangerous flags
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0deb4887d6e9..4fa0be732af1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -43,7 +43,8 @@ ENTRY(phys_startup_64)
 #endif
 
 jiffies = jiffies_64;
-const_pcpu_hot = pcpu_hot;
+const_current_task = current_task;
+const_cpu_current_top_of_stack = cpu_current_top_of_stack;
 
 #if defined(CONFIG_X86_64)
 /*
@@ -78,11 +79,13 @@ const_pcpu_hot = pcpu_hot;
 #define BSS_DECRYPTED						\
 	. = ALIGN(PMD_SIZE);					\
 	__start_bss_decrypted = .;				\
+	__pi___start_bss_decrypted = .;				\
 	*(.bss..decrypted);					\
 	. = ALIGN(PAGE_SIZE);					\
 	__start_bss_decrypted_unused = .;			\
 	. = ALIGN(PMD_SIZE);					\
 	__end_bss_decrypted = .;				\
+	__pi___end_bss_decrypted = .;				\
 
 #else
 
@@ -112,12 +115,6 @@ ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(6);        /* RW_ */
-#endif
-	init PT_LOAD FLAGS(7);          /* RWE */
-#endif
 	note PT_NOTE FLAGS(0);          /* ___ */
 }
 
@@ -133,6 +130,7 @@ SECTIONS
 	/* Text and read-only data */
 	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
 		_text = .;
+		__pi__text = .;
 		_stext = .;
 		ALIGN_ENTRY_TEXT_BEGIN
 		*(.text..__x86.rethunk_untrain)
@@ -193,6 +191,8 @@ SECTIONS
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
 
+		CACHE_HOT_DATA(L1_CACHE_BYTES)
+
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 
 		DATA_DATA
@@ -216,21 +216,7 @@ SECTIONS
 		__init_begin = .; /* paired with __init_end */
 	}
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
-	/*
-	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-	 * output PHDR, so the next output section - .init.text - should
-	 * start another segment - init.
-	 */
-	PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
-	ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
-	       "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
 	INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
-	:init
-#endif
 
 	/*
 	 * Section for code used exclusively before alternatives are run. All
@@ -347,9 +333,8 @@ SECTIONS
 		EXIT_DATA
 	}
 
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot data too large")
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
@@ -409,6 +394,7 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
+	__pi__end = .;
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	/*
@@ -484,28 +470,23 @@ SECTIONS
 }
 
 /*
- * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause
+ * this.  Let's assume that nobody will be running a COMPILE_TEST kernel and
+ * let's assert that fuller build coverage is more valuable than being able to
+ * run a COMPILE_TEST kernel.
+ */
+#ifndef CONFIG_COMPILE_TEST
+/*
+ * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility:
  */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
+#endif
 
 /* needed for Clang - see arch/x86/entry/entry.S */
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 
 #ifdef CONFIG_X86_64
-/*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(fixed_percpu_data);
-INIT_PER_CPU(irq_stack_backing_store);
-
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
-           "fixed_percpu_data is not at start of per-cpu area");
-#endif
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
@@ -528,6 +509,16 @@ INIT_PER_CPU(irq_stack_backing_store);
 		"SRSO function pair won't alias");
 #endif
 
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline");
+. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart");
+. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array");
+#endif
+
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline");
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index ea2c4f21c1ca..fe8ea8c097de 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -22,6 +22,7 @@ config KVM_X86
 	select KVM_COMMON
 	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_ELIDE_TLB_FLUSH_IF_YOUNG
+	select KVM_MMU_LOCKLESS_AGING
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_DIRTY_RING_TSO
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8eb3a88707f2..ecd85f4801cc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -21,7 +21,7 @@
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
 #include <asm/sgx.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"
@@ -58,25 +58,24 @@ void __init kvm_init_xstate_sizes(void)
 
 u32 xstate_required_size(u64 xstate_bv, bool compacted)
 {
-	int feature_bit = 0;
 	u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+	int i;
 
 	xstate_bv &= XFEATURE_MASK_EXTEND;
-	while (xstate_bv) {
-		if (xstate_bv & 0x1) {
-			struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit];
-			u32 offset;
-
-			/* ECX[1]: 64B alignment in compacted form */
-			if (compacted)
-				offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret;
-			else
-				offset = xs->ebx;
-			ret = max(ret, offset + xs->eax);
-		}
+	for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes) && xstate_bv; i++) {
+		struct cpuid_xstate_sizes *xs = &xstate_sizes[i];
+		u32 offset;
 
-		xstate_bv >>= 1;
-		feature_bit++;
+		if (!(xstate_bv & BIT_ULL(i)))
+			continue;
+
+		/* ECX[1]: 64B alignment in compacted form */
+		if (compacted)
+			offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret;
+		else
+			offset = xs->ebx;
+		ret = max(ret, offset + xs->eax);
+		xstate_bv &= ~BIT_ULL(i);
 	}
 
 	return ret;
@@ -196,6 +195,7 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu)
 }
 
 static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu);
+static void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
 
 /* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */
 static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
@@ -236,7 +236,7 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp
 	struct kvm_cpuid_entry2 *entry;
 	u32 base;
 
-	for_each_possible_hypervisor_cpuid_base(base) {
+	for_each_possible_cpuid_base_hypervisor(base) {
 		entry = kvm_find_cpuid_entry(vcpu, base);
 
 		if (entry) {
@@ -300,10 +300,12 @@ static __always_inline void kvm_update_feature_runtime(struct kvm_vcpu *vcpu,
 	guest_cpu_cap_change(vcpu, x86_feature, has_feature);
 }
 
-void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+static void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	vcpu->arch.cpuid_dynamic_bits_dirty = false;
+
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best) {
 		kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSXSAVE,
@@ -333,7 +335,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 }
-EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static bool kvm_cpuid_has_hyperv(struct kvm_vcpu *vcpu)
 {
@@ -646,6 +647,9 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 	if (cpuid->nent < vcpu->arch.cpuid_nent)
 		return -E2BIG;
 
+	if (vcpu->arch.cpuid_dynamic_bits_dirty)
+		kvm_update_cpuid_runtime(vcpu);
+
 	if (copy_to_user(entries, vcpu->arch.cpuid_entries,
 			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
 		return -EFAULT;
@@ -1423,8 +1427,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		}
 		break;
 	case 0xa: { /* Architectural Performance Monitoring */
-		union cpuid10_eax eax;
-		union cpuid10_edx edx;
+		union cpuid10_eax eax = { };
+		union cpuid10_edx edx = { };
 
 		if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) {
 			entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
@@ -1440,8 +1444,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		if (kvm_pmu_cap.version)
 			edx.split.anythread_deprecated = 1;
-		edx.split.reserved1 = 0;
-		edx.split.reserved2 = 0;
 
 		entry->eax = eax.full;
 		entry->ebx = kvm_pmu_cap.events_mask;
@@ -1704,7 +1706,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			phys_as = entry->eax & 0xff;
 			g_phys_as = phys_as;
 			if (kvm_mmu_get_max_tdp_level() < 5)
-				g_phys_as = min(g_phys_as, 48);
+				g_phys_as = min(g_phys_as, 48U);
 		}
 
 		entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16);
@@ -1759,23 +1761,17 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		break;
 	/* AMD Extended Performance Monitoring and Debug */
 	case 0x80000022: {
-		union cpuid_0x80000022_ebx ebx;
+		union cpuid_0x80000022_ebx ebx = { };
 
 		entry->ecx = entry->edx = 0;
 		if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) {
-			entry->eax = entry->ebx;
+			entry->eax = entry->ebx = 0;
 			break;
 		}
 
 		cpuid_entry_override(entry, CPUID_8000_0022_EAX);
 
-		if (kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2))
-			ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp;
-		else if (kvm_cpu_cap_has(X86_FEATURE_PERFCTR_CORE))
-			ebx.split.num_core_pmc = AMD64_NUM_COUNTERS_CORE;
-		else
-			ebx.split.num_core_pmc = AMD64_NUM_COUNTERS;
-
+		ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp;
 		entry->ebx = ebx.full;
 		break;
 	}
@@ -1985,6 +1981,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	struct kvm_cpuid_entry2 *entry;
 	bool exact, used_max_basic = false;
 
+	if (vcpu->arch.cpuid_dynamic_bits_dirty)
+		kvm_update_cpuid_runtime(vcpu);
+
 	entry = kvm_find_cpuid_entry_index(vcpu, function, index);
 	exact = !!entry;
 
@@ -2000,12 +1999,29 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 		*edx = entry->edx;
 		if (function == 7 && index == 0) {
 			u64 data;
-		        if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
+			if ((*ebx & (feature_bit(RTM) | feature_bit(HLE))) &&
+			    !__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
 			    (data & TSX_CTRL_CPUID_CLEAR))
 				*ebx &= ~(feature_bit(RTM) | feature_bit(HLE));
 		} else if (function == 0x80000007) {
 			if (kvm_hv_invtsc_suppressed(vcpu))
 				*edx &= ~feature_bit(CONSTANT_TSC);
+		} else if (IS_ENABLED(CONFIG_KVM_XEN) &&
+			   kvm_xen_is_tsc_leaf(vcpu, function)) {
+			/*
+			 * Update guest TSC frequency information if necessary.
+			 * Ignore failures, there is no sane value that can be
+			 * provided if KVM can't get the TSC frequency.
+			 */
+			if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu))
+				kvm_guest_time_update(vcpu);
+
+			if (index == 1) {
+				*ecx = vcpu->arch.pvclock_tsc_mul;
+				*edx = vcpu->arch.pvclock_tsc_shift;
+			} else if (index == 2) {
+				*eax = vcpu->arch.hw_tsc_khz;
+			}
 		}
 	} else {
 		*eax = *ebx = *ecx = *edx = 0;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 67d80aa72d50..d2884162a46a 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -11,7 +11,6 @@ extern u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
 void kvm_set_cpu_caps(void);
 
 void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu);
-void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu,
 						    u32 function, u32 index);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
@@ -232,6 +231,14 @@ static __always_inline bool guest_cpu_cap_has(struct kvm_vcpu *vcpu,
 {
 	unsigned int x86_leaf = __feature_leaf(x86_feature);
 
+	/*
+	 * Except for MWAIT, querying dynamic feature bits is disallowed, so
+	 * that KVM can defer runtime updates until the next CPUID emulation.
+	 */
+	BUILD_BUG_ON(x86_feature == X86_FEATURE_APIC ||
+		     x86_feature == X86_FEATURE_OSXSAVE ||
+		     x86_feature == X86_FEATURE_OSPKE);
+
 	return vcpu->arch.cpu_caps[x86_leaf] & __feature_bit(x86_feature);
 }
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 60986f67c35a..1349e278cd2a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -477,8 +477,11 @@ static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
 		.dst_val    = ctxt->dst.val64,
 		.src_bytes  = ctxt->src.bytes,
 		.dst_bytes  = ctxt->dst.bytes,
+		.src_type   = ctxt->src.type,
+		.dst_type   = ctxt->dst.type,
 		.ad_bytes   = ctxt->ad_bytes,
-		.next_rip   = ctxt->eip,
+		.rip	    = ctxt->eip,
+		.next_rip   = ctxt->_eip,
 	};
 
 	return ctxt->ops->intercept(ctxt, &info, stage);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 6ebeb6cea6c0..24f0318c50d7 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -952,8 +952,7 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
 {
 	memset(stimer, 0, sizeof(*stimer));
 	stimer->index = timer_index;
-	hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	stimer->timer.function = stimer_timer_callback;
+	hrtimer_setup(&stimer->timer, stimer_timer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	stimer_prepare_msg(stimer);
 }
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index d7ab8780ab9e..739aa6c0d0c3 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -690,8 +690,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pit->kvm = kvm;
 
 	pit_state = &pit->pit_state;
-	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	pit_state->timer.function = pit_timer_fn;
+	hrtimer_setup(&pit_state->timer, pit_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 8dec646e764b..a8fb19940975 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -567,7 +567,7 @@ static void pic_irq_request(struct kvm *kvm, int level)
 {
 	struct kvm_pic *s = kvm->arch.vpic;
 
-	if (!s->output)
+	if (!s->output && level)
 		s->wakeup_needed = true;
 	s->output = level;
 }
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 73072585e164..c1df5acfacaf 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -44,7 +44,10 @@ struct x86_instruction_info {
 	u64 dst_val;            /* value of destination operand         */
 	u8  src_bytes;          /* size of source operand               */
 	u8  dst_bytes;          /* size of destination operand          */
+	u8  src_type;		/* type of source operand		*/
+	u8  dst_type;		/* type of destination operand		*/
 	u8  ad_bytes;           /* size of src/dst address              */
+	u64 rip;		/* rip of the instruction		*/
 	u64 next_rip;           /* rip following the instruction        */
 };
 
@@ -272,8 +275,10 @@ struct operand {
 	};
 };
 
+#define X86_MAX_INSTRUCTION_LENGTH	15
+
 struct fetch_cache {
-	u8 data[15];
+	u8 data[X86_MAX_INSTRUCTION_LENGTH];
 	u8 *ptr;
 	u8 *end;
 };
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a009c94c26c2..28e3317124fd 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -221,13 +221,6 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 	}
 }
 
-static void kvm_apic_map_free(struct rcu_head *rcu)
-{
-	struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu);
-
-	kvfree(map);
-}
-
 static int kvm_recalculate_phys_map(struct kvm_apic_map *new,
 				    struct kvm_vcpu *vcpu,
 				    bool *xapic_id_mismatch)
@@ -489,7 +482,7 @@ out:
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
-		call_rcu(&old->rcu, kvm_apic_map_free);
+		kvfree_rcu(old, rcu);
 
 	kvm_make_scan_ioapic_request(kvm);
 }
@@ -2593,7 +2586,7 @@ static void __kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	vcpu->arch.apic_base = value;
 
 	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE)
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 
 	if (!apic)
 		return;
@@ -2921,9 +2914,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	apic->nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu);
 
-	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_HARD);
-	apic->lapic_timer.timer.function = apic_timer_fn;
+	hrtimer_setup(&apic->lapic_timer.timer, apic_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 	if (lapic_timer_advance)
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 
@@ -3397,9 +3389,9 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
-			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		else
-			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 	}
 	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) {
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
@@ -3408,7 +3400,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 			sipi_vector = apic->sipi_vector;
 			kvm_x86_call(vcpu_deliver_sipi_vector)(vcpu,
 							       sipi_vector);
-			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		}
 	}
 	return 0;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e229a4d..f2b36d32ef40 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 
 static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 {
+	if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+		kvm_mmu_free_obsolete_roots(vcpu);
+
 	/*
 	 * Checking root.hpa is sufficient even when KVM has mirror root.
 	 * We can have either:
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d4ac4a1f8b81..8d1b632e33d2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -501,7 +501,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
 		return false;
 	}
 
-	if (!spte_has_volatile_bits(old_spte))
+	if (!spte_needs_atomic_update(old_spte))
 		__update_clear_spte_fast(sptep, new_spte);
 	else
 		old_spte = __update_clear_spte_slow(sptep, new_spte);
@@ -524,7 +524,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 	int level = sptep_to_sp(sptep)->role.level;
 
 	if (!is_shadow_present_pte(old_spte) ||
-	    !spte_has_volatile_bits(old_spte))
+	    !spte_needs_atomic_update(old_spte))
 		__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 	else
 		old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
@@ -853,32 +853,173 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu
  * About rmap_head encoding:
  *
  * If the bit zero of rmap_head->val is clear, then it points to the only spte
- * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
+ * in this rmap chain. Otherwise, (rmap_head->val & ~3) points to a struct
  * pte_list_desc containing more mappings.
  */
 #define KVM_RMAP_MANY	BIT(0)
 
 /*
+ * rmaps and PTE lists are mostly protected by mmu_lock (the shadow MMU always
+ * operates with mmu_lock held for write), but rmaps can be walked without
+ * holding mmu_lock so long as the caller can tolerate SPTEs in the rmap chain
+ * being zapped/dropped _while the rmap is locked_.
+ *
+ * Other than the KVM_RMAP_LOCKED flag, modifications to rmap entries must be
+ * done while holding mmu_lock for write.  This allows a task walking rmaps
+ * without holding mmu_lock to concurrently walk the same entries as a task
+ * that is holding mmu_lock but _not_ the rmap lock.  Neither task will modify
+ * the rmaps, thus the walks are stable.
+ *
+ * As alluded to above, SPTEs in rmaps are _not_ protected by KVM_RMAP_LOCKED,
+ * only the rmap chains themselves are protected.  E.g. holding an rmap's lock
+ * ensures all "struct pte_list_desc" fields are stable.
+ */
+#define KVM_RMAP_LOCKED	BIT(1)
+
+static unsigned long __kvm_rmap_lock(struct kvm_rmap_head *rmap_head)
+{
+	unsigned long old_val, new_val;
+
+	lockdep_assert_preemption_disabled();
+
+	/*
+	 * Elide the lock if the rmap is empty, as lockless walkers (read-only
+	 * mode) don't need to (and can't) walk an empty rmap, nor can they add
+	 * entries to the rmap.  I.e. the only paths that process empty rmaps
+	 * do so while holding mmu_lock for write, and are mutually exclusive.
+	 */
+	old_val = atomic_long_read(&rmap_head->val);
+	if (!old_val)
+		return 0;
+
+	do {
+		/*
+		 * If the rmap is locked, wait for it to be unlocked before
+		 * trying acquire the lock, e.g. to avoid bouncing the cache
+		 * line.
+		 */
+		while (old_val & KVM_RMAP_LOCKED) {
+			cpu_relax();
+			old_val = atomic_long_read(&rmap_head->val);
+		}
+
+		/*
+		 * Recheck for an empty rmap, it may have been purged by the
+		 * task that held the lock.
+		 */
+		if (!old_val)
+			return 0;
+
+		new_val = old_val | KVM_RMAP_LOCKED;
+	/*
+	 * Use try_cmpxchg_acquire() to prevent reads and writes to the rmap
+	 * from being reordered outside of the critical section created by
+	 * __kvm_rmap_lock().
+	 *
+	 * Pairs with the atomic_long_set_release() in kvm_rmap_unlock().
+	 *
+	 * For the !old_val case, no ordering is needed, as there is no rmap
+	 * to walk.
+	 */
+	} while (!atomic_long_try_cmpxchg_acquire(&rmap_head->val, &old_val, new_val));
+
+	/*
+	 * Return the old value, i.e. _without_ the LOCKED bit set.  It's
+	 * impossible for the return value to be 0 (see above), i.e. the read-
+	 * only unlock flow can't get a false positive and fail to unlock.
+	 */
+	return old_val;
+}
+
+static unsigned long kvm_rmap_lock(struct kvm *kvm,
+				   struct kvm_rmap_head *rmap_head)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	return __kvm_rmap_lock(rmap_head);
+}
+
+static void __kvm_rmap_unlock(struct kvm_rmap_head *rmap_head,
+			      unsigned long val)
+{
+	KVM_MMU_WARN_ON(val & KVM_RMAP_LOCKED);
+	/*
+	 * Ensure that all accesses to the rmap have completed before unlocking
+	 * the rmap.
+	 *
+	 * Pairs with the atomic_long_try_cmpxchg_acquire() in __kvm_rmap_lock().
+	 */
+	atomic_long_set_release(&rmap_head->val, val);
+}
+
+static void kvm_rmap_unlock(struct kvm *kvm,
+			    struct kvm_rmap_head *rmap_head,
+			    unsigned long new_val)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	__kvm_rmap_unlock(rmap_head, new_val);
+}
+
+static unsigned long kvm_rmap_get(struct kvm_rmap_head *rmap_head)
+{
+	return atomic_long_read(&rmap_head->val) & ~KVM_RMAP_LOCKED;
+}
+
+/*
+ * If mmu_lock isn't held, rmaps can only be locked in read-only mode.  The
+ * actual locking is the same, but the caller is disallowed from modifying the
+ * rmap, and so the unlock flow is a nop if the rmap is/was empty.
+ */
+static unsigned long kvm_rmap_lock_readonly(struct kvm_rmap_head *rmap_head)
+{
+	unsigned long rmap_val;
+
+	preempt_disable();
+	rmap_val = __kvm_rmap_lock(rmap_head);
+
+	if (!rmap_val)
+		preempt_enable();
+
+	return rmap_val;
+}
+
+static void kvm_rmap_unlock_readonly(struct kvm_rmap_head *rmap_head,
+				     unsigned long old_val)
+{
+	if (!old_val)
+		return;
+
+	KVM_MMU_WARN_ON(old_val != kvm_rmap_get(rmap_head));
+
+	__kvm_rmap_unlock(rmap_head, old_val);
+	preempt_enable();
+}
+
+/*
  * Returns the number of pointers in the rmap chain, not counting the new one.
  */
-static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
-			struct kvm_rmap_head *rmap_head)
+static int pte_list_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			u64 *spte, struct kvm_rmap_head *rmap_head)
 {
+	unsigned long old_val, new_val;
 	struct pte_list_desc *desc;
 	int count = 0;
 
-	if (!rmap_head->val) {
-		rmap_head->val = (unsigned long)spte;
-	} else if (!(rmap_head->val & KVM_RMAP_MANY)) {
+	old_val = kvm_rmap_lock(kvm, rmap_head);
+
+	if (!old_val) {
+		new_val = (unsigned long)spte;
+	} else if (!(old_val & KVM_RMAP_MANY)) {
 		desc = kvm_mmu_memory_cache_alloc(cache);
-		desc->sptes[0] = (u64 *)rmap_head->val;
+		desc->sptes[0] = (u64 *)old_val;
 		desc->sptes[1] = spte;
 		desc->spte_count = 2;
 		desc->tail_count = 0;
-		rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY;
+		new_val = (unsigned long)desc | KVM_RMAP_MANY;
 		++count;
 	} else {
-		desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+		desc = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY);
 		count = desc->tail_count + desc->spte_count;
 
 		/*
@@ -887,21 +1028,25 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 		 */
 		if (desc->spte_count == PTE_LIST_EXT) {
 			desc = kvm_mmu_memory_cache_alloc(cache);
-			desc->more = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+			desc->more = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY);
 			desc->spte_count = 0;
 			desc->tail_count = count;
-			rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY;
+			new_val = (unsigned long)desc | KVM_RMAP_MANY;
+		} else {
+			new_val = old_val;
 		}
 		desc->sptes[desc->spte_count++] = spte;
 	}
+
+	kvm_rmap_unlock(kvm, rmap_head, new_val);
+
 	return count;
 }
 
-static void pte_list_desc_remove_entry(struct kvm *kvm,
-				       struct kvm_rmap_head *rmap_head,
+static void pte_list_desc_remove_entry(struct kvm *kvm, unsigned long *rmap_val,
 				       struct pte_list_desc *desc, int i)
 {
-	struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+	struct pte_list_desc *head_desc = (struct pte_list_desc *)(*rmap_val & ~KVM_RMAP_MANY);
 	int j = head_desc->spte_count - 1;
 
 	/*
@@ -928,9 +1073,9 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
 	 * head at the next descriptor, i.e. the new head.
 	 */
 	if (!head_desc->more)
-		rmap_head->val = 0;
+		*rmap_val = 0;
 	else
-		rmap_head->val = (unsigned long)head_desc->more | KVM_RMAP_MANY;
+		*rmap_val = (unsigned long)head_desc->more | KVM_RMAP_MANY;
 	mmu_free_pte_list_desc(head_desc);
 }
 
@@ -938,24 +1083,26 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 			    struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
+	unsigned long rmap_val;
 	int i;
 
-	if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm))
-		return;
+	rmap_val = kvm_rmap_lock(kvm, rmap_head);
+	if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_val, kvm))
+		goto out;
 
-	if (!(rmap_head->val & KVM_RMAP_MANY)) {
-		if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm))
-			return;
+	if (!(rmap_val & KVM_RMAP_MANY)) {
+		if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_val != spte, kvm))
+			goto out;
 
-		rmap_head->val = 0;
+		rmap_val = 0;
 	} else {
-		desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+		desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
 		while (desc) {
 			for (i = 0; i < desc->spte_count; ++i) {
 				if (desc->sptes[i] == spte) {
-					pte_list_desc_remove_entry(kvm, rmap_head,
+					pte_list_desc_remove_entry(kvm, &rmap_val,
 								   desc, i);
-					return;
+					goto out;
 				}
 			}
 			desc = desc->more;
@@ -963,6 +1110,9 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 
 		KVM_BUG_ON_DATA_CORRUPTION(true, kvm);
 	}
+
+out:
+	kvm_rmap_unlock(kvm, rmap_head, rmap_val);
 }
 
 static void kvm_zap_one_rmap_spte(struct kvm *kvm,
@@ -977,17 +1127,19 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
 				   struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc, *next;
+	unsigned long rmap_val;
 	int i;
 
-	if (!rmap_head->val)
+	rmap_val = kvm_rmap_lock(kvm, rmap_head);
+	if (!rmap_val)
 		return false;
 
-	if (!(rmap_head->val & KVM_RMAP_MANY)) {
-		mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val);
+	if (!(rmap_val & KVM_RMAP_MANY)) {
+		mmu_spte_clear_track_bits(kvm, (u64 *)rmap_val);
 		goto out;
 	}
 
-	desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+	desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
 
 	for (; desc; desc = next) {
 		for (i = 0; i < desc->spte_count; i++)
@@ -997,20 +1149,21 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
 	}
 out:
 	/* rmap_head is meaningless now, remember to reset it */
-	rmap_head->val = 0;
+	kvm_rmap_unlock(kvm, rmap_head, 0);
 	return true;
 }
 
 unsigned int pte_list_count(struct kvm_rmap_head *rmap_head)
 {
+	unsigned long rmap_val = kvm_rmap_get(rmap_head);
 	struct pte_list_desc *desc;
 
-	if (!rmap_head->val)
+	if (!rmap_val)
 		return 0;
-	else if (!(rmap_head->val & KVM_RMAP_MANY))
+	else if (!(rmap_val & KVM_RMAP_MANY))
 		return 1;
 
-	desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+	desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
 	return desc->tail_count + desc->spte_count;
 }
 
@@ -1053,6 +1206,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
  */
 struct rmap_iterator {
 	/* private fields */
+	struct rmap_head *head;
 	struct pte_list_desc *desc;	/* holds the sptep if not NULL */
 	int pos;			/* index of the sptep */
 };
@@ -1067,23 +1221,19 @@ struct rmap_iterator {
 static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
 			   struct rmap_iterator *iter)
 {
-	u64 *sptep;
+	unsigned long rmap_val = kvm_rmap_get(rmap_head);
 
-	if (!rmap_head->val)
+	if (!rmap_val)
 		return NULL;
 
-	if (!(rmap_head->val & KVM_RMAP_MANY)) {
+	if (!(rmap_val & KVM_RMAP_MANY)) {
 		iter->desc = NULL;
-		sptep = (u64 *)rmap_head->val;
-		goto out;
+		return (u64 *)rmap_val;
 	}
 
-	iter->desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY);
+	iter->desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
 	iter->pos = 0;
-	sptep = iter->desc->sptes[iter->pos];
-out:
-	BUG_ON(!is_shadow_present_pte(*sptep));
-	return sptep;
+	return iter->desc->sptes[iter->pos];
 }
 
 /*
@@ -1093,14 +1243,11 @@ out:
  */
 static u64 *rmap_get_next(struct rmap_iterator *iter)
 {
-	u64 *sptep;
-
 	if (iter->desc) {
 		if (iter->pos < PTE_LIST_EXT - 1) {
 			++iter->pos;
-			sptep = iter->desc->sptes[iter->pos];
-			if (sptep)
-				goto out;
+			if (iter->desc->sptes[iter->pos])
+				return iter->desc->sptes[iter->pos];
 		}
 
 		iter->desc = iter->desc->more;
@@ -1108,20 +1255,24 @@ static u64 *rmap_get_next(struct rmap_iterator *iter)
 		if (iter->desc) {
 			iter->pos = 0;
 			/* desc->sptes[0] cannot be NULL */
-			sptep = iter->desc->sptes[iter->pos];
-			goto out;
+			return iter->desc->sptes[iter->pos];
 		}
 	}
 
 	return NULL;
-out:
-	BUG_ON(!is_shadow_present_pte(*sptep));
-	return sptep;
 }
 
-#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_)			\
-	for (_spte_ = rmap_get_first(_rmap_head_, _iter_);		\
-	     _spte_; _spte_ = rmap_get_next(_iter_))
+#define __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)	\
+	for (_sptep_ = rmap_get_first(_rmap_head_, _iter_);	\
+	     _sptep_; _sptep_ = rmap_get_next(_iter_))
+
+#define for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+	__for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+		if (!WARN_ON_ONCE(!is_shadow_present_pte(*(_sptep_))))	\
+
+#define for_each_rmap_spte_lockless(_rmap_head_, _iter_, _sptep_, _spte_)	\
+	__for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+		if (is_shadow_present_pte(_spte_ = mmu_spte_get_lockless(sptep)))
 
 static void drop_spte(struct kvm *kvm, u64 *sptep)
 {
@@ -1207,12 +1358,13 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for_each_rmap_spte(rmap_head, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		if (spte_ad_need_write_protect(*sptep))
 			flush |= test_and_clear_bit(PT_WRITABLE_SHIFT,
 						    (unsigned long *)sptep);
 		else
 			flush |= spte_clear_dirty(sptep);
+	}
 
 	return flush;
 }
@@ -1401,7 +1553,7 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
 	while (++iterator->rmap <= iterator->end_rmap) {
 		iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level);
 
-		if (iterator->rmap->val)
+		if (atomic_long_read(&iterator->rmap->val))
 			return;
 	}
 
@@ -1533,7 +1685,7 @@ static void __rmap_add(struct kvm *kvm,
 	kvm_update_page_stats(kvm, sp->role.level, 1);
 
 	rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
-	rmap_count = pte_list_add(cache, spte, rmap_head);
+	rmap_count = pte_list_add(kvm, cache, spte, rmap_head);
 
 	if (rmap_count > kvm->stat.max_mmu_rmap_size)
 		kvm->stat.max_mmu_rmap_size = rmap_count;
@@ -1552,51 +1704,67 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot,
 }
 
 static bool kvm_rmap_age_gfn_range(struct kvm *kvm,
-				   struct kvm_gfn_range *range, bool test_only)
+				   struct kvm_gfn_range *range,
+				   bool test_only)
 {
-	struct slot_rmap_walk_iterator iterator;
+	struct kvm_rmap_head *rmap_head;
 	struct rmap_iterator iter;
+	unsigned long rmap_val;
 	bool young = false;
 	u64 *sptep;
+	gfn_t gfn;
+	int level;
+	u64 spte;
 
-	for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
-				 range->start, range->end - 1, &iterator) {
-		for_each_rmap_spte(iterator.rmap, &iter, sptep) {
-			u64 spte = *sptep;
+	for (level = PG_LEVEL_4K; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		for (gfn = range->start; gfn < range->end;
+		     gfn += KVM_PAGES_PER_HPAGE(level)) {
+			rmap_head = gfn_to_rmap(gfn, level, range->slot);
+			rmap_val = kvm_rmap_lock_readonly(rmap_head);
 
-			if (!is_accessed_spte(spte))
-				continue;
+			for_each_rmap_spte_lockless(rmap_head, &iter, sptep, spte) {
+				if (!is_accessed_spte(spte))
+					continue;
+
+				if (test_only) {
+					kvm_rmap_unlock_readonly(rmap_head, rmap_val);
+					return true;
+				}
 
-			if (test_only)
-				return true;
-
-			if (spte_ad_enabled(spte)) {
-				clear_bit((ffs(shadow_accessed_mask) - 1),
-					(unsigned long *)sptep);
-			} else {
-				/*
-				 * WARN if mmu_spte_update() signals the need
-				 * for a TLB flush, as Access tracking a SPTE
-				 * should never trigger an _immediate_ flush.
-				 */
-				spte = mark_spte_for_access_track(spte);
-				WARN_ON_ONCE(mmu_spte_update(sptep, spte));
+				if (spte_ad_enabled(spte))
+					clear_bit((ffs(shadow_accessed_mask) - 1),
+						  (unsigned long *)sptep);
+				else
+					/*
+					 * If the following cmpxchg fails, the
+					 * spte is being concurrently modified
+					 * and should most likely stay young.
+					 */
+					cmpxchg64(sptep, spte,
+					      mark_spte_for_access_track(spte));
+				young = true;
 			}
-			young = true;
+
+			kvm_rmap_unlock_readonly(rmap_head, rmap_val);
 		}
 	}
 	return young;
 }
 
+static bool kvm_may_have_shadow_mmu_sptes(struct kvm *kvm)
+{
+	return !tdp_mmu_enabled || READ_ONCE(kvm->arch.indirect_shadow_pages);
+}
+
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool young = false;
 
-	if (kvm_memslots_have_rmaps(kvm))
-		young = kvm_rmap_age_gfn_range(kvm, range, false);
-
 	if (tdp_mmu_enabled)
-		young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
+		young = kvm_tdp_mmu_age_gfn_range(kvm, range);
+
+	if (kvm_may_have_shadow_mmu_sptes(kvm))
+		young |= kvm_rmap_age_gfn_range(kvm, range, false);
 
 	return young;
 }
@@ -1605,11 +1773,14 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool young = false;
 
-	if (kvm_memslots_have_rmaps(kvm))
-		young = kvm_rmap_age_gfn_range(kvm, range, true);
-
 	if (tdp_mmu_enabled)
-		young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
+		young = kvm_tdp_mmu_test_age_gfn(kvm, range);
+
+	if (young)
+		return young;
+
+	if (kvm_may_have_shadow_mmu_sptes(kvm))
+		young |= kvm_rmap_age_gfn_range(kvm, range, true);
 
 	return young;
 }
@@ -1656,13 +1827,14 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn)
 	return hash_64(gfn, KVM_MMU_HASH_SHIFT);
 }
 
-static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache,
+static void mmu_page_add_parent_pte(struct kvm *kvm,
+				    struct kvm_mmu_memory_cache *cache,
 				    struct kvm_mmu_page *sp, u64 *parent_pte)
 {
 	if (!parent_pte)
 		return;
 
-	pte_list_add(cache, parent_pte, &sp->parent_ptes);
+	pte_list_add(kvm, cache, parent_pte, &sp->parent_ptes);
 }
 
 static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
@@ -2352,7 +2524,7 @@ static void __link_shadow_page(struct kvm *kvm,
 
 	mmu_spte_set(sptep, spte);
 
-	mmu_page_add_parent_pte(cache, sp, sptep);
+	mmu_page_add_parent_pte(kvm, cache, sp, sptep);
 
 	/*
 	 * The non-direct sub-pagetable must be updated before linking.  For
@@ -2416,7 +2588,8 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			 * avoids retaining a large number of stale nested SPs.
 			 */
 			if (tdp_enabled && invalid_list &&
-			    child->role.guest_mode && !child->parent_ptes.val)
+			    child->role.guest_mode &&
+			    !atomic_long_read(&child->parent_ptes.val))
 				return kvm_mmu_prepare_zap_page(kvm, child,
 								invalid_list);
 		}
@@ -5801,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
 	__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
 	__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots);
 
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 				    int *bytes)
@@ -7460,7 +7634,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7471,13 +7645,14 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
-		return;
+	if (IS_ERR(nx_thread))
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7660,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
@@ -7498,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				int level)
+{
+	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				 int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+			       int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range)
 {
+	struct kvm_memory_slot *slot = range->slot;
+	int level;
+
 	/*
 	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
 	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7515,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
 		return false;
 
+	if (WARN_ON_ONCE(range->end <= range->start))
+		return false;
+
+	/*
+	 * If the head and tail pages of the range currently allow a hugepage,
+	 * i.e. reside fully in the slot and don't have mixed attributes, then
+	 * add each corresponding hugepage range to the ongoing invalidation,
+	 * e.g. to prevent KVM from creating a hugepage in response to a fault
+	 * for a gfn whose attributes aren't changing.  Note, only the range
+	 * of gfns whose attributes are being modified needs to be explicitly
+	 * unmapped, as that will unmap any existing hugepages.
+	 */
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		gfn_t start = gfn_round_for_level(range->start, level);
+		gfn_t end = gfn_round_for_level(range->end - 1, level);
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
+
+		if ((start != range->start || start + nr_pages > range->end) &&
+		    start >= slot->base_gfn &&
+		    start + nr_pages <= slot->base_gfn + slot->npages &&
+		    !hugepage_test_mixed(slot, start, level))
+			kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
+
+		if (end == start)
+			continue;
+
+		if ((end + nr_pages) > range->end &&
+		    (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+		    !hugepage_test_mixed(slot, end, level))
+			kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+	}
+
 	/* Unmap the old attribute page. */
 	if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
 		range->attr_filter = KVM_FILTER_SHARED;
@@ -7524,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 	return kvm_unmap_gfn_range(kvm, range);
 }
 
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				int level)
-{
-	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
-
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				 int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
 
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-			       int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
-}
 
 static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       gfn_t gfn, int level, unsigned long attrs)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f4711674c47b..68e323568e95 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -510,8 +510,7 @@ error:
 		 * Note, pte_access holds the raw RWX bits from the EPTE, not
 		 * ACC_*_MASK flags!
 		 */
-		walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
-						     EPT_VIOLATION_RWX_SHIFT;
+		walker->fault.exit_qualification |= EPT_VIOLATION_RWX_TO_PROT(pte_access);
 	}
 #endif
 	walker->fault.address = addr;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 22551e2f1d00..0f9f47b4ab0e 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -129,25 +129,32 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 }
 
 /*
- * Returns true if the SPTE has bits that may be set without holding mmu_lock.
- * The caller is responsible for checking if the SPTE is shadow-present, and
- * for determining whether or not the caller cares about non-leaf SPTEs.
+ * Returns true if the SPTE needs to be updated atomically due to having bits
+ * that may be changed without holding mmu_lock, and for which KVM must not
+ * lose information.  E.g. KVM must not drop Dirty bit information.  The caller
+ * is responsible for checking if the SPTE is shadow-present, and for
+ * determining whether or not the caller cares about non-leaf SPTEs.
  */
-bool spte_has_volatile_bits(u64 spte)
+bool spte_needs_atomic_update(u64 spte)
 {
+	/* SPTEs can be made Writable bit by KVM's fast page fault handler. */
 	if (!is_writable_pte(spte) && is_mmu_writable_spte(spte))
 		return true;
 
-	if (is_access_track_spte(spte))
+	/*
+	 * A/D-disabled SPTEs can be access-tracked by aging, and access-tracked
+	 * SPTEs can be restored by KVM's fast page fault handler.
+	 */
+	if (!spte_ad_enabled(spte))
 		return true;
 
-	if (spte_ad_enabled(spte)) {
-		if (!(spte & shadow_accessed_mask) ||
-		    (is_writable_pte(spte) && !(spte & shadow_dirty_mask)))
-			return true;
-	}
-
-	return false;
+	/*
+	 * Dirty and Accessed bits can be set by the CPU.  Ignore the Accessed
+	 * bit, as KVM tolerates false negatives/positives, e.g. KVM doesn't
+	 * invalidate TLBs when aging SPTEs, and so it's safe to clobber the
+	 * Accessed bit (and rare in practice).
+	 */
+	return is_writable_pte(spte) && !(spte & shadow_dirty_mask);
 }
 
 bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 59746854c0af..79cdceba9857 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -519,7 +519,7 @@ static inline u64 get_mmio_spte_generation(u64 spte)
 	return gen;
 }
 
-bool spte_has_volatile_bits(u64 spte);
+bool spte_needs_atomic_update(u64 spte);
 
 bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	       const struct kvm_memory_slot *slot,
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 047b78333653..364c5da6c499 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -25,6 +25,13 @@ static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
 	return xchg(rcu_dereference(sptep), new_spte);
 }
 
+static inline u64 tdp_mmu_clear_spte_bits_atomic(tdp_ptep_t sptep, u64 mask)
+{
+	atomic64_t *sptep_atomic = (atomic64_t *)rcu_dereference(sptep);
+
+	return (u64)atomic64_fetch_and(~mask, sptep_atomic);
+}
+
 static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 {
 	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
@@ -32,28 +39,21 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 }
 
 /*
- * SPTEs must be modified atomically if they are shadow-present, leaf
- * SPTEs, and have volatile bits, i.e. has bits that can be set outside
- * of mmu_lock.  The Writable bit can be set by KVM's fast page fault
- * handler, and Accessed and Dirty bits can be set by the CPU.
- *
- * Note, non-leaf SPTEs do have Accessed bits and those bits are
- * technically volatile, but KVM doesn't consume the Accessed bit of
- * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit.  This
- * logic needs to be reassessed if KVM were to use non-leaf Accessed
- * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs.
+ * SPTEs must be modified atomically if they are shadow-present, leaf SPTEs,
+ * and have volatile bits (bits that can be set outside of mmu_lock) that
+ * must not be clobbered.
  */
-static inline bool kvm_tdp_mmu_spte_need_atomic_write(u64 old_spte, int level)
+static inline bool kvm_tdp_mmu_spte_need_atomic_update(u64 old_spte, int level)
 {
 	return is_shadow_present_pte(old_spte) &&
 	       is_last_spte(old_spte, level) &&
-	       spte_has_volatile_bits(old_spte);
+	       spte_needs_atomic_update(old_spte);
 }
 
 static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
 					 u64 new_spte, int level)
 {
-	if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level))
+	if (kvm_tdp_mmu_spte_need_atomic_update(old_spte, level))
 		return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte);
 
 	__kvm_tdp_mmu_write_spte(sptep, new_spte);
@@ -63,12 +63,8 @@ static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
 static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte,
 					  u64 mask, int level)
 {
-	atomic64_t *sptep_atomic;
-
-	if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) {
-		sptep_atomic = (atomic64_t *)rcu_dereference(sptep);
-		return (u64)atomic64_fetch_and(~mask, sptep_atomic);
-	}
+	if (kvm_tdp_mmu_spte_need_atomic_update(old_spte, level))
+		return tdp_mmu_clear_spte_bits_atomic(sptep, mask);
 
 	__kvm_tdp_mmu_write_spte(sptep, old_spte & ~mask);
 	return old_spte;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 046b6ba31197..21a3b8166242 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -40,7 +40,9 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS);
 	kvm_tdp_mmu_zap_invalidated_roots(kvm, false);
 
-	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
+#ifdef CONFIG_KVM_PROVE_MMU
+	KVM_MMU_WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
+#endif
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 
 	/*
@@ -193,6 +195,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 		     !tdp_mmu_root_match((_root), (_types)))) {			\
 		} else
 
+/*
+ * Iterate over all TDP MMU roots in an RCU read-side critical section.
+ * It is safe to iterate over the SPTEs under the root, but their values will
+ * be unstable, so all writes must be atomic. As this routine is meant to be
+ * used without holding the mmu_lock at all, any bits that are flipped must
+ * be reflected in kvm_tdp_mmu_spte_need_atomic_write().
+ */
+#define for_each_tdp_mmu_root_rcu(_kvm, _root, _as_id, _types)			\
+	list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link)		\
+		if ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) ||	\
+		    !tdp_mmu_root_match((_root), (_types))) {			\
+		} else
+
 #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id)		\
 	__for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS)
 
@@ -312,13 +327,17 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	kvm_account_pgtable_pages((void *)sp->spt, +1);
+#ifdef CONFIG_KVM_PROVE_MMU
 	atomic64_inc(&kvm->arch.tdp_mmu_pages);
+#endif
 }
 
 static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	kvm_account_pgtable_pages((void *)sp->spt, -1);
+#ifdef CONFIG_KVM_PROVE_MMU
 	atomic64_dec(&kvm->arch.tdp_mmu_pages);
+#endif
 }
 
 /**
@@ -774,9 +793,6 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 			continue;					\
 		else
 
-#define tdp_mmu_for_each_pte(_iter, _kvm, _root, _start, _end)	\
-	for_each_tdp_pte(_iter, _kvm, _root, _start, _end)
-
 static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm,
 							  struct tdp_iter *iter)
 {
@@ -1235,7 +1251,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 
 	rcu_read_lock();
 
-	tdp_mmu_for_each_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) {
+	for_each_tdp_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) {
 		int r;
 
 		if (fault->nx_huge_page_workaround_enabled)
@@ -1332,21 +1348,22 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
  * from the clear_young() or clear_flush_young() notifier, which uses the
  * return value to determine if the page has been accessed.
  */
-static void kvm_tdp_mmu_age_spte(struct tdp_iter *iter)
+static void kvm_tdp_mmu_age_spte(struct kvm *kvm, struct tdp_iter *iter)
 {
 	u64 new_spte;
 
 	if (spte_ad_enabled(iter->old_spte)) {
-		iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep,
-							 iter->old_spte,
-							 shadow_accessed_mask,
-							 iter->level);
+		iter->old_spte = tdp_mmu_clear_spte_bits_atomic(iter->sptep,
+								shadow_accessed_mask);
 		new_spte = iter->old_spte & ~shadow_accessed_mask;
 	} else {
 		new_spte = mark_spte_for_access_track(iter->old_spte);
-		iter->old_spte = kvm_tdp_mmu_write_spte(iter->sptep,
-							iter->old_spte, new_spte,
-							iter->level);
+		/*
+		 * It is safe for the following cmpxchg to fail. Leave the
+		 * Accessed bit set, as the spte is most likely young anyway.
+		 */
+		if (__tdp_mmu_set_spte_atomic(kvm, iter, new_spte))
+			return;
 	}
 
 	trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level,
@@ -1371,9 +1388,9 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm,
 	 * valid roots!
 	 */
 	WARN_ON(types & ~KVM_VALID_ROOTS);
-	__for_each_tdp_mmu_root(kvm, root, range->slot->as_id, types) {
-		guard(rcu)();
 
+	guard(rcu)();
+	for_each_tdp_mmu_root_rcu(kvm, root, range->slot->as_id, types) {
 		tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) {
 			if (!is_accessed_spte(iter.old_spte))
 				continue;
@@ -1382,7 +1399,7 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm,
 				return true;
 
 			ret = true;
-			kvm_tdp_mmu_age_spte(&iter);
+			kvm_tdp_mmu_age_spte(kvm, &iter);
 		}
 	}
 
@@ -1904,7 +1921,7 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
 
 	*root_level = vcpu->arch.mmu->root_role.level;
 
-	tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
+	for_each_tdp_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
 		leaf = iter.level;
 		sptes[leaf] = iter.old_spte;
 	}
@@ -1931,7 +1948,7 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn,
 	struct tdp_iter iter;
 	tdp_ptep_t sptep = NULL;
 
-	tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
+	for_each_tdp_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
 		*spte = iter.old_spte;
 		sptep = iter.sptep;
 	}
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index e0ab7df27b66..9864c057187d 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 	kvm_mmu_reset_context(vcpu);
 }
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
 
 void process_smi(struct kvm_vcpu *vcpu)
 {
@@ -358,7 +359,7 @@ void enter_smm(struct kvm_vcpu *vcpu)
 			goto error;
 #endif
 
-	kvm_update_cpuid_runtime(vcpu);
+	vcpu->arch.cpuid_dynamic_bits_dirty = true;
 	kvm_mmu_reset_context(vcpu);
 	return;
 error:
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245a9953..067f8e3f5a0d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -20,6 +20,7 @@
 #include <linux/kvm_host.h>
 
 #include <asm/irq_remapping.h>
+#include <asm/msr.h>
 
 #include "trace.h"
 #include "lapic.h"
@@ -330,7 +331,7 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
 	int cpu = READ_ONCE(vcpu->cpu);
 
 	if (cpu != get_cpu()) {
-		wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
+		wrmsrq(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
 		trace_kvm_avic_doorbell(vcpu->vcpu_id, kvm_cpu_get_apicid(cpu));
 	}
 	put_cpu();
@@ -796,12 +797,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	struct amd_svm_iommu_ir *ir;
 	u64 entry;
 
+	if (WARN_ON_ONCE(!pi->ir_data))
+		return -EINVAL;
+
 	/**
 	 * In some cases, the existing irte is updated and re-set,
 	 * so we need to check here if it's already been * added
 	 * to the ir_list.
 	 */
-	if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+	if (pi->prev_ga_tag) {
 		struct kvm *kvm = svm->vcpu.kvm;
 		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
 		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +824,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	 * Allocating new amd_iommu_pi_data, which will get
 	 * add to the per-vcpu ir_list.
 	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
 	if (!ir) {
 		ret = -ENOMEM;
 		goto out;
@@ -896,10 +900,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP))
+	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
 		return 0;
 
 	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +937,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
 			struct amd_iommu_pi_data pi;
 
+			enable_remapped_mode = false;
+
 			/* Try to enable guest_mode in IRTE */
 			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
 					    AVIC_HPA_MASK);
@@ -951,33 +957,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 			 */
 			if (!ret && pi.is_guest_mode)
 				svm_ir_list_add(svm, &pi);
-		} else {
-			/* Use legacy mode in IRTE */
-			struct amd_iommu_pi_data pi;
-
-			/**
-			 * Here, pi is used to:
-			 * - Tell IOMMU to use legacy mode for this interrupt.
-			 * - Retrieve ga_tag of prior interrupt remapping data.
-			 */
-			pi.prev_ga_tag = 0;
-			pi.is_guest_mode = false;
-			ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-			/**
-			 * Check if the posted interrupt was previously
-			 * setup with the guest_mode by checking if the ga_tag
-			 * was cached. If so, we need to clean up the per-vcpu
-			 * ir_list.
-			 */
-			if (!ret && pi.prev_ga_tag) {
-				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-				struct kvm_vcpu *vcpu;
-
-				vcpu = kvm_get_vcpu_by_id(kvm, id);
-				if (vcpu)
-					svm_ir_list_del(to_svm(vcpu), &pi);
-			}
 		}
 
 		if (!ret && svm) {
@@ -993,6 +972,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 	}
 
 	ret = 0;
+	if (enable_remapped_mode) {
+		/* Use legacy mode in IRTE */
+		struct amd_iommu_pi_data pi;
+
+		/**
+		 * Here, pi is used to:
+		 * - Tell IOMMU to use legacy mode for this interrupt.
+		 * - Retrieve ga_tag of prior interrupt remapping data.
+		 */
+		pi.prev_ga_tag = 0;
+		pi.is_guest_mode = false;
+		ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+		/**
+		 * Check if the posted interrupt was previously
+		 * setup with the guest_mode by checking if the ga_tag
+		 * was cached. If so, we need to clean up the per-vcpu
+		 * ir_list.
+		 */
+		if (!ret && pi.prev_ga_tag) {
+			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+			struct kvm_vcpu *vcpu;
+
+			vcpu = kvm_get_vcpu_by_id(kvm, id);
+			if (vcpu)
+				svm_ir_list_del(to_svm(vcpu), &pi);
+		}
+	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 04c375bf1ac2..834b67672d50 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -994,7 +994,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 
 	/* in case we halted in L2 */
-	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
 	/* Give the current vmcb to the guest */
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0dbb25442ec1..1aa0f07d3a63 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -26,6 +26,7 @@
 #include <asm/fpu/xcr.h>
 #include <asm/fpu/xstate.h>
 #include <asm/debugreg.h>
+#include <asm/msr.h>
 #include <asm/sev.h>
 
 #include "mmu.h"
@@ -140,7 +141,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
 static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
 
 	return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP;
 }
@@ -226,9 +227,7 @@ e_uncharge:
 
 static unsigned int sev_get_asid(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	return sev->asid;
+	return to_kvm_sev_info(kvm)->asid;
 }
 
 static void sev_asid_free(struct kvm_sev_info *sev)
@@ -403,7 +402,7 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 			    struct kvm_sev_init *data,
 			    unsigned long vm_type)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_platform_init_args init_args = {0};
 	bool es_active = vm_type != KVM_X86_SEV_VM;
 	u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0;
@@ -500,10 +499,9 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_init data;
 
-	if (!sev->need_init)
+	if (!to_kvm_sev_info(kvm)->need_init)
 		return -EINVAL;
 
 	if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
@@ -543,14 +541,14 @@ static int __sev_issue_cmd(int fd, int id, void *data, int *error)
 
 static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 
 	return __sev_issue_cmd(sev->fd, id, data, error);
 }
 
 static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_launch_start start;
 	struct kvm_sev_launch_start params;
 	void *dh_blob, *session_blob;
@@ -622,9 +620,9 @@ e_free_dh:
 
 static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 				    unsigned long ulen, unsigned long *n,
-				    int write)
+				    unsigned int flags)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	unsigned long npages, size;
 	int npinned;
 	unsigned long locked, lock_limit;
@@ -663,7 +661,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return ERR_PTR(-ENOMEM);
 
 	/* Pin the user virtual address. */
-	npinned = pin_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+	npinned = pin_user_pages_fast(uaddr, npages, flags, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		ret = -ENOMEM;
@@ -686,11 +684,9 @@ err:
 static void sev_unpin_memory(struct kvm *kvm, struct page **pages,
 			     unsigned long npages)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
 	unpin_user_pages(pages, npages);
 	kvfree(pages);
-	sev->pages_locked -= npages;
+	to_kvm_sev_info(kvm)->pages_locked -= npages;
 }
 
 static void sev_clflush_pages(struct page *pages[], unsigned long npages)
@@ -734,7 +730,6 @@ static unsigned long get_num_contig_pages(unsigned long idx,
 static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_launch_update_data params;
 	struct sev_data_launch_update_data data;
 	struct page **inpages;
@@ -751,7 +746,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	vaddr_end = vaddr + size;
 
 	/* Lock the user memory. */
-	inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1);
+	inpages = sev_pin_memory(kvm, vaddr, size, &npages, FOLL_WRITE);
 	if (IS_ERR(inpages))
 		return PTR_ERR(inpages);
 
@@ -762,7 +757,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	sev_clflush_pages(inpages, npages);
 
 	data.reserved = 0;
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 
 	for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) {
 		int offset, len;
@@ -802,7 +797,7 @@ e_unpin:
 static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
 	struct sev_es_save_area *save = svm->sev_es.vmsa;
 	struct xregs_state *xsave;
 	const u8 *s;
@@ -972,7 +967,6 @@ static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	void __user *measure = u64_to_user_ptr(argp->data);
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_launch_measure data;
 	struct kvm_sev_launch_measure params;
 	void __user *p = NULL;
@@ -1005,7 +999,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	}
 
 cmd:
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, &data, &argp->error);
 
 	/*
@@ -1033,19 +1027,17 @@ e_free_blob:
 
 static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_launch_finish data;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, &data, &argp->error);
 }
 
 static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_guest_status params;
 	struct sev_data_guest_status data;
 	int ret;
@@ -1055,7 +1047,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	memset(&data, 0, sizeof(data));
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, &data, &argp->error);
 	if (ret)
 		return ret;
@@ -1074,11 +1066,10 @@ static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src,
 			       unsigned long dst, int size,
 			       int *error, bool enc)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_dbg data;
 
 	data.reserved = 0;
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	data.dst_addr = dst;
 	data.src_addr = src;
 	data.len = size;
@@ -1250,7 +1241,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 		if (IS_ERR(src_p))
 			return PTR_ERR(src_p);
 
-		dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1);
+		dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, FOLL_WRITE);
 		if (IS_ERR(dst_p)) {
 			sev_unpin_memory(kvm, src_p, n);
 			return PTR_ERR(dst_p);
@@ -1302,7 +1293,6 @@ err:
 
 static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_launch_secret data;
 	struct kvm_sev_launch_secret params;
 	struct page **pages;
@@ -1316,7 +1306,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
 		return -EFAULT;
 
-	pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1);
+	pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, FOLL_WRITE);
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
@@ -1358,7 +1348,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data.hdr_address = __psp_pa(hdr);
 	data.hdr_len = params.hdr_len;
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, &data, &argp->error);
 
 	kfree(hdr);
@@ -1378,7 +1368,6 @@ e_unpin_memory:
 static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	void __user *report = u64_to_user_ptr(argp->data);
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_attestation_report data;
 	struct kvm_sev_attestation_report params;
 	void __user *p;
@@ -1411,7 +1400,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		memcpy(data.mnonce, params.mnonce, sizeof(params.mnonce));
 	}
 cmd:
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, &data, &argp->error);
 	/*
 	 * If we query the session length, FW responded with expected data.
@@ -1441,12 +1430,11 @@ static int
 __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp,
 				      struct kvm_sev_send_start *params)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_start data;
 	int ret;
 
 	memset(&data, 0, sizeof(data));
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
 
 	params->session_len = data.session_len;
@@ -1459,7 +1447,6 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp,
 
 static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_start data;
 	struct kvm_sev_send_start params;
 	void *amd_certs, *session_data;
@@ -1520,7 +1507,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data.amd_certs_len = params.amd_certs_len;
 	data.session_address = __psp_pa(session_data);
 	data.session_len = params.session_len;
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 
 	ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
 
@@ -1552,12 +1539,11 @@ static int
 __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp,
 				     struct kvm_sev_send_update_data *params)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_update_data data;
 	int ret;
 
 	memset(&data, 0, sizeof(data));
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);
 
 	params->hdr_len = data.hdr_len;
@@ -1572,7 +1558,6 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp,
 
 static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_update_data data;
 	struct kvm_sev_send_update_data params;
 	void *hdr, *trans_data;
@@ -1626,7 +1611,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
 	data.guest_address |= sev_me_mask;
 	data.guest_len = params.guest_len;
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 
 	ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error);
 
@@ -1657,31 +1642,29 @@ e_unpin:
 
 static int sev_send_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_finish data;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	return sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, &data, &argp->error);
 }
 
 static int sev_send_cancel(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_send_cancel data;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	return sev_issue_cmd(kvm, SEV_CMD_SEND_CANCEL, &data, &argp->error);
 }
 
 static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_receive_start start;
 	struct kvm_sev_receive_start params;
 	int *error = &argp->error;
@@ -1755,7 +1738,6 @@ e_free_pdh:
 
 static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_receive_update_data params;
 	struct sev_data_receive_update_data data;
 	void *hdr = NULL, *trans = NULL;
@@ -1798,7 +1780,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Pin guest memory */
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
-				    PAGE_SIZE, &n, 1);
+				    PAGE_SIZE, &n, FOLL_WRITE);
 	if (IS_ERR(guest_page)) {
 		ret = PTR_ERR(guest_page);
 		goto e_free_trans;
@@ -1815,7 +1797,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
 	data.guest_address |= sev_me_mask;
 	data.guest_len = params.guest_len;
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 
 	ret = sev_issue_cmd(kvm, SEV_CMD_RECEIVE_UPDATE_DATA, &data,
 				&argp->error);
@@ -1832,13 +1814,12 @@ e_free_hdr:
 
 static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_receive_finish data;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	data.handle = sev->handle;
+	data.handle = to_kvm_sev_info(kvm)->handle;
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
@@ -1858,8 +1839,8 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 
 static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
-	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm);
+	struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm);
 	int r = -EBUSY;
 
 	if (dst_kvm == src_kvm)
@@ -1893,8 +1874,8 @@ release_dst:
 
 static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
-	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = to_kvm_sev_info(dst_kvm);
+	struct kvm_sev_info *src_sev = to_kvm_sev_info(src_kvm);
 
 	mutex_unlock(&dst_kvm->lock);
 	mutex_unlock(&src_kvm->lock);
@@ -1968,8 +1949,8 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
 
 static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *dst = &to_kvm_svm(dst_kvm)->sev_info;
-	struct kvm_sev_info *src = &to_kvm_svm(src_kvm)->sev_info;
+	struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
+	struct kvm_sev_info *src = to_kvm_sev_info(src_kvm);
 	struct kvm_vcpu *dst_vcpu, *src_vcpu;
 	struct vcpu_svm *dst_svm, *src_svm;
 	struct kvm_sev_info *mirror;
@@ -2009,8 +1990,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 	 * and add the new mirror to the list.
 	 */
 	if (is_mirroring_enc_context(dst_kvm)) {
-		struct kvm_sev_info *owner_sev_info =
-			&to_kvm_svm(dst->enc_context_owner)->sev_info;
+		struct kvm_sev_info *owner_sev_info = to_kvm_sev_info(dst->enc_context_owner);
 
 		list_del(&src->mirror_entry);
 		list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms);
@@ -2069,7 +2049,7 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
 
 int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 {
-	struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = to_kvm_sev_info(kvm);
 	struct kvm_sev_info *src_sev, *cg_cleanup_sev;
 	CLASS(fd, f)(source_fd);
 	struct kvm *source_kvm;
@@ -2093,7 +2073,7 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 		goto out_unlock;
 	}
 
-	src_sev = &to_kvm_svm(source_kvm)->sev_info;
+	src_sev = to_kvm_sev_info(source_kvm);
 
 	dst_sev->misc_cg = get_current_misc_cg();
 	cg_cleanup_sev = dst_sev;
@@ -2181,7 +2161,7 @@ static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 static int snp_bind_asid(struct kvm *kvm, int *error)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_snp_activate data = {0};
 
 	data.gctx_paddr = __psp_pa(sev->snp_context);
@@ -2191,7 +2171,7 @@ static int snp_bind_asid(struct kvm *kvm, int *error)
 
 static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_snp_launch_start start = {0};
 	struct kvm_sev_snp_launch_start params;
 	int rc;
@@ -2260,7 +2240,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf
 				  void __user *src, int order, void *opaque)
 {
 	struct sev_gmem_populate_args *sev_populate_args = opaque;
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	int n_private = 0, ret, i;
 	int npages = (1 << order);
 	gfn_t gfn;
@@ -2350,7 +2330,7 @@ err:
 
 static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_gmem_populate_args sev_populate_args = {0};
 	struct kvm_sev_snp_launch_update params;
 	struct kvm_memory_slot *memslot;
@@ -2434,7 +2414,7 @@ out:
 
 static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_snp_launch_update data = {};
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
@@ -2482,7 +2462,7 @@ static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct kvm_sev_snp_launch_finish params;
 	struct sev_data_snp_launch_finish *data;
 	void *id_block = NULL, *id_auth = NULL;
@@ -2677,7 +2657,7 @@ out:
 int sev_mem_enc_register_region(struct kvm *kvm,
 				struct kvm_enc_region *range)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct enc_region *region;
 	int ret = 0;
 
@@ -2696,7 +2676,8 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		return -ENOMEM;
 
 	mutex_lock(&kvm->lock);
-	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages, 1);
+	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages,
+				       FOLL_WRITE | FOLL_LONGTERM);
 	if (IS_ERR(region->pages)) {
 		ret = PTR_ERR(region->pages);
 		mutex_unlock(&kvm->lock);
@@ -2729,7 +2710,7 @@ e_free:
 static struct enc_region *
 find_enc_region(struct kvm *kvm, struct kvm_enc_region *range)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct list_head *head = &sev->regions_list;
 	struct enc_region *i;
 
@@ -2824,9 +2805,9 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
 	 * disappear until we're done with it
 	 */
-	source_sev = &to_kvm_svm(source_kvm)->sev_info;
+	source_sev = to_kvm_sev_info(source_kvm);
 	kvm_get_kvm(source_kvm);
-	mirror_sev = &to_kvm_svm(kvm)->sev_info;
+	mirror_sev = to_kvm_sev_info(kvm);
 	list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms);
 
 	/* Set enc_context_owner and copy its encryption context over */
@@ -2854,7 +2835,7 @@ e_unlock:
 
 static int snp_decommission_context(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct sev_data_snp_addr data = {};
 	int ret;
 
@@ -2879,7 +2860,7 @@ static int snp_decommission_context(struct kvm *kvm)
 
 void sev_vm_destroy(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	struct list_head *head = &sev->regions_list;
 	struct list_head *pos, *q;
 
@@ -2953,6 +2934,7 @@ void __init sev_set_cpu_caps(void)
 void __init sev_hardware_setup(void)
 {
 	unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
+	struct sev_platform_init_args init_args = {0};
 	bool sev_snp_supported = false;
 	bool sev_es_supported = false;
 	bool sev_supported = false;
@@ -3079,6 +3061,15 @@ out:
 	sev_supported_vmsa_features = 0;
 	if (sev_es_debug_swap_enabled)
 		sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+
+	if (!sev_enabled)
+		return;
+
+	/*
+	 * Do both SNP and SEV initialization at KVM module load.
+	 */
+	init_args.probe = true;
+	sev_platform_init(&init_args);
 }
 
 void sev_hardware_unsetup(void)
@@ -3094,6 +3085,8 @@ void sev_hardware_unsetup(void)
 
 	misc_cg_set_capacity(MISC_CG_RES_SEV, 0);
 	misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0);
+
+	sev_platform_shutdown();
 }
 
 int sev_cpu_init(struct svm_cpu_data *sd)
@@ -3139,7 +3132,7 @@ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 	 * back to WBINVD if this faults so as not to make any problems worse
 	 * by leaving stale encrypted data in the cache.
 	 */
-	if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
+	if (WARN_ON_ONCE(wrmsrq_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
 		goto do_wbinvd;
 
 	return;
@@ -3193,9 +3186,14 @@ skip_vmsa_free:
 		kvfree(svm->sev_es.ghcb_sa);
 }
 
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
 static void dump_ghcb(struct vcpu_svm *svm)
 {
-	struct ghcb *ghcb = svm->sev_es.ghcb;
+	struct vmcb_control_area *control = &svm->vmcb->control;
 	unsigned int nbits;
 
 	/* Re-use the dump_invalid_vmcb module parameter */
@@ -3204,18 +3202,24 @@ static void dump_ghcb(struct vcpu_svm *svm)
 		return;
 	}
 
-	nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+	nbits = sizeof(svm->sev_es.valid_bitmap) * 8;
 
-	pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+	/*
+	 * Print KVM's snapshot of the GHCB values that were (unsuccessfully)
+	 * used to handle the exit.  If the guest has since modified the GHCB
+	 * itself, dumping the raw GHCB won't help debug why KVM was unable to
+	 * handle the VMGEXIT that KVM observed.
+	 */
+	pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa);
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
-	       ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+	       kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
-	       ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+	       control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
-	       ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+	       control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm));
 	pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
-	       ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
-	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+	       svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm));
+	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap);
 }
 
 static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
@@ -3271,7 +3275,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 
 	if (kvm_ghcb_xcr0_is_valid(svm)) {
 		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 	}
 
 	/* Copy the GHCB exit information into the VMCB fields */
@@ -3286,11 +3290,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
-{
-	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
-}
-
 static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3430,8 +3429,7 @@ vmgexit_err:
 		dump_ghcb(svm);
 	}
 
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, reason);
+	svm_vmgexit_bad_input(svm, reason);
 
 	/* Resume the guest to "return" the error code. */
 	return 1;
@@ -3472,10 +3470,19 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 	svm->sev_es.ghcb = NULL;
 }
 
-void pre_sev_run(struct vcpu_svm *svm, int cpu)
+int pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-	unsigned int asid = sev_get_asid(svm->vcpu.kvm);
+	struct kvm *kvm = svm->vcpu.kvm;
+	unsigned int asid = sev_get_asid(kvm);
+
+	/*
+	 * Reject KVM_RUN if userspace attempts to run the vCPU with an invalid
+	 * VMSA, e.g. if userspace forces the vCPU to be RUNNABLE after an SNP
+	 * AP Destroy event.
+	 */
+	if (sev_es_guest(kvm) && !VALID_PAGE(svm->vmcb->control.vmsa_pa))
+		return -EINVAL;
 
 	/* Assign the asid allocated with this SEV guest */
 	svm->asid = asid;
@@ -3488,11 +3495,12 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 	 */
 	if (sd->sev_vmcbs[asid] == svm->vmcb &&
 	    svm->vcpu.arch.last_vmentry_cpu == cpu)
-		return;
+		return 0;
 
 	sd->sev_vmcbs[asid] = svm->vmcb;
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
 	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
+	return 0;
 }
 
 #define GHCB_SCRATCH_AREA_LIMIT		(16ULL * PAGE_SIZE)
@@ -3574,8 +3582,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	return 0;
 
 e_scratch:
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+	svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_SCRATCH_AREA);
 
 	return 1;
 }
@@ -3675,7 +3682,14 @@ static void snp_complete_psc(struct vcpu_svm *svm, u64 psc_ret)
 	svm->sev_es.psc_inflight = 0;
 	svm->sev_es.psc_idx = 0;
 	svm->sev_es.psc_2m = false;
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, psc_ret);
+
+	/*
+	 * PSC requests always get a "no action" response in SW_EXITINFO1, with
+	 * a PSC-specific return code in SW_EXITINFO2 that provides the "real"
+	 * return code.  E.g. if the PSC request was interrupted, the need to
+	 * retry is communicated via SW_EXITINFO2, not SW_EXITINFO1.
+	 */
+	svm_vmgexit_no_action(svm, psc_ret);
 }
 
 static void __snp_complete_one_psc(struct vcpu_svm *svm)
@@ -3847,110 +3861,90 @@ next_range:
 	BUG();
 }
 
-static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu)
+/*
+ * Invoked as part of svm_vcpu_reset() processing of an init event.
+ */
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_memory_slot *slot;
+	struct page *page;
+	kvm_pfn_t pfn;
+	gfn_t gfn;
+
+	if (!sev_snp_guest(vcpu->kvm))
+		return;
+
+	guard(mutex)(&svm->sev_es.snp_vmsa_mutex);
 
-	WARN_ON(!mutex_is_locked(&svm->sev_es.snp_vmsa_mutex));
+	if (!svm->sev_es.snp_ap_waiting_for_reset)
+		return;
+
+	svm->sev_es.snp_ap_waiting_for_reset = false;
 
 	/* Mark the vCPU as offline and not runnable */
 	vcpu->arch.pv.pv_unhalted = false;
-	vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED);
 
 	/* Clear use of the VMSA */
 	svm->vmcb->control.vmsa_pa = INVALID_PAGE;
 
-	if (VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) {
-		gfn_t gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
-		struct kvm_memory_slot *slot;
-		struct page *page;
-		kvm_pfn_t pfn;
-
-		slot = gfn_to_memslot(vcpu->kvm, gfn);
-		if (!slot)
-			return -EINVAL;
-
-		/*
-		 * The new VMSA will be private memory guest memory, so
-		 * retrieve the PFN from the gmem backend.
-		 */
-		if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, &page, NULL))
-			return -EINVAL;
-
-		/*
-		 * From this point forward, the VMSA will always be a
-		 * guest-mapped page rather than the initial one allocated
-		 * by KVM in svm->sev_es.vmsa. In theory, svm->sev_es.vmsa
-		 * could be free'd and cleaned up here, but that involves
-		 * cleanups like wbinvd_on_all_cpus() which would ideally
-		 * be handled during teardown rather than guest boot.
-		 * Deferring that also allows the existing logic for SEV-ES
-		 * VMSAs to be re-used with minimal SNP-specific changes.
-		 */
-		svm->sev_es.snp_has_guest_vmsa = true;
-
-		/* Use the new VMSA */
-		svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
-
-		/* Mark the vCPU as runnable */
-		vcpu->arch.pv.pv_unhalted = false;
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-
-		svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
-
-		/*
-		 * gmem pages aren't currently migratable, but if this ever
-		 * changes then care should be taken to ensure
-		 * svm->sev_es.vmsa is pinned through some other means.
-		 */
-		kvm_release_page_clean(page);
-	}
-
 	/*
 	 * When replacing the VMSA during SEV-SNP AP creation,
 	 * mark the VMCB dirty so that full state is always reloaded.
 	 */
 	vmcb_mark_all_dirty(svm->vmcb);
 
-	return 0;
-}
+	if (!VALID_PAGE(svm->sev_es.snp_vmsa_gpa))
+		return;
 
-/*
- * Invoked as part of svm_vcpu_reset() processing of an init event.
- */
-void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int ret;
+	gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
+	svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
 
-	if (!sev_snp_guest(vcpu->kvm))
+	slot = gfn_to_memslot(vcpu->kvm, gfn);
+	if (!slot)
 		return;
 
-	mutex_lock(&svm->sev_es.snp_vmsa_mutex);
+	/*
+	 * The new VMSA will be private memory guest memory, so retrieve the
+	 * PFN from the gmem backend.
+	 */
+	if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, &page, NULL))
+		return;
 
-	if (!svm->sev_es.snp_ap_waiting_for_reset)
-		goto unlock;
+	/*
+	 * From this point forward, the VMSA will always be a guest-mapped page
+	 * rather than the initial one allocated by KVM in svm->sev_es.vmsa. In
+	 * theory, svm->sev_es.vmsa could be free'd and cleaned up here, but
+	 * that involves cleanups like wbinvd_on_all_cpus() which would ideally
+	 * be handled during teardown rather than guest boot.  Deferring that
+	 * also allows the existing logic for SEV-ES VMSAs to be re-used with
+	 * minimal SNP-specific changes.
+	 */
+	svm->sev_es.snp_has_guest_vmsa = true;
 
-	svm->sev_es.snp_ap_waiting_for_reset = false;
+	/* Use the new VMSA */
+	svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
 
-	ret = __sev_snp_update_protected_guest_state(vcpu);
-	if (ret)
-		vcpu_unimpl(vcpu, "snp: AP state update on init failed\n");
+	/* Mark the vCPU as runnable */
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
-unlock:
-	mutex_unlock(&svm->sev_es.snp_vmsa_mutex);
+	/*
+	 * gmem pages aren't currently migratable, but if this ever changes
+	 * then care should be taken to ensure svm->sev_es.vmsa is pinned
+	 * through some other means.
+	 */
+	kvm_release_page_clean(page);
 }
 
 static int sev_snp_ap_creation(struct vcpu_svm *svm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct kvm_vcpu *target_vcpu;
 	struct vcpu_svm *target_svm;
 	unsigned int request;
 	unsigned int apic_id;
-	bool kick;
-	int ret;
 
 	request = lower_32_bits(svm->vmcb->control.exit_info_1);
 	apic_id = upper_32_bits(svm->vmcb->control.exit_info_1);
@@ -3963,47 +3957,23 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 		return -EINVAL;
 	}
 
-	ret = 0;
-
 	target_svm = to_svm(target_vcpu);
 
-	/*
-	 * The target vCPU is valid, so the vCPU will be kicked unless the
-	 * request is for CREATE_ON_INIT. For any errors at this stage, the
-	 * kick will place the vCPU in an non-runnable state.
-	 */
-	kick = true;
-
-	mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
-
-	target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
-	target_svm->sev_es.snp_ap_waiting_for_reset = true;
-
-	/* Interrupt injection mode shouldn't change for AP creation */
-	if (request < SVM_VMGEXIT_AP_DESTROY) {
-		u64 sev_features;
-
-		sev_features = vcpu->arch.regs[VCPU_REGS_RAX];
-		sev_features ^= sev->vmsa_features;
-
-		if (sev_features & SVM_SEV_FEAT_INT_INJ_MODES) {
-			vcpu_unimpl(vcpu, "vmgexit: invalid AP injection mode [%#lx] from guest\n",
-				    vcpu->arch.regs[VCPU_REGS_RAX]);
-			ret = -EINVAL;
-			goto out;
-		}
-	}
+	guard(mutex)(&target_svm->sev_es.snp_vmsa_mutex);
 
 	switch (request) {
 	case SVM_VMGEXIT_AP_CREATE_ON_INIT:
-		kick = false;
-		fallthrough;
 	case SVM_VMGEXIT_AP_CREATE:
+		if (vcpu->arch.regs[VCPU_REGS_RAX] != sev->vmsa_features) {
+			vcpu_unimpl(vcpu, "vmgexit: mismatched AP sev_features [%#lx] != [%#llx] from guest\n",
+				    vcpu->arch.regs[VCPU_REGS_RAX], sev->vmsa_features);
+			return -EINVAL;
+		}
+
 		if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) {
 			vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n",
 				    svm->vmcb->control.exit_info_2);
-			ret = -EINVAL;
-			goto out;
+			return -EINVAL;
 		}
 
 		/*
@@ -4017,30 +3987,32 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 			vcpu_unimpl(vcpu,
 				    "vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n",
 				    svm->vmcb->control.exit_info_2);
-			ret = -EINVAL;
-			goto out;
+			return -EINVAL;
 		}
 
 		target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
 		break;
 	case SVM_VMGEXIT_AP_DESTROY:
+		target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
 		break;
 	default:
 		vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
 			    request);
-		ret = -EINVAL;
-		break;
+		return -EINVAL;
 	}
 
-out:
-	if (kick) {
+	target_svm->sev_es.snp_ap_waiting_for_reset = true;
+
+	/*
+	 * Unless Creation is deferred until INIT, signal the vCPU to update
+	 * its state.
+	 */
+	if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) {
 		kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
 		kvm_vcpu_kick(target_vcpu);
 	}
 
-	mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex);
-
-	return ret;
+	return 0;
 }
 
 static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
@@ -4079,7 +4051,8 @@ static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_
 		goto out_unlock;
 	}
 
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err));
+	/* No action is requested *from KVM* if there was a firmware error. */
+	svm_vmgexit_no_action(svm, SNP_GUEST_ERR(0, fw_err));
 
 	ret = 1; /* resume guest */
 
@@ -4135,8 +4108,7 @@ static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t r
 	return snp_handle_guest_req(svm, req_gpa, resp_gpa);
 
 request_invalid:
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+	svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
 	return 1; /* resume guest */
 }
 
@@ -4144,7 +4116,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
 	u64 ghcb_info;
 	int ret = 1;
 
@@ -4328,8 +4300,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 0);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 0);
+	svm_vmgexit_success(svm, 0);
 
 	exit_code = kvm_ghcb_get_sw_exit_code(control);
 	switch (exit_code) {
@@ -4364,7 +4335,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = kvm_emulate_ap_reset_hold(vcpu);
 		break;
 	case SVM_VMGEXIT_AP_JUMP_TABLE: {
-		struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+		struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
 
 		switch (control->exit_info_1) {
 		case 0:
@@ -4373,21 +4344,19 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 			break;
 		case 1:
 			/* Get AP jump table address */
-			ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, sev->ap_jump_table);
+			svm_vmgexit_success(svm, sev->ap_jump_table);
 			break;
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
-			ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+			svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
 		}
 
 		ret = 1;
 		break;
 	}
 	case SVM_VMGEXIT_HV_FEATURES:
-		ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_HV_FT_SUPPORTED);
-
+		svm_vmgexit_success(svm, GHCB_HV_FT_SUPPORTED);
 		ret = 1;
 		break;
 	case SVM_VMGEXIT_TERM_REQUEST:
@@ -4408,8 +4377,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	case SVM_VMGEXIT_AP_CREATION:
 		ret = sev_snp_ap_creation(svm);
 		if (ret) {
-			ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
-			ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+			svm_vmgexit_bad_input(svm, GHCB_ERR_INVALID_INPUT);
 		}
 
 		ret = 1;
@@ -4575,7 +4543,7 @@ void sev_init_vmcb(struct vcpu_svm *svm)
 void sev_es_vcpu_reset(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(vcpu->kvm);
 
 	/*
 	 * Set the GHCB MSR value as per the GHCB specification when emulating
@@ -4590,6 +4558,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
 {
+	struct kvm *kvm = svm->vcpu.kvm;
+
 	/*
 	 * All host state for SEV-ES guests is categorized into three swap types
 	 * based on how it is handled by hardware during a world switch:
@@ -4613,14 +4583,22 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
-	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
-	 * saves and loads debug registers (Type-A).
+	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
+	 * not save or load debug registers.  Sadly, KVM can't prevent SNP
+	 * guests from lying about DebugSwap on secondary vCPUs, i.e. the
+	 * SEV_FEATURES provided at "AP Create" isn't guaranteed to match what
+	 * the guest has actually enabled (or not!) in the VMSA.
+	 *
+	 * If DebugSwap is *possible*, save the masks so that they're restored
+	 * if the guest enables DebugSwap.  But for the DRs themselves, do NOT
+	 * rely on the CPU to restore the host values; KVM will restore them as
+	 * needed in common code, via hw_breakpoint_restore().  Note, KVM does
+	 * NOT support virtualizing Breakpoint Extensions, i.e. the mask MSRs
+	 * don't need to be restored per se, KVM just needs to ensure they are
+	 * loaded with the correct values *if* the CPU writes the MSRs.
 	 */
-	if (sev_vcpu_has_debug_swap(svm)) {
-		hostsa->dr0 = native_get_debugreg(0);
-		hostsa->dr1 = native_get_debugreg(1);
-		hostsa->dr2 = native_get_debugreg(2);
-		hostsa->dr3 = native_get_debugreg(3);
+	if (sev_vcpu_has_debug_swap(svm) ||
+	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
 		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
 		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
 		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
@@ -4645,7 +4623,7 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 		 * Return from an AP Reset Hold VMGEXIT, where the guest will
 		 * set the CS and RIP. Set SW_EXIT_INFO_2 to a non-zero value.
 		 */
-		ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
+		svm_vmgexit_success(svm, 1);
 		break;
 	case AP_RESET_HOLD_MSR_PROTO:
 		/*
@@ -4843,7 +4821,7 @@ static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order)
 
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 	kvm_pfn_t pfn_aligned;
 	gfn_t gfn_aligned;
 	int level, rc;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a713c803a3a3..67fee545d42a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -31,6 +31,7 @@
 #include <linux/string_choices.h>
 
 #include <asm/apic.h>
+#include <asm/msr.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
@@ -475,24 +476,18 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu)
 
 static void svm_init_erratum_383(void)
 {
-	u32 low, high;
-	int err;
 	u64 val;
 
 	if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
 		return;
 
 	/* Use _safe variants to not break nested virtualization */
-	val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
-	if (err)
+	if (native_read_msr_safe(MSR_AMD64_DC_CFG, &val))
 		return;
 
 	val |= (1ULL << 47);
 
-	low  = lower_32_bits(val);
-	high = upper_32_bits(val);
-
-	native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+	native_write_msr_safe(MSR_AMD64_DC_CFG, val);
 
 	erratum_383_found = true;
 }
@@ -566,7 +561,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier)
 	if (multiplier == __this_cpu_read(current_tsc_ratio))
 		return;
 
-	wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+	wrmsrq(MSR_AMD64_TSC_RATIO, multiplier);
 	__this_cpu_write(current_tsc_ratio, multiplier);
 }
 
@@ -579,15 +574,15 @@ static inline void kvm_cpu_svm_disable(void)
 {
 	uint64_t efer;
 
-	wrmsrl(MSR_VM_HSAVE_PA, 0);
-	rdmsrl(MSR_EFER, efer);
+	wrmsrq(MSR_VM_HSAVE_PA, 0);
+	rdmsrq(MSR_EFER, efer);
 	if (efer & EFER_SVME) {
 		/*
 		 * Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and
 		 * NMI aren't blocked.
 		 */
 		stgi();
-		wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+		wrmsrq(MSR_EFER, efer & ~EFER_SVME);
 	}
 }
 
@@ -616,7 +611,7 @@ static int svm_enable_virtualization_cpu(void)
 	uint64_t efer;
 	int me = raw_smp_processor_id();
 
-	rdmsrl(MSR_EFER, efer);
+	rdmsrq(MSR_EFER, efer);
 	if (efer & EFER_SVME)
 		return -EBUSY;
 
@@ -626,9 +621,9 @@ static int svm_enable_virtualization_cpu(void)
 	sd->next_asid = sd->max_asid + 1;
 	sd->min_asid = max_sev_asid + 1;
 
-	wrmsrl(MSR_EFER, efer | EFER_SVME);
+	wrmsrq(MSR_EFER, efer | EFER_SVME);
 
-	wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa);
+	wrmsrq(MSR_VM_HSAVE_PA, sd->save_area_pa);
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		/*
@@ -649,13 +644,12 @@ static int svm_enable_virtualization_cpu(void)
 	 * erratum is present everywhere).
 	 */
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
-		uint64_t len, status = 0;
+		u64 len, status = 0;
 		int err;
 
-		len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
+		err = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &len);
 		if (!err)
-			status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
-						      &err);
+			err = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, &status);
 
 		if (err)
 			osvw_status = osvw_len = 0;
@@ -1297,8 +1291,12 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm_set_intercept(svm, INTERCEPT_MWAIT);
 	}
 
-	if (!kvm_hlt_in_guest(vcpu->kvm))
-		svm_set_intercept(svm, INTERCEPT_HLT);
+	if (!kvm_hlt_in_guest(vcpu->kvm)) {
+		if (cpu_feature_enabled(X86_FEATURE_IDLE_HLT))
+			svm_set_intercept(svm, INTERCEPT_IDLE_HLT);
+		else
+			svm_set_intercept(svm, INTERCEPT_HLT);
+	}
 
 	control->iopm_base_pa = iopm_base;
 	control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
@@ -1508,6 +1506,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
 }
 
+#ifdef CONFIG_CPU_MITIGATIONS
+static DEFINE_SPINLOCK(srso_lock);
+static atomic_t srso_nr_vms;
+
+static void svm_srso_clear_bp_spec_reduce(void *ign)
+{
+	struct svm_cpu_data *sd = this_cpu_ptr(&svm_data);
+
+	if (!sd->bp_spec_reduce_set)
+		return;
+
+	msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	sd->bp_spec_reduce_set = false;
+}
+
+static void svm_srso_vm_destroy(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	if (atomic_dec_return(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	/*
+	 * Verify a new VM didn't come along, acquire the lock, and increment
+	 * the count before this task acquired the lock.
+	 */
+	if (atomic_read(&srso_nr_vms))
+		return;
+
+	on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1);
+}
+
+static void svm_srso_vm_init(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE))
+		return;
+
+	/*
+	 * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0
+	 * transition, i.e. destroying the last VM, is fully complete, e.g. so
+	 * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs.
+	 */
+	if (atomic_inc_not_zero(&srso_nr_vms))
+		return;
+
+	guard(spinlock)(&srso_lock);
+
+	atomic_inc(&srso_nr_vms);
+}
+#else
+static void svm_srso_vm_init(void) { }
+static void svm_srso_vm_destroy(void) { }
+#endif
+
 static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1540,6 +1595,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
+	if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) &&
+	    !sd->bp_spec_reduce_set) {
+		sd->bp_spec_reduce_set = true;
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT);
+	}
 	svm->guest_state_loaded = true;
 }
 
@@ -1559,7 +1619,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 
-		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT))
+		if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
+		    static_branch_likely(&switch_vcpu_ibpb))
 			indirect_branch_prediction_barrier();
 	}
 	if (kvm_vcpu_apicv_active(vcpu))
@@ -1932,7 +1993,7 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
 
 	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 }
 
 static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -2138,14 +2199,13 @@ static int ac_interception(struct kvm_vcpu *vcpu)
 
 static bool is_erratum_383(void)
 {
-	int err, i;
+	int i;
 	u64 value;
 
 	if (!erratum_383_found)
 		return false;
 
-	value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
-	if (err)
+	if (native_read_msr_safe(MSR_IA32_MC0_STATUS, &value))
 		return false;
 
 	/* Bit 62 may or may not be set for this mce */
@@ -2156,17 +2216,11 @@ static bool is_erratum_383(void)
 
 	/* Clear MCi_STATUS registers */
 	for (i = 0; i < 6; ++i)
-		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
-
-	value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
-	if (!err) {
-		u32 low, high;
+		native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0);
 
+	if (!native_read_msr_safe(MSR_IA32_MCG_STATUS, &value)) {
 		value &= ~(1ULL << 2);
-		low    = lower_32_bits(value);
-		high   = upper_32_bits(value);
-
-		native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+		native_write_msr_safe(MSR_IA32_MCG_STATUS, value);
 	}
 
 	/* Flush tlb to evict multi-match entries */
@@ -2220,6 +2274,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
 	 */
 	if (!sev_es_guest(vcpu->kvm)) {
 		clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+		if (is_smm(vcpu))
+			kvm_smm_changed(vcpu, false);
+#endif
 		kvm_vcpu_reset(vcpu, true);
 	}
 
@@ -2973,11 +3031,7 @@ static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
 	if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb))
 		return kvm_complete_insn_gp(vcpu, err);
 
-	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1);
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb,
-				X86_TRAP_GP |
-				SVM_EVTINJ_TYPE_EXEPT |
-				SVM_EVTINJ_VALID);
+	svm_vmgexit_inject_exception(svm, X86_TRAP_GP);
 	return 1;
 }
 
@@ -3165,6 +3219,27 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 			break;
 		}
+
+		/*
+		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
+		 * without BusLockTrap, bits 5:2 control "external pins", but
+		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
+		 * the guest to set bits 5:2 despite not actually virtualizing
+		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
+		 * 5:2 for backwards compatibility.
+		 */
+		data &= ~GENMASK(5, 2);
+
+		/*
+		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+		 * way to communicate lack of support to the guest.
+		 */
+		if (data & DEBUGCTLMSR_BTF) {
+			kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+			data &= ~DEBUGCTLMSR_BTF;
+		}
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
@@ -3272,6 +3347,17 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	type = svm->vmcb->control.exit_info_2;
 	gva = svm->vmcb->control.exit_info_1;
 
+	/*
+	 * FIXME: Perform segment checks for 32-bit mode, and inject #SS if the
+	 *        stack segment is used.  The intercept takes priority over all
+	 *        #GP checks except CPL>0, but somehow still generates a linear
+	 *        address?  The APM is sorely lacking.
+	 */
+	if (is_noncanonical_address(gva, vcpu, 0)) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+		return 1;
+	}
+
 	return kvm_handle_invpcid(vcpu, type, gva);
 }
 
@@ -3342,6 +3428,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_CR4_WRITE_TRAP]		= cr_trap,
 	[SVM_EXIT_CR8_WRITE_TRAP]		= cr_trap,
 	[SVM_EXIT_INVPCID]                      = invpcid_interception,
+	[SVM_EXIT_IDLE_HLT]			= kvm_emulate_halt,
 	[SVM_EXIT_NPF]				= npf_interception,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
@@ -3504,7 +3591,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 		return interrupt_window_interception(vcpu);
 	else if (exit_code == SVM_EXIT_INTR)
 		return intr_interception(vcpu);
-	else if (exit_code == SVM_EXIT_HLT)
+	else if (exit_code == SVM_EXIT_HLT || exit_code == SVM_EXIT_IDLE_HLT)
 		return kvm_emulate_halt(vcpu);
 	else if (exit_code == SVM_EXIT_NPF)
 		return npf_interception(vcpu);
@@ -3587,7 +3674,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	return svm_invoke_exit_handler(vcpu, exit_code);
 }
 
-static void pre_svm_run(struct kvm_vcpu *vcpu)
+static int pre_svm_run(struct kvm_vcpu *vcpu)
 {
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3609,6 +3696,8 @@ static void pre_svm_run(struct kvm_vcpu *vcpu)
 	/* FIXME: handle wraparound of asid_generation */
 	if (svm->current_vmcb->asid_generation != sd->asid_generation)
 		new_asid(svm, sd);
+
+	return 0;
 }
 
 static void svm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -4116,20 +4205,23 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 		vcpu->arch.nmi_injected = true;
 		svm->nmi_l1_to_l2 = nmi_l1_to_l2;
 		break;
-	case SVM_EXITINTINFO_TYPE_EXEPT:
+	case SVM_EXITINTINFO_TYPE_EXEPT: {
+		u32 error_code = 0;
+
 		/*
 		 * Never re-inject a #VC exception.
 		 */
 		if (vector == X86_TRAP_VC)
 			break;
 
-		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
-			u32 err = svm->vmcb->control.exit_int_info_err;
-			kvm_requeue_exception_e(vcpu, vector, err);
+		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR)
+			error_code = svm->vmcb->control.exit_int_info_err;
 
-		} else
-			kvm_requeue_exception(vcpu, vector);
+		kvm_requeue_exception(vcpu, vector,
+				      exitintinfo & SVM_EXITINTINFO_VALID_ERR,
+				      error_code);
 		break;
+	}
 	case SVM_EXITINTINFO_TYPE_INTR:
 		kvm_queue_interrupt(vcpu, vector, false);
 		break;
@@ -4189,6 +4281,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	/*
+	 * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+	 * VMRUN controls whether or not physical IRQs are masked (KVM always
+	 * runs with V_INTR_MASKING_MASK).  Toggle RFLAGS.IF here to avoid the
+	 * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+	 * into guest state if delivery of an event during VMRUN triggers a
+	 * #VMEXIT, and the guest_state transitions already tell lockdep that
+	 * IRQs are being enabled/disabled.  Note!  GIF=0 for the entirety of
+	 * this path, so IRQs aren't actually unmasked while running host code.
+	 */
+	raw_local_irq_enable();
+
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
@@ -4197,6 +4301,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
+	raw_local_irq_disable();
+
 	guest_state_exit_irqoff();
 }
 
@@ -4231,7 +4337,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (force_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
-	pre_svm_run(vcpu);
+	if (pre_svm_run(vcpu)) {
+		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		vcpu->run->fail_entry.hardware_entry_failure_reason = SVM_EXIT_ERR;
+		vcpu->run->fail_entry.cpu = vcpu->cpu;
+		return EXIT_FASTPATH_EXIT_USERSPACE;
+	}
 
 	sync_lapic_to_cr8(vcpu);
 
@@ -4253,6 +4364,16 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
+	/*
+	 * Hardware only context switches DEBUGCTL if LBR virtualization is
+	 * enabled.  Manually load DEBUGCTL if necessary (and restore it after
+	 * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+	 * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+	 */
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(svm->vmcb->save.dbgctl);
+
 	kvm_wait_lapic_expire(vcpu);
 
 	/*
@@ -4280,6 +4401,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
+
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
@@ -4958,6 +5083,8 @@ static void svm_vm_destroy(struct kvm *kvm)
 {
 	avic_vm_destroy(kvm);
 	sev_vm_destroy(kvm);
+
+	svm_srso_vm_destroy();
 }
 
 static int svm_vm_init(struct kvm *kvm)
@@ -4983,6 +5110,7 @@ static int svm_vm_init(struct kvm *kvm)
 			return ret;
 	}
 
+	svm_srso_vm_init();
 	return 0;
 }
 
@@ -5154,7 +5282,7 @@ static __init void svm_adjust_mmio_mask(void)
 		return;
 
 	/* If memory encryption is not enabled, use existing mask */
-	rdmsrl(MSR_AMD64_SYSCFG, msr);
+	rdmsrq(MSR_AMD64_SYSCFG, msr);
 	if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 		return;
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9d7cdb8fbf87..f16b068c4228 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -335,6 +335,8 @@ struct svm_cpu_data {
 	u32 next_asid;
 	u32 min_asid;
 
+	bool bp_spec_reduce_set;
+
 	struct vmcb *save_area;
 	unsigned long save_area_pa;
 
@@ -361,20 +363,18 @@ static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm)
 #ifdef CONFIG_KVM_AMD_SEV
 static __always_inline bool sev_guest(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	return sev->active;
+	return to_kvm_sev_info(kvm)->active;
 }
 static __always_inline bool sev_es_guest(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 
 	return sev->es_active && !WARN_ON_ONCE(!sev->active);
 }
 
 static __always_inline bool sev_snp_guest(struct kvm *kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
 
 	return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) &&
 	       !WARN_ON_ONCE(!sev_es_guest(kvm));
@@ -581,10 +581,39 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 		return false;
 }
 
+static inline void svm_vmgexit_set_return_code(struct vcpu_svm *svm,
+						u64 response, u64 data)
+{
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, response);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, data);
+}
+
+static inline void svm_vmgexit_inject_exception(struct vcpu_svm *svm, u8 vector)
+{
+	u64 data = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT | vector;
+
+	svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_ISSUE_EXCEPTION, data);
+}
+
+static inline void svm_vmgexit_bad_input(struct vcpu_svm *svm, u64 suberror)
+{
+	svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_MALFORMED_INPUT, suberror);
+}
+
+static inline void svm_vmgexit_success(struct vcpu_svm *svm, u64 data)
+{
+	svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_NO_ACTION, data);
+}
+
+static inline void svm_vmgexit_no_action(struct vcpu_svm *svm, u64 data)
+{
+	svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_NO_ACTION, data);
+}
+
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
 
 extern bool dump_invalid_vmcb;
 
@@ -715,7 +744,7 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu);
 
 /* sev.c */
 
-void pre_sev_run(struct vcpu_svm *svm, int cpu);
+int pre_sev_run(struct vcpu_svm *svm, int cpu);
 void sev_init_vmcb(struct vcpu_svm *svm);
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 2ed80aea3bb1..0c61153b275f 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -170,12 +170,8 @@ SYM_FUNC_START(__svm_vcpu_run)
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
 	/* Enter guest mode */
-	sti
-
 3:	vmrun %_ASM_AX
 4:
-	cli
-
 	/* Pop @svm to RAX while it's the only available register. */
 	pop %_ASM_AX
 
@@ -340,12 +336,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov KVM_VMCB_pa(%rax), %rax
 
 	/* Enter guest mode */
-	sti
-
 1:	vmrun %rax
-
-2:	cli
-
+2:
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 0b844cb97978..ba736cbb0587 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
 
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({					\
+	typeof(vcpu) __vcpu = vcpu;					\
+	__vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu);	\
+	})
+#endif
+
 /*
  * Tracepoint for guest mode entry.
  */
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
 
 	TP_fast_assign(
 		__entry->vcpu_id        = vcpu->vcpu_id;
-		__entry->rip		= kvm_rip_read(vcpu);
+		__entry->rip		= tracing_kvm_rip_read(vcpu);
 		__entry->immediate_exit	= force_immediate_exit;
 
 		kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name,							     \
 	),								     \
 									     \
 	TP_fast_assign(							     \
-		__entry->guest_rip	= kvm_rip_read(vcpu);		     \
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);		     \
 		__entry->isa            = isa;				     \
 		__entry->vcpu_id        = vcpu->vcpu_id;		     \
 		__entry->requests       = READ_ONCE(vcpu->requests);	     \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
 
 	TP_fast_assign(
 		__entry->vcpu_id	= vcpu->vcpu_id;
-		__entry->guest_rip	= kvm_rip_read(vcpu);
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);
 		__entry->fault_address	= fault_address;
 		__entry->error_code	= error_code;
 	),
@@ -830,12 +837,12 @@ TRACE_EVENT(kvm_emulate_insn,
 	TP_ARGS(vcpu, failed),
 
 	TP_STRUCT__entry(
-		__field(    __u64, rip                       )
-		__field(    __u32, csbase                    )
-		__field(    __u8,  len                       )
-		__array(    __u8,  insn,    15	             )
-		__field(    __u8,  flags       	   	     )
-		__field(    __u8,  failed                    )
+		__field(    __u64, rip                              )
+		__field(    __u32, csbase                           )
+		__field(    __u8,  len                              )
+		__array(    __u8,  insn, X86_MAX_INSTRUCTION_LENGTH )
+		__field(    __u8,  flags       	   	            )
+		__field(    __u8,  failed                           )
 		),
 
 	TP_fast_assign(
@@ -846,7 +853,7 @@ TRACE_EVENT(kvm_emulate_insn,
 		__entry->rip = vcpu->arch.emulate_ctxt->_eip - __entry->len;
 		memcpy(__entry->insn,
 		       vcpu->arch.emulate_ctxt->fetch.data,
-		       15);
+		       X86_MAX_INSTRUCTION_LENGTH);
 		__entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt->mode);
 		__entry->failed = failed;
 		),
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e..d268224227f0 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6,6 +6,7 @@
 
 #include <asm/debugreg.h>
 #include <asm/mmu_context.h>
+#include <asm/msr.h>
 
 #include "x86.h"
 #include "cpuid.h"
@@ -2970,7 +2971,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 		case INTR_TYPE_SOFT_EXCEPTION:
 		case INTR_TYPE_SOFT_INTR:
 		case INTR_TYPE_PRIV_SW_EXCEPTION:
-			if (CC(vmcs12->vm_entry_instruction_len > 15) ||
+			if (CC(vmcs12->vm_entry_instruction_len > X86_MAX_INSTRUCTION_LENGTH) ||
 			    CC(vmcs12->vm_entry_instruction_len == 0 &&
 			    CC(!nested_cpu_has_zero_length_injection(vcpu))))
 				return -EINVAL;
@@ -3771,7 +3772,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		break;
 	case GUEST_ACTIVITY_WAIT_SIPI:
 		vmx->nested.nested_run_pending = 0;
-		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 		break;
 	default:
 		break;
@@ -4618,7 +4619,7 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
  */
 static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			   u32 vm_exit_reason, u32 exit_intr_info,
-			   unsigned long exit_qualification)
+			   unsigned long exit_qualification, u32 exit_insn_len)
 {
 	/* update exit information fields: */
 	vmcs12->vm_exit_reason = vm_exit_reason;
@@ -4646,7 +4647,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 					  vm_exit_reason, exit_intr_info);
 
 		vmcs12->vm_exit_intr_info = exit_intr_info;
-		vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		vmcs12->vm_exit_instruction_len = exit_insn_len;
 		vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 
 		/*
@@ -4930,8 +4931,9 @@ vmabort:
  * and modify vmcs12 to make it see what it would expect to see there if
  * L2 was its real guest. Must only be called when in L2 (is_guest_mode())
  */
-void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
-		       u32 exit_intr_info, unsigned long exit_qualification)
+void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
+			 u32 exit_intr_info, unsigned long exit_qualification,
+			 u32 exit_insn_len)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -4981,7 +4983,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		if (vm_exit_reason != -1)
 			prepare_vmcs12(vcpu, vmcs12, vm_exit_reason,
-				       exit_intr_info, exit_qualification);
+				       exit_intr_info, exit_qualification,
+				       exit_insn_len);
 
 		/*
 		 * Must happen outside of sync_vmcs02_to_vmcs12() as it will
@@ -5071,7 +5074,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 
 	/* in case we halted in L2 */
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
 	if (likely(!vmx->fail)) {
 		if (vm_exit_reason != -1)
@@ -5084,6 +5087,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 
@@ -5316,9 +5330,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (enable_shadow_vmcs && !alloc_shadow_vmcs(vcpu))
 		goto out_shadow_vmcs;
 
-	hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_PINNED);
-	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
+	hrtimer_setup(&vmx->nested.preemption_timer, vmx_preemption_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED);
 
 	vmx->nested.vpid02 = allocate_vpid();
 
@@ -7190,8 +7203,8 @@ static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs)
 	msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON;
 
 	/* These MSRs specify bits which the guest must keep fixed off. */
-	rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
-	rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
+	rdmsrq(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
+	rdmsrq(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
 
 	if (vmx_umip_emulated())
 		msrs->cr4_fixed1 |= X86_CR4_UMIP;
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 2c296b6abb8c..6eedcfc91070 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -26,8 +26,26 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
 bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu);
-void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
-		       u32 exit_intr_info, unsigned long exit_qualification);
+void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
+			 u32 exit_intr_info, unsigned long exit_qualification,
+			 u32 exit_insn_len);
+
+static inline void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
+				     u32 exit_intr_info,
+				     unsigned long exit_qualification)
+{
+	u32 exit_insn_len;
+
+	if (to_vmx(vcpu)->fail || vm_exit_reason == -1 ||
+	    (vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
+		exit_insn_len = 0;
+	else
+		exit_insn_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+
+	__nested_vmx_vmexit(vcpu, vm_exit_reason, exit_intr_info,
+			    exit_qualification, exit_insn_len);
+}
+
 void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu);
 int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 77012b2eca0e..231a9633359c 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <asm/msr.h>
 #include <asm/perf_event.h>
 #include "x86.h"
 #include "cpuid.h"
@@ -279,9 +280,9 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu,
 	local_irq_disable();
 	if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) {
 		if (read)
-			rdmsrl(index, msr_info->data);
+			rdmsrq(index, msr_info->data);
 		else
-			wrmsrl(index, msr_info->data);
+			wrmsrq(index, msr_info->data);
 		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
 		local_irq_enable();
 		return true;
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index ec08fa3caf43..d70e5b90087d 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -31,6 +31,8 @@ static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
  */
 static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
+#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
+
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
 	return &(to_vmx(vcpu)->pi_desc);
@@ -89,9 +91,20 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 * current pCPU if the task was migrated.
 	 */
 	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
-		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu);
+
+		/*
+		 * In addition to taking the wakeup lock for the regular/IRQ
+		 * context, tell lockdep it is being taken for the "sched out"
+		 * context as well.  vCPU loads happens in task context, and
+		 * this is taking the lock of the *previous* CPU, i.e. can race
+		 * with both the scheduler and the wakeup handler.
+		 */
+		raw_spin_lock(spinlock);
+		spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_);
 		list_del(&vmx->pi_wakeup_list);
-		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		spin_release(&spinlock->dep_map, _RET_IP_);
+		raw_spin_unlock(spinlock);
 	}
 
 	dest = cpu_physical_id(cpu);
@@ -148,11 +161,23 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct pi_desc old, new;
-	unsigned long flags;
 
-	local_irq_save(flags);
+	lockdep_assert_irqs_disabled();
 
-	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+	/*
+	 * Acquire the wakeup lock using the "sched out" context to workaround
+	 * a lockdep false positive.  When this is called, schedule() holds
+	 * various per-CPU scheduler locks.  When the wakeup handler runs, it
+	 * holds this CPU's wakeup lock while calling try_to_wake_up(), which
+	 * can eventually take the aforementioned scheduler locks, which causes
+	 * lockdep to assume there is deadlock.
+	 *
+	 * Deadlock can't actually occur because IRQs are disabled for the
+	 * entirety of the sched_out critical section, i.e. the wakeup handler
+	 * can't run while the scheduler locks are held.
+	 */
+	raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu),
+			     PI_LOCK_SCHED_OUT);
 	list_add_tail(&vmx->pi_wakeup_list,
 		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
 	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
@@ -176,8 +201,6 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	 */
 	if (pi_test_on(&new))
 		__apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
-
-	local_irq_restore(flags);
 }
 
 static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu)
@@ -274,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
@@ -312,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 
 		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-		    !kvm_irq_is_postable(&irq)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
+		    !kvm_irq_is_postable(&irq))
 			continue;
-		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
@@ -334,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
+		if (!set)
+			continue;
+
+		enable_remapped_mode = false;
 
+		ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",
 					__func__);
@@ -346,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		}
 	}
 
+	if (enable_remapped_mode)
+		ret = irq_set_vcpu_affinity(host_irq, NULL);
+
 	ret = 0;
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 9961e07cf071..df1d0cf76947 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -2,6 +2,7 @@
 /*  Copyright(c) 2021 Intel Corporation. */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/msr.h>
 #include <asm/sgx.h>
 
 #include "x86.h"
@@ -411,16 +412,16 @@ void setup_default_sgx_lepubkeyhash(void)
 	 * MSRs exist but are read-only (locked and not writable).
 	 */
 	if (!enable_sgx || boot_cpu_has(X86_FEATURE_SGX_LC) ||
-	    rdmsrl_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) {
+	    rdmsrq_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) {
 		sgx_pubkey_hash[0] = 0xa6053e051270b7acULL;
 		sgx_pubkey_hash[1] = 0x6cfbe8ba8b3b413dULL;
 		sgx_pubkey_hash[2] = 0xc4916d99f2b3735dULL;
 		sgx_pubkey_hash[3] = 0xd4f8c05909f9bb3bULL;
 	} else {
 		/* MSR_IA32_SGXLEPUBKEYHASH0 is read above */
-		rdmsrl(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]);
-		rdmsrl(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]);
-		rdmsrl(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]);
+		rdmsrq(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]);
+		rdmsrq(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]);
+		rdmsrq(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]);
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6c56d5235f0f..157c23db22be 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -46,6 +46,7 @@
 #include <asm/perf_event.h>
 #include <asm/mmu_context.h>
 #include <asm/mshyperv.h>
+#include <asm/msr.h>
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
 #include <asm/vmx.h>
@@ -273,6 +274,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 		case L1TF_MITIGATION_OFF:
 			l1tf = VMENTER_L1D_FLUSH_NEVER;
 			break;
+		case L1TF_MITIGATION_AUTO:
 		case L1TF_MITIGATION_FLUSH_NOWARN:
 		case L1TF_MITIGATION_FLUSH:
 		case L1TF_MITIGATION_FLUSH_NOSMT:
@@ -380,9 +382,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
 	if (!vmx->disable_fb_clear)
 		return;
 
-	msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL);
+	msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL);
 	msr |= FB_CLEAR_DIS;
-	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr);
 	/* Cache the MSR value to avoid reading it later */
 	vmx->msr_ia32_mcu_opt_ctrl = msr;
 }
@@ -393,7 +395,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 		return;
 
 	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
-	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+	native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
 }
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
@@ -1063,7 +1065,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		 * provide that period, so a CPU could write host's record into
 		 * guest's memory.
 		 */
-		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+		wrmsrq(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
 	i = vmx_find_loadstore_msr_slot(&m->guest, msr);
@@ -1192,13 +1194,13 @@ static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
 {
 	u32 i;
 
-	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
-	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
-	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
-	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status);
+	wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
 	for (i = 0; i < addr_range; i++) {
-		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
-		wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+		wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
 	}
 }
 
@@ -1206,13 +1208,13 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
 {
 	u32 i;
 
-	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
-	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
-	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
-	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status);
+	rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
 	for (i = 0; i < addr_range; i++) {
-		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
-		rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+		rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+		rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
 	}
 }
 
@@ -1225,9 +1227,9 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
 	 * GUEST_IA32_RTIT_CTL is already set in the VMCS.
 	 * Save host state before VM entry.
 	 */
-	rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+	rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
-		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		wrmsrq(MSR_IA32_RTIT_CTL, 0);
 		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges);
 		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges);
 	}
@@ -1248,7 +1250,7 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 	 * i.e. RTIT_CTL is always cleared on VM-Exit.  Restore it if necessary.
 	 */
 	if (vmx->pt_desc.host.ctl)
-		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+		wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
@@ -1338,7 +1340,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
 	}
 
-	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
 	savesegment(fs, fs_sel);
 	savesegment(gs, gs_sel);
@@ -1362,7 +1364,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 	++vmx->vcpu.stat.host_state_reload;
 
 #ifdef CONFIG_X86_64
-	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #endif
 	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
 		kvm_load_ldt(host_state->ldt_sel);
@@ -1382,7 +1384,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 #endif
 	invalidate_tss_limit();
 #ifdef CONFIG_X86_64
-	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+	wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
 	load_fixmap_gdt(raw_smp_processor_id());
 	vmx->guest_state_loaded = false;
@@ -1394,7 +1396,7 @@ static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
 {
 	preempt_disable();
 	if (vmx->guest_state_loaded)
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+		rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 	preempt_enable();
 	return vmx->msr_guest_kernel_gs_base;
 }
@@ -1403,7 +1405,7 @@ static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 {
 	preempt_disable();
 	if (vmx->guest_state_loaded)
-		wrmsrl(MSR_KERNEL_GS_BASE, data);
+		wrmsrq(MSR_KERNEL_GS_BASE, data);
 	preempt_enable();
 	vmx->msr_guest_kernel_gs_base = data;
 }
@@ -1477,7 +1479,8 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 		 * performs IBPB on nested VM-Exit (a single nested transition
 		 * may switch the active VMCS multiple times).
 		 */
-		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
+		if (static_branch_likely(&switch_vcpu_ibpb) &&
+		    (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
 			indirect_branch_prediction_barrier();
 	}
 
@@ -1514,16 +1517,12 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
  */
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
-
-	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
 void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -2577,11 +2576,39 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr)
 {
 	u64 allowed;
 
-	rdmsrl(msr, allowed);
+	rdmsrq(msr, allowed);
 
 	return  ctl_opt & allowed;
 }
 
+#define vmx_check_entry_exit_pairs(pairs, entry_controls, exit_controls)	\
+({										\
+	int i, r = 0;								\
+										\
+	BUILD_BUG_ON(sizeof(pairs[0].entry_control) != sizeof(entry_controls));	\
+	BUILD_BUG_ON(sizeof(pairs[0].exit_control)  != sizeof(exit_controls));	\
+										\
+	for (i = 0; i < ARRAY_SIZE(pairs); i++) {				\
+		typeof(entry_controls) n_ctrl = pairs[i].entry_control;		\
+		typeof(exit_controls) x_ctrl = pairs[i].exit_control;		\
+										\
+		if (!(entry_controls & n_ctrl) == !(exit_controls & x_ctrl))	\
+			continue;						\
+										\
+		pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, "		\
+			     "entry = %llx (%llx), exit = %llx (%llx)\n",	\
+			     (u64)(entry_controls & n_ctrl), (u64)n_ctrl,	\
+			     (u64)(exit_controls & x_ctrl), (u64)x_ctrl);	\
+										\
+		if (error_on_inconsistent_vmcs_config)				\
+			r = -EIO;						\
+										\
+		entry_controls &= ~n_ctrl;					\
+		exit_controls &= ~x_ctrl;					\
+	}									\
+	r;									\
+})
+
 static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			     struct vmx_capability *vmx_cap)
 {
@@ -2593,7 +2620,6 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	u32 _vmentry_control = 0;
 	u64 basic_msr;
 	u64 misc_msr;
-	int i;
 
 	/*
 	 * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory.
@@ -2697,22 +2723,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 				&_vmentry_control))
 		return -EIO;
 
-	for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) {
-		u32 n_ctrl = vmcs_entry_exit_pairs[i].entry_control;
-		u32 x_ctrl = vmcs_entry_exit_pairs[i].exit_control;
-
-		if (!(_vmentry_control & n_ctrl) == !(_vmexit_control & x_ctrl))
-			continue;
-
-		pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, entry = %x, exit = %x\n",
-			     _vmentry_control & n_ctrl, _vmexit_control & x_ctrl);
-
-		if (error_on_inconsistent_vmcs_config)
-			return -EIO;
-
-		_vmentry_control &= ~n_ctrl;
-		_vmexit_control &= ~x_ctrl;
-	}
+	if (vmx_check_entry_exit_pairs(vmcs_entry_exit_pairs,
+				       _vmentry_control, _vmexit_control))
+		return -EIO;
 
 	/*
 	 * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they
@@ -2735,7 +2748,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 		break;
 	}
 
-	rdmsrl(MSR_IA32_VMX_BASIC, basic_msr);
+	rdmsrq(MSR_IA32_VMX_BASIC, basic_msr);
 
 	/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
 	if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE)
@@ -2755,7 +2768,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB)
 		return -EIO;
 
-	rdmsrl(MSR_IA32_VMX_MISC, misc_msr);
+	rdmsrq(MSR_IA32_VMX_MISC, misc_msr);
 
 	vmcs_conf->basic = basic_msr;
 	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
@@ -2839,7 +2852,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
 
 fault:
 	WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n",
-		  rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr);
+		  rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr);
 	cr4_clear_bits(X86_CR4_VMXE);
 
 	return -EFAULT;
@@ -3523,7 +3536,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vmcs_writel(GUEST_CR4, hw_cr4);
 
 	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 }
 
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
@@ -4380,7 +4393,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32))
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, 0);
 
-	rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
+	rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl);
 	vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl);   /* 22.2.3 */
 
 	if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
@@ -5215,6 +5228,12 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu)
 	       (kvm_get_rflags(vcpu) & X86_EFLAGS_AC);
 }
 
+static bool is_xfd_nm_fault(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.guest_fpu.fpstate->xfd &&
+	       !kvm_is_cr0_bit_set(vcpu, X86_CR0_TS);
+}
+
 static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5241,7 +5260,8 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	 * point.
 	 */
 	if (is_nm_fault(intr_info)) {
-		kvm_queue_exception(vcpu, NM_VECTOR);
+		kvm_queue_exception_p(vcpu, NM_VECTOR,
+				      is_xfd_nm_fault(vcpu) ? vcpu->arch.guest_fpu.xfd_err : 0);
 		return 1;
 	}
 
@@ -5821,7 +5841,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
 		      ? PFERR_FETCH_MASK : 0;
 	/* ept page table entry is present? */
-	error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK)
+	error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
 		      ? PFERR_PRESENT_MASK : 0;
 
 	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
@@ -5875,11 +5895,35 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu)
+/*
+ * Returns true if emulation is required (due to the vCPU having invalid state
+ * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the
+ * current vCPU state.
+ */
+static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	return vmx->emulation_required && !vmx->rmode.vm86_active &&
+	if (!vmx->emulation_required)
+		return false;
+
+	/*
+	 * It is architecturally impossible for emulation to be required when a
+	 * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if
+	 * guest state is invalid and unrestricted guest is disabled, i.e. KVM
+	 * should synthesize VM-Fail instead emulation L2 code.  This path is
+	 * only reachable if userspace modifies L2 guest state after KVM has
+	 * performed the nested VM-Enter consistency checks.
+	 */
+	if (vmx->nested.nested_run_pending)
+		return true;
+
+	/*
+	 * KVM only supports emulating exceptions if the vCPU is in Real Mode.
+	 * If emulation is required, KVM can't perform a successful VM-Enter to
+	 * inject the exception.
+	 */
+	return !vmx->rmode.vm86_active &&
 	       (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected);
 }
 
@@ -5902,7 +5946,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (!kvm_emulate_instruction(vcpu, 0))
 			return 0;
 
-		if (vmx_emulation_required_with_pending_exception(vcpu)) {
+		if (vmx_unhandleable_emulation_required(vcpu)) {
 			kvm_prepare_emulation_failure_exit(vcpu);
 			return 0;
 		}
@@ -5926,7 +5970,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
 {
-	if (vmx_emulation_required_with_pending_exception(vcpu)) {
+	if (vmx_unhandleable_emulation_required(vcpu)) {
 		kvm_prepare_emulation_failure_exit(vcpu);
 		return 0;
 	}
@@ -6703,7 +6747,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	vcpu->stat.l1d_flush++;
 
 	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-		native_wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
 		return;
 	}
 
@@ -7001,17 +7045,16 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
 	 * MSR value is not clobbered by the host activity before the guest
 	 * has chance to consume it.
 	 *
-	 * Do not blindly read xfd_err here, since this exception might
-	 * be caused by L1 interception on a platform which doesn't
-	 * support xfd at all.
+	 * Update the guest's XFD_ERR if and only if XFD is enabled, as the #NM
+	 * interception may have been caused by L1 interception.  Per the SDM,
+	 * XFD_ERR is not modified for non-XFD #NM, i.e. if CR0.TS=1.
 	 *
-	 * Do it conditionally upon guest_fpu::xfd. xfd_err matters
-	 * only when xfd contains a non-zero value.
-	 *
-	 * Queuing exception is done in vmx_handle_exit. See comment there.
+	 * Note, XFD_ERR is updated _before_ the #NM interception check, i.e.
+	 * unlike CR2 and DR6, the value is not a payload that is attached to
+	 * the #NM exception.
 	 */
-	if (vcpu->arch.guest_fpu.fpstate->xfd)
-		rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+	if (is_xfd_nm_fault(vcpu))
+		rdmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 }
 
 static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
@@ -7161,13 +7204,17 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
 	case INTR_TYPE_SOFT_EXCEPTION:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
 		fallthrough;
-	case INTR_TYPE_HARD_EXCEPTION:
-		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
-			u32 err = vmcs_read32(error_code_field);
-			kvm_requeue_exception_e(vcpu, vector, err);
-		} else
-			kvm_requeue_exception(vcpu, vector);
+	case INTR_TYPE_HARD_EXCEPTION: {
+		u32 error_code = 0;
+
+		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK)
+			error_code = vmcs_read32(error_code_field);
+
+		kvm_requeue_exception(vcpu, vector,
+				      idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK,
+				      error_code);
 		break;
+	}
 	case INTR_TYPE_SOFT_INTR:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
 		fallthrough;
@@ -7262,7 +7309,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
 		return;
 
 	if (flags & VMX_RUN_SAVE_SPEC_CTRL)
-		vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL);
+		vmx->spec_ctrl = native_rdmsrq(MSR_IA32_SPEC_CTRL);
 
 	/*
 	 * If the guest/host SPEC_CTRL values differ, restore the host value.
@@ -7273,7 +7320,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
 	 */
 	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
 	    vmx->spec_ctrl != hostval)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
+		native_wrmsrq(MSR_IA32_SPEC_CTRL, hostval);
 
 	barrier_nospec();
 }
@@ -7313,10 +7360,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	 * mitigation for MDS is done late in VMentry and is still
 	 * executed in spite of L1D Flush. This is because an extra VERW
 	 * should not matter much after the big hammer L1D Flush.
+	 *
+	 * cpu_buf_vm_clear is used when system is not vulnerable to MDS/TAA,
+	 * and is affected by MMIO Stale Data. In such cases mitigation in only
+	 * needed against an MMIO capable guest.
 	 */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
-	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
+	else if (static_branch_unlikely(&cpu_buf_vm_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
 		mds_clear_cpu_buffers();
 
@@ -7458,8 +7509,8 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	}
 
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (vmx->host_debugctlmsr)
-		update_debugctlmsr(vmx->host_debugctlmsr);
+	if (vcpu->arch.host_debugctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
 
 #ifndef CONFIG_X86_64
 	/*
@@ -7655,6 +7706,7 @@ int vmx_vm_init(struct kvm *kvm)
 		case L1TF_MITIGATION_FLUSH_NOWARN:
 			/* 'I explicitly don't care' is set */
 			break;
+		case L1TF_MITIGATION_AUTO:
 		case L1TF_MITIGATION_FLUSH:
 		case L1TF_MITIGATION_FLUSH_NOSMT:
 		case L1TF_MITIGATION_FULL:
@@ -7914,7 +7966,7 @@ static __init u64 vmx_get_perf_capabilities(void)
 		return 0;
 
 	if (boot_cpu_has(X86_FEATURE_PDCM))
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+		rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
 
 	if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
 		x86_perf_get_lbr(&vmx_lbr_caps);
@@ -8009,38 +8061,50 @@ static __init void vmx_set_cpu_caps(void)
 		kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG);
 }
 
-static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
-				  struct x86_instruction_info *info)
+static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info,
+				  unsigned long *exit_qualification)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	unsigned short port;
-	bool intercept;
 	int size;
+	bool imm;
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
 
 	if (info->intercept == x86_intercept_in ||
 	    info->intercept == x86_intercept_ins) {
 		port = info->src_val;
 		size = info->dst_bytes;
+		imm  = info->src_type == OP_IMM;
 	} else {
 		port = info->dst_val;
 		size = info->src_bytes;
+		imm  = info->dst_type == OP_IMM;
 	}
 
-	/*
-	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
-	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
-	 * control.
-	 *
-	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
-	 */
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		intercept = nested_cpu_has(vmcs12,
-					   CPU_BASED_UNCOND_IO_EXITING);
-	else
-		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
 
-	/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
-	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+	*exit_qualification = ((unsigned long)port << 16) | (size - 1);
+
+	if (info->intercept == x86_intercept_ins ||
+	    info->intercept == x86_intercept_outs)
+		*exit_qualification |= BIT(4);
+
+	if (info->rep_prefix)
+		*exit_qualification |= BIT(5);
+
+	if (imm)
+		*exit_qualification |= BIT(6);
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
 }
 
 int vmx_check_intercept(struct kvm_vcpu *vcpu,
@@ -8049,26 +8113,34 @@ int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			struct x86_exception *exception)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned long exit_qualification = 0;
+	u32 vm_exit_reason;
+	u64 exit_insn_len;
 
 	switch (info->intercept) {
-	/*
-	 * RDPID causes #UD if disabled through secondary execution controls.
-	 * Because it is marked as EmulateOnUD, we need to intercept it here.
-	 * Note, RDPID is hidden behind ENABLE_RDTSCP.
-	 */
 	case x86_intercept_rdpid:
+		/*
+		 * RDPID causes #UD if not enabled through secondary execution
+		 * controls (ENABLE_RDTSCP).  Note, the implicit MSR access to
+		 * TSC_AUX is NOT subject to interception, i.e. checking only
+		 * the dedicated execution control is architecturally correct.
+		 */
 		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) {
 			exception->vector = UD_VECTOR;
 			exception->error_code_valid = false;
 			return X86EMUL_PROPAGATE_FAULT;
 		}
-		break;
+		return X86EMUL_CONTINUE;
 
 	case x86_intercept_in:
 	case x86_intercept_ins:
 	case x86_intercept_out:
 	case x86_intercept_outs:
-		return vmx_check_intercept_io(vcpu, info);
+		if (!vmx_is_io_intercepted(vcpu, info, &exit_qualification))
+			return X86EMUL_CONTINUE;
+
+		vm_exit_reason = EXIT_REASON_IO_INSTRUCTION;
+		break;
 
 	case x86_intercept_lgdt:
 	case x86_intercept_lidt:
@@ -8081,7 +8153,24 @@ int vmx_check_intercept(struct kvm_vcpu *vcpu,
 		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
 			return X86EMUL_CONTINUE;
 
-		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+		if (info->intercept == x86_intercept_lldt ||
+		    info->intercept == x86_intercept_ltr ||
+		    info->intercept == x86_intercept_sldt ||
+		    info->intercept == x86_intercept_str)
+			vm_exit_reason = EXIT_REASON_LDTR_TR;
+		else
+			vm_exit_reason = EXIT_REASON_GDTR_IDTR;
+		/*
+		 * FIXME: Decode the ModR/M to generate the correct exit
+		 *        qualification for memory operands.
+		 */
+		break;
+
+	case x86_intercept_hlt:
+		if (!nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING))
+			return X86EMUL_CONTINUE;
+
+		vm_exit_reason = EXIT_REASON_HLT;
 		break;
 
 	case x86_intercept_pause:
@@ -8094,17 +8183,24 @@ int vmx_check_intercept(struct kvm_vcpu *vcpu,
 		 * the PAUSE.
 		 */
 		if ((info->rep_prefix != REPE_PREFIX) ||
-		    !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING))
+		    !nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING))
 			return X86EMUL_CONTINUE;
 
+		vm_exit_reason = EXIT_REASON_PAUSE_INSTRUCTION;
 		break;
 
 	/* TODO: check more intercepts... */
 	default:
-		break;
+		return X86EMUL_UNHANDLEABLE;
 	}
 
-	return X86EMUL_UNHANDLEABLE;
+	exit_insn_len = abs_diff((s64)info->next_rip, (s64)info->rip);
+	if (!exit_insn_len || exit_insn_len > X86_MAX_INSTRUCTION_LENGTH)
+		return X86EMUL_UNHANDLEABLE;
+
+	__nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification,
+			    exit_insn_len);
+	return X86EMUL_INTERCEPTED;
 }
 
 #ifdef CONFIG_X86_64
@@ -8419,7 +8515,7 @@ __init int vmx_hardware_setup(void)
 		kvm_enable_efer_bits(EFER_NX);
 
 	if (boot_cpu_has(X86_FEATURE_MPX)) {
-		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
+		rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs);
 		WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost");
 	}
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8b111ce1087c..951e44dc9d0e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -340,8 +340,6 @@ struct vcpu_vmx {
 	/* apic deadline value in host tsc */
 	u64 hv_deadline_tsc;
 
-	unsigned long host_debugctlmsr;
-
 	/*
 	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
 	 * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 633c87e2fd92..96677576c836 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -118,7 +118,7 @@ do_exception:
 
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 
-	asm volatile("1: vmread %2, %1\n\t"
+	asm volatile("1: vmread %[field], %[output]\n\t"
 		     ".byte 0x3e\n\t" /* branch taken hint */
 		     "ja 3f\n\t"
 
@@ -127,24 +127,26 @@ do_exception:
 		      * @field, and bounce through the trampoline to preserve
 		      * volatile registers.
 		      */
-		     "xorl %k1, %k1\n\t"
+		     "xorl %k[output], %k[output]\n\t"
 		     "2:\n\t"
-		     "push %1\n\t"
-		     "push %2\n\t"
+		     "push %[output]\n\t"
+		     "push %[field]\n\t"
 		     "call vmread_error_trampoline\n\t"
 
 		     /*
 		      * Unwind the stack.  Note, the trampoline zeros out the
 		      * memory for @fault so that the result is '0' on error.
 		      */
-		     "pop %2\n\t"
-		     "pop %1\n\t"
+		     "pop %[field]\n\t"
+		     "pop %[output]\n\t"
 		     "3:\n\t"
 
 		     /* VMREAD faulted.  As above, except push '1' for @fault. */
-		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %1)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[output])
 
-		     : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc");
+		     : ASM_CALL_CONSTRAINT, [output] "=&r" (value)
+		     : [field] "r" (field)
+		     : "cc");
 	return value;
 
 #endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29..5bdb5b854924 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -578,7 +578,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) {
 		values = &msrs->values[slot];
 		if (values->host != values->curr) {
-			wrmsrl(kvm_uret_msrs_list[slot], values->host);
+			wrmsrq(kvm_uret_msrs_list[slot], values->host);
 			values->curr = values->host;
 		}
 	}
@@ -590,10 +590,10 @@ static int kvm_probe_user_return_msr(u32 msr)
 	int ret;
 
 	preempt_disable();
-	ret = rdmsrl_safe(msr, &val);
+	ret = rdmsrq_safe(msr, &val);
 	if (ret)
 		goto out;
-	ret = wrmsrl_safe(msr, val);
+	ret = wrmsrq_safe(msr, val);
 out:
 	preempt_enable();
 	return ret;
@@ -630,7 +630,7 @@ static void kvm_user_return_msr_cpu_online(void)
 	int i;
 
 	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
-		rdmsrl_safe(kvm_uret_msrs_list[i], &value);
+		rdmsrq_safe(kvm_uret_msrs_list[i], &value);
 		msrs->values[i].host = value;
 		msrs->values[i].curr = value;
 	}
@@ -644,7 +644,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 	value = (value & mask) | (msrs->values[slot].host & ~mask);
 	if (value == msrs->values[slot].curr)
 		return 0;
-	err = wrmsrl_safe(kvm_uret_msrs_list[slot], value);
+	err = wrmsrq_safe(kvm_uret_msrs_list[slot], value);
 	if (err)
 		return 1;
 
@@ -800,9 +800,9 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
-static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
-		unsigned nr, bool has_error, u32 error_code,
-	        bool has_payload, unsigned long payload, bool reinject)
+static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned int nr,
+				   bool has_error, u32 error_code,
+				   bool has_payload, unsigned long payload)
 {
 	u32 prev_nr;
 	int class1, class2;
@@ -810,13 +810,10 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	/*
-	 * If the exception is destined for L2 and isn't being reinjected,
-	 * morph it to a VM-Exit if L1 wants to intercept the exception.  A
-	 * previously injected exception is not checked because it was checked
-	 * when it was original queued, and re-checking is incorrect if _L1_
-	 * injected the exception, in which case it's exempt from interception.
+	 * If the exception is destined for L2, morph it to a VM-Exit if L1
+	 * wants to intercept the exception.
 	 */
-	if (!reinject && is_guest_mode(vcpu) &&
+	if (is_guest_mode(vcpu) &&
 	    kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) {
 		kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code,
 					   has_payload, payload);
@@ -825,28 +822,9 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
 	queue:
-		if (reinject) {
-			/*
-			 * On VM-Entry, an exception can be pending if and only
-			 * if event injection was blocked by nested_run_pending.
-			 * In that case, however, vcpu_enter_guest() requests an
-			 * immediate exit, and the guest shouldn't proceed far
-			 * enough to need reinjection.
-			 */
-			WARN_ON_ONCE(kvm_is_exception_pending(vcpu));
-			vcpu->arch.exception.injected = true;
-			if (WARN_ON_ONCE(has_payload)) {
-				/*
-				 * A reinjected event has already
-				 * delivered its payload.
-				 */
-				has_payload = false;
-				payload = 0;
-			}
-		} else {
-			vcpu->arch.exception.pending = true;
-			vcpu->arch.exception.injected = false;
-		}
+		vcpu->arch.exception.pending = true;
+		vcpu->arch.exception.injected = false;
+
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.vector = nr;
 		vcpu->arch.exception.error_code = error_code;
@@ -887,30 +865,53 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
+	kvm_multiple_exception(vcpu, nr, false, 0, false, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception);
 
-void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
-{
-	kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
-}
-EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
 void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
 			   unsigned long payload)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
+	kvm_multiple_exception(vcpu, nr, false, 0, true, payload);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_p);
 
 static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
 				    u32 error_code, unsigned long payload)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code,
-			       true, payload, false);
+	kvm_multiple_exception(vcpu, nr, true, error_code, true, payload);
 }
 
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr,
+			   bool has_error_code, u32 error_code)
+{
+
+	/*
+	 * On VM-Entry, an exception can be pending if and only if event
+	 * injection was blocked by nested_run_pending.  In that case, however,
+	 * vcpu_enter_guest() requests an immediate exit, and the guest
+	 * shouldn't proceed far enough to need reinjection.
+	 */
+	WARN_ON_ONCE(kvm_is_exception_pending(vcpu));
+
+	/*
+	 * Do not check for interception when injecting an event for L2, as the
+	 * exception was checked for intercept when it was original queued, and
+	 * re-checking is incorrect if _L1_ injected the exception, in which
+	 * case it's exempt from interception.
+	 */
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	vcpu->arch.exception.injected = true;
+	vcpu->arch.exception.has_error_code = has_error_code;
+	vcpu->arch.exception.vector = nr;
+	vcpu->arch.exception.error_code = error_code;
+	vcpu->arch.exception.has_payload = false;
+	vcpu->arch.exception.payload = 0;
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
 {
 	if (err)
@@ -980,16 +981,10 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu)
 
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
+	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
 
-void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
-{
-	kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
-}
-EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
-
 /*
  * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
  * a #GP and return false.
@@ -1179,7 +1174,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
+			wrmsrq(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 
 	if (cpu_feature_enabled(X86_FEATURE_PKU) &&
@@ -1210,7 +1205,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+			wrmsrq(MSR_IA32_XSS, kvm_host.xss);
 	}
 
 }
@@ -1264,7 +1259,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 	return 0;
 }
 
@@ -1589,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
 	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
-	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1623,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 	if (!boot_cpu_has_bug(X86_BUG_RFDS))
 		data |= ARCH_CAP_RFDS_NO;
+	if (!boot_cpu_has_bug(X86_BUG_ITS))
+		data |= ARCH_CAP_ITS_NO;
 
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
@@ -1665,7 +1662,7 @@ static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 		*data = MSR_PLATFORM_INFO_CPUID_FAULT;
 		break;
 	case MSR_IA32_UCODE_REV:
-		rdmsrl_safe(index, data);
+		rdmsrq_safe(index, data);
 		break;
 	default:
 		return kvm_x86_call(get_feature_msr)(index, data);
@@ -2080,10 +2077,20 @@ EXPORT_SYMBOL_GPL(kvm_handle_invalid_op);
 
 static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn)
 {
-	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) &&
-	    !guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT))
+	bool enabled;
+
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS))
+		goto emulate_as_nop;
+
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT))
+		enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT);
+	else
+		enabled = vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT;
+
+	if (!enabled)
 		return kvm_handle_invalid_op(vcpu);
 
+emulate_as_nop:
 	pr_warn_once("%s instruction emulated as NOP!\n", insn);
 	return kvm_emulate_as_nop(vcpu);
 }
@@ -2569,6 +2576,9 @@ EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier);
 
 static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset)
 {
+	if (vcpu->arch.guest_tsc_protected)
+		return;
+
 	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
 				   vcpu->arch.l1_tsc_offset,
 				   l1_offset);
@@ -2626,12 +2636,18 @@ static inline bool kvm_check_tsc_unstable(void)
  * participates in.
  */
 static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
-				  u64 ns, bool matched)
+				  u64 ns, bool matched, bool user_set_tsc)
 {
 	struct kvm *kvm = vcpu->kvm;
 
 	lockdep_assert_held(&kvm->arch.tsc_write_lock);
 
+	if (vcpu->arch.guest_tsc_protected)
+		return;
+
+	if (user_set_tsc)
+		vcpu->kvm->arch.user_set_tsc = true;
+
 	/*
 	 * We also track th most recent recorded KHZ, write and time to
 	 * allow the matching interval to be extended at each write.
@@ -2717,8 +2733,6 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
 		}
 	}
 
-	if (user_value)
-		kvm->arch.user_set_tsc = true;
 
 	/*
 	 * For a reliable TSC, we can match TSC offsets, and for an unstable
@@ -2738,7 +2752,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
 		matched = true;
 	}
 
-	__kvm_synchronize_tsc(vcpu, offset, data, ns, matched);
+	__kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 }
 
@@ -3116,15 +3130,17 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	return data.clock;
 }
 
-static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
+static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,
+				    struct kvm_vcpu *vcpu,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset,
-				    bool force_tsc_unstable)
+				    unsigned int offset)
 {
-	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
+	struct pvclock_vcpu_time_info hv_clock;
 	unsigned long flags;
 
+	memcpy(&hv_clock, ref_hv_clock, sizeof(hv_clock));
+
 	read_lock_irqsave(&gpc->lock, flags);
 	while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) {
 		read_unlock_irqrestore(&gpc->lock, flags);
@@ -3144,52 +3160,34 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	 * it is consistent.
 	 */
 
-	guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1;
+	guest_hv_clock->version = hv_clock.version = (guest_hv_clock->version + 1) | 1;
 	smp_wmb();
 
 	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-	vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+	hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
 
-	if (vcpu->pvclock_set_guest_stopped_request) {
-		vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
-		vcpu->pvclock_set_guest_stopped_request = false;
-	}
-
-	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
-
-	if (force_tsc_unstable)
-		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+	memcpy(guest_hv_clock, &hv_clock, sizeof(*guest_hv_clock));
 
 	smp_wmb();
 
-	guest_hv_clock->version = ++vcpu->hv_clock.version;
+	guest_hv_clock->version = ++hv_clock.version;
 
 	kvm_gpc_mark_dirty_in_slot(gpc);
 	read_unlock_irqrestore(&gpc->lock, flags);
 
-	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+	trace_kvm_pvclock_update(vcpu->vcpu_id, &hv_clock);
 }
 
-static int kvm_guest_time_update(struct kvm_vcpu *v)
+int kvm_guest_time_update(struct kvm_vcpu *v)
 {
+	struct pvclock_vcpu_time_info hv_clock = {};
 	unsigned long flags, tgt_tsc_khz;
 	unsigned seq;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
 	s64 kernel_ns;
 	u64 tsc_timestamp, host_tsc;
-	u8 pvclock_flags;
 	bool use_master_clock;
-#ifdef CONFIG_KVM_XEN
-	/*
-	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
-	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
-	 * This default behaviour led to bugs in some guest kernels which cause
-	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
-	 */
-	bool xen_pvclock_tsc_unstable =
-		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
-#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3250,35 +3248,57 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
-				   &vcpu->hv_clock.tsc_shift,
-				   &vcpu->hv_clock.tsc_to_system_mul);
+				   &vcpu->pvclock_tsc_shift,
+				   &vcpu->pvclock_tsc_mul);
 		vcpu->hw_tsc_khz = tgt_tsc_khz;
-		kvm_xen_update_tsc_info(v);
 	}
 
-	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
-	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+	hv_clock.tsc_shift = vcpu->pvclock_tsc_shift;
+	hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul;
+	hv_clock.tsc_timestamp = tsc_timestamp;
+	hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
 
 	/* If the host uses TSC clocksource, then it is stable */
-	pvclock_flags = 0;
+	hv_clock.flags = 0;
 	if (use_master_clock)
-		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
+		hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT;
 
-	vcpu->hv_clock.flags = pvclock_flags;
+	if (vcpu->pv_time.active) {
+		/*
+		 * GUEST_STOPPED is only supported by kvmclock, and KVM's
+		 * historic behavior is to only process the request if kvmclock
+		 * is active/enabled.
+		 */
+		if (vcpu->pvclock_set_guest_stopped_request) {
+			hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
+			vcpu->pvclock_set_guest_stopped_request = false;
+		}
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->pv_time, 0);
+
+		hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED;
+	}
+
+	kvm_hv_setup_tsc_page(v->kvm, &hv_clock);
 
-	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 *
+	 * Note!  Clear TSC_STABLE only for Xen clocks, i.e. the order matters!
+	 */
+	if (ka->xen.hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		hv_clock.flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	if (vcpu->xen.vcpu_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time),
-					xen_pvclock_tsc_unstable);
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_info_cache,
+					offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
-					xen_pvclock_tsc_unstable);
+		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0);
 #endif
-	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
 
@@ -3544,7 +3564,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 					sizeof(u64)))
 		return 1;
 
-	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+	vcpu->arch.apf.send_always = (data & KVM_ASYNC_PF_SEND_ALWAYS);
 	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 
 	kvm_async_pf_wakeup_all(vcpu);
@@ -3733,7 +3753,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
 
-	if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr)
+	/*
+	 * Do not allow host-initiated writes to trigger the Xen hypercall
+	 * page setup; it could incur locking paths which are not expected
+	 * if userspace sets the MSR in an unusual location.
+	 */
+	if (kvm_xen_is_hypercall_page_msr(vcpu->kvm, msr) &&
+	    !msr_info->host_initiated)
 		return kvm_xen_write_hypercall_page(vcpu, data);
 
 	switch (msr) {
@@ -3803,7 +3829,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_PRED_CMD, data);
+		wrmsrq(MSR_IA32_PRED_CMD, data);
 		break;
 	}
 	case MSR_IA32_FLUSH_CMD:
@@ -3816,7 +3842,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
 		break;
 	case MSR_EFER:
 		return set_efer(vcpu, msr_info);
@@ -3889,7 +3915,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3))
 				return 1;
 			vcpu->arch.ia32_misc_enable_msr = data;
-			kvm_update_cpuid_runtime(vcpu);
+			vcpu->arch.cpuid_dynamic_bits_dirty = true;
 		} else {
 			vcpu->arch.ia32_misc_enable_msr = data;
 		}
@@ -3906,7 +3932,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		if (msr_info->host_initiated) {
 			kvm_synchronize_tsc(vcpu, &data);
-		} else {
+		} else if (!vcpu->arch.guest_tsc_protected) {
 			u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset;
 			adjust_tsc_offset_guest(vcpu, adj);
 			vcpu->arch.ia32_tsc_adjust_msr += adj;
@@ -3924,7 +3950,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & ~kvm_caps.supported_xss)
 			return 1;
 		vcpu->arch.ia32_xss = data;
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
@@ -4573,6 +4599,11 @@ static bool kvm_is_vm_type_supported(unsigned long type)
 	return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
 }
 
+static inline u64 kvm_sync_valid_fields(struct kvm *kvm)
+{
+	return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -4681,7 +4712,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_REGS:
-		r = KVM_SYNC_X86_VALID_FIELDS;
+		r = kvm_sync_valid_fields(kvm);
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
 		r = KVM_CLOCK_VALID_FLAGS;
@@ -4986,7 +5017,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			u64 offset = kvm_compute_l1_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_vcpu_write_tsc_offset(vcpu, offset);
-			vcpu->arch.tsc_catchup = 1;
+			if (!vcpu->arch.guest_tsc_protected)
+				vcpu->arch.tsc_catchup = 1;
 		}
 
 		if (kvm_lapic_hv_timer_in_use(vcpu))
@@ -5725,8 +5757,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
 		tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset;
 		ns = get_kvmclock_base_ns();
 
-		kvm->arch.user_set_tsc = true;
-		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched);
+		__kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched, true);
 		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 		r = 0;
@@ -6905,23 +6936,15 @@ static int kvm_arch_suspend_notifier(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
-	int ret = 0;
 
-	mutex_lock(&kvm->lock);
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!vcpu->arch.pv_time.active)
-			continue;
-
-		ret = kvm_set_guest_paused(vcpu);
-		if (ret) {
-			kvm_err("Failed to pause guest VCPU%d: %d\n",
-				vcpu->vcpu_id, ret);
-			break;
-		}
-	}
-	mutex_unlock(&kvm->lock);
+	/*
+	 * Ignore the return, marking the guest paused only "fails" if the vCPU
+	 * isn't using kvmclock; continuing on is correct and desirable.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		(void)kvm_set_guest_paused(vcpu);
 
-	return ret ? NOTIFY_BAD : NOTIFY_DONE;
+	return NOTIFY_DONE;
 }
 
 int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state)
@@ -9715,7 +9738,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	 * with an exception.  PAT[0] is set to WB on RESET and also by the
 	 * kernel, i.e. failure indicates a kernel bug or broken firmware.
 	 */
-	if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
+	if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) ||
 	    (host_pat & GENMASK(2, 0)) != 6) {
 		pr_err("host PAT[0] is not WB\n");
 		return -EIO;
@@ -9749,15 +9772,15 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 		kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
 	}
 
-	rdmsrl_safe(MSR_EFER, &kvm_host.efer);
+	rdmsrq_safe(MSR_EFER, &kvm_host.efer);
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, kvm_host.xss);
+		rdmsrq(MSR_IA32_XSS, kvm_host.xss);
 
 	kvm_init_pmu_capability(ops->pmu_ops);
 
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
+		rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
 
 	r = ops->hardware_setup();
 	if (r != 0)
@@ -10953,7 +10976,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		switch_fpu_return();
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+		wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -10968,6 +10991,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	vcpu->arch.host_debugctl = get_debugctlmsr();
+
 	guest_timing_enter_irqoff();
 
 	for (;;) {
@@ -11037,7 +11062,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_call(handle_exit_irqoff)(vcpu);
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, 0);
+		wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/*
 	 * Consume any pending interrupts, including the possible source of
@@ -11075,7 +11100,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	/*
 	 * Profile KVM exit RIPs:
 	 */
-	if (unlikely(prof_on == KVM_PROFILING)) {
+	if (unlikely(prof_on == KVM_PROFILING &&
+		     !vcpu->arch.guest_state_protected)) {
 		unsigned long rip = kvm_rip_read(vcpu);
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
@@ -11218,9 +11244,7 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
 	switch(vcpu->arch.mp_state) {
 	case KVM_MP_STATE_HALTED:
 	case KVM_MP_STATE_AP_RESET_HOLD:
-		vcpu->arch.pv.pv_unhalted = false;
-		vcpu->arch.mp_state =
-			KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		fallthrough;
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.apf.halted = false;
@@ -11297,9 +11321,8 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
 		if (kvm_vcpu_has_events(vcpu))
-			vcpu->arch.pv.pv_unhalted = false;
-		else
-			vcpu->arch.mp_state = state;
+			state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, state);
 		return 1;
 	} else {
 		vcpu->run->exit_reason = reason;
@@ -11472,6 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_queued_exception *ex = &vcpu->arch.exception;
 	struct kvm_run *kvm_run = vcpu->run;
+	u64 sync_valid_fields;
 	int r;
 
 	r = kvm_mmu_post_init_vm(vcpu->kvm);
@@ -11517,8 +11541,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) ||
-	    (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) {
+	sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm);
+	if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) ||
+	    (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -11576,7 +11601,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 out:
 	kvm_put_guest_fpu(vcpu);
-	if (kvm_run->kvm_valid_regs)
+	if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected))
 		store_regs(vcpu);
 	post_kvm_run_save(vcpu);
 	kvm_vcpu_srcu_read_unlock(vcpu);
@@ -11764,6 +11789,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	if (kvm_mpx_supported())
 		kvm_load_guest_fpu(vcpu);
 
+	kvm_vcpu_srcu_read_lock(vcpu);
+
 	r = kvm_apic_accept_events(vcpu);
 	if (r < 0)
 		goto out;
@@ -11777,6 +11804,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 		mp_state->mp_state = vcpu->arch.mp_state;
 
 out:
+	kvm_vcpu_srcu_read_unlock(vcpu);
+
 	if (kvm_mpx_supported())
 		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
@@ -11819,10 +11848,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		goto out;
 
 	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
-		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
 	} else
-		vcpu->arch.mp_state = mp_state->mp_state;
+		kvm_set_mp_state(vcpu, mp_state->mp_state);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
@@ -11949,7 +11978,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
 	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
 	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
 	    !is_protmode(vcpu))
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 
 	return 0;
 }
@@ -12252,9 +12281,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm);
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 	else
-		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_UNINITIALIZED);
 
 	r = kvm_mmu_create(vcpu);
 	if (r < 0)
@@ -12361,6 +12390,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
+	kvm_clear_async_pf_completion_queue(vcpu);
+	kvm_mmu_unload(vcpu);
+
 	kvmclock_reset(vcpu);
 
 	kvm_x86_call(vcpu_free)(vcpu);
@@ -12754,31 +12786,6 @@ out:
 	return ret;
 }
 
-static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
-{
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
-}
-
-static void kvm_unload_vcpu_mmus(struct kvm *kvm)
-{
-	unsigned long i;
-	struct kvm_vcpu *vcpu;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		kvm_clear_async_pf_completion_queue(vcpu);
-		kvm_unload_vcpu_mmu(vcpu);
-	}
-}
-
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
-	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
-	kvm_free_pit(kvm);
-}
-
 /**
  * __x86_set_memory_region: Setup KVM internal memory slot
  *
@@ -12857,6 +12864,17 @@ EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
 void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 {
+	/*
+	 * Stop all background workers and kthreads before destroying vCPUs, as
+	 * iterating over vCPUs in a different task while vCPUs are being freed
+	 * is unsafe, i.e. will lead to use-after-free.  The PIT also needs to
+	 * be stopped before IRQ routing is freed.
+	 */
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
+
+	kvm_free_pit(kvm);
+
 	kvm_mmu_pre_destroy_vm(kvm);
 }
 
@@ -12876,18 +12894,17 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		__x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
 		mutex_unlock(&kvm->slots_lock);
 	}
-	kvm_unload_vcpu_mmus(kvm);
-	kvm_x86_call(vm_destroy)(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
 	kvm_page_track_cleanup(kvm);
 	kvm_xen_destroy_vm(kvm);
 	kvm_hv_destroy_vm(kvm);
+	kvm_x86_call(vm_destroy)(kvm);
 }
 
 static void memslot_rmap_free(struct kvm_memory_slot *slot)
@@ -13381,8 +13398,8 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
 	if (!kvm_pv_async_pf_enabled(vcpu))
 		return false;
 
-	if (vcpu->arch.apf.send_user_only &&
-	    kvm_x86_call(get_cpl)(vcpu) == 0)
+	if (!vcpu->arch.apf.send_always &&
+	    (vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl)(vcpu)))
 		return false;
 
 	if (is_guest_mode(vcpu)) {
@@ -13472,7 +13489,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 	}
 
 	vcpu->arch.apf.halted = false;
-	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 }
 
 void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu)
@@ -13542,25 +13559,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 	int ret;
 
-	irqfd->producer = prod;
 	kvm_arch_start_assignment(irqfd->kvm);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = prod;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 1);
 	if (ret)
 		kvm_arch_end_assignment(irqfd->kvm);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	return ret;
 }
 
@@ -13570,9 +13589,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	int ret;
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 
 	WARN_ON(irqfd->producer != prod);
-	irqfd->producer = NULL;
 
 	/*
 	 * When producer of consumer is unregistered, we change back to
@@ -13580,12 +13599,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	 * when the irq is masked/disabled or the consumer side (KVM
 	 * int this case doesn't want to receive the interrupts.
 	*/
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = NULL;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 0);
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
 
+	spin_unlock_irq(&kvm->irqfds.lock);
+
+
 	kvm_arch_end_assignment(irqfd->kvm);
 }
 
@@ -13598,7 +13623,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 				  struct kvm_kernel_irq_routing_entry *new)
 {
-	if (new->type != KVM_IRQ_ROUTING_MSI)
+	if (old->type != KVM_IRQ_ROUTING_MSI ||
+	    new->type != KVM_IRQ_ROUTING_MSI)
 		return true;
 
 	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
@@ -13642,12 +13668,12 @@ int kvm_spec_ctrl_test_value(u64 value)
 
 	local_irq_save(flags);
 
-	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+	if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value))
 		ret = 1;
-	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+	else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value))
 		ret = 1;
 	else
-		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+		wrmsrq(MSR_IA32_SPEC_CTRL, saved_value);
 
 	local_irq_restore(flags);
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 91e50a513100..9dc32a409076 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -121,6 +121,13 @@ static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu)
 	return vcpu->arch.last_vmentry_cpu != -1;
 }
 
+static inline void kvm_set_mp_state(struct kvm_vcpu *vcpu, int mp_state)
+{
+	vcpu->arch.mp_state = mp_state;
+	if (mp_state == KVM_MP_STATE_RUNNABLE)
+		vcpu->arch.pv.pv_unhalted = false;
+}
+
 static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.exception.pending ||
@@ -362,6 +369,7 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 u64 get_kvmclock_ns(struct kvm *kvm);
 uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm);
 bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp);
+int kvm_guest_time_update(struct kvm_vcpu *v);
 
 int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 	gva_t addr, void *val, unsigned int bytes,
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index a909b817b9c0..38b33cdd4232 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -150,11 +150,46 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+static int xen_get_guest_pvclock(struct kvm_vcpu *vcpu,
+				 struct pvclock_vcpu_time_info *hv_clock,
+				 struct gfn_to_pfn_cache *gpc,
+				 unsigned int offset)
+{
+	unsigned long flags;
+	int r;
+
+	read_lock_irqsave(&gpc->lock, flags);
+	while (!kvm_gpc_check(gpc, offset + sizeof(*hv_clock))) {
+		read_unlock_irqrestore(&gpc->lock, flags);
+
+		r = kvm_gpc_refresh(gpc, offset + sizeof(*hv_clock));
+		if (r)
+			return r;
+
+		read_lock_irqsave(&gpc->lock, flags);
+	}
+
+	memcpy(hv_clock, gpc->khva + offset, sizeof(*hv_clock));
+	read_unlock_irqrestore(&gpc->lock, flags);
+
+	/*
+	 * Sanity check TSC shift+multiplier to verify the guest's view of time
+	 * is more or less consistent.
+	 */
+	if (hv_clock->tsc_shift != vcpu->arch.pvclock_tsc_shift ||
+	    hv_clock->tsc_to_system_mul != vcpu->arch.pvclock_tsc_mul)
+		return -EINVAL;
+
+	return 0;
+}
+
 static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs,
 				bool linux_wa)
 {
+	struct kvm_vcpu_xen *xen = &vcpu->arch.xen;
 	int64_t kernel_now, delta;
 	uint64_t guest_now;
+	int r = -EOPNOTSUPP;
 
 	/*
 	 * The guest provides the requested timeout in absolute nanoseconds
@@ -173,10 +208,29 @@ static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs,
 	 * the absolute CLOCK_MONOTONIC time at which the timer should
 	 * fire.
 	 */
-	if (vcpu->arch.hv_clock.version && vcpu->kvm->arch.use_master_clock &&
-	    static_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+	do {
+		struct pvclock_vcpu_time_info hv_clock;
 		uint64_t host_tsc, guest_tsc;
 
+		if (!static_cpu_has(X86_FEATURE_CONSTANT_TSC) ||
+		    !vcpu->kvm->arch.use_master_clock)
+			break;
+
+		/*
+		 * If both Xen PV clocks are active, arbitrarily try to use the
+		 * compat clock first, but also try to use the non-compat clock
+		 * if the compat clock is unusable.  The two PV clocks hold the
+		 * same information, but it's possible one (or both) is stale
+		 * and/or currently unreachable.
+		 */
+		if (xen->vcpu_info_cache.active)
+			r = xen_get_guest_pvclock(vcpu, &hv_clock, &xen->vcpu_info_cache,
+						  offsetof(struct compat_vcpu_info, time));
+		if (r && xen->vcpu_time_info_cache.active)
+			r = xen_get_guest_pvclock(vcpu, &hv_clock, &xen->vcpu_time_info_cache, 0);
+		if (r)
+			break;
+
 		if (!IS_ENABLED(CONFIG_64BIT) ||
 		    !kvm_get_monotonic_and_clockread(&kernel_now, &host_tsc)) {
 			/*
@@ -197,9 +251,10 @@ static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs,
 
 		/* Calculate the guest kvmclock as the guest would do it. */
 		guest_tsc = kvm_read_l1_tsc(vcpu, host_tsc);
-		guest_now = __pvclock_read_cycles(&vcpu->arch.hv_clock,
-						  guest_tsc);
-	} else {
+		guest_now = __pvclock_read_cycles(&hv_clock, guest_tsc);
+	} while (0);
+
+	if (r) {
 		/*
 		 * Without CONSTANT_TSC, get_kvmclock_ns() is the only option.
 		 *
@@ -1280,10 +1335,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data)
 		 * Note, truncation is a non-issue as 'lm' is guaranteed to be
 		 * false for a 32-bit kernel, i.e. when hva_t is only 4 bytes.
 		 */
-		hva_t blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64
-				     : kvm->arch.xen_hvm_config.blob_addr_32;
-		u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
-				  : kvm->arch.xen_hvm_config.blob_size_32;
+		hva_t blob_addr = lm ? kvm->arch.xen.hvm_config.blob_addr_64
+				     : kvm->arch.xen.hvm_config.blob_addr_32;
+		u8 blob_size = lm ? kvm->arch.xen.hvm_config.blob_size_64
+				  : kvm->arch.xen.hvm_config.blob_size_32;
 		u8 *page;
 		int ret;
 
@@ -1324,15 +1379,24 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	     xhc->blob_size_32 || xhc->blob_size_64))
 		return -EINVAL;
 
+	/*
+	 * Restrict the MSR to the range that is unofficially reserved for
+	 * synthetic, virtualization-defined MSRs, e.g. to prevent confusing
+	 * KVM by colliding with a real MSR that requires special handling.
+	 */
+	if (xhc->msr &&
+	    (xhc->msr < KVM_XEN_MSR_MIN_INDEX || xhc->msr > KVM_XEN_MSR_MAX_INDEX))
+		return -EINVAL;
+
 	mutex_lock(&kvm->arch.xen.xen_lock);
 
-	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
+	if (xhc->msr && !kvm->arch.xen.hvm_config.msr)
 		static_branch_inc(&kvm_xen_enabled.key);
-	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
+	else if (!xhc->msr && kvm->arch.xen.hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 
-	old_flags = kvm->arch.xen_hvm_config.flags;
-	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
+	old_flags = kvm->arch.xen.hvm_config.flags;
+	memcpy(&kvm->arch.xen.hvm_config, xhc, sizeof(*xhc));
 
 	mutex_unlock(&kvm->arch.xen.xen_lock);
 
@@ -1413,7 +1477,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 	int i;
 
 	if (!lapic_in_kernel(vcpu) ||
-	    !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
+	    !(vcpu->kvm->arch.xen.hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
 		return false;
 
 	if (IS_ENABLED(CONFIG_64BIT) && !longmode) {
@@ -1480,7 +1544,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 	set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.xen.poll_mask);
 
 	if (!wait_pending_event(vcpu, sched_poll.nr_ports, ports)) {
-		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED);
 
 		if (sched_poll.timeout)
 			mod_timer(&vcpu->arch.xen.poll_timer,
@@ -1489,9 +1553,9 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 		kvm_vcpu_halt(vcpu);
 
 		if (sched_poll.timeout)
-			del_timer(&vcpu->arch.xen.poll_timer);
+			timer_delete(&vcpu->arch.xen.poll_timer);
 
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 	}
 
 	vcpu->arch.xen.poll_evtchn = 0;
@@ -2225,8 +2289,8 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.xen.poll_evtchn = 0;
 
 	timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0);
-	hrtimer_init(&vcpu->arch.xen.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	vcpu->arch.xen.timer.function = xen_timer_callback;
+	hrtimer_setup(&vcpu->arch.xen.timer, xen_timer_callback, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 
 	kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm);
 	kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm);
@@ -2244,30 +2308,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
 	kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
 	kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);
 
-	del_timer_sync(&vcpu->arch.xen.poll_timer);
-}
-
-void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpuid_entry2 *entry;
-	u32 function;
-
-	if (!vcpu->arch.xen.cpuid.base)
-		return;
-
-	function = vcpu->arch.xen.cpuid.base | XEN_CPUID_LEAF(3);
-	if (function > vcpu->arch.xen.cpuid.limit)
-		return;
-
-	entry = kvm_find_cpuid_entry_index(vcpu, function, 1);
-	if (entry) {
-		entry->ecx = vcpu->arch.hv_clock.tsc_to_system_mul;
-		entry->edx = vcpu->arch.hv_clock.tsc_shift;
-	}
-
-	entry = kvm_find_cpuid_entry_index(vcpu, function, 2);
-	if (entry)
-		entry->eax = vcpu->arch.hw_tsc_khz;
+	timer_delete_sync(&vcpu->arch.xen.poll_timer);
 }
 
 void kvm_xen_init_vm(struct kvm *kvm)
@@ -2291,6 +2332,6 @@ void kvm_xen_destroy_vm(struct kvm *kvm)
 	}
 	idr_destroy(&kvm->arch.xen.evtchn_ports);
 
-	if (kvm->arch.xen_hvm_config.msr)
+	if (kvm->arch.xen.hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 }
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index f5841d9000ae..59e6128a7bd3 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -9,6 +9,7 @@
 #ifndef __ARCH_X86_KVM_XEN_H__
 #define __ARCH_X86_KVM_XEN_H__
 
+#include <asm/xen/cpuid.h>
 #include <asm/xen/hypervisor.h>
 
 #ifdef CONFIG_KVM_XEN
@@ -35,7 +36,6 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe,
 int kvm_xen_setup_evtchn(struct kvm *kvm,
 			 struct kvm_kernel_irq_routing_entry *e,
 			 const struct kvm_irq_routing_entry *ue);
-void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu);
 
 static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu)
 {
@@ -50,16 +50,32 @@ static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu)
 		kvm_xen_inject_vcpu_vector(vcpu);
 }
 
+static inline bool kvm_xen_is_tsc_leaf(struct kvm_vcpu *vcpu, u32 function)
+{
+	return static_branch_unlikely(&kvm_xen_enabled.key) &&
+	       vcpu->arch.xen.cpuid.base &&
+	       function <= vcpu->arch.xen.cpuid.limit &&
+	       function == (vcpu->arch.xen.cpuid.base | XEN_CPUID_LEAF(3));
+}
+
 static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 {
 	return static_branch_unlikely(&kvm_xen_enabled.key) &&
-		kvm->arch.xen_hvm_config.msr;
+		kvm->arch.xen.hvm_config.msr;
+}
+
+static inline bool kvm_xen_is_hypercall_page_msr(struct kvm *kvm, u32 msr)
+{
+	if (!static_branch_unlikely(&kvm_xen_enabled.key))
+		return false;
+
+	return msr && msr == kvm->arch.xen.hvm_config.msr;
 }
 
 static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 {
 	return static_branch_unlikely(&kvm_xen_enabled.key) &&
-		(kvm->arch.xen_hvm_config.flags &
+		(kvm->arch.xen.hvm_config.flags &
 		 KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL);
 }
 
@@ -124,6 +140,11 @@ static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 	return false;
 }
 
+static inline bool kvm_xen_is_hypercall_page_msr(struct kvm *kvm, u32 msr)
+{
+	return false;
+}
+
 static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 {
 	return false;
@@ -157,8 +178,9 @@ static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu)
 	return false;
 }
 
-static inline void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu)
+static inline bool kvm_xen_is_tsc_leaf(struct kvm_vcpu *vcpu, u32 function)
 {
+	return false;
 }
 #endif
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2..4fa5c4e1ba8a 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -3,6 +3,8 @@
 # Makefile for x86 specific library files.
 #
 
+obj-y += crypto/
+
 # Produces uninteresting flaky coverage.
 KCOV_INSTRUMENT_delay.o	:= n
 
@@ -39,11 +41,14 @@ lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-x86.o
-crc32-x86-y := crc32-glue.o crc32-pclmul.o
+crc32-x86-y := crc32.o crc32-pclmul.o
 crc32-x86-$(CONFIG_64BIT) += crc32c-3way.o
 
+obj-$(CONFIG_CRC64_ARCH) += crc64-x86.o
+crc64-x86-y := crc64.o crc64-pclmul.o
+
 obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-x86.o
-crc-t10dif-x86-y := crc-t10dif-glue.o crct10dif-pcl-asm_64.o
+crc-t10dif-x86-y := crc-t10dif.o crc16-msb-pclmul.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 obj-y += iomem.o
@@ -56,7 +61,7 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += string_32.o
         lib-y += memmove_32.o
         lib-y += cmpxchg8b_emu.o
-ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ifneq ($(CONFIG_X86_CX8),y)
         lib-y += atomic64_386_32.o
 endif
 else
@@ -66,5 +71,6 @@ endif
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o copy_user_uncached_64.o
-	lib-y += cmpxchg16b_emu.o
+        lib-y += cmpxchg16b_emu.o
+        lib-y += bhi.o
 endif
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
new file mode 100644
index 000000000000..58891681261b
--- /dev/null
+++ b/arch/x86/lib/bhi.S
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/unwind_hints.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ *
+ * The very last element is in fact larger than 32 bytes, but since its the
+ * last element, this does not matter,
+ *
+ * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they
+ * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently
+ * big alignment holes for this to not stagger the array.
+ */
+
+.pushsection .noinstr.text, "ax"
+
+	.align 32
+SYM_CODE_START(__bhi_args)
+
+#ifdef CONFIG_FINEIBT_BHI
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_1:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_2:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	cmovne %r10, %rsp
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+#endif /* CONFIG_FINEIBT_BHI */
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	nop /* Work around toolchain+objtool quirk */
+SYM_CODE_END(__bhi_args)
+
+.popsection
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 2760a15fbc00..a508e4a8c66a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -14,7 +16,7 @@
  * Zero a page.
  * %rdi	- page
  */
-SYM_FUNC_START(clear_page_rep)
+SYM_TYPED_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
@@ -22,7 +24,7 @@ SYM_FUNC_START(clear_page_rep)
 SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
-SYM_FUNC_START(clear_page_orig)
+SYM_TYPED_FUNC_START(clear_page_orig)
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -44,7 +46,7 @@ SYM_FUNC_START(clear_page_orig)
 SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
-SYM_FUNC_START(clear_page_erms)
+SYM_TYPED_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
@@ -63,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms)
  * rcx: uncleared bytes or 0 if successful.
  */
 SYM_FUNC_START(rep_stos_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Lunrolled
 
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 1c96be769adc..d4bb24347ff8 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,7 @@
 
 .text
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 
 /*
  * Emulate 'cmpxchg8b (%esi)' on UP
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index d6ae793d08fa..d8e87fedc20d 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -13,7 +14,7 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-SYM_FUNC_START(copy_page)
+SYM_TYPED_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d06174..06296eb69fd4 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -8,6 +8,8 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 #include <asm/asm.h>
@@ -30,6 +32,7 @@
  * it simpler for us, we can clobber rsi/rdi and rax freely.
  */
 SYM_FUNC_START(rep_movs_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Llarge
 
@@ -74,6 +77,24 @@ SYM_FUNC_START(rep_movs_alternative)
 	_ASM_EXTABLE_UA( 0b, 1b)
 
 .Llarge_movsq:
+	/* Do the first possibly unaligned word */
+0:	movq (%rsi),%rax
+1:	movq %rax,(%rdi)
+
+	_ASM_EXTABLE_UA( 0b, .Lcopy_user_tail)
+	_ASM_EXTABLE_UA( 1b, .Lcopy_user_tail)
+
+	/* What would be the offset to the aligned destination? */
+	leaq 8(%rdi),%rax
+	andq $-8,%rax
+	subq %rdi,%rax
+
+	/* .. and update pointers and count to match */
+	addq %rax,%rdi
+	addq %rax,%rsi
+	subq %rax,%rcx
+
+	/* make %rcx contain the number of words, %rax the remainder */
 	movq %rcx,%rax
 	shrq $3,%rcx
 	andl $7,%eax
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 2918e36eece2..18350b343c2a 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -27,6 +28,7 @@
  * rax uncopied bytes or 0 if successful.
  */
 SYM_FUNC_START(__copy_user_nocache)
+	ANNOTATE_NOENDBR
 	/* If destination is not 7-byte aligned, we'll have to align it */
 	testb $7,%dil
 	jne .Lalign
diff --git a/arch/x86/lib/crc-pclmul-consts.h b/arch/x86/lib/crc-pclmul-consts.h
new file mode 100644
index 000000000000..fcc63c064333
--- /dev/null
+++ b/arch/x86/lib/crc-pclmul-consts.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CRC constants generated by:
+ *
+ *	./scripts/gen-crc-consts.py x86_pclmul crc16_msb_0x8bb7,crc32_lsb_0xedb88320,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5
+ *
+ * Do not edit manually.
+ */
+
+/*
+ * CRC folding constants generated for most-significant-bit-first CRC-16 using
+ * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ */
+static const struct {
+	u8 bswap_mask[16];
+	u64 fold_across_2048_bits_consts[2];
+	u64 fold_across_1024_bits_consts[2];
+	u64 fold_across_512_bits_consts[2];
+	u64 fold_across_256_bits_consts[2];
+	u64 fold_across_128_bits_consts[2];
+	u8 shuf_table[48];
+	u64 barrett_reduction_consts[2];
+} crc16_msb_0x8bb7_consts ____cacheline_aligned __maybe_unused = {
+	.bswap_mask = {15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0},
+	.fold_across_2048_bits_consts = {
+		0xdccf000000000000,	/* LO64_TERMS: (x^2000 mod G) * x^48 */
+		0x4b0b000000000000,	/* HI64_TERMS: (x^2064 mod G) * x^48 */
+	},
+	.fold_across_1024_bits_consts = {
+		0x9d9d000000000000,	/* LO64_TERMS: (x^976 mod G) * x^48 */
+		0x7cf5000000000000,	/* HI64_TERMS: (x^1040 mod G) * x^48 */
+	},
+	.fold_across_512_bits_consts = {
+		0x044c000000000000,	/* LO64_TERMS: (x^464 mod G) * x^48 */
+		0xe658000000000000,	/* HI64_TERMS: (x^528 mod G) * x^48 */
+	},
+	.fold_across_256_bits_consts = {
+		0x6ee3000000000000,	/* LO64_TERMS: (x^208 mod G) * x^48 */
+		0xe7b5000000000000,	/* HI64_TERMS: (x^272 mod G) * x^48 */
+	},
+	.fold_across_128_bits_consts = {
+		0x2d56000000000000,	/* LO64_TERMS: (x^80 mod G) * x^48 */
+		0x06df000000000000,	/* HI64_TERMS: (x^144 mod G) * x^48 */
+	},
+	.shuf_table = {
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+		 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15,
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	},
+	.barrett_reduction_consts = {
+		0x8bb7000000000000,	/* LO64_TERMS: (G - x^16) * x^48 */
+		0xf65a57f81d33a48a,	/* HI64_TERMS: (floor(x^79 / G) * x) - x^64 */
+	},
+};
+
+/*
+ * CRC folding constants generated for least-significant-bit-first CRC-32 using
+ * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 +
+ *        x^5 + x^4 + x^2 + x^1 + x^0
+ */
+static const struct {
+	u64 fold_across_2048_bits_consts[2];
+	u64 fold_across_1024_bits_consts[2];
+	u64 fold_across_512_bits_consts[2];
+	u64 fold_across_256_bits_consts[2];
+	u64 fold_across_128_bits_consts[2];
+	u8 shuf_table[48];
+	u64 barrett_reduction_consts[2];
+} crc32_lsb_0xedb88320_consts ____cacheline_aligned __maybe_unused = {
+	.fold_across_2048_bits_consts = {
+		0x00000000ce3371cb,	/* HI64_TERMS: (x^2079 mod G) * x^32 */
+		0x00000000e95c1271,	/* LO64_TERMS: (x^2015 mod G) * x^32 */
+	},
+	.fold_across_1024_bits_consts = {
+		0x0000000033fff533,	/* HI64_TERMS: (x^1055 mod G) * x^32 */
+		0x00000000910eeec1,	/* LO64_TERMS: (x^991 mod G) * x^32 */
+	},
+	.fold_across_512_bits_consts = {
+		0x000000008f352d95,	/* HI64_TERMS: (x^543 mod G) * x^32 */
+		0x000000001d9513d7,	/* LO64_TERMS: (x^479 mod G) * x^32 */
+	},
+	.fold_across_256_bits_consts = {
+		0x00000000f1da05aa,	/* HI64_TERMS: (x^287 mod G) * x^32 */
+		0x0000000081256527,	/* LO64_TERMS: (x^223 mod G) * x^32 */
+	},
+	.fold_across_128_bits_consts = {
+		0x00000000ae689191,	/* HI64_TERMS: (x^159 mod G) * x^32 */
+		0x00000000ccaa009e,	/* LO64_TERMS: (x^95 mod G) * x^32 */
+	},
+	.shuf_table = {
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+		 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15,
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	},
+	.barrett_reduction_consts = {
+		0xb4e5b025f7011641,	/* HI64_TERMS: floor(x^95 / G) */
+		0x00000001db710640,	/* LO64_TERMS: (G - x^32) * x^31 */
+	},
+};
+
+/*
+ * CRC folding constants generated for most-significant-bit-first CRC-64 using
+ * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ *        x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ *        x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ *        x^7 + x^4 + x^1 + x^0
+ */
+static const struct {
+	u8 bswap_mask[16];
+	u64 fold_across_2048_bits_consts[2];
+	u64 fold_across_1024_bits_consts[2];
+	u64 fold_across_512_bits_consts[2];
+	u64 fold_across_256_bits_consts[2];
+	u64 fold_across_128_bits_consts[2];
+	u8 shuf_table[48];
+	u64 barrett_reduction_consts[2];
+} crc64_msb_0x42f0e1eba9ea3693_consts ____cacheline_aligned __maybe_unused = {
+	.bswap_mask = {15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0},
+	.fold_across_2048_bits_consts = {
+		0x7f52691a60ddc70d,	/* LO64_TERMS: (x^2048 mod G) * x^0 */
+		0x7036b0389f6a0c82,	/* HI64_TERMS: (x^2112 mod G) * x^0 */
+	},
+	.fold_across_1024_bits_consts = {
+		0x05cf79dea9ac37d6,	/* LO64_TERMS: (x^1024 mod G) * x^0 */
+		0x001067e571d7d5c2,	/* HI64_TERMS: (x^1088 mod G) * x^0 */
+	},
+	.fold_across_512_bits_consts = {
+		0x5f6843ca540df020,	/* LO64_TERMS: (x^512 mod G) * x^0 */
+		0xddf4b6981205b83f,	/* HI64_TERMS: (x^576 mod G) * x^0 */
+	},
+	.fold_across_256_bits_consts = {
+		0x571bee0a227ef92b,	/* LO64_TERMS: (x^256 mod G) * x^0 */
+		0x44bef2a201b5200c,	/* HI64_TERMS: (x^320 mod G) * x^0 */
+	},
+	.fold_across_128_bits_consts = {
+		0x05f5c3c7eb52fab6,	/* LO64_TERMS: (x^128 mod G) * x^0 */
+		0x4eb938a7d257740e,	/* HI64_TERMS: (x^192 mod G) * x^0 */
+	},
+	.shuf_table = {
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+		 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15,
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	},
+	.barrett_reduction_consts = {
+		0x42f0e1eba9ea3693,	/* LO64_TERMS: (G - x^64) * x^0 */
+		0x578d29d06cc4f872,	/* HI64_TERMS: (floor(x^127 / G) * x) - x^64 */
+	},
+};
+
+/*
+ * CRC folding constants generated for least-significant-bit-first CRC-64 using
+ * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 +
+ *        x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 +
+ *        x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 +
+ *        x^4 + x^3 + x^0
+ */
+static const struct {
+	u64 fold_across_2048_bits_consts[2];
+	u64 fold_across_1024_bits_consts[2];
+	u64 fold_across_512_bits_consts[2];
+	u64 fold_across_256_bits_consts[2];
+	u64 fold_across_128_bits_consts[2];
+	u8 shuf_table[48];
+	u64 barrett_reduction_consts[2];
+} crc64_lsb_0x9a6c9329ac4bc9b5_consts ____cacheline_aligned __maybe_unused = {
+	.fold_across_2048_bits_consts = {
+		0x37ccd3e14069cabc,	/* HI64_TERMS: (x^2111 mod G) * x^0 */
+		0xa043808c0f782663,	/* LO64_TERMS: (x^2047 mod G) * x^0 */
+	},
+	.fold_across_1024_bits_consts = {
+		0xa1ca681e733f9c40,	/* HI64_TERMS: (x^1087 mod G) * x^0 */
+		0x5f852fb61e8d92dc,	/* LO64_TERMS: (x^1023 mod G) * x^0 */
+	},
+	.fold_across_512_bits_consts = {
+		0x0c32cdb31e18a84a,	/* HI64_TERMS: (x^575 mod G) * x^0 */
+		0x62242240ace5045a,	/* LO64_TERMS: (x^511 mod G) * x^0 */
+	},
+	.fold_across_256_bits_consts = {
+		0xb0bc2e589204f500,	/* HI64_TERMS: (x^319 mod G) * x^0 */
+		0xe1e0bb9d45d7a44c,	/* LO64_TERMS: (x^255 mod G) * x^0 */
+	},
+	.fold_across_128_bits_consts = {
+		0xeadc41fd2ba3d420,	/* HI64_TERMS: (x^191 mod G) * x^0 */
+		0x21e9761e252621ac,	/* LO64_TERMS: (x^127 mod G) * x^0 */
+	},
+	.shuf_table = {
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+		 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15,
+		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+	},
+	.barrett_reduction_consts = {
+		0x27ecfa329aef9f77,	/* HI64_TERMS: floor(x^127 / G) */
+		0x34d926535897936a,	/* LO64_TERMS: (G - x^64 - x^0) / x */
+	},
+};
diff --git a/arch/x86/lib/crc-pclmul-template.S b/arch/x86/lib/crc-pclmul-template.S
new file mode 100644
index 000000000000..ae0b6144c503
--- /dev/null
+++ b/arch/x86/lib/crc-pclmul-template.S
@@ -0,0 +1,582 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+//
+// Template to generate [V]PCLMULQDQ-based CRC functions for x86
+//
+// Copyright 2025 Google LLC
+//
+// Author: Eric Biggers <ebiggers@google.com>
+
+#include <linux/linkage.h>
+#include <linux/objtool.h>
+
+// Offsets within the generated constants table
+.set OFFSETOF_BSWAP_MASK,			-5*16	// msb-first CRCs only
+.set OFFSETOF_FOLD_ACROSS_2048_BITS_CONSTS,	-4*16	// must precede next
+.set OFFSETOF_FOLD_ACROSS_1024_BITS_CONSTS,	-3*16	// must precede next
+.set OFFSETOF_FOLD_ACROSS_512_BITS_CONSTS,	-2*16	// must precede next
+.set OFFSETOF_FOLD_ACROSS_256_BITS_CONSTS,	-1*16	// must precede next
+.set OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS,	0*16	// must be 0
+.set OFFSETOF_SHUF_TABLE,			1*16
+.set OFFSETOF_BARRETT_REDUCTION_CONSTS,		4*16
+
+// Emit a VEX (or EVEX) coded instruction if allowed, or emulate it using the
+// corresponding non-VEX instruction plus any needed moves.  The supported
+// instruction formats are:
+//
+//     - Two-arg [src, dst], where the non-VEX format is the same.
+//     - Three-arg [src1, src2, dst] where the non-VEX format is
+//	 [src1, src2_and_dst].  If src2 != dst, then src1 must != dst too.
+//
+// \insn gives the instruction without a "v" prefix and including any immediate
+// argument if needed to make the instruction follow one of the above formats.
+// If \unaligned_mem_tmp is given, then the emitted non-VEX code moves \arg1 to
+// it first; this is needed when \arg1 is an unaligned mem operand.
+.macro	_cond_vex	insn:req, arg1:req, arg2:req, arg3, unaligned_mem_tmp
+.if AVX_LEVEL == 0
+  // VEX not allowed.  Emulate it.
+  .ifnb \arg3 // Three-arg [src1, src2, dst]
+    .ifc "\arg2", "\arg3" // src2 == dst?
+      .ifnb \unaligned_mem_tmp
+	movdqu		\arg1, \unaligned_mem_tmp
+	\insn		\unaligned_mem_tmp, \arg3
+      .else
+	\insn		\arg1, \arg3
+      .endif
+    .else // src2 != dst
+      .ifc "\arg1", "\arg3"
+	.error "Can't have src1 == dst when src2 != dst"
+      .endif
+      .ifnb \unaligned_mem_tmp
+	movdqu		\arg1, \unaligned_mem_tmp
+	movdqa		\arg2, \arg3
+	\insn		\unaligned_mem_tmp, \arg3
+      .else
+	movdqa		\arg2, \arg3
+	\insn		\arg1, \arg3
+      .endif
+    .endif
+  .else // Two-arg [src, dst]
+    .ifnb \unaligned_mem_tmp
+	movdqu		\arg1, \unaligned_mem_tmp
+	\insn		\unaligned_mem_tmp, \arg2
+    .else
+	\insn		\arg1, \arg2
+    .endif
+  .endif
+.else
+  // VEX is allowed.  Emit the desired instruction directly.
+  .ifnb \arg3
+	v\insn		\arg1, \arg2, \arg3
+  .else
+	v\insn		\arg1, \arg2
+  .endif
+.endif
+.endm
+
+// Broadcast an aligned 128-bit mem operand to all 128-bit lanes of a vector
+// register of length VL.
+.macro	_vbroadcast	src, dst
+.if VL == 16
+	_cond_vex movdqa,	\src, \dst
+.elseif VL == 32
+	vbroadcasti128		\src, \dst
+.else
+	vbroadcasti32x4		\src, \dst
+.endif
+.endm
+
+// Load \vl bytes from the unaligned mem operand \src into \dst, and if the CRC
+// is msb-first use \bswap_mask to reflect the bytes within each 128-bit lane.
+.macro	_load_data	vl, src, bswap_mask, dst
+.if \vl < 64
+	_cond_vex movdqu,	"\src", \dst
+.else
+	vmovdqu8		\src, \dst
+.endif
+.if !LSB_CRC
+	_cond_vex pshufb,	\bswap_mask, \dst, \dst
+.endif
+.endm
+
+.macro	_prepare_v0	vl, v0, v1, bswap_mask
+.if LSB_CRC
+  .if \vl < 64
+	_cond_vex pxor,		(BUF), \v0, \v0, unaligned_mem_tmp=\v1
+  .else
+	vpxorq			(BUF), \v0, \v0
+  .endif
+.else
+	_load_data		\vl, (BUF), \bswap_mask, \v1
+  .if \vl < 64
+	_cond_vex pxor,		\v1, \v0, \v0
+  .else
+	vpxorq			\v1, \v0, \v0
+  .endif
+.endif
+.endm
+
+// The x^0..x^63 terms, i.e. poly128 mod x^64, i.e. the physically low qword for
+// msb-first order or the physically high qword for lsb-first order
+#define LO64_TERMS 0
+
+// The x^64..x^127 terms, i.e. floor(poly128 / x^64), i.e. the physically high
+// qword for msb-first order or the physically low qword for lsb-first order
+#define HI64_TERMS 1
+
+// Multiply the given \src1_terms of each 128-bit lane of \src1 by the given
+// \src2_terms of each 128-bit lane of \src2, and write the result(s) to \dst.
+.macro	_pclmulqdq	src1, src1_terms, src2, src2_terms, dst
+	_cond_vex "pclmulqdq $((\src1_terms ^ LSB_CRC) << 4) ^ (\src2_terms ^ LSB_CRC),", \
+		  \src1, \src2, \dst
+.endm
+
+// Fold \acc into \data and store the result back into \acc.  \data can be an
+// unaligned mem operand if using VEX is allowed and the CRC is lsb-first so no
+// byte-reflection is needed; otherwise it must be a vector register.  \consts
+// is a vector register containing the needed fold constants, and \tmp is a
+// temporary vector register.  All arguments must be the same length.
+.macro	_fold_vec	acc, data, consts, tmp
+	_pclmulqdq	\consts, HI64_TERMS, \acc, HI64_TERMS, \tmp
+	_pclmulqdq	\consts, LO64_TERMS, \acc, LO64_TERMS, \acc
+.if AVX_LEVEL <= 2
+	_cond_vex pxor,	\data, \tmp, \tmp
+	_cond_vex pxor,	\tmp, \acc, \acc
+.else
+	vpternlogq	$0x96, \data, \tmp, \acc
+.endif
+.endm
+
+// Fold \acc into \data and store the result back into \acc.  \data is an
+// unaligned mem operand, \consts is a vector register containing the needed
+// fold constants, \bswap_mask is a vector register containing the
+// byte-reflection table if the CRC is msb-first, and \tmp1 and \tmp2 are
+// temporary vector registers.  All arguments must have length \vl.
+.macro	_fold_vec_mem	vl, acc, data, consts, bswap_mask, tmp1, tmp2
+.if AVX_LEVEL == 0 || !LSB_CRC
+	_load_data	\vl, \data, \bswap_mask, \tmp1
+	_fold_vec	\acc, \tmp1, \consts, \tmp2
+.else
+	_fold_vec	\acc, \data, \consts, \tmp1
+.endif
+.endm
+
+// Load the constants for folding across 2**i vectors of length VL at a time
+// into all 128-bit lanes of the vector register CONSTS.
+.macro	_load_vec_folding_consts	i
+	_vbroadcast OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS+(4-LOG2_VL-\i)*16(CONSTS_PTR), \
+		    CONSTS
+.endm
+
+// Given vector registers \v0 and \v1 of length \vl, fold \v0 into \v1 and store
+// the result back into \v0.  If the remaining length mod \vl is nonzero, also
+// fold \vl data bytes from BUF.  For both operations the fold distance is \vl.
+// \consts must be a register of length \vl containing the fold constants.
+.macro	_fold_vec_final	vl, v0, v1, consts, bswap_mask, tmp1, tmp2
+	_fold_vec	\v0, \v1, \consts, \tmp1
+	test		$\vl, LEN8
+	jz		.Lfold_vec_final_done\@
+	_fold_vec_mem	\vl, \v0, (BUF), \consts, \bswap_mask, \tmp1, \tmp2
+	add		$\vl, BUF
+.Lfold_vec_final_done\@:
+.endm
+
+// This macro generates the body of a CRC function with the following prototype:
+//
+// crc_t crc_func(crc_t crc, const u8 *buf, size_t len, const void *consts);
+//
+// |crc| is the initial CRC, and crc_t is a data type wide enough to hold it.
+// |buf| is the data to checksum.  |len| is the data length in bytes, which must
+// be at least 16.  |consts| is a pointer to the fold_across_128_bits_consts
+// field of the constants struct that was generated for the chosen CRC variant.
+//
+// Moving onto the macro parameters, \n is the number of bits in the CRC, e.g.
+// 32 for a CRC-32.  Currently the supported values are 8, 16, 32, and 64.  If
+// the file is compiled in i386 mode, then the maximum supported value is 32.
+//
+// \lsb_crc is 1 if the CRC processes the least significant bit of each byte
+// first, i.e. maps bit0 to x^7, bit1 to x^6, ..., bit7 to x^0.  \lsb_crc is 0
+// if the CRC processes the most significant bit of each byte first, i.e. maps
+// bit0 to x^0, bit1 to x^1, bit7 to x^7.
+//
+// \vl is the maximum length of vector register to use in bytes: 16, 32, or 64.
+//
+// \avx_level is the level of AVX support to use: 0 for SSE only, 2 for AVX2, or
+// 512 for AVX512.
+//
+// If \vl == 16 && \avx_level == 0, the generated code requires:
+// PCLMULQDQ && SSE4.1.  (Note: all known CPUs with PCLMULQDQ also have SSE4.1.)
+//
+// If \vl == 32 && \avx_level == 2, the generated code requires:
+// VPCLMULQDQ && AVX2.
+//
+// If \vl == 64 && \avx_level == 512, the generated code requires:
+// VPCLMULQDQ && AVX512BW && AVX512VL.
+//
+// Other \vl and \avx_level combinations are either not supported or not useful.
+.macro	_crc_pclmul	n, lsb_crc, vl, avx_level
+	.set	LSB_CRC,	\lsb_crc
+	.set	VL,		\vl
+	.set	AVX_LEVEL,	\avx_level
+
+	// Define aliases for the xmm, ymm, or zmm registers according to VL.
+.irp i, 0,1,2,3,4,5,6,7
+  .if VL == 16
+	.set	V\i,		%xmm\i
+	.set	LOG2_VL,	4
+  .elseif VL == 32
+	.set	V\i,		%ymm\i
+	.set	LOG2_VL,	5
+  .elseif VL == 64
+	.set	V\i,		%zmm\i
+	.set	LOG2_VL,	6
+  .else
+	.error "Unsupported vector length"
+  .endif
+.endr
+	// Define aliases for the function parameters.
+	// Note: when crc_t is shorter than u32, zero-extension to 32 bits is
+	// guaranteed by the ABI.  Zero-extension to 64 bits is *not* guaranteed
+	// when crc_t is shorter than u64.
+#ifdef __x86_64__
+.if \n <= 32
+	.set	CRC,		%edi
+.else
+	.set	CRC,		%rdi
+.endif
+	.set	BUF,		%rsi
+	.set	LEN,		%rdx
+	.set	LEN32,		%edx
+	.set	LEN8,		%dl
+	.set	CONSTS_PTR,	%rcx
+#else
+	// 32-bit support, assuming -mregparm=3 and not including support for
+	// CRC-64 (which would use both eax and edx to pass the crc parameter).
+	.set	CRC,		%eax
+	.set	BUF,		%edx
+	.set	LEN,		%ecx
+	.set	LEN32,		%ecx
+	.set	LEN8,		%cl
+	.set	CONSTS_PTR,	%ebx	// Passed on stack
+#endif
+
+	// Define aliases for some local variables.  V0-V5 are used without
+	// aliases (for accumulators, data, temporary values, etc).  Staying
+	// within the first 8 vector registers keeps the code 32-bit SSE
+	// compatible and reduces the size of 64-bit SSE code slightly.
+	.set	BSWAP_MASK,	V6
+	.set	BSWAP_MASK_YMM,	%ymm6
+	.set	BSWAP_MASK_XMM,	%xmm6
+	.set	CONSTS,		V7
+	.set	CONSTS_YMM,	%ymm7
+	.set	CONSTS_XMM,	%xmm7
+
+	// Use ANNOTATE_NOENDBR to suppress an objtool warning, since the
+	// functions generated by this macro are called only by static_call.
+	ANNOTATE_NOENDBR
+
+#ifdef __i386__
+	push		CONSTS_PTR
+	mov		8(%esp), CONSTS_PTR
+#endif
+
+	// Create a 128-bit vector that contains the initial CRC in the end
+	// representing the high-order polynomial coefficients, and the rest 0.
+	// If the CRC is msb-first, also load the byte-reflection table.
+.if \n <= 32
+	_cond_vex movd,	CRC, %xmm0
+.else
+	_cond_vex movq,	CRC, %xmm0
+.endif
+.if !LSB_CRC
+	_cond_vex pslldq, $(128-\n)/8, %xmm0, %xmm0
+	_vbroadcast	OFFSETOF_BSWAP_MASK(CONSTS_PTR), BSWAP_MASK
+.endif
+
+	// Load the first vector of data and XOR the initial CRC into the
+	// appropriate end of the first 128-bit lane of data.  If LEN < VL, then
+	// use a short vector and jump ahead to the final reduction.  (LEN >= 16
+	// is guaranteed here but not necessarily LEN >= VL.)
+.if VL >= 32
+	cmp		$VL, LEN
+	jae		.Lat_least_1vec\@
+  .if VL == 64
+	cmp		$32, LEN32
+	jb		.Lless_than_32bytes\@
+	_prepare_v0	32, %ymm0, %ymm1, BSWAP_MASK_YMM
+	add		$32, BUF
+	jmp		.Lreduce_256bits_to_128bits\@
+.Lless_than_32bytes\@:
+  .endif
+	_prepare_v0	16, %xmm0, %xmm1, BSWAP_MASK_XMM
+	add		$16, BUF
+	vmovdqa		OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
+	jmp		.Lcheck_for_partial_block\@
+.Lat_least_1vec\@:
+.endif
+	_prepare_v0	VL, V0, V1, BSWAP_MASK
+
+	// Handle VL <= LEN < 4*VL.
+	cmp		$4*VL-1, LEN
+	ja		.Lat_least_4vecs\@
+	add		$VL, BUF
+	// If VL <= LEN < 2*VL, then jump ahead to the reduction from 1 vector.
+	// If VL==16 then load fold_across_128_bits_consts first, as the final
+	// reduction depends on it and it won't be loaded anywhere else.
+	cmp		$2*VL-1, LEN32
+.if VL == 16
+	_cond_vex movdqa, OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
+.endif
+	jbe		.Lreduce_1vec_to_128bits\@
+	// Otherwise 2*VL <= LEN < 4*VL.  Load one more vector and jump ahead to
+	// the reduction from 2 vectors.
+	_load_data	VL, (BUF), BSWAP_MASK, V1
+	add		$VL, BUF
+	jmp		.Lreduce_2vecs_to_1\@
+
+.Lat_least_4vecs\@:
+	// Load 3 more vectors of data.
+	_load_data	VL, 1*VL(BUF), BSWAP_MASK, V1
+	_load_data	VL, 2*VL(BUF), BSWAP_MASK, V2
+	_load_data	VL, 3*VL(BUF), BSWAP_MASK, V3
+	sub		$-4*VL, BUF	// Shorter than 'add 4*VL' when VL=32
+	add		$-4*VL, LEN	// Shorter than 'sub 4*VL' when VL=32
+
+	// Main loop: while LEN >= 4*VL, fold the 4 vectors V0-V3 into the next
+	// 4 vectors of data and write the result back to V0-V3.
+	cmp		$4*VL-1, LEN	// Shorter than 'cmp 4*VL' when VL=32
+	jbe		.Lreduce_4vecs_to_2\@
+	_load_vec_folding_consts	2
+.Lfold_4vecs_loop\@:
+	_fold_vec_mem	VL, V0, 0*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	_fold_vec_mem	VL, V1, 1*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	_fold_vec_mem	VL, V2, 2*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	_fold_vec_mem	VL, V3, 3*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	sub		$-4*VL, BUF
+	add		$-4*VL, LEN
+	cmp		$4*VL-1, LEN
+	ja		.Lfold_4vecs_loop\@
+
+	// Fold V0,V1 into V2,V3 and write the result back to V0,V1.  Then fold
+	// two more vectors of data from BUF, if at least that much remains.
+.Lreduce_4vecs_to_2\@:
+	_load_vec_folding_consts	1
+	_fold_vec	V0, V2, CONSTS, V4
+	_fold_vec	V1, V3, CONSTS, V4
+	test		$2*VL, LEN8
+	jz		.Lreduce_2vecs_to_1\@
+	_fold_vec_mem	VL, V0, 0*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	_fold_vec_mem	VL, V1, 1*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
+	sub		$-2*VL, BUF
+
+	// Fold V0 into V1 and write the result back to V0.  Then fold one more
+	// vector of data from BUF, if at least that much remains.
+.Lreduce_2vecs_to_1\@:
+	_load_vec_folding_consts	0
+	_fold_vec_final	VL, V0, V1, CONSTS, BSWAP_MASK, V4, V5
+
+.Lreduce_1vec_to_128bits\@:
+.if VL == 64
+	// Reduce 512-bit %zmm0 to 256-bit %ymm0.  Then fold 256 more bits of
+	// data from BUF, if at least that much remains.
+	vbroadcasti128	OFFSETOF_FOLD_ACROSS_256_BITS_CONSTS(CONSTS_PTR), CONSTS_YMM
+	vextracti64x4	$1, %zmm0, %ymm1
+	_fold_vec_final	32, %ymm0, %ymm1, CONSTS_YMM, BSWAP_MASK_YMM, %ymm4, %ymm5
+.Lreduce_256bits_to_128bits\@:
+.endif
+.if VL >= 32
+	// Reduce 256-bit %ymm0 to 128-bit %xmm0.  Then fold 128 more bits of
+	// data from BUF, if at least that much remains.
+	vmovdqa		OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
+	vextracti128	$1, %ymm0, %xmm1
+	_fold_vec_final	16, %xmm0, %xmm1, CONSTS_XMM, BSWAP_MASK_XMM, %xmm4, %xmm5
+.Lcheck_for_partial_block\@:
+.endif
+	and		$15, LEN32
+	jz		.Lreduce_128bits_to_crc\@
+
+	// 1 <= LEN <= 15 data bytes remain in BUF.  The polynomial is now
+	// A*(x^(8*LEN)) + B, where A is the 128-bit polynomial stored in %xmm0
+	// and B is the polynomial of the remaining LEN data bytes.  To reduce
+	// this to 128 bits without needing fold constants for each possible
+	// LEN, rearrange this expression into C1*(x^128) + C2, where
+	// C1 = floor(A / x^(128 - 8*LEN)) and C2 = A*x^(8*LEN) + B mod x^128.
+	// Then fold C1 into C2, which is just another fold across 128 bits.
+
+.if !LSB_CRC || AVX_LEVEL == 0
+	// Load the last 16 data bytes.  Note that originally LEN was >= 16.
+	_load_data	16, "-16(BUF,LEN)", BSWAP_MASK_XMM, %xmm2
+.endif // Else will use vpblendvb mem operand later.
+.if !LSB_CRC
+	neg		LEN	// Needed for indexing shuf_table
+.endif
+
+	// tmp = A*x^(8*LEN) mod x^128
+	// lsb: pshufb by [LEN, LEN+1, ..., 15, -1, -1, ..., -1]
+	//	i.e. right-shift by LEN bytes.
+	// msb: pshufb by [-1, -1, ..., -1, 0, 1, ..., 15-LEN]
+	//	i.e. left-shift by LEN bytes.
+	_cond_vex movdqu,	"OFFSETOF_SHUF_TABLE+16(CONSTS_PTR,LEN)", %xmm3
+	_cond_vex pshufb,	%xmm3, %xmm0, %xmm1
+
+	// C1 = floor(A / x^(128 - 8*LEN))
+	// lsb: pshufb by [-1, -1, ..., -1, 0, 1, ..., LEN-1]
+	//	i.e. left-shift by 16-LEN bytes.
+	// msb: pshufb by [16-LEN, 16-LEN+1, ..., 15, -1, -1, ..., -1]
+	//	i.e. right-shift by 16-LEN bytes.
+	_cond_vex pshufb,	"OFFSETOF_SHUF_TABLE+32*!LSB_CRC(CONSTS_PTR,LEN)", \
+				%xmm0, %xmm0, unaligned_mem_tmp=%xmm4
+
+	// C2 = tmp + B.  This is just a blend of tmp with the last 16 data
+	// bytes (reflected if msb-first).  The blend mask is the shuffle table
+	// that was used to create tmp.  0 selects tmp, and 1 last16databytes.
+.if AVX_LEVEL == 0
+	movdqa		%xmm0, %xmm4
+	movdqa		%xmm3, %xmm0
+	pblendvb	%xmm2, %xmm1	// uses %xmm0 as implicit operand
+	movdqa		%xmm4, %xmm0
+.elseif LSB_CRC
+	vpblendvb	%xmm3, -16(BUF,LEN), %xmm1, %xmm1
+.else
+	vpblendvb	%xmm3, %xmm2, %xmm1, %xmm1
+.endif
+
+	// Fold C1 into C2 and store the 128-bit result in %xmm0.
+	_fold_vec	%xmm0, %xmm1, CONSTS_XMM, %xmm4
+
+.Lreduce_128bits_to_crc\@:
+	// Compute the CRC as %xmm0 * x^n mod G.  Here %xmm0 means the 128-bit
+	// polynomial stored in %xmm0 (using either lsb-first or msb-first bit
+	// order according to LSB_CRC), and G is the CRC's generator polynomial.
+
+	// First, multiply %xmm0 by x^n and reduce the result to 64+n bits:
+	//
+	//	t0 := (x^(64+n) mod G) * floor(%xmm0 / x^64) +
+	//	      x^n * (%xmm0 mod x^64)
+	//
+	// Store t0 * x^(64-n) in %xmm0.  I.e., actually do:
+	//
+	//	%xmm0 := ((x^(64+n) mod G) * x^(64-n)) * floor(%xmm0 / x^64) +
+	//		 x^64 * (%xmm0 mod x^64)
+	//
+	// The extra unreduced factor of x^(64-n) makes floor(t0 / x^n) aligned
+	// to the HI64_TERMS of %xmm0 so that the next pclmulqdq can easily
+	// select it.  The 64-bit constant (x^(64+n) mod G) * x^(64-n) in the
+	// msb-first case, or (x^(63+n) mod G) * x^(64-n) in the lsb-first case
+	// (considering the extra factor of x that gets implicitly introduced by
+	// each pclmulqdq when using lsb-first order), is identical to the
+	// constant that was used earlier for folding the LO64_TERMS across 128
+	// bits.  Thus it's already available in LO64_TERMS of CONSTS_XMM.
+	_pclmulqdq		CONSTS_XMM, LO64_TERMS, %xmm0, HI64_TERMS, %xmm1
+.if LSB_CRC
+	_cond_vex psrldq,	$8, %xmm0, %xmm0  // x^64 * (%xmm0 mod x^64)
+.else
+	_cond_vex pslldq,	$8, %xmm0, %xmm0  // x^64 * (%xmm0 mod x^64)
+.endif
+	_cond_vex pxor,		%xmm1, %xmm0, %xmm0
+	// The HI64_TERMS of %xmm0 now contain floor(t0 / x^n).
+	// The LO64_TERMS of %xmm0 now contain (t0 mod x^n) * x^(64-n).
+
+	// First step of Barrett reduction: Compute floor(t0 / G).  This is the
+	// polynomial by which G needs to be multiplied to cancel out the x^n
+	// and higher terms of t0, i.e. to reduce t0 mod G.  First do:
+	//
+	//	t1 := floor(x^(63+n) / G) * x * floor(t0 / x^n)
+	//
+	// Then the desired value floor(t0 / G) is floor(t1 / x^64).  The 63 in
+	// x^(63+n) is the maximum degree of floor(t0 / x^n) and thus the lowest
+	// value that makes enough precision be carried through the calculation.
+	//
+	// The '* x' makes it so the result is floor(t1 / x^64) rather than
+	// floor(t1 / x^63), making it qword-aligned in HI64_TERMS so that it
+	// can be extracted much more easily in the next step.  In the lsb-first
+	// case the '* x' happens implicitly.  In the msb-first case it must be
+	// done explicitly; floor(x^(63+n) / G) * x is a 65-bit constant, so the
+	// constant passed to pclmulqdq is (floor(x^(63+n) / G) * x) - x^64, and
+	// the multiplication by the x^64 term is handled using a pxor.  The
+	// pxor causes the low 64 terms of t1 to be wrong, but they are unused.
+	_cond_vex movdqa,	OFFSETOF_BARRETT_REDUCTION_CONSTS(CONSTS_PTR), CONSTS_XMM
+	_pclmulqdq		CONSTS_XMM, HI64_TERMS, %xmm0, HI64_TERMS, %xmm1
+.if !LSB_CRC
+	_cond_vex pxor,		%xmm0, %xmm1, %xmm1 // += x^64 * floor(t0 / x^n)
+.endif
+	// The HI64_TERMS of %xmm1 now contain floor(t1 / x^64) = floor(t0 / G).
+
+	// Second step of Barrett reduction: Cancel out the x^n and higher terms
+	// of t0 by subtracting the needed multiple of G.  This gives the CRC:
+	//
+	//	crc := t0 - (G * floor(t0 / G))
+	//
+	// But %xmm0 contains t0 * x^(64-n), so it's more convenient to do:
+	//
+	//	crc := ((t0 * x^(64-n)) - ((G * x^(64-n)) * floor(t0 / G))) / x^(64-n)
+	//
+	// Furthermore, since the resulting CRC is n-bit, if mod x^n is
+	// explicitly applied to it then the x^n term of G makes no difference
+	// in the result and can be omitted.  This helps keep the constant
+	// multiplier in 64 bits in most cases.  This gives the following:
+	//
+	//	%xmm0 := %xmm0 - (((G - x^n) * x^(64-n)) * floor(t0 / G))
+	//	crc := (%xmm0 / x^(64-n)) mod x^n
+	//
+	// In the lsb-first case, each pclmulqdq implicitly introduces
+	// an extra factor of x, so in that case the constant that needs to be
+	// passed to pclmulqdq is actually '(G - x^n) * x^(63-n)' when n <= 63.
+	// For lsb-first CRCs where n=64, the extra factor of x cannot be as
+	// easily avoided.  In that case, instead pass '(G - x^n - x^0) / x' to
+	// pclmulqdq and handle the x^0 term (i.e. 1) separately.  (All CRC
+	// polynomials have nonzero x^n and x^0 terms.)  It works out as: the
+	// CRC has be XORed with the physically low qword of %xmm1, representing
+	// floor(t0 / G).  The most efficient way to do that is to move it to
+	// the physically high qword and use a ternlog to combine the two XORs.
+.if LSB_CRC && \n == 64
+	_cond_vex punpcklqdq,	%xmm1, %xmm2, %xmm2
+	_pclmulqdq		CONSTS_XMM, LO64_TERMS, %xmm1, HI64_TERMS, %xmm1
+    .if AVX_LEVEL <= 2
+	_cond_vex pxor,		%xmm2, %xmm0, %xmm0
+	_cond_vex pxor,		%xmm1, %xmm0, %xmm0
+    .else
+	vpternlogq		$0x96, %xmm2, %xmm1, %xmm0
+    .endif
+	_cond_vex "pextrq $1,",	%xmm0, %rax  // (%xmm0 / x^0) mod x^64
+.else
+	_pclmulqdq		CONSTS_XMM, LO64_TERMS, %xmm1, HI64_TERMS, %xmm1
+	_cond_vex pxor,		%xmm1, %xmm0, %xmm0
+  .if \n == 8
+	_cond_vex "pextrb $7 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^56) mod x^8
+  .elseif \n == 16
+	_cond_vex "pextrw $3 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^48) mod x^16
+  .elseif \n == 32
+	_cond_vex "pextrd $1 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^32) mod x^32
+  .else // \n == 64 && !LSB_CRC
+	_cond_vex movq,		%xmm0, %rax  // (%xmm0 / x^0) mod x^64
+  .endif
+.endif
+
+.if VL > 16
+	vzeroupper	// Needed when ymm or zmm registers may have been used.
+.endif
+#ifdef __i386__
+	pop		CONSTS_PTR
+#endif
+	RET
+.endm
+
+#ifdef CONFIG_AS_VPCLMULQDQ
+#define DEFINE_CRC_PCLMUL_FUNCS(prefix, bits, lsb)			\
+SYM_FUNC_START(prefix##_pclmul_sse);					\
+	_crc_pclmul	n=bits, lsb_crc=lsb, vl=16, avx_level=0;	\
+SYM_FUNC_END(prefix##_pclmul_sse);					\
+									\
+SYM_FUNC_START(prefix##_vpclmul_avx2);					\
+	_crc_pclmul	n=bits, lsb_crc=lsb, vl=32, avx_level=2;	\
+SYM_FUNC_END(prefix##_vpclmul_avx2);					\
+									\
+SYM_FUNC_START(prefix##_vpclmul_avx512);				\
+	_crc_pclmul	n=bits, lsb_crc=lsb, vl=64, avx_level=512;	\
+SYM_FUNC_END(prefix##_vpclmul_avx512);
+#else
+#define DEFINE_CRC_PCLMUL_FUNCS(prefix, bits, lsb)			\
+SYM_FUNC_START(prefix##_pclmul_sse);					\
+	_crc_pclmul	n=bits, lsb_crc=lsb, vl=16, avx_level=0;	\
+SYM_FUNC_END(prefix##_pclmul_sse);
+#endif // !CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/lib/crc-pclmul-template.h b/arch/x86/lib/crc-pclmul-template.h
new file mode 100644
index 000000000000..c5b3bfe11d8d
--- /dev/null
+++ b/arch/x86/lib/crc-pclmul-template.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Macros for accessing the [V]PCLMULQDQ-based CRC functions that are
+ * instantiated by crc-pclmul-template.S
+ *
+ * Copyright 2025 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+#ifndef _CRC_PCLMUL_TEMPLATE_H
+#define _CRC_PCLMUL_TEMPLATE_H
+
+#include <asm/cpufeatures.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <linux/static_call.h>
+#include "crc-pclmul-consts.h"
+
+#define DECLARE_CRC_PCLMUL_FUNCS(prefix, crc_t)				\
+crc_t prefix##_pclmul_sse(crc_t crc, const u8 *p, size_t len,		\
+			  const void *consts_ptr);			\
+crc_t prefix##_vpclmul_avx2(crc_t crc, const u8 *p, size_t len,		\
+			    const void *consts_ptr);			\
+crc_t prefix##_vpclmul_avx512(crc_t crc, const u8 *p, size_t len,	\
+			      const void *consts_ptr);			\
+DEFINE_STATIC_CALL(prefix##_pclmul, prefix##_pclmul_sse)
+
+#define INIT_CRC_PCLMUL(prefix)						\
+do {									\
+	if (IS_ENABLED(CONFIG_AS_VPCLMULQDQ) &&				\
+	    boot_cpu_has(X86_FEATURE_VPCLMULQDQ) &&			\
+	    boot_cpu_has(X86_FEATURE_AVX2) &&				\
+	    cpu_has_xfeatures(XFEATURE_MASK_YMM, NULL)) {		\
+		if (boot_cpu_has(X86_FEATURE_AVX512BW) &&		\
+		    boot_cpu_has(X86_FEATURE_AVX512VL) &&		\
+		    !boot_cpu_has(X86_FEATURE_PREFER_YMM) &&		\
+		    cpu_has_xfeatures(XFEATURE_MASK_AVX512, NULL)) {	\
+			static_call_update(prefix##_pclmul,		\
+					   prefix##_vpclmul_avx512);	\
+		} else {						\
+			static_call_update(prefix##_pclmul,		\
+					   prefix##_vpclmul_avx2);	\
+		}							\
+	}								\
+} while (0)
+
+/*
+ * Call a [V]PCLMULQDQ optimized CRC function if the data length is at least 16
+ * bytes, the CPU has PCLMULQDQ support, and the current context may use SIMD.
+ *
+ * 16 bytes is the minimum length supported by the [V]PCLMULQDQ functions.
+ * There is overhead associated with kernel_fpu_begin() and kernel_fpu_end(),
+ * varying by CPU and factors such as which parts of the "FPU" state userspace
+ * has touched, which could result in a larger cutoff being better.  Indeed, a
+ * larger cutoff is usually better for a *single* message.  However, the
+ * overhead of the FPU section gets amortized if multiple FPU sections get
+ * executed before returning to userspace, since the XSAVE and XRSTOR occur only
+ * once.  Considering that and the fact that the [V]PCLMULQDQ code is lighter on
+ * the dcache than the table-based code is, a 16-byte cutoff seems to work well.
+ */
+#define CRC_PCLMUL(crc, p, len, prefix, consts, have_pclmulqdq)		\
+do {									\
+	if ((len) >= 16 && static_branch_likely(&(have_pclmulqdq)) &&	\
+	    crypto_simd_usable()) {					\
+		const void *consts_ptr;					\
+									\
+		consts_ptr = (consts).fold_across_128_bits_consts;	\
+		kernel_fpu_begin();					\
+		crc = static_call(prefix##_pclmul)((crc), (p), (len),	\
+						   consts_ptr);		\
+		kernel_fpu_end();					\
+		return crc;						\
+	}								\
+} while (0)
+
+#endif /* _CRC_PCLMUL_TEMPLATE_H */
diff --git a/arch/x86/lib/crc-t10dif-glue.c b/arch/x86/lib/crc-t10dif-glue.c
deleted file mode 100644
index 13f07ddc9122..000000000000
--- a/arch/x86/lib/crc-t10dif-glue.c
+++ /dev/null
@@ -1,51 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * CRC-T10DIF using PCLMULQDQ instructions
- *
- * Copyright 2024 Google LLC
- */
-
-#include <asm/cpufeatures.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
-#include <linux/crc-t10dif.h>
-#include <linux/module.h>
-
-static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
-
-asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len);
-
-u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len)
-{
-	if (len >= 16 &&
-	    static_key_enabled(&have_pclmulqdq) && crypto_simd_usable()) {
-		kernel_fpu_begin();
-		crc = crc_t10dif_pcl(crc, p, len);
-		kernel_fpu_end();
-		return crc;
-	}
-	return crc_t10dif_generic(crc, p, len);
-}
-EXPORT_SYMBOL(crc_t10dif_arch);
-
-static int __init crc_t10dif_x86_init(void)
-{
-	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ))
-		static_branch_enable(&have_pclmulqdq);
-	return 0;
-}
-arch_initcall(crc_t10dif_x86_init);
-
-static void __exit crc_t10dif_x86_exit(void)
-{
-}
-module_exit(crc_t10dif_x86_exit);
-
-bool crc_t10dif_is_optimized(void)
-{
-	return static_key_enabled(&have_pclmulqdq);
-}
-EXPORT_SYMBOL(crc_t10dif_is_optimized);
-
-MODULE_DESCRIPTION("CRC-T10DIF using PCLMULQDQ instructions");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crc-t10dif.c b/arch/x86/lib/crc-t10dif.c
new file mode 100644
index 000000000000..db7ce59c31ac
--- /dev/null
+++ b/arch/x86/lib/crc-t10dif.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * CRC-T10DIF using [V]PCLMULQDQ instructions
+ *
+ * Copyright 2024 Google LLC
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/module.h>
+#include "crc-pclmul-template.h"
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
+
+DECLARE_CRC_PCLMUL_FUNCS(crc16_msb, u16);
+
+u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len)
+{
+	CRC_PCLMUL(crc, p, len, crc16_msb, crc16_msb_0x8bb7_consts,
+		   have_pclmulqdq);
+	return crc_t10dif_generic(crc, p, len);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_x86_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
+		static_branch_enable(&have_pclmulqdq);
+		INIT_CRC_PCLMUL(crc16_msb);
+	}
+	return 0;
+}
+subsys_initcall(crc_t10dif_x86_init);
+
+static void __exit crc_t10dif_x86_exit(void)
+{
+}
+module_exit(crc_t10dif_x86_exit);
+
+MODULE_DESCRIPTION("CRC-T10DIF using [V]PCLMULQDQ instructions");
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crc16-msb-pclmul.S b/arch/x86/lib/crc16-msb-pclmul.S
new file mode 100644
index 000000000000..e9fe248093a8
--- /dev/null
+++ b/arch/x86/lib/crc16-msb-pclmul.S
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+// Copyright 2025 Google LLC
+
+#include "crc-pclmul-template.S"
+
+DEFINE_CRC_PCLMUL_FUNCS(crc16_msb, /* bits= */ 16, /* lsb= */ 0)
diff --git a/arch/x86/lib/crc32-pclmul.S b/arch/x86/lib/crc32-pclmul.S
index f9637789cac1..f20f40fb0172 100644
--- a/arch/x86/lib/crc32-pclmul.S
+++ b/arch/x86/lib/crc32-pclmul.S
@@ -1,217 +1,6 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2012 Xyratex Technology Limited
- *
- * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
- * calculation.
- * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
- * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
- * at:
- * http://www.intel.com/products/processor/manuals/
- * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
- * Volume 2B: Instruction Set Reference, N-Z
- *
- * Authors:   Gregory Prestas <Gregory_Prestas@us.xyratex.com>
- *	      Alexander Boyko <Alexander_Boyko@xyratex.com>
- */
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+// Copyright 2025 Google LLC
 
-#include <linux/linkage.h>
+#include "crc-pclmul-template.S"
 
-
-.section .rodata
-.align 16
-/*
- * [x4*128+32 mod P(x) << 32)]'  << 1   = 0x154442bd4
- * #define CONSTANT_R1  0x154442bd4LL
- *
- * [(x4*128-32 mod P(x) << 32)]' << 1   = 0x1c6e41596
- * #define CONSTANT_R2  0x1c6e41596LL
- */
-.Lconstant_R2R1:
-	.octa 0x00000001c6e415960000000154442bd4
-/*
- * [(x128+32 mod P(x) << 32)]'   << 1   = 0x1751997d0
- * #define CONSTANT_R3  0x1751997d0LL
- *
- * [(x128-32 mod P(x) << 32)]'   << 1   = 0x0ccaa009e
- * #define CONSTANT_R4  0x0ccaa009eLL
- */
-.Lconstant_R4R3:
-	.octa 0x00000000ccaa009e00000001751997d0
-/*
- * [(x64 mod P(x) << 32)]'       << 1   = 0x163cd6124
- * #define CONSTANT_R5  0x163cd6124LL
- */
-.Lconstant_R5:
-	.octa 0x00000000000000000000000163cd6124
-.Lconstant_mask32:
-	.octa 0x000000000000000000000000FFFFFFFF
-/*
- * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
- *
- * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))` = 0x1F7011641LL
- * #define CONSTANT_RU  0x1F7011641LL
- */
-.Lconstant_RUpoly:
-	.octa 0x00000001F701164100000001DB710641
-
-#define CONSTANT %xmm0
-
-#ifdef __x86_64__
-#define CRC     %edi
-#define BUF     %rsi
-#define LEN     %rdx
-#else
-#define CRC     %eax
-#define BUF     %edx
-#define LEN     %ecx
-#endif
-
-
-
-.text
-/**
- *      Calculate crc32
- *      CRC - initial crc32
- *      BUF - buffer (16 bytes aligned)
- *      LEN - sizeof buffer (16 bytes aligned), LEN should be greater than 63
- *      return %eax crc32
- *      u32 crc32_pclmul_le_16(u32 crc, const u8 *buffer, size_t len);
- */
-
-SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */
-	movdqa  (BUF), %xmm1
-	movdqa  0x10(BUF), %xmm2
-	movdqa  0x20(BUF), %xmm3
-	movdqa  0x30(BUF), %xmm4
-	movd    CRC, CONSTANT
-	pxor    CONSTANT, %xmm1
-	sub     $0x40, LEN
-	add     $0x40, BUF
-	cmp     $0x40, LEN
-	jb      .Lless_64
-
-#ifdef __x86_64__
-	movdqa .Lconstant_R2R1(%rip), CONSTANT
-#else
-	movdqa .Lconstant_R2R1, CONSTANT
-#endif
-
-.Lloop_64:/*  64 bytes Full cache line folding */
-	prefetchnta    0x40(BUF)
-	movdqa  %xmm1, %xmm5
-	movdqa  %xmm2, %xmm6
-	movdqa  %xmm3, %xmm7
-#ifdef __x86_64__
-	movdqa  %xmm4, %xmm8
-#endif
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pclmulqdq $0x00, CONSTANT, %xmm2
-	pclmulqdq $0x00, CONSTANT, %xmm3
-#ifdef __x86_64__
-	pclmulqdq $0x00, CONSTANT, %xmm4
-#endif
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pclmulqdq $0x11, CONSTANT, %xmm6
-	pclmulqdq $0x11, CONSTANT, %xmm7
-#ifdef __x86_64__
-	pclmulqdq $0x11, CONSTANT, %xmm8
-#endif
-	pxor    %xmm5, %xmm1
-	pxor    %xmm6, %xmm2
-	pxor    %xmm7, %xmm3
-#ifdef __x86_64__
-	pxor    %xmm8, %xmm4
-#else
-	/* xmm8 unsupported for x32 */
-	movdqa  %xmm4, %xmm5
-	pclmulqdq $0x00, CONSTANT, %xmm4
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pxor    %xmm5, %xmm4
-#endif
-
-	pxor    (BUF), %xmm1
-	pxor    0x10(BUF), %xmm2
-	pxor    0x20(BUF), %xmm3
-	pxor    0x30(BUF), %xmm4
-
-	sub     $0x40, LEN
-	add     $0x40, BUF
-	cmp     $0x40, LEN
-	jge     .Lloop_64
-.Lless_64:/*  Folding cache line into 128bit */
-#ifdef __x86_64__
-	movdqa  .Lconstant_R4R3(%rip), CONSTANT
-#else
-	movdqa  .Lconstant_R4R3, CONSTANT
-#endif
-	prefetchnta     (BUF)
-
-	movdqa  %xmm1, %xmm5
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pxor    %xmm5, %xmm1
-	pxor    %xmm2, %xmm1
-
-	movdqa  %xmm1, %xmm5
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pxor    %xmm5, %xmm1
-	pxor    %xmm3, %xmm1
-
-	movdqa  %xmm1, %xmm5
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pxor    %xmm5, %xmm1
-	pxor    %xmm4, %xmm1
-
-	cmp     $0x10, LEN
-	jb      .Lfold_64
-.Lloop_16:/* Folding rest buffer into 128bit */
-	movdqa  %xmm1, %xmm5
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pclmulqdq $0x11, CONSTANT, %xmm5
-	pxor    %xmm5, %xmm1
-	pxor    (BUF), %xmm1
-	sub     $0x10, LEN
-	add     $0x10, BUF
-	cmp     $0x10, LEN
-	jge     .Lloop_16
-
-.Lfold_64:
-	/* perform the last 64 bit fold, also adds 32 zeroes
-	 * to the input stream */
-	pclmulqdq $0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
-	psrldq  $0x08, %xmm1
-	pxor    CONSTANT, %xmm1
-
-	/* final 32-bit fold */
-	movdqa  %xmm1, %xmm2
-#ifdef __x86_64__
-	movdqa  .Lconstant_R5(%rip), CONSTANT
-	movdqa  .Lconstant_mask32(%rip), %xmm3
-#else
-	movdqa  .Lconstant_R5, CONSTANT
-	movdqa  .Lconstant_mask32, %xmm3
-#endif
-	psrldq  $0x04, %xmm2
-	pand    %xmm3, %xmm1
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pxor    %xmm2, %xmm1
-
-	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
-#ifdef __x86_64__
-	movdqa  .Lconstant_RUpoly(%rip), CONSTANT
-#else
-	movdqa  .Lconstant_RUpoly, CONSTANT
-#endif
-	movdqa  %xmm1, %xmm2
-	pand    %xmm3, %xmm1
-	pclmulqdq $0x10, CONSTANT, %xmm1
-	pand    %xmm3, %xmm1
-	pclmulqdq $0x00, CONSTANT, %xmm1
-	pxor    %xmm2, %xmm1
-	pextrd  $0x01, %xmm1, %eax
-
-	RET
-SYM_FUNC_END(crc32_pclmul_le_16)
+DEFINE_CRC_PCLMUL_FUNCS(crc32_lsb, /* bits= */ 32, /* lsb= */ 1)
diff --git a/arch/x86/lib/crc32-glue.c b/arch/x86/lib/crc32.c
index 2dd18a886ded..d09343e2cea9 100644
--- a/arch/x86/lib/crc32-glue.c
+++ b/arch/x86/lib/crc32.c
@@ -7,43 +7,20 @@
  * Copyright 2024 Google LLC
  */
 
-#include <asm/cpufeatures.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
 #include <linux/crc32.h>
-#include <linux/linkage.h>
 #include <linux/module.h>
+#include "crc-pclmul-template.h"
 
-/* minimum size of buffer for crc32_pclmul_le_16 */
-#define CRC32_PCLMUL_MIN_LEN	64
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
 
-static DEFINE_STATIC_KEY_FALSE(have_crc32);
-static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
-
-u32 crc32_pclmul_le_16(u32 crc, const u8 *buffer, size_t len);
+DECLARE_CRC_PCLMUL_FUNCS(crc32_lsb, u32);
 
 u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
 {
-	if (len >= CRC32_PCLMUL_MIN_LEN + 15 &&
-	    static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) {
-		size_t n = -(uintptr_t)p & 15;
-
-		/* align p to 16-byte boundary */
-		if (n) {
-			crc = crc32_le_base(crc, p, n);
-			p += n;
-			len -= n;
-		}
-		n = round_down(len, 16);
-		kernel_fpu_begin();
-		crc = crc32_pclmul_le_16(crc, p, n);
-		kernel_fpu_end();
-		p += n;
-		len -= n;
-	}
-	if (len)
-		crc = crc32_le_base(crc, p, len);
-	return crc;
+	CRC_PCLMUL(crc, p, len, crc32_lsb, crc32_lsb_0xedb88320_consts,
+		   have_pclmulqdq);
+	return crc32_le_base(crc, p, len);
 }
 EXPORT_SYMBOL(crc32_le_arch);
 
@@ -61,12 +38,12 @@ EXPORT_SYMBOL(crc32_le_arch);
 
 asmlinkage u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len);
 
-u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	size_t num_longs;
 
 	if (!static_branch_likely(&have_crc32))
-		return crc32c_le_base(crc, p, len);
+		return crc32c_base(crc, p, len);
 
 	if (IS_ENABLED(CONFIG_X86_64) && len >= CRC32C_PCLMUL_BREAKEVEN &&
 	    static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) {
@@ -78,14 +55,22 @@ u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
 
 	for (num_longs = len / sizeof(unsigned long);
 	     num_longs != 0; num_longs--, p += sizeof(unsigned long))
-		asm(CRC32_INST : "+r" (crc) : "rm" (*(unsigned long *)p));
+		asm(CRC32_INST : "+r" (crc) : ASM_INPUT_RM (*(unsigned long *)p));
 
-	for (len %= sizeof(unsigned long); len; len--, p++)
-		asm("crc32b %1, %0" : "+r" (crc) : "rm" (*p));
+	if (sizeof(unsigned long) > 4 && (len & 4)) {
+		asm("crc32l %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u32 *)p));
+		p += 4;
+	}
+	if (len & 2) {
+		asm("crc32w %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u16 *)p));
+		p += 2;
+	}
+	if (len & 1)
+		asm("crc32b %1, %0" : "+r" (crc) : ASM_INPUT_RM (*p));
 
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_le_arch);
+EXPORT_SYMBOL(crc32c_arch);
 
 u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
 {
@@ -97,11 +82,13 @@ static int __init crc32_x86_init(void)
 {
 	if (boot_cpu_has(X86_FEATURE_XMM4_2))
 		static_branch_enable(&have_crc32);
-	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ))
+	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
 		static_branch_enable(&have_pclmulqdq);
+		INIT_CRC_PCLMUL(crc32_lsb);
+	}
 	return 0;
 }
-arch_initcall(crc32_x86_init);
+subsys_initcall(crc32_x86_init);
 
 static void __exit crc32_x86_exit(void)
 {
diff --git a/arch/x86/lib/crc64-pclmul.S b/arch/x86/lib/crc64-pclmul.S
new file mode 100644
index 000000000000..4173051b5197
--- /dev/null
+++ b/arch/x86/lib/crc64-pclmul.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+// Copyright 2025 Google LLC
+
+#include "crc-pclmul-template.S"
+
+DEFINE_CRC_PCLMUL_FUNCS(crc64_msb, /* bits= */ 64, /* lsb= */ 0)
+DEFINE_CRC_PCLMUL_FUNCS(crc64_lsb, /* bits= */ 64, /* lsb= */ 1)
diff --git a/arch/x86/lib/crc64.c b/arch/x86/lib/crc64.c
new file mode 100644
index 000000000000..351a09f5813e
--- /dev/null
+++ b/arch/x86/lib/crc64.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * CRC64 using [V]PCLMULQDQ instructions
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include <linux/crc64.h>
+#include <linux/module.h>
+#include "crc-pclmul-template.h"
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
+
+DECLARE_CRC_PCLMUL_FUNCS(crc64_msb, u64);
+DECLARE_CRC_PCLMUL_FUNCS(crc64_lsb, u64);
+
+u64 crc64_be_arch(u64 crc, const u8 *p, size_t len)
+{
+	CRC_PCLMUL(crc, p, len, crc64_msb, crc64_msb_0x42f0e1eba9ea3693_consts,
+		   have_pclmulqdq);
+	return crc64_be_generic(crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_be_arch);
+
+u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len)
+{
+	CRC_PCLMUL(crc, p, len, crc64_lsb, crc64_lsb_0x9a6c9329ac4bc9b5_consts,
+		   have_pclmulqdq);
+	return crc64_nvme_generic(crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_nvme_arch);
+
+static int __init crc64_x86_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
+		static_branch_enable(&have_pclmulqdq);
+		INIT_CRC_PCLMUL(crc64_msb);
+		INIT_CRC_PCLMUL(crc64_lsb);
+	}
+	return 0;
+}
+subsys_initcall(crc64_x86_init);
+
+static void __exit crc64_x86_exit(void)
+{
+}
+module_exit(crc64_x86_exit);
+
+MODULE_DESCRIPTION("CRC64 using [V]PCLMULQDQ instructions");
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crct10dif-pcl-asm_64.S b/arch/x86/lib/crct10dif-pcl-asm_64.S
deleted file mode 100644
index 5286db5b8165..000000000000
--- a/arch/x86/lib/crct10dif-pcl-asm_64.S
+++ /dev/null
@@ -1,332 +0,0 @@
-########################################################################
-# Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
-#
-# Copyright (c) 2013, Intel Corporation
-#
-# Authors:
-#     Erdinc Ozturk <erdinc.ozturk@intel.com>
-#     Vinodh Gopal <vinodh.gopal@intel.com>
-#     James Guilford <james.guilford@intel.com>
-#     Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses.  You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions are
-# met:
-#
-# * Redistributions of source code must retain the above copyright
-#   notice, this list of conditions and the following disclaimer.
-#
-# * Redistributions in binary form must reproduce the above copyright
-#   notice, this list of conditions and the following disclaimer in the
-#   documentation and/or other materials provided with the
-#   distribution.
-#
-# * Neither the name of the Intel Corporation nor the names of its
-#   contributors may be used to endorse or promote products derived from
-#   this software without specific prior written permission.
-#
-#
-# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
-# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
-# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-#
-#       Reference paper titled "Fast CRC Computation for Generic
-#	Polynomials Using PCLMULQDQ Instruction"
-#       URL: http://www.intel.com/content/dam/www/public/us/en/documents
-#  /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
-#
-
-#include <linux/linkage.h>
-
-.text
-
-#define		init_crc	%edi
-#define		buf		%rsi
-#define		len		%rdx
-
-#define		FOLD_CONSTS	%xmm10
-#define		BSWAP_MASK	%xmm11
-
-# Fold reg1, reg2 into the next 32 data bytes, storing the result back into
-# reg1, reg2.
-.macro	fold_32_bytes	offset, reg1, reg2
-	movdqu	\offset(buf), %xmm9
-	movdqu	\offset+16(buf), %xmm12
-	pshufb	BSWAP_MASK, %xmm9
-	pshufb	BSWAP_MASK, %xmm12
-	movdqa	\reg1, %xmm8
-	movdqa	\reg2, %xmm13
-	pclmulqdq	$0x00, FOLD_CONSTS, \reg1
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm8
-	pclmulqdq	$0x00, FOLD_CONSTS, \reg2
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm13
-	pxor	%xmm9 , \reg1
-	xorps	%xmm8 , \reg1
-	pxor	%xmm12, \reg2
-	xorps	%xmm13, \reg2
-.endm
-
-# Fold src_reg into dst_reg.
-.macro	fold_16_bytes	src_reg, dst_reg
-	movdqa	\src_reg, %xmm8
-	pclmulqdq	$0x11, FOLD_CONSTS, \src_reg
-	pclmulqdq	$0x00, FOLD_CONSTS, %xmm8
-	pxor	%xmm8, \dst_reg
-	xorps	\src_reg, \dst_reg
-.endm
-
-#
-# u16 crc_t10dif_pcl(u16 init_crc, const *u8 buf, size_t len);
-#
-# Assumes len >= 16.
-#
-SYM_FUNC_START(crc_t10dif_pcl)
-
-	movdqa	.Lbswap_mask(%rip), BSWAP_MASK
-
-	# For sizes less than 256 bytes, we can't fold 128 bytes at a time.
-	cmp	$256, len
-	jl	.Lless_than_256_bytes
-
-	# Load the first 128 data bytes.  Byte swapping is necessary to make the
-	# bit order match the polynomial coefficient order.
-	movdqu	16*0(buf), %xmm0
-	movdqu	16*1(buf), %xmm1
-	movdqu	16*2(buf), %xmm2
-	movdqu	16*3(buf), %xmm3
-	movdqu	16*4(buf), %xmm4
-	movdqu	16*5(buf), %xmm5
-	movdqu	16*6(buf), %xmm6
-	movdqu	16*7(buf), %xmm7
-	add	$128, buf
-	pshufb	BSWAP_MASK, %xmm0
-	pshufb	BSWAP_MASK, %xmm1
-	pshufb	BSWAP_MASK, %xmm2
-	pshufb	BSWAP_MASK, %xmm3
-	pshufb	BSWAP_MASK, %xmm4
-	pshufb	BSWAP_MASK, %xmm5
-	pshufb	BSWAP_MASK, %xmm6
-	pshufb	BSWAP_MASK, %xmm7
-
-	# XOR the first 16 data *bits* with the initial CRC value.
-	pxor	%xmm8, %xmm8
-	pinsrw	$7, init_crc, %xmm8
-	pxor	%xmm8, %xmm0
-
-	movdqa	.Lfold_across_128_bytes_consts(%rip), FOLD_CONSTS
-
-	# Subtract 128 for the 128 data bytes just consumed.  Subtract another
-	# 128 to simplify the termination condition of the following loop.
-	sub	$256, len
-
-	# While >= 128 data bytes remain (not counting xmm0-7), fold the 128
-	# bytes xmm0-7 into them, storing the result back into xmm0-7.
-.Lfold_128_bytes_loop:
-	fold_32_bytes	0, %xmm0, %xmm1
-	fold_32_bytes	32, %xmm2, %xmm3
-	fold_32_bytes	64, %xmm4, %xmm5
-	fold_32_bytes	96, %xmm6, %xmm7
-	add	$128, buf
-	sub	$128, len
-	jge	.Lfold_128_bytes_loop
-
-	# Now fold the 112 bytes in xmm0-xmm6 into the 16 bytes in xmm7.
-
-	# Fold across 64 bytes.
-	movdqa	.Lfold_across_64_bytes_consts(%rip), FOLD_CONSTS
-	fold_16_bytes	%xmm0, %xmm4
-	fold_16_bytes	%xmm1, %xmm5
-	fold_16_bytes	%xmm2, %xmm6
-	fold_16_bytes	%xmm3, %xmm7
-	# Fold across 32 bytes.
-	movdqa	.Lfold_across_32_bytes_consts(%rip), FOLD_CONSTS
-	fold_16_bytes	%xmm4, %xmm6
-	fold_16_bytes	%xmm5, %xmm7
-	# Fold across 16 bytes.
-	movdqa	.Lfold_across_16_bytes_consts(%rip), FOLD_CONSTS
-	fold_16_bytes	%xmm6, %xmm7
-
-	# Add 128 to get the correct number of data bytes remaining in 0...127
-	# (not counting xmm7), following the previous extra subtraction by 128.
-	# Then subtract 16 to simplify the termination condition of the
-	# following loop.
-	add	$128-16, len
-
-	# While >= 16 data bytes remain (not counting xmm7), fold the 16 bytes
-	# xmm7 into them, storing the result back into xmm7.
-	jl	.Lfold_16_bytes_loop_done
-.Lfold_16_bytes_loop:
-	movdqa	%xmm7, %xmm8
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm7
-	pclmulqdq	$0x00, FOLD_CONSTS, %xmm8
-	pxor	%xmm8, %xmm7
-	movdqu	(buf), %xmm0
-	pshufb	BSWAP_MASK, %xmm0
-	pxor	%xmm0 , %xmm7
-	add	$16, buf
-	sub	$16, len
-	jge	.Lfold_16_bytes_loop
-
-.Lfold_16_bytes_loop_done:
-	# Add 16 to get the correct number of data bytes remaining in 0...15
-	# (not counting xmm7), following the previous extra subtraction by 16.
-	add	$16, len
-	je	.Lreduce_final_16_bytes
-
-.Lhandle_partial_segment:
-	# Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first 16
-	# bytes are in xmm7 and the rest are the remaining data in 'buf'.  To do
-	# this without needing a fold constant for each possible 'len', redivide
-	# the bytes into a first chunk of 'len' bytes and a second chunk of 16
-	# bytes, then fold the first chunk into the second.
-
-	movdqa	%xmm7, %xmm2
-
-	# xmm1 = last 16 original data bytes
-	movdqu	-16(buf, len), %xmm1
-	pshufb	BSWAP_MASK, %xmm1
-
-	# xmm2 = high order part of second chunk: xmm7 left-shifted by 'len' bytes.
-	lea	.Lbyteshift_table+16(%rip), %rax
-	sub	len, %rax
-	movdqu	(%rax), %xmm0
-	pshufb	%xmm0, %xmm2
-
-	# xmm7 = first chunk: xmm7 right-shifted by '16-len' bytes.
-	pxor	.Lmask1(%rip), %xmm0
-	pshufb	%xmm0, %xmm7
-
-	# xmm1 = second chunk: 'len' bytes from xmm1 (low-order bytes),
-	# then '16-len' bytes from xmm2 (high-order bytes).
-	pblendvb	%xmm2, %xmm1	#xmm0 is implicit
-
-	# Fold the first chunk into the second chunk, storing the result in xmm7.
-	movdqa	%xmm7, %xmm8
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm7
-	pclmulqdq	$0x00, FOLD_CONSTS, %xmm8
-	pxor	%xmm8, %xmm7
-	pxor	%xmm1, %xmm7
-
-.Lreduce_final_16_bytes:
-	# Reduce the 128-bit value M(x), stored in xmm7, to the final 16-bit CRC
-
-	# Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
-	movdqa	.Lfinal_fold_consts(%rip), FOLD_CONSTS
-
-	# Fold the high 64 bits into the low 64 bits, while also multiplying by
-	# x^64.  This produces a 128-bit value congruent to x^64 * M(x) and
-	# whose low 48 bits are 0.
-	movdqa	%xmm7, %xmm0
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm7 # high bits * x^48 * (x^80 mod G(x))
-	pslldq	$8, %xmm0
-	pxor	%xmm0, %xmm7			  # + low bits * x^64
-
-	# Fold the high 32 bits into the low 96 bits.  This produces a 96-bit
-	# value congruent to x^64 * M(x) and whose low 48 bits are 0.
-	movdqa	%xmm7, %xmm0
-	pand	.Lmask2(%rip), %xmm0		  # zero high 32 bits
-	psrldq	$12, %xmm7			  # extract high 32 bits
-	pclmulqdq	$0x00, FOLD_CONSTS, %xmm7 # high 32 bits * x^48 * (x^48 mod G(x))
-	pxor	%xmm0, %xmm7			  # + low bits
-
-	# Load G(x) and floor(x^48 / G(x)).
-	movdqa	.Lbarrett_reduction_consts(%rip), FOLD_CONSTS
-
-	# Use Barrett reduction to compute the final CRC value.
-	movdqa	%xmm7, %xmm0
-	pclmulqdq	$0x11, FOLD_CONSTS, %xmm7 # high 32 bits * floor(x^48 / G(x))
-	psrlq	$32, %xmm7			  # /= x^32
-	pclmulqdq	$0x00, FOLD_CONSTS, %xmm7 # *= G(x)
-	psrlq	$48, %xmm0
-	pxor	%xmm7, %xmm0		     # + low 16 nonzero bits
-	# Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of xmm0.
-
-	pextrw	$0, %xmm0, %eax
-	RET
-
-.align 16
-.Lless_than_256_bytes:
-	# Checksumming a buffer of length 16...255 bytes
-
-	# Load the first 16 data bytes.
-	movdqu	(buf), %xmm7
-	pshufb	BSWAP_MASK, %xmm7
-	add	$16, buf
-
-	# XOR the first 16 data *bits* with the initial CRC value.
-	pxor	%xmm0, %xmm0
-	pinsrw	$7, init_crc, %xmm0
-	pxor	%xmm0, %xmm7
-
-	movdqa	.Lfold_across_16_bytes_consts(%rip), FOLD_CONSTS
-	cmp	$16, len
-	je	.Lreduce_final_16_bytes		# len == 16
-	sub	$32, len
-	jge	.Lfold_16_bytes_loop		# 32 <= len <= 255
-	add	$16, len
-	jmp	.Lhandle_partial_segment	# 17 <= len <= 31
-SYM_FUNC_END(crc_t10dif_pcl)
-
-.section	.rodata, "a", @progbits
-.align 16
-
-# Fold constants precomputed from the polynomial 0x18bb7
-# G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
-.Lfold_across_128_bytes_consts:
-	.quad		0x0000000000006123	# x^(8*128)	mod G(x)
-	.quad		0x0000000000002295	# x^(8*128+64)	mod G(x)
-.Lfold_across_64_bytes_consts:
-	.quad		0x0000000000001069	# x^(4*128)	mod G(x)
-	.quad		0x000000000000dd31	# x^(4*128+64)	mod G(x)
-.Lfold_across_32_bytes_consts:
-	.quad		0x000000000000857d	# x^(2*128)	mod G(x)
-	.quad		0x0000000000007acc	# x^(2*128+64)	mod G(x)
-.Lfold_across_16_bytes_consts:
-	.quad		0x000000000000a010	# x^(1*128)	mod G(x)
-	.quad		0x0000000000001faa	# x^(1*128+64)	mod G(x)
-.Lfinal_fold_consts:
-	.quad		0x1368000000000000	# x^48 * (x^48 mod G(x))
-	.quad		0x2d56000000000000	# x^48 * (x^80 mod G(x))
-.Lbarrett_reduction_consts:
-	.quad		0x0000000000018bb7	# G(x)
-	.quad		0x00000001f65a57f8	# floor(x^48 / G(x))
-
-.section	.rodata.cst16.mask1, "aM", @progbits, 16
-.align 16
-.Lmask1:
-	.octa	0x80808080808080808080808080808080
-
-.section	.rodata.cst16.mask2, "aM", @progbits, 16
-.align 16
-.Lmask2:
-	.octa	0x00000000FFFFFFFFFFFFFFFFFFFFFFFF
-
-.section	.rodata.cst16.bswap_mask, "aM", @progbits, 16
-.align 16
-.Lbswap_mask:
-	.octa	0x000102030405060708090A0B0C0D0E0F
-
-.section	.rodata.cst32.byteshift_table, "aM", @progbits, 32
-.align 16
-# For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 - len]
-# is the index vector to shift left by 'len' bytes, and is also {0x80, ...,
-# 0x80} XOR the index vector to shift right by '16 - len' bytes.
-.Lbyteshift_table:
-	.byte		 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87
-	.byte		0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
-	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
-	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe , 0x0
diff --git a/arch/x86/lib/crypto/.gitignore b/arch/x86/lib/crypto/.gitignore
new file mode 100644
index 000000000000..580c839bb177
--- /dev/null
+++ b/arch/x86/lib/crypto/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+poly1305-x86_64-cryptogams.S
diff --git a/arch/x86/lib/crypto/Kconfig b/arch/x86/lib/crypto/Kconfig
new file mode 100644
index 000000000000..5e94cdee492c
--- /dev/null
+++ b/arch/x86/lib/crypto/Kconfig
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_BLAKE2S_X86
+	bool "Hash functions: BLAKE2s (SSSE3/AVX-512)"
+	depends on 64BIT
+	select CRYPTO_LIB_BLAKE2S_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+	help
+	  BLAKE2s cryptographic hash function (RFC 7693)
+
+	  Architecture: x86_64 using:
+	  - SSSE3 (Supplemental SSE3)
+	  - AVX-512 (Advanced Vector Extensions-512)
+
+config CRYPTO_CHACHA20_X86_64
+	tristate
+	depends on 64BIT
+	default CRYPTO_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_X86_64
+	tristate
+	depends on 64BIT
+	default CRYPTO_LIB_POLY1305
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+config CRYPTO_SHA256_X86_64
+	tristate
+	depends on 64BIT
+	default CRYPTO_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256
+	select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD
+	select CRYPTO_LIB_SHA256_GENERIC
diff --git a/arch/x86/lib/crypto/Makefile b/arch/x86/lib/crypto/Makefile
new file mode 100644
index 000000000000..abceca3d31c0
--- /dev/null
+++ b/arch/x86/lib/crypto/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o
+libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
+
+obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
+chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha-avx512vl-x86_64.o chacha_glue.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
+poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
+targets += poly1305-x86_64-cryptogams.S
+
+obj-$(CONFIG_CRYPTO_SHA256_X86_64) += sha256-x86_64.o
+sha256-x86_64-y := sha256.o sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256-ni-asm.o
+
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $< > $@
+
+$(obj)/%.S: $(src)/%.pl FORCE
+	$(call if_changed,perlasm)
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/lib/crypto/blake2s-core.S
index b50b35ff1fdb..ac1c845445a4 100644
--- a/arch/x86/crypto/blake2s-core.S
+++ b/arch/x86/lib/crypto/blake2s-core.S
@@ -29,7 +29,6 @@ SIGMA:
 .byte 13,  7, 12,  3, 11, 14,  1,  9,  2,  5, 15,  8, 10,  0,  4,  6
 .byte  6, 14, 11,  0, 15,  9,  3,  8, 10, 12, 13,  1,  5,  2,  7,  4
 .byte 10,  8,  7,  1,  2,  4,  6,  5, 13, 15,  9,  3,  0, 11, 14, 12
-#ifdef CONFIG_AS_AVX512
 .section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
 .align 64
 SIGMA2:
@@ -43,7 +42,6 @@ SIGMA2:
 .long  6, 13,  0, 14, 12,  2,  1, 11, 15,  4,  5,  8,  7,  9,  3, 10
 .long 15,  5,  4, 13, 10,  7,  3, 11, 12,  2,  0,  6,  9,  8,  1, 14
 .long  8,  7, 14, 11, 13, 15,  0, 12, 10,  4,  5,  6,  3,  2,  1,  9
-#endif /* CONFIG_AS_AVX512 */
 
 .text
 SYM_FUNC_START(blake2s_compress_ssse3)
@@ -174,7 +172,6 @@ SYM_FUNC_START(blake2s_compress_ssse3)
 	RET
 SYM_FUNC_END(blake2s_compress_ssse3)
 
-#ifdef CONFIG_AS_AVX512
 SYM_FUNC_START(blake2s_compress_avx512)
 	vmovdqu		(%rdi),%xmm0
 	vmovdqu		0x10(%rdi),%xmm1
@@ -253,4 +250,3 @@ SYM_FUNC_START(blake2s_compress_avx512)
 	vzeroupper
 	RET
 SYM_FUNC_END(blake2s_compress_avx512)
-#endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/lib/crypto/blake2s-glue.c
index 0313f9673f56..adc296cd17c9 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/lib/crypto/blake2s-glue.c
@@ -3,17 +3,15 @@
  * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
-#include <crypto/internal/blake2s.h>
-
-#include <linux/types.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/sizes.h>
-
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
 #include <asm/processor.h>
 #include <asm/simd.h>
+#include <crypto/internal/blake2s.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
 
 asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state,
 				       const u8 *block, const size_t nblocks,
@@ -41,8 +39,7 @@ void blake2s_compress(struct blake2s_state *state, const u8 *block,
 					    SZ_4K / BLAKE2S_BLOCK_SIZE);
 
 		kernel_fpu_begin();
-		if (IS_ENABLED(CONFIG_AS_AVX512) &&
-		    static_branch_likely(&blake2s_use_avx512))
+		if (static_branch_likely(&blake2s_use_avx512))
 			blake2s_compress_avx512(state, block, blocks, inc);
 		else
 			blake2s_compress_ssse3(state, block, blocks, inc);
@@ -59,8 +56,7 @@ static int __init blake2s_mod_init(void)
 	if (boot_cpu_has(X86_FEATURE_SSSE3))
 		static_branch_enable(&blake2s_use_ssse3);
 
-	if (IS_ENABLED(CONFIG_AS_AVX512) &&
-	    boot_cpu_has(X86_FEATURE_AVX) &&
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
 	    boot_cpu_has(X86_FEATURE_AVX2) &&
 	    boot_cpu_has(X86_FEATURE_AVX512F) &&
 	    boot_cpu_has(X86_FEATURE_AVX512VL) &&
diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/lib/crypto/chacha-avx2-x86_64.S
index f3d8fc018249..f3d8fc018249 100644
--- a/arch/x86/crypto/chacha-avx2-x86_64.S
+++ b/arch/x86/lib/crypto/chacha-avx2-x86_64.S
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/lib/crypto/chacha-avx512vl-x86_64.S
index 259383e1ad44..259383e1ad44 100644
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ b/arch/x86/lib/crypto/chacha-avx512vl-x86_64.S
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/lib/crypto/chacha-ssse3-x86_64.S
index 7111949cd5b9..7111949cd5b9 100644
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ b/arch/x86/lib/crypto/chacha-ssse3-x86_64.S
diff --git a/arch/x86/lib/crypto/chacha_glue.c b/arch/x86/lib/crypto/chacha_glue.c
new file mode 100644
index 000000000000..10b2c945f541
--- /dev/null
+++ b/arch/x86/lib/crypto/chacha_glue.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * ChaCha and HChaCha functions (x86_64 optimized)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <asm/simd.h>
+#include <crypto/chacha.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+
+asmlinkage void chacha_block_xor_ssse3(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_ssse3(const struct chacha_state *state,
+					u8 *dst, const u8 *src,
+					unsigned int len, int nrounds);
+asmlinkage void hchacha_block_ssse3(const struct chacha_state *state,
+				    u32 out[HCHACHA_OUT_WORDS], int nrounds);
+
+asmlinkage void chacha_2block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx2(const struct chacha_state *state,
+				       u8 *dst, const u8 *src,
+				       unsigned int len, int nrounds);
+
+asmlinkage void chacha_2block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_4block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+asmlinkage void chacha_8block_xor_avx512vl(const struct chacha_state *state,
+					   u8 *dst, const u8 *src,
+					   unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
+
+static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
+{
+	len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
+	return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
+}
+
+static void chacha_dosimd(struct chacha_state *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	if (static_branch_likely(&chacha_use_avx512vl)) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state->x[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes) {
+			chacha_2block_xor_avx512vl(state, dst, src, bytes,
+						   nrounds);
+			state->x[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+
+	if (static_branch_likely(&chacha_use_avx2)) {
+		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			bytes -= CHACHA_BLOCK_SIZE * 8;
+			src += CHACHA_BLOCK_SIZE * 8;
+			dst += CHACHA_BLOCK_SIZE * 8;
+			state->x[12] += 8;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 4) {
+			chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 8);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE * 2) {
+			chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 4);
+			return;
+		}
+		if (bytes > CHACHA_BLOCK_SIZE) {
+			chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
+			state->x[12] += chacha_advance(bytes, 2);
+			return;
+		}
+	}
+
+	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		bytes -= CHACHA_BLOCK_SIZE * 4;
+		src += CHACHA_BLOCK_SIZE * 4;
+		dst += CHACHA_BLOCK_SIZE * 4;
+		state->x[12] += 4;
+	}
+	if (bytes > CHACHA_BLOCK_SIZE) {
+		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state->x[12] += chacha_advance(bytes, 4);
+		return;
+	}
+	if (bytes) {
+		chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
+		state->x[12]++;
+	}
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+			u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	if (!static_branch_likely(&chacha_use_simd)) {
+		hchacha_block_generic(state, out, nrounds);
+	} else {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, out, nrounds);
+		kernel_fpu_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+		       unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&chacha_use_simd) ||
+	    bytes <= CHACHA_BLOCK_SIZE)
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_fpu_begin();
+		chacha_dosimd(state, dst, src, todo, nrounds);
+		kernel_fpu_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+	return static_key_enabled(&chacha_use_simd);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_simd_mod_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_SSSE3))
+		return 0;
+
+	static_branch_enable(&chacha_use_simd);
+
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
+		static_branch_enable(&chacha_use_avx2);
+
+		if (boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
+			static_branch_enable(&chacha_use_avx512vl);
+	}
+	return 0;
+}
+subsys_initcall(chacha_simd_mod_init);
+
+static void __exit chacha_simd_mod_exit(void)
+{
+}
+module_exit(chacha_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("ChaCha and HChaCha functions (x86_64 optimized)");
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/lib/crypto/poly1305-x86_64-cryptogams.pl
index b9abcd79c1f4..501827254fed 100644
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ b/arch/x86/lib/crypto/poly1305-x86_64-cryptogams.pl
@@ -118,6 +118,19 @@ sub declare_function() {
 	}
 }
 
+sub declare_typed_function() {
+	my ($name, $align, $nargs) = @_;
+	if($kernel) {
+		$code .= "SYM_TYPED_FUNC_START($name)\n";
+		$code .= ".L$name:\n";
+	} else {
+		$code .= ".globl	$name\n";
+		$code .= ".type	$name,\@function,$nargs\n";
+		$code .= ".align	$align\n";
+		$code .= "$name:\n";
+	}
+}
+
 sub end_function() {
 	my ($name) = @_;
 	if($kernel) {
@@ -128,7 +141,7 @@ sub end_function() {
 }
 
 $code.=<<___ if $kernel;
-#include <linux/linkage.h>
+#include <linux/cfi_types.h>
 ___
 
 if ($avx) {
@@ -236,14 +249,14 @@ ___
 $code.=<<___ if (!$kernel);
 .extern	OPENSSL_ia32cap_P
 
-.globl	poly1305_init_x86_64
-.hidden	poly1305_init_x86_64
+.globl	poly1305_block_init_arch
+.hidden	poly1305_block_init_arch
 .globl	poly1305_blocks_x86_64
 .hidden	poly1305_blocks_x86_64
 .globl	poly1305_emit_x86_64
 .hidden	poly1305_emit_x86_64
 ___
-&declare_function("poly1305_init_x86_64", 32, 3);
+&declare_typed_function("poly1305_block_init_arch", 32, 3);
 $code.=<<___;
 	xor	%eax,%eax
 	mov	%rax,0($ctx)		# initialize hash value
@@ -298,7 +311,7 @@ $code.=<<___;
 .Lno_key:
 	RET
 ___
-&end_function("poly1305_init_x86_64");
+&end_function("poly1305_block_init_arch");
 
 &declare_function("poly1305_blocks_x86_64", 32, 4);
 $code.=<<___;
@@ -2811,18 +2824,10 @@ if ($avx>2) {
 # reason stack layout is kept identical to poly1305_blocks_avx2. If not
 # for this tail, we wouldn't have to even allocate stack frame...
 
-if($kernel) {
-	$code .= "#ifdef CONFIG_AS_AVX512\n";
-}
-
 &declare_function("poly1305_blocks_avx512", 32, 4);
 poly1305_blocks_avxN(1);
 &end_function("poly1305_blocks_avx512");
 
-if ($kernel) {
-	$code .= "#endif\n";
-}
-
 if (!$kernel && $avx>3) {
 ########################################################################
 # VPMADD52 version using 2^44 radix.
@@ -4113,9 +4118,9 @@ avx_handler:
 
 .section	.pdata
 .align	4
-	.rva	.LSEH_begin_poly1305_init_x86_64
-	.rva	.LSEH_end_poly1305_init_x86_64
-	.rva	.LSEH_info_poly1305_init_x86_64
+	.rva	.LSEH_begin_poly1305_block_init_arch
+	.rva	.LSEH_end_poly1305_block_init_arch
+	.rva	.LSEH_info_poly1305_block_init_arch
 
 	.rva	.LSEH_begin_poly1305_blocks_x86_64
 	.rva	.LSEH_end_poly1305_blocks_x86_64
@@ -4163,10 +4168,10 @@ ___
 $code.=<<___;
 .section	.xdata
 .align	8
-.LSEH_info_poly1305_init_x86_64:
+.LSEH_info_poly1305_block_init_arch:
 	.byte	9,0,0,0
 	.rva	se_handler
-	.rva	.LSEH_begin_poly1305_init_x86_64,.LSEH_begin_poly1305_init_x86_64
+	.rva	.LSEH_begin_poly1305_block_init_arch,.LSEH_begin_poly1305_block_init_arch
 
 .LSEH_info_poly1305_blocks_x86_64:
 	.byte	9,0,0,0
diff --git a/arch/x86/lib/crypto/poly1305_glue.c b/arch/x86/lib/crypto/poly1305_glue.c
new file mode 100644
index 000000000000..b7e78a583e07
--- /dev/null
+++ b/arch/x86/lib/crypto/poly1305_glue.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <asm/cpu_device_id.h>
+#include <asm/fpu/api.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <linux/unaligned.h>
+
+struct poly1305_arch_internal {
+	union {
+		struct {
+			u32 h[5];
+			u32 is_base2_26;
+		};
+		u64 hs[3];
+	};
+	u64 r[2];
+	u64 pad;
+	struct { u32 r2, r1, r4, r3; } rn[9];
+};
+
+asmlinkage void poly1305_block_init_arch(
+	struct poly1305_block_state *state,
+	const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks_x86_64(struct poly1305_arch_internal *ctx,
+				       const u8 *inp,
+				       const size_t len, const u32 padbit);
+asmlinkage void poly1305_emit_x86_64(const struct poly1305_state *ctx,
+				     u8 mac[POLY1305_DIGEST_SIZE],
+				     const u32 nonce[4]);
+asmlinkage void poly1305_emit_avx(const struct poly1305_state *ctx,
+				  u8 mac[POLY1305_DIGEST_SIZE],
+				  const u32 nonce[4]);
+asmlinkage void poly1305_blocks_avx(struct poly1305_arch_internal *ctx,
+				    const u8 *inp, const size_t len,
+				    const u32 padbit);
+asmlinkage void poly1305_blocks_avx2(struct poly1305_arch_internal *ctx,
+				     const u8 *inp, const size_t len,
+				     const u32 padbit);
+asmlinkage void poly1305_blocks_avx512(struct poly1305_arch_internal *ctx,
+				       const u8 *inp,
+				       const size_t len, const u32 padbit);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *inp,
+			  unsigned int len, u32 padbit)
+{
+	struct poly1305_arch_internal *ctx =
+		container_of(&state->h.h, struct poly1305_arch_internal, h);
+
+	/* SIMD disables preemption, so relax after processing each page. */
+	BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE ||
+		     SZ_4K % POLY1305_BLOCK_SIZE);
+
+	if (!static_branch_likely(&poly1305_use_avx)) {
+		poly1305_blocks_x86_64(ctx, inp, len, padbit);
+		return;
+	}
+
+	do {
+		const unsigned int bytes = min(len, SZ_4K);
+
+		kernel_fpu_begin();
+		if (static_branch_likely(&poly1305_use_avx512))
+			poly1305_blocks_avx512(ctx, inp, bytes, padbit);
+		else if (static_branch_likely(&poly1305_use_avx2))
+			poly1305_blocks_avx2(ctx, inp, bytes, padbit);
+		else
+			poly1305_blocks_avx(ctx, inp, bytes, padbit);
+		kernel_fpu_end();
+
+		len -= bytes;
+		inp += bytes;
+	} while (len);
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+void poly1305_emit_arch(const struct poly1305_state *ctx,
+			u8 mac[POLY1305_DIGEST_SIZE], const u32 nonce[4])
+{
+	if (!static_branch_likely(&poly1305_use_avx))
+		poly1305_emit_x86_64(ctx, mac, nonce);
+	else
+		poly1305_emit_avx(ctx, mac, nonce);
+}
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+	return static_key_enabled(&poly1305_use_avx);
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init poly1305_simd_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx);
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		static_branch_enable(&poly1305_use_avx2);
+	if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
+	    /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
+	    boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
+		static_branch_enable(&poly1305_use_avx512);
+	return 0;
+}
+subsys_initcall(poly1305_simd_mod_init);
+
+static void __exit poly1305_simd_mod_exit(void)
+{
+}
+module_exit(poly1305_simd_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/lib/crypto/sha256-avx-asm.S
index 53de72bdd851..0d7b2c3e45d9 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/lib/crypto/sha256-avx-asm.S
@@ -48,7 +48,7 @@
 ########################################################################
 
 #include <linux/linkage.h>
-#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 
 ## assume buffers not aligned
 #define    VMOVDQ vmovdqu
@@ -341,13 +341,13 @@ a = TMP_
 .endm
 
 ########################################################################
-## void sha256_transform_avx(state sha256_state *state, const u8 *data, int blocks)
-## arg 1 : pointer to state
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
+## void sha256_transform_avx(u32 state[SHA256_STATE_WORDS],
+##			     const u8 *data, size_t nblocks);
 ########################################################################
 .text
-SYM_TYPED_FUNC_START(sha256_transform_avx)
+SYM_FUNC_START(sha256_transform_avx)
+	ANNOTATE_NOENDBR	# since this is called only via static_call
+
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/lib/crypto/sha256-avx2-asm.S
index 0bbec1c75cd0..25d3380321ec 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/lib/crypto/sha256-avx2-asm.S
@@ -49,7 +49,7 @@
 ########################################################################
 
 #include <linux/linkage.h>
-#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 
 ## assume buffers not aligned
 #define	VMOVDQ vmovdqu
@@ -518,13 +518,13 @@ STACK_SIZE	= _CTX      + _CTX_SIZE
 .endm
 
 ########################################################################
-## void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks)
-## arg 1 : pointer to state
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
+## void sha256_transform_rorx(u32 state[SHA256_STATE_WORDS],
+##			      const u8 *data, size_t nblocks);
 ########################################################################
 .text
-SYM_TYPED_FUNC_START(sha256_transform_rorx)
+SYM_FUNC_START(sha256_transform_rorx)
+	ANNOTATE_NOENDBR	# since this is called only via static_call
+
 	pushq	%rbx
 	pushq	%r12
 	pushq	%r13
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/lib/crypto/sha256-ni-asm.S
index d515a55a3bc1..d3548206cf3d 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/arch/x86/lib/crypto/sha256-ni-asm.S
@@ -54,9 +54,9 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 
-#define DIGEST_PTR	%rdi	/* 1st arg */
+#define STATE_PTR	%rdi	/* 1st arg */
 #define DATA_PTR	%rsi	/* 2nd arg */
 #define NUM_BLKS	%rdx	/* 3rd arg */
 
@@ -98,24 +98,20 @@
 .endm
 
 /*
- * Intel SHA Extensions optimized implementation of a SHA-256 update function
+ * Intel SHA Extensions optimized implementation of a SHA-256 block function
  *
- * The function takes a pointer to the current hash values, a pointer to the
- * input data, and a number of 64 byte blocks to process.  Once all blocks have
- * been processed, the digest pointer is  updated with the resulting hash value.
- * The function only processes complete blocks, there is no functionality to
- * store partial blocks.  All message padding and hash value initialization must
- * be done outside the update function.
+ * This function takes a pointer to the current SHA-256 state, a pointer to the
+ * input data, and the number of 64-byte blocks to process.  Once all blocks
+ * have been processed, the state is updated with the new state.  This function
+ * only processes complete blocks.  State initialization, buffering of partial
+ * blocks, and digest finalization is expected to be handled elsewhere.
  *
- * void sha256_ni_transform(uint32_t *digest, const void *data,
-		uint32_t numBlocks);
- * digest : pointer to digest
- * data: pointer to input data
- * numBlocks: Number of blocks to process
+ * void sha256_ni_transform(u32 state[SHA256_STATE_WORDS],
+ *			    const u8 *data, size_t nblocks);
  */
-
 .text
-SYM_TYPED_FUNC_START(sha256_ni_transform)
+SYM_FUNC_START(sha256_ni_transform)
+	ANNOTATE_NOENDBR	# since this is called only via static_call
 
 	shl		$6, NUM_BLKS		/*  convert to bytes */
 	jz		.Ldone_hash
@@ -126,8 +122,8 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
 	 * Need to reorder these appropriately
 	 * DCBA, HGFE -> ABEF, CDGH
 	 */
-	movdqu		0*16(DIGEST_PTR), STATE0	/* DCBA */
-	movdqu		1*16(DIGEST_PTR), STATE1	/* HGFE */
+	movdqu		0*16(STATE_PTR), STATE0		/* DCBA */
+	movdqu		1*16(STATE_PTR), STATE1		/* HGFE */
 
 	movdqa		STATE0, TMP
 	punpcklqdq	STATE1, STATE0			/* FEBA */
@@ -166,8 +162,8 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
 	pshufd		$0xB1, STATE0, STATE0		/* HGFE */
 	pshufd		$0x1B, STATE1, STATE1		/* DCBA */
 
-	movdqu		STATE1, 0*16(DIGEST_PTR)
-	movdqu		STATE0, 1*16(DIGEST_PTR)
+	movdqu		STATE1, 0*16(STATE_PTR)
+	movdqu		STATE0, 1*16(STATE_PTR)
 
 .Ldone_hash:
 
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/lib/crypto/sha256-ssse3-asm.S
index 93264ee44543..7f24a4cdcb25 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/lib/crypto/sha256-ssse3-asm.S
@@ -47,7 +47,7 @@
 ########################################################################
 
 #include <linux/linkage.h>
-#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 
 ## assume buffers not aligned
 #define    MOVDQ movdqu
@@ -348,15 +348,13 @@ a = TMP_
 .endm
 
 ########################################################################
-## void sha256_transform_ssse3(struct sha256_state *state, const u8 *data,
-##			       int blocks);
-## arg 1 : pointer to state
-##	   (struct sha256_state is assumed to begin with u32 state[8])
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
+## void sha256_transform_ssse3(u32 state[SHA256_STATE_WORDS],
+##			       const u8 *data, size_t nblocks);
 ########################################################################
 .text
-SYM_TYPED_FUNC_START(sha256_transform_ssse3)
+SYM_FUNC_START(sha256_transform_ssse3)
+	ANNOTATE_NOENDBR	# since this is called only via static_call
+
 	pushq   %rbx
 	pushq   %r12
 	pushq   %r13
diff --git a/arch/x86/lib/crypto/sha256.c b/arch/x86/lib/crypto/sha256.c
new file mode 100644
index 000000000000..80380f8fdcee
--- /dev/null
+++ b/arch/x86/lib/crypto/sha256.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized for x86_64
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/fpu/api.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/static_call.h>
+
+asmlinkage void sha256_transform_ssse3(u32 state[SHA256_STATE_WORDS],
+				       const u8 *data, size_t nblocks);
+asmlinkage void sha256_transform_avx(u32 state[SHA256_STATE_WORDS],
+				     const u8 *data, size_t nblocks);
+asmlinkage void sha256_transform_rorx(u32 state[SHA256_STATE_WORDS],
+				      const u8 *data, size_t nblocks);
+asmlinkage void sha256_ni_transform(u32 state[SHA256_STATE_WORDS],
+				    const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha256_x86);
+
+DEFINE_STATIC_CALL(sha256_blocks_x86, sha256_transform_ssse3);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_sha256_x86)) {
+		kernel_fpu_begin();
+		static_call(sha256_blocks_x86)(state, data, nblocks);
+		kernel_fpu_end();
+	} else {
+		sha256_blocks_generic(state, data, nblocks);
+	}
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_sha256_x86);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_x86_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SHA_NI)) {
+		static_call_update(sha256_blocks_x86, sha256_ni_transform);
+	} else if (cpu_has_xfeatures(XFEATURE_MASK_SSE |
+				     XFEATURE_MASK_YMM, NULL) &&
+		   boot_cpu_has(X86_FEATURE_AVX)) {
+		if (boot_cpu_has(X86_FEATURE_AVX2) &&
+		    boot_cpu_has(X86_FEATURE_BMI2))
+			static_call_update(sha256_blocks_x86,
+					   sha256_transform_rorx);
+		else
+			static_call_update(sha256_blocks_x86,
+					   sha256_transform_avx);
+	} else if (!boot_cpu_has(X86_FEATURE_SSSE3)) {
+		return 0;
+	}
+	static_branch_enable(&have_sha256_x86);
+	return 0;
+}
+subsys_initcall(sha256_x86_mod_init);
+
+static void __exit sha256_x86_mod_exit(void)
+{
+}
+module_exit(sha256_x86_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 optimized for x86_64");
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 23f81ca3f06b..eb2d2e1cbddd 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -75,7 +75,7 @@ static void delay_tsc(u64 cycles)
 
 		/* Allow RT tasks to run */
 		preempt_enable();
-		rep_nop();
+		native_pause();
 		preempt_disable();
 
 		/*
@@ -131,7 +131,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles)
 	 * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu
 	 * variable as the monitor target.
 	 */
-	 __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
+	__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 	/*
 	 * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 89ecd57c9d42..9d5654b8a72a 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,22 +28,20 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/runtime-const.h>
 
 #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
 
 .macro check_range size:req
 .if IS_ENABLED(CONFIG_X86_64)
-	movq $0x0123456789abcdef,%rdx
-  1:
-  .pushsection runtime_ptr_USER_PTR_MAX,"a"
-	.long 1b - 8 - .
-  .popsection
+	RUNTIME_CONST_PTR USER_PTR_MAX, rdx
 	cmp %rdx, %rax
 	cmova %rdx, %rax
 .else
@@ -62,6 +60,7 @@
 
 	.text
 SYM_FUNC_START(__get_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -72,6 +71,7 @@ SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
 SYM_FUNC_START(__get_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -82,6 +82,7 @@ SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
 SYM_FUNC_START(__get_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 	UACCESS movl (%_ASM_AX),%edx
@@ -92,6 +93,7 @@ SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
 SYM_FUNC_START(__get_user_8)
+	ANNOTATE_NOENDBR
 #ifndef CONFIG_X86_64
 	xor %ecx,%ecx
 #endif
@@ -111,6 +113,7 @@ EXPORT_SYMBOL(__get_user_8)
 
 /* .. and the same for __get_user, just without the range checks */
 SYM_FUNC_START(__get_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -121,6 +124,7 @@ SYM_FUNC_END(__get_user_nocheck_1)
 EXPORT_SYMBOL(__get_user_nocheck_1)
 
 SYM_FUNC_START(__get_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -131,6 +135,7 @@ SYM_FUNC_END(__get_user_nocheck_2)
 EXPORT_SYMBOL(__get_user_nocheck_2)
 
 SYM_FUNC_START(__get_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movl (%_ASM_AX),%edx
@@ -141,6 +146,7 @@ SYM_FUNC_END(__get_user_nocheck_4)
 EXPORT_SYMBOL(__get_user_nocheck_4)
 
 SYM_FUNC_START(__get_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 774bdf3e6f0a..edbeb3ecad38 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 
 #include <asm/asm.h>
 
@@ -9,6 +10,7 @@
  * %rdi: w
  */
 SYM_FUNC_START(__sw_hweight32)
+	ANNOTATE_NOENDBR
 
 #ifdef CONFIG_X86_64
 	movl %edi, %eax				# w
@@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32)
  */
 #ifdef CONFIG_X86_64
 SYM_FUNC_START(__sw_hweight64)
+	ANNOTATE_NOENDBR
 	pushq   %rdi
 	pushq   %rdx
 
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 98631c0e7a11..4e385cbfd444 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -13,6 +13,7 @@
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/ldt.h>
+#include <asm/msr.h>
 #include <asm/vm86.h>
 
 #undef pr_fmt
@@ -631,14 +632,21 @@ static bool get_desc(struct desc_struct *out, unsigned short sel)
 		/* Bits [15:3] contain the index of the desired entry. */
 		sel >>= 3;
 
-		mutex_lock(&current->active_mm->context.lock);
-		ldt = current->active_mm->context.ldt;
+		/*
+		 * If we're not in a valid context with a real (not just lazy)
+		 * user mm, then don't even try.
+		 */
+		if (!nmi_uaccess_okay())
+			return false;
+
+		mutex_lock(&current->mm->context.lock);
+		ldt = current->mm->context.ldt;
 		if (ldt && sel < ldt->nr_entries) {
 			*out = ldt->entries[sel];
 			success = true;
 		}
 
-		mutex_unlock(&current->active_mm->context.lock);
+		mutex_unlock(&current->mm->context.lock);
 
 		return success;
 	}
@@ -702,16 +710,16 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
 		unsigned long base;
 
 		if (seg_reg_idx == INAT_SEG_REG_FS) {
-			rdmsrl(MSR_FS_BASE, base);
+			rdmsrq(MSR_FS_BASE, base);
 		} else if (seg_reg_idx == INAT_SEG_REG_GS) {
 			/*
 			 * swapgs was called at the kernel entry point. Thus,
 			 * MSR_KERNEL_GS_BASE will have the user-space GS base.
 			 */
 			if (user_mode(regs))
-				rdmsrl(MSR_KERNEL_GS_BASE, base);
+				rdmsrq(MSR_KERNEL_GS_BASE, base);
 			else
-				rdmsrl(MSR_GS_BASE, base);
+				rdmsrq(MSR_GS_BASE, base);
 		} else {
 			base = 0;
 		}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 6ffb931b9fb1..149a57e334ab 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -324,6 +324,11 @@ int insn_get_opcode(struct insn *insn)
 	}
 
 	insn->attr = inat_get_opcode_attribute(op);
+	if (insn->x86_64 && inat_is_invalid64(insn->attr)) {
+		/* This instruction is invalid, like UD2. Stop decoding. */
+		insn->attr &= INAT_INV64;
+	}
+
 	while (inat_is_escape(insn->attr)) {
 		/* Get escaped opcode */
 		op = get_next(insn_byte_t, insn);
@@ -337,6 +342,7 @@ int insn_get_opcode(struct insn *insn)
 		insn->attr = 0;
 		return -EINVAL;
 	}
+
 end:
 	opcode->got = 1;
 	return 0;
@@ -658,7 +664,6 @@ int insn_get_immediate(struct insn *insn)
 	}
 
 	if (!inat_has_immediate(insn->attr))
-		/* no immediates */
 		goto done;
 
 	switch (inat_immediate_size(insn->attr)) {
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 5eecb45d05d5..c20e04764edc 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -10,7 +10,7 @@
 static __always_inline void rep_movs(void *to, const void *from, size_t n)
 {
 	unsigned long d0, d1, d2;
-	asm volatile("rep ; movsl\n\t"
+	asm volatile("rep movsl\n\t"
 		     "testb $2,%b4\n\t"
 		     "je 1f\n\t"
 		     "movsw\n"
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index a58f451a7dd3..b5893928d55c 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -8,7 +8,7 @@
  */
 #include <asm/asm.h>
 #include <asm/kaslr.h>
-#include <asm/msr.h>
+#include <asm/tsc.h>
 #include <asm/archrandom.h>
 #include <asm/e820/api.h>
 #include <asm/shared/io.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 0ae2e1712e2e..12a23fa7c44c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -41,6 +41,7 @@ SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
 SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 1b60ae81ecd8..aa1f92ee6b2e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -26,7 +27,7 @@
  * Output:
  * rax: dest
  */
-SYM_FUNC_START(__memmove)
+SYM_TYPED_FUNC_START(__memmove)
 
 	mov %rdi, %rax
 
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0199d56cb479..fb5a03cf5ab7 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -28,7 +29,7 @@
  * only for the return value that is the same as the source input,
  * which the compiler could/should do much better anyway.
  */
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
 	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
@@ -41,6 +42,7 @@ SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
 SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ebd259f31496..5ef8494896e8 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 #include <linux/errno.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -12,7 +13,7 @@
  *
  */
 .macro op_safe_regs op
-SYM_FUNC_START(\op\()_safe_regs)
+SYM_TYPED_FUNC_START(\op\()_safe_regs)
 	pushq %rbx
 	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index acd463d887e1..b8f63419e6ae 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -47,7 +47,7 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 }
 EXPORT_SYMBOL(rdmsr_on_cpu);
 
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
 	int err;
 	struct msr_info rv;
@@ -60,7 +60,7 @@ int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 
 	return err;
 }
-EXPORT_SYMBOL(rdmsrl_on_cpu);
+EXPORT_SYMBOL(rdmsrq_on_cpu);
 
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
@@ -78,7 +78,7 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 }
 EXPORT_SYMBOL(wrmsr_on_cpu);
 
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
 	int err;
 	struct msr_info rv;
@@ -92,7 +92,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 
 	return err;
 }
-EXPORT_SYMBOL(wrmsrl_on_cpu);
+EXPORT_SYMBOL(wrmsrq_on_cpu);
 
 static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
 			    struct msr __percpu *msrs,
@@ -204,7 +204,7 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 }
 EXPORT_SYMBOL(wrmsr_safe_on_cpu);
 
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 {
 	int err;
 	struct msr_info rv;
@@ -218,9 +218,9 @@ int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 
 	return err ? err : rv.err;
 }
-EXPORT_SYMBOL(wrmsrl_safe_on_cpu);
+EXPORT_SYMBOL(wrmsrq_safe_on_cpu);
 
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 {
 	u32 low, high;
 	int err;
@@ -230,7 +230,7 @@ int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
 
 	return err;
 }
-EXPORT_SYMBOL(rdmsrl_safe_on_cpu);
+EXPORT_SYMBOL(rdmsrq_safe_on_cpu);
 
 /*
  * These variants are significantly slower, but allows control over
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4bf4fad5b148..4ef7c6dcbea6 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -41,7 +41,7 @@ static int msr_read(u32 msr, struct msr *m)
 	int err;
 	u64 val;
 
-	err = rdmsrl_safe(msr, &val);
+	err = rdmsrq_safe(msr, &val);
 	if (!err)
 		m->q = val;
 
@@ -58,7 +58,7 @@ static int msr_read(u32 msr, struct msr *m)
  */
 static int msr_write(u32 msr, struct msr *m)
 {
-	return wrmsrl_safe(msr, m->q);
+	return wrmsrq_safe(msr, m->q);
 }
 
 static inline int __flip_bit(u32 msr, u8 bit, bool set)
@@ -103,6 +103,7 @@ int msr_set_bit(u32 msr, u8 bit)
 {
 	return __flip_bit(msr, bit, true);
 }
+EXPORT_SYMBOL_GPL(msr_set_bit);
 
 /**
  * msr_clear_bit - Clear @bit in a MSR @msr.
@@ -118,25 +119,26 @@ int msr_clear_bit(u32 msr, u8 bit)
 {
 	return __flip_bit(msr, bit, false);
 }
+EXPORT_SYMBOL_GPL(msr_clear_bit);
 
 #ifdef CONFIG_TRACEPOINTS
-void do_trace_write_msr(unsigned int msr, u64 val, int failed)
+void do_trace_write_msr(u32 msr, u64 val, int failed)
 {
 	trace_write_msr(msr, val, failed);
 }
 EXPORT_SYMBOL(do_trace_write_msr);
 EXPORT_TRACEPOINT_SYMBOL(write_msr);
 
-void do_trace_read_msr(unsigned int msr, u64 val, int failed)
+void do_trace_read_msr(u32 msr, u64 val, int failed)
 {
 	trace_read_msr(msr, val, failed);
 }
 EXPORT_SYMBOL(do_trace_read_msr);
 EXPORT_TRACEPOINT_SYMBOL(read_msr);
 
-void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+void do_trace_rdpmc(u32 msr, u64 val, int failed)
 {
-	trace_rdpmc(counter, val, failed);
+	trace_rdpmc(msr, val, failed);
 }
 EXPORT_SYMBOL(do_trace_rdpmc);
 EXPORT_TRACEPOINT_SYMBOL(rdpmc);
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 975c9c18263d..46d9e9b98a61 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -13,6 +13,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -45,6 +46,7 @@
 
 .text
 SYM_FUNC_START(__put_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
@@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
 
 SYM_FUNC_START(__put_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 3:	movw %ax,(%_ASM_CX)
@@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
 
 SYM_FUNC_START(__put_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 5:	movl %eax,(%_ASM_CX)
@@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
 
 SYM_FUNC_START(__put_user_8)
+	ANNOTATE_NOENDBR
 	check_range size=8
 	ASM_STAC
 7:	mov %_ASM_AX,(%_ASM_CX)
@@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fb..d78d769a02bd 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -40,6 +40,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 	ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
 		      __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
+SYM_PIC_ALIAS(__x86_indirect_thunk_\reg)
 
 .endm
 
@@ -326,6 +327,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
 #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
+	ANNOTATE_NOENDBR
 	ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
@@ -342,7 +344,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	 * case.
 	 */
 	CALL_THUNKS_DEBUG_INC_RETS
-	shlq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+	shlq	$5, PER_CPU_VAR(__x86_call_depth)
 	jz	1f
 	ANNOTATE_UNRET_SAFE
 	ret
@@ -366,6 +368,54 @@ SYM_FUNC_END(call_depth_return_thunk)
 
 #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+/*
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * that complete the fineibt_paranoid caller sequence.
+ */
+1:	.byte 0xea
+SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	jne 1b
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	ANNOTATE_RETPOLINE_SAFE
+	jmp *%\reg
+	int3
+	.align 32, 0xcc		/* fill to the end of the line */
+	.skip  32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 29, 0xcc
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+	.align 64, 0xcc
+SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax)
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
  * for the compiler to generate JMPs to it.
@@ -393,6 +443,7 @@ SYM_CODE_START(__x86_return_thunk)
 #endif
 	int3
 SYM_CODE_END(__x86_return_thunk)
+SYM_PIC_ALIAS(__x86_return_thunk)
 EXPORT_SYMBOL(__x86_return_thunk)
 
 #endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 53b3f202267c..f87ec24fa579 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -40,8 +40,7 @@ char *strncpy(char *dest, const char *src, size_t count)
 		"stosb\n\t"
 		"testb %%al,%%al\n\t"
 		"jne 1b\n\t"
-		"rep\n\t"
-		"stosb\n"
+		"rep stosb\n"
 		"2:"
 		: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
 		: "0" (src), "1" (dest), "2" (count) : "memory");
@@ -54,8 +53,7 @@ EXPORT_SYMBOL(strncpy);
 char *strcat(char *dest, const char *src)
 {
 	int d0, d1, d2, d3;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"decl %1\n"
 		"1:\tlodsb\n\t"
 		"stosb\n\t"
@@ -72,8 +70,7 @@ EXPORT_SYMBOL(strcat);
 char *strncat(char *dest, const char *src, size_t count)
 {
 	int d0, d1, d2, d3;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"decl %1\n\t"
 		"movl %8,%3\n"
 		"1:\tdecl %3\n\t"
@@ -167,8 +164,7 @@ size_t strlen(const char *s)
 {
 	int d0;
 	size_t res;
-	asm volatile("repne\n\t"
-		"scasb"
+	asm volatile("repne scasb"
 		: "=c" (res), "=&D" (d0)
 		: "1" (s), "a" (0), "0" (0xffffffffu)
 		: "memory");
@@ -184,8 +180,7 @@ void *memchr(const void *cs, int c, size_t count)
 	void *res;
 	if (!count)
 		return NULL;
-	asm volatile("repne\n\t"
-		"scasb\n\t"
+	asm volatile("repne scasb\n\t"
 		"je 1f\n\t"
 		"movl $1,%0\n"
 		"1:\tdecl %0"
@@ -202,7 +197,7 @@ void *memscan(void *addr, int c, size_t size)
 {
 	if (!size)
 		return addr;
-	asm volatile("repnz; scasb\n\t"
+	asm volatile("repnz scasb\n\t"
 	    "jnz 1f\n\t"
 	    "dec %%edi\n"
 	    "1:"
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 38f37df056f7..28267985e85f 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -8,16 +8,14 @@ int	d0, d1;
 register char *__res;
 __asm__ __volatile__(
 	"movl %6,%%edi\n\t"
-	"repne\n\t"
-	"scasb\n\t"
+	"repne scasb\n\t"
 	"notl %%ecx\n\t"
 	"decl %%ecx\n\t"	/* NOTE! This also sets Z if searchstring='' */
 	"movl %%ecx,%%edx\n"
 	"1:\tmovl %6,%%edi\n\t"
 	"movl %%esi,%%eax\n\t"
 	"movl %%edx,%%ecx\n\t"
-	"repe\n\t"
-	"cmpsb\n\t"
+	"repe cmpsb\n\t"
 	"je 2f\n\t"		/* also works for empty string, see above */
 	"xchgl %%eax,%%esi\n\t"
 	"incl %%esi\n\t"
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 422257c350c6..f6f436f1d573 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -38,9 +38,9 @@ do {									\
 	might_fault();							\
 	__asm__ __volatile__(						\
 		ASM_STAC "\n"						\
-		"0:	rep; stosl\n"					\
+		"0:	rep stosl\n"					\
 		"	movl %2,%0\n"					\
-		"1:	rep; stosb\n"					\
+		"1:	rep stosb\n"					\
 		"2: " ASM_CLAC "\n"					\
 		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %2)	\
 		_ASM_EXTABLE_UA(1b, 2b)					\
@@ -140,9 +140,9 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
 		       "       shrl  $2, %0\n"
 		       "       andl  $3, %%eax\n"
 		       "       cld\n"
-		       "99:    rep; movsl\n"
+		       "99:    rep movsl\n"
 		       "36:    movl %%eax, %0\n"
-		       "37:    rep; movsb\n"
+		       "37:    rep movsb\n"
 		       "100:\n"
 		       _ASM_EXTABLE_UA(1b, 100b)
 		       _ASM_EXTABLE_UA(2b, 100b)
@@ -242,9 +242,9 @@ static unsigned long __copy_user_intel_nocache(void *to,
 	       "        shrl  $2, %0\n"
 	       "        andl $3, %%eax\n"
 	       "        cld\n"
-	       "6:      rep; movsl\n"
+	       "6:      rep movsl\n"
 	       "        movl %%eax,%0\n"
-	       "7:      rep; movsb\n"
+	       "7:      rep movsb\n"
 	       "8:\n"
 	       _ASM_EXTABLE_UA(0b, 8b)
 	       _ASM_EXTABLE_UA(1b, 8b)
@@ -293,14 +293,14 @@ do {									\
 		"	negl %0\n"					\
 		"	andl $7,%0\n"					\
 		"	subl %0,%3\n"					\
-		"4:	rep; movsb\n"					\
+		"4:	rep movsb\n"					\
 		"	movl %3,%0\n"					\
 		"	shrl $2,%0\n"					\
 		"	andl $3,%3\n"					\
 		"	.align 2,0x90\n"				\
-		"0:	rep; movsl\n"					\
+		"0:	rep movsl\n"					\
 		"	movl %3,%0\n"					\
-		"1:	rep; movsb\n"					\
+		"1:	rep movsb\n"					\
 		"2:\n"							\
 		_ASM_EXTABLE_TYPE_REG(4b, 2b, EX_TYPE_UCOPY_LEN1, %3)	\
 		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %3)	\
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e9251b89a9e9..654280aaa3e9 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -18,7 +18,7 @@
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
- * @vaddr:	virtual start address
+ * @addr:	virtual start address
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..262f7ca1fb95 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -35,7 +35,7 @@
 #  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 #  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
 #
-# REX2 Prefix
+# REX2 Prefix Superscripts
 #  - (!REX2): REX2 is not allowed
 #  - (REX2): REX2 variant e.g. JMPABS
 
@@ -147,7 +147,7 @@ AVXcode:
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix),(o64)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -253,8 +253,8 @@ c0: Grp2 Eb,Ib (1A)
 c1: Grp2 Ev,Ib (1A)
 c2: RETN Iw (f64)
 c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix),(o64)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix),(o64)
 c6: Grp11A Eb,Ib (1A)
 c7: Grp11B Ev,Iz (1A)
 c8: ENTER Iw,Ib
@@ -286,10 +286,10 @@ df: ESC
 # Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
 # in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
 # to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
-e1: LOOPE/LOOPZ Jb (f64) (!REX2)
-e2: LOOP Jb (f64) (!REX2)
-e3: JrCXZ Jb (f64) (!REX2)
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
 e4: IN AL,Ib (!REX2)
 e5: IN eAX,Ib (!REX2)
 e6: OUT Ib,AL (!REX2)
@@ -298,10 +298,10 @@ e7: OUT Ib,eAX (!REX2)
 # in "near" jumps and calls is 16-bit. For CALL,
 # push of return address is 16-bit wide, RSP is decremented by 2
 # but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64) (!REX2)
-e9: JMP-near Jz (f64) (!REX2)
-ea: JMP-far Ap (i64) (!REX2)
-eb: JMP-short Jb (f64) (!REX2)
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
 ec: IN AL,DX (!REX2)
 ed: IN eAX,DX (!REX2)
 ee: OUT DX,AL (!REX2)
@@ -478,22 +478,22 @@ AVXcode: 1
 7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64) (!REX2)
-81: JNO Jz (f64) (!REX2)
-82: JB/JC/JNAE Jz (f64) (!REX2)
-83: JAE/JNB/JNC Jz (f64) (!REX2)
-84: JE/JZ Jz (f64) (!REX2)
-85: JNE/JNZ Jz (f64) (!REX2)
-86: JBE/JNA Jz (f64) (!REX2)
-87: JA/JNBE Jz (f64) (!REX2)
-88: JS Jz (f64) (!REX2)
-89: JNS Jz (f64) (!REX2)
-8a: JP/JPE Jz (f64) (!REX2)
-8b: JNP/JPO Jz (f64) (!REX2)
-8c: JL/JNGE Jz (f64) (!REX2)
-8d: JNL/JGE Jz (f64) (!REX2)
-8e: JLE/JNG Jz (f64) (!REX2)
-8f: JNLE/JG Jz (f64) (!REX2)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
 # 0x0f 0x90-0x9f
 90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
 91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -996,8 +996,8 @@ AVXcode: 4
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/math-emu/control_w.h b/arch/x86/math-emu/control_w.h
index 60f4dcc5edc3..93cbc89b34e2 100644
--- a/arch/x86/math-emu/control_w.h
+++ b/arch/x86/math-emu/control_w.h
@@ -11,7 +11,7 @@
 #ifndef _CONTROLW_H_
 #define _CONTROLW_H_
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	_Const_(x)	$##x
 #else
 #define	_Const_(x)	x
diff --git a/arch/x86/math-emu/exception.h b/arch/x86/math-emu/exception.h
index 75230b977577..59961d350bc4 100644
--- a/arch/x86/math-emu/exception.h
+++ b/arch/x86/math-emu/exception.h
@@ -10,7 +10,7 @@
 #ifndef _EXCEPTION_H_
 #define _EXCEPTION_H_
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	Const_(x)	$##x
 #else
 #define	Const_(x)	x
@@ -37,7 +37,7 @@
 #define PRECISION_LOST_UP    Const_((EX_Precision | SW_C1))
 #define PRECISION_LOST_DOWN  Const_(EX_Precision)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef DEBUG
 #define	EXCEPTION(x)	{ printk("exception in %s at line %d\n", \
@@ -46,6 +46,6 @@
 #define	EXCEPTION(x)	FPU_exception(x)
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _EXCEPTION_H_ */
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index d62662bdd460..5f253ae406b6 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft)
 
 void finit(void)
 {
-	fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+	fpstate_init_soft(&x86_task_fpu(current)->fpstate->regs.soft);
 }
 
 /*
diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h
index 0c122226ca56..def569c50b76 100644
--- a/arch/x86/math-emu/fpu_emu.h
+++ b/arch/x86/math-emu/fpu_emu.h
@@ -20,7 +20,7 @@
  */
 #define PECULIAR_486
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #include "fpu_asm.h"
 #define	Const(x)	$##x
 #else
@@ -68,7 +68,7 @@
 
 #define FPU_Exception   Const(0x80000000)	/* Added to tag returns. */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include "fpu_system.h"
 
@@ -213,6 +213,6 @@ asmlinkage int FPU_round(FPU_REG *arg, unsigned int extent, int dummy,
 #include "fpu_proto.h"
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _FPU_EMU_H_ */
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 91c52ead1226..5034df617740 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -641,7 +641,7 @@ int fpregs_soft_set(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
@@ -692,7 +692,7 @@ int fpregs_soft_get(struct task_struct *target,
 		    const struct user_regset *regset,
 		    struct membuf to)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	const void *space = s387->st_space;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;
 
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index eec3e4805c75..5e238e930fe3 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d)
 	return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
 }
 
-#define I387			(&current->thread.fpu.fpstate->regs)
+#define I387			(&x86_task_fpu(current)->fpstate->regs)
 #define FPU_info		(I387->soft.info)
 
 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/math-emu/status_w.h b/arch/x86/math-emu/status_w.h
index b77bafec9526..f642957330ef 100644
--- a/arch/x86/math-emu/status_w.h
+++ b/arch/x86/math-emu/status_w.h
@@ -13,7 +13,7 @@
 
 #include "fpu_emu.h"		/* for definition of PECULIAR_486 */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	Const__(x)	$##x
 #else
 #define	Const__(x)	x
@@ -37,7 +37,7 @@
 
 #define SW_Exc_Mask     Const__(0x27f)	/* Status word exception bit mask */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define COMP_A_gt_B	1
 #define COMP_A_eq_B	2
@@ -63,6 +63,6 @@ static inline void setcc(int cc)
 #  define clear_C1()
 #endif /* PECULIAR_486 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _STATUS_H_ */
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 690fbf48e853..5b9908f13dcf 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -3,12 +3,10 @@
 KCOV_INSTRUMENT_tlb.o			:= n
 KCOV_INSTRUMENT_mem_encrypt.o		:= n
 KCOV_INSTRUMENT_mem_encrypt_amd.o	:= n
-KCOV_INSTRUMENT_mem_encrypt_identity.o	:= n
 KCOV_INSTRUMENT_pgprot.o		:= n
 
 KASAN_SANITIZE_mem_encrypt.o		:= n
 KASAN_SANITIZE_mem_encrypt_amd.o	:= n
-KASAN_SANITIZE_mem_encrypt_identity.o	:= n
 KASAN_SANITIZE_pgprot.o		:= n
 
 # Disable KCSAN entirely, because otherwise we get warnings that some functions
@@ -16,12 +14,10 @@ KASAN_SANITIZE_pgprot.o		:= n
 KCSAN_SANITIZE := n
 # Avoid recursion by not calling KMSAN hooks for CEA code.
 KMSAN_SANITIZE_cpu_entry_area.o := n
-KMSAN_SANITIZE_mem_encrypt_identity.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
 CFLAGS_REMOVE_mem_encrypt_amd.o		= -pg
-CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 CFLAGS_REMOVE_pgprot.o			= -pg
 endif
 
@@ -32,18 +28,13 @@ obj-y				+= pat/
 
 # Make sure __phys_addr has no stackprotector
 CFLAGS_physaddr.o		:= -fno-stack-protector
-CFLAGS_mem_encrypt_identity.o	:= -fno-stack-protector
-
-CFLAGS_fault.o := -I $(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_PTDUMP_CORE)	+= dump_pagetables.o
+obj-$(CONFIG_PTDUMP)		+= dump_pagetables.o
 obj-$(CONFIG_PTDUMP_DEBUGFS)	+= debug_pagetables.o
 
-obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
-
 KASAN_SANITIZE_kasan_init_$(BITS).o := n
 obj-$(CONFIG_KASAN)		+= kasan_init_$(BITS).o
 
@@ -54,7 +45,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 
@@ -65,5 +56,4 @@ obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)	+= pti.o
 obj-$(CONFIG_X86_MEM_ENCRYPT)	+= mem_encrypt.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_amd.o
 
-obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_identity.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_boot.o
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index 628833afee37..f980b0eb0105 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -25,7 +25,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 
 static unsigned char __initdata nodeids[8];
 
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 51986e8a9d35..bf8dab18be97 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -111,7 +111,7 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup,
 
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
- * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * here because the FPU state of a task using the FPU (struct fpu::fpstate)
  * should always be valid.  However, past bugs have allowed userspace to set
  * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
  * These caused XRSTOR to fail when switching to the task, leaking the FPU
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 296d294142c8..998bd807fc7b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,7 +13,6 @@
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
-#include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
@@ -38,7 +37,7 @@
 #include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
 
 #define CREATE_TRACE_POINTS
-#include <asm/trace/exceptions.h>
+#include <trace/events/exceptions.h>
 
 /*
  * Returns 0 if mmiotrace is disabled, or if the fault is not
@@ -1455,9 +1454,6 @@ static __always_inline void
 trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
 			 unsigned long address)
 {
-	if (!trace_pagefault_enabled())
-		return;
-
 	if (user_mode(regs))
 		trace_page_fault_user(address, regs, error_code);
 	else
@@ -1496,8 +1492,6 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 
 	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
-	prefetchw(&current->mm->mmap_lock);
-
 	/*
 	 * KVM uses #PF vector to deliver 'page not present' events to guests
 	 * (asynchronous page fault mechanism). The event happens when a
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
deleted file mode 100644
index d9efa35711ee..000000000000
--- a/arch/x86/mm/highmem_32.c
+++ /dev/null
@@ -1,34 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/highmem.h>
-#include <linux/export.h>
-#include <linux/swap.h> /* for totalram_pages */
-#include <linux/memblock.h>
-#include <asm/numa.h>
-
-void __init set_highmem_pages_init(void)
-{
-	struct zone *zone;
-	int nid;
-
-	/*
-	 * Explicitly reset zone->managed_pages because set_highmem_pages_init()
-	 * is invoked before memblock_free_all()
-	 */
-	reset_all_zones_managed_pages();
-	for_each_zone(zone) {
-		unsigned long zone_start_pfn, zone_end_pfn;
-
-		if (!is_highmem(zone))
-			continue;
-
-		zone_start_pfn = zone->zone_start_pfn;
-		zone_end_pfn = zone_start_pfn + zone->spanned_pages;
-
-		nid = zone_to_nid(zone);
-		printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n",
-				zone->name, nid, zone_start_pfn, zone_end_pfn);
-
-		add_highpages_with_active_regions(nid, zone_start_pfn,
-				 zone_end_pfn);
-	}
-}
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 5ab7bd2f1983..bd5d101c5c37 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -101,9 +101,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		pmd_t *pmd;
 		bool use_gbpage;
 
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (next > end)
-			next = end;
+		next = pud_addr_end(addr, end);
 
 		/* if this is already a gbpage, this portion is already mapped */
 		if (pud_leaf(*pud))
@@ -154,10 +152,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		p4d_t *p4d = p4d_page + p4d_index(addr);
 		pud_t *pud;
 
-		next = (addr & P4D_MASK) + P4D_SIZE;
-		if (next > end)
-			next = end;
-
+		next = p4d_addr_end(addr, end);
 		if (p4d_present(*p4d)) {
 			pud = pud_offset(p4d, 0);
 			result = ident_pud_init(info, pud, addr, next);
@@ -199,10 +194,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		pgd_t *pgd = pgd_page + pgd_index(addr);
 		p4d_t *p4d;
 
-		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-
+		next = pgd_addr_end(addr, end);
 		if (pgd_present(*pgd)) {
 			p4d = p4d_offset(pgd, 0);
 			result = ident_p4d_init(info, p4d, addr, next);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 62aa4d66a032..7456df985d96 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -28,6 +28,7 @@
 #include <asm/text-patching.h>
 #include <asm/memtype.h>
 #include <asm/paravirt.h>
+#include <asm/mmu_context.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -173,11 +174,7 @@ __ref void *alloc_low_pages(unsigned int num)
  * randomization is enabled.
  */
 
-#ifndef CONFIG_X86_5LEVEL
-#define INIT_PGD_PAGE_TABLES    3
-#else
 #define INIT_PGD_PAGE_TABLES    4
-#endif
 
 #ifndef CONFIG_RANDOMIZE_MEMORY
 #define INIT_PGD_PAGE_COUNT      (2 * INIT_PGD_PAGE_TABLES)
@@ -645,8 +642,13 @@ static void __init memory_map_top_down(unsigned long map_start,
 	 */
 	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
 					 map_end);
-	memblock_phys_free(addr, PMD_SIZE);
-	real_end = addr + PMD_SIZE;
+	if (!addr) {
+		pr_warn("Failed to release memory for alloc_low_pages()");
+		real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE));
+	} else {
+		memblock_phys_free(addr, PMD_SIZE);
+		real_end = addr + PMD_SIZE;
+	}
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	step_size = PMD_SIZE;
@@ -819,31 +821,33 @@ void __init poking_init(void)
 	spinlock_t *ptl;
 	pte_t *ptep;
 
-	poking_mm = mm_alloc();
-	BUG_ON(!poking_mm);
+	text_poke_mm = mm_alloc();
+	BUG_ON(!text_poke_mm);
 
 	/* Xen PV guests need the PGD to be pinned. */
-	paravirt_enter_mmap(poking_mm);
+	paravirt_enter_mmap(text_poke_mm);
+
+	set_notrack_mm(text_poke_mm);
 
 	/*
 	 * Randomize the poking address, but make sure that the following page
 	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
 	 * and adjust the address if the PMD ends after the first one.
 	 */
-	poking_addr = TASK_UNMAPPED_BASE;
+	text_poke_mm_addr = TASK_UNMAPPED_BASE;
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+		text_poke_mm_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
 			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
 
-	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
-		poking_addr += PAGE_SIZE;
+	if (((text_poke_mm_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		text_poke_mm_addr += PAGE_SIZE;
 
 	/*
 	 * We need to trigger the allocation of the page-tables that will be
 	 * needed for poking now. Later, poking may be performed in an atomic
 	 * section, which might cause allocation to fail.
 	 */
-	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
 	BUG_ON(!ptep);
 	pte_unmap_unlock(ptep, ptl);
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ac41b1e0940d..607d6a2e66e2 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,6 +30,7 @@
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
+#include <linux/execmem.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
@@ -394,23 +395,6 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 
 	pkmap_page_table = virt_to_kpte(vaddr);
 }
-
-void __init add_highpages_with_active_regions(int nid,
-			 unsigned long start_pfn, unsigned long end_pfn)
-{
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) {
-		unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
-					    start_pfn, end_pfn);
-		unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
-					      start_pfn, end_pfn);
-		for ( ; pfn < e_pfn; pfn++)
-			if (pfn_valid(pfn))
-				free_highmem_page(pfn_to_page(pfn));
-	}
-}
 #else
 static inline void permanent_kmaps_init(pgd_t *pgd_base)
 {
@@ -582,7 +566,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+	"Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
@@ -606,18 +590,13 @@ static void __init highmem_pfn_init(void)
 #ifndef CONFIG_HIGHMEM
 	/* Maximum memory usable is what is directly addressable */
 	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
-	if (max_pfn > MAX_NONPAE_PFN)
-		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
-	else
-		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
 	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_HIGHMEM64G
 	if (max_pfn > MAX_NONPAE_PFN) {
 		max_pfn = MAX_NONPAE_PFN;
 		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
 	}
-#endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
 }
 
@@ -634,7 +613,6 @@ void __init find_low_pfn_range(void)
 		highmem_pfn_init();
 }
 
-#ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
@@ -650,20 +628,11 @@ void __init initmem_init(void)
 
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
 
-#ifdef CONFIG_FLATMEM
-	max_mapnr = IS_ENABLED(CONFIG_HIGHMEM) ? highend_pfn : max_low_pfn;
-#endif
 	__vmalloc_start_set = true;
 
 	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
 			pages_to_mb(max_low_pfn));
 
-	setup_bootmem_allocator();
-}
-#endif /* !CONFIG_NUMA */
-
-void __init setup_bootmem_allocator(void)
-{
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
@@ -714,27 +683,17 @@ static void __init test_wp_bit(void)
 	panic("Linux doesn't support CPUs with broken WP.");
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	pci_iommu_alloc();
 
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
-	/*
-	 * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to
-	 * be done before memblock_free_all(). Memblock use free low memory for
-	 * temporary data (see find_range_array()) and for this purpose can use
-	 * pages that was already passed to the buddy allocator, hence marked as
-	 * not accessible in the page tables when compiled with
-	 * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not
-	 * important here.
-	 */
-	set_highmem_pages_init();
-
-	/* this will put all low memory onto the freelists */
-	memblock_free_all();
+}
 
+void __init mem_init(void)
+{
 	after_bootmem = 1;
 	x86_init.hyper.init_after_bootmem();
 
@@ -790,6 +749,8 @@ void mark_rodata_ro(void)
 	pr_info("Write protecting kernel text and read-only data: %luk\n",
 		size >> 10);
 
+	execmem_cache_make_ro();
+
 	kernel_set_to_readonly = 1;
 
 #ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 01ea7c6df303..66330fe4e18c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,6 +34,7 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
+#include <linux/execmem.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -469,8 +470,6 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
-			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pte_init(pte, __pte(0), init);
 			continue;
@@ -526,8 +525,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
-			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pmd_init(pmd, __pmd(0), init);
 			continue;
@@ -615,8 +612,6 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
-			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_pud_init(pud, __pud(0), init);
 			continue;
@@ -704,8 +699,6 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN) &&
-			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_ACPI))
 				set_p4d_init(p4d, __p4d(0), init);
 			continue;
@@ -813,12 +806,17 @@ kernel_physical_mapping_change(unsigned long paddr_start,
 }
 
 #ifndef CONFIG_NUMA
-void __init initmem_init(void)
+static inline void x86_numa_init(void)
 {
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
 }
 #endif
 
+void __init initmem_init(void)
+{
+	x86_numa_init();
+}
+
 void __init paging_init(void)
 {
 	sparse_init();
@@ -835,7 +833,6 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define PAGE_UNUSED 0xFD
 
 /*
@@ -934,7 +931,6 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long
 	if (!IS_ALIGNED(end, PMD_SIZE))
 		unused_pmd_start = end;
 }
-#endif
 
 /*
  * Memory hotplug specific functions
@@ -967,9 +963,18 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 
-	/* update max_pfn, max_low_pfn and high_memory */
-	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
-				  nr_pages << PAGE_SHIFT);
+	/*
+	 * Special case: add_pages() is called by memremap_pages() for adding device
+	 * private pages. Do not bump up max_pfn in the device private path,
+	 * because max_pfn changes affect dma_addressing_limited().
+	 *
+	 * dma_addressing_limited() returning true when max_pfn is the device's
+	 * addressable memory can force device drivers to use bounce buffers
+	 * and impact their performance negatively:
+	 */
+	if (!params->pgmap)
+		/* update max_pfn, max_low_pfn and high_memory */
+		update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
 
 	return ret;
 }
@@ -1145,16 +1150,13 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				pmd_clear(pmd);
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
-			}
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-			else if (vmemmap_pmd_is_unused(addr, next)) {
+			} else if (vmemmap_pmd_is_unused(addr, next)) {
 					free_hugepage_table(pmd_page(*pmd),
 							    altmap);
 					spin_lock(&init_mm.page_table_lock);
 					pmd_clear(pmd);
 					spin_unlock(&init_mm.page_table_lock);
 			}
-#endif
 			continue;
 		}
 
@@ -1348,14 +1350,15 @@ failed:
 	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	pci_iommu_alloc();
+}
 
+void __init mem_init(void)
+{
 	/* clear_bss() already clear the empty_zero_page */
 
-	/* this will put all memory onto the freelists */
-	memblock_free_all();
 	after_bootmem = 1;
 	x86_init.hyper.init_after_bootmem();
 
@@ -1389,6 +1392,8 @@ void mark_rodata_ro(void)
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+	execmem_cache_make_ro();
+
 	kernel_set_to_readonly = 1;
 
 	/*
@@ -1490,7 +1495,6 @@ unsigned long memory_block_size_bytes(void)
 	return memory_block_size_probed;
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
@@ -1599,11 +1603,14 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!boot_cpu_has(X86_FEATURE_PSE)) {
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+
+		if (!boot_cpu_has(X86_FEATURE_PSE) || !pmd_leaf(*pmd)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
-			pmd = pmd_offset(pud, addr);
-			if (pmd_none(*pmd))
-				continue;
 			get_page_bootmem(section_nr, pmd_page(*pmd),
 					 MIX_SECTION_INFO);
 
@@ -1614,12 +1621,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 					 SECTION_INFO);
 		} else {
 			next = pmd_addr_end(addr, end);
-
-			pmd = pmd_offset(pud, addr);
-			if (pmd_none(*pmd))
-				continue;
-
-			nr_pmd_pages = 1 << get_order(PMD_SIZE);
+			nr_pmd_pages = (next - addr) >> PAGE_SHIFT;
 			page = pmd_page(*pmd);
 			while (nr_pmd_pages--)
 				get_page_bootmem(section_nr, page++,
@@ -1639,4 +1641,3 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
-#endif
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 38ff7791a9c7..331e101bf801 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -440,10 +440,10 @@ void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_cache);
 
 void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
-				unsigned long prot_val)
+			   pgprot_t prot)
 {
 	return __ioremap_caller(phys_addr, size,
-				pgprot2cachemode(__pgprot(prot_val)),
+				pgprot2cachemode(prot),
 				__builtin_return_address(0), false);
 }
 EXPORT_SYMBOL(ioremap_prot);
@@ -503,6 +503,14 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
+{
+	if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (void __force *)ioremap_cache(phys_addr, size);
+
+	return (void __force *)ioremap_encrypted(phys_addr, size);
+}
+
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 9dddf19a5571..0539efd0d216 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 
 /* cpu_feature_enabled() cannot be used this early */
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 11a93542d198..3c306de52fd4 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -113,8 +113,14 @@ void __init kernel_randomize_memory(void)
 	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
-	/* Adapt physical memory region size based on available memory */
-	if (memory_tb < kaslr_regions[0].size_tb)
+	/*
+	 * Adapt physical memory region size based on available memory,
+	 * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
+	 * device BAR space assuming the direct map space is large enough
+	 * for creating a ZONE_DEVICE mapping in the direct map corresponding
+	 * to the physical BAR address.
+	 */
+	if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
 		kaslr_regions[0].size_tb = memory_tb;
 
 	/*
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index b56c5c073003..faf3a13fb6ba 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -7,8 +7,6 @@
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  */
 
-#define DISABLE_BRANCH_PROFILING
-
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
@@ -42,7 +40,9 @@
  * section is later cleared.
  */
 u64 sme_me_mask __section(".data") = 0;
+SYM_PIC_ALIAS(sme_me_mask);
 u64 sev_status __section(".data") = 0;
+SYM_PIC_ALIAS(sev_status);
 u64 sev_check_data __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index e25288ee33c2..f8a33b25ae86 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -72,6 +72,7 @@ SYM_FUNC_START(sme_encrypt_execute)
 SYM_FUNC_END(sme_encrypt_execute)
 
 SYM_FUNC_START(__enc_copy)
+	ANNOTATE_NOENDBR
 /*
  * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 3f37b5c80bb3..097aadc250f7 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -25,4 +25,8 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
 
 extern unsigned long tlb_single_page_flush_ceiling;
 
+#ifdef CONFIG_NUMA
+void __init x86_numa_init(void);
+#endif
+
 #endif	/* __X86_MM_INTERNAL_H */
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index b8a6ffffb451..5ed2109211da 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -84,7 +84,6 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 {
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
-	unsigned long gap_min, gap_max;
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
@@ -94,13 +93,7 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 	 * Top of mmap area (just below the process stack).
 	 * Leave an at least ~128 MB hole with possible stack randomization.
 	 */
-	gap_min = SIZE_128M;
-	gap_max = (task_size / 6) * 5;
-
-	if (gap < gap_min)
-		gap = gap_min;
-	else if (gap > gap_max)
-		gap = gap_max;
+	gap = clamp(gap, SIZE_128M, (task_size / 6) * 5);
 
 	return PAGE_ALIGN(task_size - gap - rnd);
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 64e5cdb2460a..c24890c40138 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -18,9 +18,10 @@
 #include <asm/e820/api.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/numa.h>
+#include <asm/amd/nb.h>
 
-#include "numa_internal.h"
+#include "mm_internal.h"
 
 int numa_off;
 
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
deleted file mode 100644
index 65fda406e6f2..000000000000
--- a/arch/x86/mm/numa_32.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
- * August 2002: added remote node KVA remap - Martin J. Bligh 
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.          
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/memblock.h>
-#include <linux/init.h>
-#include <linux/vmalloc.h>
-#include <asm/pgtable_areas.h>
-
-#include "numa_internal.h"
-
-extern unsigned long highend_pfn, highstart_pfn;
-
-void __init initmem_init(void)
-{
-	x86_numa_init();
-
-#ifdef CONFIG_HIGHMEM
-	highstart_pfn = highend_pfn = max_pfn;
-	if (max_pfn > max_low_pfn)
-		highstart_pfn = max_low_pfn;
-	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
-	       pages_to_mb(highend_pfn - highstart_pfn));
-	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
-#else
-	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
-#endif
-	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
-			pages_to_mb(max_low_pfn));
-	printk(KERN_DEBUG "max_low_pfn = %lx, highstart_pfn = %lx\n",
-			max_low_pfn, highstart_pfn);
-
-	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
-			(ulong) pfn_to_kaddr(max_low_pfn));
-
-	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
-			(ulong) pfn_to_kaddr(highstart_pfn));
-
-	__vmalloc_start_set = true;
-	setup_bootmem_allocator();
-}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
deleted file mode 100644
index 59d80160fa5a..000000000000
--- a/arch/x86/mm/numa_64.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Generic VM initialization for x86-64 NUMA setups.
- * Copyright 2002,2003 Andi Kleen, SuSE Labs.
- */
-#include <linux/memblock.h>
-
-#include "numa_internal.h"
-
-void __init initmem_init(void)
-{
-	x86_numa_init();
-}
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
deleted file mode 100644
index 11e1ff370c10..000000000000
--- a/arch/x86/mm/numa_internal.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __X86_MM_NUMA_INTERNAL_H
-#define __X86_MM_NUMA_INTERNAL_H
-
-#include <linux/types.h>
-#include <asm/numa.h>
-
-void __init x86_numa_init(void);
-
-#endif	/* __X86_MM_NUMA_INTERNAL_H */
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
index 3d2f7f0a6ed1..ad3c1feec990 100644
--- a/arch/x86/mm/pat/cpa-test.c
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -183,7 +183,7 @@ static int pageattr_test(void)
 			break;
 
 		case 1:
-			err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
 			break;
 
 		case 2:
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index feb8cc6a12bf..c97b527c66fe 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -38,11 +38,13 @@
 #include <linux/kernel.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
 
+#include <asm/cpu_device_id.h>
 #include <asm/cacheflush.h>
 #include <asm/cacheinfo.h>
 #include <asm/processor.h>
@@ -231,7 +233,7 @@ void pat_cpu_init(void)
 		panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
 	}
 
-	wrmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+	wrmsrq(MSR_IA32_CR_PAT, pat_msr_val);
 
 	__flush_tlb_all();
 }
@@ -255,7 +257,7 @@ void __init pat_bp_init(void)
 	if (!cpu_feature_enabled(X86_FEATURE_PAT))
 		pat_disable("PAT not supported by the CPU.");
 	else
-		rdmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+		rdmsrq(MSR_IA32_CR_PAT, pat_msr_val);
 
 	if (!pat_msr_val) {
 		pat_disable("PAT support disabled by the firmware.");
@@ -290,9 +292,8 @@ void __init pat_bp_init(void)
 		return;
 	}
 
-	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
-	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
-	     ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+	if ((c->x86_vfm >= INTEL_PENTIUM_PRO   && c->x86_vfm <= INTEL_PENTIUM_M_DOTHAN) ||
+	    (c->x86_vfm >= INTEL_P4_WILLAMETTE && c->x86_vfm <= INTEL_P4_CEDARMILL)) {
 		/*
 		 * PAT support with the lower four entries. Intel Pentium 2,
 		 * 3, M, and 4 are affected by PAT errata, which makes the
@@ -682,6 +683,7 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
 /**
  * pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type
  * of @pfn cannot be overridden by UC MTRR memory type.
+ * @pfn: The page frame number to check.
  *
  * Only to be called when PAT is enabled.
  *
@@ -773,38 +775,14 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 	return vma_prot;
 }
 
-#ifdef CONFIG_STRICT_DEVMEM
-/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	return 1;
-}
-#else
-/* This check is needed to avoid cache aliasing when PAT is enabled */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	u64 from = ((u64)pfn) << PAGE_SHIFT;
-	u64 to = from + size;
-	u64 cursor = from;
-
-	if (!pat_enabled())
-		return 1;
-
-	while (cursor < to) {
-		if (!devmem_is_allowed(pfn))
-			return 0;
-		cursor += PAGE_SIZE;
-		pfn++;
-	}
-	return 1;
-}
-#endif /* CONFIG_STRICT_DEVMEM */
-
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
 	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
 
+	if (!pat_enabled())
+		return 1;
+
 	if (!range_is_allowed(pfn, size))
 		return 0;
 
@@ -984,29 +962,42 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
 	return -EINVAL;
 }
 
-/*
- * track_pfn_copy is called when vma that is covering the pfnmap gets
- * copied through copy_page_range().
- *
- * If the vma has a linear pfn mapping for the entire range, we get the prot
- * from pte and reserve the entire vma range with single reserve_pfn_range call.
- */
-int track_pfn_copy(struct vm_area_struct *vma)
+int track_pfn_copy(struct vm_area_struct *dst_vma,
+		struct vm_area_struct *src_vma, unsigned long *pfn)
 {
+	const unsigned long vma_size = src_vma->vm_end - src_vma->vm_start;
 	resource_size_t paddr;
-	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
+	int rc;
 
-	if (vma->vm_flags & VM_PAT) {
-		if (get_pat_info(vma, &paddr, &pgprot))
-			return -EINVAL;
-		/* reserve the whole chunk covered by vma. */
-		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
-	}
+	if (!(src_vma->vm_flags & VM_PAT))
+		return 0;
+
+	/*
+	 * Duplicate the PAT information for the dst VMA based on the src
+	 * VMA.
+	 */
+	if (get_pat_info(src_vma, &paddr, &pgprot))
+		return -EINVAL;
+	rc = reserve_pfn_range(paddr, vma_size, &pgprot, 1);
+	if (rc)
+		return rc;
 
+	/* Reservation for the destination VMA succeeded. */
+	vm_flags_set(dst_vma, VM_PAT);
+	*pfn = PHYS_PFN(paddr);
 	return 0;
 }
 
+void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn)
+{
+	untrack_pfn(dst_vma, pfn, dst_vma->vm_end - dst_vma->vm_start, true);
+	/*
+	 * Reservation was freed, any copied page tables will get cleaned
+	 * up later, but without getting PAT involved again.
+	 */
+}
+
 /*
  * prot is passed in as a parameter for the new mapping. If the vma has
  * a linear pfn mapping for the entire range, or no vma is provided,
@@ -1095,15 +1086,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	}
 }
 
-/*
- * untrack_pfn_clear is called if the following situation fits:
- *
- * 1) while mremapping a pfnmap for a new region,  with the old vma after
- * its pfnmap page table has been removed.  The new vma has a new pfnmap
- * to the same pfn & cache type with VM_PAT set.
- * 2) while duplicating vm area, the new vma fails to copy the pgtable from
- * old vma.
- */
 void untrack_pfn_clear(struct vm_area_struct *vma)
 {
 	vm_flags_clear(vma, VM_PAT);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c05..30ab4aced761 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -73,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
+#define CPA_COLLAPSE 16 /* try to collapse large pages */
 
 static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
 {
@@ -105,6 +106,18 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
+static void collapse_page_count(int level)
+{
+	direct_pages_count[level]++;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+	}
+	direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
 void arch_report_meminfo(struct seq_file *m)
 {
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
@@ -122,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #else
 static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
 #endif
 
 #ifdef CONFIG_X86_CPA_STATISTICS
@@ -211,14 +225,14 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
+#ifdef CONFIG_X86_64
+
 static inline int
 within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
 {
 	return addr >= start && addr <= end;
 }
 
-#ifdef CONFIG_X86_64
-
 /*
  * The kernel image is mapped into two places in the virtual address space
  * (addresses without KASLR, of course):
@@ -394,16 +408,49 @@ static void __cpa_flush_tlb(void *data)
 		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
-static void cpa_flush(struct cpa_data *data, int cache)
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+	unsigned long start, addr, end;
+	struct ptdesc *ptdesc, *tmp;
+	LIST_HEAD(pgtables);
+	int collapsed = 0;
+	int i;
+
+	if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+		for (i = 0; i < cpa->numpages; i++)
+			collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+							  &pgtables);
+	} else {
+		addr = __cpa_addr(cpa, 0);
+		start = addr & PMD_MASK;
+		end = addr + PAGE_SIZE * cpa->numpages;
+
+		for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+			collapsed += collapse_large_pages(addr, &pgtables);
+	}
+
+	if (!collapsed)
+		return;
+
+	flush_tlb_all();
+
+	list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+		list_del(&ptdesc->pt_list);
+		__free_page(ptdesc_page(ptdesc));
+	}
+}
+
+static void cpa_flush(struct cpa_data *cpa, int cache)
 {
-	struct cpa_data *cpa = data;
 	unsigned int i;
 
 	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
 	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		cpa_flush_all(cache);
-		return;
+		goto collapse_large_pages;
 	}
 
 	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
@@ -412,7 +459,7 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
-		return;
+		goto collapse_large_pages;
 
 	mb();
 	for (i = 0; i < cpa->numpages; i++) {
@@ -428,6 +475,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
 	}
 	mb();
+
+collapse_large_pages:
+	if (cpa->flags & CPA_COLLAPSE)
+		cpa_collapse_large_pages(cpa);
 }
 
 static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -838,7 +889,7 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
 	/* change init_mm */
 	set_pte_atomic(kpte, pte);
 #ifdef CONFIG_X86_32
-	if (!SHARED_KERNEL_PMD) {
+	{
 		struct page *page;
 
 		list_for_each_entry(page, &pgd_list, lru) {
@@ -1197,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 	return 0;
 }
 
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	pmd_t _pmd, old_pmd;
+	pte_t *pte, first;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	int i = 0;
+
+	addr &= PMD_MASK;
+	pte = pte_offset_kernel(pmd, addr);
+	first = *pte;
+	pfn = pte_pfn(first);
+
+	/* Make sure alignment is suitable */
+	if (PFN_PHYS(pfn) & ~PMD_MASK)
+		return 0;
+
+	/* The page is 4k intentionally */
+	if (pte_flags(first) & _PAGE_KERNEL_4K)
+		return 0;
+
+	/* Check that the rest of PTEs are compatible with the first one */
+	for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+		pte_t entry = *pte;
+
+		if (!pte_present(entry))
+			return 0;
+		if (pte_flags(entry) != pte_flags(first))
+			return 0;
+		if (pte_pfn(entry) != pte_pfn(first) + i)
+			return 0;
+	}
+
+	old_pmd = *pmd;
+
+	/* Success: set up a large page */
+	pgprot = pgprot_4k_2_large(pte_pgprot(first));
+	pgprot_val(pgprot) |= _PAGE_PSE;
+	_pmd = pfn_pmd(pfn, pgprot);
+	set_pmd(pmd, _pmd);
+
+	/* Queue the page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		struct page *page;
+
+		/* Update all PGD tables to use the same large page */
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+			p4d_t *p4d = p4d_offset(pgd, addr);
+			pud_t *pud = pud_offset(p4d, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
+			/* Something is wrong if entries doesn't match */
+			if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+				continue;
+			set_pmd(pmd, _pmd);
+		}
+	}
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_2M);
+
+	return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	unsigned long pfn;
+	pmd_t *pmd, first;
+	int i;
+
+	if (!direct_gbpages)
+		return 0;
+
+	addr &= PUD_MASK;
+	pmd = pmd_offset(pud, addr);
+	first = *pmd;
+
+	/*
+	 * To restore PUD page all PMD entries must be large and
+	 * have suitable alignment
+	 */
+	pfn = pmd_pfn(first);
+	if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+		return 0;
+
+	/*
+	 * To restore PUD page, all following PMDs must be compatible with the
+	 * first one.
+	 */
+	for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+		pmd_t entry = *pmd;
+
+		if (!pmd_present(entry) || !pmd_leaf(entry))
+			return 0;
+		if (pmd_flags(entry) != pmd_flags(first))
+			return 0;
+		if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+			return 0;
+	}
+
+	/* Restore PUD page and queue page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+	set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_1G);
+
+	return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+	int collapsed = 0;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	addr &= PMD_MASK;
+
+	spin_lock(&pgd_lock);
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		goto out;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		goto out;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		goto out;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	collapsed = collapse_pmd_page(pmd, addr, pgtables);
+	if (collapsed)
+		collapsed += collapse_pud_page(pud, addr, pgtables);
+
+out:
+	spin_unlock(&pgd_lock);
+	return collapsed;
+}
+
 static bool try_to_free_pte_page(pte_t *pte)
 {
 	int i;
@@ -1942,19 +2148,6 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 		CPA_PAGES_ARRAY, pages);
 }
 
-/*
- * __set_memory_prot is an internal helper for callers that have been passed
- * a pgprot_t value from upper layers and a reservation has already been taken.
- * If you want to set the pgprot to a specific page protocol, use the
- * set_memory_xx() functions.
- */
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
-{
-	return change_page_attr_set_clr(&addr, numpages, prot,
-					__pgprot(~pgprot_val(prot)), 0, 0,
-					NULL);
-}
-
 int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
@@ -2081,6 +2274,7 @@ int set_mce_nospec(unsigned long pfn)
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(set_mce_nospec);
 
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
@@ -2120,7 +2314,8 @@ int set_memory_rox(unsigned long addr, int numpages)
 	if (__supported_pte_mask & _PAGE_NX)
 		clr.pgprot |= _PAGE_NX;
 
-	return change_page_attr_clear(&addr, numpages, clr, 0);
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+					CPA_COLLAPSE, NULL);
 }
 
 int set_memory_rw(unsigned long addr, int numpages)
@@ -2147,7 +2342,8 @@ int set_memory_p(unsigned long addr, int numpages)
 
 int set_memory_4k(unsigned long addr, int numpages)
 {
-	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+	return change_page_attr_set_clr(&addr, numpages,
+					__pgprot(_PAGE_KERNEL_4K),
 					__pgprot(0), 1, 0, NULL);
 }
 
@@ -2420,7 +2616,7 @@ static int __set_pages_np(struct page *page, int numpages)
 				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
-				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 				.flags = CPA_NO_CHECK_ALIAS };
 
 	/*
@@ -2507,7 +2703,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)),
 		.flags = CPA_NO_CHECK_ALIAS,
 	};
 
@@ -2550,7 +2746,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 		.pgd		= pgd,
 		.numpages	= numpages,
 		.mask_set	= __pgprot(0),
-		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 		.flags		= CPA_NO_CHECK_ALIAS,
 	};
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1fef5ad32d5a..62777ba4de1a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -10,61 +10,18 @@
 #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
 phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
 EXPORT_SYMBOL(physical_mask);
+SYM_PIC_ALIAS(physical_mask);
 #endif
 
-#ifdef CONFIG_HIGHPTE
-#define PGTABLE_HIGHMEM __GFP_HIGHMEM
-#else
-#define PGTABLE_HIGHMEM 0
-#endif
-
-#ifndef CONFIG_PARAVIRT
-#ifndef CONFIG_PT_RECLAIM
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif /* !CONFIG_PT_RECLAIM */
-#endif /* !CONFIG_PARAVIRT */
-
-gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
-
 pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, __userpte_alloc_gfp);
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
 }
 
-static int __init setup_userpte(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	/*
-	 * "userpte=nohigh" disables allocation of user pagetables in
-	 * high memory.
-	 */
-	if (strcmp(arg, "nohigh") == 0)
-		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-	else
-		return -EINVAL;
-	return 0;
-}
-early_param("userpte", setup_userpte);
-
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
+	tlb_remove_ptdesc(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
@@ -78,21 +35,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
@@ -112,12 +69,6 @@ static inline void pgd_list_del(pgd_t *pgd)
 	list_del(&ptdesc->pt_list);
 }
 
-#define UNSHARED_PTRS_PER_PGD				\
-	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
-#define MAX_UNSHARED_PTRS_PER_PGD			\
-	MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
-
-
 static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
 {
 	virt_to_ptdesc(pgd)->pt_mm = mm;
@@ -130,29 +81,19 @@ struct mm_struct *pgd_page_get_mm(struct page *page)
 
 static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 {
-	/* If the pgd points to a shared pagetable level (either the
-	   ptes in non-PAE, or shared PMD in PAE), then just copy the
-	   references from swapper_pg_dir. */
-	if (CONFIG_PGTABLE_LEVELS == 2 ||
-	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
-	    CONFIG_PGTABLE_LEVELS >= 4) {
+	/* PAE preallocates all its PMDs.  No cloning needed. */
+	if (!IS_ENABLED(CONFIG_X86_PAE))
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
-	}
 
-	/* list required to sync kernel mapping updates */
-	if (!SHARED_KERNEL_PMD) {
-		pgd_set_mm(pgd, mm);
-		pgd_list_add(pgd);
-	}
+	/* List used to sync kernel mapping updates */
+	pgd_set_mm(pgd, mm);
+	pgd_list_add(pgd);
 }
 
 static void pgd_dtor(pgd_t *pgd)
 {
-	if (SHARED_KERNEL_PMD)
-		return;
-
 	spin_lock(&pgd_lock);
 	pgd_list_del(pgd);
 	spin_unlock(&pgd_lock);
@@ -176,15 +117,15 @@ static void pgd_dtor(pgd_t *pgd)
  * processor notices the update.  Since this is expensive, and
  * all 4 top-level entries are used almost immediately in a
  * new process's life, we just pre-populate them here.
- *
- * Also, if we're in a paravirt environment where the kernel pmd is
- * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
- * and initialize the kernel pmds here.
  */
-#define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
-#define MAX_PREALLOCATED_PMDS	MAX_UNSHARED_PTRS_PER_PGD
+#define PREALLOCATED_PMDS	PTRS_PER_PGD
 
 /*
+ * "USER_PMDS" are the PMDs for the user copy of the page tables when
+ * PTI is enabled. They do not exist when PTI is disabled.  Note that
+ * this is distinct from the user _portion_ of the kernel page tables
+ * which always exists.
+ *
  * We allocate separate PMDs for the kernel part of the user page-table
  * when PTI is enabled. We need them to map the per-process LDT into the
  * user-space page-table.
@@ -213,7 +154,6 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
-#define MAX_PREALLOCATED_PMDS	0
 #define PREALLOCATED_USER_PMDS	 0
 #define MAX_PREALLOCATED_USER_PMDS 0
 #endif	/* CONFIG_X86_PAE */
@@ -362,82 +302,28 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 {
 }
 #endif
-/*
- * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
- * assumes that pgd should be in one page.
- *
- * But kernel with PAE paging that is not running as a Xen domain
- * only needs to allocate 32 bytes for pgd instead of one page.
- */
-#ifdef CONFIG_X86_PAE
-
-#include <linux/slab.h>
-
-#define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
-#define PGD_ALIGN	32
-
-static struct kmem_cache *pgd_cache;
-
-void __init pgtable_cache_init(void)
-{
-	/*
-	 * When PAE kernel is running as a Xen domain, it does not use
-	 * shared kernel pmd. And this requires a whole page for pgd.
-	 */
-	if (!SHARED_KERNEL_PMD)
-		return;
-
-	/*
-	 * when PAE kernel is not running as a Xen domain, it uses
-	 * shared kernel pmd. Shared kernel pmd does not require a whole
-	 * page for pgd. We are able to just allocate a 32-byte for pgd.
-	 * During boot time, we create a 32-byte slab for pgd table allocation.
-	 */
-	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
-				      SLAB_PANIC, NULL);
-}
 
 static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
 	/*
-	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
-	 * We allocate one page for pgd.
-	 */
-	if (!SHARED_KERNEL_PMD)
-		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
-
-	/*
-	 * Now PAE kernel is not running as a Xen domain. We can allocate
-	 * a 32-byte slab for pgd to save memory space.
+	 * PTI and Xen need a whole page for the PAE PGD
+	 * even though the hardware only needs 32 bytes.
+	 *
+	 * For simplicity, allocate a page for all users.
 	 */
-	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
-}
-
-static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	if (!SHARED_KERNEL_PMD)
-		__pgd_free(mm, pgd);
-	else
-		kmem_cache_free(pgd_cache, pgd);
-}
-#else
-
-static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
-{
-	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, pgd_allocation_order());
 }
 
 static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	__pgd_free(mm, pgd);
 }
-#endif /* CONFIG_X86_PAE */
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
-	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
+	pmd_t *pmds[PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc(mm);
 
@@ -657,11 +543,11 @@ pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
 #endif
 
 /**
- * reserve_top_address - reserves a hole in the top of kernel address space
- * @reserve - size of hole to reserve
+ * reserve_top_address - Reserve a hole in the top of the kernel address space
+ * @reserve: Size of hole to reserve
  *
  * Can be used to relocate the fixmap area and poke a hole in the top
- * of kernel address space to make room for a hypervisor.
+ * of the kernel address space to make room for a hypervisor.
  */
 void __init reserve_top_address(unsigned long reserve)
 {
@@ -706,9 +592,12 @@ void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
 }
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-#ifdef CONFIG_X86_5LEVEL
+#if CONFIG_PGTABLE_LEVELS > 4
 /**
- * p4d_set_huge - setup kernel P4D mapping
+ * p4d_set_huge - Set up kernel P4D mapping
+ * @p4d: Pointer to the P4D entry
+ * @addr: Virtual address associated with the P4D entry
+ * @prot: Protection bits to use
  *
  * No 512GB pages yet -- always return 0
  */
@@ -718,9 +607,10 @@ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 }
 
 /**
- * p4d_clear_huge - clear kernel P4D mapping when it is set
+ * p4d_clear_huge - Clear kernel P4D mapping when it is set
+ * @p4d: Pointer to the P4D entry to clear
  *
- * No 512GB pages yet -- always return 0
+ * No 512GB pages yet -- do nothing
  */
 void p4d_clear_huge(p4d_t *p4d)
 {
@@ -728,7 +618,10 @@ void p4d_clear_huge(p4d_t *p4d)
 #endif
 
 /**
- * pud_set_huge - setup kernel PUD mapping
+ * pud_set_huge - Set up kernel PUD mapping
+ * @pud: Pointer to the PUD entry
+ * @addr: Virtual address associated with the PUD entry
+ * @prot: Protection bits to use
  *
  * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
  * function sets up a huge page only if the complete range has the same MTRR
@@ -759,7 +652,10 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 }
 
 /**
- * pmd_set_huge - setup kernel PMD mapping
+ * pmd_set_huge - Set up kernel PMD mapping
+ * @pmd: Pointer to the PMD entry
+ * @addr: Virtual address associated with the PMD entry
+ * @prot: Protection bits to use
  *
  * See text over pud_set_huge() above.
  *
@@ -788,7 +684,8 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 }
 
 /**
- * pud_clear_huge - clear kernel PUD mapping when it is set
+ * pud_clear_huge - Clear kernel PUD mapping when it is set
+ * @pud: Pointer to the PUD entry to clear.
  *
  * Returns 1 on success and 0 on failure (no PUD map is found).
  */
@@ -803,7 +700,8 @@ int pud_clear_huge(pud_t *pud)
 }
 
 /**
- * pmd_clear_huge - clear kernel PMD mapping when it is set
+ * pmd_clear_huge - Clear kernel PMD mapping when it is set
+ * @pmd: Pointer to the PMD entry to clear.
  *
  * Returns 1 on success and 0 on failure (no PMD map is found).
  */
@@ -819,11 +717,11 @@ int pmd_clear_huge(pmd_t *pmd)
 
 #ifdef CONFIG_X86_64
 /**
- * pud_free_pmd_page - Clear pud entry and free pmd page.
- * @pud: Pointer to a PUD.
- * @addr: Virtual address associated with pud.
+ * pud_free_pmd_page - Clear PUD entry and free PMD page
+ * @pud: Pointer to a PUD
+ * @addr: Virtual address associated with PUD
  *
- * Context: The pud range has been unmapped and TLB purged.
+ * Context: The PUD range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  *
  * NOTE: Callers must allow a single page allocation.
@@ -866,11 +764,11 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 }
 
 /**
- * pmd_free_pte_page - Clear pmd entry and free pte page.
- * @pmd: Pointer to a PMD.
- * @addr: Virtual address associated with pmd.
+ * pmd_free_pte_page - Clear PMD entry and free PTE page.
+ * @pmd: Pointer to the PMD
+ * @addr: Virtual address associated with PMD
  *
- * Context: The pmd range has been unmapped and TLB purged.
+ * Context: The PMD range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
@@ -892,7 +790,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 
 /*
  * Disable free page handling on x86-PAE. This assures that ioremap()
- * does not update sync'd pmd entries. See vmalloc_sync_one().
+ * does not update sync'd PMD entries. See vmalloc_sync_one().
  */
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5f0d579932c6..190299834011 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -185,7 +185,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 
 		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
 	}
-	BUILD_BUG_ON(pgd_leaf(*pgd) != 0);
+	BUILD_BUG_ON(pgd_leaf(*pgd));
 
 	return p4d_offset(pgd, address);
 }
@@ -206,7 +206,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	if (!p4d)
 		return NULL;
 
-	BUILD_BUG_ON(p4d_leaf(*p4d) != 0);
+	BUILD_BUG_ON(p4d_leaf(*p4d));
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
 		if (WARN_ON_ONCE(!new_pud_page))
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bb..39f80111e6f1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -19,6 +19,7 @@
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 #include <asm/apic.h>
+#include <asm/msr.h>
 #include <asm/perf_event.h>
 #include <asm/tlb.h>
 
@@ -74,13 +75,15 @@
  * use different names for each of them:
  *
  * ASID  - [0, TLB_NR_DYN_ASIDS-1]
- *         the canonical identifier for an mm
+ *         the canonical identifier for an mm, dynamically allocated on each CPU
+ *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
+ *         the canonical, global identifier for an mm, identical across all CPUs
  *
- * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * kPCID - [1, MAX_ASID_AVAILABLE]
  *         the value we write into the PCID part of CR3; corresponds to the
  *         ASID+1, because PCID 0 is special.
  *
- * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
  *         for KPTI each mm has two address spaces and thus needs two
  *         PCID values, but we can still do with a single ASID denomination
  *         for each mm. Corresponds to kPCID + 2048.
@@ -213,16 +216,34 @@ static void clear_asid_other(void)
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
+struct new_asid {
+	unsigned int asid	: 16;
+	unsigned int need_flush : 1;
+};
 
-static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
-			    u16 *new_asid, bool *need_flush)
+static struct new_asid choose_new_asid(struct mm_struct *next, u64 next_tlb_gen)
 {
+	struct new_asid ns;
 	u16 asid;
 
 	if (!static_cpu_has(X86_FEATURE_PCID)) {
-		*new_asid = 0;
-		*need_flush = true;
-		return;
+		ns.asid = 0;
+		ns.need_flush = 1;
+		return ns;
+	}
+
+	/*
+	 * TLB consistency for global ASIDs is maintained with hardware assisted
+	 * remote TLB flushing. Global ASIDs are always up to date.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		u16 global_asid = mm_global_asid(next);
+
+		if (global_asid) {
+			ns.asid = global_asid;
+			ns.need_flush = 0;
+			return ns;
+		}
 	}
 
 	if (this_cpu_read(cpu_tlbstate.invalidate_other))
@@ -233,22 +254,285 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		    next->context.ctx_id)
 			continue;
 
-		*new_asid = asid;
-		*need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) <
-			       next_tlb_gen);
-		return;
+		ns.asid = asid;
+		ns.need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < next_tlb_gen);
+		return ns;
 	}
 
 	/*
 	 * We don't currently own an ASID slot on this CPU.
 	 * Allocate a slot.
 	 */
-	*new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
-	if (*new_asid >= TLB_NR_DYN_ASIDS) {
-		*new_asid = 0;
+	ns.asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
+	if (ns.asid >= TLB_NR_DYN_ASIDS) {
+		ns.asid = 0;
 		this_cpu_write(cpu_tlbstate.next_asid, 1);
 	}
-	*need_flush = true;
+	ns.need_flush = true;
+
+	return ns;
+}
+
+/*
+ * Global ASIDs are allocated for multi-threaded processes that are
+ * active on multiple CPUs simultaneously, giving each of those
+ * processes the same PCID on every CPU, for use with hardware-assisted
+ * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
+ *
+ * These global ASIDs are held for the lifetime of the process.
+ */
+static DEFINE_RAW_SPINLOCK(global_asid_lock);
+static u16 last_global_asid = MAX_ASID_AVAILABLE;
+static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
+static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
+static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;
+
+/*
+ * When the search for a free ASID in the global ASID space reaches
+ * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
+ * freed global ASIDs are safe to re-use.
+ *
+ * This way the global flush only needs to happen at ASID rollover
+ * time, and not at ASID allocation time.
+ */
+static void reset_global_asid_space(void)
+{
+	lockdep_assert_held(&global_asid_lock);
+
+	invlpgb_flush_all_nonglobals();
+
+	/*
+	 * The TLB flush above makes it safe to re-use the previously
+	 * freed global ASIDs.
+	 */
+	bitmap_andnot(global_asid_used, global_asid_used,
+			global_asid_freed, MAX_ASID_AVAILABLE);
+	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);
+
+	/* Restart the search from the start of global ASID space. */
+	last_global_asid = TLB_NR_DYN_ASIDS;
+}
+
+static u16 allocate_global_asid(void)
+{
+	u16 asid;
+
+	lockdep_assert_held(&global_asid_lock);
+
+	/* The previous allocation hit the edge of available address space */
+	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
+		reset_global_asid_space();
+
+	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);
+
+	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
+		/* This should never happen. */
+		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
+				global_asid_available);
+		return 0;
+	}
+
+	/* Claim this global ASID. */
+	__set_bit(asid, global_asid_used);
+	last_global_asid = asid;
+	global_asid_available--;
+	return asid;
+}
+
+/*
+ * Check whether a process is currently active on more than @threshold CPUs.
+ * This is a cheap estimation on whether or not it may make sense to assign
+ * a global ASID to this process, and use broadcast TLB invalidation.
+ */
+static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
+{
+	int count = 0;
+	int cpu;
+
+	/* This quick check should eliminate most single threaded programs. */
+	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
+		return false;
+
+	/* Slower check to make sure. */
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/* Skip the CPUs that aren't really running this process. */
+		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
+			continue;
+
+		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+			continue;
+
+		if (++count > threshold)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Assign a global ASID to the current process, protecting against
+ * races between multiple threads in the process.
+ */
+static void use_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* This process is already using broadcast TLB invalidation. */
+	if (mm_global_asid(mm))
+		return;
+
+	/*
+	 * The last global ASID was consumed while waiting for the lock.
+	 *
+	 * If this fires, a more aggressive ASID reuse scheme might be
+	 * needed.
+	 */
+	if (!global_asid_available) {
+		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
+		return;
+	}
+
+	asid = allocate_global_asid();
+	if (!asid)
+		return;
+
+	mm_assign_global_asid(mm, asid);
+}
+
+void mm_free_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	if (!mm_global_asid(mm))
+		return;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* The global ASID can be re-used only after flush at wrap-around. */
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	__set_bit(mm->context.global_asid, global_asid_freed);
+
+	mm->context.global_asid = 0;
+	global_asid_available++;
+#endif
+}
+
+/*
+ * Is the mm transitioning from a CPU-local ASID to a global ASID?
+ */
+static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
+{
+	u16 global_asid = mm_global_asid(mm);
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	/* Process is transitioning to a global ASID */
+	if (global_asid && asid != global_asid)
+		return true;
+
+	return false;
+}
+
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
+ * systems have over 8k CPUs. Because of this potential ASID shortage,
+ * global ASIDs are handed out to processes that have frequent TLB
+ * flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!mm_in_asid_transition(mm))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	mm_clear_asid_transition(mm);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = mm_global_asid(info->mm);
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
 }
 
 /*
@@ -345,7 +629,7 @@ static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
 {
 	/* Flush L1D if the outgoing task requests it */
 	if (prev_mm & LAST_USER_MM_L1D_FLUSH)
-		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
 
 	/* Check whether the incoming task opted in for L1D flush */
 	if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
@@ -389,9 +673,9 @@ static void cond_mitigation(struct task_struct *next)
 	prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);
 
 	/*
-	 * Avoid user/user BTB poisoning by flushing the branch predictor
-	 * when switching between processes. This stops one process from
-	 * doing Spectre-v2 attacks on another.
+	 * Avoid user->user BTB/RSB poisoning by flushing them when switching
+	 * between processes. This stops one process from doing Spectre-v2
+	 * attacks on another.
 	 *
 	 * Both, the conditional and the always IBPB mode use the mm
 	 * pointer to avoid the IBPB when switching between tasks of the
@@ -447,8 +731,7 @@ static void cond_mitigation(struct task_struct *next)
 		 * different context than the user space task which ran
 		 * last on this CPU.
 		 */
-		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) !=
-					(unsigned long)next->mm)
+		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm)
 			indirect_branch_prediction_barrier();
 	}
 
@@ -504,9 +787,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
 	unsigned cpu = smp_processor_id();
 	unsigned long new_lam;
+	struct new_asid ns;
 	u64 next_tlb_gen;
-	bool need_flush;
-	u16 new_asid;
+
 
 	/* We don't want flush_tlb_func() to run concurrently with us. */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
@@ -556,7 +839,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	 */
 	if (prev == next) {
 		/* Not actually switching mm's */
-		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+		VM_WARN_ON(is_dyn_asid(prev_asid) &&
+			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
 
 		/*
@@ -569,10 +853,25 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 * mm_cpumask. The TLB shootdown code can figure out from
 		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
 		 */
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && WARN_ON_ONCE(prev != &init_mm &&
+		if (IS_ENABLED(CONFIG_DEBUG_VM) &&
+		    WARN_ON_ONCE(prev != &init_mm && !is_notrack_mm(prev) &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
+		/* Check if the current mm is transitioning to a global ASID */
+		if (mm_needs_global_asid(next, prev_asid)) {
+			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+			ns = choose_new_asid(next, next_tlb_gen);
+			goto reload_tlb;
+		}
+
+		/*
+		 * Broadcast TLB invalidation keeps this ASID up to date
+		 * all the time.
+		 */
+		if (is_global_asid(prev_asid))
+			return;
+
 		/*
 		 * If the CPU is not in lazy TLB mode, we are just switching
 		 * from one thread in a process to another thread in the same
@@ -597,8 +896,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 * TLB contents went out of date while we were in lazy
 		 * mode. Fall through to the TLB switching code below.
 		 */
-		new_asid = prev_asid;
-		need_flush = true;
+		ns.asid = prev_asid;
+		ns.need_flush = true;
 	} else {
 		/*
 		 * Apply process to process speculation vulnerability
@@ -607,35 +906,33 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
-		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
-		 * mm_cpumask can be expensive under contention. The CPU
-		 * will be removed lazily at TLB flush time.
+		 * Indicate that CR3 is about to change. nmi_uaccess_okay()
+		 * and others are sensitive to the window where mm_cpumask(),
+		 * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
 		 */
-		VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu,
-				mm_cpumask(prev)));
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
 
 		/* Start receiving IPIs and then read tlb_gen (and LAM below) */
 		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
-		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
-
-		/* Let nmi_uaccess_okay() know that we're changing CR3. */
-		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
-		barrier();
+		ns = choose_new_asid(next, next_tlb_gen);
 	}
 
+reload_tlb:
 	new_lam = mm_lam_cr3_mask(next);
-	if (need_flush) {
-		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
+	if (ns.need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(ns.asid));
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, true);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
-		load_new_mm_cr3(next->pgd, new_asid, new_lam, false);
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, false);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
@@ -644,7 +941,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	barrier();
 
 	this_cpu_write(cpu_tlbstate.loaded_mm, next);
-	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, ns.asid);
 	cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next));
 
 	if (next != prev) {
@@ -675,6 +972,77 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 }
 
 /*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.  Temporary mms can also be used for EFI runtime service
+ * calls or similar functionality.
+ *
+ * It is illegal to schedule while using a temporary mm -- the context switch
+ * code is unaware of the temporary mm and does not know how to context switch.
+ * Use a real (non-temporary) mm in a kernel thread if you need to sleep.
+ *
+ * Note: For sensitive memory writes, the temporary mm needs to be used
+ *       exclusively by a single core, and IRQs should be disabled while the
+ *       temporary mm is loaded, thereby preventing interrupt handler bugs from
+ *       overriding the kernel memory protection.
+ */
+struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm)
+{
+	struct mm_struct *prev_mm;
+
+	lockdep_assert_preemption_disabled();
+	guard(irqsave)();
+
+	/*
+	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+	 * with a stale address space WITHOUT being in lazy mode after
+	 * restoring the previous mm.
+	 */
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
+		leave_mm();
+
+	prev_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, temp_mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return prev_mm;
+}
+
+void unuse_temporary_mm(struct mm_struct *prev_mm)
+{
+	lockdep_assert_preemption_disabled();
+	guard(irqsave)();
+
+	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
+	cpumask_clear_cpu(smp_processor_id(), mm_cpumask(this_cpu_read(cpu_tlbstate.loaded_mm)));
+
+	switch_mm_irqs_off(NULL, prev_mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
+/*
  * Call this when reinitializing a CPU.  It fixes the following potential
  * problems:
  *
@@ -746,7 +1114,7 @@ static void flush_tlb_func(void *info)
 	const struct flush_tlb_info *f = info;
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+	u64 local_tlb_gen;
 	bool local = smp_processor_id() == f->initiating_cpu;
 	unsigned long nr_invalidate = 0;
 	u64 mm_tlb_gen;
@@ -769,6 +1137,16 @@ static void flush_tlb_func(void *info)
 	if (unlikely(loaded_mm == &init_mm))
 		return;
 
+	/* Reload the ASID if transitioning into or out of a global ASID */
+	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
+		switch_mm_irqs_off(NULL, loaded_mm, NULL);
+		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	}
+
+	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
+	if (is_global_asid(loaded_mm_asid))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
@@ -786,6 +1164,8 @@ static void flush_tlb_func(void *info)
 		return;
 	}
 
+	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+
 	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
 		     f->new_tlb_gen <= local_tlb_gen)) {
 		/*
@@ -895,8 +1275,16 @@ done:
 
 static bool should_flush_tlb(int cpu, void *data)
 {
+	struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
 	struct flush_tlb_info *info = data;
 
+	/*
+	 * Order the 'loaded_mm' and 'is_lazy' against their
+	 * write ordering in switch_mm_irqs_off(). Ensure
+	 * 'is_lazy' is at least as new as 'loaded_mm'.
+	 */
+	smp_rmb();
+
 	/* Lazy TLB will get flushed at the next context switch. */
 	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
 		return false;
@@ -905,8 +1293,15 @@ static bool should_flush_tlb(int cpu, void *data)
 	if (!info->mm)
 		return true;
 
+	/*
+	 * While switching, the remote CPU could have state from
+	 * either the prev or next mm. Assume the worst and flush.
+	 */
+	if (loaded_mm == LOADED_MM_SWITCHING)
+		return true;
+
 	/* The target mm is loaded, and the CPU is not lazy. */
-	if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+	if (loaded_mm == info->mm)
 		return true;
 
 	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
@@ -953,7 +1348,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
+	if (info->freed_tables || mm_in_asid_transition(info->mm))
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
 		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
@@ -1000,6 +1395,15 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
 #endif
 
+	/*
+	 * If the number of flushes is so large that a full flush
+	 * would be faster, do a full flush.
+	 */
+	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
+	}
+
 	info->start		= start;
 	info->end		= end;
 	info->mm		= mm;
@@ -1026,17 +1430,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				bool freed_tables)
 {
 	struct flush_tlb_info *info;
+	int cpu = get_cpu();
 	u64 new_tlb_gen;
-	int cpu;
-
-	cpu = get_cpu();
-
-	/* Should we flush just the requested range? */
-	if ((end == TLB_FLUSH_ALL) ||
-	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
-		start = 0;
-		end = TLB_FLUSH_ALL;
-	}
 
 	/* This is also a barrier that synchronizes with switch_mm(). */
 	new_tlb_gen = inc_mm_tlb_gen(mm);
@@ -1049,9 +1444,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
 		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
@@ -1064,7 +1462,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -1074,7 +1471,32 @@ static void do_flush_tlb_all(void *info)
 void flush_tlb_all(void)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	on_each_cpu(do_flush_tlb_all, NULL, 1);
+
+	/* First try (faster) hardware-assisted TLB invalidation. */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		/* Fall back to the IPI-based invalidation. */
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+/* Flush an arbitrarily large range of memory with INVLPGB. */
+static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
+{
+	unsigned long addr, nr;
+
+	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
+		nr = (info->end - addr) >> PAGE_SHIFT;
+
+		/*
+		 * INVLPGB has a limit on the size of ranges it can
+		 * flush. Break up large flushes.
+		 */
+		nr = clamp_val(nr, 1, invlpgb_count_max);
+
+		invlpgb_flush_addr_nosync(addr, nr);
+	}
+	__tlbsync();
 }
 
 static void do_kernel_range_flush(void *info)
@@ -1087,24 +1509,37 @@ static void do_kernel_range_flush(void *info)
 		flush_tlb_one_kernel(addr);
 }
 
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+static void kernel_tlb_flush_all(struct flush_tlb_info *info)
 {
-	/* Balance as user space task's flush, a bit conservative */
-	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
-	} else {
-		struct flush_tlb_info *info;
-
-		preempt_disable();
-		info = get_flush_tlb_info(NULL, start, end, 0, false,
-					  TLB_GENERATION_INVALID);
+}
 
+static void kernel_tlb_flush_range(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_kernel_range_flush(info);
+	else
 		on_each_cpu(do_kernel_range_flush, info, 1);
+}
 
-		put_flush_tlb_info();
-		preempt_enable();
-	}
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct flush_tlb_info *info;
+
+	guard(preempt)();
+
+	info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false,
+				  TLB_GENERATION_INVALID);
+
+	if (info->end == TLB_FLUSH_ALL)
+		kernel_tlb_flush_all(info);
+	else
+		kernel_tlb_flush_range(info);
+
+	put_flush_tlb_info();
 }
 
 /*
@@ -1283,7 +1718,10 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
+		invlpgb_flush_all_nonglobals();
+		batch->unmapped_pages = false;
+	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
@@ -1325,7 +1763,7 @@ bool nmi_uaccess_okay(void)
 	if (loaded_mm != current_mm)
 		return false;
 
-	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
 
 	return true;
 }
diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile
index 383c87300b0d..dddbefc0f439 100644
--- a/arch/x86/net/Makefile
+++ b/arch/x86/net/Makefile
@@ -6,5 +6,5 @@
 ifeq ($(CONFIG_X86_32),y)
         obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
 else
-        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o bpf_timed_may_goto.o
 endif
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a43fc5af973d..15672cb926fc 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+#define EMIT5(b1, b2, b3, b4, b5) \
+	do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0)
 
 #define EMIT1_off32(b1, off) \
 	do { EMIT1(b1); EMIT(off, 4); } while (0)
@@ -410,16 +412,20 @@ static void emit_nops(u8 **pprog, int len)
  * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
  * in arch/x86/kernel/alternative.c
  */
+static int emit_call(u8 **prog, void *func, void *ip);
 
-static void emit_fineibt(u8 **pprog, u32 hash)
+static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
 	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
-	EMIT2(0x74, 0x07);				/* jz.d8 +7		*/
-	EMIT2(0x0f, 0x0b);				/* ud2			*/
-	EMIT1(0x90);					/* nop			*/
+	if (cfi_bhi) {
+		emit_call(&prog, __bhi_args[arity], ip + 11);
+	} else {
+		EMIT2(0x75, 0xf9);			/* jne.d8 .-7		*/
+		EMIT3(0x0f, 0x1f, 0x00);		/* nop3			*/
+	}
 	EMIT_ENDBR_POISON();
 
 	*pprog = prog;
@@ -448,13 +454,13 @@ static void emit_kcfi(u8 **pprog, u32 hash)
 	*pprog = prog;
 }
 
-static void emit_cfi(u8 **pprog, u32 hash)
+static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		emit_fineibt(&prog, hash);
+		emit_fineibt(&prog, ip, hash, arity);
 		break;
 
 	case CFI_KCFI:
@@ -505,13 +511,17 @@ static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
  * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
  * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf,
 			  bool tail_call_reachable, bool is_subprog,
 			  bool is_exception_cb)
 {
 	u8 *prog = *pprog;
 
-	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
+	if (is_subprog) {
+		emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5);
+	} else {
+		emit_cfi(&prog, ip, cfi_bpf_hash, 1);
+	}
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
@@ -621,7 +631,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		goto out;
 	ret = 1;
 	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
-		text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
+		smp_text_poke_single(ip, new_insn, X86_PATCH_SIZE, NULL);
 		ret = 0;
 	}
 out:
@@ -641,7 +651,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	 * See emit_prologue(), for IBT builds the trampoline hook is preceded
 	 * with an ENDBR instruction.
 	 */
-	if (is_endbr(*(u32 *)ip))
+	if (is_endbr(ip))
 		ip += ENDBR_INSN_SIZE;
 
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
@@ -653,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
+	if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
+		OPTIMIZER_HIDE_VAR(reg);
+		emit_jump(&prog, its_static_thunk(reg), ip);
+	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
 		EMIT_LFENCE();
 		EMIT2(0xFF, 0xE0 + reg);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
@@ -675,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk()) {
 		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */
@@ -1242,8 +1255,8 @@ static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm)
 	emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm);
 }
 
-static int emit_atomic(u8 **pprog, u8 atomic_op,
-		       u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
+static int emit_atomic_rmw(u8 **pprog, u32 atomic_op,
+			   u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
 {
 	u8 *prog = *pprog;
 
@@ -1283,8 +1296,9 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 	return 0;
 }
 
-static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
-			     u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+static int emit_atomic_rmw_index(u8 **pprog, u32 atomic_op, u32 size,
+				 u32 dst_reg, u32 src_reg, u32 index_reg,
+				 int off)
 {
 	u8 *prog = *pprog;
 
@@ -1297,7 +1311,7 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
 		EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg));
 		break;
 	default:
-		pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n");
+		pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
 		return -EFAULT;
 	}
 
@@ -1331,6 +1345,49 @@ static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
 	return 0;
 }
 
+static int emit_atomic_ld_st(u8 **pprog, u32 atomic_op, u32 dst_reg,
+			     u32 src_reg, s16 off, u8 bpf_size)
+{
+	switch (atomic_op) {
+	case BPF_LOAD_ACQ:
+		/* dst_reg = smp_load_acquire(src_reg + off16) */
+		emit_ldx(pprog, bpf_size, dst_reg, src_reg, off);
+		break;
+	case BPF_STORE_REL:
+		/* smp_store_release(dst_reg + off16, src_reg) */
+		emit_stx(pprog, bpf_size, dst_reg, src_reg, off);
+		break;
+	default:
+		pr_err("bpf_jit: unknown atomic load/store opcode %02x\n",
+		       atomic_op);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int emit_atomic_ld_st_index(u8 **pprog, u32 atomic_op, u32 size,
+				   u32 dst_reg, u32 src_reg, u32 index_reg,
+				   int off)
+{
+	switch (atomic_op) {
+	case BPF_LOAD_ACQ:
+		/* dst_reg = smp_load_acquire(src_reg + idx_reg + off16) */
+		emit_ldx_index(pprog, size, dst_reg, src_reg, index_reg, off);
+		break;
+	case BPF_STORE_REL:
+		/* smp_store_release(dst_reg + idx_reg + off16, src_reg) */
+		emit_stx_index(pprog, size, dst_reg, src_reg, index_reg, off);
+		break;
+	default:
+		pr_err("bpf_jit: unknown atomic load/store opcode %02x\n",
+		       atomic_op);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 #define DONT_CLEAR 1
 
 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
@@ -1450,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
 #define PRIV_STACK_GUARD_SZ    8
 #define PRIV_STACK_GUARD_VAL   0xEB9F12345678eb9fULL
 
+static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
+				    struct bpf_prog *bpf_prog)
+{
+	u8 *prog = *pprog;
+	u8 *func;
+
+	if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) {
+		/* The clearing sequence clobbers eax and ecx. */
+		EMIT1(0x50); /* push rax */
+		EMIT1(0x51); /* push rcx */
+		ip += 2;
+
+		func = (u8 *)clear_bhb_loop;
+		ip += x86_call_depth_emit_accounting(&prog, func, ip);
+
+		if (emit_call(&prog, func, ip))
+			return -EINVAL;
+		EMIT1(0x59); /* pop rcx */
+		EMIT1(0x58); /* pop rax */
+	}
+	/* Insert IBHF instruction */
+	if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) &&
+	     cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) ||
+	    cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) {
+		/*
+		 * Add an Indirect Branch History Fence (IBHF). IBHF acts as a
+		 * fence preventing branch history from before the fence from
+		 * affecting indirect branches after the fence. This is
+		 * specifically used in cBPF jitted code to prevent Intra-mode
+		 * BHI attacks. The IBHF instruction is designed to be a NOP on
+		 * hardware that doesn't need or support it.  The REP and REX.W
+		 * prefixes are required by the microcode, and they also ensure
+		 * that the NOP is unlikely to be used in existing code.
+		 *
+		 * IBHF is not a valid instruction in 32-bit mode.
+		 */
+		EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */
+	}
+	*pprog = prog;
+	return 0;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
 		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
@@ -1480,7 +1579,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used);
 
-	emit_prologue(&prog, stack_depth,
+	emit_prologue(&prog, image, stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
 		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
 	/* Exception callback will clobber callee regs for its own use, and
@@ -2113,6 +2212,13 @@ populate_extable:
 			}
 			break;
 
+		case BPF_STX | BPF_ATOMIC | BPF_B:
+		case BPF_STX | BPF_ATOMIC | BPF_H:
+			if (!bpf_atomic_is_load_store(insn)) {
+				pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
+				return -EFAULT;
+			}
+			fallthrough;
 		case BPF_STX | BPF_ATOMIC | BPF_W:
 		case BPF_STX | BPF_ATOMIC | BPF_DW:
 			if (insn->imm == (BPF_AND | BPF_FETCH) ||
@@ -2148,10 +2254,10 @@ populate_extable:
 				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
 				      add_2reg(0xC0, AUX_REG, real_src_reg));
 				/* Attempt to swap in new value */
-				err = emit_atomic(&prog, BPF_CMPXCHG,
-						  real_dst_reg, AUX_REG,
-						  insn->off,
-						  BPF_SIZE(insn->code));
+				err = emit_atomic_rmw(&prog, BPF_CMPXCHG,
+						      real_dst_reg, AUX_REG,
+						      insn->off,
+						      BPF_SIZE(insn->code));
 				if (WARN_ON(err))
 					return err;
 				/*
@@ -2166,17 +2272,35 @@ populate_extable:
 				break;
 			}
 
-			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
-					  insn->off, BPF_SIZE(insn->code));
+			if (bpf_atomic_is_load_store(insn))
+				err = emit_atomic_ld_st(&prog, insn->imm, dst_reg, src_reg,
+							insn->off, BPF_SIZE(insn->code));
+			else
+				err = emit_atomic_rmw(&prog, insn->imm, dst_reg, src_reg,
+						      insn->off, BPF_SIZE(insn->code));
 			if (err)
 				return err;
 			break;
 
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
+			if (!bpf_atomic_is_load_store(insn)) {
+				pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n");
+				return -EFAULT;
+			}
+			fallthrough;
 		case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 		case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
 			start_of_ldx = prog;
-			err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code),
-						dst_reg, src_reg, X86_REG_R12, insn->off);
+
+			if (bpf_atomic_is_load_store(insn))
+				err = emit_atomic_ld_st_index(&prog, insn->imm,
+							      BPF_SIZE(insn->code), dst_reg,
+							      src_reg, X86_REG_R12, insn->off);
+			else
+				err = emit_atomic_rmw_index(&prog, insn->imm, BPF_SIZE(insn->code),
+							    dst_reg, src_reg, X86_REG_R12,
+							    insn->off);
 			if (err)
 				return err;
 			goto populate_extable;
@@ -2467,6 +2591,13 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
+			if (bpf_prog_was_classic(bpf_prog) &&
+			    !capable(CAP_SYS_ADMIN)) {
+				u8 *ip = image + addrs[i - 1];
+
+				if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
+					return -EINVAL;
+			}
 			if (bpf_prog->aux->exception_boundary) {
 				pop_callee_regs(&prog, all_callee_regs_used);
 				pop_r12(&prog);
@@ -3036,7 +3167,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
-		if (is_endbr(*(u32 *)orig_call))
+		if (is_endbr(orig_call))
 			orig_call += ENDBR_INSN_SIZE;
 		orig_call += X86_PATCH_SIZE;
 	}
@@ -3047,7 +3178,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/*
 		 * Indirect call for bpf_struct_ops
 		 */
-		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+		emit_cfi(&prog, image,
+			 cfi_get_func_hash(func_addr),
+			 cfi_get_func_arity(func_addr));
 	} else {
 		/*
 		 * Direct-call fentry stub, as such it needs accounting for the
@@ -3791,3 +3924,8 @@ u64 bpf_arch_uaddress_limit(void)
 {
 	return 0;
 }
+
+bool bpf_jit_supports_timed_may_goto(void)
+{
+	return true;
+}
diff --git a/arch/x86/net/bpf_timed_may_goto.S b/arch/x86/net/bpf_timed_may_goto.S
new file mode 100644
index 000000000000..54c690cae190
--- /dev/null
+++ b/arch/x86/net/bpf_timed_may_goto.S
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+
+	.code64
+	.section .text, "ax"
+
+SYM_FUNC_START(arch_bpf_timed_may_goto)
+	ANNOTATE_NOENDBR
+
+	/*
+	 * r10 passes us stack depth, load the pointer to count and timestamp
+	 * into r10 by adding it to BPF frame pointer.
+	 */
+	leaq (%rbp, %r10, 1), %r10
+
+	/* Setup frame. */
+	pushq %rbp
+	movq %rsp, %rbp
+
+	/* Save r0-r5. */
+	pushq %rax
+	pushq %rdi
+	pushq %rsi
+	pushq %rdx
+	pushq %rcx
+	pushq %r8
+
+	/*
+	 * r10 has the pointer to count and timestamp, pass it as first
+	 * argument.
+	 */
+	movq %r10, %rdi
+
+	/* Emit call depth accounting for call below. */
+	CALL_DEPTH_ACCOUNT
+	call bpf_check_timed_may_goto
+
+	/* BPF_REG_AX=r10 will be stored into count, so move return value to it. */
+	movq %rax, %r10
+
+	/* Restore r5-r0. */
+	popq %r8
+	popq %rcx
+	popq %rdx
+	popq %rsi
+	popq %rdi
+	popq %rax
+
+	leave
+	RET
+SYM_FUNC_END(arch_bpf_timed_may_goto)
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 48bcada5cabe..4933fb337983 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -12,8 +12,6 @@ obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 
-obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
-
 obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_pci.o
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 631512f7ec85..99b1727136c1 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -5,7 +5,7 @@
 #include <linux/cpu.h>
 #include <linux/range.h>
 
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
 #include <asm/pci_x86.h>
 
 #include <asm/pci-direct.h>
@@ -202,7 +202,7 @@ static int __init early_root_info_init(void)
 
 	/* need to take out [0, TOM) for RAM*/
 	address = MSR_K8_TOP_MEM1;
-	rdmsrl(address, val);
+	rdmsrq(address, val);
 	end = (val & 0xffffff800000ULL);
 	printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
 	if (end < (1ULL<<32))
@@ -293,12 +293,12 @@ static int __init early_root_info_init(void)
 	/* need to take out [4G, TOM2) for RAM*/
 	/* SYS_CFG */
 	address = MSR_AMD64_SYSCFG;
-	rdmsrl(address, val);
+	rdmsrq(address, val);
 	/* TOP_MEM2 is enabled? */
 	if (val & (1<<21)) {
 		/* TOP_MEM2 */
 		address = MSR_K8_TOP_MEM2;
-		rdmsrl(address, val);
+		rdmsrq(address, val);
 		end = (val & 0xffffff800000ULL);
 		printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
 		subtract_range(range, RANGE_NUM, 1ULL<<32, end);
@@ -341,10 +341,10 @@ static int amd_bus_cpu_online(unsigned int cpu)
 {
 	u64 reg;
 
-	rdmsrl(MSR_AMD64_NB_CFG, reg);
+	rdmsrq(MSR_AMD64_NB_CFG, reg);
 	if (!(reg & ENABLE_CF8_EXT_CFG)) {
 		reg |= ENABLE_CF8_EXT_CFG;
-		wrmsrl(MSR_AMD64_NB_CFG, reg);
+		wrmsrq(MSR_AMD64_NB_CFG, reg);
 	}
 	return 0;
 }
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index efefeb82ab61..36336299596b 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -9,7 +9,7 @@
 #include <linux/pci.h>
 #include <linux/suspend.h>
 #include <linux/vgaarb.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
 #include <asm/hpet.h>
 #include <asm/pci_x86.h>
 
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 39255f0eb14d..1f4522325920 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -22,9 +22,10 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/rculist.h>
+#include <asm/acpi.h>
 #include <asm/e820/api.h>
+#include <asm/msr.h>
 #include <asm/pci_x86.h>
-#include <asm/acpi.h>
 
 /* Indicate if the ECAM resources have been placed into the resource table */
 static bool pci_mmcfg_running_state;
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
deleted file mode 100644
index 8c8ddc4dcc08..000000000000
--- a/arch/x86/pci/sta2x11-fixup.c
+++ /dev/null
@@ -1,233 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping
- *
- * ST Microelectronics ConneXt (STA2X11/STA2X10)
- *
- * Copyright (c) 2010-2011 Wind River Systems, Inc.
- */
-
-#include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/export.h>
-#include <linux/list.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
-#include <asm/iommu.h>
-#include <asm/sta2x11.h>
-
-#define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-
-/*
- * We build a list of bus numbers that are under the ConneXt. The
- * main bridge hosts 4 busses, which are the 4 endpoints, in order.
- */
-#define STA2X11_NR_EP		4	/* 0..3 included */
-#define STA2X11_NR_FUNCS	8	/* 0..7 included */
-#define STA2X11_AMBA_SIZE	(512 << 20)
-
-struct sta2x11_ahb_regs { /* saved during suspend */
-	u32 base, pexlbase, pexhbase, crw;
-};
-
-struct sta2x11_mapping {
-	int is_suspended;
-	struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
-};
-
-struct sta2x11_instance {
-	struct list_head list;
-	int bus0;
-	struct sta2x11_mapping map[STA2X11_NR_EP];
-};
-
-static LIST_HEAD(sta2x11_instance_list);
-
-/* At probe time, record new instances of this bridge (likely one only) */
-static void sta2x11_new_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = kzalloc(sizeof(*instance), GFP_ATOMIC);
-	if (!instance)
-		return;
-	/* This has a subordinate bridge, with 4 more-subordinate ones */
-	instance->bus0 = pdev->subordinate->number + 1;
-
-	if (list_empty(&sta2x11_instance_list)) {
-		int size = STA2X11_SWIOTLB_SIZE;
-		/* First instance: register your own swiotlb area */
-		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size, GFP_DMA, NULL))
-			dev_emerg(&pdev->dev, "init swiotlb failed\n");
-	}
-	list_add(&instance->list, &sta2x11_instance_list);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, 0xcc17, sta2x11_new_instance);
-
-/*
- * Utility functions used in this file from below
- */
-static struct sta2x11_instance *sta2x11_pdev_to_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	list_for_each_entry(instance, &sta2x11_instance_list, list) {
-		ep = pdev->bus->number - instance->bus0;
-		if (ep >= 0 && ep < STA2X11_NR_EP)
-			return instance;
-	}
-	return NULL;
-}
-
-static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return -1;
-
-	return pdev->bus->number - instance->bus0;
-}
-
-/* This is exported, as some devices need to access the MFD registers */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
-{
-	return sta2x11_pdev_to_instance(pdev);
-}
-EXPORT_SYMBOL(sta2x11_get_instance);
-
-/* At setup time, we use our own ops if the device is a ConneXt one */
-static void sta2x11_setup_pdev(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-
-	if (!instance) /* either a sta2x11 bridge or another ST device */
-		return;
-
-	/* We must enable all devices as master, for audio DMA to work */
-	pci_set_master(pdev);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
-
-/*
- * At boot we must set up the mappings for the pcie-to-amba bridge.
- * It involves device access, and the same happens at suspend/resume time
- */
-
-#define AHB_MAPB		0xCA4
-#define AHB_CRW(i)		(AHB_MAPB + 0  + (i) * 0x10)
-#define AHB_CRW_SZMASK			0xfffffc00UL
-#define AHB_CRW_ENABLE			(1 << 0)
-#define AHB_CRW_WTYPE_MEM		(2 << 1)
-#define AHB_CRW_ROE			(1UL << 3)	/* Relax Order Ena */
-#define AHB_CRW_NSE			(1UL << 4)	/* No Snoop Enable */
-#define AHB_BASE(i)		(AHB_MAPB + 4  + (i) * 0x10)
-#define AHB_PEXLBASE(i)		(AHB_MAPB + 8  + (i) * 0x10)
-#define AHB_PEXHBASE(i)		(AHB_MAPB + 12 + (i) * 0x10)
-
-/* At probe time, enable mapping for each endpoint, using the pdev */
-static void sta2x11_map_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-	struct device *dev = &pdev->dev;
-	u32 amba_base, max_amba_addr;
-	int i, ret;
-
-	if (!instance)
-		return;
-
-	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
-	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
-
-	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
-	if (ret)
-		dev_err(dev, "sta2x11: could not set DMA offset\n");
-
-	dev->bus_dma_limit = max_amba_addr;
-	dma_set_mask_and_coherent(&pdev->dev, max_amba_addr);
-
-	/* Configure AHB mapping */
-	pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_PEXHBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_CRW(0), STA2X11_AMBA_SIZE |
-			       AHB_CRW_WTYPE_MEM | AHB_CRW_ENABLE);
-
-	/* Disable all the other windows */
-	for (i = 1; i < STA2X11_NR_FUNCS; i++)
-		pci_write_config_dword(pdev, AHB_CRW(i), 0);
-
-	dev_info(&pdev->dev,
-		 "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
-		 sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
-
-#ifdef CONFIG_PM /* Some register values must be saved and restored */
-
-static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return NULL;
-	ep = sta2x11_pdev_to_ep(pdev);
-	return instance->map + ep;
-}
-
-static void suspend_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-	if (map->is_suspended)
-		return;
-	map->is_suspended = 1;
-
-	/* Save all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_read_config_dword(pdev, AHB_BASE(i), &regs->base);
-		pci_read_config_dword(pdev, AHB_PEXLBASE(i), &regs->pexlbase);
-		pci_read_config_dword(pdev, AHB_PEXHBASE(i), &regs->pexhbase);
-		pci_read_config_dword(pdev, AHB_CRW(i), &regs->crw);
-	}
-}
-DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, suspend_mapping);
-
-static void resume_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-
-	if (!map->is_suspended)
-		goto out;
-	map->is_suspended = 0;
-
-	/* Restore all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_write_config_dword(pdev, AHB_BASE(i), regs->base);
-		pci_write_config_dword(pdev, AHB_PEXLBASE(i), regs->pexlbase);
-		pci_write_config_dword(pdev, AHB_PEXHBASE(i), regs->pexhbase);
-		pci_write_config_dword(pdev, AHB_CRW(i), regs->crw);
-	}
-out:
-	pci_set_master(pdev); /* Like at boot, enable master on all devices */
-}
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, resume_mapping);
-
-#endif /* CONFIG_PM */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 0f2fe524f60d..b8755cde2419 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -436,7 +436,8 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = {
 };
 
 static struct msi_domain_info xen_pci_msi_domain_info = {
-	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
+	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS |
+				  MSI_FLAG_DEV_SYSFS | MSI_FLAG_NO_MASK,
 	.ops			= &xen_pci_msi_domain_ops,
 };
 
@@ -484,11 +485,6 @@ static __init void xen_setup_pci_msi(void)
 	 * in allocating the native domain and never use it.
 	 */
 	x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain;
-	/*
-	 * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely
-	 * controlled by the hypervisor.
-	 */
-	pci_msi_ignore_mask = 1;
 }
 
 #else /* CONFIG_PCI_MSI */
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259a432b..e7e8f77f77f8 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
 	gfp_t gfp_mask;
 
 	gfp_mask = GFP_KERNEL | __GFP_ZERO;
-	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
 	if (!efi_pgd)
 		goto fail;
 
@@ -89,6 +89,7 @@ int __init efi_alloc_page_tables(void)
 	efi_mm.pgd = efi_pgd;
 	mm_init_cpumask(&efi_mm);
 	init_new_context(NULL, &efi_mm);
+	set_notrack_mm(&efi_mm);
 
 	return 0;
 
@@ -96,7 +97,7 @@ free_p4d:
 	if (pgtable_l5_enabled())
 		free_page((unsigned long)pgd_page_vaddr(*pgd));
 free_pgd:
-	free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)efi_pgd, pgd_allocation_order());
 fail:
 	return -ENOMEM;
 }
@@ -434,15 +435,12 @@ void __init efi_dump_pagetable(void)
  */
 static void efi_enter_mm(void)
 {
-	efi_prev_mm = current->active_mm;
-	current->active_mm = &efi_mm;
-	switch_mm(efi_prev_mm, &efi_mm, NULL);
+	efi_prev_mm = use_temporary_mm(&efi_mm);
 }
 
 static void efi_leave_mm(void)
 {
-	current->active_mm = efi_prev_mm;
-	switch_mm(&efi_mm, efi_prev_mm, NULL);
+	unuse_temporary_mm(efi_prev_mm);
 }
 
 void arch_efi_call_virt_setup(void)
diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
index c81cea208c2c..40ae94db20d8 100644
--- a/arch/x86/platform/intel/iosf_mbi.c
+++ b/arch/x86/platform/intel/iosf_mbi.c
@@ -422,19 +422,6 @@ int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
 }
 EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier_unlocked);
 
-int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
-{
-	int ret;
-
-	/* Wait for the bus to go inactive before unregistering */
-	iosf_mbi_punit_acquire();
-	ret = iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(nb);
-	iosf_mbi_punit_release();
-
-	return ret;
-}
-EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier);
-
 void iosf_mbi_assert_punit_acquired(void)
 {
 	WARN_ON(iosf_mbi_pmic_punit_access_count == 0);
diff --git a/arch/x86/platform/olpc/olpc-xo1-rtc.c b/arch/x86/platform/olpc/olpc-xo1-rtc.c
index 57f210cda761..ee77d57bcab7 100644
--- a/arch/x86/platform/olpc/olpc-xo1-rtc.c
+++ b/arch/x86/platform/olpc/olpc-xo1-rtc.c
@@ -64,9 +64,9 @@ static int __init xo1_rtc_init(void)
 	of_node_put(node);
 
 	pr_info("olpc-xo1-rtc: Initializing OLPC XO-1 RTC\n");
-	rdmsrl(MSR_RTC_DOMA_OFFSET, rtc_info.rtc_day_alarm);
-	rdmsrl(MSR_RTC_MONA_OFFSET, rtc_info.rtc_mon_alarm);
-	rdmsrl(MSR_RTC_CEN_OFFSET, rtc_info.rtc_century);
+	rdmsrq(MSR_RTC_DOMA_OFFSET, rtc_info.rtc_day_alarm);
+	rdmsrq(MSR_RTC_MONA_OFFSET, rtc_info.rtc_mon_alarm);
+	rdmsrq(MSR_RTC_CEN_OFFSET, rtc_info.rtc_century);
 
 	r = platform_device_register(&xo1_rtc_device);
 	if (r)
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index ccb23c73cbe8..30751b42d54e 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
-#include <linux/pm_wakeup.h>
 #include <linux/power_supply.h>
 #include <linux/suspend.h>
 #include <linux/workqueue.h>
@@ -326,7 +325,7 @@ static int setup_sci_interrupt(struct platform_device *pdev)
 		dev_info(&pdev->dev, "SCI unmapped. Mapping to IRQ 3\n");
 		sci_irq = 3;
 		lo |= 0x00300000;
-		wrmsrl(0x51400020, lo);
+		wrmsrq(0x51400020, lo);
 	}
 
 	/* Select level triggered in PIC */
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index cf5dca2dbb91..e108ce7dad6a 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -215,13 +215,12 @@ static u32 __init olpc_dt_get_board_revision(void)
 static int __init olpc_dt_compatible_match(phandle node, const char *compat)
 {
 	char buf[64], *p;
-	int plen, len;
+	int plen;
 
 	plen = olpc_dt_getproperty(node, "compatible", buf, sizeof(buf));
 	if (plen <= 0)
 		return 0;
 
-	len = strlen(compat);
 	for (p = buf; p < buf + plen; p += strlen(p) + 1) {
 		if (strcmp(p, compat) == 0)
 			return 1;
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 4733a5f467b8..1d78e5631bb8 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -87,8 +87,7 @@ SYM_CODE_START(pvh_start_xen)
 	mov %ebx, %esi
 	movl rva(pvh_start_info_sz)(%ebp), %ecx
 	shr $2,%ecx
-	rep
-	movsl
+	rep movsl
 
 	leal rva(early_stack_end)(%ebp), %esp
 
@@ -173,10 +172,14 @@ SYM_CODE_START(pvh_start_xen)
 1:
 	UNWIND_HINT_END_OF_STACK
 
-	/* Set base address in stack canary descriptor. */
-	mov $MSR_GS_BASE,%ecx
-	leal canary(%rip), %eax
-	xor %edx, %edx
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
+	movl $MSR_GS_BASE,%ecx
+	xorl %eax, %eax
+	xorl %edx, %edx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
@@ -238,8 +241,6 @@ SYM_DATA_START_LOCAL(gdt_start)
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
-SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
-
 SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 63230ff8cf4f..916441f5e85c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -27,6 +27,8 @@
 #include <asm/mmu_context.h>
 #include <asm/cpu_device_id.h>
 #include <asm/microcode.h>
+#include <asm/msr.h>
+#include <asm/fred.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -43,7 +45,7 @@ static void msr_save_context(struct saved_context *ctxt)
 
 	while (msr < end) {
 		if (msr->valid)
-			rdmsrl(msr->info.msr_no, msr->info.reg.q);
+			rdmsrq(msr->info.msr_no, msr->info.reg.q);
 		msr++;
 	}
 }
@@ -55,7 +57,7 @@ static void msr_restore_context(struct saved_context *ctxt)
 
 	while (msr < end) {
 		if (msr->valid)
-			wrmsrl(msr->info.msr_no, msr->info.reg.q);
+			wrmsrq(msr->info.msr_no, msr->info.reg.q);
 		msr++;
 	}
 }
@@ -109,12 +111,12 @@ static void __save_processor_state(struct saved_context *ctxt)
 	savesegment(ds, ctxt->ds);
 	savesegment(es, ctxt->es);
 
-	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
-	rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
-	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+	rdmsrq(MSR_FS_BASE, ctxt->fs_base);
+	rdmsrq(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+	rdmsrq(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
 	mtrr_save_fixed_ranges(NULL);
 
-	rdmsrl(MSR_EFER, ctxt->efer);
+	rdmsrq(MSR_EFER, ctxt->efer);
 #endif
 
 	/*
@@ -124,7 +126,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 	ctxt->cr2 = read_cr2();
 	ctxt->cr3 = __read_cr3();
 	ctxt->cr4 = __read_cr4();
-	ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+	ctxt->misc_enable_saved = !rdmsrq_safe(MSR_IA32_MISC_ENABLE,
 					       &ctxt->misc_enable);
 	msr_save_context(ctxt);
 }
@@ -197,7 +199,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	struct cpuinfo_x86 *c;
 
 	if (ctxt->misc_enable_saved)
-		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
+		wrmsrq(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
 	 * control registers
 	 */
@@ -207,7 +209,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 		__write_cr4(ctxt->cr4);
 #else
 /* CONFIG X86_64 */
-	wrmsrl(MSR_EFER, ctxt->efer);
+	wrmsrq(MSR_EFER, ctxt->efer);
 	__write_cr4(ctxt->cr4);
 #endif
 	write_cr3(ctxt->cr3);
@@ -230,7 +232,20 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	 * handlers or in complicated helpers like load_gs_index().
 	 */
 #ifdef CONFIG_X86_64
-	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+	wrmsrq(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+
+	/*
+	 * Reinitialize FRED to ensure the FRED MSRs contain the same values
+	 * as before hibernation.
+	 *
+	 * Note, the setup of FRED RSPs requires access to percpu data
+	 * structures.  Therefore, FRED reinitialization can only occur after
+	 * the percpu access pointer (i.e., MSR_GS_BASE) is restored.
+	 */
+	if (ctxt->cr4 & X86_CR4_FRED) {
+		cpu_init_fred_exceptions();
+		cpu_init_fred_rsps();
+	}
 #else
 	loadsegment(fs, __KERNEL_PERCPU);
 #endif
@@ -253,8 +268,8 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	 * restoring the selectors clobbers the bases.  Keep in mind
 	 * that MSR_KERNEL_GS_BASE is horribly misnamed.
 	 */
-	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+	wrmsrq(MSR_FS_BASE, ctxt->fs_base);
+	wrmsrq(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
 #else
 	loadsegment(gs, ctxt->gs);
 #endif
@@ -400,7 +415,7 @@ static int msr_build_context(const u32 *msr_id, const int num)
 		u64 dummy;
 
 		msr_array[i].info.msr_no	= msr_id[j];
-		msr_array[i].valid		= !rdmsrl_safe(msr_id[j], &dummy);
+		msr_array[i].valid		= !rdmsrq_safe(msr_id[j], &dummy);
 		msr_array[i].info.reg.q		= 0;
 	}
 	saved_msrs->num   = total_num;
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index 5b81d19cd114..a7c23f2a58c9 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -42,6 +42,7 @@ unsigned long relocated_restore_code __visible;
 
 /**
  *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ *	@pfn: the page frame number to check.
  */
 int pfn_is_nosave(unsigned long pfn)
 {
@@ -86,7 +87,10 @@ static inline u32 compute_e820_crc32(struct e820_table *table)
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
  *		of a hibernation image header
- *	@addr: address to save the data at
+ *	@addr: address where architecture specific header data will be saved.
+ *	@max_size: maximum size of architecture specific data in hibernation header.
+ *
+ *	Return: 0 on success, -EOVERFLOW if max_size is insufficient.
  */
 int arch_hibernation_header_save(void *addr, unsigned int max_size)
 {
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 5606a15cf9a1..fb910d9f8471 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -69,8 +69,7 @@ copy_loop:
 	movl	pbe_orig_address(%edx), %edi
 
 	movl	$(PAGE_SIZE >> 2), %ecx
-	rep
-	movsl
+	rep movsl
 
 	movl	pbe_next(%edx), %edx
 	jmp	copy_loop
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0a0539e1cc81..c73be0a02a6c 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,6 +26,7 @@
 	 /* code below belongs to the image kernel */
 	.align PAGE_SIZE
 SYM_FUNC_START(restore_registers)
+	ENDBR
 	/* go back to the original page tables */
 	movq    %r9, %cr3
 
@@ -119,6 +120,7 @@ SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
 SYM_FUNC_START(core_restore_code)
+	ENDBR
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
@@ -136,8 +138,7 @@ SYM_FUNC_START(core_restore_code)
 	movq	pbe_address(%rdx), %rsi
 	movq	pbe_orig_address(%rdx), %rdi
 	movq	$(PAGE_SIZE >> 3), %rcx
-	rep
-	movsq
+	rep movsq
 
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index f9bc444a3064..ed5c63c0b4e5 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -9,6 +9,7 @@
 #include <asm/realmode.h>
 #include <asm/tlbflush.h>
 #include <asm/crash.h>
+#include <asm/msr.h>
 #include <asm/sev.h>
 
 struct real_mode_header *real_mode_header;
@@ -145,7 +146,7 @@ static void __init setup_real_mode(void)
 	 * Some AMD processors will #GP(0) if EFER.LMA is set in WRMSR
 	 * so we need to mask it out.
 	 */
-	rdmsrl(MSR_EFER, efer);
+	rdmsrq(MSR_EFER, efer);
 	trampoline_header->efer = efer & ~EFER_LMA;
 
 	trampoline_header->start = (u64) secondary_startup_64;
diff --git a/arch/x86/realmode/rm/realmode.h b/arch/x86/realmode/rm/realmode.h
index c76041a35397..867e55f1d6af 100644
--- a/arch/x86/realmode/rm/realmode.h
+++ b/arch/x86/realmode/rm/realmode.h
@@ -2,7 +2,7 @@
 #ifndef ARCH_X86_REALMODE_RM_REALMODE_H
 #define ARCH_X86_REALMODE_RM_REALMODE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * 16-bit ljmpw to the real_mode_seg
@@ -12,7 +12,7 @@
  */
 #define LJMPW_RM(to)	.byte 0xea ; .word (to), real_mode_seg
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Signature at the end of the realmode region
diff --git a/arch/x86/realmode/rm/wakeup.h b/arch/x86/realmode/rm/wakeup.h
index 0e4fd08ae447..3b6d8fa82d3e 100644
--- a/arch/x86/realmode/rm/wakeup.h
+++ b/arch/x86/realmode/rm/wakeup.h
@@ -7,7 +7,7 @@
 #ifndef ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H
 #define ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 /* This must match data at wakeup.S */
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
new file mode 100755
index 000000000000..173d5bf2d999
--- /dev/null
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -0,0 +1,88 @@
+#!/usr/bin/awk
+#
+# Convert cpufeatures.h to a list of compile-time masks
+# Note: this blithely assumes that each word has at least one
+# feature defined in it; if not, something else is wrong!
+#
+
+BEGIN {
+	printf "#ifndef _ASM_X86_CPUFEATUREMASKS_H\n";
+	printf "#define _ASM_X86_CPUFEATUREMASKS_H\n\n";
+
+	file = 0
+}
+
+FNR == 1 {
+	++file;
+
+	# arch/x86/include/asm/cpufeatures.h
+	if (file == 1)
+		FS = "[ \t()*+]+";
+
+	# .config
+	if (file == 2)
+		FS = "=";
+}
+
+# Create a dictionary of sorts, containing all defined feature bits
+file == 1 && $1 ~ /^#define$/ && $2 ~ /^X86_FEATURE_/ {
+	nfeat = $3 * $4 + $5;
+	feat = $2;
+	sub(/^X86_FEATURE_/, "", feat);
+	feats[nfeat] = feat;
+}
+file == 1 && $1 ~ /^#define$/ && $2 == "NCAPINTS" {
+	ncapints = int($3);
+}
+
+# Create a dictionary featstat[REQUIRED|DISABLED, FEATURE_NAME] = on | off
+file == 2 && $1 ~ /^CONFIG_X86_(REQUIRED|DISABLED)_FEATURE_/ {
+	on = ($2 == "y");
+	if (split($1, fs, "CONFIG_X86_|_FEATURE_") == 3)
+		featstat[fs[2], fs[3]] = on;
+}
+
+END {
+	sets[1] = "REQUIRED";
+	sets[2] = "DISABLED";
+
+	for (ns in sets) {
+		s = sets[ns];
+
+		printf "/*\n";
+		printf " * %s features:\n", s;
+		printf " *\n";
+		fstr = "";
+		for (i = 0; i < ncapints; i++) {
+			mask = 0;
+			for (j = 0; j < 32; j++) {
+				feat = feats[i*32 + j];
+				if (featstat[s, feat]) {
+					nfstr = fstr " " feat;
+					if (length(nfstr) > 72) {
+						printf " *   %s\n", fstr;
+						nfstr = " " feat;
+					}
+					fstr = nfstr;
+					mask += (2 ^ j);
+				}
+			}
+			masks[i] = mask;
+		}
+		printf " *   %s\n */\n", fstr;
+
+		for (i = 0; i < ncapints; i++)
+			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
+
+		printf "\n#define %s_MASK_BIT_SET(x)\t\t\t\\\n", s;
+		printf "\t((\t\t\t\t\t";
+		for (i = 0; i < ncapints; i++) {
+			if (masks[i])
+				printf "\t\\\n\t\t((x) >> 5) == %2d ? %s_MASK%d :", i, s, i;
+		}
+		printf " 0\t\\\n";
+		printf "\t) & (1U << ((x) & 31)))\n\n";
+	}
+
+	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";
+}
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5770c8097f32..2c19d7fc8a85 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -64,6 +64,8 @@ BEGIN {
 
 	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
 	force64_expr = "\\([df]64\\)"
+	invalid64_expr = "\\(i64\\)"
+	only64_expr = "\\(o64\\)"
 	rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
 	rex2_expr = "\\(REX2\\)"
 	no_rex2_expr = "\\(!REX2\\)"
@@ -319,6 +321,11 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, force64_expr))
 			flags = add_flags(flags, "INAT_FORCE64")
 
+		# check invalid in 64-bit (and no only64)
+		if (match(ext, invalid64_expr) &&
+		    !match($0, only64_expr))
+			flags = add_flags(flags, "INAT_INV64")
+
 		# check REX2 not allowed
 		if (match(ext, no_rex2_expr))
 			flags = add_flags(flags, "INAT_NO_REX2")
diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c
index 472540aeabc2..08cd913cbd4e 100644
--- a/arch/x86/tools/insn_decoder_test.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -10,8 +10,7 @@
 #include <assert.h>
 #include <unistd.h>
 #include <stdarg.h>
-
-#define unlikely(cond) (cond)
+#include <linux/kallsyms.h>
 
 #include <asm/insn.h>
 #include <inat.c>
@@ -106,7 +105,7 @@ static void parse_args(int argc, char **argv)
 	}
 }
 
-#define BUFSIZE 256
+#define BUFSIZE (256 + KSYM_NAME_LEN)
 
 int main(int argc, char **argv)
 {
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e937be979ec8..5778bc498415 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,9 +29,13 @@ static struct relocs		relocs16;
 static struct relocs		relocs32;
 
 #if ELF_BITS == 64
-static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
 #else
 # define FMT PRIu32
 #endif
@@ -86,8 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"
@@ -227,6 +229,7 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_X86_64_PC16),
 		REL_TYPE(R_X86_64_8),
 		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
 #else
 		REL_TYPE(R_386_NONE),
 		REL_TYPE(R_386_32),
@@ -284,34 +287,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 	return name;
 }
 
-static Elf_Sym *sym_lookup(const char *symname)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		struct section *sec = &secs[i];
-		long nsyms;
-		char *strtab;
-		Elf_Sym *symtab;
-		Elf_Sym *sym;
-
-		if (sec->shdr.sh_type != SHT_SYMTAB)
-			continue;
-
-		nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
-		symtab = sec->symtab;
-		strtab = sec->link->strtab;
-
-		for (sym = symtab; --nsyms >= 0; sym++) {
-			if (!sym->st_name)
-				continue;
-			if (strcmp(symname, strtab + sym->st_name) == 0)
-				return sym;
-		}
-	}
-	return 0;
-}
-
 #if BYTE_ORDER == LITTLE_ENDIAN
 # define le16_to_cpu(val)	(val)
 # define le32_to_cpu(val)	(val)
@@ -760,84 +735,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 	}
 }
 
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- *	Relocations that reference symbols in the per_cpu area do not
- *	need further relocation (since the value is an offset relative
- *	to the start of the per_cpu area that does not change).
- *
- *	Relocations that apply to the per_cpu area need to have their
- *	offset adjusted by by the value of __per_cpu_load to make them
- *	point to the correct place in the loaded image (because the
- *	virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		ElfW(Sym) *sym;
-
-		if (strcmp(sec_name(i), ".data..percpu"))
-			continue;
-
-		if (secs[i].shdr.sh_addr != 0)	/* non SMP kernel */
-			return;
-
-		sym = sym_lookup("__per_cpu_load");
-		if (!sym)
-			die("can't find __per_cpu_load\n");
-
-		per_cpu_shndx = i;
-		per_cpu_load_addr = sym->st_value;
-
-		return;
-	}
-}
-
 #if ELF_BITS == 64
 
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- *	__init_begin
- *	__per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- *	init_per_cpu__fixed_percpu_data
- *	init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
-	int shndx = sym_index(sym);
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
-}
-
-
 static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 		      const char *symname)
 {
@@ -848,12 +747,6 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	if (sym->st_shndx == SHN_UNDEF)
 		return 0;
 
-	/*
-	 * Adjust the offset if this reloc applies to the percpu section.
-	 */
-	if (sec->shdr.sh_info == per_cpu_shndx)
-		offset += per_cpu_load_addr;
-
 	switch (r_type) {
 	case R_X86_64_NONE:
 		/* NONE can be ignored. */
@@ -861,33 +754,23 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 
 	case R_X86_64_PC32:
 	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
 		/*
-		 * PC relative relocations don't need to be adjusted unless
-		 * referencing a percpu symbol.
+		 * PC relative relocations don't need to be adjusted.
 		 *
 		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
-		if (is_percpu_sym(sym, symname))
-			add_reloc(&relocs32neg, offset);
 		break;
 
 	case R_X86_64_PC64:
 		/*
 		 * Only used by jump labels
 		 */
-		if (is_percpu_sym(sym, symname))
-			die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
 		break;
 
 	case R_X86_64_32:
 	case R_X86_64_32S:
 	case R_X86_64_64:
-		/*
-		 * References to the percpu area don't need to be adjusted.
-		 */
-		if (is_percpu_sym(sym, symname))
-			break;
-
 		if (shn_abs) {
 			/*
 			 * Whitelisted absolute symbols do not require
@@ -1055,7 +938,8 @@ static int cmp_relocs(const void *va, const void *vb)
 
 static void sort_relocs(struct relocs *r)
 {
-	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
 }
 
 static int write32(uint32_t v, FILE *f)
@@ -1099,7 +983,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
@@ -1131,13 +1014,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 		/* Now print each relocation */
 		for (i = 0; i < relocs64.count; i++)
 			write_reloc(relocs64.offset[i], stdout);
-
-		/* Print a stop */
-		write_reloc(0, stdout);
-
-		/* Now print each inverse 32-bit relocation */
-		for (i = 0; i < relocs32neg.count; i++)
-			write_reloc(relocs32neg.offset[i], stdout);
 #endif
 
 		/* Print a stop */
@@ -1190,9 +1066,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
 	read_symtabs(fp);
 	read_relocs(fp);
 
-	if (ELF_BITS == 64)
-		percpu_init();
-
 	if (show_absolute_syms) {
 		print_absolute_symbols();
 		return;
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 4da336965698..b51aefd6ec2b 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -12,9 +12,9 @@
  */
 #ifdef CONFIG_X86_32
 
-#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define mb()	alternative("lock addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb()	alternative("lock addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
 
 #else /* CONFIG_X86_32 */
 
diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h
deleted file mode 100644
index a3b061d66082..000000000000
--- a/arch/x86/um/asm/module.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_MODULE_H
-#define __UM_MODULE_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#ifdef CONFIG_X86_32
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#else
-
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-
-#endif
-
-#endif
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
index e80ab7d28117..37decaa74761 100644
--- a/arch/x86/um/os-Linux/mcontext.c
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -4,6 +4,7 @@
 #include <asm/ptrace.h>
 #include <sysdep/ptrace.h>
 #include <sysdep/mcontext.h>
+#include <arch.h>
 
 void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 {
@@ -27,7 +28,17 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
 	COPY(RIP);
 	COPY2(EFLAGS, EFL);
 	COPY2(CS, CSGSFS);
-	regs->gp[CS / sizeof(unsigned long)] &= 0xffff;
-	regs->gp[CS / sizeof(unsigned long)] |= 3;
+	regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48;
+#endif
+}
+
+void mc_set_rip(void *_mc, void *target)
+{
+	mcontext_t *mc = _mc;
+
+#ifdef __i386__
+	mc->gregs[REG_EIP] = (unsigned long)target;
+#else
+	mc->gregs[REG_RIP] = (unsigned long)target;
 #endif
 }
diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index b6f2437ec29c..9193a7790a71 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_32.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -29,4 +29,16 @@ struct faultinfo {
 
 #define PTRACE_FULL_FAULTINFO 0
 
+#define ___backtrack_faulted(_faulted)					\
+	asm volatile (							\
+		"movl $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
+		"jmp _end_%=\n"						\
+		"__get_kernel_nofault_faulted_%=:\n"			\
+		"mov $1, %0;"						\
+		"_end_%=:"						\
+		: "=r" (_faulted),					\
+		  "=m" (current->thread.segv_continue) ::		\
+	)
+
 #endif
diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index ee88f88974ea..61e4ca1e0ab5 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_64.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -29,4 +29,16 @@ struct faultinfo {
 
 #define PTRACE_FULL_FAULTINFO 1
 
+#define ___backtrack_faulted(_faulted)					\
+	asm volatile (							\
+		"movq $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
+		"jmp _end_%=\n"						\
+		"__get_kernel_nofault_faulted_%=:\n"			\
+		"mov $1, %0;"						\
+		"_end_%=:"						\
+		: "=r" (_faulted),					\
+		  "=m" (current->thread.segv_continue) ::		\
+	)
+
 #endif
diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c
index f238f7b33cdd..dc8dfb2abd80 100644
--- a/arch/x86/um/vdso/vma.c
+++ b/arch/x86/um/vdso/vma.c
@@ -12,33 +12,22 @@
 
 static unsigned int __read_mostly vdso_enabled = 1;
 unsigned long um_vdso_addr;
+static struct page *um_vdso;
 
 extern unsigned long task_size;
 extern char vdso_start[], vdso_end[];
 
-static struct page **vdsop;
-
 static int __init init_vdso(void)
 {
-	struct page *um_vdso;
-
 	BUG_ON(vdso_end - vdso_start > PAGE_SIZE);
 
 	um_vdso_addr = task_size - PAGE_SIZE;
 
-	vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL);
-	if (!vdsop)
-		goto oom;
-
 	um_vdso = alloc_page(GFP_KERNEL);
-	if (!um_vdso) {
-		kfree(vdsop);
-
+	if (!um_vdso)
 		goto oom;
-	}
 
 	copy_page(page_address(um_vdso), vdso_start);
-	*vdsop = um_vdso;
 
 	return 0;
 
@@ -56,6 +45,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	struct mm_struct *mm = current->mm;
 	static struct vm_special_mapping vdso_mapping = {
 		.name = "[vdso]",
+		.pages = &um_vdso,
 	};
 
 	if (!vdso_enabled)
@@ -64,7 +54,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	vdso_mapping.pages = vdsop;
 	vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE,
 		VM_READ|VM_EXEC|
 		VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 42e74a5a7d78..942372e69b4d 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -27,9 +27,10 @@
 #include <asm/smp.h>
 #include <asm/cpu.h>
 #include <asm/apic.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/cmdline.h>
 #include <asm/iommu.h>
+#include <asm/msr.h>
 
 /*
  * The RMP entry information as returned by the RMPREAD instruction.
@@ -136,11 +137,11 @@ static int __mfd_enable(unsigned int cpu)
 	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
 		return 0;
 
-	rdmsrl(MSR_AMD64_SYSCFG, val);
+	rdmsrq(MSR_AMD64_SYSCFG, val);
 
 	val |= MSR_AMD64_SYSCFG_MFDM;
 
-	wrmsrl(MSR_AMD64_SYSCFG, val);
+	wrmsrq(MSR_AMD64_SYSCFG, val);
 
 	return 0;
 }
@@ -157,12 +158,12 @@ static int __snp_enable(unsigned int cpu)
 	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
 		return 0;
 
-	rdmsrl(MSR_AMD64_SYSCFG, val);
+	rdmsrq(MSR_AMD64_SYSCFG, val);
 
 	val |= MSR_AMD64_SYSCFG_SNP_EN;
 	val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN;
 
-	wrmsrl(MSR_AMD64_SYSCFG, val);
+	wrmsrq(MSR_AMD64_SYSCFG, val);
 
 	return 0;
 }
@@ -198,7 +199,6 @@ static void __init __snp_fixup_e820_tables(u64 pa)
 		pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
 		e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
-		e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		if (!memblock_is_region_reserved(pa, PMD_SIZE))
 			memblock_reserve(pa, PMD_SIZE);
 	}
@@ -523,7 +523,7 @@ int __init snp_rmptable_init(void)
 	 * Check if SEV-SNP is already enabled, this can happen in case of
 	 * kexec boot.
 	 */
-	rdmsrl(MSR_AMD64_SYSCFG, val);
+	rdmsrq(MSR_AMD64_SYSCFG, val);
 	if (val & MSR_AMD64_SYSCFG_SNP_EN)
 		goto skip_enable;
 
@@ -577,8 +577,8 @@ static bool probe_contiguous_rmptable_info(void)
 {
 	u64 rmp_sz, rmp_base, rmp_end;
 
-	rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
-	rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+	rdmsrq(MSR_AMD64_RMP_BASE, rmp_base);
+	rdmsrq(MSR_AMD64_RMP_END, rmp_end);
 
 	if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) {
 		pr_err("Memory for the RMP table has not been reserved by BIOS\n");
@@ -611,13 +611,13 @@ static bool probe_segmented_rmptable_info(void)
 	unsigned int eax, ebx, segment_shift, segment_shift_min, segment_shift_max;
 	u64 rmp_base, rmp_end;
 
-	rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
+	rdmsrq(MSR_AMD64_RMP_BASE, rmp_base);
 	if (!(rmp_base & RMP_ADDR_MASK)) {
 		pr_err("Memory for the RMP table has not been reserved by BIOS\n");
 		return false;
 	}
 
-	rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+	rdmsrq(MSR_AMD64_RMP_END, rmp_end);
 	WARN_ONCE(rmp_end & RMP_ADDR_MASK,
 		  "Segmented RMP enabled but RMP_END MSR is non-zero\n");
 
@@ -653,7 +653,7 @@ static bool probe_segmented_rmptable_info(void)
 bool snp_probe_rmptable_info(void)
 {
 	if (cpu_feature_enabled(X86_FEATURE_SEGMENTED_RMP))
-		rdmsrl(MSR_AMD64_RMP_CFG, rmp_cfg);
+		rdmsrq(MSR_AMD64_RMP_CFG, rmp_cfg);
 
 	if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED)
 		return probe_segmented_rmptable_info();
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 77e788e928cd..98d8a50d2aed 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,7 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MATOM)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 43dcd8c7badc..53282dc7d5ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -70,6 +70,9 @@ EXPORT_SYMBOL(xen_start_flags);
  */
 struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
 
+/* Number of pages released from the initial allocation. */
+unsigned long xen_released_pages;
+
 static __ref void xen_get_vendor(void)
 {
 	init_cpu_devs();
@@ -100,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void)
 	void (*func)(void);
 
 	/*
-	 * Xen is supported only on CPUs with CPUID, so testing for
-	 * X86_FEATURE_CPUID is a test for early_cpu_init() having been
-	 * run.
-	 *
 	 * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
 	 * dependency chain: it is being called via the xen_hypercall static
 	 * call when running as a PVH or HVM guest. Hypercalls need to be
@@ -115,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void)
 	 */
 	instrumentation_begin();
 
-	if (!boot_cpu_has(X86_FEATURE_CPUID))
-		xen_get_vendor();
+	xen_get_vendor();
 
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 	     boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
@@ -466,6 +464,13 @@ int __init arch_xen_unpopulated_init(struct resource **res)
 			xen_free_unpopulated_pages(1, &pg);
 		}
 
+		/*
+		 * Account for the region being in the physmap but unpopulated.
+		 * The value in xen_released_pages is used by the balloon
+		 * driver to know how much of the physmap is unpopulated and
+		 * set an accurate initial memory target.
+		 */
+		xen_released_pages += xen_extra_mem[i].n_pfns;
 		/* Zero so region is not also added to the balloon driver. */
 		xen_extra_mem[i].n_pfns = 0;
 	}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5e57835e999d..26bbaf4b7330 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -49,7 +49,7 @@
 #include <xen/hvc-console.h>
 #include <xen/acpi.h>
 
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
 #include <asm/paravirt.h>
 #include <asm/apic.h>
 #include <asm/page.h>
@@ -61,6 +61,7 @@
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/msr-index.h>
+#include <asm/msr.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
@@ -73,6 +74,7 @@
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/cpu.h>
+#include <asm/irq_stack.h>
 #ifdef CONFIG_X86_IOPL_IOPERM
 #include <asm/io_bitmap.h>
 #endif
@@ -94,12 +96,49 @@ void *xen_initial_gdt;
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
 static int xen_cpu_dead_pv(unsigned int cpu);
 
+#ifndef CONFIG_PREEMPTION
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+/*
+ * In case of scheduling the flag must be cleared and restored after
+ * returning from schedule as the task might move to a different CPU.
+ */
+static __always_inline bool get_and_clear_inhcall(void)
+{
+	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
+
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+	return inhcall;
+}
+
+static __always_inline void restore_inhcall(bool inhcall)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
+}
+
+#else
+
+static __always_inline bool get_and_clear_inhcall(void) { return false; }
+static __always_inline void restore_inhcall(bool inhcall) { }
+
+#endif
+
 struct tls_descs {
 	struct desc_struct desc[3];
 };
 
 DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE;
-DEFINE_PER_CPU(unsigned int, xen_lazy_nesting);
 
 enum xen_lazy_mode xen_get_lazy_mode(void)
 {
@@ -687,6 +726,36 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check)
 }
 #endif
 
+static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	xen_evtchn_do_upcall();
+
+	set_irq_regs(old_regs);
+}
+
+__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+	bool inhcall;
+
+	instrumentation_begin();
+	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
+
+	inhcall = get_and_clear_inhcall();
+	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
+		irqentry_exit_cond_resched();
+		instrumentation_end();
+		restore_inhcall(inhcall);
+	} else {
+		instrumentation_end();
+		irqentry_exit(regs, state);
+	}
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -1018,15 +1087,15 @@ static void xen_write_cr4(unsigned long cr4)
 	native_write_cr4(cr4);
 }
 
-static u64 xen_do_read_msr(unsigned int msr, int *err)
+static u64 xen_do_read_msr(u32 msr, int *err)
 {
 	u64 val = 0;	/* Avoid uninitialized value for safe variant. */
 
-	if (pmu_msr_read(msr, &val, err))
+	if (pmu_msr_chk_emulated(msr, &val, true))
 		return val;
 
 	if (err)
-		val = native_read_msr_safe(msr, err);
+		*err = native_read_msr_safe(msr, &val);
 	else
 		val = native_read_msr(msr);
 
@@ -1042,17 +1111,9 @@ static u64 xen_do_read_msr(unsigned int msr, int *err)
 	return val;
 }
 
-static void set_seg(unsigned int which, unsigned int low, unsigned int high,
-		    int *err)
+static void set_seg(u32 which, u64 base)
 {
-	u64 base = ((u64)high << 32) | low;
-
-	if (HYPERVISOR_set_segment_base(which, base) == 0)
-		return;
-
-	if (err)
-		*err = -EIO;
-	else
+	if (HYPERVISOR_set_segment_base(which, base))
 		WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base);
 }
 
@@ -1061,20 +1122,19 @@ static void set_seg(unsigned int which, unsigned int low, unsigned int high,
  * With err == NULL write_msr() semantics are selected.
  * Supplying an err pointer requires err to be pre-initialized with 0.
  */
-static void xen_do_write_msr(unsigned int msr, unsigned int low,
-			     unsigned int high, int *err)
+static void xen_do_write_msr(u32 msr, u64 val, int *err)
 {
 	switch (msr) {
 	case MSR_FS_BASE:
-		set_seg(SEGBASE_FS, low, high, err);
+		set_seg(SEGBASE_FS, val);
 		break;
 
 	case MSR_KERNEL_GS_BASE:
-		set_seg(SEGBASE_GS_USER, low, high, err);
+		set_seg(SEGBASE_GS_USER, val);
 		break;
 
 	case MSR_GS_BASE:
-		set_seg(SEGBASE_GS_KERNEL, low, high, err);
+		set_seg(SEGBASE_GS_KERNEL, val);
 		break;
 
 	case MSR_STAR:
@@ -1090,42 +1150,45 @@ static void xen_do_write_msr(unsigned int msr, unsigned int low,
 		break;
 
 	default:
-		if (!pmu_msr_write(msr, low, high, err)) {
-			if (err)
-				*err = native_write_msr_safe(msr, low, high);
-			else
-				native_write_msr(msr, low, high);
-		}
+		if (pmu_msr_chk_emulated(msr, &val, false))
+			return;
+
+		if (err)
+			*err = native_write_msr_safe(msr, val);
+		else
+			native_write_msr(msr, val);
 	}
 }
 
-static u64 xen_read_msr_safe(unsigned int msr, int *err)
+static int xen_read_msr_safe(u32 msr, u64 *val)
 {
-	return xen_do_read_msr(msr, err);
+	int err = 0;
+
+	*val = xen_do_read_msr(msr, &err);
+	return err;
 }
 
-static int xen_write_msr_safe(unsigned int msr, unsigned int low,
-			      unsigned int high)
+static int xen_write_msr_safe(u32 msr, u64 val)
 {
 	int err = 0;
 
-	xen_do_write_msr(msr, low, high, &err);
+	xen_do_write_msr(msr, val, &err);
 
 	return err;
 }
 
-static u64 xen_read_msr(unsigned int msr)
+static u64 xen_read_msr(u32 msr)
 {
-	int err;
+	int err = 0;
 
 	return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL);
 }
 
-static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+static void xen_write_msr(u32 msr, u64 val)
 {
 	int err;
 
-	xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL);
+	xen_do_write_msr(msr, val, xen_msr_safe ? &err : NULL);
 }
 
 /* This is called once we have the cpu_possible_mask */
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 0e3d930bcb89..9d25d9373945 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/acpi.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 
@@ -123,8 +125,23 @@ static void __init pvh_arch_setup(void)
 {
 	pvh_reserve_extra_memory();
 
-	if (xen_initial_domain())
+	if (xen_initial_domain()) {
 		xen_add_preferred_consoles();
+
+		/*
+		 * Disable usage of CPU idle and frequency drivers: when
+		 * running as hardware domain the exposed native ACPI tables
+		 * causes idle and/or frequency drivers to attach and
+		 * malfunction.  It's Xen the entity that controls the idle and
+		 * frequency states.
+		 *
+		 * For unprivileged domains the exposed ACPI tables are
+		 * fabricated and don't contain such data.
+		 */
+		disable_cpuidle();
+		disable_cpufreq();
+		WARN_ON(xen_set_default_idle());
+	}
 }
 
 void __init xen_pvh_init(struct boot_params *boot_params)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d078de2c952b..2a4a8deaf612 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -578,7 +578,6 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 	xen_mc_issue(XEN_LAZY_MMU);
 }
 
-#if CONFIG_PGTABLE_LEVELS >= 5
 __visible p4dval_t xen_p4d_val(p4d_t p4d)
 {
 	return pte_mfn_to_pfn(p4d.p4d);
@@ -592,7 +591,6 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d)
 	return native_make_p4d(p4d);
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
-#endif  /* CONFIG_PGTABLE_LEVELS >= 5 */
 
 static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
 			 void (*func)(struct mm_struct *mm, struct page *,
@@ -2189,7 +2187,6 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.flush_tlb_kernel = xen_flush_tlb,
 		.flush_tlb_one_user = xen_flush_tlb_one_user,
 		.flush_tlb_multi = xen_flush_tlb_multi,
-		.tlb_remove_table = tlb_remove_table,
 
 		.pgd_alloc = xen_pgd_alloc,
 		.pgd_free = xen_pgd_free,
@@ -2223,10 +2220,8 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.alloc_pud = xen_alloc_pmd_init,
 		.release_pud = xen_release_pmd_init,
 
-#if CONFIG_PGTABLE_LEVELS >= 5
 		.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
 		.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
-#endif
 
 		.enter_mmap = xen_enter_mmap,
 		.exit_mmap = xen_exit_mmap,
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 10c660fae8b3..7237d56a9d3f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,14 +54,20 @@ struct mc_debug_data {
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 static struct mc_debug_data mc_debug_data_early __initdata;
-static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
-	&mc_debug_data_early;
 static struct mc_debug_data __percpu *mc_debug_data_ptr;
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 static struct static_key mc_debug __ro_after_init;
 static bool mc_debug_enabled __initdata;
 
+static struct mc_debug_data * __ref get_mc_debug(void)
+{
+	if (!mc_debug_data_ptr)
+		return &mc_debug_data_early;
+
+	return this_cpu_ptr(mc_debug_data_ptr);
+}
+
 static int __init xen_parse_mc_debug(char *arg)
 {
 	mc_debug_enabled = true;
@@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg)
 }
 early_param("xen_mc_debug", xen_parse_mc_debug);
 
-void mc_percpu_init(unsigned int cpu)
-{
-	per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
-}
-
 static int __init mc_debug_enable(void)
 {
 	unsigned long flags;
+	struct mc_debug_data __percpu *mcdb;
 
 	if (!mc_debug_enabled)
 		return 0;
 
-	mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
-	if (!mc_debug_data_ptr) {
+	mcdb = alloc_percpu(struct mc_debug_data);
+	if (!mcdb) {
 		pr_err("xen_mc_debug inactive\n");
 		static_key_slow_dec(&mc_debug);
 		return -ENOMEM;
@@ -93,7 +95,7 @@ static int __init mc_debug_enable(void)
 	/* Be careful when switching to percpu debug data. */
 	local_irq_save(flags);
 	xen_mc_flush();
-	mc_percpu_init(0);
+	mc_debug_data_ptr = mcdb;
 	local_irq_restore(flags);
 
 	pr_info("xen_mc_debug active\n");
@@ -155,7 +157,7 @@ void xen_mc_flush(void)
 	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
 
 	if (static_key_false(&mc_debug)) {
-		mcdb = __this_cpu_read(mc_debug_data);
+		mcdb = get_mc_debug();
 		memcpy(mcdb->entries, b->entries,
 		       b->mcidx * sizeof(struct multicall_entry));
 	}
@@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 	ret.mc = &b->entries[b->mcidx];
 	if (static_key_false(&mc_debug)) {
-		struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
+		struct mc_debug_data *mcdb = get_mc_debug();
 
 		mcdb->caller[b->mcidx] = __builtin_return_address(0);
 		mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index f06987b0efc3..8f89ce0b67e3 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -2,6 +2,7 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 
+#include <asm/msr.h>
 #include <asm/xen/hypercall.h>
 #include <xen/xen.h>
 #include <xen/page.h>
@@ -128,7 +129,7 @@ static inline uint32_t get_fam15h_addr(u32 addr)
 	return addr;
 }
 
-static inline bool is_amd_pmu_msr(unsigned int msr)
+static bool is_amd_pmu_msr(u32 msr)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -194,8 +195,7 @@ static bool is_intel_pmu_msr(u32 msr_index, int *type, int *index)
 	}
 }
 
-static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
-				  int index, bool is_read)
+static bool xen_intel_pmu_emulate(u32 msr, u64 *val, int type, int index, bool is_read)
 {
 	uint64_t *reg = NULL;
 	struct xen_pmu_intel_ctxt *ctxt;
@@ -257,7 +257,7 @@ static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
 	return false;
 }
 
-static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
+static bool xen_amd_pmu_emulate(u32 msr, u64 *val, bool is_read)
 {
 	uint64_t *reg = NULL;
 	int i, off = 0;
@@ -298,55 +298,20 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
 	return false;
 }
 
-static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
-				 bool *emul)
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read)
 {
 	int type, index = 0;
 
 	if (is_amd_pmu_msr(msr))
-		*emul = xen_amd_pmu_emulate(msr, val, is_read);
-	else if (is_intel_pmu_msr(msr, &type, &index))
-		*emul = xen_intel_pmu_emulate(msr, val, type, index, is_read);
-	else
-		return false;
-
-	return true;
-}
-
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
-{
-	bool emulated;
+		return xen_amd_pmu_emulate(msr, val, is_read);
 
-	if (!pmu_msr_chk_emulated(msr, val, true, &emulated))
-		return false;
+	if (is_intel_pmu_msr(msr, &type, &index))
+		return xen_intel_pmu_emulate(msr, val, type, index, is_read);
 
-	if (!emulated) {
-		*val = err ? native_read_msr_safe(msr, err)
-			   : native_read_msr(msr);
-	}
-
-	return true;
-}
-
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
-{
-	uint64_t val = ((uint64_t)high << 32) | low;
-	bool emulated;
-
-	if (!pmu_msr_chk_emulated(msr, &val, false, &emulated))
-		return false;
-
-	if (!emulated) {
-		if (err)
-			*err = native_write_msr_safe(msr, low, high);
-		else
-			native_write_msr(msr, low, high);
-	}
-
-	return true;
+	return false;
 }
 
-static unsigned long long xen_amd_read_pmc(int counter)
+static u64 xen_amd_read_pmc(int counter)
 {
 	struct xen_pmu_amd_ctxt *ctxt;
 	uint64_t *counter_regs;
@@ -354,11 +319,12 @@ static unsigned long long xen_amd_read_pmc(int counter)
 	uint8_t xenpmu_flags = get_xenpmu_flags();
 
 	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
-		uint32_t msr;
-		int err;
+		u32 msr;
+		u64 val;
 
 		msr = amd_counters_base + (counter * amd_msr_step);
-		return native_read_msr_safe(msr, &err);
+		native_read_msr_safe(msr, &val);
+		return val;
 	}
 
 	ctxt = &xenpmu_data->pmu.c.amd;
@@ -366,7 +332,7 @@ static unsigned long long xen_amd_read_pmc(int counter)
 	return counter_regs[counter];
 }
 
-static unsigned long long xen_intel_read_pmc(int counter)
+static u64 xen_intel_read_pmc(int counter)
 {
 	struct xen_pmu_intel_ctxt *ctxt;
 	uint64_t *fixed_counters;
@@ -375,15 +341,16 @@ static unsigned long long xen_intel_read_pmc(int counter)
 	uint8_t xenpmu_flags = get_xenpmu_flags();
 
 	if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
-		uint32_t msr;
-		int err;
+		u32 msr;
+		u64 val;
 
 		if (counter & (1 << INTEL_PMC_TYPE_SHIFT))
 			msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff);
 		else
 			msr = MSR_IA32_PERFCTR0 + counter;
 
-		return native_read_msr_safe(msr, &err);
+		native_read_msr_safe(msr, &val);
+		return val;
 	}
 
 	ctxt = &xenpmu_data->pmu.c.intel;
@@ -396,7 +363,7 @@ static unsigned long long xen_intel_read_pmc(int counter)
 	return arch_cntr_pair[counter].counter;
 }
 
-unsigned long long xen_read_pmc(int counter)
+u64 xen_read_pmc(int counter)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return xen_amd_read_pmc(counter);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c3db71d96c43..3823e52aef52 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -37,9 +37,6 @@
 
 #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
 
-/* Number of pages released from the initial allocation. */
-unsigned long xen_released_pages;
-
 /* Memory map would allow PCI passthrough. */
 bool xen_pv_pci_possible;
 
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6863d3da7dec..9bb8ff8bff30 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -70,7 +70,7 @@ static void cpu_bringup(void)
 		xen_enable_syscall();
 	}
 	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
+	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
@@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
 		return rc;
 
 	xen_pmu_init(cpu);
-	mc_percpu_init(cpu);
 
 	/*
 	 * Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 77a6ea1c60e4..ba2f17e64321 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -13,6 +13,7 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/fixmap.h>
+#include <asm/msr.h>
 
 #include "xen-ops.h"
 
@@ -39,7 +40,7 @@ void xen_arch_post_suspend(int cancelled)
 static void xen_vcpu_notify_restore(void *data)
 {
 	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
-		wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+		wrmsrq(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
 
 	/* Boot processor notified via generic timekeeping_resume() */
 	if (smp_processor_id() == 0)
@@ -55,9 +56,9 @@ static void xen_vcpu_notify_suspend(void *data)
 	tick_suspend_local();
 
 	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
-		rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+		rdmsrq(MSR_IA32_SPEC_CTRL, tmp);
 		this_cpu_write(spec_ctrl, tmp);
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		wrmsrq(MSR_IA32_SPEC_CTRL, 0);
 	}
 }
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index b518f36d1ca2..461bb1526502 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -51,6 +51,7 @@ SYM_FUNC_END(xen_hypercall_pv)
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
+	ENDBR
 	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
@@ -90,6 +91,7 @@ SYM_FUNC_END(check_events)
  * then enter the hypervisor to get them handled.
  */
 SYM_FUNC_START(xen_irq_enable_direct)
+	ENDBR
 	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
@@ -120,6 +122,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
+	ENDBR
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
@@ -127,6 +130,7 @@ SYM_FUNC_START(xen_save_fl_direct)
 SYM_FUNC_END(xen_save_fl_direct)
 
 SYM_FUNC_START(xen_read_cr2)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
@@ -135,6 +139,7 @@ SYM_FUNC_START(xen_read_cr2)
 SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
@@ -221,9 +226,7 @@ SYM_CODE_END(xen_early_idt_handler_array)
 	push %rax
 	mov  $__HYPERVISOR_iret, %eax
 	syscall		/* Do the IRET. */
-#ifdef CONFIG_MITIGATION_SLS
-	int3
-#endif
+	ud2		/* The SYSCALL should never return. */
 .endm
 
 SYM_CODE_START(xen_iret)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62..5dad6c51cdc3 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,16 +31,14 @@ SYM_CODE_START(startup_xen)
 
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
-	cdq
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi
@@ -133,11 +131,13 @@ SYM_FUNC_START(xen_hypercall_hvm)
 SYM_FUNC_END(xen_hypercall_hvm)
 
 SYM_FUNC_START(xen_hypercall_amd)
+	ANNOTATE_NOENDBR
 	vmmcall
 	RET
 SYM_FUNC_END(xen_hypercall_amd)
 
 SYM_FUNC_START(xen_hypercall_intel)
+	ANNOTATE_NOENDBR
 	vmcall
 	RET
 SYM_FUNC_END(xen_hypercall_intel)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 63c13a2ccf55..090349baec09 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data);
  */
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
 
-/* Do percpu data initialization for multicalls. */
-void mc_percpu_init(unsigned int cpu);
-
 extern bool is_xen_pmu;
 
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
@@ -274,10 +271,9 @@ void xen_pmu_finish(int cpu);
 static inline void xen_pmu_init(int cpu) {}
 static inline void xen_pmu_finish(int cpu) {}
 #endif
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read);
 int pmu_apic_update(uint32_t reg);
-unsigned long long xen_read_pmc(int counter);
+u64 xen_read_pmc(int counter);
 
 #ifdef CONFIG_SMP
 
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index 91c4c4cae8a7..49f50d1bd724 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -1,6 +1,5 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_USELIB=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IRQ_TIME_ACCOUNTING=y
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 934e58399c8c..7cdcc2deab3e 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -29,7 +29,7 @@
  * I/O memory mapping functions.
  */
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot);
+			   pgprot_t prot);
 #define ioremap_prot ioremap_prot
 #define iounmap iounmap
 
@@ -40,7 +40,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 		return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_BYPASS_VADDR);
 	else
 		return ioremap_prot(offset, size,
-			pgprot_val(pgprot_noncached(PAGE_KERNEL)));
+				    pgprot_noncached(PAGE_KERNEL));
 }
 #define ioremap ioremap
 
@@ -51,7 +51,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset,
 	    && offset - XCHAL_KIO_PADDR < XCHAL_KIO_SIZE)
 		return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_CACHED_VADDR);
 	else
-		return ioremap_prot(offset, size, pgprot_val(PAGE_KERNEL));
+		return ioremap_prot(offset, size, PAGE_KERNEL);
 
 }
 #define ioremap_cache ioremap_cache
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 183618090d05..223f1d452310 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -388,8 +388,7 @@ irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id)
 			struct pt_regs *regs = get_irq_regs();
 
 			perf_sample_data_init(&data, 0, last_period);
-			if (perf_event_overflow(event, &data, regs))
-				xtensa_pmu_stop(event, 0);
+			perf_event_overflow(event, &data, regs);
 		}
 
 		rc = IRQ_HANDLED;
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 37effc1b134e..f657a77314f8 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 464	common	getxattrat			sys_getxattrat
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 38092d21acf8..44c07c4e0833 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -629,15 +629,11 @@ DEFINE_SPINLOCK(die_lock);
 void __noreturn die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
-	const char *pr = "";
-
-	if (IS_ENABLED(CONFIG_PREEMPTION))
-		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
 
-	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter, pr);
+	pr_info("%s: sig: %ld [#%d]\n", str, err, ++die_counter);
 	show_regs(regs);
 	if (!user_mode(regs))
 		show_stack(NULL, (unsigned long *)regs->areg[1], KERN_INFO);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index b2587a1a7c46..cc52733a0649 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -66,59 +66,8 @@ void __init bootmem_init(void)
 	memblock_dump_all();
 }
 
-
-void __init zones_init(void)
+static void __init print_vm_layout(void)
 {
-	/* All pages are DMA-able, so we put them all in the DMA zone. */
-	unsigned long max_zone_pfn[MAX_NR_ZONES] = {
-		[ZONE_NORMAL] = max_low_pfn,
-#ifdef CONFIG_HIGHMEM
-		[ZONE_HIGHMEM] = max_pfn,
-#endif
-	};
-	free_area_init(max_zone_pfn);
-}
-
-static void __init free_highpages(void)
-{
-#ifdef CONFIG_HIGHMEM
-	unsigned long max_low = max_low_pfn;
-	phys_addr_t range_start, range_end;
-	u64 i;
-
-	/* set highmem page free */
-	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
-				&range_start, &range_end, NULL) {
-		unsigned long start = PFN_UP(range_start);
-		unsigned long end = PFN_DOWN(range_end);
-
-		/* Ignore complete lowmem entries */
-		if (end <= max_low)
-			continue;
-
-		/* Truncate partial highmem entries */
-		if (start < max_low)
-			start = max_low;
-
-		for (; start < end; start++)
-			free_highmem_page(pfn_to_page(start));
-	}
-#endif
-}
-
-/*
- * Initialize memory pages.
- */
-
-void __init mem_init(void)
-{
-	free_highpages();
-
-	max_mapnr = max_pfn - ARCH_PFN_OFFSET;
-	high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT);
-
-	memblock_free_all();
-
 	pr_info("virtual kernel memory layout:\n"
 #ifdef CONFIG_KASAN
 		"    kasan   : 0x%08lx - 0x%08lx  (%5lu MB)\n"
@@ -167,6 +116,19 @@ void __init mem_init(void)
 		(unsigned long)(__bss_stop - __bss_start) >> 10);
 }
 
+void __init zones_init(void)
+{
+	/* All pages are DMA-able, so we put them all in the DMA zone. */
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = {
+		[ZONE_NORMAL] = max_low_pfn,
+#ifdef CONFIG_HIGHMEM
+		[ZONE_HIGHMEM] = max_pfn,
+#endif
+	};
+	free_area_init(max_zone_pfn);
+	print_vm_layout();
+}
+
 static void __init parse_memmap_one(char *p)
 {
 	char *oldp;
diff --git a/arch/xtensa/mm/ioremap.c b/arch/xtensa/mm/ioremap.c
index 8ca660b7ab49..26f238fa9d0d 100644
--- a/arch/xtensa/mm/ioremap.c
+++ b/arch/xtensa/mm/ioremap.c
@@ -11,12 +11,12 @@
 #include <asm/io.h>
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot)
+			   pgprot_t prot)
 {
 	unsigned long pfn = __phys_to_pfn((phys_addr));
 	WARN_ON(pfn_valid(pfn));
 
-	return generic_ioremap_prot(phys_addr, size, __pgprot(prot));
+	return generic_ioremap_prot(phys_addr, size, prot);
 }
 EXPORT_SYMBOL(ioremap_prot);
 
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index abec44b687df..8b95221375a8 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -48,7 +48,7 @@ static int rs_open(struct tty_struct *tty, struct file * filp)
 static void rs_close(struct tty_struct *tty, struct file * filp)
 {
 	if (tty->count == 1)
-		del_timer_sync(&serial_timer);
+		timer_delete_sync(&serial_timer);
 }
 
 
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index e89f27f2bb18..c6d8c62695e1 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -375,7 +375,7 @@ static int iss_net_close(struct net_device *dev)
 	struct iss_net_private *lp = netdev_priv(dev);
 
 	netif_stop_queue(dev);
-	del_timer_sync(&lp->timer);
+	timer_delete_sync(&lp->timer);
 	lp->tp.net_ops->close(lp);
 
 	return 0;